From: Yi Liu <yi.l.liu@intel.com>
To: joro@8bytes.org, jgg@nvidia.com, kevin.tian@intel.com,
baolu.lu@linux.intel.com
Cc: alex.williamson@redhat.com, robin.murphy@arm.com,
eric.auger@redhat.com, nicolinc@nvidia.com, kvm@vger.kernel.org,
chao.p.peng@linux.intel.com, yi.l.liu@intel.com,
iommu@lists.linux.dev
Subject: [PATCH 2/6] iommu/vt-d: Move intel_drain_pasid_prq() into intel_pasid_tear_down_entry()
Date: Fri, 28 Jun 2024 01:55:34 -0700 [thread overview]
Message-ID: <20240628085538.47049-3-yi.l.liu@intel.com> (raw)
In-Reply-To: <20240628085538.47049-1-yi.l.liu@intel.com>
Draining PRQ is needed before repurposing a PASID. It makes sense to invoke
it in the intel_pasid_tear_down_entry().
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
---
drivers/iommu/intel/iommu.c | 5 ++---
drivers/iommu/intel/pasid.c | 9 ++++++++-
drivers/iommu/intel/pasid.h | 5 ++---
drivers/iommu/intel/svm.c | 6 +++++-
4 files changed, 17 insertions(+), 8 deletions(-)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 288c929b3d15..dd3de95c7122 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3241,7 +3241,7 @@ void device_block_translation(struct device *dev)
if (!dev_is_real_dma_subdevice(dev)) {
if (sm_supported(iommu))
intel_pasid_tear_down_entry(iommu, dev,
- IOMMU_NO_PASID, false);
+ IOMMU_NO_PASID, false, false);
else
domain_context_clear(info);
}
@@ -4060,8 +4060,7 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid,
intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
kfree(dev_pasid);
out_tear_down:
- intel_pasid_tear_down_entry(iommu, dev, pasid, false);
- intel_drain_pasid_prq(dev, pasid);
+ intel_pasid_tear_down_entry(iommu, dev, pasid, false, true);
}
static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 573e1b8e3cfb..b18eebb479de 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -233,8 +233,12 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
qi_flush_dev_iotlb_pasid(iommu, sid, pfsid, pasid, qdep, 0, 64 - VTD_PAGE_SHIFT);
}
+/*
+ * Not all PASID entry destroy requires PRQ drain as it can be handled in
+ * the remove_dev_pasid path. Caller should be clear on it.
+ */
void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
- u32 pasid, bool fault_ignore)
+ u32 pasid, bool fault_ignore, bool drain_prq)
{
struct pasid_entry *pte;
u16 did, pgtt;
@@ -264,6 +268,9 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
/* Device IOTLB doesn't need to be flushed in caching mode. */
if (!cap_caching_mode(iommu->cap))
devtlb_invalidation_with_pasid(iommu, dev, pasid);
+
+ if (drain_prq)
+ intel_drain_pasid_prq(dev, pasid);
}
/*
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index da9978fef7ac..8b77b0d21c6e 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -313,9 +313,8 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
struct device *dev, u32 pasid);
int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
u32 pasid, struct dmar_domain *domain);
-void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
- struct device *dev, u32 pasid,
- bool fault_ignore);
+void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
+ u32 pasid, bool fault_ignore, bool drain_prq);
void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
struct device *dev, u32 pasid);
int intel_pasid_setup_sm_context(struct device *dev);
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index a5845ca94867..679e094d9f52 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -175,8 +175,12 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
spin_lock_irqsave(&domain->lock, flags);
list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) {
info = dev_iommu_priv_get(dev_pasid->dev);
+ /*
+ * PRQ drain would happen in the remove_dev_pasid() path,
+ * no need to do it here.
+ */
intel_pasid_tear_down_entry(info->iommu, dev_pasid->dev,
- dev_pasid->pasid, true);
+ dev_pasid->pasid, true, false);
}
spin_unlock_irqrestore(&domain->lock, flags);
--
2.34.1
next prev parent reply other threads:[~2024-06-28 8:55 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-28 8:55 [PATCH 0/6] Make set_dev_pasid op supportting domain replacement Yi Liu
2024-06-28 8:55 ` [PATCH 1/6] iommu: Pass old domain to set_dev_pasid op Yi Liu
2024-06-28 8:55 ` Yi Liu [this message]
2024-06-28 9:42 ` [PATCH 2/6] iommu/vt-d: Move intel_drain_pasid_prq() into intel_pasid_tear_down_entry() Baolu Lu
2024-06-28 10:51 ` Yi Liu
2024-07-10 8:25 ` Tian, Kevin
2024-06-28 8:55 ` [PATCH 3/6] iommu/vt-d: Make helpers support modifying present pasid entry Yi Liu
2024-06-28 9:52 ` Baolu Lu
2024-06-28 10:56 ` Yi Liu
2024-07-15 7:53 ` Tian, Kevin
2024-07-15 8:05 ` Yi Liu
2024-06-28 8:55 ` [PATCH 4/6] iommu/vt-d: Make intel_iommu_set_dev_pasid() to handle domain replacement Yi Liu
2024-07-15 7:58 ` Tian, Kevin
2024-06-28 8:55 ` [PATCH 5/6] iommu/vt-d: Add set_dev_pasid callback for nested domain Yi Liu
2024-06-28 8:55 ` [PATCH 6/6] iommu: Make set_dev_pasid op support domain replacement Yi Liu
2024-07-15 8:02 ` Tian, Kevin
2024-07-15 8:37 ` Yi Liu
2024-07-10 8:24 ` [PATCH 0/6] Make set_dev_pasid op supportting " Tian, Kevin
2024-07-11 18:41 ` Jason Gunthorpe
2024-07-15 8:16 ` Tian, Kevin
2024-07-15 12:19 ` Jason Gunthorpe
2024-07-15 8:23 ` Yi Liu
2024-07-15 12:19 ` Jason Gunthorpe
2024-07-16 2:07 ` Yi Liu
2024-07-11 18:37 ` Jason Gunthorpe
2024-07-15 8:11 ` Yi Liu
2024-07-15 12:16 ` Jason Gunthorpe
2024-08-15 17:49 ` Vasant Hegde
2024-08-16 1:19 ` Yi Liu
2024-08-16 2:49 ` Baolu Lu
2024-08-16 5:17 ` Vasant Hegde
2024-08-16 2:52 ` Baolu Lu
2024-08-16 6:08 ` Yi Liu
2024-08-16 5:19 ` Vasant Hegde
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=20240628085538.47049-3-yi.l.liu@intel.com \
--to=yi.l.liu@intel.com \
--cc=alex.williamson@redhat.com \
--cc=baolu.lu@linux.intel.com \
--cc=chao.p.peng@linux.intel.com \
--cc=eric.auger@redhat.com \
--cc=iommu@lists.linux.dev \
--cc=jgg@nvidia.com \
--cc=joro@8bytes.org \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=nicolinc@nvidia.com \
--cc=robin.murphy@arm.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