Skip to contentSkip to conversation

Consolidate domain cache invalidation

PATCH Superseded Lu Baolu 4 participants 24 messages Apr 10, 2024 – Apr 15, 2024

Subsystems (2)

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore

Lu Baolu

author maintainer
#0 lore raw

v2 cover Consolidate domain cache invalidation

The IOMMU hardware cache needs to be invalidated whenever the mappings in the domain are changed. Currently, domain cache invalidation is scattered across different places, causing several issues:

- IOMMU IOTLB Invalidation: This is done by iterating through the domain IDs of each domain using the following code:

        xa_for_each(&dmar_domain->iommu_array, i, info)
                iommu_flush_iotlb_psi(info->iommu, dmar_domain,
                                      start_pfn, nrpages,
                                      list_empty(&gather->freelist), 0);

This code could theoretically cause a use-after-free problem because there's no lock to protect the "info" pointer within the loop.

- Inconsistent Invalidation Methods: Different domain types implement their own cache invalidation methods, making the code difficult to maintain. For example, the DMA domain, SVA domain, and nested domain have similar cache invalidation code scattered across different files.

- SVA Domain Inconsistency: The SVA domain implementation uses a completely different data structure to track attached devices compared to other domains. This creates unnecessary differences and, even worse, leads to duplicate IOTLB invalidation when an SVA domain is attached to devices belonging to a same IOMMU.

- Nested Domain Dependency: The special overlap between a nested domain and its parent domain requires a dedicated parent_domain_flush() helper function to be called everywhere the parent domain's mapping changes.

- Limited Debugging Support: There are currently no debugging aids available for domain cache invalidation.

By consolidating domain cache invalidation into a common location, we can address the issues mentioned above and improve the code's maintainability and debuggability.

The series and related patches are available on GitHub:
https://github.com/LuBaolu/intel-iommu/commits/iommu-vtd-cache-tag-v2

Change log:

v2:
- Allow cache tags of parent_type to be reusable.
- Save the the iommu device pointer to @dev of IOTLB tag type to make it present the location of the TLB explicitly.
- Rename cache_tag_flush_cm_range() to cache_tag_flush_range_pt() to make it clear that cache_tag_flush_range_pt() is called for PTEs changes from non-present to present.
- Split out a patch series to clean up all inconsistent devtlb invalidation policies for caching mode.
https://lore.kernel.org/linux-iommu/[email protected]/
- Fix a bug in intel_nested_cache_invalidate_user() where the @nrpages is misused as @end.
- Various mics refinements and adjustments.

v1: https://lore.kernel.org/linux-iommu/[email protected]/

Jason Gunthorpe (1):
iommu: Add ops->domain_alloc_sva()

Lu Baolu (11):
iommu/vt-d: Add cache tag assignment interface iommu/vt-d: Add cache tag invalidation helpers iommu/vt-d: Add trace events for cache tag interface iommu/vt-d: Use cache_tag_flush_all() in flush_iotlb_all iommu/vt-d: Use cache_tag_flush_range() in tlb_sync iommu/vt-d: Use cache_tag_flush_range_np() in iotlb_sync_map iommu/vt-d: Cleanup use of iommu_flush_iotlb_psi() iommu/vt-d: Use cache_tag_flush_range() in cache_invalidate_user iommu/vt-d: Use cache helpers in arch_invalidate_secondary_tlbs iommu/vt-d: Retire intel_svm_dev
iommu/vt-d: Retire struct intel_svm

 include/linux/iommu.h        |   3 +
 drivers/iommu/intel/iommu.h  |  79 ++++---
 drivers/iommu/intel/trace.h  |  97 +++++++++
 drivers/iommu/intel/cache.c  | 401 +++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/iommu.c  | 296 ++++----------------------
 drivers/iommu/intel/nested.c |  71 ++-----
 drivers/iommu/intel/svm.c    | 279 +++++-------------------
 drivers/iommu/iommu-sva.c    |  16 +-
 drivers/iommu/intel/Makefile |   2 +-
 9 files changed, 685 insertions(+), 559 deletions(-)
 create mode 100644 drivers/iommu/intel/cache.c
Signature · 1 line
2.34.1
author maintainer
#1 lore raw

PATCH v2 1/12 iommu/vt-d: Add cache tag assignment interface

Caching tag is a combination of tags used by the hardware to cache various translations. Whenever a mapping in a domain is changed, the IOMMU driver should invalidate the caches with the caching tags. The VT-d specification describes caching tags in section 6.2.1, Tagging of Cached Translations.

Add interface to assign caching tags to an IOMMU domain when attached to a RID or PASID, and unassign caching tags when a domain is detached from a RID or PASID. All caching tags are listed in the per-domain tag list and are protected by a dedicated lock.

In addition to the basic IOTLB and devTLB caching tag types, PARENT_IOTLB and PARENT_DEVTLB tag types are also introduced. These tags are used for caches that store translations for DMA accesses through a nested user domain. They are affected by changes to mappings in the parent domain.

---
 drivers/iommu/intel/iommu.h  |  25 +++++
 drivers/iommu/intel/cache.c  | 196 +++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/iommu.c  |  31 +++++-
 drivers/iommu/intel/nested.c |  21 +++-
 drivers/iommu/intel/svm.c    |  12 ++-
 drivers/iommu/intel/Makefile |   2 +-
 6 files changed, 278 insertions(+), 9 deletions(-)
 create mode 100644 drivers/iommu/intel/cache.c
drivers/iommu/intel/iommu.h +25 -0
index 404d2476a877..6f6bffc60852 100644
@@ -607,6 +607,9 @@ struct dmar_domain {
 	struct list_head devices;	/* all devices' list */
 	struct list_head dev_pasids;	/* all attached pasids */
 
+	spinlock_t cache_lock;		/* Protect the cache tag list */
+	struct list_head cache_tags;	/* Cache tag list */
+
 	int		iommu_superpage;/* Level of superpages supported:
 					   0 == 4KiB (no superpages), 1 == 2MiB,
 					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
@@ -1092,6 +1095,28 @@ struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 					       const struct iommu_user_data *user_data);
 struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid);
 
+enum cache_tag_type {
+	CACHE_TAG_IOTLB,
+	CACHE_TAG_DEVTLB,
+	CACHE_TAG_PARENT_IOTLB,
+	CACHE_TAG_PARENT_DEVTLB,
+};
+
+struct cache_tag {
+	struct list_head node;
+	enum cache_tag_type type;
+	struct intel_iommu *iommu;
+	struct device *dev;
+	u16 domain_id;
+	ioasid_t pasid;
+	int users;
+};
+
+int cache_tag_assign_domain(struct dmar_domain *domain, u16 did,
+			    struct device *dev, ioasid_t pasid);
+void cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,
+			       struct device *dev, ioasid_t pasid);
+
 #ifdef CONFIG_INTEL_IOMMU_SVM
 void intel_svm_check(struct intel_iommu *iommu);
 int intel_svm_enable_prq(struct intel_iommu *iommu);
drivers/iommu/intel/cache.c new file +196 -0

196 lines not on this page · raw message

drivers/iommu/intel/iommu.c +29 -2
index 681789b1258d..17b8ce4b9154 100644
@@ -1745,7 +1745,9 @@ static struct dmar_domain *alloc_domain(unsigned int type)
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
 	INIT_LIST_HEAD(&domain->dev_pasids);
+	INIT_LIST_HEAD(&domain->cache_tags);
 	spin_lock_init(&domain->lock);
+	spin_lock_init(&domain->cache_lock);
 	xa_init(&domain->iommu_array);
 
 	return domain;
@@ -2317,11 +2319,20 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
+	u16 did;
 	int ret;
 
 	ret = domain_attach_iommu(domain, iommu);
 	if (ret)
 		return ret;
+
+	did = domain_id_iommu(domain, iommu);
+	ret = cache_tag_assign_domain(domain, did, dev, IOMMU_NO_PASID);
+	if (ret) {
+		domain_detach_iommu(domain, iommu);
+		return ret;
+	}
+
 	info->domain = domain;
 	spin_lock_irqsave(&domain->lock, flags);
 	list_add(&info->link, &domain->devices);
@@ -3793,6 +3804,7 @@ void device_block_translation(struct device *dev)
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
+	u16 did;
 
 	iommu_disable_pci_caps(info);
 	if (!dev_is_real_dma_subdevice(dev)) {
@@ -3810,6 +3822,8 @@ void device_block_translation(struct device *dev)
 	list_del(&info->link);
 	spin_unlock_irqrestore(&info->domain->lock, flags);
 
+	did = domain_id_iommu(info->domain, iommu);
+	cache_tag_unassign_domain(info->domain, did, dev, IOMMU_NO_PASID);
 	domain_detach_iommu(info->domain, iommu);
 	info->domain = NULL;
 }
@@ -4590,10 +4604,12 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
 	unsigned long flags;
+	u16 did;
 
 	domain = iommu_get_domain_for_dev_pasid(dev, pasid, 0);
 	if (WARN_ON_ONCE(!domain))
 		goto out_tear_down;
+	dmar_domain = to_dmar_domain(domain);
 
 	/*
 	 * The SVA implementation needs to handle its own stuffs like the mm
@@ -4602,10 +4618,11 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 	 */
 	if (domain->type == IOMMU_DOMAIN_SVA) {
 		intel_svm_remove_dev_pasid(dev, pasid);
+		cache_tag_unassign_domain(dmar_domain,
+					  FLPT_DEFAULT_DID, dev, pasid);
 		goto out_tear_down;
 	}
 
-	dmar_domain = to_dmar_domain(domain);
 	spin_lock_irqsave(&dmar_domain->lock, flags);
 	list_for_each_entry(curr, &dmar_domain->dev_pasids, link_domain) {
 		if (curr->dev == dev && curr->pasid == pasid) {
@@ -4617,6 +4634,8 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 	WARN_ON_ONCE(!dev_pasid);
 	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
+	did = domain_id_iommu(dmar_domain, iommu);
+	cache_tag_unassign_domain(dmar_domain, did, dev, pasid);
 	domain_detach_iommu(dmar_domain, iommu);
 	intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
 	kfree(dev_pasid);
@@ -4633,6 +4652,7 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 	struct intel_iommu *iommu = info->iommu;
 	struct dev_pasid_info *dev_pasid;
 	unsigned long flags;
+	u16 did;
 	int ret;
 
 	if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev))
@@ -4656,6 +4676,11 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 	if (ret)
 		goto out_free;
 
+	did = domain_id_iommu(dmar_domain, iommu);
+	ret = cache_tag_assign_domain(dmar_domain, did, dev, pasid);
+	if (ret)
+		goto out_detach_iommu;
+
 	if (domain_type_is_si(dmar_domain))
 		ret = intel_pasid_setup_pass_through(iommu, dev, pasid);
 	else if (dmar_domain->use_first_level)
@@ -4665,7 +4690,7 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 		ret = intel_pasid_setup_second_level(iommu, dmar_domain,
 						     dev, pasid);
 	if (ret)
-		goto out_detach_iommu;
+		goto out_unassign_tag;
 
 	dev_pasid->dev = dev;
 	dev_pasid->pasid = pasid;
@@ -4677,6 +4702,8 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 		intel_iommu_debugfs_create_dev_pasid(dev_pasid);
 
 	return 0;
+out_unassign_tag:
+	cache_tag_unassign_domain(dmar_domain, did, dev, pasid);
 out_detach_iommu:
 	domain_detach_iommu(dmar_domain, iommu);
 out_free:
drivers/iommu/intel/nested.c +16 -5
index a7d68f3d518a..85c744099558 100644
@@ -26,6 +26,7 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
 	int ret = 0;
+	u16 did;
 
 	if (info->domain)
 		device_block_translation(dev);
@@ -52,13 +53,15 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 		return ret;
 	}
 
+	did = domain_id_iommu(dmar_domain, iommu);
+	ret = cache_tag_assign_domain(dmar_domain, did, dev, IOMMU_NO_PASID);
+	if (ret)
+		goto detach_iommu;
+
 	ret = intel_pasid_setup_nested(iommu, dev,
 				       IOMMU_NO_PASID, dmar_domain);
-	if (ret) {
-		domain_detach_iommu(dmar_domain, iommu);
-		dev_err_ratelimited(dev, "Failed to setup pasid entry\n");
-		return ret;
-	}
+	if (ret)
+		goto unassign_tag;
 
 	info->domain = dmar_domain;
 	spin_lock_irqsave(&dmar_domain->lock, flags);
@@ -68,6 +71,12 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 	domain_update_iotlb(dmar_domain);
 
 	return 0;
+unassign_tag:
+	cache_tag_unassign_domain(dmar_domain, did, dev, IOMMU_NO_PASID);
+detach_iommu:
+	domain_detach_iommu(dmar_domain, iommu);
+
+	return ret;
 }
 
 static void intel_nested_domain_free(struct iommu_domain *domain)
@@ -206,7 +215,9 @@ struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 	domain->domain.type = IOMMU_DOMAIN_NESTED;
 	INIT_LIST_HEAD(&domain->devices);
 	INIT_LIST_HEAD(&domain->dev_pasids);
+	INIT_LIST_HEAD(&domain->cache_tags);
 	spin_lock_init(&domain->lock);
+	spin_lock_init(&domain->cache_lock);
 	xa_init(&domain->iommu_array);
 
 	spin_lock(&s2_domain->s1_lock);
drivers/iommu/intel/svm.c +11 -1
index c1bed89b1026..d706226e84ee 100644
@@ -366,17 +366,25 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 			sdev->qdep = 0;
 	}
 
+	ret = cache_tag_assign_domain(to_dmar_domain(domain),
+				      FLPT_DEFAULT_DID, dev, pasid);
+	if (ret)
+		goto free_sdev;
+
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
 	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, pasid,
 					    FLPT_DEFAULT_DID, sflags);
 	if (ret)
-		goto free_sdev;
+		goto unassign_tag;
 
 	list_add_rcu(&sdev->list, &svm->devs);
 
 	return 0;
 
+unassign_tag:
+	cache_tag_unassign_domain(to_dmar_domain(domain),
+				  FLPT_DEFAULT_DID, dev, pasid);
 free_sdev:
 	kfree(sdev);
 free_svm:
@@ -795,6 +803,8 @@ struct iommu_domain *intel_svm_domain_alloc(void)
 	if (!domain)
 		return NULL;
 	domain->domain.ops = &intel_svm_domain_ops;
+	INIT_LIST_HEAD(&domain->cache_tags);
+	spin_lock_init(&domain->cache_lock);
 
 	return &domain->domain;
 }
drivers/iommu/intel/Makefile +1 -1
index 5402b699a122..c8beb0281559 100644
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
-obj-$(CONFIG_INTEL_IOMMU) += iommu.o pasid.o nested.o
+obj-$(CONFIG_INTEL_IOMMU) += iommu.o pasid.o nested.o cache.o
 obj-$(CONFIG_DMAR_TABLE) += trace.o cap_audit.o
 obj-$(CONFIG_DMAR_PERF) += perf.o
 obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o
Signature · 1 line
2.34.1
author maintainer
#2 lore raw

PATCH v2 2/12 iommu/vt-d: Add cache tag invalidation helpers

In reply to Lu Baolu

Add several helpers to invalidate the caches after mappings in the affected domain are changed.

- cache_tag_flush_range() invalidates a range of caches after mappings within this range are changed. It uses the page-selective cache invalidation methods.

- cache_tag_flush_all() invalidates all caches tagged by a domain ID. It uses the domain-selective cache invalidation methods.

- cache_tag_flush_range_np() invalidates a range of caches when new mappings are created in the domain and the corresponding page table entries change from non-present to present.

---
 drivers/iommu/intel/iommu.h |  14 +++
 drivers/iommu/intel/cache.c | 195 ++++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/iommu.c |  12 ---
 3 files changed, 209 insertions(+), 12 deletions(-)
drivers/iommu/intel/iommu.h +14 -0
index 6f6bffc60852..700574421b51 100644
@@ -35,6 +35,8 @@
 #define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
 #define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
 
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
+
 #define VTD_STRIDE_SHIFT        (9)
 #define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
 
@@ -1041,6 +1043,13 @@ static inline void context_set_sm_pre(struct context_entry *context)
 	context->lo |= BIT_ULL(4);
 }
 
+/* Returns a number of VTD pages, but aligned to MM page size */
+static inline unsigned long aligned_nrpages(unsigned long host_addr, size_t size)
+{
+	host_addr &= ~PAGE_MASK;
+	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
+}
+
 /* Convert value to context PASID directory size field coding. */
 #define context_pdts(pds)	(((pds) & 0x7) << 9)
 
@@ -1116,6 +1125,11 @@ int cache_tag_assign_domain(struct dmar_domain *domain, u16 did,
 			    struct device *dev, ioasid_t pasid);
 void cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,
 			       struct device *dev, ioasid_t pasid);
+void cache_tag_flush_range(struct dmar_domain *domain, unsigned long start,
+			   unsigned long end, int ih);
+void cache_tag_flush_all(struct dmar_domain *domain);
+void cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long start,
+			      unsigned long end);
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
 void intel_svm_check(struct intel_iommu *iommu);
drivers/iommu/intel/cache.c +195 -0

204 lines not on this page · raw message

drivers/iommu/intel/iommu.c +0 -12
index 17b8ce4b9154..4572624a275e 100644
@@ -54,11 +54,6 @@
 				__DOMAIN_MAX_PFN(gaw), (unsigned long)-1))
 #define DOMAIN_MAX_ADDR(gaw)	(((uint64_t)__DOMAIN_MAX_PFN(gaw)) << VTD_PAGE_SHIFT)
 
-/* IO virtual address start page frame number */
-#define IOVA_START_PFN		(1)
-
-#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
-
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
 
@@ -1985,13 +1980,6 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 				      domain_context_mapping_cb, domain);
 }
 
-/* Returns a number of VTD pages, but aligned to MM page size */
-static unsigned long aligned_nrpages(unsigned long host_addr, size_t size)
-{
-	host_addr &= ~PAGE_MASK;
-	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
-}
-
 /* Return largest possible superpage level for a given mapping */
 static int hardware_largepage_caps(struct dmar_domain *domain, unsigned long iov_pfn,
 				   unsigned long phy_pfn, unsigned long pages)
Signature · 1 line
2.34.1
author maintainer
#6 lore raw

PATCH v2 3/12 iommu/vt-d: Add trace events for cache tag interface

In reply to Lu Baolu

Add trace events for cache tag assign/unassign/flush operations and trace the events in the interfaces. These trace events will improve debugging capabilities by providing detailed information about cache tag activity. A sample of the traced messages looks like below [messages have been stripped and wrapped to make the line short].

cache_tag_assign: dmar9/0000:00:01.0 type iotlb did 1 pasid 9 ref 1
cache_tag_assign: dmar9/0000:00:01.0 type devtlb did 1 pasid 9 ref 1
cache_tag_flush_all: dmar6/0000:8a:00.0 type iotlb did 7 pasid 0 ref 1
cache_tag_flush_range: dmar1 0000:00:1b.0[0] type iotlb did 9

        [0xeab00000-0xeab1afff] addr 0xeab00000 pages 0x20 mask 0x5
 cache_tag_flush_range: dmar1 0000:00:1b.0[0] type iotlb did 9
        [0xeab20000-0xeab31fff] addr 0xeab20000 pages 0x20 mask 0x5
 cache_tag_flush_range: dmar1 0000:00:1b.0[0] type iotlb did 9
        [0xeaa40000-0xeaa51fff] addr 0xeaa40000 pages 0x20 mask 0x5
 cache_tag_flush_range: dmar1 0000:00:1b.0[0] type iotlb did 9
        [0x98de0000-0x98de4fff] addr 0x98de0000 pages 0x8 mask 0x3
 cache_tag_flush_range: dmar1 0000:00:1b.0[0] type iotlb did 9
        [0xe9828000-0xe9828fff] addr 0xe9828000 pages 0x1 mask 0x0

cache_tag_unassign: dmar9/0000:00:01.0 type iotlb did 1 pasid 9 ref 1
cache_tag_unassign: dmar9/0000:00:01.0 type devtlb did 1 pasid 9 ref 1

---
 drivers/iommu/intel/trace.h | 97 +++++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/cache.c | 10 ++++
 2 files changed, 107 insertions(+)
drivers/iommu/intel/trace.h +97 -0
index 93d96f93a89b..c34cef760f0b 100644
@@ -89,6 +89,103 @@ TRACE_EVENT(prq_report,
 				      __entry->dw1, __entry->dw2, __entry->dw3)
 	)
 );
+
+DECLARE_EVENT_CLASS(cache_tag_log,
+	TP_PROTO(struct cache_tag *tag),
+	TP_ARGS(tag),
+	TP_STRUCT__entry(
+		__string(iommu, tag->iommu->name)
+		__string(dev, dev_name(tag->dev))
+		__field(u16, type)
+		__field(u16, domain_id)
+		__field(u32, pasid)
+		__field(u32, users)
+	),
+	TP_fast_assign(
+		__assign_str(iommu, tag->iommu->name);
+		__assign_str(dev, dev_name(tag->dev));
+		__entry->type = tag->type;
+		__entry->domain_id = tag->domain_id;
+		__entry->pasid = tag->pasid;
+		__entry->users = tag->users;
+	),
+	TP_printk("%s/%s type %s did %d pasid %d ref %d",
+		  __get_str(iommu), __get_str(dev),
+		  __print_symbolic(__entry->type,
+			{ CACHE_TAG_IOTLB,		"iotlb" },
+			{ CACHE_TAG_DEVTLB,		"devtlb" },
+			{ CACHE_TAG_PARENT_IOTLB,	"parent_iotlb" },
+			{ CACHE_TAG_PARENT_DEVTLB,	"parent_devtlb" }),
+		__entry->domain_id, __entry->pasid, __entry->users
+	)
+);
+
+DEFINE_EVENT(cache_tag_log, cache_tag_assign,
+	TP_PROTO(struct cache_tag *tag),
+	TP_ARGS(tag)
+);
+
+DEFINE_EVENT(cache_tag_log, cache_tag_unassign,
+	TP_PROTO(struct cache_tag *tag),
+	TP_ARGS(tag)
+);
+
+DEFINE_EVENT(cache_tag_log, cache_tag_flush_all,
+	TP_PROTO(struct cache_tag *tag),
+	TP_ARGS(tag)
+);
+
+DECLARE_EVENT_CLASS(cache_tag_flush,
+	TP_PROTO(struct cache_tag *tag, unsigned long start, unsigned long end,
+		 unsigned long addr, unsigned long pages, unsigned long mask),
+	TP_ARGS(tag, start, end, addr, pages, mask),
+	TP_STRUCT__entry(
+		__string(iommu, tag->iommu->name)
+		__string(dev, dev_name(tag->dev))
+		__field(u16, type)
+		__field(u16, domain_id)
+		__field(u32, pasid)
+		__field(unsigned long, start)
+		__field(unsigned long, end)
+		__field(unsigned long, addr)
+		__field(unsigned long, pages)
+		__field(unsigned long, mask)
+	),
+	TP_fast_assign(
+		__assign_str(iommu, tag->iommu->name);
+		__assign_str(dev, dev_name(tag->dev));
+		__entry->type = tag->type;
+		__entry->domain_id = tag->domain_id;
+		__entry->pasid = tag->pasid;
+		__entry->start = start;
+		__entry->end = end;
+		__entry->addr = addr;
+		__entry->pages = pages;
+		__entry->mask = mask;
+	),
+	TP_printk("%s %s[%d] type %s did %d [0x%lx-0x%lx] addr 0x%lx pages 0x%lx mask 0x%lx",
+		  __get_str(iommu), __get_str(dev), __entry->pasid,
+		  __print_symbolic(__entry->type,
+			{ CACHE_TAG_IOTLB,		"iotlb" },
+			{ CACHE_TAG_DEVTLB,		"devtlb" },
+			{ CACHE_TAG_PARENT_IOTLB,	"parent_iotlb" },
+			{ CACHE_TAG_PARENT_DEVTLB,	"parent_devtlb" }),
+		__entry->domain_id, __entry->start, __entry->end,
+		__entry->addr, __entry->pages, __entry->mask
+	)
+);
+
+DEFINE_EVENT(cache_tag_flush, cache_tag_flush_range,
+	TP_PROTO(struct cache_tag *tag, unsigned long start, unsigned long end,
+		 unsigned long addr, unsigned long pages, unsigned long mask),
+	TP_ARGS(tag, start, end, addr, pages, mask)
+);
+
+DEFINE_EVENT(cache_tag_flush, cache_tag_flush_range_np,
+	TP_PROTO(struct cache_tag *tag, unsigned long start, unsigned long end,
+		 unsigned long addr, unsigned long pages, unsigned long mask),
+	TP_ARGS(tag, start, end, addr, pages, mask)
+);
 #endif /* _TRACE_INTEL_IOMMU_H */
 
 /* This part must be outside protection */
drivers/iommu/intel/cache.c +10 -0
index b2270dc8a765..63873b17f963 100644
@@ -17,6 +17,7 @@
 
 #include "iommu.h"
 #include "pasid.h"
+#include "trace.h"
 
 /* Check if an existing cache tag can be reused for a new association. */
 static bool cache_tage_match(struct cache_tag *tag, u16 domain_id,
@@ -69,11 +70,13 @@ static int cache_tag_assign(struct dmar_domain *domain, u16 did,
 			temp->users++;
 			spin_unlock_irqrestore(&domain->cache_lock, flags);
 			kfree(tag);
+			trace_cache_tag_assign(temp);
 			return 0;
 		}
 	}
 	list_add_tail(&tag->node, &domain->cache_tags);
 	spin_unlock_irqrestore(&domain->cache_lock, flags);
+	trace_cache_tag_assign(tag);
 
 	return 0;
 }
@@ -91,6 +94,7 @@ static void cache_tag_unassign(struct dmar_domain *domain, u16 did,
 	spin_lock_irqsave(&domain->cache_lock, flags);
 	list_for_each_entry(tag, &domain->cache_tags, node) {
 		if (cache_tage_match(tag, did, iommu, dev, pasid, type)) {
+			trace_cache_tag_unassign(tag);
 			if (--tag->users == 0) {
 				list_del(&tag->node);
 				kfree(tag);
@@ -298,6 +302,8 @@ void cache_tag_flush_range(struct dmar_domain *domain, unsigned long start,
 			quirk_extra_dev_tlb_flush(info, addr, mask, tag->pasid, info->ats_qdep);
 			break;
 		}
+
+		trace_cache_tag_flush_range(tag, start, end, addr, pages, mask);
 	}
 	spin_unlock_irqrestore(&domain->cache_lock, flags);
 }
@@ -338,6 +344,8 @@ void cache_tag_flush_all(struct dmar_domain *domain)
 						  IOMMU_NO_PASID, info->ats_qdep);
 			break;
 		}
+
+		trace_cache_tag_flush_all(tag);
 	}
 	spin_unlock_irqrestore(&domain->cache_lock, flags);
 }
@@ -386,6 +394,8 @@ void cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long start,
 							 addr, mask,
 							 DMA_TLB_PSI_FLUSH);
 		}
+
+		trace_cache_tag_flush_range_np(tag, start, end, addr, pages, mask);
 	}
 	spin_unlock_irqrestore(&domain->cache_lock, flags);
 }
Signature · 1 line
2.34.1
author maintainer
#7 lore raw

PATCH v2 4/12 iommu/vt-d: Use cache_tag_flush_all() in flush_iotlb_all

In reply to Lu Baolu

The flush_iotlb_all callback is called by the iommu core to flush all caches for the affected domain. Use cache_tag_flush_all() in this callback.

---
 drivers/iommu/intel/iommu.c | 20 +-------------------
 1 file changed, 1 insertion(+), 19 deletions(-)
drivers/iommu/intel/iommu.c +1 -19
index 4572624a275e..2af3e6f54af0 100644
@@ -1556,25 +1556,7 @@ static void parent_domain_flush(struct dmar_domain *domain,
 
 static void intel_flush_iotlb_all(struct iommu_domain *domain)
 {
-	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct iommu_domain_info *info;
-	unsigned long idx;
-
-	xa_for_each(&dmar_domain->iommu_array, idx, info) {
-		struct intel_iommu *iommu = info->iommu;
-		u16 did = domain_id_iommu(dmar_domain, iommu);
-
-		if (dmar_domain->use_first_level)
-			domain_flush_pasid_iotlb(iommu, dmar_domain, 0, -1, 0);
-		else
-			iommu->flush.flush_iotlb(iommu, did, 0, 0,
-						 DMA_TLB_DSI_FLUSH);
-
-		iommu_flush_dev_iotlb(dmar_domain, 0, MAX_AGAW_PFN_WIDTH);
-	}
-
-	if (dmar_domain->nested_parent)
-		parent_domain_flush(dmar_domain, 0, -1, 0);
+	cache_tag_flush_all(to_dmar_domain(domain));
 }
 
 static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
Signature · 1 line
2.34.1
author maintainer
#8 lore raw

PATCH v2 5/12 iommu/vt-d: Use cache_tag_flush_range() in tlb_sync

In reply to Lu Baolu

The tlb_sync callback is called by the iommu core to flush a range of caches for the affected domain. Use cache_tag_flush_range() in this callback.

---
 drivers/iommu/intel/iommu.c | 21 ++-------------------
 1 file changed, 2 insertions(+), 19 deletions(-)
drivers/iommu/intel/iommu.c +2 -19
index 2af3e6f54af0..8ec69f09935d 100644
@@ -4101,25 +4101,8 @@ static size_t intel_iommu_unmap_pages(struct iommu_domain *domain,
 static void intel_iommu_tlb_sync(struct iommu_domain *domain,
 				 struct iommu_iotlb_gather *gather)
 {
-	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	unsigned long iova_pfn = IOVA_PFN(gather->start);
-	size_t size = gather->end - gather->start;
-	struct iommu_domain_info *info;
-	unsigned long start_pfn;
-	unsigned long nrpages;
-	unsigned long i;
-
-	nrpages = aligned_nrpages(gather->start, size);
-	start_pfn = mm_to_dma_pfn_start(iova_pfn);
-
-	xa_for_each(&dmar_domain->iommu_array, i, info)
-		iommu_flush_iotlb_psi(info->iommu, dmar_domain,
-				      start_pfn, nrpages,
-				      list_empty(&gather->freelist), 0);
-
-	if (dmar_domain->nested_parent)
-		parent_domain_flush(dmar_domain, start_pfn, nrpages,
-				    list_empty(&gather->freelist));
+	cache_tag_flush_range(to_dmar_domain(domain), gather->start,
+			      gather->end, list_empty(&gather->freelist));
 	put_pages_list(&gather->freelist);
 }
 
Signature · 1 line
2.34.1
author maintainer
#9 lore raw

PATCH v2 6/12 iommu/vt-d: Use cache_tag_flush_range_np() in iotlb_sync_map

In reply to Lu Baolu

The iotlb_sync_map callback is called by the iommu core after non-present to present mappings are created. The iommu driver uses this callback to invalidate caches if IOMMU is working in caching mode and second-only translation is used for the domain. Use cache_tag_flush_range_np() in this callback.

---
 drivers/iommu/intel/iommu.c | 22 +---------------------
 1 file changed, 1 insertion(+), 21 deletions(-)
drivers/iommu/intel/iommu.c +1 -21
index 8ec69f09935d..ee5cac6ce4af 100644
@@ -1500,20 +1500,6 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 		iommu_flush_dev_iotlb(domain, addr, mask);
 }
 
-/* Notification for newly created mappings */
-static void __mapping_notify_one(struct intel_iommu *iommu, struct dmar_domain *domain,
-				 unsigned long pfn, unsigned int pages)
-{
-	/*
-	 * It's a non-present to present mapping. Only flush if caching mode
-	 * and second level.
-	 */
-	if (cap_caching_mode(iommu->cap) && !domain->use_first_level)
-		iommu_flush_iotlb_psi(iommu, domain, pfn, pages, 0, 1);
-	else
-		iommu_flush_write_buffer(iommu);
-}
-
 /*
  * Flush the relevant caches in nested translation if the domain
  * also serves as a parent
@@ -4538,14 +4524,8 @@ static bool risky_device(struct pci_dev *pdev)
 static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				      unsigned long iova, size_t size)
 {
-	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	unsigned long pages = aligned_nrpages(iova, size);
-	unsigned long pfn = iova >> VTD_PAGE_SHIFT;
-	struct iommu_domain_info *info;
-	unsigned long i;
+	cache_tag_flush_range_np(to_dmar_domain(domain), iova, iova + size - 1);
 
-	xa_for_each(&dmar_domain->iommu_array, i, info)
-		__mapping_notify_one(info->iommu, dmar_domain, pfn, pages);
 	return 0;
 }
 
Signature · 1 line
2.34.1
author maintainer
#10 lore raw

PATCH v2 7/12 iommu/vt-d: Cleanup use of iommu_flush_iotlb_psi()

In reply to Lu Baolu

Use cache_tag_flush_range() in switch_to_super_page() to invalidate the necessary caches when switching mappings from normal to super pages. The iommu_flush_iotlb_psi() call in intel_iommu_memory_notifier() is unnecessary since there should be no cache invalidation for the identity domain.

Clean up iommu_flush_iotlb_psi() after the last call site is removed.

---
 drivers/iommu/intel/iommu.c | 171 +-----------------------------------
 1 file changed, 2 insertions(+), 169 deletions(-)
drivers/iommu/intel/iommu.c +2 -169
index ee5cac6ce4af..586b6a6afc23 100644
@@ -1389,157 +1389,6 @@ static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
 	quirk_extra_dev_tlb_flush(info, addr, mask, IOMMU_NO_PASID, qdep);
 }
 
-static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
-				  u64 addr, unsigned mask)
-{
-	struct dev_pasid_info *dev_pasid;
-	struct device_domain_info *info;
-	unsigned long flags;
-
-	if (!domain->has_iotlb_device)
-		return;
-
-	spin_lock_irqsave(&domain->lock, flags);
-	list_for_each_entry(info, &domain->devices, link)
-		__iommu_flush_dev_iotlb(info, addr, mask);
-
-	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) {
-		info = dev_iommu_priv_get(dev_pasid->dev);
-
-		if (!info->ats_enabled)
-			continue;
-
-		qi_flush_dev_iotlb_pasid(info->iommu,
-					 PCI_DEVID(info->bus, info->devfn),
-					 info->pfsid, dev_pasid->pasid,
-					 info->ats_qdep, addr,
-					 mask);
-	}
-	spin_unlock_irqrestore(&domain->lock, flags);
-}
-
-static void domain_flush_pasid_iotlb(struct intel_iommu *iommu,
-				     struct dmar_domain *domain, u64 addr,
-				     unsigned long npages, bool ih)
-{
-	u16 did = domain_id_iommu(domain, iommu);
-	struct dev_pasid_info *dev_pasid;
-	unsigned long flags;
-
-	spin_lock_irqsave(&domain->lock, flags);
-	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain)
-		qi_flush_piotlb(iommu, did, dev_pasid->pasid, addr, npages, ih);
-
-	if (!list_empty(&domain->devices))
-		qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, addr, npages, ih);
-	spin_unlock_irqrestore(&domain->lock, flags);
-}
-
-static void __iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
-				    unsigned long pfn, unsigned int pages,
-				    int ih)
-{
-	unsigned int aligned_pages = __roundup_pow_of_two(pages);
-	unsigned long bitmask = aligned_pages - 1;
-	unsigned int mask = ilog2(aligned_pages);
-	u64 addr = (u64)pfn << VTD_PAGE_SHIFT;
-
-	/*
-	 * PSI masks the low order bits of the base address. If the
-	 * address isn't aligned to the mask, then compute a mask value
-	 * needed to ensure the target range is flushed.
-	 */
-	if (unlikely(bitmask & pfn)) {
-		unsigned long end_pfn = pfn + pages - 1, shared_bits;
-
-		/*
-		 * Since end_pfn <= pfn + bitmask, the only way bits
-		 * higher than bitmask can differ in pfn and end_pfn is
-		 * by carrying. This means after masking out bitmask,
-		 * high bits starting with the first set bit in
-		 * shared_bits are all equal in both pfn and end_pfn.
-		 */
-		shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
-		mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
-	}
-
-	/*
-	 * Fallback to domain selective flush if no PSI support or
-	 * the size is too big.
-	 */
-	if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
-		iommu->flush.flush_iotlb(iommu, did, 0, 0,
-					 DMA_TLB_DSI_FLUSH);
-	else
-		iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
-					 DMA_TLB_PSI_FLUSH);
-}
-
-static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
-				  struct dmar_domain *domain,
-				  unsigned long pfn, unsigned int pages,
-				  int ih, int map)
-{
-	unsigned int aligned_pages = __roundup_pow_of_two(pages);
-	unsigned int mask = ilog2(aligned_pages);
-	uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT;
-	u16 did = domain_id_iommu(domain, iommu);
-
-	if (WARN_ON(!pages))
-		return;
-
-	if (ih)
-		ih = 1 << 6;
-
-	if (domain->use_first_level)
-		domain_flush_pasid_iotlb(iommu, domain, addr, pages, ih);
-	else
-		__iommu_flush_iotlb_psi(iommu, did, pfn, pages, ih);
-
-	if (!map)
-		iommu_flush_dev_iotlb(domain, addr, mask);
-}
-
-/*
- * Flush the relevant caches in nested translation if the domain
- * also serves as a parent
- */
-static void parent_domain_flush(struct dmar_domain *domain,
-				unsigned long pfn,
-				unsigned long pages, int ih)
-{
-	struct dmar_domain *s1_domain;
-
-	spin_lock(&domain->s1_lock);
-	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
-		struct device_domain_info *device_info;
-		struct iommu_domain_info *info;
-		unsigned long flags;
-		unsigned long i;
-
-		xa_for_each(&s1_domain->iommu_array, i, info)
-			__iommu_flush_iotlb_psi(info->iommu, info->did,
-						pfn, pages, ih);
-
-		if (!s1_domain->has_iotlb_device)
-			continue;
-
-		spin_lock_irqsave(&s1_domain->lock, flags);
-		list_for_each_entry(device_info, &s1_domain->devices, link)
-			/*
-			 * Address translation cache in device side caches the
-			 * result of nested translation. There is no easy way
-			 * to identify the exact set of nested translations
-			 * affected by a change in S2. So just flush the entire
-			 * device cache.
-			 */
-			__iommu_flush_dev_iotlb(device_info, 0,
-						MAX_AGAW_PFN_WIDTH);
-		spin_unlock_irqrestore(&s1_domain->lock, flags);
-	}
-	spin_unlock(&domain->s1_lock);
-}
-
 static void intel_flush_iotlb_all(struct iommu_domain *domain)
 {
 	cache_tag_flush_all(to_dmar_domain(domain));
@@ -1984,9 +1833,7 @@ static void switch_to_super_page(struct dmar_domain *domain,
 				 unsigned long end_pfn, int level)
 {
 	unsigned long lvl_pages = lvl_to_nr_pages(level);
-	struct iommu_domain_info *info;
 	struct dma_pte *pte = NULL;
-	unsigned long i;
 
 	while (start_pfn <= end_pfn) {
 		if (!pte)
@@ -1998,13 +1845,8 @@ static void switch_to_super_page(struct dmar_domain *domain,
 					       start_pfn + lvl_pages - 1,
 					       level + 1);
 
-			xa_for_each(&domain->iommu_array, i, info)
-				iommu_flush_iotlb_psi(info->iommu, domain,
-						      start_pfn, lvl_pages,
-						      0, 0);
-			if (domain->nested_parent)
-				parent_domain_flush(domain, start_pfn,
-						    lvl_pages, 0);
+			cache_tag_flush_range(domain, start_pfn << VTD_PAGE_SHIFT,
+					      end_pfn << VTD_PAGE_SHIFT, 0);
 		}
 
 		pte++;
@@ -3376,18 +3218,9 @@ static int intel_iommu_memory_notifier(struct notifier_block *nb,
 	case MEM_OFFLINE:
 	case MEM_CANCEL_ONLINE:
 		{
-			struct dmar_drhd_unit *drhd;
-			struct intel_iommu *iommu;
 			LIST_HEAD(freelist);
 
 			domain_unmap(si_domain, start_vpfn, last_vpfn, &freelist);
-
-			rcu_read_lock();
-			for_each_active_iommu(iommu, drhd)
-				iommu_flush_iotlb_psi(iommu, si_domain,
-					start_vpfn, mhp->nr_pages,
-					list_empty(&freelist), 0);
-			rcu_read_unlock();
 			put_pages_list(&freelist);
 		}
 		break;
Signature · 1 line
2.34.1
author maintainer
#11 lore raw

PATCH v2 8/12 iommu/vt-d: Use cache_tag_flush_range() in cache_invalidate_user

In reply to Lu Baolu

The cache_invalidate_user callback is called to invalidate a range of caches for the affected user domain. Use cache_tag_flush_range() in this callback.

---
 drivers/iommu/intel/iommu.h  |  6 +++++
 drivers/iommu/intel/nested.c | 50 +++---------------------------------
 2 files changed, 9 insertions(+), 47 deletions(-)
drivers/iommu/intel/iommu.h +6 -0
index 700574421b51..90a300665962 100644
@@ -1050,6 +1050,12 @@ static inline unsigned long aligned_nrpages(unsigned long host_addr, size_t size
 	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
 }
 
+/* Return a size from number of VTD pages. */
+static inline unsigned long nrpages_to_size(unsigned long npages)
+{
+	return npages << VTD_PAGE_SHIFT;
+}
+
 /* Convert value to context PASID directory size field coding. */
 #define context_pdts(pds)	(((pds) & 0x7) << 9)
 
drivers/iommu/intel/nested.c +3 -47

62 lines not on this page · raw message

Signature · 1 line
2.34.1
author maintainer
#12 lore raw

PATCH v2 9/12 iommu/vt-d: Use cache helpers in arch_invalidate_secondary_tlbs

In reply to Lu Baolu

The arch_invalidate_secondary_tlbs callback is called in the SVA mm notification path. It invalidates all or a range of caches after the CPU page table is modified. Use the cache tag helps in this path.

---
 drivers/iommu/intel/iommu.h |  1 +
 drivers/iommu/intel/svm.c   | 76 +++----------------------------------
 2 files changed, 6 insertions(+), 71 deletions(-)
drivers/iommu/intel/iommu.h +1 -0
index 90a300665962..5a42d6ee9119 100644
@@ -1161,6 +1161,7 @@ struct intel_svm {
 	struct mm_struct *mm;
 	u32 pasid;
 	struct list_head devs;
+	struct dmar_domain *domain;
 };
 #else
 static inline void intel_svm_check(struct intel_iommu *iommu) {}
drivers/iommu/intel/svm.c +5 -71

105 lines not on this page · raw message

Signature · 1 line
2.34.1
author maintainer
#15 lore raw

PATCH v2 10/12 iommu/vt-d: Retire intel_svm_dev

In reply to Lu Baolu

The intel_svm_dev data structure used in the sva implementation for the Intel IOMMU driver stores information about a device attached to an SVA domain. It is a duplicate of dev_pasid_info that serves the same purpose.

Replace intel_svm_dev with dev_pasid_info and clean up the use of intel_svm_dev.

---
 drivers/iommu/intel/iommu.h |  15 +----
 drivers/iommu/intel/iommu.c |  30 ++++-----
 drivers/iommu/intel/svm.c   | 131 +++++++++++-------------------------
 3 files changed, 55 insertions(+), 121 deletions(-)
drivers/iommu/intel/iommu.h +3 -12
index 5a42d6ee9119..90611ec08a7c 100644
@@ -650,6 +650,7 @@ struct dmar_domain {
 			struct list_head s2_link;
 		};
 	};
+	struct intel_svm *svm;
 
 	struct iommu_domain domain;	/* generic domain data structure for
 					   iommu core */
@@ -1144,23 +1145,13 @@ int intel_svm_finish_prq(struct intel_iommu *iommu);
 void intel_svm_page_response(struct device *dev, struct iopf_fault *evt,
 			     struct iommu_page_response *msg);
 struct iommu_domain *intel_svm_domain_alloc(void);
-void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid);
+void intel_svm_remove_dev_pasid(struct iommu_domain *domain);
 void intel_drain_pasid_prq(struct device *dev, u32 pasid);
 
-struct intel_svm_dev {
-	struct list_head list;
-	struct rcu_head rcu;
-	struct device *dev;
-	struct intel_iommu *iommu;
-	u16 did;
-	u16 sid, qdep;
-};
-
 struct intel_svm {
 	struct mmu_notifier notifier;
 	struct mm_struct *mm;
 	u32 pasid;
-	struct list_head devs;
 	struct dmar_domain *domain;
 };
 #else
@@ -1171,7 +1162,7 @@ static inline struct iommu_domain *intel_svm_domain_alloc(void)
 	return NULL;
 }
 
-static inline void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid)
+static inline void intel_svm_remove_dev_pasid(struct iommu_domain *domain)
 {
 }
 #endif
drivers/iommu/intel/iommu.c +14 -16
index 586b6a6afc23..d7f205cd0aac 100644
@@ -4377,18 +4377,6 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 		goto out_tear_down;
 	dmar_domain = to_dmar_domain(domain);
 
-	/*
-	 * The SVA implementation needs to handle its own stuffs like the mm
-	 * notification. Before consolidating that code into iommu core, let
-	 * the intel sva code handle it.
-	 */
-	if (domain->type == IOMMU_DOMAIN_SVA) {
-		intel_svm_remove_dev_pasid(dev, pasid);
-		cache_tag_unassign_domain(dmar_domain,
-					  FLPT_DEFAULT_DID, dev, pasid);
-		goto out_tear_down;
-	}
-
 	spin_lock_irqsave(&dmar_domain->lock, flags);
 	list_for_each_entry(curr, &dmar_domain->dev_pasids, link_domain) {
 		if (curr->dev == dev && curr->pasid == pasid) {
@@ -4400,10 +4388,20 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 	WARN_ON_ONCE(!dev_pasid);
 	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
-	did = domain_id_iommu(dmar_domain, iommu);
-	cache_tag_unassign_domain(dmar_domain, did, dev, pasid);
-	domain_detach_iommu(dmar_domain, iommu);
-	intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
+	/*
+	 * The SVA implementation needs to handle its own stuffs like the mm
+	 * notification. Before consolidating that code into iommu core, let
+	 * the intel sva code handle it.
+	 */
+	if (domain->type == IOMMU_DOMAIN_SVA) {
+		cache_tag_unassign_domain(dmar_domain, FLPT_DEFAULT_DID, dev, pasid);
+		intel_svm_remove_dev_pasid(domain);
+	} else {
+		did = domain_id_iommu(dmar_domain, iommu);
+		cache_tag_unassign_domain(dmar_domain, did, dev, pasid);
+		domain_detach_iommu(dmar_domain, iommu);
+		intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
+	}
 	kfree(dev_pasid);
 out_tear_down:
 	intel_pasid_tear_down_entry(iommu, dev, pasid, false);
drivers/iommu/intel/svm.c +38 -93

210 lines not on this page · raw message

Signature · 1 line
2.34.1
author maintainer
#16 lore raw

PATCH v2 11/12 iommu: Add ops->domain_alloc_sva()

In reply to Lu Baolu

From: Jason Gunthorpe <[email protected]>

Make a new op that receives the device and the mm_struct that the SVA domain should be created for. Unlike domain_alloc_paging() the dev argument is never NULL here.

This allows drivers to fully initialize the SVA domain and allocate the mmu_notifier during allocation. It allows the notifier lifetime to follow the lifetime of the iommu_domain.

Since we have only one call site, upgrade the new op to return ERR_PTR instead of NULL.

---
 include/linux/iommu.h     |  3 +++
 drivers/iommu/iommu-sva.c | 16 +++++++++++-----
 2 files changed, 14 insertions(+), 5 deletions(-)
include/linux/iommu.h +3 -0
index 2e925b5eba53..8aabe83af8f2 100644
@@ -518,6 +518,7 @@ static inline int __iommu_copy_struct_from_user_array(
  *                     Upon failure, ERR_PTR must be returned.
  * @domain_alloc_paging: Allocate an iommu_domain that can be used for
  *                       UNMANAGED, DMA, and DMA_FQ domain types.
+ * @domain_alloc_sva: Allocate an iommu_domain for Shared Virtual Addressing.
  * @probe_device: Add device to iommu driver handling
  * @release_device: Remove device from iommu driver handling
  * @probe_finalize: Do final setup work after the device is added to an IOMMU
@@ -558,6 +559,8 @@ struct iommu_ops {
 		struct device *dev, u32 flags, struct iommu_domain *parent,
 		const struct iommu_user_data *user_data);
 	struct iommu_domain *(*domain_alloc_paging)(struct device *dev);
+	struct iommu_domain *(*domain_alloc_sva)(struct device *dev,
+						 struct mm_struct *mm);
 
 	struct iommu_device *(*probe_device)(struct device *dev);
 	void (*release_device)(struct device *dev);
drivers/iommu/iommu-sva.c +11 -5
index 640acc804e8c..18a35e798b72 100644
@@ -108,8 +108,8 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 
 	/* Allocate a new domain and set it on device pasid. */
 	domain = iommu_sva_domain_alloc(dev, mm);
-	if (!domain) {
-		ret = -ENOMEM;
+	if (IS_ERR(domain)) {
+		ret = PTR_ERR(domain);
 		goto out_free_handle;
 	}
 
@@ -283,9 +283,15 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
 	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	struct iommu_domain *domain;
 
-	domain = ops->domain_alloc(IOMMU_DOMAIN_SVA);
-	if (!domain)
-		return NULL;
+	if (ops->domain_alloc_sva) {
+		domain = ops->domain_alloc_sva(dev, mm);
+		if (IS_ERR(domain))
+			return domain;
+	} else {
+		domain = ops->domain_alloc(IOMMU_DOMAIN_SVA);
+		if (!domain)
+			return ERR_PTR(-ENOMEM);
+	}
 
 	domain->type = IOMMU_DOMAIN_SVA;
 	mmgrab(mm);
Signature · 1 line
2.34.1
author maintainer
#17 lore raw

PATCH v2 12/12 iommu/vt-d: Retire struct intel_svm

In reply to Lu Baolu

The struct intel_svm was used for keeping attached devices info for sva domain. Since sva domain is a kind of iommu_domain, the struct dmar_domain should centralize all info of a sva domain, including the info of attached devices. Therefore, retire struct intel_svm to clean up the code.

Besides, allocate sva domain in domain_alloc_sva() callback which allows the memory management notifier lifetime to follow the lifetime of the iommu_domain.

---
 drivers/iommu/intel/iommu.h | 26 ++++------
 drivers/iommu/intel/iommu.c |  9 +---
 drivers/iommu/intel/svm.c   | 94 +++++++++----------------------------
 3 files changed, 32 insertions(+), 97 deletions(-)
drivers/iommu/intel/iommu.h +10 -16
index 90611ec08a7c..0951be947ff9 100644
@@ -649,8 +649,12 @@ struct dmar_domain {
 			/* link to parent domain siblings */
 			struct list_head s2_link;
 		};
+
+		/* SVA domain */
+		struct {
+			struct mmu_notifier notifier;
+		};
 	};
-	struct intel_svm *svm;
 
 	struct iommu_domain domain;	/* generic domain data structure for
 					   iommu core */
@@ -1144,26 +1148,16 @@ int intel_svm_enable_prq(struct intel_iommu *iommu);
 int intel_svm_finish_prq(struct intel_iommu *iommu);
 void intel_svm_page_response(struct device *dev, struct iopf_fault *evt,
 			     struct iommu_page_response *msg);
-struct iommu_domain *intel_svm_domain_alloc(void);
-void intel_svm_remove_dev_pasid(struct iommu_domain *domain);
+struct iommu_domain *intel_svm_domain_alloc(struct device *dev,
+					    struct mm_struct *mm);
 void intel_drain_pasid_prq(struct device *dev, u32 pasid);
-
-struct intel_svm {
-	struct mmu_notifier notifier;
-	struct mm_struct *mm;
-	u32 pasid;
-	struct dmar_domain *domain;
-};
 #else
 static inline void intel_svm_check(struct intel_iommu *iommu) {}
 static inline void intel_drain_pasid_prq(struct device *dev, u32 pasid) {}
-static inline struct iommu_domain *intel_svm_domain_alloc(void)
-{
-	return NULL;
-}
-
-static inline void intel_svm_remove_dev_pasid(struct iommu_domain *domain)
+static inline struct iommu_domain *intel_svm_domain_alloc(struct device *dev,
+							  struct mm_struct *mm)
 {
+	return ERR_PTR(-ENODEV);
 }
 #endif
 
drivers/iommu/intel/iommu.c +1 -8
index d7f205cd0aac..b8a0f759a24f 100644
@@ -3680,8 +3680,6 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 		return domain;
 	case IOMMU_DOMAIN_IDENTITY:
 		return &si_domain->domain;
-	case IOMMU_DOMAIN_SVA:
-		return intel_svm_domain_alloc();
 	default:
 		return NULL;
 	}
@@ -4388,14 +4386,8 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 	WARN_ON_ONCE(!dev_pasid);
 	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
-	/*
-	 * The SVA implementation needs to handle its own stuffs like the mm
-	 * notification. Before consolidating that code into iommu core, let
-	 * the intel sva code handle it.
-	 */
 	if (domain->type == IOMMU_DOMAIN_SVA) {
 		cache_tag_unassign_domain(dmar_domain, FLPT_DEFAULT_DID, dev, pasid);
-		intel_svm_remove_dev_pasid(domain);
 	} else {
 		did = domain_id_iommu(dmar_domain, iommu);
 		cache_tag_unassign_domain(dmar_domain, did, dev, pasid);
@@ -4624,6 +4616,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.hw_info		= intel_iommu_hw_info,
 	.domain_alloc		= intel_iommu_domain_alloc,
 	.domain_alloc_user	= intel_iommu_domain_alloc_user,
+	.domain_alloc_sva	= intel_svm_domain_alloc,
 	.probe_device		= intel_iommu_probe_device,
 	.probe_finalize		= intel_iommu_probe_finalize,
 	.release_device		= intel_iommu_release_device,
drivers/iommu/intel/svm.c +21 -73

156 lines not on this page · raw message

Signature · 1 line
2.34.1
#18 lore raw

Re: [PATCH v2 12/12] iommu/vt-d: Retire struct intel_svm

Quoted 10 lines · Lu Baolu

The struct intel_svm was used for keeping attached devices info for sva domain. Since sva domain is a kind of iommu_domain, the struct dmar_domain should centralize all info of a sva domain, including the info of attached devices. Therefore, retire struct intel_svm to clean up the code.

Besides, allocate sva domain in domain_alloc_sva() callback which allows the memory management notifier lifetime to follow the lifetime of the iommu_domain.

Quoted 8 lines
---
 drivers/iommu/intel/iommu.h | 26 ++++------
 drivers/iommu/intel/iommu.c |  9 +---
 drivers/iommu/intel/svm.c   | 94 +++++++++----------------------------
 3 files changed, 32 insertions(+), 97 deletions(-)

Happy to see the pasid xarray in the driver go away.

Quoted 5 lines
drivers/iommu/intel/iommu.c +0 -1
@@ -4388,14 +4386,8 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 	WARN_ON_ONCE(!dev_pasid);
 	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
-	/*

drivers/iommu/intel/iommu.c static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid) · line 4393

Quoted 10 lines
drivers/iommu/intel/iommu.c +0 -5
-	 * The SVA implementation needs to handle its own stuffs like the mm
-	 * notification. Before consolidating that code into iommu core, let
-	 * the intel sva code handle it.
-	 */
 	if (domain->type == IOMMU_DOMAIN_SVA) {
 		cache_tag_unassign_domain(dmar_domain, FLPT_DEFAULT_DID, dev, pasid);
-		intel_svm_remove_dev_pasid(domain);
 	} else {
 		did = domain_id_iommu(dmar_domain, iommu);
 		cache_tag_unassign_domain(dmar_domain, did, dev, pasid);

It seems very strange that SVA has a different DID scheme, why is this? PASID and SVA should not be different at this layer.

drivers/iommu/intel/svm.c void intel_svm_page_response(struct device *dev, struct iopf_fault *evt, · line 602

Quoted 9 lines
drivers/iommu/intel/svm.c +4 -1
@@ -663,7 +596,12 @@ void intel_svm_page_response(struct device *dev, struct iopf_fault *evt,
 
 static void intel_svm_domain_free(struct iommu_domain *domain)
 {
-	kfree(to_dmar_domain(domain));
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	if (dmar_domain->notifier.ops)
+		mmu_notifier_unregister(&dmar_domain->notifier, domain->mm);

This should really use mmu_notifier_put() and a delayed kfree, see my part 2 ARM series for how that should look.

Otherwise I think it looks fine

Jason

#13 lore raw

Re: [PATCH v2 09/12] iommu/vt-d: Use cache helpers in arch_invalidate_secondary_tlbs

In reply to Lu Baolu

drivers/iommu/intel/svm.c void intel_svm_check(struct intel_iommu *iommu) · line 179

Quoted 9 lines · Lu Baolu

/* Pages have been freed at this point */
static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,

drivers/iommu/intel/svm.c +1 -0
 					struct mm_struct *mm,
 					unsigned long start, unsigned long end)
 {
 	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
+	struct dmar_domain *domain = svm->domain;
 
 	if (start == 0 && end == -1UL) {

ULONG_MAX ideally.

drivers/iommu/intel/svm.c void intel_svm_check(struct intel_iommu *iommu) · line 184

Quoted 8 lines
drivers/iommu/intel/svm.c +2 -3
-		intel_flush_svm_all(svm);
+		cache_tag_flush_all(domain);
 		return;
 	}
 
-	intel_flush_svm_range(svm, start,
-			      (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0);
+	cache_tag_flush_range(domain, start, end, 0);

Be mindful of the note from the ARM driver:

/*
* The mm_types defines vm_end as the first byte after the end address,
* different from IOMMU subsystem using the last address of an address
* range. So do a simple translation here by calculating size correctly. */
size = end - start;

Given that the cache_tag_flush_range's are all tied directly to the iommu gather API, this is probably missing a -1 though perhaps it does not cause a functional problem here.

Jason

author maintainer
#19 lore raw

Re: [PATCH v2 12/12] iommu/vt-d: Retire struct intel_svm

In reply to Jason Gunthorpe
Quoted 20 lines · Jason Gunthorpe
Quoted 10 lines · Lu Baolu

The struct intel_svm was used for keeping attached devices info for sva domain. Since sva domain is a kind of iommu_domain, the struct dmar_domain should centralize all info of a sva domain, including the info of attached devices. Therefore, retire struct intel_svm to clean up the code.

Besides, allocate sva domain in domain_alloc_sva() callback which allows the memory management notifier lifetime to follow the lifetime of the iommu_domain.

Quoted 8 lines
---
  drivers/iommu/intel/iommu.h | 26 ++++------
  drivers/iommu/intel/iommu.c |  9 +---
  drivers/iommu/intel/svm.c   | 94 +++++++++----------------------------
  3 files changed, 32 insertions(+), 97 deletions(-)
Quoted 1 line

Happy to see the pasid xarray in the driver go away.

Yeah, it was really ugly.

Quoted 5 lines
Quoted 5 lines
(quoted diff) +0 -0
@@ -4388,14 +4386,8 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
  	WARN_ON_ONCE(!dev_pasid);
  	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
Quoted 14 lines

Review static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid) · line 4393

Quoted 11 lines
(quoted diff) +0 -6
-	/*
-	 * The SVA implementation needs to handle its own stuffs like the mm
-	 * notification. Before consolidating that code into iommu core, let
-	 * the intel sva code handle it.
-	 */
  	if (domain->type == IOMMU_DOMAIN_SVA) {
  		cache_tag_unassign_domain(dmar_domain, FLPT_DEFAULT_DID, dev, pasid);
-		intel_svm_remove_dev_pasid(domain);
  	} else {
  		did = domain_id_iommu(dmar_domain, iommu);
  		cache_tag_unassign_domain(dmar_domain, did, dev, pasid);

It seems very strange that SVA has a different DID scheme, why is this? PASID and SVA should not be different at this layer.

The VT-d spec recommends that all SVA domains share a single domain ID. The PASID is unique to each SVA domain, hence the cache tags are unique. Currently, the Intel IOMMU driver assigns different domain IDs for all domains except the SVA type.

Sharing a domain ID is not specific to SVA. In general, for devices under a single IOMMU, domains with unique PASIDs can share the same domain ID.

In the long term (also on my task list), we will extend the cache tag code to support sharing domain IDs and remove the domain type check from the main code. This will also benefit the nesting case, where user domains nested on the same parent could share a domain ID.

Quoted 13 lines

Review void intel_svm_page_response(struct device *dev, struct iopf_fault *evt, · line 602

Quoted 10 lines
(quoted diff) +4 -1
@@ -663,7 +596,12 @@ void intel_svm_page_response(struct device *dev, struct iopf_fault *evt,
 
  static void intel_svm_domain_free(struct iommu_domain *domain)
  {
-	kfree(to_dmar_domain(domain));
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	if (dmar_domain->notifier.ops)
+		mmu_notifier_unregister(&dmar_domain->notifier, domain->mm);

This should really use mmu_notifier_put() and a delayed kfree, see my part 2 ARM series for how that should look.

Learning from

https://lore.kernel.org/linux-iommu/[email protected]/

I will make it like below

drivers/iommu/intel/svm.c +5 -0
index 47e475f67046..41374979eecc 100644
@@ -178,9 +178,15 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 
 }
 
+static void intel_mm_free_notifier(struct mmu_notifier *mn)
+{
+       kfree(container_of(mn, struct dmar_domain, notifier));
+}
+
 static const struct mmu_notifier_ops intel_mmuops = {
        .release = intel_mm_release,
        .arch_invalidate_secondary_tlbs = 

intel_arch_invalidate_secondary_tlbs,
+ .free_notifier = intel_mm_free_notifier,
};

static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
@@ -598,10 +604,8 @@ static void intel_svm_domain_free(struct iommu_domain *domain)

 {
        struct dmar_domain *dmar_domain = to_dmar_domain(domain);

- if (dmar_domain->notifier.ops)
- mmu_notifier_unregister(&dmar_domain->notifier, domain->mm);
-

-       kfree(dmar_domain);
+       /* dmar_domain free is defered to the mmu free_notifier callback. */
+       mmu_notifier_put(&dmar_domain->notifier);

}

static const struct iommu_domain_ops intel_svm_domain_ops = {

Quoted 2 lines

Otherwise I think it looks fine

Thank you for review.

Best regards,
baolu

author maintainer
#14 lore raw

Re: [PATCH v2 09/12] iommu/vt-d: Use cache helpers in arch_invalidate_secondary_tlbs

In reply to Jason Gunthorpe
Quoted 9 lines · Jason Gunthorpe
Quoted 8 lines · Lu Baolu

/* Pages have been freed at this point */
static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
struct mm_struct *mm, unsigned long start, unsigned long end)
{
struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);

(quoted diff) +1 -0
+	struct dmar_domain *domain = svm->domain;
Quoted 3 lines
Quoted 1 line
  	if (start == 0 && end == -1UL) {

ULONG_MAX ideally.

Done.

Quoted 12 lines

Review

Quoted 9 lines
(quoted diff) +2 -3
-		intel_flush_svm_all(svm);
+		cache_tag_flush_all(domain);
  		return;
  	}
 
-	intel_flush_svm_range(svm, start,
-			      (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0);
+	cache_tag_flush_range(domain, start, end, 0);

Be mindful of the note from the ARM driver:

Quoted 6 lines

/*
* The mm_types defines vm_end as the first byte after the end address,
* different from IOMMU subsystem using the last address of an address
* range. So do a simple translation here by calculating size correctly. */
size = end - start;

I didn't find any documentation about the @end in this callback, but in mm subsystem, it does like this,

flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false);

So, yes, the @end in arch_invalidate_secondary_tlbs callback is different from the iommu gather.

I was not aware of this. Thanks for pointing this out.

Quoted 4 lines

Given that the cache_tag_flush_range's are all tied directly to the iommu gather API, this is probably missing a -1 though perhaps it does not cause a functional problem here.

I will change it like below,

drivers/iommu/intel/svm.c +6 -1
index 858a64fbdaab..15dcd1b30df1 100644
@@ -146,7 +146,12 @@ static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
                return;
        }
 
-       cache_tag_flush_range(domain, start, end, 0);
+       /*
+        * The mm_types defines vm_end as the first byte after the end address,
+        * different from IOMMU subsystem using the last address of an address
+        * range.
+        */
+       cache_tag_flush_range(domain, start, end - 1, 0);
 }
 
 static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct 

*mm)

Best regards,
baolu

#20 lore raw

RE: [PATCH v2 12/12] iommu/vt-d: Retire struct intel_svm

In reply to Baolu Lu
Quoted 32 lines

From: Baolu Lu <[email protected]>
Sent: Thursday, April 11, 2024 3:56 PM

Quoted 2 lines · Jason Gunthorpe

Review static void

Quoted 1 line · Lu Baolu
(quoted diff) +0 -0
@@ -4388,14 +4386,8 @@ static void

intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)

Quoted 5 lines

Review static void · line 4392

Quoted 5 lines
(quoted diff) +0 -2
  	WARN_ON_ONCE(!dev_pasid);
  	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
-	/*
-	 * The SVA implementation needs to handle its own stuffs like the

mm

Quoted 5 lines

Review static void · line 4390

Quoted 5 lines
(quoted diff) +0 -3
-	 * notification. Before consolidating that code into iommu core, let
-	 * the intel sva code handle it.
-	 */
  	if (domain->type == IOMMU_DOMAIN_SVA) {
  		cache_tag_unassign_domain(dmar_domain,

FLPT_DEFAULT_DID, dev, pasid);

Quoted 7 lines

Review static void · line 4393

Quoted 4 lines
(quoted diff) +0 -1
-		intel_svm_remove_dev_pasid(domain);
  	} else {
  		did = domain_id_iommu(dmar_domain, iommu);
  		cache_tag_unassign_domain(dmar_domain, did, dev, pasid);

It seems very strange that SVA has a different DID scheme, why is this? PASID and SVA should not be different at this layer.

The VT-d spec recommends that all SVA domains share a single domain ID. The PASID is unique to each SVA domain, hence the cache tags are unique. Currently, the Intel IOMMU driver assigns different domain IDs for all domains except the SVA type.

Quoted 9 lines

Sharing a domain ID is not specific to SVA. In general, for devices under a single IOMMU, domains with unique PASIDs can share the same domain ID.

In the long term (also on my task list), we will extend the cache tag code to support sharing domain IDs and remove the domain type check from the main code. This will also benefit the nesting case, where user domains nested on the same parent could share a domain ID.

at least above might be changed to a unified call with the helper accepting an iommu parameter and then finding proper did internally based on domain type, e.g.

cache_tag_unassign_domain(domain, iommu, dev, pasid)

{
	if (domain->type == IOMMU_DOMAIN_SVA)
		did = FLPT_DEFAULT_DID;
	else
		did = domain_id_iommu(domain, iommu);

	...
}
author maintainer
#21 lore raw

Re: [PATCH v2 12/12] iommu/vt-d: Retire struct intel_svm

Quoted 44 lines · Kevin
Quoted 30 lines

From: Baolu Lu<[email protected]>
Sent: Thursday, April 11, 2024 3:56 PM

Quoted 2 lines · Jason Gunthorpe

Review static void

Quoted 1 line · Lu Baolu
(quoted diff) +0 -0
@@ -4388,14 +4386,8 @@ static void

intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)

Quoted 5 lines

Review static void · line 4392

Quoted 5 lines
(quoted diff) +0 -2
   	WARN_ON_ONCE(!dev_pasid);
   	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
-	/*
-	 * The SVA implementation needs to handle its own stuffs like the

mm

Quoted 5 lines

Review static void · line 4390

Quoted 5 lines
(quoted diff) +0 -3
-	 * notification. Before consolidating that code into iommu core, let
-	 * the intel sva code handle it.
-	 */
   	if (domain->type == IOMMU_DOMAIN_SVA) {
   		cache_tag_unassign_domain(dmar_domain,

FLPT_DEFAULT_DID, dev, pasid);

Quoted 6 lines

Review static void · line 4393

Quoted 4 lines
(quoted diff) +0 -1
-		intel_svm_remove_dev_pasid(domain);
   	} else {
   		did = domain_id_iommu(dmar_domain, iommu);
   		cache_tag_unassign_domain(dmar_domain, did, dev, pasid);

It seems very strange that SVA has a different DID scheme, why is this? PASID and SVA should not be different at this layer.

The VT-d spec recommends that all SVA domains share a single domain ID. The PASID is unique to each SVA domain, hence the cache tags are unique. Currently, the Intel IOMMU driver assigns different domain IDs for all domains except the SVA type.

Quoted 9 lines

Sharing a domain ID is not specific to SVA. In general, for devices under a single IOMMU, domains with unique PASIDs can share the same domain ID.

In the long term (also on my task list), we will extend the cache tag code to support sharing domain IDs and remove the domain type check from the main code. This will also benefit the nesting case, where user domains nested on the same parent could share a domain ID.

at least above might be changed to a unified call with the helper accepting an iommu parameter and then finding proper did internally based on domain type, e.g.

cache_tag_unassign_domain(domain, iommu, dev, pasid)

Quoted 8 lines
{
	if (domain->type == IOMMU_DOMAIN_SVA)
		did = FLPT_DEFAULT_DID;
	else
		did = domain_id_iommu(domain, iommu);

	...
}

Yeah, your code is more graceful.

Best regards,
baolu

#22 lore raw

Re: [PATCH v2 12/12] iommu/vt-d: Retire struct intel_svm

In reply to Baolu Lu
Quoted 23 lines · Baolu Lu
Quoted 9 lines
Quoted 9 lines
(quoted diff) +0 -5
@@ -4388,14 +4386,8 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
  	WARN_ON_ONCE(!dev_pasid);
  	spin_unlock_irqrestore(&dmar_domain->lock, flags);
-	/*
-	 * The SVA implementation needs to handle its own stuffs like the mm
-	 * notification. Before consolidating that code into iommu core, let
-	 * the intel sva code handle it.
-	 */
  	if (domain->type == IOMMU_DOMAIN_SVA) {
Quoted 8 lines

Review static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid) · line 4392

Quoted 5 lines
(quoted diff) +0 -1
  		cache_tag_unassign_domain(dmar_domain, FLPT_DEFAULT_DID, dev, pasid);
-		intel_svm_remove_dev_pasid(domain);
  	} else {
  		did = domain_id_iommu(dmar_domain, iommu);
  		cache_tag_unassign_domain(dmar_domain, did, dev, pasid);

It seems very strange that SVA has a different DID scheme, why is this? PASID and SVA should not be different at this layer.

The VT-d spec recommends that all SVA domains share a single domain ID. The PASID is unique to each SVA domain, hence the cache tags are unique. Currently, the Intel IOMMU driver assigns different domain IDs for all domains except the SVA type.

Quoted 8 lines

Sharing a domain ID is not specific to SVA. In general, for devices under a single IOMMU, domains with unique PASIDs can share the same domain ID.

In the long term (also on my task list), we will extend the cache tag code to support sharing domain IDs and remove the domain type check from the main code. This will also benefit the nesting case, where user domains nested on the same parent could share a domain ID.

Okay, that makes sense

Quoted 15 lines
drivers/iommu/intel/svm.c +5 -0
+static void intel_mm_free_notifier(struct mmu_notifier *mn)
+{
+       kfree(container_of(mn, struct dmar_domain, notifier));
+}
+
 static const struct mmu_notifier_ops intel_mmuops = {
        .release = intel_mm_release,
        .arch_invalidate_secondary_tlbs =

intel_arch_invalidate_secondary_tlbs,

(quoted diff) +1 -0
+       .free_notifier = intel_mm_free_notifier,
 };
 
 static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
@@ -598,10 +604,8 @@ static void intel_svm_domain_free(struct iommu_domain
 *domain)

Review static void intel_svm_domain_free(struct iommu_domain · line 610

Quoted 10 lines
(quoted diff) +2 -4
 {
        struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 
-       if (dmar_domain->notifier.ops)
-               mmu_notifier_unregister(&dmar_domain->notifier, domain->mm);
-
-       kfree(dmar_domain);
+       /* dmar_domain free is defered to the mmu free_notifier callback. */
+       mmu_notifier_put(&dmar_domain->notifier);
 }

Yeah, that is better.

Also you need to have mmu notifier call on module unload when using this scheme.

Jason

author maintainer
#23 lore raw

Re: [PATCH v2 12/12] iommu/vt-d: Retire struct intel_svm

Quoted 27 lines · Jason Gunthorpe
Quoted 15 lines
drivers/iommu/intel/svm.c +5 -0
+static void intel_mm_free_notifier(struct mmu_notifier *mn)
+{
+       kfree(container_of(mn, struct dmar_domain, notifier));
+}
+
  static const struct mmu_notifier_ops intel_mmuops = {
         .release = intel_mm_release,
         .arch_invalidate_secondary_tlbs =

intel_arch_invalidate_secondary_tlbs,

(quoted diff) +1 -0
+       .free_notifier = intel_mm_free_notifier,
  };
 
  static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
@@ -598,10 +604,8 @@ static void intel_svm_domain_free(struct iommu_domain
 *domain)

Review static void intel_svm_domain_free(struct iommu_domain · line 610

Quoted 10 lines
(quoted diff) +2 -4
  {
         struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 
-       if (dmar_domain->notifier.ops)
-               mmu_notifier_unregister(&dmar_domain->notifier, domain->mm);
-
-       kfree(dmar_domain);
+       /* dmar_domain free is defered to the mmu free_notifier callback. */
+       mmu_notifier_put(&dmar_domain->notifier);
  }

Yeah, that is better.

Quoted 2 lines

Also you need to have mmu notifier call on module unload when using this scheme.

The Intel IOMMU driver doesn't support being a module. It's always built-in.

Best regards,
baolu

#3 lore raw

RE: [PATCH v2 02/12] iommu/vt-d: Add cache tag invalidation helpers

In reply to Lu Baolu
Quoted 120 lines

-----Original Message-----
From: Lu Baolu <[email protected]>
Sent: Wednesday, April 10, 2024 10:09 AM
To: Joerg Roedel <[email protected]>; Will Deacon <[email protected]>; Robin Murphy <[email protected]>; Tian, Kevin <[email protected]>; Jason Gunthorpe <[email protected]>
Cc: Zhang, Tina <[email protected]>; Liu, Yi L <[email protected]>; [email protected]; [email protected]; Lu Baolu <[email protected]>
Subject: [PATCH v2 02/12] iommu/vt-d: Add cache tag invalidation helpers

Add several helpers to invalidate the caches after mappings in the affected domain are changed.

- cache_tag_flush_range() invalidates a range of caches after mappings within this range are changed. It uses the page-selective cache invalidation methods.

- cache_tag_flush_all() invalidates all caches tagged by a domain ID. It uses the domain-selective cache invalidation methods.

- cache_tag_flush_range_np() invalidates a range of caches when new mappings are created in the domain and the corresponding page table entries change from non-present to present.

---
 drivers/iommu/intel/iommu.h |  14 +++
 drivers/iommu/intel/cache.c | 195
++++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/iommu.c |  12 ---
 3 files changed, 209 insertions(+), 12 deletions(-)
drivers/iommu/intel/iommu.h +13 -0
index 6f6bffc60852..700574421b51 100644
@@ -35,6 +35,8 @@
 #define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
 #define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) &
 VTD_PAGE_MASK)
 
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
+
 #define VTD_STRIDE_SHIFT        (9)
 #define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
@@ -1041,6 +1043,13 @@ static inline void context_set_sm_pre(struct
 context_entry *context)
 	context->lo |= BIT_ULL(4);
 }
 
+/* Returns a number of VTD pages, but aligned to MM page size */ static
+inline unsigned long aligned_nrpages(unsigned long host_addr, size_t
+size) {
+	host_addr &= ~PAGE_MASK;
+	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; }
+
 /* Convert value to context PASID directory size field coding. */
 #define context_pdts(pds)	(((pds) & 0x7) << 9)
@@ -1116,6 +1125,11 @@ int cache_tag_assign_domain(struct
 dmar_domain *domain, u16 did,
 			    struct device *dev, ioasid_t pasid);  void
 cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,
 			       struct device *dev, ioasid_t pasid);
+void cache_tag_flush_range(struct dmar_domain *domain, unsigned long
 start,
+			   unsigned long end, int ih);
+void cache_tag_flush_all(struct dmar_domain *domain); void
+cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long
 start,
+			      unsigned long end);

#ifdef CONFIG_INTEL_IOMMU_SVM
void intel_svm_check(struct intel_iommu *iommu); diff --git
a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c index debbdaeff1c4..b2270dc8a765 100644

drivers/iommu/intel/cache.c +1 -0
@@ -12,6 +12,7 @@
 #include <linux/dmar.h>
 #include <linux/iommu.h>
 #include <linux/memory.h>
+#include <linux/pci.h>
 #include <linux/spinlock.h>
 
 #include "iommu.h"
@@ -194,3 +195,197 @@ void cache_tag_unassign_domain(struct
 dmar_domain *domain, u16 did,
 	if (domain->domain.type == IOMMU_DOMAIN_NESTED)
 		__cache_tag_unassign_parent_domain(domain->s2_domain,

did, dev, pasid); }

drivers/iommu/intel/cache.c +25 -0
+
+static unsigned long calculate_psi_aligned_address(unsigned long start,
+						   unsigned long end,
+						   unsigned long *_pages,
+						   unsigned long *_mask)
+{
+	unsigned long pages = aligned_nrpages(start, end - start + 1);
+	unsigned long aligned_pages = __roundup_pow_of_two(pages);
+	unsigned long bitmask = aligned_pages - 1;
+	unsigned long mask = ilog2(aligned_pages);
+	unsigned long pfn = IOVA_PFN(start);
+
+	/*
+	 * PSI masks the low order bits of the base address. If the
+	 * address isn't aligned to the mask, then compute a mask value
+	 * needed to ensure the target range is flushed.
+	 */
+	if (unlikely(bitmask & pfn)) {
+		unsigned long end_pfn = pfn + pages - 1, shared_bits;
+
+		/*
+		 * Since end_pfn <= pfn + bitmask, the only way bits
+		 * higher than bitmask can differ in pfn and end_pfn is
+		 * by carrying. This means after masking out bitmask,
+		 * high bits starting with the first set bit in

drivers/iommu/intel/cache.c void cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,

Quoted 10 lines
drivers/iommu/intel/cache.c +10 -0
+		 * shared_bits are all equal in both pfn and end_pfn.
+		 */
+		shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
+		mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
+	}
+
+	*_pages = aligned_pages;
+	*_mask = mask;
+
+	return ALIGN_DOWN(start, VTD_PAGE_SIZE); }

It's a good idea to use the above logic to calculate the appropriate mask for non-size-aligned page selective invalidation for all domains, including sva domain. Sounds like we plan to allow non-size-aligned page selection invalidation.

However, currently there are some places in the code which have the assumption that the size of the page selective invalidation should be aligned with the start address, a.k.a. only size-aligned page selective invalidation should happen and non-size-aligned one isn't expected.

One example is in qi_flush_dev_iotlb_pasid() and there is a checking:

	if (!IS_ALIGNED(addr, VTD_PAGE_SIZE << size_order)
		pr_warn_ratelimited(...)

If the non-size-aligned page selective invalidation is allowed, the warning message may come out which sounds confusing and impacts performance.

Another example is in qi_flush_piotlb() and there is a WARN_ON_ONCE() to remind user when non-size-aligned page selective invalidation is being used.

	If (WARN_ON_ONCE(!IS_ALIGNED(addr, align))
		...

So, can we consider removing the checking as well in this patch-set?

Regards,
-Tina

author maintainer
#4 lore raw

Re: [PATCH v2 02/12] iommu/vt-d: Add cache tag invalidation helpers

Quoted 136 lines · Tina
Quoted 119 lines

-----Original Message-----
From: Lu Baolu<[email protected]>
Sent: Wednesday, April 10, 2024 10:09 AM
To: Joerg Roedel<[email protected]>; Will Deacon<[email protected]>; Robin Murphy<[email protected]>; Tian, Kevin<[email protected]>; Jason Gunthorpe<[email protected]>
Cc: Zhang, Tina<[email protected]>; Liu, Yi L<[email protected]>; [email protected];[email protected]; Lu Baolu <[email protected]>
Subject: [PATCH v2 02/12] iommu/vt-d: Add cache tag invalidation helpers

Add several helpers to invalidate the caches after mappings in the affected domain are changed.

- cache_tag_flush_range() invalidates a range of caches after mappings within this range are changed. It uses the page-selective cache invalidation methods.

- cache_tag_flush_all() invalidates all caches tagged by a domain ID. It uses the domain-selective cache invalidation methods.

- cache_tag_flush_range_np() invalidates a range of caches when new mappings are created in the domain and the corresponding page table entries change from non-present to present.

---
  drivers/iommu/intel/iommu.h |  14 +++
  drivers/iommu/intel/cache.c | 195
++++++++++++++++++++++++++++++++++++
  drivers/iommu/intel/iommu.c |  12 ---
  3 files changed, 209 insertions(+), 12 deletions(-)
drivers/iommu/intel/iommu.h +13 -0
index 6f6bffc60852..700574421b51 100644
@@ -35,6 +35,8 @@
  #define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
  #define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) &
 VTD_PAGE_MASK)
 
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
+
  #define VTD_STRIDE_SHIFT        (9)
  #define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
@@ -1041,6 +1043,13 @@ static inline void context_set_sm_pre(struct
 context_entry *context)
  	context->lo |= BIT_ULL(4);
  }
 
+/* Returns a number of VTD pages, but aligned to MM page size */ static
+inline unsigned long aligned_nrpages(unsigned long host_addr, size_t
+size) {
+	host_addr &= ~PAGE_MASK;
+	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; }
+
  /* Convert value to context PASID directory size field coding. */
  #define context_pdts(pds)	(((pds) & 0x7) << 9)
@@ -1116,6 +1125,11 @@ int cache_tag_assign_domain(struct
 dmar_domain *domain, u16 did,
  			    struct device *dev, ioasid_t pasid);  void
 cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,
  			       struct device *dev, ioasid_t pasid);
+void cache_tag_flush_range(struct dmar_domain *domain, unsigned long
 start,
+			   unsigned long end, int ih);
+void cache_tag_flush_all(struct dmar_domain *domain); void
+cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long
 start,
+			      unsigned long end);

#ifdef CONFIG_INTEL_IOMMU_SVM
void intel_svm_check(struct intel_iommu *iommu); diff --git
a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c index debbdaeff1c4..b2270dc8a765 100644

drivers/iommu/intel/cache.c +1 -0
@@ -12,6 +12,7 @@
  #include <linux/dmar.h>
  #include <linux/iommu.h>
  #include <linux/memory.h>
+#include <linux/pci.h>
  #include <linux/spinlock.h>
 
  #include "iommu.h"
@@ -194,3 +195,197 @@ void cache_tag_unassign_domain(struct
 dmar_domain *domain, u16 did,
  	if (domain->domain.type == IOMMU_DOMAIN_NESTED)
  		__cache_tag_unassign_parent_domain(domain->s2_domain,

did, dev, pasid); }

drivers/iommu/intel/cache.c +25 -0
+
+static unsigned long calculate_psi_aligned_address(unsigned long start,
+						   unsigned long end,
+						   unsigned long *_pages,
+						   unsigned long *_mask)
+{
+	unsigned long pages = aligned_nrpages(start, end - start + 1);
+	unsigned long aligned_pages = __roundup_pow_of_two(pages);
+	unsigned long bitmask = aligned_pages - 1;
+	unsigned long mask = ilog2(aligned_pages);
+	unsigned long pfn = IOVA_PFN(start);
+
+	/*
+	 * PSI masks the low order bits of the base address. If the
+	 * address isn't aligned to the mask, then compute a mask value
+	 * needed to ensure the target range is flushed.
+	 */
+	if (unlikely(bitmask & pfn)) {
+		unsigned long end_pfn = pfn + pages - 1, shared_bits;
+
+		/*
+		 * Since end_pfn <= pfn + bitmask, the only way bits
+		 * higher than bitmask can differ in pfn and end_pfn is
+		 * by carrying. This means after masking out bitmask,
+		 * high bits starting with the first set bit in

drivers/iommu/intel/cache.c void cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,

Quoted 10 lines
drivers/iommu/intel/cache.c +10 -0
+		 * shared_bits are all equal in both pfn and end_pfn.
+		 */
+		shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
+		mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
+	}
+
+	*_pages = aligned_pages;
+	*_mask = mask;
+
+	return ALIGN_DOWN(start, VTD_PAGE_SIZE); }

It's a good idea to use the above logic to calculate the appropriate mask for non-size-aligned page selective invalidation for all domains, including sva domain. Sounds like we plan to allow non-size-aligned page selection invalidation.

However, currently there are some places in the code which have the assumption that the size of the page selective invalidation should be aligned with the start address, a.k.a. only size-aligned page selective invalidation should happen and non-size-aligned one isn't expected.

One example is in qi_flush_dev_iotlb_pasid() and there is a checking:

	if (!IS_ALIGNED(addr, VTD_PAGE_SIZE << size_order)
		pr_warn_ratelimited(...)
Quoted 7 lines

If the non-size-aligned page selective invalidation is allowed, the warning message may come out which sounds confusing and impacts performance.

Another example is in qi_flush_piotlb() and there is a WARN_ON_ONCE() to remind user when non-size-aligned page selective invalidation is being used.

	If (WARN_ON_ONCE(!IS_ALIGNED(addr, align))
		...

So, can we consider removing the checking as well in this patch-set?

This series doesn't intend to change the driver's behavior, so the check and warning you mentioned should be kept. The iommu core ensures the invalidation size is page-size aligned. Those checks in the iommu driver just make sure that the callers are doing things right.

Best regards,
baolu

#5 lore raw

RE: [PATCH v2 02/12] iommu/vt-d: Add cache tag invalidation helpers

Quoted 168 lines

-----Original Message-----
From: Baolu Lu <[email protected]>
Sent: Monday, April 15, 2024 1:07 PM
To: Zhang, Tina <[email protected]>; Joerg Roedel <[email protected]>; Will Deacon <[email protected]>; Robin Murphy <[email protected]>; Tian, Kevin <[email protected]>; Jason Gunthorpe <[email protected]>
Cc: [email protected]; Liu, Yi L <[email protected]>; [email protected]; [email protected]
Subject: Re: [PATCH v2 02/12] iommu/vt-d: Add cache tag invalidation helpers

Quoted 35 lines · Tina
Quoted 35 lines

-----Original Message-----
From: Lu Baolu<[email protected]>
Sent: Wednesday, April 10, 2024 10:09 AM
To: Joerg Roedel<[email protected]>; Will Deacon<[email protected]>; Robin Murphy<[email protected]>; Tian, Kevin<[email protected]>; Jason Gunthorpe<[email protected]>
Cc: Zhang, Tina<[email protected]>; Liu, Yi L<[email protected]>; [email protected];[email protected]; Lu Baolu <[email protected]>
Subject: [PATCH v2 02/12] iommu/vt-d: Add cache tag invalidation helpers

Add several helpers to invalidate the caches after mappings in the affected domain are changed.

- cache_tag_flush_range() invalidates a range of caches after mappings within this range are changed. It uses the page-selective cache invalidation methods.

- cache_tag_flush_all() invalidates all caches tagged by a domain ID. It uses the domain-selective cache invalidation methods.

- cache_tag_flush_range_np() invalidates a range of caches when new mappings are created in the domain and the corresponding page table entries change from non-present to present.

---
  drivers/iommu/intel/iommu.h |  14 +++
  drivers/iommu/intel/cache.c | 195
++++++++++++++++++++++++++++++++++++
  drivers/iommu/intel/iommu.c |  12 ---
  3 files changed, 209 insertions(+), 12 deletions(-)
Quoted 2 lines
Quoted 2 lines
(quoted diff) +0 -0

b/drivers/iommu/intel/iommu.h index 6f6bffc60852..700574421b51

100644

Quoted 27 lines
Quoted 27 lines
drivers/iommu/intel/iommu.h +9 -0
@@ -35,6 +35,8 @@
  #define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
  #define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) &
 VTD_PAGE_MASK)
 
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
+
  #define VTD_STRIDE_SHIFT        (9)
  #define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
@@ -1041,6 +1043,13 @@ static inline void context_set_sm_pre(struct
 context_entry *context)
  	context->lo |= BIT_ULL(4);
  }
 
+/* Returns a number of VTD pages, but aligned to MM page size */
+static inline unsigned long aligned_nrpages(unsigned long host_addr,
+size_t
+size) {
+	host_addr &= ~PAGE_MASK;
+	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; }
+
  /* Convert value to context PASID directory size field coding. */
  #define context_pdts(pds)	(((pds) & 0x7) << 9)
Quoted 1 line

drivers/iommu/intel/iommu.h int cache_tag_assign_domain(struct

Quoted 1 line
drivers/iommu/intel/iommu.h +0 -0
@@ -1116,6 +1125,11 @@ int cache_tag_assign_domain(struct

dmar_domain

Quoted 59 lines
Quoted 59 lines
drivers/iommu/intel/iommu.h +5 -0
 *domain, u16 did,
  			    struct device *dev, ioasid_t pasid);  void
 cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,
  			       struct device *dev, ioasid_t pasid);
+void cache_tag_flush_range(struct dmar_domain *domain, unsigned long
 start,
+			   unsigned long end, int ih);
+void cache_tag_flush_all(struct dmar_domain *domain); void
+cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long
 start,
+			      unsigned long end);

#ifdef CONFIG_INTEL_IOMMU_SVM
void intel_svm_check(struct intel_iommu *iommu); diff --git
a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c index debbdaeff1c4..b2270dc8a765 100644

drivers/iommu/intel/cache.c +1 -0
@@ -12,6 +12,7 @@
  #include <linux/dmar.h>
  #include <linux/iommu.h>
  #include <linux/memory.h>
+#include <linux/pci.h>
  #include <linux/spinlock.h>
 
  #include "iommu.h"
@@ -194,3 +195,197 @@ void cache_tag_unassign_domain(struct
 dmar_domain *domain, u16 did,
  	if (domain->domain.type == IOMMU_DOMAIN_NESTED)
  		__cache_tag_unassign_parent_domain(domain->s2_domain,

did, dev, pasid); }

drivers/iommu/intel/cache.c +28 -0
+
+static unsigned long calculate_psi_aligned_address(unsigned long start,
+						   unsigned long end,
+						   unsigned long *_pages,
+						   unsigned long *_mask)
+{
+	unsigned long pages = aligned_nrpages(start, end - start + 1);
+	unsigned long aligned_pages = __roundup_pow_of_two(pages);
+	unsigned long bitmask = aligned_pages - 1;
+	unsigned long mask = ilog2(aligned_pages);
+	unsigned long pfn = IOVA_PFN(start);
+
+	/*
+	 * PSI masks the low order bits of the base address. If the
+	 * address isn't aligned to the mask, then compute a mask value
+	 * needed to ensure the target range is flushed.
+	 */
+	if (unlikely(bitmask & pfn)) {
+		unsigned long end_pfn = pfn + pages - 1, shared_bits;
+
+		/*
+		 * Since end_pfn <= pfn + bitmask, the only way bits
+		 * higher than bitmask can differ in pfn and end_pfn is
+		 * by carrying. This means after masking out bitmask,
+		 * high bits starting with the first set bit in
+		 * shared_bits are all equal in both pfn and end_pfn.
+		 */
+		shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
Quoted 8 lines

drivers/iommu/intel/cache.c void cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,

Quoted 7 lines
drivers/iommu/intel/cache.c +7 -0
+		mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
+	}
+
+	*_pages = aligned_pages;
+	*_mask = mask;
+
+	return ALIGN_DOWN(start, VTD_PAGE_SIZE); }

It's a good idea to use the above logic to calculate the appropriate mask for

non-size-aligned page selective invalidation for all domains, including sva domain. Sounds like we plan to allow non-size-aligned page selection invalidation.

Quoted 2 lines

However, currently there are some places in the code which have the

assumption that the size of the page selective invalidation should be aligned with the start address, a.k.a. only size-aligned page selective invalidation should happen and non-size-aligned one isn't expected.

Quoted 5 lines

One example is in qi_flush_dev_iotlb_pasid() and there is a checking:

	if (!IS_ALIGNED(addr, VTD_PAGE_SIZE << size_order)
		pr_warn_ratelimited(...)

If the non-size-aligned page selective invalidation is allowed, the warning

message may come out which sounds confusing and impacts performance.

Quoted 2 lines

Another example is in qi_flush_piotlb() and there is a WARN_ON_ONCE() to

remind user when non-size-aligned page selective invalidation is being used.

Quoted 3 lines
	If (WARN_ON_ONCE(!IS_ALIGNED(addr, align))
		...
Quoted 6 lines
Quoted 1 line

So, can we consider removing the checking as well in this patch-set?

This series doesn't intend to change the driver's behavior, so the check and warning you mentioned should be kept. The iommu core ensures the invalidation size is page-size aligned. Those checks in the iommu driver just make sure that the callers are doing things right.

The fact is this patch aims to allow non-size-aligned page selective invalidation which aren't expected by those warning messages.

So, either we disable use non-size-aligned page selective invalidation just like what we did previously for sva domain, or we remove those warning messages and use non-size-aligned page selective invalidation introduced in this patch for sva domain.

Regards,
-Tina

Quoted 3 lines

Best regards,
baolu