[PATCH 00/19] [PULL REQUEST] Intel IOMMU updates for v6.13

[PATCH 00/19] [PULL REQUEST] Intel IOMMU updates for v6.13

[Lu Baolu]

Hi Joerg,

The following changes have been queued for v6.13-rc1. They are about new
features and code refactoring, including:

 - Add domain_alloc_paging support
 - Enable user space IOPFs in non-PASID and non-svm cases
 - Small code refactoring and cleanups

These patches are based on v6.12-rc6. The complete patches are also
available at:

https://github.com/LuBaolu/intel-iommu/commits/vtd-update-for-v6.13

Please consider them for iommu next.

Best regards,
baolu

Andy Shevchenko (1):
  iommu/vt-d: Increase buffer size for device name

Dr. David Alan Gilbert (1):
  iommu/vt-d: Remove unused dmar_msi_read

Jinjie Ruan (1):
  iommu/vt-d: Use PCI_DEVID() macro

Joel Granados (3):
  iommu/vt-d: Separate page request queue from SVM
  iommu/vt-d: Move IOMMU_IOPF into INTEL_IOMMU
  iommufd: Enable PRI when doing the iommufd_hwpt_alloc

Klaus Jensen (2):
  iommu/vt-d: Remove the pasid present check in prq_event_thread
  iommu/vt-d: Drop pasid requirement for prq initialization

Lu Baolu (8):
  iommu/vt-d: Add domain_alloc_paging support
  iommu/vt-d: Remove unused domain_alloc callback
  iommu/vt-d: Enhance compatibility check for paging domain attach
  iommu/vt-d: Remove domain_update_iommu_cap()
  iommu/vt-d: Remove domain_update_iommu_superpage()
  iommu/vt-d: Refactor first_level_by_default()
  iommu/vt-d: Refine intel_iommu_domain_alloc_user()
  iommu/vt-d: Drain PRQs when domain removed from RID

Yi Liu (1):
  iommu/vt-d: Drop s1_pgtbl from dmar_domain

Zhenzhong Duan (2):
  iommu/vt-d: Fix checks and print in dmar_fault_dump_ptes()
  iommu/vt-d: Fix checks and print in pgtable_walk()

 drivers/iommu/intel/Kconfig          |   2 +-
 drivers/iommu/intel/Makefile         |   2 +-
 drivers/iommu/intel/dmar.c           |  15 +-
 drivers/iommu/intel/iommu.c          | 404 +++++++--------------------
 drivers/iommu/intel/iommu.h          |  22 +-
 drivers/iommu/intel/irq_remapping.c  |   4 +-
 drivers/iommu/intel/nested.c         |   3 +-
 drivers/iommu/intel/pasid.c          |  34 +--
 drivers/iommu/intel/prq.c            | 396 ++++++++++++++++++++++++++
 drivers/iommu/intel/svm.c            | 397 --------------------------
 drivers/iommu/iommufd/hw_pagetable.c |   3 +-
 include/linux/dmar.h                 |   1 -
 12 files changed, 517 insertions(+), 766 deletions(-)
 create mode 100644 drivers/iommu/intel/prq.c

-- 
2.43.0

[PATCH 01/19] iommu/vt-d: Add domain_alloc_paging support

[Lu Baolu]

Add the domain_alloc_paging callback for domain allocation using the
iommu_paging_domain_alloc() interface.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241021085125.192333-2-baolu.lu@linux.intel.com
---
 drivers/iommu/intel/iommu.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index e860bc9439a2..0d2237b55b6b 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4592,6 +4592,19 @@ static struct iommu_domain identity_domain = {
 	},
 };
 
+static struct iommu_domain *intel_iommu_domain_alloc_paging(struct device *dev)
+{
+	struct dmar_domain *dmar_domain;
+	bool first_stage;
+
+	first_stage = first_level_by_default(0);
+	dmar_domain = paging_domain_alloc(dev, first_stage);
+	if (IS_ERR(dmar_domain))
+		return ERR_CAST(dmar_domain);
+
+	return &dmar_domain->domain;
+}
+
 const struct iommu_ops intel_iommu_ops = {
 	.blocked_domain		= &blocking_domain,
 	.release_domain		= &blocking_domain,
@@ -4601,6 +4614,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.domain_alloc		= intel_iommu_domain_alloc,
 	.domain_alloc_user	= intel_iommu_domain_alloc_user,
 	.domain_alloc_sva	= intel_svm_domain_alloc,
+	.domain_alloc_paging	= intel_iommu_domain_alloc_paging,
 	.probe_device		= intel_iommu_probe_device,
 	.release_device		= intel_iommu_release_device,
 	.get_resv_regions	= intel_iommu_get_resv_regions,
-- 
2.43.0

[PATCH 02/19] iommu/vt-d: Remove unused domain_alloc callback

[Lu Baolu]

With domain_alloc_paging callback supported, the legacy domain_alloc
callback will never be used anymore. Remove it to avoid dead code.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241021085125.192333-3-baolu.lu@linux.intel.com
---
 drivers/iommu/intel/iommu.c | 90 -------------------------------------
 1 file changed, 90 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 0d2237b55b6b..204e624b3f9a 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1454,27 +1454,6 @@ static bool first_level_by_default(unsigned int type)
 	return type != IOMMU_DOMAIN_UNMANAGED;
 }
 
-static struct dmar_domain *alloc_domain(unsigned int type)
-{
-	struct dmar_domain *domain;
-
-	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
-	if (!domain)
-		return NULL;
-
-	domain->nid = NUMA_NO_NODE;
-	if (first_level_by_default(type))
-		domain->use_first_level = true;
-	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;
-}
-
 int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 {
 	struct iommu_domain_info *info, *curr;
@@ -1546,20 +1525,6 @@ void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 	spin_unlock(&iommu->lock);
 }
 
-static int guestwidth_to_adjustwidth(int gaw)
-{
-	int agaw;
-	int r = (gaw - 12) % 9;
-
-	if (r == 0)
-		agaw = gaw;
-	else
-		agaw = gaw + 9 - r;
-	if (agaw > 64)
-		agaw = 64;
-	return agaw;
-}
-
 static void domain_exit(struct dmar_domain *domain)
 {
 	if (domain->pgd) {
@@ -3381,27 +3346,6 @@ void device_block_translation(struct device *dev)
 	info->domain = NULL;
 }
 
-static int md_domain_init(struct dmar_domain *domain, int guest_width)
-{
-	int adjust_width;
-
-	/* calculate AGAW */
-	domain->gaw = guest_width;
-	adjust_width = guestwidth_to_adjustwidth(guest_width);
-	domain->agaw = width_to_agaw(adjust_width);
-
-	domain->iommu_coherency = false;
-	domain->iommu_superpage = 0;
-	domain->max_addr = 0;
-
-	/* always allocate the top pgd */
-	domain->pgd = iommu_alloc_page_node(domain->nid, GFP_ATOMIC);
-	if (!domain->pgd)
-		return -ENOMEM;
-	domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
-	return 0;
-}
-
 static int blocking_domain_attach_dev(struct iommu_domain *domain,
 				      struct device *dev)
 {
@@ -3488,39 +3432,6 @@ static struct dmar_domain *paging_domain_alloc(struct device *dev, bool first_st
 	return domain;
 }
 
-static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
-{
-	struct dmar_domain *dmar_domain;
-	struct iommu_domain *domain;
-
-	switch (type) {
-	case IOMMU_DOMAIN_DMA:
-	case IOMMU_DOMAIN_UNMANAGED:
-		dmar_domain = alloc_domain(type);
-		if (!dmar_domain) {
-			pr_err("Can't allocate dmar_domain\n");
-			return NULL;
-		}
-		if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
-			pr_err("Domain initialization failed\n");
-			domain_exit(dmar_domain);
-			return NULL;
-		}
-
-		domain = &dmar_domain->domain;
-		domain->geometry.aperture_start = 0;
-		domain->geometry.aperture_end   =
-				__DOMAIN_MAX_ADDR(dmar_domain->gaw);
-		domain->geometry.force_aperture = true;
-
-		return domain;
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
 static struct iommu_domain *
 intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 			      struct iommu_domain *parent,
@@ -4611,7 +4522,6 @@ const struct iommu_ops intel_iommu_ops = {
 	.identity_domain	= &identity_domain,
 	.capable		= intel_iommu_capable,
 	.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,
 	.domain_alloc_paging	= intel_iommu_domain_alloc_paging,
-- 
2.43.0

[PATCH 03/19] iommu/vt-d: Enhance compatibility check for paging domain attach

[Lu Baolu]

The driver now supports domain_alloc_paging, ensuring that a valid device
pointer is provided whenever a paging domain is allocated. Additionally,
the dmar_domain attributes are set up at the time of allocation.

Consistent with the established semantics in the IOMMU core, if a domain is
attached to a device and found to be incompatible with the IOMMU hardware
capabilities, the operation will return an -EINVAL error. This implicitly
advises the caller to allocate a new domain for the device and attempt the
domain attachment again.

Rename prepare_domain_attach_device() to a more meaningful name.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241021085125.192333-4-baolu.lu@linux.intel.com
---
 drivers/iommu/intel/iommu.c  | 70 ++++++++++++------------------------
 drivers/iommu/intel/iommu.h  |  3 +-
 drivers/iommu/intel/nested.c |  2 +-
 drivers/iommu/intel/pasid.c  | 28 +--------------
 4 files changed, 26 insertions(+), 77 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 204e624b3f9a..0fca84ac6794 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1606,7 +1606,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	int translation = CONTEXT_TT_MULTI_LEVEL;
 	struct dma_pte *pgd = domain->pgd;
 	struct context_entry *context;
-	int agaw, ret;
+	int ret;
 
 	pr_debug("Set context mapping for %02x:%02x.%d\n",
 		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
@@ -1623,27 +1623,15 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 
 	copied_context_tear_down(iommu, context, bus, devfn);
 	context_clear_entry(context);
-
 	context_set_domain_id(context, did);
 
-	/*
-	 * Skip top levels of page tables for iommu which has
-	 * less agaw than default. Unnecessary for PT mode.
-	 */
-	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
-		ret = -ENOMEM;
-		pgd = phys_to_virt(dma_pte_addr(pgd));
-		if (!dma_pte_present(pgd))
-			goto out_unlock;
-	}
-
 	if (info && info->ats_supported)
 		translation = CONTEXT_TT_DEV_IOTLB;
 	else
 		translation = CONTEXT_TT_MULTI_LEVEL;
 
 	context_set_address_root(context, virt_to_phys(pgd));
-	context_set_address_width(context, agaw);
+	context_set_address_width(context, domain->agaw);
 	context_set_translation_type(context, translation);
 	context_set_fault_enable(context);
 	context_set_present(context);
@@ -1876,20 +1864,9 @@ static int domain_setup_first_level(struct intel_iommu *iommu,
 				    u32 pasid)
 {
 	struct dma_pte *pgd = domain->pgd;
-	int agaw, level;
-	int flags = 0;
+	int level, flags = 0;
 
-	/*
-	 * Skip top levels of page tables for iommu which has
-	 * less agaw than default. Unnecessary for PT mode.
-	 */
-	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
-		pgd = phys_to_virt(dma_pte_addr(pgd));
-		if (!dma_pte_present(pgd))
-			return -ENOMEM;
-	}
-
-	level = agaw_to_level(agaw);
+	level = agaw_to_level(domain->agaw);
 	if (level != 4 && level != 5)
 		return -EINVAL;
 
@@ -3494,42 +3471,41 @@ static void intel_iommu_domain_free(struct iommu_domain *domain)
 	domain_exit(dmar_domain);
 }
 
-int prepare_domain_attach_device(struct iommu_domain *domain,
-				 struct device *dev)
+int paging_domain_compatible(struct iommu_domain *domain, struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct intel_iommu *iommu = info->iommu;
 	int addr_width;
 
+	if (WARN_ON_ONCE(!(domain->type & __IOMMU_DOMAIN_PAGING)))
+		return -EPERM;
+
 	if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap))
 		return -EINVAL;
 
 	if (domain->dirty_ops && !ssads_supported(iommu))
 		return -EINVAL;
 
+	if (dmar_domain->iommu_coherency !=
+			iommu_paging_structure_coherency(iommu))
+		return -EINVAL;
+
+	if (dmar_domain->iommu_superpage !=
+			iommu_superpage_capability(iommu, dmar_domain->use_first_level))
+		return -EINVAL;
+
+	if (dmar_domain->use_first_level &&
+	    (!sm_supported(iommu) || !ecap_flts(iommu->ecap)))
+		return -EINVAL;
+
 	/* check if this iommu agaw is sufficient for max mapped address */
 	addr_width = agaw_to_width(iommu->agaw);
 	if (addr_width > cap_mgaw(iommu->cap))
 		addr_width = cap_mgaw(iommu->cap);
 
-	if (dmar_domain->max_addr > (1LL << addr_width))
+	if (dmar_domain->gaw > addr_width || dmar_domain->agaw > iommu->agaw)
 		return -EINVAL;
-	dmar_domain->gaw = addr_width;
-
-	/*
-	 * Knock out extra levels of page tables if necessary
-	 */
-	while (iommu->agaw < dmar_domain->agaw) {
-		struct dma_pte *pte;
-
-		pte = dmar_domain->pgd;
-		if (dma_pte_present(pte)) {
-			dmar_domain->pgd = phys_to_virt(dma_pte_addr(pte));
-			iommu_free_page(pte);
-		}
-		dmar_domain->agaw--;
-	}
 
 	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev) &&
 	    context_copied(iommu, info->bus, info->devfn))
@@ -3545,7 +3521,7 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 
 	device_block_translation(dev);
 
-	ret = prepare_domain_attach_device(domain, dev);
+	ret = paging_domain_compatible(domain, dev);
 	if (ret)
 		return ret;
 
@@ -4216,7 +4192,7 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 	if (context_copied(iommu, info->bus, info->devfn))
 		return -EBUSY;
 
-	ret = prepare_domain_attach_device(domain, dev);
+	ret = paging_domain_compatible(domain, dev);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 1497f3112b12..b1928ca3aaa8 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -1230,8 +1230,7 @@ void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void device_block_translation(struct device *dev);
-int prepare_domain_attach_device(struct iommu_domain *domain,
-				 struct device *dev);
+int paging_domain_compatible(struct iommu_domain *domain, struct device *dev);
 void domain_update_iommu_cap(struct dmar_domain *domain);
 
 int dmar_ir_support(void);
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index 433c58944401..96016bc40f94 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -40,7 +40,7 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 	 * The s2_domain will be used in nested translation, hence needs
 	 * to ensure the s2_domain is compatible with this IOMMU.
 	 */
-	ret = prepare_domain_attach_device(&dmar_domain->s2_domain->domain, dev);
+	ret = paging_domain_compatible(&dmar_domain->s2_domain->domain, dev);
 	if (ret) {
 		dev_err_ratelimited(dev, "s2 domain is not compatible\n");
 		return ret;
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 2e5fa0a23299..53157e1194f4 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -345,25 +345,6 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	return 0;
 }
 
-/*
- * Skip top levels of page tables for iommu which has less agaw
- * than default. Unnecessary for PT mode.
- */
-static int iommu_skip_agaw(struct dmar_domain *domain,
-			   struct intel_iommu *iommu,
-			   struct dma_pte **pgd)
-{
-	int agaw;
-
-	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
-		*pgd = phys_to_virt(dma_pte_addr(*pgd));
-		if (!dma_pte_present(*pgd))
-			return -EINVAL;
-	}
-
-	return agaw;
-}
-
 /*
  * Set up the scalable mode pasid entry for second only translation type.
  */
@@ -374,7 +355,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	struct pasid_entry *pte;
 	struct dma_pte *pgd;
 	u64 pgd_val;
-	int agaw;
 	u16 did;
 
 	/*
@@ -388,12 +368,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	}
 
 	pgd = domain->pgd;
-	agaw = iommu_skip_agaw(domain, iommu, &pgd);
-	if (agaw < 0) {
-		dev_err(dev, "Invalid domain page table\n");
-		return -EINVAL;
-	}
-
 	pgd_val = virt_to_phys(pgd);
 	did = domain_id_iommu(domain, iommu);
 
@@ -412,7 +386,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	pasid_clear_entry(pte);
 	pasid_set_domain_id(pte, did);
 	pasid_set_slptr(pte, pgd_val);
-	pasid_set_address_width(pte, agaw);
+	pasid_set_address_width(pte, domain->agaw);
 	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY);
 	pasid_set_fault_enable(pte);
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
-- 
2.43.0

[PATCH 04/19] iommu/vt-d: Remove domain_update_iommu_cap()

[Lu Baolu]

The attributes of a paging domain are initialized during the allocation
process, and any attempt to attach a domain that is not compatible will
result in a failure. Therefore, there is no need to update the domain
attributes at the time of domain attachment.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241021085125.192333-5-baolu.lu@linux.intel.com
---
 drivers/iommu/intel/iommu.c | 83 -------------------------------------
 drivers/iommu/intel/iommu.h |  1 -
 2 files changed, 84 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 0fca84ac6794..d148274e7135 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -352,36 +352,6 @@ static bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
 			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
 }
 
-static void domain_update_iommu_coherency(struct dmar_domain *domain)
-{
-	struct iommu_domain_info *info;
-	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
-	bool found = false;
-	unsigned long i;
-
-	domain->iommu_coherency = true;
-	xa_for_each(&domain->iommu_array, i, info) {
-		found = true;
-		if (!iommu_paging_structure_coherency(info->iommu)) {
-			domain->iommu_coherency = false;
-			break;
-		}
-	}
-	if (found)
-		return;
-
-	/* No hardware attached; use lowest common denominator */
-	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd) {
-		if (!iommu_paging_structure_coherency(iommu)) {
-			domain->iommu_coherency = false;
-			break;
-		}
-	}
-	rcu_read_unlock();
-}
-
 static int domain_update_iommu_superpage(struct dmar_domain *domain,
 					 struct intel_iommu *skip)
 {
@@ -412,29 +382,6 @@ static int domain_update_iommu_superpage(struct dmar_domain *domain,
 	return fls(mask);
 }
 
-static int domain_update_device_node(struct dmar_domain *domain)
-{
-	struct device_domain_info *info;
-	int nid = NUMA_NO_NODE;
-	unsigned long flags;
-
-	spin_lock_irqsave(&domain->lock, flags);
-	list_for_each_entry(info, &domain->devices, link) {
-		/*
-		 * There could possibly be multiple device numa nodes as devices
-		 * within the same domain may sit behind different IOMMUs. There
-		 * isn't perfect answer in such situation, so we select first
-		 * come first served policy.
-		 */
-		nid = dev_to_node(info->dev);
-		if (nid != NUMA_NO_NODE)
-			break;
-	}
-	spin_unlock_irqrestore(&domain->lock, flags);
-
-	return nid;
-}
-
 /* Return the super pagesize bitmap if supported. */
 static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
 {
@@ -452,34 +399,6 @@ static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
 	return bitmap;
 }
 
-/* Some capabilities may be different across iommus */
-void domain_update_iommu_cap(struct dmar_domain *domain)
-{
-	domain_update_iommu_coherency(domain);
-	domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
-
-	/*
-	 * If RHSA is missing, we should default to the device numa domain
-	 * as fall back.
-	 */
-	if (domain->nid == NUMA_NO_NODE)
-		domain->nid = domain_update_device_node(domain);
-
-	/*
-	 * First-level translation restricts the input-address to a
-	 * canonical address (i.e., address bits 63:N have the same
-	 * value as address bit [N-1], where N is 48-bits with 4-level
-	 * paging and 57-bits with 5-level paging). Hence, skip bit
-	 * [N-1].
-	 */
-	if (domain->use_first_level)
-		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw - 1);
-	else
-		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw);
-
-	domain->domain.pgsize_bitmap |= domain_super_pgsize_bitmap(domain);
-}
-
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 					 u8 devfn, int alloc)
 {
@@ -1493,7 +1412,6 @@ int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 		ret = xa_err(curr) ? : -EBUSY;
 		goto err_clear;
 	}
-	domain_update_iommu_cap(domain);
 
 	spin_unlock(&iommu->lock);
 	return 0;
@@ -1519,7 +1437,6 @@ void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 		clear_bit(info->did, iommu->domain_ids);
 		xa_erase(&domain->iommu_array, iommu->seq_id);
 		domain->nid = NUMA_NO_NODE;
-		domain_update_iommu_cap(domain);
 		kfree(info);
 	}
 	spin_unlock(&iommu->lock);
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index b1928ca3aaa8..f9fba9a26dac 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -1231,7 +1231,6 @@ int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void device_block_translation(struct device *dev);
 int paging_domain_compatible(struct iommu_domain *domain, struct device *dev);
-void domain_update_iommu_cap(struct dmar_domain *domain);
 
 int dmar_ir_support(void);
 
-- 
2.43.0

[PATCH 05/19] iommu/vt-d: Remove domain_update_iommu_superpage()

[Lu Baolu]

The requirement for consistent super page support across all the IOMMU
hardware in the system has been removed. In the past, if a new IOMMU
was hot-added and lacked consistent super page capability, the hot-add
process would be aborted. However, with the updated attachment semantics,
it is now permissible for the super page capability to vary among
different IOMMU hardware units.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241021085125.192333-6-baolu.lu@linux.intel.com
---
 drivers/iommu/intel/iommu.c | 39 +------------------------------------
 1 file changed, 1 insertion(+), 38 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index d148274e7135..f6dc83c26fa5 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -352,36 +352,6 @@ static bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
 			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
 }
 
-static int domain_update_iommu_superpage(struct dmar_domain *domain,
-					 struct intel_iommu *skip)
-{
-	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
-	int mask = 0x3;
-
-	if (!intel_iommu_superpage)
-		return 0;
-
-	/* set iommu_superpage to the smallest common denominator */
-	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd) {
-		if (iommu != skip) {
-			if (domain && domain->use_first_level) {
-				if (!cap_fl1gp_support(iommu->cap))
-					mask = 0x1;
-			} else {
-				mask &= cap_super_page_val(iommu->cap);
-			}
-
-			if (!mask)
-				break;
-		}
-	}
-	rcu_read_unlock();
-
-	return fls(mask);
-}
-
 /* Return the super pagesize bitmap if supported. */
 static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
 {
@@ -2605,20 +2575,13 @@ int dmar_parse_one_satc(struct acpi_dmar_header *hdr, void *arg)
 
 static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 {
-	int sp, ret;
 	struct intel_iommu *iommu = dmaru->iommu;
+	int ret;
 
 	ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_DMAR, iommu);
 	if (ret)
 		goto out;
 
-	sp = domain_update_iommu_superpage(NULL, iommu) - 1;
-	if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
-		pr_warn("%s: Doesn't support large page.\n",
-			iommu->name);
-		return -ENXIO;
-	}
-
 	/*
 	 * Disable translation if already enabled prior to OS handover.
 	 */
-- 
2.43.0

[PATCH 06/19] iommu/vt-d: Refactor first_level_by_default()

[Lu Baolu]

The first stage page table is compatible across host and guest kernels.
Therefore, this driver uses the first stage page table as the default for
paging domains.

The helper first_level_by_default() determines the feasibility of using
the first stage page table based on a global policy. This policy requires
consistency in scalable mode and first stage translation capability among
all iommu units. However, this is unnecessary as domain allocation,
attachment, and removal operations are performed on a per-device basis.

The domain type (IOMMU_DOMAIN_DMA vs. IOMMU_DOMAIN_UNMANAGED) should not
be a factor in determining the first stage page table usage. Both types
are for paging domains, and there's no fundamental difference between them.
The driver should not be aware of this distinction unless the core
specifies allocation flags that require special handling.

Convert first_level_by_default() from global to per-iommu and remove the
'type' input.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241021085125.192333-7-baolu.lu@linux.intel.com
---
 drivers/iommu/intel/iommu.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index f6dc83c26fa5..ebdb97835fc3 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1329,18 +1329,17 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
  * Check and return whether first level is used by default for
  * DMA translation.
  */
-static bool first_level_by_default(unsigned int type)
+static bool first_level_by_default(struct intel_iommu *iommu)
 {
 	/* Only SL is available in legacy mode */
-	if (!scalable_mode_support())
+	if (!sm_supported(iommu))
 		return false;
 
 	/* Only level (either FL or SL) is available, just use it */
-	if (intel_cap_flts_sanity() ^ intel_cap_slts_sanity())
-		return intel_cap_flts_sanity();
+	if (ecap_flts(iommu->ecap) ^ ecap_slts(iommu->ecap))
+		return ecap_flts(iommu->ecap);
 
-	/* Both levels are available, decide it based on domain type */
-	return type != IOMMU_DOMAIN_UNMANAGED;
+	return true;
 }
 
 int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
@@ -3110,7 +3109,7 @@ int __init intel_iommu_init(void)
 		 * the virtual and physical IOMMU page-tables.
 		 */
 		if (cap_caching_mode(iommu->cap) &&
-		    !first_level_by_default(IOMMU_DOMAIN_DMA)) {
+		    !first_level_by_default(iommu)) {
 			pr_info_once("IOMMU batching disallowed due to virtualization\n");
 			iommu_set_dma_strict();
 		}
@@ -4361,10 +4360,12 @@ static struct iommu_domain identity_domain = {
 
 static struct iommu_domain *intel_iommu_domain_alloc_paging(struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
 	struct dmar_domain *dmar_domain;
 	bool first_stage;
 
-	first_stage = first_level_by_default(0);
+	first_stage = first_level_by_default(iommu);
 	dmar_domain = paging_domain_alloc(dev, first_stage);
 	if (IS_ERR(dmar_domain))
 		return ERR_CAST(dmar_domain);
-- 
2.43.0

[PATCH 07/19] iommu/vt-d: Refine intel_iommu_domain_alloc_user()

[Lu Baolu]

The domain_alloc_user ops should always allocate a guest-compatible page
table unless specific allocation flags are specified.

Currently, IOMMU_HWPT_ALLOC_NEST_PARENT and IOMMU_HWPT_ALLOC_DIRTY_TRACKING
require special handling, as both require hardware support for scalable
mode and second-stage translation. In such cases, the driver should select
a second-stage page table for the paging domain.

Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241021085125.192333-8-baolu.lu@linux.intel.com
---
 drivers/iommu/intel/iommu.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index ebdb97835fc3..5fbf1237188c 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3299,6 +3299,7 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	struct intel_iommu *iommu = info->iommu;
 	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
+	bool first_stage;
 
 	/* Must be NESTING domain */
 	if (parent) {
@@ -3315,8 +3316,20 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	if (user_data || (dirty_tracking && !ssads_supported(iommu)))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	/* Do not use first stage for user domain translation. */
-	dmar_domain = paging_domain_alloc(dev, false);
+	/*
+	 * Always allocate the guest compatible page table unless
+	 * IOMMU_HWPT_ALLOC_NEST_PARENT or IOMMU_HWPT_ALLOC_DIRTY_TRACKING
+	 * is specified.
+	 */
+	if (nested_parent || dirty_tracking) {
+		if (!sm_supported(iommu) || !ecap_slts(iommu->ecap))
+			return ERR_PTR(-EOPNOTSUPP);
+		first_stage = false;
+	} else {
+		first_stage = first_level_by_default(iommu);
+	}
+
+	dmar_domain = paging_domain_alloc(dev, first_stage);
 	if (IS_ERR(dmar_domain))
 		return ERR_CAST(dmar_domain);
 	domain = &dmar_domain->domain;
-- 
2.43.0

[PATCH 08/19] iommu/vt-d: Use PCI_DEVID() macro

[Lu Baolu]

From: Jinjie Ruan <ruanjinjie@huawei.com>

The macro PCI_DEVID() can be used instead of compose it manually.

Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20240829021011.4135618-1-ruanjinjie@huawei.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/iommu.c         | 4 ++--
 drivers/iommu/intel/irq_remapping.c | 4 ++--
 drivers/iommu/intel/pasid.c         | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 5fbf1237188c..a2212d15371d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1452,7 +1452,7 @@ static void copied_context_tear_down(struct intel_iommu *iommu,
 
 	if (did_old < cap_ndoms(iommu->cap)) {
 		iommu->flush.flush_context(iommu, did_old,
-					   (((u16)bus) << 8) | devfn,
+					   PCI_DEVID(bus, devfn),
 					   DMA_CCMD_MASK_NOBIT,
 					   DMA_CCMD_DEVICE_INVL);
 		iommu->flush.flush_iotlb(iommu, did_old, 0, 0,
@@ -1473,7 +1473,7 @@ static void context_present_cache_flush(struct intel_iommu *iommu, u16 did,
 {
 	if (cap_caching_mode(iommu->cap)) {
 		iommu->flush.flush_context(iommu, 0,
-					   (((u16)bus) << 8) | devfn,
+					   PCI_DEVID(bus, devfn),
 					   DMA_CCMD_MASK_NOBIT,
 					   DMA_CCMD_DEVICE_INVL);
 		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index 7a6d188e3bea..466c1412dd45 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -312,7 +312,7 @@ static int set_ioapic_sid(struct irte *irte, int apic)
 
 	for (i = 0; i < MAX_IO_APICS; i++) {
 		if (ir_ioapic[i].iommu && ir_ioapic[i].id == apic) {
-			sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
+			sid = PCI_DEVID(ir_ioapic[i].bus, ir_ioapic[i].devfn);
 			break;
 		}
 	}
@@ -337,7 +337,7 @@ static int set_hpet_sid(struct irte *irte, u8 id)
 
 	for (i = 0; i < MAX_HPET_TBS; i++) {
 		if (ir_hpet[i].iommu && ir_hpet[i].id == id) {
-			sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
+			sid = PCI_DEVID(ir_hpet[i].bus, ir_hpet[i].devfn);
 			break;
 		}
 	}
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 53157e1194f4..7ef157615e0f 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -220,7 +220,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 	if (pci_dev_is_disconnected(to_pci_dev(dev)))
 		return;
 
-	sid = info->bus << 8 | info->devfn;
+	sid = PCI_DEVID(info->bus, info->devfn);
 	qdep = info->ats_qdep;
 	pfsid = info->pfsid;
 
-- 
2.43.0

[PATCH 09/19] iommu/vt-d: Increase buffer size for device name

[Lu Baolu]

From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>

GCC is not happy with the current code, e.g.:

.../iommu/intel/dmar.c:1063:9: note: ‘sprintf’ output between 6 and 15 bytes into a destination of size 13
 1063 |         sprintf(iommu->name, "dmar%d", iommu->seq_id);

When `make W=1` is supplied, this prevents kernel building. Fix it by
increasing the buffer size for device name and use sizeoF() instead of
hard coded constants.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20241014104529.4025937-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/dmar.c  | 2 +-
 drivers/iommu/intel/iommu.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index eaf862e8dea1..e16c2b1d7633 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1060,7 +1060,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 		err = iommu->seq_id;
 		goto error;
 	}
-	sprintf(iommu->name, "dmar%d", iommu->seq_id);
+	snprintf(iommu->name, sizeof(iommu->name), "dmar%d", iommu->seq_id);
 
 	err = map_iommu(iommu, drhd);
 	if (err) {
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index f9fba9a26dac..79692d7a26d1 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -720,7 +720,7 @@ struct intel_iommu {
 	int		msagaw; /* max sagaw of this iommu */
 	unsigned int	irq, pr_irq, perf_irq;
 	u16		segment;     /* PCI segment# */
-	unsigned char 	name[13];    /* Device Name */
+	unsigned char	name[16];    /* Device Name */
 
 #ifdef CONFIG_INTEL_IOMMU
 	unsigned long 	*domain_ids; /* bitmap of domains */
-- 
2.43.0

[PATCH 10/19] iommu/vt-d: Remove unused dmar_msi_read

[Lu Baolu]

From: "Dr. David Alan Gilbert" <linux@treblig.org>

dmar_msi_read() has been unused since 2022 in
commit cf8e8658100d ("arch: Remove Itanium (IA-64) architecture")

Remove it.

(dmar_msi_write still exists and is used once).

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20241022002702.302728-1-linux@treblig.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/dmar.c | 13 -------------
 include/linux/dmar.h       |  1 -
 2 files changed, 14 deletions(-)

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index e16c2b1d7633..9f424acf474e 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1895,19 +1895,6 @@ void dmar_msi_write(int irq, struct msi_msg *msg)
 	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
 }
 
-void dmar_msi_read(int irq, struct msi_msg *msg)
-{
-	struct intel_iommu *iommu = irq_get_handler_data(irq);
-	int reg = dmar_msi_reg(iommu, irq);
-	unsigned long flag;
-
-	raw_spin_lock_irqsave(&iommu->register_lock, flag);
-	msg->data = readl(iommu->reg + reg + 4);
-	msg->address_lo = readl(iommu->reg + reg + 8);
-	msg->address_hi = readl(iommu->reg + reg + 12);
-	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
-}
-
 static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
 		u8 fault_reason, u32 pasid, u16 source_id,
 		unsigned long long addr)
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 499bb2c63483..692b2b445761 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -292,7 +292,6 @@ static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src)
 struct irq_data;
 extern void dmar_msi_unmask(struct irq_data *data);
 extern void dmar_msi_mask(struct irq_data *data);
-extern void dmar_msi_read(int irq, struct msi_msg *msg);
 extern void dmar_msi_write(int irq, struct msi_msg *msg);
 extern int dmar_set_interrupt(struct intel_iommu *iommu);
 extern irqreturn_t dmar_fault(int irq, void *dev_id);
-- 
2.43.0

[PATCH 11/19] iommu/vt-d: Drop s1_pgtbl from dmar_domain

[Lu Baolu]

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

dmar_domian has stored the s1_cfg which includes the s1_pgtbl info, so
no need to store s1_pgtbl, hence drop it.

Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20241025143339.2328991-1-yi.l.liu@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/iommu.h  | 2 --
 drivers/iommu/intel/nested.c | 1 -
 drivers/iommu/intel/pasid.c  | 3 +--
 3 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 79692d7a26d1..4c6135a2e2f8 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -653,8 +653,6 @@ struct dmar_domain {
 		struct {
 			/* parent page table which the user domain is nested on */
 			struct dmar_domain *s2_domain;
-			/* user page table pointer (in GPA) */
-			unsigned long s1_pgtbl;
 			/* page table attributes */
 			struct iommu_hwpt_vtd_s1 s1_cfg;
 			/* link to parent domain siblings */
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index 96016bc40f94..989ca5cc04eb 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -162,7 +162,6 @@ struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 
 	domain->use_first_level = true;
 	domain->s2_domain = s2_domain;
-	domain->s1_pgtbl = vtd.pgtbl_addr;
 	domain->s1_cfg = vtd;
 	domain->domain.ops = &intel_nested_domain_ops;
 	domain->domain.type = IOMMU_DOMAIN_NESTED;
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 7ef157615e0f..7e76062a7ad2 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -560,7 +560,6 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 			     u32 pasid, struct dmar_domain *domain)
 {
 	struct iommu_hwpt_vtd_s1 *s1_cfg = &domain->s1_cfg;
-	pgd_t *s1_gpgd = (pgd_t *)(uintptr_t)domain->s1_pgtbl;
 	struct dmar_domain *s2_domain = domain->s2_domain;
 	u16 did = domain_id_iommu(domain, iommu);
 	struct dma_pte *pgd = s2_domain->pgd;
@@ -611,7 +610,7 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 	if (s1_cfg->addr_width == ADDR_WIDTH_5LEVEL)
 		pasid_set_flpm(pte, 1);
 
-	pasid_set_flptr(pte, (uintptr_t)s1_gpgd);
+	pasid_set_flptr(pte, s1_cfg->pgtbl_addr);
 
 	if (s1_cfg->flags & IOMMU_VTD_S1_SRE) {
 		pasid_set_sre(pte);
-- 
2.43.0

[PATCH 12/19] iommu/vt-d: Fix checks and print in dmar_fault_dump_ptes()

[Lu Baolu]

From: Zhenzhong Duan <zhenzhong.duan@intel.com>

There are some issues in dmar_fault_dump_ptes():

1. return value of phys_to_virt() is used for checking if an entry is
   present.
2. dump is confusing, e.g., "pasid table entry is not present", confusing
   by unpresent pasid table vs. unpresent pasid table entry. Current code
   means the former.
3. pgtable_walk() is called without checking if page table is present.

Fix 1 by checking present bit of an entry before dump a lower level entry.
Fix 2 by removing "entry" string, e.g., "pasid table is not present".
Fix 3 by checking page table present before walk.

Take issue 3 for example, before fix:

[  442.240357] DMAR: pasid dir entry: 0x000000012c83e001
[  442.246661] DMAR: pasid table entry[0]: 0x0000000000000000
[  442.253429] DMAR: pasid table entry[1]: 0x0000000000000000
[  442.260203] DMAR: pasid table entry[2]: 0x0000000000000000
[  442.266969] DMAR: pasid table entry[3]: 0x0000000000000000
[  442.273733] DMAR: pasid table entry[4]: 0x0000000000000000
[  442.280479] DMAR: pasid table entry[5]: 0x0000000000000000
[  442.287234] DMAR: pasid table entry[6]: 0x0000000000000000
[  442.293989] DMAR: pasid table entry[7]: 0x0000000000000000
[  442.300742] DMAR: PTE not present at level 2

After fix:
...
[  357.241214] DMAR: pasid table entry[6]: 0x0000000000000000
[  357.248022] DMAR: pasid table entry[7]: 0x0000000000000000
[  357.254824] DMAR: scalable mode page table is not present

Fixes: 914ff7719e8a ("iommu/vt-d: Dump DMAR translation structure when DMA fault occurs")
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/r/20241024092146.715063-2-zhenzhong.duan@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/iommu.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index a2212d15371d..96d40e0268a2 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -626,11 +626,11 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
 	pr_info("Dump %s table entries for IOVA 0x%llx\n", iommu->name, addr);
 
 	/* root entry dump */
+	if (!iommu->root_entry) {
+		pr_info("root table is not present\n");
+		return;
+	}
 	rt_entry = &iommu->root_entry[bus];
-	if (!rt_entry) {
-		pr_info("root table entry is not present\n");
-		return;
-	}
 
 	if (sm_supported(iommu))
 		pr_info("scalable mode root entry: hi 0x%016llx, low 0x%016llx\n",
@@ -641,7 +641,7 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
 	/* context entry dump */
 	ctx_entry = iommu_context_addr(iommu, bus, devfn, 0);
 	if (!ctx_entry) {
-		pr_info("context table entry is not present\n");
+		pr_info("context table is not present\n");
 		return;
 	}
 
@@ -650,17 +650,23 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
 
 	/* legacy mode does not require PASID entries */
 	if (!sm_supported(iommu)) {
+		if (!context_present(ctx_entry)) {
+			pr_info("legacy mode page table is not present\n");
+			return;
+		}
 		level = agaw_to_level(ctx_entry->hi & 7);
 		pgtable = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);
 		goto pgtable_walk;
 	}
 
+	if (!context_present(ctx_entry)) {
+		pr_info("pasid directory table is not present\n");
+		return;
+	}
+
 	/* get the pointer to pasid directory entry */
 	dir = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);
-	if (!dir) {
-		pr_info("pasid directory entry is not present\n");
-		return;
-	}
+
 	/* For request-without-pasid, get the pasid from context entry */
 	if (intel_iommu_sm && pasid == IOMMU_PASID_INVALID)
 		pasid = IOMMU_NO_PASID;
@@ -672,7 +678,7 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
 	/* get the pointer to the pasid table entry */
 	entries = get_pasid_table_from_pde(pde);
 	if (!entries) {
-		pr_info("pasid table entry is not present\n");
+		pr_info("pasid table is not present\n");
 		return;
 	}
 	index = pasid & PASID_PTE_MASK;
@@ -680,6 +686,11 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
 	for (i = 0; i < ARRAY_SIZE(pte->val); i++)
 		pr_info("pasid table entry[%d]: 0x%016llx\n", i, pte->val[i]);
 
+	if (!pasid_pte_is_present(pte)) {
+		pr_info("scalable mode page table is not present\n");
+		return;
+	}
+
 	if (pasid_pte_get_pgtt(pte) == PASID_ENTRY_PGTT_FL_ONLY) {
 		level = pte->val[2] & BIT_ULL(2) ? 5 : 4;
 		pgtable = phys_to_virt(pte->val[2] & VTD_PAGE_MASK);
-- 
2.43.0

[PATCH 13/19] iommu/vt-d: Fix checks and print in pgtable_walk()

[Lu Baolu]

From: Zhenzhong Duan <zhenzhong.duan@intel.com>

There are some issues in pgtable_walk():

1. Super page is dumped as non-present page
2. dma_pte_superpage() should not check against leaf page table entries
3. Pointer pte is never NULL so checking it is meaningless
4. When an entry is not present, it still makes sense to dump the entry
   content.

Fix 1,2 by checking dma_pte_superpage()'s returned value after level check.
Fix 3 by removing pte check.
Fix 4 by checking present bit after printing.

By this chance, change to print "page table not present" instead of "PTE
not present" to be clearer.

Fixes: 914ff7719e8a ("iommu/vt-d: Dump DMAR translation structure when DMA fault occurs")
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/r/20241024092146.715063-3-zhenzhong.duan@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/iommu.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 96d40e0268a2..b7351d81b77d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -596,14 +596,15 @@ static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn,
 	while (1) {
 		offset = pfn_level_offset(pfn, level);
 		pte = &parent[offset];
-		if (!pte || (dma_pte_superpage(pte) || !dma_pte_present(pte))) {
-			pr_info("PTE not present at level %d\n", level);
-			break;
-		}
 
 		pr_info("pte level: %d, pte value: 0x%016llx\n", level, pte->val);
 
-		if (level == 1)
+		if (!dma_pte_present(pte)) {
+			pr_info("page table not present at level %d\n", level - 1);
+			break;
+		}
+
+		if (level == 1 || dma_pte_superpage(pte))
 			break;
 
 		parent = phys_to_virt(dma_pte_addr(pte));
-- 
2.43.0

[PATCH 14/19] iommu/vt-d: Separate page request queue from SVM

[Lu Baolu]

From: Joel Granados <joel.granados@kernel.org>

IO page faults are no longer dependent on CONFIG_INTEL_IOMMU_SVM. Move
all Page Request Queue (PRQ) functions that handle prq events to a new
file in drivers/iommu/intel/prq.c. The page_req_des struct is now
declared in drivers/iommu/intel/prq.c.

No functional changes are intended. This is a preparation patch to
enable the use of IO page faults outside the SVM/PASID use cases.

Signed-off-by: Joel Granados <joel.granados@kernel.org>
Link: https://lore.kernel.org/r/20241015-jag-iopfv8-v4-1-b696ca89ba29@kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/Makefile |   2 +-
 drivers/iommu/intel/iommu.c  |  20 +-
 drivers/iommu/intel/iommu.h  |  14 +-
 drivers/iommu/intel/prq.c    | 410 +++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/svm.c    | 397 ---------------------------------
 5 files changed, 424 insertions(+), 419 deletions(-)
 create mode 100644 drivers/iommu/intel/prq.c

diff --git a/drivers/iommu/intel/Makefile b/drivers/iommu/intel/Makefile
index c8beb0281559..d3bb0798092d 100644
--- a/drivers/iommu/intel/Makefile
+++ b/drivers/iommu/intel/Makefile
@@ -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 cache.o
+obj-$(CONFIG_INTEL_IOMMU) += iommu.o pasid.o nested.o cache.o prq.o
 obj-$(CONFIG_DMAR_TABLE) += trace.o cap_audit.o
 obj-$(CONFIG_DMAR_PERF) += perf.o
 obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index b7351d81b77d..3a20795b3f8d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1329,12 +1329,10 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 	/* free context mapping */
 	free_context_table(iommu);
 
-#ifdef CONFIG_INTEL_IOMMU_SVM
 	if (pasid_supported(iommu)) {
 		if (ecap_prs(iommu->ecap))
-			intel_svm_finish_prq(iommu);
+			intel_iommu_finish_prq(iommu);
 	}
-#endif
 }
 
 /*
@@ -2194,19 +2192,18 @@ static int __init init_dmars(void)
 
 		iommu_flush_write_buffer(iommu);
 
-#ifdef CONFIG_INTEL_IOMMU_SVM
 		if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) {
 			/*
 			 * Call dmar_alloc_hwirq() with dmar_global_lock held,
 			 * could cause possible lock race condition.
 			 */
 			up_write(&dmar_global_lock);
-			ret = intel_svm_enable_prq(iommu);
+			ret = intel_iommu_enable_prq(iommu);
 			down_write(&dmar_global_lock);
 			if (ret)
 				goto free_iommu;
 		}
-#endif
+
 		ret = dmar_set_interrupt(iommu);
 		if (ret)
 			goto free_iommu;
@@ -2619,13 +2616,12 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 	intel_iommu_init_qi(iommu);
 	iommu_flush_write_buffer(iommu);
 
-#ifdef CONFIG_INTEL_IOMMU_SVM
 	if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) {
-		ret = intel_svm_enable_prq(iommu);
+		ret = intel_iommu_enable_prq(iommu);
 		if (ret)
 			goto disable_iommu;
 	}
-#endif
+
 	ret = dmar_set_interrupt(iommu);
 	if (ret)
 		goto disable_iommu;
@@ -4074,7 +4070,7 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid,
 	intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
 	kfree(dev_pasid);
 	intel_pasid_tear_down_entry(iommu, dev, pasid, false);
-	intel_drain_pasid_prq(dev, pasid);
+	intel_iommu_drain_pasid_prq(dev, pasid);
 }
 
 static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
@@ -4417,9 +4413,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.def_domain_type	= device_def_domain_type,
 	.remove_dev_pasid	= intel_iommu_remove_dev_pasid,
 	.pgsize_bitmap		= SZ_4K,
-#ifdef CONFIG_INTEL_IOMMU_SVM
-	.page_response		= intel_svm_page_response,
-#endif
+	.page_response		= intel_iommu_page_response,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev		= intel_iommu_attach_device,
 		.set_dev_pasid		= intel_iommu_set_dev_pasid,
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 4c6135a2e2f8..b3912633ce25 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -728,12 +728,10 @@ struct intel_iommu {
 
 	struct iommu_flush flush;
 #endif
-#ifdef CONFIG_INTEL_IOMMU_SVM
 	struct page_req_dsc *prq;
 	unsigned char prq_name[16];    /* Name for PRQ interrupt */
 	unsigned long prq_seq_number;
 	struct completion prq_complete;
-#endif
 	struct iopf_queue *iopf_queue;
 	unsigned char iopfq_name[16];
 	/* Synchronization between fault report and iommu device release. */
@@ -1274,18 +1272,18 @@ void intel_context_flush_present(struct device_domain_info *info,
 				 struct context_entry *context,
 				 u16 did, bool affect_domains);
 
+int intel_iommu_enable_prq(struct intel_iommu *iommu);
+int intel_iommu_finish_prq(struct intel_iommu *iommu);
+void intel_iommu_page_response(struct device *dev, struct iopf_fault *evt,
+			       struct iommu_page_response *msg);
+void intel_iommu_drain_pasid_prq(struct device *dev, u32 pasid);
+
 #ifdef CONFIG_INTEL_IOMMU_SVM
 void intel_svm_check(struct intel_iommu *iommu);
-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(struct device *dev,
 					    struct mm_struct *mm);
-void intel_drain_pasid_prq(struct device *dev, u32 pasid);
 #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(struct device *dev,
 							  struct mm_struct *mm)
 {
diff --git a/drivers/iommu/intel/prq.c b/drivers/iommu/intel/prq.c
new file mode 100644
index 000000000000..edda5da8ba15
--- /dev/null
+++ b/drivers/iommu/intel/prq.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 Intel Corporation
+ *
+ * Originally split from drivers/iommu/intel/svm.c
+ */
+
+#include <linux/pci.h>
+#include <linux/pci-ats.h>
+
+#include "iommu.h"
+#include "pasid.h"
+#include "../iommu-pages.h"
+#include "trace.h"
+
+/* Page request queue descriptor */
+struct page_req_dsc {
+	union {
+		struct {
+			u64 type:8;
+			u64 pasid_present:1;
+			u64 rsvd:7;
+			u64 rid:16;
+			u64 pasid:20;
+			u64 exe_req:1;
+			u64 pm_req:1;
+			u64 rsvd2:10;
+		};
+		u64 qw_0;
+	};
+	union {
+		struct {
+			u64 rd_req:1;
+			u64 wr_req:1;
+			u64 lpig:1;
+			u64 prg_index:9;
+			u64 addr:52;
+		};
+		u64 qw_1;
+	};
+	u64 qw_2;
+	u64 qw_3;
+};
+
+/**
+ * intel_iommu_drain_pasid_prq - Drain page requests and responses for a pasid
+ * @dev: target device
+ * @pasid: pasid for draining
+ *
+ * Drain all pending page requests and responses related to @pasid in both
+ * software and hardware. This is supposed to be called after the device
+ * driver has stopped DMA, the pasid entry has been cleared, and both IOTLB
+ * and DevTLB have been invalidated.
+ *
+ * It waits until all pending page requests for @pasid in the page fault
+ * queue are completed by the prq handling thread. Then follow the steps
+ * described in VT-d spec CH7.10 to drain all page requests and page
+ * responses pending in the hardware.
+ */
+void intel_iommu_drain_pasid_prq(struct device *dev, u32 pasid)
+{
+	struct device_domain_info *info;
+	struct dmar_domain *domain;
+	struct intel_iommu *iommu;
+	struct qi_desc desc[3];
+	struct pci_dev *pdev;
+	int head, tail;
+	u16 sid, did;
+	int qdep;
+
+	info = dev_iommu_priv_get(dev);
+	if (WARN_ON(!info || !dev_is_pci(dev)))
+		return;
+
+	if (!info->pri_enabled)
+		return;
+
+	iommu = info->iommu;
+	domain = info->domain;
+	pdev = to_pci_dev(dev);
+	sid = PCI_DEVID(info->bus, info->devfn);
+	did = domain ? domain_id_iommu(domain, iommu) : FLPT_DEFAULT_DID;
+
+	qdep = pci_ats_queue_depth(pdev);
+
+	/*
+	 * Check and wait until all pending page requests in the queue are
+	 * handled by the prq handling thread.
+	 */
+prq_retry:
+	reinit_completion(&iommu->prq_complete);
+	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
+	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
+	while (head != tail) {
+		struct page_req_dsc *req;
+
+		req = &iommu->prq[head / sizeof(*req)];
+		if (!req->pasid_present || req->pasid != pasid) {
+			head = (head + sizeof(*req)) & PRQ_RING_MASK;
+			continue;
+		}
+
+		wait_for_completion(&iommu->prq_complete);
+		goto prq_retry;
+	}
+
+	iopf_queue_flush_dev(dev);
+
+	/*
+	 * Perform steps described in VT-d spec CH7.10 to drain page
+	 * requests and responses in hardware.
+	 */
+	memset(desc, 0, sizeof(desc));
+	desc[0].qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
+			QI_IWD_FENCE |
+			QI_IWD_TYPE;
+	desc[1].qw0 = QI_EIOTLB_PASID(pasid) |
+			QI_EIOTLB_DID(did) |
+			QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+			QI_EIOTLB_TYPE;
+	desc[2].qw0 = QI_DEV_EIOTLB_PASID(pasid) |
+			QI_DEV_EIOTLB_SID(sid) |
+			QI_DEV_EIOTLB_QDEP(qdep) |
+			QI_DEIOTLB_TYPE |
+			QI_DEV_IOTLB_PFSID(info->pfsid);
+qi_retry:
+	reinit_completion(&iommu->prq_complete);
+	qi_submit_sync(iommu, desc, 3, QI_OPT_WAIT_DRAIN);
+	if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO) {
+		wait_for_completion(&iommu->prq_complete);
+		goto qi_retry;
+	}
+}
+
+static bool is_canonical_address(u64 addr)
+{
+	int shift = 64 - (__VIRTUAL_MASK_SHIFT + 1);
+	long saddr = (long)addr;
+
+	return (((saddr << shift) >> shift) == saddr);
+}
+
+static void handle_bad_prq_event(struct intel_iommu *iommu,
+				 struct page_req_dsc *req, int result)
+{
+	struct qi_desc desc = { };
+
+	pr_err("%s: Invalid page request: %08llx %08llx\n",
+	       iommu->name, ((unsigned long long *)req)[0],
+	       ((unsigned long long *)req)[1]);
+
+	if (!req->lpig)
+		return;
+
+	desc.qw0 = QI_PGRP_PASID(req->pasid) |
+			QI_PGRP_DID(req->rid) |
+			QI_PGRP_PASID_P(req->pasid_present) |
+			QI_PGRP_RESP_CODE(result) |
+			QI_PGRP_RESP_TYPE;
+	desc.qw1 = QI_PGRP_IDX(req->prg_index) |
+			QI_PGRP_LPIG(req->lpig);
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+static int prq_to_iommu_prot(struct page_req_dsc *req)
+{
+	int prot = 0;
+
+	if (req->rd_req)
+		prot |= IOMMU_FAULT_PERM_READ;
+	if (req->wr_req)
+		prot |= IOMMU_FAULT_PERM_WRITE;
+	if (req->exe_req)
+		prot |= IOMMU_FAULT_PERM_EXEC;
+	if (req->pm_req)
+		prot |= IOMMU_FAULT_PERM_PRIV;
+
+	return prot;
+}
+
+static void intel_prq_report(struct intel_iommu *iommu, struct device *dev,
+			     struct page_req_dsc *desc)
+{
+	struct iopf_fault event = { };
+
+	/* Fill in event data for device specific processing */
+	event.fault.type = IOMMU_FAULT_PAGE_REQ;
+	event.fault.prm.addr = (u64)desc->addr << VTD_PAGE_SHIFT;
+	event.fault.prm.pasid = desc->pasid;
+	event.fault.prm.grpid = desc->prg_index;
+	event.fault.prm.perm = prq_to_iommu_prot(desc);
+
+	if (desc->lpig)
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+	if (desc->pasid_present) {
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID;
+	}
+
+	iommu_report_device_fault(dev, &event);
+}
+
+static irqreturn_t prq_event_thread(int irq, void *d)
+{
+	struct intel_iommu *iommu = d;
+	struct page_req_dsc *req;
+	int head, tail, handled;
+	struct device *dev;
+	u64 address;
+
+	/*
+	 * Clear PPR bit before reading head/tail registers, to ensure that
+	 * we get a new interrupt if needed.
+	 */
+	writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG);
+
+	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
+	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
+	handled = (head != tail);
+	while (head != tail) {
+		req = &iommu->prq[head / sizeof(*req)];
+		address = (u64)req->addr << VTD_PAGE_SHIFT;
+
+		if (unlikely(!req->pasid_present)) {
+			pr_err("IOMMU: %s: Page request without PASID\n",
+			       iommu->name);
+bad_req:
+			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
+			goto prq_advance;
+		}
+
+		if (unlikely(!is_canonical_address(address))) {
+			pr_err("IOMMU: %s: Address is not canonical\n",
+			       iommu->name);
+			goto bad_req;
+		}
+
+		if (unlikely(req->pm_req && (req->rd_req | req->wr_req))) {
+			pr_err("IOMMU: %s: Page request in Privilege Mode\n",
+			       iommu->name);
+			goto bad_req;
+		}
+
+		if (unlikely(req->exe_req && req->rd_req)) {
+			pr_err("IOMMU: %s: Execution request not supported\n",
+			       iommu->name);
+			goto bad_req;
+		}
+
+		/* Drop Stop Marker message. No need for a response. */
+		if (unlikely(req->lpig && !req->rd_req && !req->wr_req))
+			goto prq_advance;
+
+		/*
+		 * If prq is to be handled outside iommu driver via receiver of
+		 * the fault notifiers, we skip the page response here.
+		 */
+		mutex_lock(&iommu->iopf_lock);
+		dev = device_rbtree_find(iommu, req->rid);
+		if (!dev) {
+			mutex_unlock(&iommu->iopf_lock);
+			goto bad_req;
+		}
+
+		intel_prq_report(iommu, dev, req);
+		trace_prq_report(iommu, dev, req->qw_0, req->qw_1,
+				 req->qw_2, req->qw_3,
+				 iommu->prq_seq_number++);
+		mutex_unlock(&iommu->iopf_lock);
+prq_advance:
+		head = (head + sizeof(*req)) & PRQ_RING_MASK;
+	}
+
+	dmar_writeq(iommu->reg + DMAR_PQH_REG, tail);
+
+	/*
+	 * Clear the page request overflow bit and wake up all threads that
+	 * are waiting for the completion of this handling.
+	 */
+	if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO) {
+		pr_info_ratelimited("IOMMU: %s: PRQ overflow detected\n",
+				    iommu->name);
+		head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
+		tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
+		if (head == tail) {
+			iopf_queue_discard_partial(iommu->iopf_queue);
+			writel(DMA_PRS_PRO, iommu->reg + DMAR_PRS_REG);
+			pr_info_ratelimited("IOMMU: %s: PRQ overflow cleared",
+					    iommu->name);
+		}
+	}
+
+	if (!completion_done(&iommu->prq_complete))
+		complete(&iommu->prq_complete);
+
+	return IRQ_RETVAL(handled);
+}
+
+int intel_iommu_enable_prq(struct intel_iommu *iommu)
+{
+	struct iopf_queue *iopfq;
+	int irq, ret;
+
+	iommu->prq = iommu_alloc_pages_node(iommu->node, GFP_KERNEL, PRQ_ORDER);
+	if (!iommu->prq) {
+		pr_warn("IOMMU: %s: Failed to allocate page request queue\n",
+			iommu->name);
+		return -ENOMEM;
+	}
+
+	irq = dmar_alloc_hwirq(IOMMU_IRQ_ID_OFFSET_PRQ + iommu->seq_id, iommu->node, iommu);
+	if (irq <= 0) {
+		pr_err("IOMMU: %s: Failed to create IRQ vector for page request queue\n",
+		       iommu->name);
+		ret = -EINVAL;
+		goto free_prq;
+	}
+	iommu->pr_irq = irq;
+
+	snprintf(iommu->iopfq_name, sizeof(iommu->iopfq_name),
+		 "dmar%d-iopfq", iommu->seq_id);
+	iopfq = iopf_queue_alloc(iommu->iopfq_name);
+	if (!iopfq) {
+		pr_err("IOMMU: %s: Failed to allocate iopf queue\n", iommu->name);
+		ret = -ENOMEM;
+		goto free_hwirq;
+	}
+	iommu->iopf_queue = iopfq;
+
+	snprintf(iommu->prq_name, sizeof(iommu->prq_name), "dmar%d-prq", iommu->seq_id);
+
+	ret = request_threaded_irq(irq, NULL, prq_event_thread, IRQF_ONESHOT,
+				   iommu->prq_name, iommu);
+	if (ret) {
+		pr_err("IOMMU: %s: Failed to request IRQ for page request queue\n",
+		       iommu->name);
+		goto free_iopfq;
+	}
+	dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL);
+	dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
+	dmar_writeq(iommu->reg + DMAR_PQA_REG, virt_to_phys(iommu->prq) | PRQ_ORDER);
+
+	init_completion(&iommu->prq_complete);
+
+	return 0;
+
+free_iopfq:
+	iopf_queue_free(iommu->iopf_queue);
+	iommu->iopf_queue = NULL;
+free_hwirq:
+	dmar_free_hwirq(irq);
+	iommu->pr_irq = 0;
+free_prq:
+	iommu_free_pages(iommu->prq, PRQ_ORDER);
+	iommu->prq = NULL;
+
+	return ret;
+}
+
+int intel_iommu_finish_prq(struct intel_iommu *iommu)
+{
+	dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL);
+	dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
+	dmar_writeq(iommu->reg + DMAR_PQA_REG, 0ULL);
+
+	if (iommu->pr_irq) {
+		free_irq(iommu->pr_irq, iommu);
+		dmar_free_hwirq(iommu->pr_irq);
+		iommu->pr_irq = 0;
+	}
+
+	if (iommu->iopf_queue) {
+		iopf_queue_free(iommu->iopf_queue);
+		iommu->iopf_queue = NULL;
+	}
+
+	iommu_free_pages(iommu->prq, PRQ_ORDER);
+	iommu->prq = NULL;
+
+	return 0;
+}
+
+void intel_iommu_page_response(struct device *dev, struct iopf_fault *evt,
+			       struct iommu_page_response *msg)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	u8 bus = info->bus, devfn = info->devfn;
+	struct iommu_fault_page_request *prm;
+	struct qi_desc desc;
+	bool pasid_present;
+	bool last_page;
+	u16 sid;
+
+	prm = &evt->fault.prm;
+	sid = PCI_DEVID(bus, devfn);
+	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+	last_page = prm->flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+
+	desc.qw0 = QI_PGRP_PASID(prm->pasid) | QI_PGRP_DID(sid) |
+			QI_PGRP_PASID_P(pasid_present) |
+			QI_PGRP_RESP_CODE(msg->code) |
+			QI_PGRP_RESP_TYPE;
+	desc.qw1 = QI_PGRP_IDX(prm->grpid) | QI_PGRP_LPIG(last_page);
+	desc.qw2 = 0;
+	desc.qw3 = 0;
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 078d1e32a24e..3cc43a958b4d 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -25,92 +25,6 @@
 #include "../iommu-pages.h"
 #include "trace.h"
 
-static irqreturn_t prq_event_thread(int irq, void *d);
-
-int intel_svm_enable_prq(struct intel_iommu *iommu)
-{
-	struct iopf_queue *iopfq;
-	int irq, ret;
-
-	iommu->prq = iommu_alloc_pages_node(iommu->node, GFP_KERNEL, PRQ_ORDER);
-	if (!iommu->prq) {
-		pr_warn("IOMMU: %s: Failed to allocate page request queue\n",
-			iommu->name);
-		return -ENOMEM;
-	}
-
-	irq = dmar_alloc_hwirq(IOMMU_IRQ_ID_OFFSET_PRQ + iommu->seq_id, iommu->node, iommu);
-	if (irq <= 0) {
-		pr_err("IOMMU: %s: Failed to create IRQ vector for page request queue\n",
-		       iommu->name);
-		ret = -EINVAL;
-		goto free_prq;
-	}
-	iommu->pr_irq = irq;
-
-	snprintf(iommu->iopfq_name, sizeof(iommu->iopfq_name),
-		 "dmar%d-iopfq", iommu->seq_id);
-	iopfq = iopf_queue_alloc(iommu->iopfq_name);
-	if (!iopfq) {
-		pr_err("IOMMU: %s: Failed to allocate iopf queue\n", iommu->name);
-		ret = -ENOMEM;
-		goto free_hwirq;
-	}
-	iommu->iopf_queue = iopfq;
-
-	snprintf(iommu->prq_name, sizeof(iommu->prq_name), "dmar%d-prq", iommu->seq_id);
-
-	ret = request_threaded_irq(irq, NULL, prq_event_thread, IRQF_ONESHOT,
-				   iommu->prq_name, iommu);
-	if (ret) {
-		pr_err("IOMMU: %s: Failed to request IRQ for page request queue\n",
-		       iommu->name);
-		goto free_iopfq;
-	}
-	dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL);
-	dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
-	dmar_writeq(iommu->reg + DMAR_PQA_REG, virt_to_phys(iommu->prq) | PRQ_ORDER);
-
-	init_completion(&iommu->prq_complete);
-
-	return 0;
-
-free_iopfq:
-	iopf_queue_free(iommu->iopf_queue);
-	iommu->iopf_queue = NULL;
-free_hwirq:
-	dmar_free_hwirq(irq);
-	iommu->pr_irq = 0;
-free_prq:
-	iommu_free_pages(iommu->prq, PRQ_ORDER);
-	iommu->prq = NULL;
-
-	return ret;
-}
-
-int intel_svm_finish_prq(struct intel_iommu *iommu)
-{
-	dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL);
-	dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
-	dmar_writeq(iommu->reg + DMAR_PQA_REG, 0ULL);
-
-	if (iommu->pr_irq) {
-		free_irq(iommu->pr_irq, iommu);
-		dmar_free_hwirq(iommu->pr_irq);
-		iommu->pr_irq = 0;
-	}
-
-	if (iommu->iopf_queue) {
-		iopf_queue_free(iommu->iopf_queue);
-		iommu->iopf_queue = NULL;
-	}
-
-	iommu_free_pages(iommu->prq, PRQ_ORDER);
-	iommu->prq = NULL;
-
-	return 0;
-}
-
 void intel_svm_check(struct intel_iommu *iommu)
 {
 	if (!pasid_supported(iommu))
@@ -240,317 +154,6 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 	return ret;
 }
 
-/* Page request queue descriptor */
-struct page_req_dsc {
-	union {
-		struct {
-			u64 type:8;
-			u64 pasid_present:1;
-			u64 rsvd:7;
-			u64 rid:16;
-			u64 pasid:20;
-			u64 exe_req:1;
-			u64 pm_req:1;
-			u64 rsvd2:10;
-		};
-		u64 qw_0;
-	};
-	union {
-		struct {
-			u64 rd_req:1;
-			u64 wr_req:1;
-			u64 lpig:1;
-			u64 prg_index:9;
-			u64 addr:52;
-		};
-		u64 qw_1;
-	};
-	u64 qw_2;
-	u64 qw_3;
-};
-
-static bool is_canonical_address(u64 addr)
-{
-	int shift = 64 - (__VIRTUAL_MASK_SHIFT + 1);
-	long saddr = (long) addr;
-
-	return (((saddr << shift) >> shift) == saddr);
-}
-
-/**
- * intel_drain_pasid_prq - Drain page requests and responses for a pasid
- * @dev: target device
- * @pasid: pasid for draining
- *
- * Drain all pending page requests and responses related to @pasid in both
- * software and hardware. This is supposed to be called after the device
- * driver has stopped DMA, the pasid entry has been cleared, and both IOTLB
- * and DevTLB have been invalidated.
- *
- * It waits until all pending page requests for @pasid in the page fault
- * queue are completed by the prq handling thread. Then follow the steps
- * described in VT-d spec CH7.10 to drain all page requests and page
- * responses pending in the hardware.
- */
-void intel_drain_pasid_prq(struct device *dev, u32 pasid)
-{
-	struct device_domain_info *info;
-	struct dmar_domain *domain;
-	struct intel_iommu *iommu;
-	struct qi_desc desc[3];
-	struct pci_dev *pdev;
-	int head, tail;
-	u16 sid, did;
-	int qdep;
-
-	info = dev_iommu_priv_get(dev);
-	if (WARN_ON(!info || !dev_is_pci(dev)))
-		return;
-
-	if (!info->pri_enabled)
-		return;
-
-	iommu = info->iommu;
-	domain = info->domain;
-	pdev = to_pci_dev(dev);
-	sid = PCI_DEVID(info->bus, info->devfn);
-	did = domain ? domain_id_iommu(domain, iommu) : FLPT_DEFAULT_DID;
-	qdep = pci_ats_queue_depth(pdev);
-
-	/*
-	 * Check and wait until all pending page requests in the queue are
-	 * handled by the prq handling thread.
-	 */
-prq_retry:
-	reinit_completion(&iommu->prq_complete);
-	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
-	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
-	while (head != tail) {
-		struct page_req_dsc *req;
-
-		req = &iommu->prq[head / sizeof(*req)];
-		if (!req->pasid_present || req->pasid != pasid) {
-			head = (head + sizeof(*req)) & PRQ_RING_MASK;
-			continue;
-		}
-
-		wait_for_completion(&iommu->prq_complete);
-		goto prq_retry;
-	}
-
-	iopf_queue_flush_dev(dev);
-
-	/*
-	 * Perform steps described in VT-d spec CH7.10 to drain page
-	 * requests and responses in hardware.
-	 */
-	memset(desc, 0, sizeof(desc));
-	desc[0].qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
-			QI_IWD_FENCE |
-			QI_IWD_TYPE;
-	desc[1].qw0 = QI_EIOTLB_PASID(pasid) |
-			QI_EIOTLB_DID(did) |
-			QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
-			QI_EIOTLB_TYPE;
-	desc[2].qw0 = QI_DEV_EIOTLB_PASID(pasid) |
-			QI_DEV_EIOTLB_SID(sid) |
-			QI_DEV_EIOTLB_QDEP(qdep) |
-			QI_DEIOTLB_TYPE |
-			QI_DEV_IOTLB_PFSID(info->pfsid);
-qi_retry:
-	reinit_completion(&iommu->prq_complete);
-	qi_submit_sync(iommu, desc, 3, QI_OPT_WAIT_DRAIN);
-	if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO) {
-		wait_for_completion(&iommu->prq_complete);
-		goto qi_retry;
-	}
-}
-
-static int prq_to_iommu_prot(struct page_req_dsc *req)
-{
-	int prot = 0;
-
-	if (req->rd_req)
-		prot |= IOMMU_FAULT_PERM_READ;
-	if (req->wr_req)
-		prot |= IOMMU_FAULT_PERM_WRITE;
-	if (req->exe_req)
-		prot |= IOMMU_FAULT_PERM_EXEC;
-	if (req->pm_req)
-		prot |= IOMMU_FAULT_PERM_PRIV;
-
-	return prot;
-}
-
-static void intel_svm_prq_report(struct intel_iommu *iommu, struct device *dev,
-				 struct page_req_dsc *desc)
-{
-	struct iopf_fault event = { };
-
-	/* Fill in event data for device specific processing */
-	event.fault.type = IOMMU_FAULT_PAGE_REQ;
-	event.fault.prm.addr = (u64)desc->addr << VTD_PAGE_SHIFT;
-	event.fault.prm.pasid = desc->pasid;
-	event.fault.prm.grpid = desc->prg_index;
-	event.fault.prm.perm = prq_to_iommu_prot(desc);
-
-	if (desc->lpig)
-		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
-	if (desc->pasid_present) {
-		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
-		event.fault.prm.flags |= IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID;
-	}
-
-	iommu_report_device_fault(dev, &event);
-}
-
-static void handle_bad_prq_event(struct intel_iommu *iommu,
-				 struct page_req_dsc *req, int result)
-{
-	struct qi_desc desc = { };
-
-	pr_err("%s: Invalid page request: %08llx %08llx\n",
-	       iommu->name, ((unsigned long long *)req)[0],
-	       ((unsigned long long *)req)[1]);
-
-	if (!req->lpig)
-		return;
-
-	desc.qw0 = QI_PGRP_PASID(req->pasid) |
-			QI_PGRP_DID(req->rid) |
-			QI_PGRP_PASID_P(req->pasid_present) |
-			QI_PGRP_RESP_CODE(result) |
-			QI_PGRP_RESP_TYPE;
-	desc.qw1 = QI_PGRP_IDX(req->prg_index) |
-			QI_PGRP_LPIG(req->lpig);
-
-	qi_submit_sync(iommu, &desc, 1, 0);
-}
-
-static irqreturn_t prq_event_thread(int irq, void *d)
-{
-	struct intel_iommu *iommu = d;
-	struct page_req_dsc *req;
-	int head, tail, handled;
-	struct device *dev;
-	u64 address;
-
-	/*
-	 * Clear PPR bit before reading head/tail registers, to ensure that
-	 * we get a new interrupt if needed.
-	 */
-	writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG);
-
-	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
-	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
-	handled = (head != tail);
-	while (head != tail) {
-		req = &iommu->prq[head / sizeof(*req)];
-		address = (u64)req->addr << VTD_PAGE_SHIFT;
-
-		if (unlikely(!req->pasid_present)) {
-			pr_err("IOMMU: %s: Page request without PASID\n",
-			       iommu->name);
-bad_req:
-			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
-			goto prq_advance;
-		}
-
-		if (unlikely(!is_canonical_address(address))) {
-			pr_err("IOMMU: %s: Address is not canonical\n",
-			       iommu->name);
-			goto bad_req;
-		}
-
-		if (unlikely(req->pm_req && (req->rd_req | req->wr_req))) {
-			pr_err("IOMMU: %s: Page request in Privilege Mode\n",
-			       iommu->name);
-			goto bad_req;
-		}
-
-		if (unlikely(req->exe_req && req->rd_req)) {
-			pr_err("IOMMU: %s: Execution request not supported\n",
-			       iommu->name);
-			goto bad_req;
-		}
-
-		/* Drop Stop Marker message. No need for a response. */
-		if (unlikely(req->lpig && !req->rd_req && !req->wr_req))
-			goto prq_advance;
-
-		/*
-		 * If prq is to be handled outside iommu driver via receiver of
-		 * the fault notifiers, we skip the page response here.
-		 */
-		mutex_lock(&iommu->iopf_lock);
-		dev = device_rbtree_find(iommu, req->rid);
-		if (!dev) {
-			mutex_unlock(&iommu->iopf_lock);
-			goto bad_req;
-		}
-
-		intel_svm_prq_report(iommu, dev, req);
-		trace_prq_report(iommu, dev, req->qw_0, req->qw_1,
-				 req->qw_2, req->qw_3,
-				 iommu->prq_seq_number++);
-		mutex_unlock(&iommu->iopf_lock);
-prq_advance:
-		head = (head + sizeof(*req)) & PRQ_RING_MASK;
-	}
-
-	dmar_writeq(iommu->reg + DMAR_PQH_REG, tail);
-
-	/*
-	 * Clear the page request overflow bit and wake up all threads that
-	 * are waiting for the completion of this handling.
-	 */
-	if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO) {
-		pr_info_ratelimited("IOMMU: %s: PRQ overflow detected\n",
-				    iommu->name);
-		head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
-		tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
-		if (head == tail) {
-			iopf_queue_discard_partial(iommu->iopf_queue);
-			writel(DMA_PRS_PRO, iommu->reg + DMAR_PRS_REG);
-			pr_info_ratelimited("IOMMU: %s: PRQ overflow cleared",
-					    iommu->name);
-		}
-	}
-
-	if (!completion_done(&iommu->prq_complete))
-		complete(&iommu->prq_complete);
-
-	return IRQ_RETVAL(handled);
-}
-
-void intel_svm_page_response(struct device *dev, struct iopf_fault *evt,
-			     struct iommu_page_response *msg)
-{
-	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct intel_iommu *iommu = info->iommu;
-	u8 bus = info->bus, devfn = info->devfn;
-	struct iommu_fault_page_request *prm;
-	struct qi_desc desc;
-	bool pasid_present;
-	bool last_page;
-	u16 sid;
-
-	prm = &evt->fault.prm;
-	sid = PCI_DEVID(bus, devfn);
-	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
-	last_page = prm->flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
-
-	desc.qw0 = QI_PGRP_PASID(prm->pasid) | QI_PGRP_DID(sid) |
-			QI_PGRP_PASID_P(pasid_present) |
-			QI_PGRP_RESP_CODE(msg->code) |
-			QI_PGRP_RESP_TYPE;
-	desc.qw1 = QI_PGRP_IDX(prm->grpid) | QI_PGRP_LPIG(last_page);
-	desc.qw2 = 0;
-	desc.qw3 = 0;
-
-	qi_submit_sync(iommu, &desc, 1, 0);
-}
-
 static void intel_svm_domain_free(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-- 
2.43.0

[PATCH 15/19] iommu/vt-d: Remove the pasid present check in prq_event_thread

[Lu Baolu]

From: Klaus Jensen <k.jensen@samsung.com>

PASID is not strictly needed when handling a PRQ event; remove the check
for the pasid present bit in the request. This change was not included
in the creation of prq.c to emphasize the change in capability checks
when handing PRQ events.

Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
Link: https://lore.kernel.org/r/20241015-jag-iopfv8-v4-2-b696ca89ba29@kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/prq.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/iommu/intel/prq.c b/drivers/iommu/intel/prq.c
index edda5da8ba15..621cd26504b3 100644
--- a/drivers/iommu/intel/prq.c
+++ b/drivers/iommu/intel/prq.c
@@ -222,18 +222,12 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		req = &iommu->prq[head / sizeof(*req)];
 		address = (u64)req->addr << VTD_PAGE_SHIFT;
 
-		if (unlikely(!req->pasid_present)) {
-			pr_err("IOMMU: %s: Page request without PASID\n",
-			       iommu->name);
-bad_req:
-			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
-			goto prq_advance;
-		}
-
 		if (unlikely(!is_canonical_address(address))) {
 			pr_err("IOMMU: %s: Address is not canonical\n",
 			       iommu->name);
-			goto bad_req;
+bad_req:
+			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
+			goto prq_advance;
 		}
 
 		if (unlikely(req->pm_req && (req->rd_req | req->wr_req))) {
-- 
2.43.0

[PATCH 16/19] iommu/vt-d: Move IOMMU_IOPF into INTEL_IOMMU

[Lu Baolu]

From: Joel Granados <joel.granados@kernel.org>

Move IOMMU_IOPF from under INTEL_IOMMU_SVM into INTEL_IOMMU. This
certifies that the core intel iommu utilizes the IOPF library
functions, independent of the INTEL_IOMMU_SVM config.

Signed-off-by: Joel Granados <joel.granados@kernel.org>
Link: https://lore.kernel.org/r/20241015-jag-iopfv8-v4-3-b696ca89ba29@kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig
index 88fd32a9323c..f2f538c70650 100644
--- a/drivers/iommu/intel/Kconfig
+++ b/drivers/iommu/intel/Kconfig
@@ -14,6 +14,7 @@ config INTEL_IOMMU
 	depends on PCI_MSI && ACPI && X86
 	select IOMMU_API
 	select IOMMU_IOVA
+	select IOMMU_IOPF
 	select IOMMUFD_DRIVER if IOMMUFD
 	select NEED_DMA_MAP_STATE
 	select DMAR_TABLE
@@ -50,7 +51,6 @@ config INTEL_IOMMU_SVM
 	depends on X86_64
 	select MMU_NOTIFIER
 	select IOMMU_SVA
-	select IOMMU_IOPF
 	help
 	  Shared Virtual Memory (SVM) provides a facility for devices
 	  to access DMA resources through process address space by
-- 
2.43.0

[PATCH 17/19] iommufd: Enable PRI when doing the iommufd_hwpt_alloc

[Lu Baolu]

From: Joel Granados <joel.granados@kernel.org>

Add IOMMU_HWPT_FAULT_ID_VALID as part of the valid flags when doing an
iommufd_hwpt_alloc allowing the use of an iommu fault allocation
(iommu_fault_alloc) with the IOMMU_HWPT_ALLOC ioctl.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
Link: https://lore.kernel.org/r/20241015-jag-iopfv8-v4-4-b696ca89ba29@kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/iommu.c          | 3 ++-
 drivers/iommu/iommufd/hw_pagetable.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 3a20795b3f8d..1e432729ea09 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3317,7 +3317,8 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	}
 
 	if (flags &
-	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING)))
+	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING
+	       | IOMMU_HWPT_FAULT_ID_VALID)))
 		return ERR_PTR(-EOPNOTSUPP);
 	if (nested_parent && !nested_supported(iommu))
 		return ERR_PTR(-EOPNOTSUPP);
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index d06bf6e6c19f..8f020bc0815f 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -107,7 +107,8 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 			  const struct iommu_user_data *user_data)
 {
 	const u32 valid_flags = IOMMU_HWPT_ALLOC_NEST_PARENT |
-				IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
+				IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
+				IOMMU_HWPT_FAULT_ID_VALID;
 	const struct iommu_ops *ops = dev_iommu_ops(idev->dev);
 	struct iommufd_hwpt_paging *hwpt_paging;
 	struct iommufd_hw_pagetable *hwpt;
-- 
2.43.0

[PATCH 18/19] iommu/vt-d: Drop pasid requirement for prq initialization

[Lu Baolu]

From: Klaus Jensen <k.jensen@samsung.com>

PASID support within the IOMMU is not required to enable the Page
Request Queue, only the PRS capability.

Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
Link: https://lore.kernel.org/r/20241015-jag-iopfv8-v4-5-b696ca89ba29@kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/iommu.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 1e432729ea09..87a3563dfe54 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1329,10 +1329,8 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 	/* free context mapping */
 	free_context_table(iommu);
 
-	if (pasid_supported(iommu)) {
-		if (ecap_prs(iommu->ecap))
-			intel_iommu_finish_prq(iommu);
-	}
+	if (ecap_prs(iommu->ecap))
+		intel_iommu_finish_prq(iommu);
 }
 
 /*
@@ -2192,7 +2190,7 @@ static int __init init_dmars(void)
 
 		iommu_flush_write_buffer(iommu);
 
-		if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) {
+		if (ecap_prs(iommu->ecap)) {
 			/*
 			 * Call dmar_alloc_hwirq() with dmar_global_lock held,
 			 * could cause possible lock race condition.
@@ -2616,7 +2614,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 	intel_iommu_init_qi(iommu);
 	iommu_flush_write_buffer(iommu);
 
-	if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) {
+	if (ecap_prs(iommu->ecap)) {
 		ret = intel_iommu_enable_prq(iommu);
 		if (ret)
 			goto disable_iommu;
-- 
2.43.0

[PATCH 19/19] iommu/vt-d: Drain PRQs when domain removed from RID

[Lu Baolu]

As this iommu driver now supports page faults for requests without
PASID, page requests should be drained when a domain is removed from
the RID2PASID entry.

This results in the intel_iommu_drain_pasid_prq() call being moved to
intel_pasid_tear_down_entry(). This indicates that when a translation
is removed from any PASID entry and the PRI has been enabled on the
device, page requests are drained in the domain detachment path.

The intel_iommu_drain_pasid_prq() helper has been modified to support
sending device TLB invalidation requests for both PASID and non-PASID
cases.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20241101045543.70086-1-baolu.lu@linux.intel.com
---
 drivers/iommu/intel/iommu.c |  1 -
 drivers/iommu/intel/pasid.c |  1 +
 drivers/iommu/intel/prq.c   | 26 +++++++++-----------------
 3 files changed, 10 insertions(+), 18 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 87a3563dfe54..3878f35be09d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4069,7 +4069,6 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid,
 	intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
 	kfree(dev_pasid);
 	intel_pasid_tear_down_entry(iommu, dev, pasid, false);
-	intel_iommu_drain_pasid_prq(dev, pasid);
 }
 
 static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 7e76062a7ad2..31665fb62e1c 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -265,6 +265,7 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
 
 	devtlb_invalidation_with_pasid(iommu, dev, pasid);
+	intel_iommu_drain_pasid_prq(dev, pasid);
 }
 
 /*
diff --git a/drivers/iommu/intel/prq.c b/drivers/iommu/intel/prq.c
index 621cd26504b3..c2d792db52c3 100644
--- a/drivers/iommu/intel/prq.c
+++ b/drivers/iommu/intel/prq.c
@@ -63,26 +63,18 @@ void intel_iommu_drain_pasid_prq(struct device *dev, u32 pasid)
 	struct dmar_domain *domain;
 	struct intel_iommu *iommu;
 	struct qi_desc desc[3];
-	struct pci_dev *pdev;
 	int head, tail;
 	u16 sid, did;
-	int qdep;
 
 	info = dev_iommu_priv_get(dev);
-	if (WARN_ON(!info || !dev_is_pci(dev)))
-		return;
-
 	if (!info->pri_enabled)
 		return;
 
 	iommu = info->iommu;
 	domain = info->domain;
-	pdev = to_pci_dev(dev);
 	sid = PCI_DEVID(info->bus, info->devfn);
 	did = domain ? domain_id_iommu(domain, iommu) : FLPT_DEFAULT_DID;
 
-	qdep = pci_ats_queue_depth(pdev);
-
 	/*
 	 * Check and wait until all pending page requests in the queue are
 	 * handled by the prq handling thread.
@@ -114,15 +106,15 @@ void intel_iommu_drain_pasid_prq(struct device *dev, u32 pasid)
 	desc[0].qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
 			QI_IWD_FENCE |
 			QI_IWD_TYPE;
-	desc[1].qw0 = QI_EIOTLB_PASID(pasid) |
-			QI_EIOTLB_DID(did) |
-			QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
-			QI_EIOTLB_TYPE;
-	desc[2].qw0 = QI_DEV_EIOTLB_PASID(pasid) |
-			QI_DEV_EIOTLB_SID(sid) |
-			QI_DEV_EIOTLB_QDEP(qdep) |
-			QI_DEIOTLB_TYPE |
-			QI_DEV_IOTLB_PFSID(info->pfsid);
+	if (pasid == IOMMU_NO_PASID) {
+		qi_desc_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH, &desc[1]);
+		qi_desc_dev_iotlb(sid, info->pfsid, info->ats_qdep, 0,
+				  MAX_AGAW_PFN_WIDTH, &desc[2]);
+	} else {
+		qi_desc_piotlb(did, pasid, 0, -1, 0, &desc[1]);
+		qi_desc_dev_iotlb_pasid(sid, info->pfsid, pasid, info->ats_qdep,
+					0, MAX_AGAW_PFN_WIDTH, &desc[2]);
+	}
 qi_retry:
 	reinit_completion(&iommu->prq_complete);
 	qi_submit_sync(iommu, desc, 3, QI_OPT_WAIT_DRAIN);
-- 
2.43.0

Re: [PATCH 00/19] [PULL REQUEST] Intel IOMMU updates for v6.13

[Joerg Roedel]

On Mon, Nov 04, 2024 at 09:40:20AM +0800, Lu Baolu wrote:
> Andy Shevchenko (1):
>   iommu/vt-d: Increase buffer size for device name
> 
> Dr. David Alan Gilbert (1):
>   iommu/vt-d: Remove unused dmar_msi_read
> 
> Jinjie Ruan (1):
>   iommu/vt-d: Use PCI_DEVID() macro
> 
> Joel Granados (3):
>   iommu/vt-d: Separate page request queue from SVM
>   iommu/vt-d: Move IOMMU_IOPF into INTEL_IOMMU
>   iommufd: Enable PRI when doing the iommufd_hwpt_alloc
> 
> Klaus Jensen (2):
>   iommu/vt-d: Remove the pasid present check in prq_event_thread
>   iommu/vt-d: Drop pasid requirement for prq initialization
> 
> Lu Baolu (8):
>   iommu/vt-d: Add domain_alloc_paging support
>   iommu/vt-d: Remove unused domain_alloc callback
>   iommu/vt-d: Enhance compatibility check for paging domain attach
>   iommu/vt-d: Remove domain_update_iommu_cap()
>   iommu/vt-d: Remove domain_update_iommu_superpage()
>   iommu/vt-d: Refactor first_level_by_default()
>   iommu/vt-d: Refine intel_iommu_domain_alloc_user()
>   iommu/vt-d: Drain PRQs when domain removed from RID
> 
> Yi Liu (1):
>   iommu/vt-d: Drop s1_pgtbl from dmar_domain
> 
> Zhenzhong Duan (2):
>   iommu/vt-d: Fix checks and print in dmar_fault_dump_ptes()
>   iommu/vt-d: Fix checks and print in pgtable_walk()

Applied, thanks Baolu.