public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Lu Baolu <baolu.lu@linux.intel.com>
To: Joerg Roedel <joro@8bytes.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>,
	Kevin Tian <kevin.tian@intel.com>, Yi Liu <yi.l.liu@intel.com>,
	iommu@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: [PATCH 02/13] iommu/vt-d: Add a helper to flush cache for updating present pasid entry
Date: Fri,  8 Nov 2024 10:13:53 +0800	[thread overview]
Message-ID: <20241108021406.173972-3-baolu.lu@linux.intel.com> (raw)
In-Reply-To: <20241108021406.173972-1-baolu.lu@linux.intel.com>

From: Yi Liu <yi.l.liu@intel.com>

Generalize the logic for flushing pasid-related cache upon changes to
bits other than SSADE and P which requires a different flow according
to VT-d spec.

No functional change is intended.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20241107122234.7424-3-yi.l.liu@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/pasid.c | 52 ++++++++++++++++++++++++-------------
 1 file changed, 34 insertions(+), 18 deletions(-)

diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 31665fb62e1c..8d11701c2e76 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -287,6 +287,39 @@ static void pasid_flush_caches(struct intel_iommu *iommu,
 	}
 }
 
+/*
+ * This function is supposed to be used after caller updates the fields
+ * except for the SSADE and P bit of a pasid table entry. It does the
+ * below:
+ * - Flush cacheline if needed
+ * - Flush the caches per Table 28 ”Guidance to Software for Invalidations“
+ *   of VT-d spec 5.0.
+ */
+static void intel_pasid_flush_present(struct intel_iommu *iommu,
+				      struct device *dev,
+				      u32 pasid, u16 did,
+				      struct pasid_entry *pte)
+{
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	/*
+	 * VT-d spec 5.0 table28 states guides for cache invalidation:
+	 *
+	 * - PASID-selective-within-Domain PASID-cache invalidation
+	 * - PASID-selective PASID-based IOTLB invalidation
+	 * - If (pasid is RID_PASID)
+	 *    - Global Device-TLB invalidation to affected functions
+	 *   Else
+	 *    - PASID-based Device-TLB invalidation (with S=1 and
+	 *      Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions
+	 */
+	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+	qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
+
+	devtlb_invalidation_with_pasid(iommu, dev, pasid);
+}
+
 /*
  * Set up the scalable mode pasid table entry for first only
  * translation type.
@@ -526,24 +559,7 @@ void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
 	did = pasid_get_domain_id(pte);
 	spin_unlock(&iommu->lock);
 
-	if (!ecap_coherent(iommu->ecap))
-		clflush_cache_range(pte, sizeof(*pte));
-
-	/*
-	 * VT-d spec 3.4 table23 states guides for cache invalidation:
-	 *
-	 * - PASID-selective-within-Domain PASID-cache invalidation
-	 * - PASID-selective PASID-based IOTLB invalidation
-	 * - If (pasid is RID_PASID)
-	 *    - Global Device-TLB invalidation to affected functions
-	 *   Else
-	 *    - PASID-based Device-TLB invalidation (with S=1 and
-	 *      Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions
-	 */
-	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
-	qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
-
-	devtlb_invalidation_with_pasid(iommu, dev, pasid);
+	intel_pasid_flush_present(iommu, dev, pasid, did, pte);
 }
 
 /**
-- 
2.43.0


  parent reply	other threads:[~2024-11-08  2:15 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-08  2:13 [PATCH 00/13] [PULL REQUEST] Intel IOMMU updates for v6.13 (2nd Lu Baolu
2024-11-08  2:13 ` [PATCH 01/13] iommu: Pass old domain to set_dev_pasid op Lu Baolu
2024-11-08  2:13 ` Lu Baolu [this message]
2024-11-08  2:13 ` [PATCH 03/13] iommu/vt-d: Refactor the pasid setup helpers Lu Baolu
2024-11-08  2:13 ` [PATCH 04/13] iommu/vt-d: Add pasid replace helpers Lu Baolu
2024-11-08  2:13 ` [PATCH 05/13] iommu/vt-d: Consolidate the struct dev_pasid_info add/remove Lu Baolu
2024-11-08  2:13 ` [PATCH 06/13] iommu/vt-d: Add iommu_domain_did() to get did Lu Baolu
2024-11-08  2:13 ` [PATCH 07/13] iommu/vt-d: Make intel_iommu_set_dev_pasid() to handle domain replacement Lu Baolu
2024-11-08  2:13 ` [PATCH 08/13] iommu/vt-d: Limit intel_iommu_set_dev_pasid() for paging domain Lu Baolu
2024-11-08  2:14 ` [PATCH 09/13] iommu/vt-d: Make intel_svm_set_dev_pasid() support domain replacement Lu Baolu
2024-11-08  2:14 ` [PATCH 10/13] iommu/vt-d: Make identity_domain_set_dev_pasid() to handle " Lu Baolu
2024-11-08  2:14 ` [PATCH 11/13] iommu/vt-d: Add set_dev_pasid callback for nested domain Lu Baolu
2024-11-08  2:14 ` [PATCH 12/13] iommu/arm-smmu-v3: Make set_dev_pasid() op support replace Lu Baolu
2024-11-08  2:14 ` [PATCH 13/13] iommu: Make set_dev_pasid op support domain replacement Lu Baolu
2024-11-08 13:05 ` [PATCH 00/13] [PULL REQUEST] Intel IOMMU updates for v6.13 (2nd Joerg Roedel

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=20241108021406.173972-3-baolu.lu@linux.intel.com \
    --to=baolu.lu@linux.intel.com \
    --cc=iommu@lists.linux.dev \
    --cc=jgg@nvidia.com \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=yi.l.liu@intel.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