All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nicolin Chen <nicolinc@nvidia.com>
To: <joro@8bytes.org>, <will@kernel.org>, <marcan@marcan.st>,
	<sven@svenpeter.dev>, <robin.murphy@arm.com>,
	<robdclark@gmail.com>, <baolu.lu@linux.intel.com>,
	<orsonzhai@gmail.com>, <baolin.wang7@gmail.com>,
	<zhang.lyra@gmail.com>, <jean-philippe@linaro.org>,
	<alex.williamson@redhat.com>, <jgg@nvidia.com>,
	<kevin.tian@intel.com>
Cc: <suravee.suthikulpanit@amd.com>, <alyssa@rosenzweig.io>,
	<dwmw2@infradead.org>, <mjrosato@linux.ibm.com>,
	<gerald.schaefer@linux.ibm.com>, <thierry.reding@gmail.com>,
	<vdumpa@nvidia.com>, <jonathanh@nvidia.com>, <cohuck@redhat.com>,
	<thunder.leizhen@huawei.com>, <christophe.jaillet@wanadoo.fr>,
	<chenxiang66@hisilicon.com>, <john.garry@huawei.com>,
	<yangyingliang@huawei.com>, <iommu@lists.linux-foundation.org>,
	<iommu@lists.linux.dev>, <linux-kernel@vger.kernel.org>,
	<linux-arm-kernel@lists.infradead.org>,
	<linux-arm-msm@vger.kernel.org>, <linux-s390@vger.kernel.org>,
	<linux-tegra@vger.kernel.org>,
	<virtualization@lists.linux-foundation.org>,
	<kvm@vger.kernel.org>
Subject: [PATCH v4 2/5] vfio/iommu_type1: Prefer to reuse domains vs match enforced cache coherency
Date: Thu, 30 Jun 2022 13:36:32 -0700	[thread overview]
Message-ID: <20220630203635.33200-3-nicolinc@nvidia.com> (raw)
In-Reply-To: <20220630203635.33200-1-nicolinc@nvidia.com>

From: Jason Gunthorpe <jgg@nvidia.com>

The KVM mechanism for controlling wbinvd is based on OR of the coherency
property of all devices attached to a guest, no matter whether those
devices are attached to a single domain or multiple domains.

On the other hand, the benefit to using separate domains was that those
devices attached to domains supporting enforced cache coherency always
mapped with the attributes necessary to provide that feature, therefore
if a non-enforced domain was dropped, the associated group removal would
re-trigger an evaluation by KVM.

In practice however, the only known cases of such mixed domains included
an Intel IGD device behind an IOMMU lacking snoop control, where such
devices do not support hotplug, therefore this scenario lacks testing and
is not considered sufficiently relevant to support.

After all, KVM won't take advantage of trying to push a device that could
do enforced cache coherency to a dedicated domain vs re-using an existing
domain, which is non-coherent.

Simplify this code and eliminate the test. This removes the only logic
that needed to have a dummy domain attached prior to searching for a
matching domain and simplifies the next patches.

It's unclear whether we want to further optimize the Intel driver to
update the domain coherency after a device is detached from it, at
least not before KVM can be verified to handle such dynamics in related
emulation paths (wbinvd, vcpu load, write_cr0, ept, etc.). In reality
we don't see an usage requiring such optimization as the only device
which imposes such non-coherency is Intel GPU which even doesn't
support hotplug/hot remove.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
---
 drivers/vfio/vfio_iommu_type1.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index c13b9290e357..f4e3b423a453 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2285,9 +2285,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	 * testing if they're on the same bus_type.
 	 */
 	list_for_each_entry(d, &iommu->domain_list, next) {
-		if (d->domain->ops == domain->domain->ops &&
-		    d->enforce_cache_coherency ==
-			    domain->enforce_cache_coherency) {
+		if (d->domain->ops == domain->domain->ops) {
 			iommu_detach_group(domain->domain, group->iommu_group);
 			if (!iommu_attach_group(d->domain,
 						group->iommu_group)) {
-- 
2.17.1


WARNING: multiple messages have this Message-ID (diff)
From: Nicolin Chen via iommu <iommu@lists.linux-foundation.org>
To: <joro@8bytes.org>, <will@kernel.org>, <marcan@marcan.st>,
	<sven@svenpeter.dev>, <robin.murphy@arm.com>,
	<robdclark@gmail.com>, <baolu.lu@linux.intel.com>,
	<orsonzhai@gmail.com>, <baolin.wang7@gmail.com>,
	<zhang.lyra@gmail.com>, <jean-philippe@linaro.org>,
	<alex.williamson@redhat.com>, <jgg@nvidia.com>,
	<kevin.tian@intel.com>
Cc: virtualization@lists.linux-foundation.org,
	thierry.reding@gmail.com, alyssa@rosenzweig.io,
	linux-s390@vger.kernel.org, kvm@vger.kernel.org,
	jonathanh@nvidia.com, iommu@lists.linux.dev,
	yangyingliang@huawei.com, gerald.schaefer@linux.ibm.com,
	linux-arm-msm@vger.kernel.org, christophe.jaillet@wanadoo.fr,
	linux-tegra@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org, cohuck@redhat.com,
	linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org,
	dwmw2@infradead.org
Subject: [PATCH v4 2/5] vfio/iommu_type1: Prefer to reuse domains vs match enforced cache coherency
Date: Thu, 30 Jun 2022 13:36:32 -0700	[thread overview]
Message-ID: <20220630203635.33200-3-nicolinc@nvidia.com> (raw)
In-Reply-To: <20220630203635.33200-1-nicolinc@nvidia.com>

From: Jason Gunthorpe <jgg@nvidia.com>

The KVM mechanism for controlling wbinvd is based on OR of the coherency
property of all devices attached to a guest, no matter whether those
devices are attached to a single domain or multiple domains.

On the other hand, the benefit to using separate domains was that those
devices attached to domains supporting enforced cache coherency always
mapped with the attributes necessary to provide that feature, therefore
if a non-enforced domain was dropped, the associated group removal would
re-trigger an evaluation by KVM.

In practice however, the only known cases of such mixed domains included
an Intel IGD device behind an IOMMU lacking snoop control, where such
devices do not support hotplug, therefore this scenario lacks testing and
is not considered sufficiently relevant to support.

After all, KVM won't take advantage of trying to push a device that could
do enforced cache coherency to a dedicated domain vs re-using an existing
domain, which is non-coherent.

Simplify this code and eliminate the test. This removes the only logic
that needed to have a dummy domain attached prior to searching for a
matching domain and simplifies the next patches.

It's unclear whether we want to further optimize the Intel driver to
update the domain coherency after a device is detached from it, at
least not before KVM can be verified to handle such dynamics in related
emulation paths (wbinvd, vcpu load, write_cr0, ept, etc.). In reality
we don't see an usage requiring such optimization as the only device
which imposes such non-coherency is Intel GPU which even doesn't
support hotplug/hot remove.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
---
 drivers/vfio/vfio_iommu_type1.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index c13b9290e357..f4e3b423a453 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2285,9 +2285,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	 * testing if they're on the same bus_type.
 	 */
 	list_for_each_entry(d, &iommu->domain_list, next) {
-		if (d->domain->ops == domain->domain->ops &&
-		    d->enforce_cache_coherency ==
-			    domain->enforce_cache_coherency) {
+		if (d->domain->ops == domain->domain->ops) {
 			iommu_detach_group(domain->domain, group->iommu_group);
 			if (!iommu_attach_group(d->domain,
 						group->iommu_group)) {
-- 
2.17.1

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

WARNING: multiple messages have this Message-ID (diff)
From: Nicolin Chen <nicolinc@nvidia.com>
To: <joro@8bytes.org>, <will@kernel.org>, <marcan@marcan.st>,
	<sven@svenpeter.dev>, <robin.murphy@arm.com>,
	<robdclark@gmail.com>, <baolu.lu@linux.intel.com>,
	<orsonzhai@gmail.com>, <baolin.wang7@gmail.com>,
	<zhang.lyra@gmail.com>, <jean-philippe@linaro.org>,
	<alex.williamson@redhat.com>, <jgg@nvidia.com>,
	<kevin.tian@intel.com>
Cc: mjrosato@linux.ibm.com,
	virtualization@lists.linux-foundation.org,
	thierry.reding@gmail.com, alyssa@rosenzweig.io,
	linux-s390@vger.kernel.org, kvm@vger.kernel.org,
	jonathanh@nvidia.com, iommu@lists.linux.dev,
	yangyingliang@huawei.com, gerald.schaefer@linux.ibm.com,
	linux-arm-msm@vger.kernel.org, john.garry@huawei.com,
	christophe.jaillet@wanadoo.fr, thunder.leizhen@huawei.com,
	linux-tegra@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org, chenxiang66@hisilicon.com,
	cohuck@redhat.com, linux-kernel@vger.kernel.org,
	iommu@lists.linux-foundation.org, suravee.suthikulpanit@amd.com,
	dwmw2@infradead.org
Subject: [PATCH v4 2/5] vfio/iommu_type1: Prefer to reuse domains vs match enforced cache coherency
Date: Thu, 30 Jun 2022 13:36:32 -0700	[thread overview]
Message-ID: <20220630203635.33200-3-nicolinc@nvidia.com> (raw)
In-Reply-To: <20220630203635.33200-1-nicolinc@nvidia.com>

From: Jason Gunthorpe <jgg@nvidia.com>

The KVM mechanism for controlling wbinvd is based on OR of the coherency
property of all devices attached to a guest, no matter whether those
devices are attached to a single domain or multiple domains.

On the other hand, the benefit to using separate domains was that those
devices attached to domains supporting enforced cache coherency always
mapped with the attributes necessary to provide that feature, therefore
if a non-enforced domain was dropped, the associated group removal would
re-trigger an evaluation by KVM.

In practice however, the only known cases of such mixed domains included
an Intel IGD device behind an IOMMU lacking snoop control, where such
devices do not support hotplug, therefore this scenario lacks testing and
is not considered sufficiently relevant to support.

After all, KVM won't take advantage of trying to push a device that could
do enforced cache coherency to a dedicated domain vs re-using an existing
domain, which is non-coherent.

Simplify this code and eliminate the test. This removes the only logic
that needed to have a dummy domain attached prior to searching for a
matching domain and simplifies the next patches.

It's unclear whether we want to further optimize the Intel driver to
update the domain coherency after a device is detached from it, at
least not before KVM can be verified to handle such dynamics in related
emulation paths (wbinvd, vcpu load, write_cr0, ept, etc.). In reality
we don't see an usage requiring such optimization as the only device
which imposes such non-coherency is Intel GPU which even doesn't
support hotplug/hot remove.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
---
 drivers/vfio/vfio_iommu_type1.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index c13b9290e357..f4e3b423a453 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2285,9 +2285,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	 * testing if they're on the same bus_type.
 	 */
 	list_for_each_entry(d, &iommu->domain_list, next) {
-		if (d->domain->ops == domain->domain->ops &&
-		    d->enforce_cache_coherency ==
-			    domain->enforce_cache_coherency) {
+		if (d->domain->ops == domain->domain->ops) {
 			iommu_detach_group(domain->domain, group->iommu_group);
 			if (!iommu_attach_group(d->domain,
 						group->iommu_group)) {
-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply	other threads:[~2022-06-30 20:37 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-30 20:36 [PATCH v4 0/5] Simplify vfio_iommu_type1 attach/detach routine Nicolin Chen
2022-06-30 20:36 ` Nicolin Chen
2022-06-30 20:36 ` Nicolin Chen via iommu
2022-06-30 20:36 ` [PATCH v4 1/5] iommu: Return -EMEDIUMTYPE for incompatible domain and device/group Nicolin Chen
2022-06-30 20:36   ` Nicolin Chen
2022-06-30 20:36   ` Nicolin Chen via iommu
2022-07-01  6:53   ` Baolu Lu
2022-07-01  6:53     ` Baolu Lu
2022-07-01  6:53     ` Baolu Lu
2022-07-01 10:21   ` Robin Murphy
2022-07-01 10:21     ` Robin Murphy
2022-07-01 10:21     ` Robin Murphy
2022-07-01 10:21     ` Robin Murphy
2022-07-01 16:43     ` Nicolin Chen
2022-07-01 16:43       ` Nicolin Chen
2022-07-01 16:43       ` Nicolin Chen via iommu
2022-07-01 18:17       ` Robin Murphy
2022-07-01 18:17         ` Robin Murphy
2022-07-01 18:17         ` Robin Murphy
2022-07-01 18:17         ` Robin Murphy
2022-07-01 19:08         ` Nicolin Chen
2022-07-01 19:08           ` Nicolin Chen
2022-07-01 19:08           ` Nicolin Chen via iommu
2022-06-30 20:36 ` Nicolin Chen [this message]
2022-06-30 20:36   ` [PATCH v4 2/5] vfio/iommu_type1: Prefer to reuse domains vs match enforced cache coherency Nicolin Chen
2022-06-30 20:36   ` Nicolin Chen via iommu
2022-06-30 20:36 ` [PATCH v4 3/5] vfio/iommu_type1: Remove the domain->ops comparison Nicolin Chen
2022-06-30 20:36   ` Nicolin Chen
2022-06-30 20:36   ` Nicolin Chen via iommu
2022-06-30 20:36 ` [PATCH v4 4/5] vfio/iommu_type1: Clean up update_dirty_scope in detach_group() Nicolin Chen
2022-06-30 20:36   ` Nicolin Chen
2022-06-30 20:36   ` Nicolin Chen via iommu
2022-06-30 20:36 ` [PATCH v4 5/5] vfio/iommu_type1: Simplify group attachment Nicolin Chen
2022-06-30 20:36   ` Nicolin Chen
2022-06-30 20:36   ` Nicolin Chen via iommu

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=20220630203635.33200-3-nicolinc@nvidia.com \
    --to=nicolinc@nvidia.com \
    --cc=alex.williamson@redhat.com \
    --cc=alyssa@rosenzweig.io \
    --cc=baolin.wang7@gmail.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=chenxiang66@hisilicon.com \
    --cc=christophe.jaillet@wanadoo.fr \
    --cc=cohuck@redhat.com \
    --cc=dwmw2@infradead.org \
    --cc=gerald.schaefer@linux.ibm.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=iommu@lists.linux.dev \
    --cc=jean-philippe@linaro.org \
    --cc=jgg@nvidia.com \
    --cc=john.garry@huawei.com \
    --cc=jonathanh@nvidia.com \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-arm-msm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=linux-tegra@vger.kernel.org \
    --cc=marcan@marcan.st \
    --cc=mjrosato@linux.ibm.com \
    --cc=orsonzhai@gmail.com \
    --cc=robdclark@gmail.com \
    --cc=robin.murphy@arm.com \
    --cc=suravee.suthikulpanit@amd.com \
    --cc=sven@svenpeter.dev \
    --cc=thierry.reding@gmail.com \
    --cc=thunder.leizhen@huawei.com \
    --cc=vdumpa@nvidia.com \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=will@kernel.org \
    --cc=yangyingliang@huawei.com \
    --cc=zhang.lyra@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 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.