iommu/vt-d: Manage scalalble mode PASID tables

In scalable mode, pasid structure is a two level table with
a pasid directory table and a pasid table. Any pasid entry
can be identified by a pasid value in below way.

   1
   9                       6 5      0
    .-----------------------.-------.
    |              PASID    |       |
    '-----------------------'-------'    .-------------.
             |                    |      |             |
             |                    |      |             |
             |                    |      |             |
             |     .-----------.  |      .-------------.
             |     |           |  |----->| PASID Entry |
             |     |           |  |      '-------------'
             |     |           |  |Plus  |             |
             |     .-----------.  |      |             |
             |---->| DIR Entry |-------->|             |
             |     '-----------'         '-------------'
.---------.  |Plus |           |
| Context |  |     |           |
|  Entry  |------->|           |
'---------'        '-----------'

This changes the pasid table APIs to support scalable mode
PASID directory and PASID table. It also adds a helper to
get the PASID table entry according to the pasid value.

Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Sanjay Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

4 files changed, 97 insertions, 31 deletions

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 2b9784a1887b..5552a1aaf5ea 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -425,21 +425,24 @@ static LIST_HEAD(device_domain_list);
 
 /*
  * Iterate over elements in device_domain_list and call the specified
- * callback @fn against each element. This helper should only be used
- * in the context where the device_domain_lock has already been holden.
+ * callback @fn against each element.
  */
 int for_each_device_domain(int (*fn)(struct device_domain_info *info,
 				     void *data), void *data)
 {
 	int ret = 0;
+	unsigned long flags;
 	struct device_domain_info *info;
 
-	assert_spin_locked(&device_domain_lock);
+	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_entry(info, &device_domain_list, global) {
 		ret = fn(info, data);
-		if (ret)
+		if (ret) {
+			spin_unlock_irqrestore(&device_domain_lock, flags);
 			return ret;
+		}
 	}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return 0;
 }
@@ -2481,16 +2484,18 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 	list_add(&info->global, &device_domain_list);
 	if (dev)
 		dev->archdata.iommu = info;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
 
-	if (dev && dev_is_pci(dev) && info->pasid_supported) {
+	/* PASID table is mandatory for a PCI device in scalable mode. */
+	if (dev && dev_is_pci(dev) && sm_supported(iommu)) {
 		ret = intel_pasid_alloc_table(dev);
 		if (ret) {
-			pr_warn("No pasid table for %s, pasid disabled\n",
-				dev_name(dev));
-			info->pasid_supported = 0;
+			pr_err("PASID table allocation for %s failed\n",
+			       dev_name(dev));
+			dmar_remove_one_dev_info(domain, dev);
+			return NULL;
 		}
 	}
-	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	if (dev && domain_context_mapping(domain, dev)) {
 		pr_err("Domain context map for %s failed\n", dev_name(dev));
diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index fe95c9bd4d33..fd3ccc0753b0 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -123,12 +123,13 @@ int intel_pasid_alloc_table(struct device *dev)
 	struct pasid_table *pasid_table;
 	struct pasid_table_opaque data;
 	struct page *pages;
-	size_t size, count;
+	int max_pasid = 0;
 	int ret, order;
+	int size;
 
+	might_sleep();
 	info = dev->archdata.iommu;
-	if (WARN_ON(!info || !dev_is_pci(dev) ||
-		    !info->pasid_supported || info->pasid_table))
+	if (WARN_ON(!info || !dev_is_pci(dev) || info->pasid_table))
 		return -EINVAL;
 
 	/* DMA alias device already has a pasid table, use it: */
@@ -138,23 +139,25 @@ int intel_pasid_alloc_table(struct device *dev)
 	if (ret)
 		goto attach_out;
 
-	pasid_table = kzalloc(sizeof(*pasid_table), GFP_ATOMIC);
+	pasid_table = kzalloc(sizeof(*pasid_table), GFP_KERNEL);
 	if (!pasid_table)
 		return -ENOMEM;
 	INIT_LIST_HEAD(&pasid_table->dev);
 
-	size = sizeof(struct pasid_entry);
-	count = min_t(int, pci_max_pasids(to_pci_dev(dev)), intel_pasid_max_id);
-	order = get_order(size * count);
+	if (info->pasid_supported)
+		max_pasid = min_t(int, pci_max_pasids(to_pci_dev(dev)),
+				  intel_pasid_max_id);
+
+	size = max_pasid >> (PASID_PDE_SHIFT - 3);
+	order = size ? get_order(size) : 0;
 	pages = alloc_pages_node(info->iommu->node,
-				 GFP_ATOMIC | __GFP_ZERO,
-				 order);
+				 GFP_KERNEL | __GFP_ZERO, order);
 	if (!pages)
 		return -ENOMEM;
 
 	pasid_table->table = page_address(pages);
 	pasid_table->order = order;
-	pasid_table->max_pasid = count;
+	pasid_table->max_pasid = 1 << (order + PAGE_SHIFT + 3);
 
 attach_out:
 	device_attach_pasid_table(info, pasid_table);
@@ -162,14 +165,33 @@ attach_out:
 	return 0;
 }
 
+/* Get PRESENT bit of a PASID directory entry. */
+static inline bool
+pasid_pde_is_present(struct pasid_dir_entry *pde)
+{
+	return READ_ONCE(pde->val) & PASID_PTE_PRESENT;
+}
+
+/* Get PASID table from a PASID directory entry. */
+static inline struct pasid_entry *
+get_pasid_table_from_pde(struct pasid_dir_entry *pde)
+{
+	if (!pasid_pde_is_present(pde))
+		return NULL;
+
+	return phys_to_virt(READ_ONCE(pde->val) & PDE_PFN_MASK);
+}
+
 void intel_pasid_free_table(struct device *dev)
 {
 	struct device_domain_info *info;
 	struct pasid_table *pasid_table;
+	struct pasid_dir_entry *dir;
+	struct pasid_entry *table;
+	int i, max_pde;
 
 	info = dev->archdata.iommu;
-	if (!info || !dev_is_pci(dev) ||
-	    !info->pasid_supported || !info->pasid_table)
+	if (!info || !dev_is_pci(dev) || !info->pasid_table)
 		return;
 
 	pasid_table = info->pasid_table;
@@ -178,6 +200,14 @@ void intel_pasid_free_table(struct device *dev)
 	if (!list_empty(&pasid_table->dev))
 		return;
 
+	/* Free scalable mode PASID directory tables: */
+	dir = pasid_table->table;
+	max_pde = pasid_table->max_pasid >> PASID_PDE_SHIFT;
+	for (i = 0; i < max_pde; i++) {
+		table = get_pasid_table_from_pde(&dir[i]);
+		free_pgtable_page(table);
+	}
+
 	free_pages((unsigned long)pasid_table->table, pasid_table->order);
 	kfree(pasid_table);
 }
@@ -206,17 +236,37 @@ int intel_pasid_get_dev_max_id(struct device *dev)
 
 struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
 {
+	struct device_domain_info *info;
 	struct pasid_table *pasid_table;
+	struct pasid_dir_entry *dir;
 	struct pasid_entry *entries;
+	int dir_index, index;
 
 	pasid_table = intel_pasid_get_table(dev);
 	if (WARN_ON(!pasid_table || pasid < 0 ||
 		    pasid >= intel_pasid_get_dev_max_id(dev)))
 		return NULL;
 
-	entries = pasid_table->table;
+	dir = pasid_table->table;
+	info = dev->archdata.iommu;
+	dir_index = pasid >> PASID_PDE_SHIFT;
+	index = pasid & PASID_PTE_MASK;
+
+	spin_lock(&pasid_lock);
+	entries = get_pasid_table_from_pde(&dir[dir_index]);
+	if (!entries) {
+		entries = alloc_pgtable_page(info->iommu->node);
+		if (!entries) {
+			spin_unlock(&pasid_lock);
+			return NULL;
+		}
+
+		WRITE_ONCE(dir[dir_index].val,
+			   (u64)virt_to_phys(entries) | PASID_PTE_PRESENT);
+	}
+	spin_unlock(&pasid_lock);
 
-	return &entries[pasid];
+	return &entries[index];
 }
 
 /*
@@ -224,7 +274,14 @@ struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
  */
 static inline void pasid_clear_entry(struct pasid_entry *pe)
 {
-	WRITE_ONCE(pe->val, 0);
+	WRITE_ONCE(pe->val[0], 0);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
 }
 
 void intel_pasid_clear_entry(struct device *dev, int pasid)
diff --git a/drivers/iommu/intel-pasid.h b/drivers/iommu/intel-pasid.h
index 1fb5e12b029a..12f480c2bb8b 100644
--- a/drivers/iommu/intel-pasid.h
+++ b/drivers/iommu/intel-pasid.h
@@ -11,12 +11,20 @@
 #define __INTEL_PASID_H
 
 #define PASID_MIN			0x1
-#define PASID_MAX			0x20000
+#define PASID_MAX			0x100000
+#define PASID_PTE_MASK			0x3F
+#define PASID_PTE_PRESENT		1
+#define PDE_PFN_MASK			PAGE_MASK
+#define PASID_PDE_SHIFT			6
 
-struct pasid_entry {
+struct pasid_dir_entry {
 	u64 val;
 };
 
+struct pasid_entry {
+	u64 val[8];
+};
+
 /* The representative of a PASID table */
 struct pasid_table {
 	void			*table;		/* pasid table pointer */
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index db301efe126d..d6c99935d5d9 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -65,8 +65,6 @@ int intel_svm_init(struct intel_iommu *iommu)
 
 	order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);
 	if (ecap_dis(iommu->ecap)) {
-		/* Just making it explicit... */
-		BUILD_BUG_ON(sizeof(struct pasid_entry) != sizeof(struct pasid_state_entry));
 		pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 		if (pages)
 			iommu->pasid_state_table = page_address(pages);
@@ -405,9 +403,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 			pasid_entry_val |= PASID_ENTRY_FLPM_5LP;
 
 		entry = intel_pasid_get_entry(dev, svm->pasid);
-		entry->val = pasid_entry_val;
-
-		wmb();
+		WRITE_ONCE(entry->val[0], pasid_entry_val);
 
 		/*
 		 * Flush PASID cache when a PASID table entry becomes