1 files changed, 167 insertions, 86 deletions

diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 6cd98ffca198..4a2fc7ab42c3 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -25,12 +25,12 @@ struct pci_p2pdma {
 	struct gen_pool *pool;
 	bool p2pmem_published;
 	struct xarray map_types;
+	struct p2pdma_provider mem[PCI_STD_NUM_BARS];
 };
 
 struct pci_p2pdma_pagemap {
 	struct dev_pagemap pgmap;
-	struct pci_dev *provider;
-	u64 bus_offset;
+	struct p2pdma_provider *mem;
 };
 
 static struct pci_p2pdma_pagemap *to_p2p_pgmap(struct dev_pagemap *pgmap)
@@ -90,7 +90,7 @@ static ssize_t published_show(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR_RO(published);
 
 static int p2pmem_alloc_mmap(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr, struct vm_area_struct *vma)
+		const struct bin_attribute *attr, struct vm_area_struct *vma)
 {
 	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
 	size_t len = vma->vm_end - vma->vm_start;
@@ -140,13 +140,22 @@ static int p2pmem_alloc_mmap(struct file *filp, struct kobject *kobj,
 	rcu_read_unlock();
 
 	for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) {
-		ret = vm_insert_page(vma, vaddr, virt_to_page(kaddr));
+		struct page *page = virt_to_page(kaddr);
+
+		/*
+		 * Initialise the refcount for the freshly allocated page. As
+		 * we have just allocated the page no one else should be
+		 * using it.
+		 */
+		VM_WARN_ON_ONCE_PAGE(!page_ref_count(page), page);
+		set_page_count(page, 1);
+		ret = vm_insert_page(vma, vaddr, page);
 		if (ret) {
 			gen_pool_free(p2pdma->pool, (uintptr_t)kaddr, len);
 			return ret;
 		}
 		percpu_ref_get(ref);
-		put_page(virt_to_page(kaddr));
+		put_page(page);
 		kaddr += PAGE_SIZE;
 		len -= PAGE_SIZE;
 	}
@@ -161,7 +170,7 @@ out:
 	return ret;
 }
 
-static struct bin_attribute p2pmem_alloc_attr = {
+static const struct bin_attribute p2pmem_alloc_attr = {
 	.attr = { .name = "allocate", .mode = 0660 },
 	.mmap = p2pmem_alloc_mmap,
 	/*
@@ -180,7 +189,7 @@ static struct attribute *p2pmem_attrs[] = {
 	NULL,
 };
 
-static struct bin_attribute *p2pmem_bin_attrs[] = {
+static const struct bin_attribute *const p2pmem_bin_attrs[] = {
 	&p2pmem_alloc_attr,
 	NULL,
 };
@@ -191,12 +200,13 @@ static const struct attribute_group p2pmem_group = {
 	.name = "p2pmem",
 };
 
-static void p2pdma_page_free(struct page *page)
+static void p2pdma_folio_free(struct folio *folio)
 {
-	struct pci_p2pdma_pagemap *pgmap = to_p2p_pgmap(page->pgmap);
+	struct page *page = &folio->page;
+	struct pci_p2pdma_pagemap *pgmap = to_p2p_pgmap(page_pgmap(page));
 	/* safe to dereference while a reference is held to the percpu ref */
-	struct pci_p2pdma *p2pdma =
-		rcu_dereference_protected(pgmap->provider->p2pdma, 1);
+	struct pci_p2pdma *p2pdma = rcu_dereference_protected(
+		to_pci_dev(pgmap->mem->owner)->p2pdma, 1);
 	struct percpu_ref *ref;
 
 	gen_pool_free_owner(p2pdma->pool, (uintptr_t)page_to_virt(page),
@@ -205,7 +215,7 @@ static void p2pdma_page_free(struct page *page)
 }
 
 static const struct dev_pagemap_ops p2pdma_pgmap_ops = {
-	.page_free = p2pdma_page_free,
+	.folio_free = p2pdma_folio_free,
 };
 
 static void pci_p2pdma_release(void *data)
@@ -219,56 +229,136 @@ static void pci_p2pdma_release(void *data)
 
 	/* Flush and disable pci_alloc_p2p_mem() */
 	pdev->p2pdma = NULL;
-	synchronize_rcu();
+	if (p2pdma->pool)
+		synchronize_rcu();
+	xa_destroy(&p2pdma->map_types);
+
+	if (!p2pdma->pool)
+		return;
 
 	gen_pool_destroy(p2pdma->pool);
 	sysfs_remove_group(&pdev->dev.kobj, &p2pmem_group);
-	xa_destroy(&p2pdma->map_types);
 }
 
-static int pci_p2pdma_setup(struct pci_dev *pdev)
+/**
+ * pcim_p2pdma_init - Initialise peer-to-peer DMA providers
+ * @pdev: The PCI device to enable P2PDMA for
+ *
+ * This function initializes the peer-to-peer DMA infrastructure
+ * for a PCI device. It allocates and sets up the necessary data
+ * structures to support P2PDMA operations, including mapping type
+ * tracking.
+ */
+int pcim_p2pdma_init(struct pci_dev *pdev)
 {
-	int error = -ENOMEM;
 	struct pci_p2pdma *p2p;
+	int i, ret;
+
+	p2p = rcu_dereference_protected(pdev->p2pdma, 1);
+	if (p2p)
+		return 0;
 
 	p2p = devm_kzalloc(&pdev->dev, sizeof(*p2p), GFP_KERNEL);
 	if (!p2p)
 		return -ENOMEM;
 
 	xa_init(&p2p->map_types);
+	/*
+	 * Iterate over all standard PCI BARs and record only those that
+	 * correspond to MMIO regions. Skip non-memory resources (e.g. I/O
+	 * port BARs) since they cannot be used for peer-to-peer (P2P)
+	 * transactions.
+	 */
+	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+		if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM))
+			continue;
 
-	p2p->pool = gen_pool_create(PAGE_SHIFT, dev_to_node(&pdev->dev));
-	if (!p2p->pool)
-		goto out;
+		p2p->mem[i].owner = &pdev->dev;
+		p2p->mem[i].bus_offset =
+			pci_bus_address(pdev, i) - pci_resource_start(pdev, i);
+	}
 
-	error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev);
-	if (error)
-		goto out_pool_destroy;
+	ret = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev);
+	if (ret)
+		goto out_p2p;
 
-	error = sysfs_create_group(&pdev->dev.kobj, &p2pmem_group);
-	if (error)
+	rcu_assign_pointer(pdev->p2pdma, p2p);
+	return 0;
+
+out_p2p:
+	devm_kfree(&pdev->dev, p2p);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pcim_p2pdma_init);
+
+/**
+ * pcim_p2pdma_provider - Get peer-to-peer DMA provider
+ * @pdev: The PCI device to enable P2PDMA for
+ * @bar: BAR index to get provider
+ *
+ * This function gets peer-to-peer DMA provider for a PCI device. The lifetime
+ * of the provider (and of course the MMIO) is bound to the lifetime of the
+ * driver. A driver calling this function must ensure that all references to the
+ * provider, and any DMA mappings created for any MMIO, are all cleaned up
+ * before the driver remove() completes.
+ *
+ * Since P2P is almost always shared with a second driver this means some system
+ * to notify, invalidate and revoke the MMIO's DMA must be in place to use this
+ * function. For example a revoke can be built using DMABUF.
+ */
+struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev, int bar)
+{
+	struct pci_p2pdma *p2p;
+
+	if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM))
+		return NULL;
+
+	p2p = rcu_dereference_protected(pdev->p2pdma, 1);
+	if (WARN_ON(!p2p))
+		/* Someone forgot to call to pcim_p2pdma_init() before */
+		return NULL;
+
+	return &p2p->mem[bar];
+}
+EXPORT_SYMBOL_GPL(pcim_p2pdma_provider);
+
+static int pci_p2pdma_setup_pool(struct pci_dev *pdev)
+{
+	struct pci_p2pdma *p2pdma;
+	int ret;
+
+	p2pdma = rcu_dereference_protected(pdev->p2pdma, 1);
+	if (p2pdma->pool)
+		/* We already setup pools, do nothing, */
+		return 0;
+
+	p2pdma->pool = gen_pool_create(PAGE_SHIFT, dev_to_node(&pdev->dev));
+	if (!p2pdma->pool)
+		return -ENOMEM;
+
+	ret = sysfs_create_group(&pdev->dev.kobj, &p2pmem_group);
+	if (ret)
 		goto out_pool_destroy;
 
-	rcu_assign_pointer(pdev->p2pdma, p2p);
 	return 0;
 
 out_pool_destroy:
-	gen_pool_destroy(p2p->pool);
-out:
-	devm_kfree(&pdev->dev, p2p);
-	return error;
+	gen_pool_destroy(p2pdma->pool);
+	p2pdma->pool = NULL;
+	return ret;
 }
 
 static void pci_p2pdma_unmap_mappings(void *data)
 {
-	struct pci_dev *pdev = data;
+	struct pci_p2pdma_pagemap *p2p_pgmap = data;
 
 	/*
 	 * Removing the alloc attribute from sysfs will call
 	 * unmap_mapping_range() on the inode, teardown any existing userspace
 	 * mappings and prevent new ones from being created.
 	 */
-	sysfs_remove_file_from_group(&pdev->dev.kobj, &p2pmem_alloc_attr.attr,
+	sysfs_remove_file_from_group(&p2p_pgmap->mem->owner->kobj,
+				     &p2pmem_alloc_attr.attr,
 				     p2pmem_group.name);
 }
 
@@ -286,6 +376,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 			    u64 offset)
 {
 	struct pci_p2pdma_pagemap *p2p_pgmap;
+	struct p2pdma_provider *mem;
 	struct dev_pagemap *pgmap;
 	struct pci_p2pdma *p2pdma;
 	void *addr;
@@ -303,11 +394,21 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	if (size + offset > pci_resource_len(pdev, bar))
 		return -EINVAL;
 
-	if (!pdev->p2pdma) {
-		error = pci_p2pdma_setup(pdev);
-		if (error)
-			return error;
-	}
+	error = pcim_p2pdma_init(pdev);
+	if (error)
+		return error;
+
+	error = pci_p2pdma_setup_pool(pdev);
+	if (error)
+		return error;
+
+	mem = pcim_p2pdma_provider(pdev, bar);
+	/*
+	 * We checked validity of BAR prior to call
+	 * to pcim_p2pdma_provider. It should never return NULL.
+	 */
+	if (WARN_ON(!mem))
+		return -EINVAL;
 
 	p2p_pgmap = devm_kzalloc(&pdev->dev, sizeof(*p2p_pgmap), GFP_KERNEL);
 	if (!p2p_pgmap)
@@ -319,10 +420,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	pgmap->nr_range = 1;
 	pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
 	pgmap->ops = &p2pdma_pgmap_ops;
-
-	p2p_pgmap->provider = pdev;
-	p2p_pgmap->bus_offset = pci_bus_address(pdev, bar) -
-		pci_resource_start(pdev, bar);
+	p2p_pgmap->mem = mem;
 
 	addr = devm_memremap_pages(&pdev->dev, pgmap);
 	if (IS_ERR(addr)) {
@@ -331,7 +429,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	}
 
 	error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_unmap_mappings,
-					 pdev);
+					 p2p_pgmap);
 	if (error)
 		goto pages_free;
 
@@ -351,7 +449,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 pages_free:
 	devm_memunmap_pages(&pdev->dev, pgmap);
 pgmap_free:
-	devm_kfree(&pdev->dev, pgmap);
+	devm_kfree(&pdev->dev, p2p_pgmap);
 	return error;
 }
 EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource);
@@ -435,7 +533,7 @@ static const struct pci_p2pdma_whitelist_entry {
 	/* Intel Xeon E7 v3/Xeon E5 v3/Core i7 */
 	{PCI_VENDOR_ID_INTEL,	0x2f00, REQ_SAME_HOST_BRIDGE},
 	{PCI_VENDOR_ID_INTEL,	0x2f01, REQ_SAME_HOST_BRIDGE},
-	/* Intel SkyLake-E */
+	/* Intel Skylake-E */
 	{PCI_VENDOR_ID_INTEL,	0x2030, 0},
 	{PCI_VENDOR_ID_INTEL,	0x2031, 0},
 	{PCI_VENDOR_ID_INTEL,	0x2032, 0},
@@ -532,8 +630,7 @@ static bool host_bridge_whitelist(struct pci_dev *a, struct pci_dev *b,
 
 static unsigned long map_types_idx(struct pci_dev *client)
 {
-	return (pci_domain_nr(client->bus) << 16) |
-		(client->bus->number << 8) | client->devfn;
+	return (pci_domain_nr(client->bus) << 16) | pci_dev_id(client);
 }
 
 /*
@@ -662,7 +759,7 @@ done:
 	p2pdma = rcu_dereference(provider->p2pdma);
 	if (p2pdma)
 		xa_store(&p2pdma->map_types, map_types_idx(client),
-			 xa_mk_value(map_type), GFP_KERNEL);
+			 xa_mk_value(map_type), GFP_ATOMIC);
 	rcu_read_unlock();
 	return map_type;
 }
@@ -730,7 +827,7 @@ EXPORT_SYMBOL_GPL(pci_p2pdma_distance_many);
  * pci_has_p2pmem - check if a given PCI device has published any p2pmem
  * @pdev: PCI device to check
  */
-bool pci_has_p2pmem(struct pci_dev *pdev)
+static bool pci_has_p2pmem(struct pci_dev *pdev)
 {
 	struct pci_p2pdma *p2pdma;
 	bool res;
@@ -742,7 +839,6 @@ bool pci_has_p2pmem(struct pci_dev *pdev)
 
 	return res;
 }
-EXPORT_SYMBOL_GPL(pci_has_p2pmem);
 
 /**
  * pci_p2pmem_find_many - find a peer-to-peer DMA memory device compatible with
@@ -838,7 +934,6 @@ void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size)
 	if (unlikely(!percpu_ref_tryget_live_rcu(ref))) {
 		gen_pool_free(p2pdma->pool, (unsigned long) ret, size);
 		ret = NULL;
-		goto out;
 	}
 out:
 	rcu_read_unlock();
@@ -966,16 +1061,26 @@ void pci_p2pmem_publish(struct pci_dev *pdev, bool publish)
 }
 EXPORT_SYMBOL_GPL(pci_p2pmem_publish);
 
-static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap,
-						    struct device *dev)
+/**
+ * pci_p2pdma_map_type - Determine the mapping type for P2PDMA transfers
+ * @provider: P2PDMA provider structure
+ * @dev: Target device for the transfer
+ *
+ * Determines how peer-to-peer DMA transfers should be mapped between
+ * the provider and the target device. The mapping type indicates whether
+ * the transfer can be done directly through PCI switches or must go
+ * through the host bridge.
+ */
+enum pci_p2pdma_map_type pci_p2pdma_map_type(struct p2pdma_provider *provider,
+					     struct device *dev)
 {
 	enum pci_p2pdma_map_type type = PCI_P2PDMA_MAP_NOT_SUPPORTED;
-	struct pci_dev *provider = to_p2p_pgmap(pgmap)->provider;
+	struct pci_dev *pdev = to_pci_dev(provider->owner);
 	struct pci_dev *client;
 	struct pci_p2pdma *p2pdma;
 	int dist;
 
-	if (!provider->p2pdma)
+	if (!pdev->p2pdma)
 		return PCI_P2PDMA_MAP_NOT_SUPPORTED;
 
 	if (!dev_is_pci(dev))
@@ -984,7 +1089,7 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap,
 	client = to_pci_dev(dev);
 
 	rcu_read_lock();
-	p2pdma = rcu_dereference(provider->p2pdma);
+	p2pdma = rcu_dereference(pdev->p2pdma);
 
 	if (p2pdma)
 		type = xa_to_value(xa_load(&p2pdma->map_types,
@@ -992,45 +1097,21 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap,
 	rcu_read_unlock();
 
 	if (type == PCI_P2PDMA_MAP_UNKNOWN)
-		return calc_map_type_and_dist(provider, client, &dist, true);
+		return calc_map_type_and_dist(pdev, client, &dist, true);
 
 	return type;
 }
 
-/**
- * pci_p2pdma_map_segment - map an sg segment determining the mapping type
- * @state: State structure that should be declared outside of the for_each_sg()
- *	loop and initialized to zero.
- * @dev: DMA device that's doing the mapping operation
- * @sg: scatterlist segment to map
- *
- * This is a helper to be used by non-IOMMU dma_map_sg() implementations where
- * the sg segment is the same for the page_link and the dma_address.
- *
- * Attempt to map a single segment in an SGL with the PCI bus address.
- * The segment must point to a PCI P2PDMA page and thus must be
- * wrapped in a is_pci_p2pdma_page(sg_page(sg)) check.
- *
- * Returns the type of mapping used and maps the page if the type is
- * PCI_P2PDMA_MAP_BUS_ADDR.
- */
-enum pci_p2pdma_map_type
-pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
-		       struct scatterlist *sg)
+void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state,
+		struct device *dev, struct page *page)
 {
-	if (state->pgmap != sg_page(sg)->pgmap) {
-		state->pgmap = sg_page(sg)->pgmap;
-		state->map = pci_p2pdma_map_type(state->pgmap, dev);
-		state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset;
-	}
+	struct pci_p2pdma_pagemap *p2p_pgmap = to_p2p_pgmap(page_pgmap(page));
 
-	if (state->map == PCI_P2PDMA_MAP_BUS_ADDR) {
-		sg->dma_address = sg_phys(sg) + state->bus_off;
-		sg_dma_len(sg) = sg->length;
-		sg_dma_mark_bus_address(sg);
-	}
+	if (state->mem == p2p_pgmap->mem)
+		return;
 
-	return state->map;
+	state->mem = p2p_pgmap->mem;
+	state->map = pci_p2pdma_map_type(p2p_pgmap->mem, dev);
 }
 
 /**