All of lore.kernel.org
 help / color / mirror / Atom feed
From: Si-Wei Liu <si-wei.liu@oracle.com>
To: jasowang@redhat.com, mst@redhat.com, eperezma@redhat.com,
	sgarzare@redhat.com, dtatulea@nvidia.com
Cc: linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org
Subject: [PATCH v4 7/7] vdpa_sim: implement .reset_map support
Date: Sat, 21 Oct 2023 02:25:19 -0700	[thread overview]
Message-ID: <1697880319-4937-8-git-send-email-si-wei.liu@oracle.com> (raw)
In-Reply-To: <1697880319-4937-1-git-send-email-si-wei.liu@oracle.com>

In order to reduce excessive memory mapping cost in live migration and
VM reboot, it is desirable to decouple the vhost-vdpa IOTLB abstraction
from the virtio device life cycle, i.e. mappings can be kept intact
across virtio device reset. Leverage the .reset_map callback, which is
meant to destroy the iotlb on the given ASID and recreate the 1:1
passthrough/identity mapping. To be consistent, the mapping on device
creation is initiailized to passthrough/identity with PA 1:1 mapped as
IOVA. With this the device .reset op doesn't have to maintain and clean
up memory mappings by itself.

Additionally, implement .compat_reset to cater for older userspace,
which may wish to see mapping to be cleared during reset.

Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Tested-by: Stefano Garzarella <sgarzare@redhat.com>
---
 drivers/vdpa/vdpa_sim/vdpa_sim.c | 52 ++++++++++++++++++++++++++------
 1 file changed, 43 insertions(+), 9 deletions(-)

diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 76d41058add9..be2925d0d283 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -139,7 +139,7 @@ static void vdpasim_vq_reset(struct vdpasim *vdpasim,
 	vq->vring.notify = NULL;
 }
 
-static void vdpasim_do_reset(struct vdpasim *vdpasim)
+static void vdpasim_do_reset(struct vdpasim *vdpasim, u32 flags)
 {
 	int i;
 
@@ -151,11 +151,13 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim)
 				 &vdpasim->iommu_lock);
 	}
 
-	for (i = 0; i < vdpasim->dev_attr.nas; i++) {
-		vhost_iotlb_reset(&vdpasim->iommu[i]);
-		vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX,
-				      0, VHOST_MAP_RW);
-		vdpasim->iommu_pt[i] = true;
+	if (flags & VDPA_RESET_F_CLEAN_MAP) {
+		for (i = 0; i < vdpasim->dev_attr.nas; i++) {
+			vhost_iotlb_reset(&vdpasim->iommu[i]);
+			vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX,
+					      0, VHOST_MAP_RW);
+			vdpasim->iommu_pt[i] = true;
+		}
 	}
 
 	vdpasim->running = true;
@@ -259,8 +261,12 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
 	if (!vdpasim->iommu_pt)
 		goto err_iommu;
 
-	for (i = 0; i < vdpasim->dev_attr.nas; i++)
+	for (i = 0; i < vdpasim->dev_attr.nas; i++) {
 		vhost_iotlb_init(&vdpasim->iommu[i], max_iotlb_entries, 0);
+		vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX, 0,
+				      VHOST_MAP_RW);
+		vdpasim->iommu_pt[i] = true;
+	}
 
 	for (i = 0; i < dev_attr->nvqs; i++)
 		vringh_set_iotlb(&vdpasim->vqs[i].vring, &vdpasim->iommu[0],
@@ -480,18 +486,23 @@ static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status)
 	mutex_unlock(&vdpasim->mutex);
 }
 
-static int vdpasim_reset(struct vdpa_device *vdpa)
+static int vdpasim_compat_reset(struct vdpa_device *vdpa, u32 flags)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
 	mutex_lock(&vdpasim->mutex);
 	vdpasim->status = 0;
-	vdpasim_do_reset(vdpasim);
+	vdpasim_do_reset(vdpasim, flags);
 	mutex_unlock(&vdpasim->mutex);
 
 	return 0;
 }
 
+static int vdpasim_reset(struct vdpa_device *vdpa)
+{
+	return vdpasim_compat_reset(vdpa, 0);
+}
+
 static int vdpasim_suspend(struct vdpa_device *vdpa)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -637,6 +648,25 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,
 	return ret;
 }
 
+static int vdpasim_reset_map(struct vdpa_device *vdpa, unsigned int asid)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	if (asid >= vdpasim->dev_attr.nas)
+		return -EINVAL;
+
+	spin_lock(&vdpasim->iommu_lock);
+	if (vdpasim->iommu_pt[asid])
+		goto out;
+	vhost_iotlb_reset(&vdpasim->iommu[asid]);
+	vhost_iotlb_add_range(&vdpasim->iommu[asid], 0, ULONG_MAX,
+			      0, VHOST_MAP_RW);
+	vdpasim->iommu_pt[asid] = true;
+out:
+	spin_unlock(&vdpasim->iommu_lock);
+	return 0;
+}
+
 static int vdpasim_bind_mm(struct vdpa_device *vdpa, struct mm_struct *mm)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -749,6 +779,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
 	.get_status             = vdpasim_get_status,
 	.set_status             = vdpasim_set_status,
 	.reset			= vdpasim_reset,
+	.compat_reset		= vdpasim_compat_reset,
 	.suspend		= vdpasim_suspend,
 	.resume			= vdpasim_resume,
 	.get_config_size        = vdpasim_get_config_size,
@@ -759,6 +790,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
 	.set_group_asid         = vdpasim_set_group_asid,
 	.dma_map                = vdpasim_dma_map,
 	.dma_unmap              = vdpasim_dma_unmap,
+	.reset_map              = vdpasim_reset_map,
 	.bind_mm		= vdpasim_bind_mm,
 	.unbind_mm		= vdpasim_unbind_mm,
 	.free                   = vdpasim_free,
@@ -787,6 +819,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.get_status             = vdpasim_get_status,
 	.set_status             = vdpasim_set_status,
 	.reset			= vdpasim_reset,
+	.compat_reset		= vdpasim_compat_reset,
 	.suspend		= vdpasim_suspend,
 	.resume			= vdpasim_resume,
 	.get_config_size        = vdpasim_get_config_size,
@@ -796,6 +829,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.get_iova_range         = vdpasim_get_iova_range,
 	.set_group_asid         = vdpasim_set_group_asid,
 	.set_map                = vdpasim_set_map,
+	.reset_map              = vdpasim_reset_map,
 	.bind_mm		= vdpasim_bind_mm,
 	.unbind_mm		= vdpasim_unbind_mm,
 	.free                   = vdpasim_free,
-- 
2.39.3

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

WARNING: multiple messages have this Message-ID (diff)
From: Si-Wei Liu <si-wei.liu@oracle.com>
To: jasowang@redhat.com, mst@redhat.com, eperezma@redhat.com,
	sgarzare@redhat.com, dtatulea@nvidia.com
Cc: virtualization@lists.linux-foundation.org, linux-kernel@vger.kernel.org
Subject: [PATCH v4 7/7] vdpa_sim: implement .reset_map support
Date: Sat, 21 Oct 2023 02:25:19 -0700	[thread overview]
Message-ID: <1697880319-4937-8-git-send-email-si-wei.liu@oracle.com> (raw)
In-Reply-To: <1697880319-4937-1-git-send-email-si-wei.liu@oracle.com>

In order to reduce excessive memory mapping cost in live migration and
VM reboot, it is desirable to decouple the vhost-vdpa IOTLB abstraction
from the virtio device life cycle, i.e. mappings can be kept intact
across virtio device reset. Leverage the .reset_map callback, which is
meant to destroy the iotlb on the given ASID and recreate the 1:1
passthrough/identity mapping. To be consistent, the mapping on device
creation is initiailized to passthrough/identity with PA 1:1 mapped as
IOVA. With this the device .reset op doesn't have to maintain and clean
up memory mappings by itself.

Additionally, implement .compat_reset to cater for older userspace,
which may wish to see mapping to be cleared during reset.

Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Tested-by: Stefano Garzarella <sgarzare@redhat.com>
---
 drivers/vdpa/vdpa_sim/vdpa_sim.c | 52 ++++++++++++++++++++++++++------
 1 file changed, 43 insertions(+), 9 deletions(-)

diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 76d41058add9..be2925d0d283 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -139,7 +139,7 @@ static void vdpasim_vq_reset(struct vdpasim *vdpasim,
 	vq->vring.notify = NULL;
 }
 
-static void vdpasim_do_reset(struct vdpasim *vdpasim)
+static void vdpasim_do_reset(struct vdpasim *vdpasim, u32 flags)
 {
 	int i;
 
@@ -151,11 +151,13 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim)
 				 &vdpasim->iommu_lock);
 	}
 
-	for (i = 0; i < vdpasim->dev_attr.nas; i++) {
-		vhost_iotlb_reset(&vdpasim->iommu[i]);
-		vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX,
-				      0, VHOST_MAP_RW);
-		vdpasim->iommu_pt[i] = true;
+	if (flags & VDPA_RESET_F_CLEAN_MAP) {
+		for (i = 0; i < vdpasim->dev_attr.nas; i++) {
+			vhost_iotlb_reset(&vdpasim->iommu[i]);
+			vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX,
+					      0, VHOST_MAP_RW);
+			vdpasim->iommu_pt[i] = true;
+		}
 	}
 
 	vdpasim->running = true;
@@ -259,8 +261,12 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
 	if (!vdpasim->iommu_pt)
 		goto err_iommu;
 
-	for (i = 0; i < vdpasim->dev_attr.nas; i++)
+	for (i = 0; i < vdpasim->dev_attr.nas; i++) {
 		vhost_iotlb_init(&vdpasim->iommu[i], max_iotlb_entries, 0);
+		vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX, 0,
+				      VHOST_MAP_RW);
+		vdpasim->iommu_pt[i] = true;
+	}
 
 	for (i = 0; i < dev_attr->nvqs; i++)
 		vringh_set_iotlb(&vdpasim->vqs[i].vring, &vdpasim->iommu[0],
@@ -480,18 +486,23 @@ static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status)
 	mutex_unlock(&vdpasim->mutex);
 }
 
-static int vdpasim_reset(struct vdpa_device *vdpa)
+static int vdpasim_compat_reset(struct vdpa_device *vdpa, u32 flags)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
 	mutex_lock(&vdpasim->mutex);
 	vdpasim->status = 0;
-	vdpasim_do_reset(vdpasim);
+	vdpasim_do_reset(vdpasim, flags);
 	mutex_unlock(&vdpasim->mutex);
 
 	return 0;
 }
 
+static int vdpasim_reset(struct vdpa_device *vdpa)
+{
+	return vdpasim_compat_reset(vdpa, 0);
+}
+
 static int vdpasim_suspend(struct vdpa_device *vdpa)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -637,6 +648,25 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,
 	return ret;
 }
 
+static int vdpasim_reset_map(struct vdpa_device *vdpa, unsigned int asid)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	if (asid >= vdpasim->dev_attr.nas)
+		return -EINVAL;
+
+	spin_lock(&vdpasim->iommu_lock);
+	if (vdpasim->iommu_pt[asid])
+		goto out;
+	vhost_iotlb_reset(&vdpasim->iommu[asid]);
+	vhost_iotlb_add_range(&vdpasim->iommu[asid], 0, ULONG_MAX,
+			      0, VHOST_MAP_RW);
+	vdpasim->iommu_pt[asid] = true;
+out:
+	spin_unlock(&vdpasim->iommu_lock);
+	return 0;
+}
+
 static int vdpasim_bind_mm(struct vdpa_device *vdpa, struct mm_struct *mm)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -749,6 +779,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
 	.get_status             = vdpasim_get_status,
 	.set_status             = vdpasim_set_status,
 	.reset			= vdpasim_reset,
+	.compat_reset		= vdpasim_compat_reset,
 	.suspend		= vdpasim_suspend,
 	.resume			= vdpasim_resume,
 	.get_config_size        = vdpasim_get_config_size,
@@ -759,6 +790,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
 	.set_group_asid         = vdpasim_set_group_asid,
 	.dma_map                = vdpasim_dma_map,
 	.dma_unmap              = vdpasim_dma_unmap,
+	.reset_map              = vdpasim_reset_map,
 	.bind_mm		= vdpasim_bind_mm,
 	.unbind_mm		= vdpasim_unbind_mm,
 	.free                   = vdpasim_free,
@@ -787,6 +819,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.get_status             = vdpasim_get_status,
 	.set_status             = vdpasim_set_status,
 	.reset			= vdpasim_reset,
+	.compat_reset		= vdpasim_compat_reset,
 	.suspend		= vdpasim_suspend,
 	.resume			= vdpasim_resume,
 	.get_config_size        = vdpasim_get_config_size,
@@ -796,6 +829,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.get_iova_range         = vdpasim_get_iova_range,
 	.set_group_asid         = vdpasim_set_group_asid,
 	.set_map                = vdpasim_set_map,
+	.reset_map              = vdpasim_reset_map,
 	.bind_mm		= vdpasim_bind_mm,
 	.unbind_mm		= vdpasim_unbind_mm,
 	.free                   = vdpasim_free,
-- 
2.39.3


  parent reply	other threads:[~2023-10-21  9:28 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-21  9:25 [PATCH v4 0/7] vdpa: decouple reset of iotlb mapping from device reset Si-Wei Liu
2023-10-21  9:25 ` Si-Wei Liu
2023-10-21  9:25 ` [PATCH v4 1/7] vdpa: introduce .reset_map operation callback Si-Wei Liu
2023-10-21  9:25   ` Si-Wei Liu
2023-10-21  9:25 ` [PATCH v4 2/7] vhost-vdpa: reset vendor specific mapping to initial state in .release Si-Wei Liu
2023-10-21  9:25   ` Si-Wei Liu
2023-10-21  9:25 ` [PATCH v4 3/7] vhost-vdpa: introduce IOTLB_PERSIST backend feature bit Si-Wei Liu
2023-10-21  9:25   ` Si-Wei Liu
2023-10-21  9:25 ` [PATCH v4 4/7] vdpa: introduce .compat_reset operation callback Si-Wei Liu
2023-10-21  9:25   ` Si-Wei Liu
2023-10-21  9:25 ` [PATCH v4 5/7] vhost-vdpa: clean iotlb map during reset for older userspace Si-Wei Liu
2023-10-21  9:25   ` Si-Wei Liu
     [not found]   ` <8a3ec6465bc150fba804f34d456115c4f8a29c70.camel@nvidia.com>
2023-10-23 23:03     ` Si-Wei Liu
2023-10-23 23:03       ` Si-Wei Liu
2023-10-24  5:45   ` Jason Wang
2023-10-24  5:45     ` Jason Wang
2023-10-24 16:21     ` Si-Wei Liu
2023-10-24 16:21       ` Si-Wei Liu
2023-10-24 16:25       ` Si-Wei Liu
2023-10-24 16:25         ` Si-Wei Liu
2023-10-25  1:15         ` Jason Wang
2023-10-25  1:15           ` Jason Wang
2023-10-21  9:25 ` [PATCH v4 6/7] vdpa/mlx5: implement .reset_map driver op Si-Wei Liu
2023-10-21  9:25   ` Si-Wei Liu
2023-10-21  9:25 ` Si-Wei Liu [this message]
2023-10-21  9:25   ` [PATCH v4 7/7] vdpa_sim: implement .reset_map support Si-Wei Liu
2023-10-23  3:51 ` [PATCH v4 0/7] vdpa: decouple reset of iotlb mapping from device reset Jason Wang
2023-10-23  3:51   ` Jason Wang
2023-10-23 22:00   ` Si-Wei Liu
2023-10-23 22:00     ` Si-Wei Liu
2023-10-24  6:51     ` Lei Yang
2023-10-24 17:27       ` Si-Wei Liu
2023-10-24 17:27         ` Si-Wei Liu
2023-10-25  9:41         ` Lei Yang
2023-10-25 23:31           ` Si-Wei Liu
2023-10-25 23:31             ` Si-Wei Liu
2023-10-26  6:16             ` Lei Yang

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=1697880319-4937-8-git-send-email-si-wei.liu@oracle.com \
    --to=si-wei.liu@oracle.com \
    --cc=dtatulea@nvidia.com \
    --cc=eperezma@redhat.com \
    --cc=jasowang@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=sgarzare@redhat.com \
    --cc=virtualization@lists.linux-foundation.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.