1 files changed, 106 insertions, 165 deletions

diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index c48ef6083020..c752ae9fad6c 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -41,67 +41,72 @@
 #include <linux/hugetlb.h>
 #include <linux/interval_tree.h>
 #include <linux/hmm.h>
+#include <linux/hmm-dma.h>
 #include <linux/pagemap.h>
 
 #include <rdma/ib_umem_odp.h>
 
 #include "uverbs.h"
 
-static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
-				   const struct mmu_interval_notifier_ops *ops)
+static void ib_init_umem_implicit_odp(struct ib_umem_odp *umem_odp)
 {
-	int ret;
+	umem_odp->is_implicit_odp = 1;
+	umem_odp->umem.is_odp = 1;
+	mutex_init(&umem_odp->umem_mutex);
+}
+
+static int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
+			    const struct mmu_interval_notifier_ops *ops)
+{
+	struct ib_device *dev = umem_odp->umem.ibdev;
+	size_t page_size = 1UL << umem_odp->page_shift;
+	struct hmm_dma_map *map;
+	unsigned long start;
+	unsigned long end;
+	size_t nr_entries;
+	int ret = 0;
 
 	umem_odp->umem.is_odp = 1;
 	mutex_init(&umem_odp->umem_mutex);
 
-	if (!umem_odp->is_implicit_odp) {
-		size_t page_size = 1UL << umem_odp->page_shift;
-		unsigned long start;
-		unsigned long end;
-		size_t ndmas, npfns;
-
-		start = ALIGN_DOWN(umem_odp->umem.address, page_size);
-		if (check_add_overflow(umem_odp->umem.address,
-				       (unsigned long)umem_odp->umem.length,
-				       &end))
-			return -EOVERFLOW;
-		end = ALIGN(end, page_size);
-		if (unlikely(end < page_size))
-			return -EOVERFLOW;
-
-		ndmas = (end - start) >> umem_odp->page_shift;
-		if (!ndmas)
-			return -EINVAL;
-
-		npfns = (end - start) >> PAGE_SHIFT;
-		umem_odp->pfn_list = kvcalloc(
-			npfns, sizeof(*umem_odp->pfn_list),
-			GFP_KERNEL | __GFP_NOWARN);
-		if (!umem_odp->pfn_list)
-			return -ENOMEM;
-
-		umem_odp->dma_list = kvcalloc(
-			ndmas, sizeof(*umem_odp->dma_list),
-			GFP_KERNEL | __GFP_NOWARN);
-		if (!umem_odp->dma_list) {
+	start = ALIGN_DOWN(umem_odp->umem.address, page_size);
+	if (check_add_overflow(umem_odp->umem.address,
+			       (unsigned long)umem_odp->umem.length, &end))
+		return -EOVERFLOW;
+	end = ALIGN(end, page_size);
+	if (unlikely(end < page_size))
+		return -EOVERFLOW;
+
+	nr_entries = (end - start) >> PAGE_SHIFT;
+	if (!(nr_entries * PAGE_SIZE / page_size))
+		return -EINVAL;
+
+	map = &umem_odp->map;
+	if (ib_uses_virt_dma(dev)) {
+		map->pfn_list = kvcalloc(nr_entries, sizeof(*map->pfn_list),
+					 GFP_KERNEL | __GFP_NOWARN);
+		if (!map->pfn_list)
 			ret = -ENOMEM;
-			goto out_pfn_list;
-		}
+	} else
+		ret = hmm_dma_map_alloc(dev->dma_device, map,
+					(end - start) >> PAGE_SHIFT,
+					1 << umem_odp->page_shift);
+	if (ret)
+		return ret;
 
-		ret = mmu_interval_notifier_insert(&umem_odp->notifier,
-						   umem_odp->umem.owning_mm,
-						   start, end - start, ops);
-		if (ret)
-			goto out_dma_list;
-	}
+	ret = mmu_interval_notifier_insert(&umem_odp->notifier,
+					   umem_odp->umem.owning_mm, start,
+					   end - start, ops);
+	if (ret)
+		goto out_free_map;
 
 	return 0;
 
-out_dma_list:
-	kvfree(umem_odp->dma_list);
-out_pfn_list:
-	kvfree(umem_odp->pfn_list);
+out_free_map:
+	if (ib_uses_virt_dma(dev))
+		kfree(map->pfn_list);
+	else
+		hmm_dma_map_free(dev->dma_device, map);
 	return ret;
 }
 
@@ -120,7 +125,6 @@ struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_device *device,
 {
 	struct ib_umem *umem;
 	struct ib_umem_odp *umem_odp;
-	int ret;
 
 	if (access & IB_ACCESS_HUGETLB)
 		return ERR_PTR(-EINVAL);
@@ -132,16 +136,10 @@ struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_device *device,
 	umem->ibdev = device;
 	umem->writable = ib_access_writable(access);
 	umem->owning_mm = current->mm;
-	umem_odp->is_implicit_odp = 1;
 	umem_odp->page_shift = PAGE_SHIFT;
 
 	umem_odp->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
-	ret = ib_init_umem_odp(umem_odp, NULL);
-	if (ret) {
-		put_pid(umem_odp->tgid);
-		kfree(umem_odp);
-		return ERR_PTR(ret);
-	}
+	ib_init_umem_implicit_odp(umem_odp);
 	return umem_odp;
 }
 EXPORT_SYMBOL(ib_umem_odp_alloc_implicit);
@@ -262,74 +260,41 @@ err_put_pid:
 }
 EXPORT_SYMBOL(ib_umem_odp_get);
 
-void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
+static void ib_umem_odp_free(struct ib_umem_odp *umem_odp)
 {
+	struct ib_device *dev = umem_odp->umem.ibdev;
+
 	/*
 	 * Ensure that no more pages are mapped in the umem.
 	 *
 	 * It is the driver's responsibility to ensure, before calling us,
 	 * that the hardware will not attempt to access the MR any more.
 	 */
-	if (!umem_odp->is_implicit_odp) {
-		mutex_lock(&umem_odp->umem_mutex);
-		ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp),
-					    ib_umem_end(umem_odp));
-		mutex_unlock(&umem_odp->umem_mutex);
-		mmu_interval_notifier_remove(&umem_odp->notifier);
-		kvfree(umem_odp->dma_list);
-		kvfree(umem_odp->pfn_list);
-	}
-	put_pid(umem_odp->tgid);
-	kfree(umem_odp);
+	mutex_lock(&umem_odp->umem_mutex);
+	ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp),
+				    ib_umem_end(umem_odp));
+	mutex_unlock(&umem_odp->umem_mutex);
+	mmu_interval_notifier_remove(&umem_odp->notifier);
+	if (ib_uses_virt_dma(dev))
+		kfree(umem_odp->map.pfn_list);
+	else
+		hmm_dma_map_free(dev->dma_device, &umem_odp->map);
 }
-EXPORT_SYMBOL(ib_umem_odp_release);
 
-/*
- * Map for DMA and insert a single page into the on-demand paging page tables.
- *
- * @umem: the umem to insert the page to.
- * @dma_index: index in the umem to add the dma to.
- * @page: the page struct to map and add.
- * @access_mask: access permissions needed for this page.
- *
- * The function returns -EFAULT if the DMA mapping operation fails.
- *
- */
-static int ib_umem_odp_map_dma_single_page(
-		struct ib_umem_odp *umem_odp,
-		unsigned int dma_index,
-		struct page *page,
-		u64 access_mask)
+void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
 {
-	struct ib_device *dev = umem_odp->umem.ibdev;
-	dma_addr_t *dma_addr = &umem_odp->dma_list[dma_index];
-
-	if (*dma_addr) {
-		/*
-		 * If the page is already dma mapped it means it went through
-		 * a non-invalidating trasition, like read-only to writable.
-		 * Resync the flags.
-		 */
-		*dma_addr = (*dma_addr & ODP_DMA_ADDR_MASK) | access_mask;
-		return 0;
-	}
+	if (!umem_odp->is_implicit_odp)
+		ib_umem_odp_free(umem_odp);
 
-	*dma_addr = ib_dma_map_page(dev, page, 0, 1 << umem_odp->page_shift,
-				    DMA_BIDIRECTIONAL);
-	if (ib_dma_mapping_error(dev, *dma_addr)) {
-		*dma_addr = 0;
-		return -EFAULT;
-	}
-	umem_odp->npages++;
-	*dma_addr |= access_mask;
-	return 0;
+	put_pid(umem_odp->tgid);
+	kfree(umem_odp);
 }
+EXPORT_SYMBOL(ib_umem_odp_release);
 
 /**
  * ib_umem_odp_map_dma_and_lock - DMA map userspace memory in an ODP MR and lock it.
  *
  * Maps the range passed in the argument to DMA addresses.
- * The DMA addresses of the mapped pages is updated in umem_odp->dma_list.
  * Upon success the ODP MR will be locked to let caller complete its device
  * page table update.
  *
@@ -357,9 +322,6 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 	struct hmm_range range = {};
 	unsigned long timeout;
 
-	if (access_mask == 0)
-		return -EINVAL;
-
 	if (user_virt < ib_umem_start(umem_odp) ||
 	    user_virt + bcnt > ib_umem_end(umem_odp))
 		return -EFAULT;
@@ -385,11 +347,11 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 	if (fault) {
 		range.default_flags = HMM_PFN_REQ_FAULT;
 
-		if (access_mask & ODP_WRITE_ALLOWED_BIT)
+		if (access_mask & HMM_PFN_WRITE)
 			range.default_flags |= HMM_PFN_REQ_WRITE;
 	}
 
-	range.hmm_pfns = &(umem_odp->pfn_list[pfn_start_idx]);
+	range.hmm_pfns = &(umem_odp->map.pfn_list[pfn_start_idx]);
 	timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
 
 retry:
@@ -417,22 +379,17 @@ retry:
 	for (pfn_index = 0; pfn_index < num_pfns;
 		pfn_index += 1 << (page_shift - PAGE_SHIFT), dma_index++) {
 
-		if (fault) {
-			/*
-			 * Since we asked for hmm_range_fault() to populate
-			 * pages it shouldn't return an error entry on success.
-			 */
-			WARN_ON(range.hmm_pfns[pfn_index] & HMM_PFN_ERROR);
-			WARN_ON(!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID));
-		} else {
-			if (!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID)) {
-				WARN_ON(umem_odp->dma_list[dma_index]);
-				continue;
-			}
-			access_mask = ODP_READ_ALLOWED_BIT;
-			if (range.hmm_pfns[pfn_index] & HMM_PFN_WRITE)
-				access_mask |= ODP_WRITE_ALLOWED_BIT;
-		}
+		/*
+		 * Since we asked for hmm_range_fault() to populate
+		 * pages it shouldn't return an error entry on success.
+		 */
+		WARN_ON(fault && range.hmm_pfns[pfn_index] & HMM_PFN_ERROR);
+		WARN_ON(fault && !(range.hmm_pfns[pfn_index] & HMM_PFN_VALID));
+		if (!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID))
+			continue;
+
+		if (range.hmm_pfns[pfn_index] & HMM_PFN_DMA_MAPPED)
+			continue;
 
 		hmm_order = hmm_pfn_to_map_order(range.hmm_pfns[pfn_index]);
 		/* If a hugepage was detected and ODP wasn't set for, the umem
@@ -445,15 +402,6 @@ retry:
 				  __func__, hmm_order, page_shift);
 			break;
 		}
-
-		ret = ib_umem_odp_map_dma_single_page(
-				umem_odp, dma_index, hmm_pfn_to_page(range.hmm_pfns[pfn_index]),
-				access_mask);
-		if (ret < 0) {
-			ibdev_dbg(umem_odp->umem.ibdev,
-				  "ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
-			break;
-		}
 	}
 	/* upon success lock should stay on hold for the callee */
 	if (!ret)
@@ -473,45 +421,38 @@ EXPORT_SYMBOL(ib_umem_odp_map_dma_and_lock);
 void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 				 u64 bound)
 {
-	dma_addr_t dma_addr;
-	dma_addr_t dma;
-	int idx;
-	u64 addr;
 	struct ib_device *dev = umem_odp->umem.ibdev;
+	u64 addr;
 
 	lockdep_assert_held(&umem_odp->umem_mutex);
 
 	virt = max_t(u64, virt, ib_umem_start(umem_odp));
 	bound = min_t(u64, bound, ib_umem_end(umem_odp));
 	for (addr = virt; addr < bound; addr += BIT(umem_odp->page_shift)) {
-		idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
-		dma = umem_odp->dma_list[idx];
-
-		/* The access flags guaranteed a valid DMA address in case was NULL */
-		if (dma) {
-			unsigned long pfn_idx = (addr - ib_umem_start(umem_odp)) >> PAGE_SHIFT;
-			struct page *page = hmm_pfn_to_page(umem_odp->pfn_list[pfn_idx]);
-
-			dma_addr = dma & ODP_DMA_ADDR_MASK;
-			ib_dma_unmap_page(dev, dma_addr,
-					  BIT(umem_odp->page_shift),
-					  DMA_BIDIRECTIONAL);
-			if (dma & ODP_WRITE_ALLOWED_BIT) {
-				struct page *head_page = compound_head(page);
-				/*
-				 * set_page_dirty prefers being called with
-				 * the page lock. However, MMU notifiers are
-				 * called sometimes with and sometimes without
-				 * the lock. We rely on the umem_mutex instead
-				 * to prevent other mmu notifiers from
-				 * continuing and allowing the page mapping to
-				 * be removed.
-				 */
-				set_page_dirty(head_page);
-			}
-			umem_odp->dma_list[idx] = 0;
-			umem_odp->npages--;
+		u64 offset = addr - ib_umem_start(umem_odp);
+		size_t idx = offset >> umem_odp->page_shift;
+		unsigned long pfn = umem_odp->map.pfn_list[idx];
+
+		if (!hmm_dma_unmap_pfn(dev->dma_device, &umem_odp->map, idx))
+			goto clear;
+
+		if (pfn & HMM_PFN_WRITE) {
+			struct page *page = hmm_pfn_to_page(pfn);
+			struct page *head_page = compound_head(page);
+			/*
+			 * set_page_dirty prefers being called with
+			 * the page lock. However, MMU notifiers are
+			 * called sometimes with and sometimes without
+			 * the lock. We rely on the umem_mutex instead
+			 * to prevent other mmu notifiers from
+			 * continuing and allowing the page mapping to
+			 * be removed.
+			 */
+			set_page_dirty(head_page);
 		}
+		umem_odp->npages--;
+clear:
+		umem_odp->map.pfn_list[idx] &= ~HMM_PFN_FLAGS;
 	}
 }
 EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);