From 25f003de987aed630db265ceae9cd978537a3f80 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 19 Dec 2019 12:03:41 +0000
Subject: drivers/iommu: Take a ref to the IOMMU driver prior to ->add_device()

To avoid accidental removal of an active IOMMU driver module, take a
reference to the driver module in 'iommu_probe_device()' immediately
prior to invoking the '->add_device()' callback and hold it until the
after the device has been removed by '->remove_device()'.

Suggested-by: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Will Deacon <will@kernel.org>
Tested-by: John Garry <john.garry@huawei.com> # smmu v3
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/iommu.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index f2223cbb5fd5..e9f94d3f7a04 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -246,9 +246,10 @@ struct iommu_iotlb_gather {
  * @sva_get_pasid: Get PASID associated to a SVA handle
  * @page_response: handle page request response
  * @cache_invalidate: invalidate translation caches
- * @pgsize_bitmap: bitmap of all possible supported page sizes
  * @sva_bind_gpasid: bind guest pasid and mm
  * @sva_unbind_gpasid: unbind guest pasid and mm
+ * @pgsize_bitmap: bitmap of all possible supported page sizes
+ * @owner: Driver module providing these ops
  */
 struct iommu_ops {
 	bool (*capable)(enum iommu_cap);
@@ -318,6 +319,7 @@ struct iommu_ops {
 	int (*sva_unbind_gpasid)(struct device *dev, int pasid);
 
 	unsigned long pgsize_bitmap;
+	struct module *owner;
 };
 
 /**
-- 
cgit v1.2.3


From f9f6971ebb75f5bc302d77e3380dd6363cc1a0f6 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Wed, 18 Dec 2019 14:42:01 +0100
Subject: iommu: Implement generic_iommu_put_resv_regions()

Implement a generic function for removing reserved regions. This can be
used by drivers that don't do anything fancy with these regions other
than allocating memory for them.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 19 +++++++++++++++++++
 include/linux/iommu.h |  2 ++
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index fdd40756dbc1..101f2d68eb6e 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2229,6 +2229,25 @@ void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 		ops->put_resv_regions(dev, list);
 }
 
+/**
+ * generic_iommu_put_resv_regions - Reserved region driver helper
+ * @dev: device for which to free reserved regions
+ * @list: reserved region list for device
+ *
+ * IOMMU drivers can use this to implement their .put_resv_regions() callback
+ * for simple reservations. Memory allocated for each reserved region will be
+ * freed. If an IOMMU driver allocates additional resources per region, it is
+ * going to have to implement a custom callback.
+ */
+void generic_iommu_put_resv_regions(struct device *dev, struct list_head *list)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, list, list)
+		kfree(entry);
+}
+EXPORT_SYMBOL(generic_iommu_put_resv_regions);
+
 struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
 						  size_t length, int prot,
 						  enum iommu_resv_type type)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index f2223cbb5fd5..e80b83b8cab8 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -456,6 +456,8 @@ extern void iommu_set_fault_handler(struct iommu_domain *domain,
 
 extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
 extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
+extern void generic_iommu_put_resv_regions(struct device *dev,
+					   struct list_head *list);
 extern int iommu_request_dm_for_dev(struct device *dev);
 extern int iommu_request_dma_domain_for_dev(struct device *dev);
 extern void iommu_set_default_passthrough(bool cmd_line);
-- 
cgit v1.2.3


From ff3dc6521f78132eaaf62a842c3ece9060dcde26 Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
Date: Thu, 2 Jan 2020 08:18:03 +0800
Subject: iommu/vt-d: Fix CPU and IOMMU SVM feature matching checks

Shared Virtual Memory(SVM) is based on a collective set of hardware
features detected at runtime. There are requirements for matching CPU
and IOMMU capabilities.

The current code checks CPU and IOMMU feature set for SVM support but
the result is never stored nor used. Therefore, SVM can still be used
even when these checks failed. The consequences can be:
1. CPU uses 5-level paging mode for virtual address of 57 bits, but
IOMMU can only support 4-level paging mode with 48 bits address for DMA.
2. 1GB page size is used by CPU but IOMMU does not support it. VT-d
unrecoverable faults may be generated.

The best solution to fix these problems is to prevent them in the first
place.

This patch consolidates code for checking PASID, CPU vs. IOMMU paging
mode compatibility, as well as provides specific error messages for
each failed checks. On sane hardware configurations, these error message
shall never appear in kernel log.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel-iommu.c | 10 ++--------
 drivers/iommu/intel-svm.c   | 40 +++++++++++++++++++++++++++-------------
 include/linux/intel-iommu.h |  5 ++++-
 3 files changed, 33 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 26c40134817e..5328e2ed2dd3 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3299,10 +3299,7 @@ static int __init init_dmars(void)
 
 		if (!ecap_pass_through(iommu->ecap))
 			hw_pass_through = 0;
-#ifdef CONFIG_INTEL_IOMMU_SVM
-		if (pasid_supported(iommu))
-			intel_svm_init(iommu);
-#endif
+		intel_svm_check(iommu);
 	}
 
 	/*
@@ -4495,10 +4492,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 	if (ret)
 		goto out;
 
-#ifdef CONFIG_INTEL_IOMMU_SVM
-	if (pasid_supported(iommu))
-		intel_svm_init(iommu);
-#endif
+	intel_svm_check(iommu);
 
 	if (dmaru->ignored) {
 		/*
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index dca88f9fdf29..e4a5d542b84f 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -23,19 +23,6 @@
 
 static irqreturn_t prq_event_thread(int irq, void *d);
 
-int intel_svm_init(struct intel_iommu *iommu)
-{
-	if (cpu_feature_enabled(X86_FEATURE_GBPAGES) &&
-			!cap_fl1gp_support(iommu->cap))
-		return -EINVAL;
-
-	if (cpu_feature_enabled(X86_FEATURE_LA57) &&
-			!cap_5lp_support(iommu->cap))
-		return -EINVAL;
-
-	return 0;
-}
-
 #define PRQ_ORDER 0
 
 int intel_svm_enable_prq(struct intel_iommu *iommu)
@@ -99,6 +86,33 @@ int intel_svm_finish_prq(struct intel_iommu *iommu)
 	return 0;
 }
 
+static inline bool intel_svm_capable(struct intel_iommu *iommu)
+{
+	return iommu->flags & VTD_FLAG_SVM_CAPABLE;
+}
+
+void intel_svm_check(struct intel_iommu *iommu)
+{
+	if (!pasid_supported(iommu))
+		return;
+
+	if (cpu_feature_enabled(X86_FEATURE_GBPAGES) &&
+	    !cap_fl1gp_support(iommu->cap)) {
+		pr_err("%s SVM disabled, incompatible 1GB page capability\n",
+		       iommu->name);
+		return;
+	}
+
+	if (cpu_feature_enabled(X86_FEATURE_LA57) &&
+	    !cap_5lp_support(iommu->cap)) {
+		pr_err("%s SVM disabled, incompatible paging mode\n",
+		       iommu->name);
+		return;
+	}
+
+	iommu->flags |= VTD_FLAG_SVM_CAPABLE;
+}
+
 static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev,
 				unsigned long address, unsigned long pages, int ih)
 {
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 6d8bf4bdf240..aaece25c055f 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -435,6 +435,7 @@ enum {
 
 #define VTD_FLAG_TRANS_PRE_ENABLED	(1 << 0)
 #define VTD_FLAG_IRQ_REMAP_PRE_ENABLED	(1 << 1)
+#define VTD_FLAG_SVM_CAPABLE		(1 << 2)
 
 extern int intel_iommu_sm;
 
@@ -658,7 +659,7 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu);
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev);
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
-int intel_svm_init(struct intel_iommu *iommu);
+extern void intel_svm_check(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
 
@@ -686,6 +687,8 @@ struct intel_svm {
 };
 
 extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev);
+#else
+static inline void intel_svm_check(struct intel_iommu *iommu) {}
 #endif
 
 #ifdef CONFIG_INTEL_IOMMU_DEBUGFS
-- 
cgit v1.2.3


From 984d03adc9bdfb1bea408f9cc41a67214ccdffd3 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Thu, 2 Jan 2020 08:18:11 +0800
Subject: iommu/vt-d: trace: Extend map_sg trace event

Current map_sg stores trace message in a coarse manner. This
extends it so that more detailed messages could be traced.

The map_sg trace message looks like:

map_sg: dev=0000:00:17.0 [1/9] dev_addr=0xf8f90000 phys_addr=0x158051000 size=4096
map_sg: dev=0000:00:17.0 [2/9] dev_addr=0xf8f91000 phys_addr=0x15a858000 size=4096
map_sg: dev=0000:00:17.0 [3/9] dev_addr=0xf8f92000 phys_addr=0x15aa13000 size=4096
map_sg: dev=0000:00:17.0 [4/9] dev_addr=0xf8f93000 phys_addr=0x1570f1000 size=8192
map_sg: dev=0000:00:17.0 [5/9] dev_addr=0xf8f95000 phys_addr=0x15c6d0000 size=4096
map_sg: dev=0000:00:17.0 [6/9] dev_addr=0xf8f96000 phys_addr=0x157194000 size=4096
map_sg: dev=0000:00:17.0 [7/9] dev_addr=0xf8f97000 phys_addr=0x169552000 size=4096
map_sg: dev=0000:00:17.0 [8/9] dev_addr=0xf8f98000 phys_addr=0x169dde000 size=4096
map_sg: dev=0000:00:17.0 [9/9] dev_addr=0xf8f99000 phys_addr=0x148351000 size=4096

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel-iommu.c        |  7 ++++--
 include/trace/events/intel_iommu.h | 48 +++++++++++++++++++++++++++++++++-----
 2 files changed, 47 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 0d100741cf2e..fb21a7745db2 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3776,8 +3776,8 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 		return 0;
 	}
 
-	trace_map_sg(dev, iova_pfn << PAGE_SHIFT,
-		     sg_phys(sglist), size << VTD_PAGE_SHIFT);
+	for_each_sg(sglist, sg, nelems, i)
+		trace_map_sg(dev, i + 1, nelems, sg);
 
 	return nelems;
 }
@@ -3989,6 +3989,9 @@ bounce_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
 		sg_dma_len(sg) = sg->length;
 	}
 
+	for_each_sg(sglist, sg, nelems, i)
+		trace_bounce_map_sg(dev, i + 1, nelems, sg);
+
 	return nelems;
 
 out_unmap:
diff --git a/include/trace/events/intel_iommu.h b/include/trace/events/intel_iommu.h
index 54e61d456cdf..112bd06487bf 100644
--- a/include/trace/events/intel_iommu.h
+++ b/include/trace/events/intel_iommu.h
@@ -49,12 +49,6 @@ DEFINE_EVENT(dma_map, map_single,
 	TP_ARGS(dev, dev_addr, phys_addr, size)
 );
 
-DEFINE_EVENT(dma_map, map_sg,
-	TP_PROTO(struct device *dev, dma_addr_t dev_addr, phys_addr_t phys_addr,
-		 size_t size),
-	TP_ARGS(dev, dev_addr, phys_addr, size)
-);
-
 DEFINE_EVENT(dma_map, bounce_map_single,
 	TP_PROTO(struct device *dev, dma_addr_t dev_addr, phys_addr_t phys_addr,
 		 size_t size),
@@ -99,6 +93,48 @@ DEFINE_EVENT(dma_unmap, bounce_unmap_single,
 	TP_ARGS(dev, dev_addr, size)
 );
 
+DECLARE_EVENT_CLASS(dma_map_sg,
+	TP_PROTO(struct device *dev, int index, int total,
+		 struct scatterlist *sg),
+
+	TP_ARGS(dev, index, total, sg),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(dev))
+		__field(dma_addr_t, dev_addr)
+		__field(phys_addr_t, phys_addr)
+		__field(size_t,	size)
+		__field(int, index)
+		__field(int, total)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name(dev));
+		__entry->dev_addr = sg->dma_address;
+		__entry->phys_addr = sg_phys(sg);
+		__entry->size = sg->dma_length;
+		__entry->index = index;
+		__entry->total = total;
+	),
+
+	TP_printk("dev=%s [%d/%d] dev_addr=0x%llx phys_addr=0x%llx size=%zu",
+		  __get_str(dev_name), __entry->index, __entry->total,
+		  (unsigned long long)__entry->dev_addr,
+		  (unsigned long long)__entry->phys_addr,
+		  __entry->size)
+);
+
+DEFINE_EVENT(dma_map_sg, map_sg,
+	TP_PROTO(struct device *dev, int index, int total,
+		 struct scatterlist *sg),
+	TP_ARGS(dev, index, total, sg)
+);
+
+DEFINE_EVENT(dma_map_sg, bounce_map_sg,
+	TP_PROTO(struct device *dev, int index, int total,
+		 struct scatterlist *sg),
+	TP_ARGS(dev, index, total, sg)
+);
 #endif /* _TRACE_INTEL_IOMMU_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From ddf09b6d43ece8e4d5591e4957e89c4fe7714792 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Thu, 2 Jan 2020 08:18:17 +0800
Subject: iommu/vt-d: Setup pasid entries for iova over first level

Intel VT-d in scalable mode supports two types of page tables for
IOVA translation: first level and second level. The IOMMU driver
can choose one from both for IOVA translation according to the use
case. This sets up the pasid entry if a domain is selected to use
the first-level page table for iova translation.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel-iommu.c | 57 +++++++++++++++++++++++++++++++++++++++++----
 include/linux/intel-iommu.h | 16 ++++++++-----
 2 files changed, 62 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 35f65628202c..071cbc172ce8 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -571,6 +571,11 @@ static inline int domain_type_is_si(struct dmar_domain *domain)
 	return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY;
 }
 
+static inline bool domain_use_first_level(struct dmar_domain *domain)
+{
+	return domain->flags & DOMAIN_FLAG_USE_FIRST_LEVEL;
+}
+
 static inline int domain_pfn_supported(struct dmar_domain *domain,
 				       unsigned long pfn)
 {
@@ -932,6 +937,8 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 
 			domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
 			pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
+			if (domain_use_first_level(domain))
+				pteval |= DMA_FL_PTE_XD;
 			if (cmpxchg64(&pte->val, 0ULL, pteval))
 				/* Someone else set it while we were thinking; use theirs. */
 				free_pgtable_page(tmp_page);
@@ -2281,17 +2288,20 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	unsigned long sg_res = 0;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
+	u64 attr;
 
 	BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1));
 
 	if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
 		return -EINVAL;
 
-	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
+	attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
+	if (domain_use_first_level(domain))
+		attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD;
 
 	if (!sg) {
 		sg_res = nr_pages;
-		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
+		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
 	}
 
 	while (nr_pages > 0) {
@@ -2303,7 +2313,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			sg_res = aligned_nrpages(sg->offset, sg->length);
 			sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + pgoff;
 			sg->dma_length = sg->length;
-			pteval = (sg_phys(sg) - pgoff) | prot;
+			pteval = (sg_phys(sg) - pgoff) | attr;
 			phys_pfn = pteval >> VTD_PAGE_SHIFT;
 		}
 
@@ -2515,6 +2525,36 @@ dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
 	return NULL;
 }
 
+static int domain_setup_first_level(struct intel_iommu *iommu,
+				    struct dmar_domain *domain,
+				    struct device *dev,
+				    int pasid)
+{
+	int flags = PASID_FLAG_SUPERVISOR_MODE;
+	struct dma_pte *pgd = domain->pgd;
+	int agaw, level;
+
+	/*
+	 * 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);
+	if (level != 4 && level != 5)
+		return -EINVAL;
+
+	flags |= (level == 5) ? PASID_FLAG_FL5LP : 0;
+
+	return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
+					     domain->iommu_did[iommu->seq_id],
+					     flags);
+}
+
 static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 						    int bus, int devfn,
 						    struct device *dev,
@@ -2614,6 +2654,9 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 		if (hw_pass_through && domain_type_is_si(domain))
 			ret = intel_pasid_setup_pass_through(iommu, domain,
 					dev, PASID_RID2PASID);
+		else if (domain_use_first_level(domain))
+			ret = domain_setup_first_level(iommu, domain, dev,
+					PASID_RID2PASID);
 		else
 			ret = intel_pasid_setup_second_level(iommu, domain,
 					dev, PASID_RID2PASID);
@@ -5374,8 +5417,12 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 		goto attach_failed;
 
 	/* Setup the PASID entry for mediated devices: */
-	ret = intel_pasid_setup_second_level(iommu, domain, dev,
-					     domain->default_pasid);
+	if (domain_use_first_level(domain))
+		ret = domain_setup_first_level(iommu, domain, dev,
+					       domain->default_pasid);
+	else
+		ret = intel_pasid_setup_second_level(iommu, domain, dev,
+						     domain->default_pasid);
 	if (ret)
 		goto table_failed;
 	spin_unlock(&iommu->lock);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index aaece25c055f..454c69712131 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -34,10 +34,13 @@
 #define VTD_STRIDE_SHIFT        (9)
 #define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
 
-#define DMA_PTE_READ (1)
-#define DMA_PTE_WRITE (2)
-#define DMA_PTE_LARGE_PAGE (1 << 7)
-#define DMA_PTE_SNP (1 << 11)
+#define DMA_PTE_READ		BIT_ULL(0)
+#define DMA_PTE_WRITE		BIT_ULL(1)
+#define DMA_PTE_LARGE_PAGE	BIT_ULL(7)
+#define DMA_PTE_SNP		BIT_ULL(11)
+
+#define DMA_FL_PTE_PRESENT	BIT_ULL(0)
+#define DMA_FL_PTE_XD		BIT_ULL(63)
 
 #define CONTEXT_TT_MULTI_LEVEL	0
 #define CONTEXT_TT_DEV_IOTLB	1
@@ -610,10 +613,11 @@ static inline void dma_clear_pte(struct dma_pte *pte)
 static inline u64 dma_pte_addr(struct dma_pte *pte)
 {
 #ifdef CONFIG_64BIT
-	return pte->val & VTD_PAGE_MASK;
+	return pte->val & VTD_PAGE_MASK & (~DMA_FL_PTE_XD);
 #else
 	/* Must have a full atomic 64-bit read */
-	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK;
+	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) &
+			VTD_PAGE_MASK & (~DMA_FL_PTE_XD);
 #endif
 }
 
-- 
cgit v1.2.3


From 33cd6e642d6a76c1d338ce25cba5fd79a5029011 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Thu, 2 Jan 2020 08:18:18 +0800
Subject: iommu/vt-d: Flush PASID-based iotlb for iova over first level

When software has changed first-level tables, it should invalidate
the affected IOTLB and the paging-structure-caches using the PASID-
based-IOTLB Invalidate Descriptor defined in spec 6.5.2.4.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/dmar.c        | 41 +++++++++++++++++++++++++++++++++
 drivers/iommu/intel-iommu.c | 56 +++++++++++++++++++++++++++++++++------------
 include/linux/intel-iommu.h |  2 ++
 3 files changed, 84 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 3acfa6a25fa2..fb30d5053664 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1371,6 +1371,47 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	qi_submit_sync(&desc, iommu);
 }
 
+/* PASID-based IOTLB invalidation */
+void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
+		     unsigned long npages, bool ih)
+{
+	struct qi_desc desc = {.qw2 = 0, .qw3 = 0};
+
+	/*
+	 * npages == -1 means a PASID-selective invalidation, otherwise,
+	 * a positive value for Page-selective-within-PASID invalidation.
+	 * 0 is not a valid input.
+	 */
+	if (WARN_ON(!npages)) {
+		pr_err("Invalid input npages = %ld\n", npages);
+		return;
+	}
+
+	if (npages == -1) {
+		desc.qw0 = QI_EIOTLB_PASID(pasid) |
+				QI_EIOTLB_DID(did) |
+				QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+				QI_EIOTLB_TYPE;
+		desc.qw1 = 0;
+	} else {
+		int mask = ilog2(__roundup_pow_of_two(npages));
+		unsigned long align = (1ULL << (VTD_PAGE_SHIFT + mask));
+
+		if (WARN_ON_ONCE(!ALIGN(addr, align)))
+			addr &= ~(align - 1);
+
+		desc.qw0 = QI_EIOTLB_PASID(pasid) |
+				QI_EIOTLB_DID(did) |
+				QI_EIOTLB_GRAN(QI_GRAN_PSI_PASID) |
+				QI_EIOTLB_TYPE;
+		desc.qw1 = QI_EIOTLB_ADDR(addr) |
+				QI_EIOTLB_IH(ih) |
+				QI_EIOTLB_AM(mask);
+	}
+
+	qi_submit_sync(&desc, iommu);
+}
+
 /*
  * Disable Queued Invalidation interface.
  */
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 071cbc172ce8..54db6bc0b281 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1509,6 +1509,20 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
+static void domain_flush_piotlb(struct intel_iommu *iommu,
+				struct dmar_domain *domain,
+				u64 addr, unsigned long npages, bool ih)
+{
+	u16 did = domain->iommu_did[iommu->seq_id];
+
+	if (domain->default_pasid)
+		qi_flush_piotlb(iommu, did, domain->default_pasid,
+				addr, npages, ih);
+
+	if (!list_empty(&domain->devices))
+		qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, npages, ih);
+}
+
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 				  struct dmar_domain *domain,
 				  unsigned long pfn, unsigned int pages,
@@ -1522,18 +1536,23 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 
 	if (ih)
 		ih = 1 << 6;
-	/*
-	 * Fallback to domain selective flush if no PSI support or the size is
-	 * too big.
-	 * PSI requires page size to be 2 ^ x, and the base address is naturally
-	 * aligned to the size
-	 */
-	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);
+
+	if (domain_use_first_level(domain)) {
+		domain_flush_piotlb(iommu, domain, addr, pages, ih);
+	} else {
+		/*
+		 * Fallback to domain selective flush if no PSI support or
+		 * the size is too big. PSI requires page size to be 2 ^ x,
+		 * and the base address is naturally aligned to the size.
+		 */
+		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);
+	}
 
 	/*
 	 * In caching mode, changes of pages from non-present to present require
@@ -1548,8 +1567,11 @@ static inline 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 */
-	if (cap_caching_mode(iommu->cap))
+	/*
+	 * 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(domain))
 		iommu_flush_iotlb_psi(iommu, domain, pfn, pages, 0, 1);
 	else
 		iommu_flush_write_buffer(iommu);
@@ -1566,7 +1588,11 @@ static void iommu_flush_iova(struct iova_domain *iovad)
 		struct intel_iommu *iommu = g_iommus[idx];
 		u16 did = domain->iommu_did[iommu->seq_id];
 
-		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
+		if (domain_use_first_level(domain))
+			domain_flush_piotlb(iommu, domain, 0, -1, 0);
+		else
+			iommu->flush.flush_iotlb(iommu, did, 0, 0,
+						 DMA_TLB_DSI_FLUSH);
 
 		if (!cap_caching_mode(iommu->cap))
 			iommu_flush_dev_iotlb(get_iommu_domain(iommu, did),
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 454c69712131..3a4708a8a414 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -650,6 +650,8 @@ extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 			  unsigned int size_order, u64 type);
 extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 			u16 qdep, u64 addr, unsigned mask);
+void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
+		     unsigned long npages, bool ih);
 extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
 
 extern int dmar_ir_support(void);
-- 
cgit v1.2.3


From e2726daea583d81e447b71e09b79e67f618d6152 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Thu, 2 Jan 2020 08:18:22 +0800
Subject: iommu/vt-d: debugfs: Add support to show page table internals

Export page table internals of the domain attached to each device.
Example of such dump on a Skylake machine:

$ sudo cat /sys/kernel/debug/iommu/intel/domain_translation_struct
[ ... ]
Device 0000:00:14.0 with pasid 0 @0x15f3d9000
IOVA_PFN                PML5E                   PML4E
0x000000008ced0 |       0x0000000000000000      0x000000015f3da003
0x000000008ced1 |       0x0000000000000000      0x000000015f3da003
0x000000008ced2 |       0x0000000000000000      0x000000015f3da003
0x000000008ced3 |       0x0000000000000000      0x000000015f3da003
0x000000008ced4 |       0x0000000000000000      0x000000015f3da003
0x000000008ced5 |       0x0000000000000000      0x000000015f3da003
0x000000008ced6 |       0x0000000000000000      0x000000015f3da003
0x000000008ced7 |       0x0000000000000000      0x000000015f3da003
0x000000008ced8 |       0x0000000000000000      0x000000015f3da003
0x000000008ced9 |       0x0000000000000000      0x000000015f3da003

PDPE                    PDE                     PTE
0x000000015f3db003      0x000000015f3dc003      0x000000008ced0003
0x000000015f3db003      0x000000015f3dc003      0x000000008ced1003
0x000000015f3db003      0x000000015f3dc003      0x000000008ced2003
0x000000015f3db003      0x000000015f3dc003      0x000000008ced3003
0x000000015f3db003      0x000000015f3dc003      0x000000008ced4003
0x000000015f3db003      0x000000015f3dc003      0x000000008ced5003
0x000000015f3db003      0x000000015f3dc003      0x000000008ced6003
0x000000015f3db003      0x000000015f3dc003      0x000000008ced7003
0x000000015f3db003      0x000000015f3dc003      0x000000008ced8003
0x000000015f3db003      0x000000015f3dc003      0x000000008ced9003
[ ... ]

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel-iommu-debugfs.c | 75 +++++++++++++++++++++++++++++++++++++
 drivers/iommu/intel-iommu.c         |  4 +-
 include/linux/intel-iommu.h         |  2 +
 3 files changed, 79 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c
index 471f05d452e0..c1257bef553c 100644
--- a/drivers/iommu/intel-iommu-debugfs.c
+++ b/drivers/iommu/intel-iommu-debugfs.c
@@ -5,6 +5,7 @@
  * Authors: Gayatri Kammela <gayatri.kammela@intel.com>
  *	    Sohil Mehta <sohil.mehta@intel.com>
  *	    Jacob Pan <jacob.jun.pan@linux.intel.com>
+ *	    Lu Baolu <baolu.lu@linux.intel.com>
  */
 
 #include <linux/debugfs.h>
@@ -283,6 +284,77 @@ static int dmar_translation_struct_show(struct seq_file *m, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(dmar_translation_struct);
 
+static inline unsigned long level_to_directory_size(int level)
+{
+	return BIT_ULL(VTD_PAGE_SHIFT + VTD_STRIDE_SHIFT * (level - 1));
+}
+
+static inline void
+dump_page_info(struct seq_file *m, unsigned long iova, u64 *path)
+{
+	seq_printf(m, "0x%013lx |\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\n",
+		   iova >> VTD_PAGE_SHIFT, path[5], path[4],
+		   path[3], path[2], path[1]);
+}
+
+static void pgtable_walk_level(struct seq_file *m, struct dma_pte *pde,
+			       int level, unsigned long start,
+			       u64 *path)
+{
+	int i;
+
+	if (level > 5 || level < 1)
+		return;
+
+	for (i = 0; i < BIT_ULL(VTD_STRIDE_SHIFT);
+			i++, pde++, start += level_to_directory_size(level)) {
+		if (!dma_pte_present(pde))
+			continue;
+
+		path[level] = pde->val;
+		if (dma_pte_superpage(pde) || level == 1)
+			dump_page_info(m, start, path);
+		else
+			pgtable_walk_level(m, phys_to_virt(dma_pte_addr(pde)),
+					   level - 1, start, path);
+		path[level] = 0;
+	}
+}
+
+static int show_device_domain_translation(struct device *dev, void *data)
+{
+	struct dmar_domain *domain = find_domain(dev);
+	struct seq_file *m = data;
+	u64 path[6] = { 0 };
+
+	if (!domain)
+		return 0;
+
+	seq_printf(m, "Device %s with pasid %d @0x%llx\n",
+		   dev_name(dev), domain->default_pasid,
+		   (u64)virt_to_phys(domain->pgd));
+	seq_puts(m, "IOVA_PFN\t\tPML5E\t\t\tPML4E\t\t\tPDPE\t\t\tPDE\t\t\tPTE\n");
+
+	pgtable_walk_level(m, domain->pgd, domain->agaw + 2, 0, path);
+	seq_putc(m, '\n');
+
+	return 0;
+}
+
+static int domain_translation_struct_show(struct seq_file *m, void *unused)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	ret = bus_for_each_dev(&pci_bus_type, NULL, m,
+			       show_device_domain_translation);
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	return ret;
+}
+DEFINE_SHOW_ATTRIBUTE(domain_translation_struct);
+
 #ifdef CONFIG_IRQ_REMAP
 static void ir_tbl_remap_entry_show(struct seq_file *m,
 				    struct intel_iommu *iommu)
@@ -396,6 +468,9 @@ void __init intel_iommu_debugfs_init(void)
 			    &iommu_regset_fops);
 	debugfs_create_file("dmar_translation_struct", 0444, intel_iommu_debug,
 			    NULL, &dmar_translation_struct_fops);
+	debugfs_create_file("domain_translation_struct", 0444,
+			    intel_iommu_debug, NULL,
+			    &domain_translation_struct_fops);
 #ifdef CONFIG_IRQ_REMAP
 	debugfs_create_file("ir_translation_struct", 0444, intel_iommu_debug,
 			    NULL, &ir_translation_struct_fops);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 51d60bad0b1d..609931f6d771 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -396,7 +396,7 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
 
 #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
 #define DEFER_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-2))
-static DEFINE_SPINLOCK(device_domain_lock);
+DEFINE_SPINLOCK(device_domain_lock);
 static LIST_HEAD(device_domain_list);
 
 #define device_needs_bounce(d) (!intel_no_bounce && dev_is_pci(d) &&	\
@@ -2513,7 +2513,7 @@ static void domain_remove_dev_info(struct dmar_domain *domain)
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
-static struct dmar_domain *find_domain(struct device *dev)
+struct dmar_domain *find_domain(struct device *dev)
 {
 	struct device_domain_info *info;
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 3a4708a8a414..4a16b39ae353 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -441,6 +441,7 @@ enum {
 #define VTD_FLAG_SVM_CAPABLE		(1 << 2)
 
 extern int intel_iommu_sm;
+extern spinlock_t device_domain_lock;
 
 #define sm_supported(iommu)	(intel_iommu_sm && ecap_smts((iommu)->ecap))
 #define pasid_supported(iommu)	(sm_supported(iommu) &&			\
@@ -663,6 +664,7 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info,
 				     void *data), void *data);
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev);
+struct dmar_domain *find_domain(struct device *dev);
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
 extern void intel_svm_check(struct intel_iommu *iommu);
-- 
cgit v1.2.3


From fc10cca69ee8af49778ad76c1e5fddf83d5026c8 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 9 Jan 2020 14:08:41 +0000
Subject: drivers/iommu: Initialise module 'owner' field in
 iommu_device_set_ops()

Requiring each IOMMU driver to initialise the 'owner' field of their
'struct iommu_ops' is error-prone and easily forgotten. Follow the
example set by PCI and USB by assigning THIS_MODULE automatically when
registering the ops structure with IOMMU core.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Suggested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu-v3.c |  1 -
 drivers/iommu/arm-smmu.c    |  1 -
 include/linux/iommu.h       | 11 +++++++++--
 3 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 03dc97842875..e82997a705a8 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2733,7 +2733,6 @@ static struct iommu_ops arm_smmu_ops = {
 	.get_resv_regions	= arm_smmu_get_resv_regions,
 	.put_resv_regions	= arm_smmu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
-	.owner			= THIS_MODULE,
 };
 
 /* Probing and initialisation functions */
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 5ef1f2e100d7..93d332423f6f 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1623,7 +1623,6 @@ static struct iommu_ops arm_smmu_ops = {
 	.get_resv_regions	= arm_smmu_get_resv_regions,
 	.put_resv_regions	= arm_smmu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
-	.owner			= THIS_MODULE,
 };
 
 static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e9f94d3f7a04..90007c92ad2d 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -388,12 +388,19 @@ void iommu_device_sysfs_remove(struct iommu_device *iommu);
 int  iommu_device_link(struct iommu_device   *iommu, struct device *link);
 void iommu_device_unlink(struct iommu_device *iommu, struct device *link);
 
-static inline void iommu_device_set_ops(struct iommu_device *iommu,
-					const struct iommu_ops *ops)
+static inline void __iommu_device_set_ops(struct iommu_device *iommu,
+					  const struct iommu_ops *ops)
 {
 	iommu->ops = ops;
 }
 
+#define iommu_device_set_ops(iommu, ops)				\
+do {									\
+	struct iommu_ops *__ops = (struct iommu_ops *)(ops);		\
+	__ops->owner = THIS_MODULE;					\
+	__iommu_device_set_ops(iommu, __ops);				\
+} while (0)
+
 static inline void iommu_device_set_fwnode(struct iommu_device *iommu,
 					   struct fwnode_handle *fwnode)
 {
-- 
cgit v1.2.3


From d1e5f26f14272b5039cc198569ec4fabed14e6db Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Fri, 25 Oct 2019 19:08:37 +0100
Subject: iommu/io-pgtable-arm: Rationalise TTBRn handling

TTBR1 values have so far been redundant since no users implement any
support for split address spaces. Crucially, though, one of the main
reasons for wanting to do so is to be able to manage each half entirely
independently, e.g. context-switching one set of mappings without
disturbing the other. Thus it seems unlikely that tying two tables
together in a single io_pgtable_cfg would ever be particularly desirable
or useful.

Streamline the configs to just a single conceptual TTBR value
representing the allocated table. This paves the way for future users to
support split address spaces by simply allocating a table and dealing
with the detailed TTBRn logistics themselves.

Tested-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[will: Drop change to ttbr value]
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu-v3.c        |  2 +-
 drivers/iommu/arm-smmu.c           |  9 ++++-----
 drivers/iommu/io-pgtable-arm-v7s.c | 17 ++++++++---------
 drivers/iommu/io-pgtable-arm.c     |  5 ++---
 drivers/iommu/ipmmu-vmsa.c         |  2 +-
 drivers/iommu/msm_iommu.c          |  4 ++--
 drivers/iommu/mtk_iommu.c          |  4 ++--
 drivers/iommu/qcom_iommu.c         |  3 +--
 include/linux/io-pgtable.h         |  4 ++--
 9 files changed, 23 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index aa7e53023585..cf2ae065a6c2 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2166,7 +2166,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 	}
 
 	cfg->cd.asid	= (u16)asid;
-	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
+	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
 	cfg->cd.tcr	= pgtbl_cfg->arm_lpae_s1_cfg.tcr;
 	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair;
 	return 0;
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 46b87740d708..72640e045268 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -553,13 +553,12 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 	/* TTBRs */
 	if (stage1) {
 		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
-			cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr[0];
-			cb->ttbr[1] = pgtbl_cfg->arm_v7s_cfg.ttbr[1];
+			cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr;
+			cb->ttbr[1] = 0;
 		} else {
-			cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
+			cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
 			cb->ttbr[0] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
-			cb->ttbr[1] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
-			cb->ttbr[1] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
+			cb->ttbr[1] = FIELD_PREP(TTBRn_ASID, cfg->asid);
 		}
 	} else {
 		cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 7c3bd2c3cdca..eac886f7619d 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -822,15 +822,14 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	/* Ensure the empty pgd is visible before any actual TTBR write */
 	wmb();
 
-	/* TTBRs */
-	cfg->arm_v7s_cfg.ttbr[0] = virt_to_phys(data->pgd) |
-				   ARM_V7S_TTBR_S | ARM_V7S_TTBR_NOS |
-				   (cfg->coherent_walk ?
-				   (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
-				    ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
-				   (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
-				    ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
-	cfg->arm_v7s_cfg.ttbr[1] = 0;
+	/* TTBR */
+	cfg->arm_v7s_cfg.ttbr = virt_to_phys(data->pgd) |
+				ARM_V7S_TTBR_S | ARM_V7S_TTBR_NOS |
+				(cfg->coherent_walk ?
+				(ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
+				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
+				(ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
+				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
 	return &data->iop;
 
 out_free_data:
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index bdf47f745268..7b422b9fe05b 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -872,9 +872,8 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	/* Ensure the empty pgd is visible before any actual TTBR write */
 	wmb();
 
-	/* TTBRs */
-	cfg->arm_lpae_s1_cfg.ttbr[0] = virt_to_phys(data->pgd);
-	cfg->arm_lpae_s1_cfg.ttbr[1] = 0;
+	/* TTBR */
+	cfg->arm_lpae_s1_cfg.ttbr = virt_to_phys(data->pgd);
 	return &data->iop;
 
 out_free_data:
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index d02edd2751f3..ecb3f9464dd5 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -374,7 +374,7 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain)
 	u32 tmp;
 
 	/* TTBR0 */
-	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr[0];
+	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr;
 	ipmmu_ctx_write_root(domain, IMTTLBR0, ttbr);
 	ipmmu_ctx_write_root(domain, IMTTUBR0, ttbr >> 32);
 
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 93f14bca26ee..94a6df1bddd6 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -279,8 +279,8 @@ static void __program_context(void __iomem *base, int ctx,
 	SET_V2PCFG(base, ctx, 0x3);
 
 	SET_TTBCR(base, ctx, priv->cfg.arm_v7s_cfg.tcr);
-	SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[0]);
-	SET_TTBR1(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[1]);
+	SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr);
+	SET_TTBR1(base, ctx, 0);
 
 	/* Set prrr and nmrr */
 	SET_PRRR(base, ctx, priv->cfg.arm_v7s_cfg.prrr);
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 6fc1f5ecf91e..95945f467c03 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -367,7 +367,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 	/* Update the pgtable base address register of the M4U HW */
 	if (!data->m4u_dom) {
 		data->m4u_dom = dom;
-		writel(dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
+		writel(dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
 		       data->base + REG_MMU_PT_BASE_ADDR);
 	}
 
@@ -765,7 +765,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
 	writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
 	writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
 	if (m4u_dom)
-		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
+		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
 		       base + REG_MMU_PT_BASE_ADDR);
 	return 0;
 }
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 52f38292df5b..c200bc066257 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -269,10 +269,9 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 
 		/* TTBRs */
 		iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
-				pgtbl_cfg.arm_lpae_s1_cfg.ttbr[0] |
+				pgtbl_cfg.arm_lpae_s1_cfg.ttbr |
 				FIELD_PREP(TTBRn_ASID, ctx->asid));
 		iommu_writeq(ctx, ARM_SMMU_CB_TTBR1,
-				pgtbl_cfg.arm_lpae_s1_cfg.ttbr[1] |
 				FIELD_PREP(TTBRn_ASID, ctx->asid));
 
 		/* TCR */
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index ee21eedafe98..53bca5343f52 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -100,7 +100,7 @@ struct io_pgtable_cfg {
 	/* Low-level data specific to the table format */
 	union {
 		struct {
-			u64	ttbr[2];
+			u64	ttbr;
 			u64	tcr;
 			u64	mair;
 		} arm_lpae_s1_cfg;
@@ -111,7 +111,7 @@ struct io_pgtable_cfg {
 		} arm_lpae_s2_cfg;
 
 		struct {
-			u32	ttbr[2];
+			u32	ttbr;
 			u32	tcr;
 			u32	nmrr;
 			u32	prrr;
-- 
cgit v1.2.3


From fb485eb18e632ff1071662122b9d9b7d40c23c73 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Fri, 25 Oct 2019 19:08:38 +0100
Subject: iommu/io-pgtable-arm: Rationalise TCR handling

Although it's conceptually nice for the io_pgtable_cfg to provide a
standard VMSA TCR value, the reality is that no VMSA-compliant IOMMU
looks exactly like an Arm CPU, and they all have various other TCR
controls which io-pgtable can't be expected to understand. Thus since
there is an expectation that drivers will have to add to the given TCR
value anyway, let's strip it down to just the essentials that are
directly relevant to io-pgtable's inner workings - namely the various
sizes and the walk attributes.

Tested-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[will: Add missing include of bitfield.h]
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu-v3.c        | 41 ++++------------
 drivers/iommu/arm-smmu.c           |  7 +--
 drivers/iommu/arm-smmu.h           | 28 +++++++++++
 drivers/iommu/io-pgtable-arm-v7s.c |  6 +--
 drivers/iommu/io-pgtable-arm.c     | 98 ++++++++++++++++----------------------
 drivers/iommu/io-pgtable.c         |  2 +-
 drivers/iommu/qcom_iommu.c         |  8 ++--
 include/linux/io-pgtable.h         |  9 +++-
 8 files changed, 95 insertions(+), 104 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index cf2ae065a6c2..d127974afdb7 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -260,27 +260,18 @@
 /* Context descriptor (stage-1 only) */
 #define CTXDESC_CD_DWORDS		8
 #define CTXDESC_CD_0_TCR_T0SZ		GENMASK_ULL(5, 0)
-#define ARM64_TCR_T0SZ			GENMASK_ULL(5, 0)
 #define CTXDESC_CD_0_TCR_TG0		GENMASK_ULL(7, 6)
-#define ARM64_TCR_TG0			GENMASK_ULL(15, 14)
 #define CTXDESC_CD_0_TCR_IRGN0		GENMASK_ULL(9, 8)
-#define ARM64_TCR_IRGN0			GENMASK_ULL(9, 8)
 #define CTXDESC_CD_0_TCR_ORGN0		GENMASK_ULL(11, 10)
-#define ARM64_TCR_ORGN0			GENMASK_ULL(11, 10)
 #define CTXDESC_CD_0_TCR_SH0		GENMASK_ULL(13, 12)
-#define ARM64_TCR_SH0			GENMASK_ULL(13, 12)
 #define CTXDESC_CD_0_TCR_EPD0		(1ULL << 14)
-#define ARM64_TCR_EPD0			(1ULL << 7)
 #define CTXDESC_CD_0_TCR_EPD1		(1ULL << 30)
-#define ARM64_TCR_EPD1			(1ULL << 23)
 
 #define CTXDESC_CD_0_ENDI		(1UL << 15)
 #define CTXDESC_CD_0_V			(1UL << 31)
 
 #define CTXDESC_CD_0_TCR_IPS		GENMASK_ULL(34, 32)
-#define ARM64_TCR_IPS			GENMASK_ULL(34, 32)
 #define CTXDESC_CD_0_TCR_TBI0		(1ULL << 38)
-#define ARM64_TCR_TBI0			(1ULL << 37)
 
 #define CTXDESC_CD_0_AA64		(1UL << 41)
 #define CTXDESC_CD_0_S			(1UL << 44)
@@ -291,10 +282,6 @@
 
 #define CTXDESC_CD_1_TTB0_MASK		GENMASK_ULL(51, 4)
 
-/* Convert between AArch64 (CPU) TCR format and SMMU CD format */
-#define ARM_SMMU_TCR2CD(tcr, fld)	FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \
-					FIELD_GET(ARM64_TCR_##fld, tcr))
-
 /* Command queue */
 #define CMDQ_ENT_SZ_SHIFT		4
 #define CMDQ_ENT_DWORDS			((1 << CMDQ_ENT_SZ_SHIFT) >> 3)
@@ -1439,23 +1426,6 @@ static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
 }
 
 /* Context descriptor manipulation functions */
-static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr)
-{
-	u64 val = 0;
-
-	/* Repack the TCR. Just care about TTBR0 for now */
-	val |= ARM_SMMU_TCR2CD(tcr, T0SZ);
-	val |= ARM_SMMU_TCR2CD(tcr, TG0);
-	val |= ARM_SMMU_TCR2CD(tcr, IRGN0);
-	val |= ARM_SMMU_TCR2CD(tcr, ORGN0);
-	val |= ARM_SMMU_TCR2CD(tcr, SH0);
-	val |= ARM_SMMU_TCR2CD(tcr, EPD0);
-	val |= ARM_SMMU_TCR2CD(tcr, EPD1);
-	val |= ARM_SMMU_TCR2CD(tcr, IPS);
-
-	return val;
-}
-
 static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
 				    struct arm_smmu_s1_cfg *cfg)
 {
@@ -1465,7 +1435,7 @@ static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
 	 * We don't need to issue any invalidation here, as we'll invalidate
 	 * the STE when installing the new entry anyway.
 	 */
-	val = arm_smmu_cpu_tcr_to_cd(cfg->cd.tcr) |
+	val = cfg->cd.tcr |
 #ifdef __BIG_ENDIAN
 	      CTXDESC_CD_0_ENDI |
 #endif
@@ -2151,6 +2121,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 	int asid;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+	typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr = &pgtbl_cfg->arm_lpae_s1_cfg.tcr;
 
 	asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits);
 	if (asid < 0)
@@ -2167,7 +2138,13 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 
 	cfg->cd.asid	= (u16)asid;
 	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
-	cfg->cd.tcr	= pgtbl_cfg->arm_lpae_s1_cfg.tcr;
+	cfg->cd.tcr	= FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, tcr->tsz) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_TG0, tcr->tg) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, tcr->irgn) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, tcr->orgn) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_SH0, tcr->sh) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_IPS, tcr->ips) |
+			  CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
 	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair;
 	return 0;
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 72640e045268..e65eb60812ec 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -540,11 +540,12 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
 			cb->tcr[0] = pgtbl_cfg->arm_v7s_cfg.tcr;
 		} else {
-			cb->tcr[0] = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
-			cb->tcr[1] = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
-			cb->tcr[1] |= FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM);
+			cb->tcr[0] = arm_smmu_lpae_tcr(pgtbl_cfg);
+			cb->tcr[1] = arm_smmu_lpae_tcr2(pgtbl_cfg);
 			if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
 				cb->tcr[1] |= TCR2_AS;
+			else
+				cb->tcr[0] |= TCR_EAE;
 		}
 	} else {
 		cb->tcr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 62b9f0cec49b..aade2b0ae175 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -11,6 +11,7 @@
 #define _ARM_SMMU_H
 
 #include <linux/atomic.h>
+#include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/clk.h>
 #include <linux/device.h>
@@ -158,12 +159,24 @@ enum arm_smmu_cbar_type {
 #define TCR2_SEP			GENMASK(17, 15)
 #define TCR2_SEP_UPSTREAM		0x7
 #define TCR2_AS				BIT(4)
+#define TCR2_PASIZE			GENMASK(3, 0)
 
 #define ARM_SMMU_CB_TTBR0		0x20
 #define ARM_SMMU_CB_TTBR1		0x28
 #define TTBRn_ASID			GENMASK_ULL(63, 48)
 
+/* arm64 headers leak this somehow :( */
+#undef TCR_T0SZ
+
 #define ARM_SMMU_CB_TCR			0x30
+#define TCR_EAE				BIT(31)
+#define TCR_EPD1			BIT(23)
+#define TCR_TG0				GENMASK(15, 14)
+#define TCR_SH0				GENMASK(13, 12)
+#define TCR_ORGN0			GENMASK(11, 10)
+#define TCR_IRGN0			GENMASK(9, 8)
+#define TCR_T0SZ			GENMASK(5, 0)
+
 #define ARM_SMMU_CB_CONTEXTIDR		0x34
 #define ARM_SMMU_CB_S1_MAIR0		0x38
 #define ARM_SMMU_CB_S1_MAIR1		0x3c
@@ -318,6 +331,21 @@ struct arm_smmu_domain {
 	struct iommu_domain		domain;
 };
 
+static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg)
+{
+	return TCR_EPD1 |
+	       FIELD_PREP(TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
+	       FIELD_PREP(TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
+	       FIELD_PREP(TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
+	       FIELD_PREP(TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
+	       FIELD_PREP(TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+}
+
+static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg)
+{
+	return FIELD_PREP(TCR2_PASIZE, cfg->arm_lpae_s1_cfg.tcr.ips) |
+	       FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM);
+}
 
 /* Implementation details, yay! */
 struct arm_smmu_impl {
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 697ffffe34df..4272fe4e17f4 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -149,8 +149,6 @@
 #define ARM_V7S_TTBR_IRGN_ATTR(attr)					\
 	((((attr) & 0x1) << 6) | (((attr) & 0x2) >> 1))
 
-#define ARM_V7S_TCR_PD1			BIT(5)
-
 #ifdef CONFIG_ZONE_DMA32
 #define ARM_V7S_TABLE_GFP_DMA GFP_DMA32
 #define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32
@@ -798,8 +796,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	 */
 	cfg->pgsize_bitmap &= SZ_4K | SZ_64K | SZ_1M | SZ_16M;
 
-	/* TCR: T0SZ=0, disable TTBR1 */
-	cfg->arm_v7s_cfg.tcr = ARM_V7S_TCR_PD1;
+	/* TCR: T0SZ=0, EAE=0 (if applicable) */
+	cfg->arm_v7s_cfg.tcr = 0;
 
 	/*
 	 * TEX remap: the indices used map to the closest equivalent types
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 1c0ec16effbb..a868ce594871 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -100,40 +100,32 @@
 #define ARM_LPAE_PTE_MEMATTR_DEV	(((arm_lpae_iopte)0x1) << 2)
 
 /* Register bits */
-#define ARM_32_LPAE_TCR_EAE		(1 << 31)
-#define ARM_64_LPAE_S2_TCR_RES1		(1U << 31)
+#define ARM_64_LPAE_VTCR_RES1		(1U << 31)
 
-#define ARM_LPAE_TCR_EPD1		(1 << 23)
-
-#define ARM_LPAE_TCR_TG0_4K		(0 << 14)
-#define ARM_LPAE_TCR_TG0_64K		(1 << 14)
-#define ARM_LPAE_TCR_TG0_16K		(2 << 14)
+#define ARM_LPAE_VTCR_TG0_SHIFT		14
+#define ARM_LPAE_TCR_TG0_4K		0
+#define ARM_LPAE_TCR_TG0_64K		1
+#define ARM_LPAE_TCR_TG0_16K		2
 
 #define ARM_LPAE_TCR_SH0_SHIFT		12
-#define ARM_LPAE_TCR_SH0_MASK		0x3
 #define ARM_LPAE_TCR_SH_NS		0
 #define ARM_LPAE_TCR_SH_OS		2
 #define ARM_LPAE_TCR_SH_IS		3
 
 #define ARM_LPAE_TCR_ORGN0_SHIFT	10
 #define ARM_LPAE_TCR_IRGN0_SHIFT	8
-#define ARM_LPAE_TCR_RGN_MASK		0x3
 #define ARM_LPAE_TCR_RGN_NC		0
 #define ARM_LPAE_TCR_RGN_WBWA		1
 #define ARM_LPAE_TCR_RGN_WT		2
 #define ARM_LPAE_TCR_RGN_WB		3
 
-#define ARM_LPAE_TCR_SL0_SHIFT		6
-#define ARM_LPAE_TCR_SL0_MASK		0x3
+#define ARM_LPAE_VTCR_SL0_SHIFT		6
+#define ARM_LPAE_VTCR_SL0_MASK		0x3
 
 #define ARM_LPAE_TCR_T0SZ_SHIFT		0
-#define ARM_LPAE_TCR_SZ_MASK		0xf
-
-#define ARM_LPAE_TCR_PS_SHIFT		16
-#define ARM_LPAE_TCR_PS_MASK		0x7
 
-#define ARM_LPAE_TCR_IPS_SHIFT		32
-#define ARM_LPAE_TCR_IPS_MASK		0x7
+#define ARM_LPAE_VTCR_PS_SHIFT		16
+#define ARM_LPAE_VTCR_PS_MASK		0x7
 
 #define ARM_LPAE_TCR_PS_32_BIT		0x0ULL
 #define ARM_LPAE_TCR_PS_36_BIT		0x1ULL
@@ -792,6 +784,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 {
 	u64 reg;
 	struct arm_lpae_io_pgtable *data;
+	typeof(&cfg->arm_lpae_s1_cfg.tcr) tcr = &cfg->arm_lpae_s1_cfg.tcr;
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NON_STRICT))
@@ -803,58 +796,54 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* TCR */
 	if (cfg->coherent_walk) {
-		reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+		tcr->sh = ARM_LPAE_TCR_SH_IS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+		tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
 	} else {
-		reg = (ARM_LPAE_TCR_SH_OS << ARM_LPAE_TCR_SH0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_ORGN0_SHIFT);
+		tcr->sh = ARM_LPAE_TCR_SH_OS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		tcr->orgn = ARM_LPAE_TCR_RGN_NC;
 	}
 
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		reg |= ARM_LPAE_TCR_TG0_4K;
+		tcr->tg = ARM_LPAE_TCR_TG0_4K;
 		break;
 	case SZ_16K:
-		reg |= ARM_LPAE_TCR_TG0_16K;
+		tcr->tg = ARM_LPAE_TCR_TG0_16K;
 		break;
 	case SZ_64K:
-		reg |= ARM_LPAE_TCR_TG0_64K;
+		tcr->tg = ARM_LPAE_TCR_TG0_64K;
 		break;
 	}
 
 	switch (cfg->oas) {
 	case 32:
-		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_32_BIT;
 		break;
 	case 36:
-		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_36_BIT;
 		break;
 	case 40:
-		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_40_BIT;
 		break;
 	case 42:
-		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_42_BIT;
 		break;
 	case 44:
-		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_44_BIT;
 		break;
 	case 48:
-		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_48_BIT;
 		break;
 	case 52:
-		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_52_BIT;
 		break;
 	default:
 		goto out_free_data;
 	}
 
-	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-
-	/* Disable speculative walks through TTBR1 */
-	reg |= ARM_LPAE_TCR_EPD1;
-	cfg->arm_lpae_s1_cfg.tcr = reg;
+	tcr->tsz = 64ULL - cfg->ias;
 
 	/* MAIRs */
 	reg = (ARM_LPAE_MAIR_ATTR_NC
@@ -915,7 +904,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	}
 
 	/* VTCR */
-	reg = ARM_64_LPAE_S2_TCR_RES1;
+	reg = ARM_64_LPAE_VTCR_RES1;
 	if (cfg->coherent_walk) {
 		reg |= (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
 		       (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
@@ -930,45 +919,45 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		reg |= ARM_LPAE_TCR_TG0_4K;
+		reg |= (ARM_LPAE_TCR_TG0_4K << ARM_LPAE_VTCR_TG0_SHIFT);
 		sl++; /* SL0 format is different for 4K granule size */
 		break;
 	case SZ_16K:
-		reg |= ARM_LPAE_TCR_TG0_16K;
+		reg |= (ARM_LPAE_TCR_TG0_16K << ARM_LPAE_VTCR_TG0_SHIFT);
 		break;
 	case SZ_64K:
-		reg |= ARM_LPAE_TCR_TG0_64K;
+		reg |= (ARM_LPAE_TCR_TG0_64K << ARM_LPAE_VTCR_TG0_SHIFT);
 		break;
 	}
 
 	switch (cfg->oas) {
 	case 32:
-		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 36:
-		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 40:
-		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 42:
-		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 44:
-		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 48:
-		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 52:
-		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	default:
 		goto out_free_data;
 	}
 
 	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-	reg |= (~sl & ARM_LPAE_TCR_SL0_MASK) << ARM_LPAE_TCR_SL0_SHIFT;
+	reg |= (~sl & ARM_LPAE_VTCR_SL0_MASK) << ARM_LPAE_VTCR_SL0_SHIFT;
 	cfg->arm_lpae_s2_cfg.vtcr = reg;
 
 	/* Allocate pgd pages */
@@ -992,19 +981,12 @@ out_free_data:
 static struct io_pgtable *
 arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
-
 	if (cfg->ias > 32 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
-	if (iop) {
-		cfg->arm_lpae_s1_cfg.tcr |= ARM_32_LPAE_TCR_EAE;
-		cfg->arm_lpae_s1_cfg.tcr &= 0xffffffff;
-	}
 
-	return iop;
+	return arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
 }
 
 static struct io_pgtable *
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index ced53e5b72b5..94394c81468f 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -63,7 +63,7 @@ void free_io_pgtable_ops(struct io_pgtable_ops *ops)
 	if (!ops)
 		return;
 
-	iop = container_of(ops, struct io_pgtable, ops);
+	iop = io_pgtable_ops_to_pgtable(ops);
 	io_pgtable_tlb_flush_all(iop);
 	io_pgtable_init_table[iop->fmt]->free(iop);
 }
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index c200bc066257..2eeaf2eec946 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -271,15 +271,13 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 		iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
 				pgtbl_cfg.arm_lpae_s1_cfg.ttbr |
 				FIELD_PREP(TTBRn_ASID, ctx->asid));
-		iommu_writeq(ctx, ARM_SMMU_CB_TTBR1,
-				FIELD_PREP(TTBRn_ASID, ctx->asid));
+		iommu_writeq(ctx, ARM_SMMU_CB_TTBR1, 0);
 
 		/* TCR */
 		iommu_writel(ctx, ARM_SMMU_CB_TCR2,
-				(pgtbl_cfg.arm_lpae_s1_cfg.tcr >> 32) |
-				FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM));
+				arm_smmu_lpae_tcr2(&pgtbl_cfg));
 		iommu_writel(ctx, ARM_SMMU_CB_TCR,
-				pgtbl_cfg.arm_lpae_s1_cfg.tcr);
+				arm_smmu_lpae_tcr(&pgtbl_cfg) | TCR_EAE);
 
 		/* MAIRs (stage-1 only) */
 		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 53bca5343f52..6ae104cedfd7 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -101,7 +101,14 @@ struct io_pgtable_cfg {
 	union {
 		struct {
 			u64	ttbr;
-			u64	tcr;
+			struct {
+				u32	ips:3;
+				u32	tg:2;
+				u32	sh:2;
+				u32	orgn:2;
+				u32	irgn:2;
+				u32	tsz:6;
+			}	tcr;
 			u64	mair;
 		} arm_lpae_s1_cfg;
 
-- 
cgit v1.2.3


From ac4b80e5b9d0ecf906300d79e4dc4df5526579a8 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 10 Jan 2020 14:51:59 +0000
Subject: iommu/io-pgtable-arm: Rationalise VTCR handling

Commit 05a648cd2dd7 ("iommu/io-pgtable-arm: Rationalise TCR handling")
reworked the way in which the TCR register value is returned from the
io-pgtable code when targetting the Arm long-descriptor format, in
preparation for allowing page-tables to target TTBR1.

As it turns out, the new interface is a lot nicer to use, so do the same
conversion for the VTCR register even though there is only a single base
register for stage-2 translation.

Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu-v3.c    | 17 ++++++++++++-
 drivers/iommu/arm-smmu.c       |  2 +-
 drivers/iommu/arm-smmu.h       | 21 ++++++++++++++++
 drivers/iommu/io-pgtable-arm.c | 57 ++++++++++++++++--------------------------
 include/linux/io-pgtable.h     | 10 +++++++-
 5 files changed, 68 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index d127974afdb7..4443e1890077 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -250,6 +250,13 @@
 
 #define STRTAB_STE_2_S2VMID		GENMASK_ULL(15, 0)
 #define STRTAB_STE_2_VTCR		GENMASK_ULL(50, 32)
+#define STRTAB_STE_2_VTCR_S2T0SZ	GENMASK_ULL(5, 0)
+#define STRTAB_STE_2_VTCR_S2SL0		GENMASK_ULL(7, 6)
+#define STRTAB_STE_2_VTCR_S2IR0		GENMASK_ULL(9, 8)
+#define STRTAB_STE_2_VTCR_S2OR0		GENMASK_ULL(11, 10)
+#define STRTAB_STE_2_VTCR_S2SH0		GENMASK_ULL(13, 12)
+#define STRTAB_STE_2_VTCR_S2TG		GENMASK_ULL(15, 14)
+#define STRTAB_STE_2_VTCR_S2PS		GENMASK_ULL(18, 16)
 #define STRTAB_STE_2_S2AA64		(1UL << 51)
 #define STRTAB_STE_2_S2ENDI		(1UL << 52)
 #define STRTAB_STE_2_S2PTW		(1UL << 54)
@@ -2159,14 +2166,22 @@ static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
 	int vmid;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+	typeof(&pgtbl_cfg->arm_lpae_s2_cfg.vtcr) vtcr;
 
 	vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
 	if (vmid < 0)
 		return vmid;
 
+	vtcr = &pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
 	cfg->vmid	= (u16)vmid;
 	cfg->vttbr	= pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
-	cfg->vtcr	= pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+	cfg->vtcr	= FIELD_PREP(STRTAB_STE_2_VTCR_S2T0SZ, vtcr->tsz) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2SL0, vtcr->sl) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2IR0, vtcr->irgn) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2OR0, vtcr->orgn) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2SH0, vtcr->sh) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2TG, vtcr->tg) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2PS, vtcr->ps);
 	return 0;
 }
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 214be09f6ded..f067783ebd59 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -548,7 +548,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 				cb->tcr[0] |= ARM_SMMU_TCR_EAE;
 		}
 	} else {
-		cb->tcr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+		cb->tcr[0] = arm_smmu_lpae_vtcr(pgtbl_cfg);
 	}
 
 	/* TTBRs */
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 6501f38a5966..8d1cd54d82a6 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -174,6 +174,15 @@ enum arm_smmu_cbar_type {
 #define ARM_SMMU_TCR_IRGN0		GENMASK(9, 8)
 #define ARM_SMMU_TCR_T0SZ		GENMASK(5, 0)
 
+#define ARM_SMMU_VTCR_RES1		BIT(31)
+#define ARM_SMMU_VTCR_PS		GENMASK(18, 16)
+#define ARM_SMMU_VTCR_TG0		ARM_SMMU_TCR_TG0
+#define ARM_SMMU_VTCR_SH0		ARM_SMMU_TCR_SH0
+#define ARM_SMMU_VTCR_ORGN0		ARM_SMMU_TCR_ORGN0
+#define ARM_SMMU_VTCR_IRGN0		ARM_SMMU_TCR_IRGN0
+#define ARM_SMMU_VTCR_SL0		GENMASK(7, 6)
+#define ARM_SMMU_VTCR_T0SZ		ARM_SMMU_TCR_T0SZ
+
 #define ARM_SMMU_CB_CONTEXTIDR		0x34
 #define ARM_SMMU_CB_S1_MAIR0		0x38
 #define ARM_SMMU_CB_S1_MAIR1		0x3c
@@ -352,6 +361,18 @@ static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg)
 	       FIELD_PREP(ARM_SMMU_TCR2_SEP, ARM_SMMU_TCR2_SEP_UPSTREAM);
 }
 
+static inline u32 arm_smmu_lpae_vtcr(struct io_pgtable_cfg *cfg)
+{
+	return ARM_SMMU_VTCR_RES1 |
+	       FIELD_PREP(ARM_SMMU_VTCR_PS, cfg->arm_lpae_s2_cfg.vtcr.ps) |
+	       FIELD_PREP(ARM_SMMU_VTCR_TG0, cfg->arm_lpae_s2_cfg.vtcr.tg) |
+	       FIELD_PREP(ARM_SMMU_VTCR_SH0, cfg->arm_lpae_s2_cfg.vtcr.sh) |
+	       FIELD_PREP(ARM_SMMU_VTCR_ORGN0, cfg->arm_lpae_s2_cfg.vtcr.orgn) |
+	       FIELD_PREP(ARM_SMMU_VTCR_IRGN0, cfg->arm_lpae_s2_cfg.vtcr.irgn) |
+	       FIELD_PREP(ARM_SMMU_VTCR_SL0, cfg->arm_lpae_s2_cfg.vtcr.sl) |
+	       FIELD_PREP(ARM_SMMU_VTCR_T0SZ, cfg->arm_lpae_s2_cfg.vtcr.tsz);
+}
+
 /* Implementation details, yay! */
 struct arm_smmu_impl {
 	u32 (*read_reg)(struct arm_smmu_device *smmu, int page, int offset);
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index a868ce594871..2ae4da4dea5e 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -100,26 +100,19 @@
 #define ARM_LPAE_PTE_MEMATTR_DEV	(((arm_lpae_iopte)0x1) << 2)
 
 /* Register bits */
-#define ARM_64_LPAE_VTCR_RES1		(1U << 31)
-
-#define ARM_LPAE_VTCR_TG0_SHIFT		14
 #define ARM_LPAE_TCR_TG0_4K		0
 #define ARM_LPAE_TCR_TG0_64K		1
 #define ARM_LPAE_TCR_TG0_16K		2
 
-#define ARM_LPAE_TCR_SH0_SHIFT		12
 #define ARM_LPAE_TCR_SH_NS		0
 #define ARM_LPAE_TCR_SH_OS		2
 #define ARM_LPAE_TCR_SH_IS		3
 
-#define ARM_LPAE_TCR_ORGN0_SHIFT	10
-#define ARM_LPAE_TCR_IRGN0_SHIFT	8
 #define ARM_LPAE_TCR_RGN_NC		0
 #define ARM_LPAE_TCR_RGN_WBWA		1
 #define ARM_LPAE_TCR_RGN_WT		2
 #define ARM_LPAE_TCR_RGN_WB		3
 
-#define ARM_LPAE_VTCR_SL0_SHIFT		6
 #define ARM_LPAE_VTCR_SL0_MASK		0x3
 
 #define ARM_LPAE_TCR_T0SZ_SHIFT		0
@@ -878,8 +871,9 @@ out_free_data:
 static struct io_pgtable *
 arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	u64 reg, sl;
+	u64 sl;
 	struct arm_lpae_io_pgtable *data;
+	typeof(&cfg->arm_lpae_s2_cfg.vtcr) vtcr = &cfg->arm_lpae_s2_cfg.vtcr;
 
 	/* The NS quirk doesn't apply at stage 2 */
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_NON_STRICT))
@@ -904,61 +898,59 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	}
 
 	/* VTCR */
-	reg = ARM_64_LPAE_VTCR_RES1;
 	if (cfg->coherent_walk) {
-		reg |= (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
-		       (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		       (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+		vtcr->sh = ARM_LPAE_TCR_SH_IS;
+		vtcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+		vtcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
 	} else {
-		reg |= (ARM_LPAE_TCR_SH_OS << ARM_LPAE_TCR_SH0_SHIFT) |
-		       (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		       (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_ORGN0_SHIFT);
+		vtcr->sh = ARM_LPAE_TCR_SH_OS;
+		vtcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		vtcr->orgn = ARM_LPAE_TCR_RGN_NC;
 	}
 
 	sl = data->start_level;
 
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		reg |= (ARM_LPAE_TCR_TG0_4K << ARM_LPAE_VTCR_TG0_SHIFT);
+		vtcr->tg = ARM_LPAE_TCR_TG0_4K;
 		sl++; /* SL0 format is different for 4K granule size */
 		break;
 	case SZ_16K:
-		reg |= (ARM_LPAE_TCR_TG0_16K << ARM_LPAE_VTCR_TG0_SHIFT);
+		vtcr->tg = ARM_LPAE_TCR_TG0_16K;
 		break;
 	case SZ_64K:
-		reg |= (ARM_LPAE_TCR_TG0_64K << ARM_LPAE_VTCR_TG0_SHIFT);
+		vtcr->tg = ARM_LPAE_TCR_TG0_64K;
 		break;
 	}
 
 	switch (cfg->oas) {
 	case 32:
-		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_32_BIT;
 		break;
 	case 36:
-		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_36_BIT;
 		break;
 	case 40:
-		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_40_BIT;
 		break;
 	case 42:
-		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_42_BIT;
 		break;
 	case 44:
-		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_44_BIT;
 		break;
 	case 48:
-		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_48_BIT;
 		break;
 	case 52:
-		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_52_BIT;
 		break;
 	default:
 		goto out_free_data;
 	}
 
-	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-	reg |= (~sl & ARM_LPAE_VTCR_SL0_MASK) << ARM_LPAE_VTCR_SL0_SHIFT;
-	cfg->arm_lpae_s2_cfg.vtcr = reg;
+	vtcr->tsz = 64ULL - cfg->ias;
+	vtcr->sl = ~sl & ARM_LPAE_VTCR_SL0_MASK;
 
 	/* Allocate pgd pages */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
@@ -985,24 +977,17 @@ arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-
 	return arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
 }
 
 static struct io_pgtable *
 arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
-
 	if (cfg->ias > 40 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
-	if (iop)
-		cfg->arm_lpae_s2_cfg.vtcr &= 0xffffffff;
-
-	return iop;
+	return arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
 }
 
 static struct io_pgtable *
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 6ae104cedfd7..40c1b7745fb6 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -114,7 +114,15 @@ struct io_pgtable_cfg {
 
 		struct {
 			u64	vttbr;
-			u64	vtcr;
+			struct {
+				u32	ps:3;
+				u32	tg:2;
+				u32	sh:2;
+				u32	orgn:2;
+				u32	irgn:2;
+				u32	sl:2;
+				u32	tsz:6;
+			}	vtcr;
 		} arm_lpae_s2_cfg;
 
 		struct {
-- 
cgit v1.2.3


From db6903010aa5b7691d8234a179f4cf71a119445a Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Fri, 25 Oct 2019 19:08:39 +0100
Subject: iommu/io-pgtable-arm: Prepare for TTBR1 usage

Now that we can correctly extract top-level indices without relying on
the remaining upper bits being zero, the only remaining impediments to
using a given table for TTBR1 are the address validation on map/unmap
and the awkward TCR translation granule format. Add a quirk so that we
can do the right thing at those points.

Tested-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm.c | 25 +++++++++++++++++++------
 include/linux/io-pgtable.h     |  4 ++++
 2 files changed, 23 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 2ae4da4dea5e..983b08477e64 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -104,6 +104,10 @@
 #define ARM_LPAE_TCR_TG0_64K		1
 #define ARM_LPAE_TCR_TG0_16K		2
 
+#define ARM_LPAE_TCR_TG1_16K		1
+#define ARM_LPAE_TCR_TG1_4K		2
+#define ARM_LPAE_TCR_TG1_64K		3
+
 #define ARM_LPAE_TCR_SH_NS		0
 #define ARM_LPAE_TCR_SH_OS		2
 #define ARM_LPAE_TCR_SH_IS		3
@@ -464,6 +468,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 	arm_lpae_iopte *ptep = data->pgd;
 	int ret, lvl = data->start_level;
 	arm_lpae_iopte prot;
+	long iaext = (long)iova >> cfg->ias;
 
 	/* If no access, then nothing to do */
 	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
@@ -472,7 +477,9 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
 		return -EINVAL;
 
-	if (WARN_ON(iova >> data->iop.cfg.ias || paddr >> data->iop.cfg.oas))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext || paddr >> cfg->oas))
 		return -ERANGE;
 
 	prot = arm_lpae_prot_to_pte(data, iommu_prot);
@@ -638,11 +645,14 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_lpae_iopte *ptep = data->pgd;
+	long iaext = (long)iova >> cfg->ias;
 
 	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
 		return 0;
 
-	if (WARN_ON(iova >> data->iop.cfg.ias))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext))
 		return 0;
 
 	return __arm_lpae_unmap(data, gather, iova, size, data->start_level, ptep);
@@ -778,9 +788,11 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	u64 reg;
 	struct arm_lpae_io_pgtable *data;
 	typeof(&cfg->arm_lpae_s1_cfg.tcr) tcr = &cfg->arm_lpae_s1_cfg.tcr;
+	bool tg1;
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
-			    IO_PGTABLE_QUIRK_NON_STRICT))
+			    IO_PGTABLE_QUIRK_NON_STRICT |
+			    IO_PGTABLE_QUIRK_ARM_TTBR1))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
@@ -798,15 +810,16 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 		tcr->orgn = ARM_LPAE_TCR_RGN_NC;
 	}
 
+	tg1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1;
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		tcr->tg = ARM_LPAE_TCR_TG0_4K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_4K : ARM_LPAE_TCR_TG0_4K;
 		break;
 	case SZ_16K:
-		tcr->tg = ARM_LPAE_TCR_TG0_16K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_16K : ARM_LPAE_TCR_TG0_16K;
 		break;
 	case SZ_64K:
-		tcr->tg = ARM_LPAE_TCR_TG0_64K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_64K : ARM_LPAE_TCR_TG0_64K;
 		break;
 	}
 
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 40c1b7745fb6..53d53c6c2be9 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -83,12 +83,16 @@ struct io_pgtable_cfg {
 	 * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
 	 *	on unmap, for DMA domains using the flush queue mechanism for
 	 *	delayed invalidation.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table
+	 *	for use in the upper half of a split address space.
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
 	#define IO_PGTABLE_QUIRK_TLBI_ON_MAP	BIT(2)
 	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
 	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
+	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
-- 
cgit v1.2.3


From 89535821c04256964e266bf585cf224f65e08983 Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Wed, 15 Jan 2020 13:52:29 +0100
Subject: iommu/arm-smmu-v3: Parse PASID devicetree property of platform
 devices

For platform devices that support SubstreamID (SSID), firmware provides
the number of supported SSID bits. Restrict it to what the SMMU supports
and cache it into master->ssid_bits, which will also be used for PCI
PASID.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu-v3.c | 13 +++++++++++++
 drivers/iommu/of_iommu.c    |  6 +++++-
 include/linux/iommu.h       |  2 ++
 3 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 4a9442f004ca..2717c2b211d2 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -289,6 +289,12 @@
 
 #define CTXDESC_CD_1_TTB0_MASK		GENMASK_ULL(51, 4)
 
+/*
+ * When the SMMU only supports linear context descriptor tables, pick a
+ * reasonable size limit (64kB).
+ */
+#define CTXDESC_LINEAR_CDMAX		ilog2(SZ_64K / (CTXDESC_CD_DWORDS << 3))
+
 /* Command queue */
 #define CMDQ_ENT_SZ_SHIFT		4
 #define CMDQ_ENT_DWORDS			((1 << CMDQ_ENT_SZ_SHIFT) >> 3)
@@ -627,6 +633,7 @@ struct arm_smmu_master {
 	u32				*sids;
 	unsigned int			num_sids;
 	bool				ats_enabled;
+	unsigned int			ssid_bits;
 };
 
 /* SMMU private data for an IOMMU domain */
@@ -2559,6 +2566,12 @@ static int arm_smmu_add_device(struct device *dev)
 		}
 	}
 
+	master->ssid_bits = min(smmu->ssid_bits, fwspec->num_pasid_bits);
+
+	if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB))
+		master->ssid_bits = min_t(u8, master->ssid_bits,
+					  CTXDESC_LINEAR_CDMAX);
+
 	group = iommu_group_get_for_dev(dev);
 	if (!IS_ERR(group)) {
 		iommu_group_put(group);
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index e7bc8b721947..20738aacac89 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -203,8 +203,12 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 			if (err)
 				break;
 		}
-	}
 
+		fwspec = dev_iommu_fwspec_get(dev);
+		if (!err && fwspec)
+			of_property_read_u32(master_np, "pasid-num-bits",
+					     &fwspec->num_pasid_bits);
+	}
 
 	/*
 	 * Two success conditions can be represented by non-negative err here:
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 90007c92ad2d..c1ad15228447 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -579,6 +579,7 @@ struct iommu_group *fsl_mc_device_group(struct device *dev);
  * @ops: ops for this device's IOMMU
  * @iommu_fwnode: firmware handle for this device's IOMMU
  * @iommu_priv: IOMMU driver private data for this device
+ * @num_pasid_bits: number of PASID bits supported by this device
  * @num_ids: number of associated device IDs
  * @ids: IDs which this device may present to the IOMMU
  */
@@ -587,6 +588,7 @@ struct iommu_fwspec {
 	struct fwnode_handle	*iommu_fwnode;
 	void			*iommu_priv;
 	u32			flags;
+	u32			num_pasid_bits;
 	unsigned int		num_ids;
 	u32			ids[1];
 };
-- 
cgit v1.2.3


From 5a4549fd790500d7db94b7d2af6d60cee42110c3 Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Wed, 15 Jan 2020 13:52:38 +0100
Subject: PCI/ATS: Add PASID stubs

The SMMUv3 driver, which may be built without CONFIG_PCI, will soon gain
PASID support.  Partially revert commit c6e9aefbf9db ("PCI/ATS: Remove
unused PRI and PASID stubs") to re-introduce the PASID stubs, and avoid
adding more #ifdefs to the SMMU driver.

Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/pci-ats.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h
index 5d62e78946a3..d08f0869f121 100644
--- a/include/linux/pci-ats.h
+++ b/include/linux/pci-ats.h
@@ -33,6 +33,9 @@ void pci_disable_pasid(struct pci_dev *pdev);
 int pci_pasid_features(struct pci_dev *pdev);
 int pci_max_pasids(struct pci_dev *pdev);
 #else /* CONFIG_PCI_PASID */
+static inline int pci_enable_pasid(struct pci_dev *pdev, int features)
+{ return -EINVAL; }
+static inline void pci_disable_pasid(struct pci_dev *pdev) { }
 static inline int pci_pasid_features(struct pci_dev *pdev)
 { return -EINVAL; }
 static inline int pci_max_pasids(struct pci_dev *pdev)
-- 
cgit v1.2.3