mm: turn migrate_vma upside down

There isn't any good reason to pass callbacks to migrate_vma.  Instead
we can just export the three steps done by this function to drivers and
let them sequence the operation without callbacks.  This removes a lot
of boilerplate code as-is, and will allow the drivers to drastically
improve code flow and error handling further on.

Link: https://lore.kernel.org/r/20190814075928.23766-2-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Tested-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 110 insertions, 134 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 8992741f10aa..8111e031fa2b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2118,16 +2118,6 @@ out_unlock:
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_MIGRATE_VMA_HELPER)
-struct migrate_vma {
-	struct vm_area_struct	*vma;
-	unsigned long		*dst;
-	unsigned long		*src;
-	unsigned long		cpages;
-	unsigned long		npages;
-	unsigned long		start;
-	unsigned long		end;
-};
-
 static int migrate_vma_collect_hole(unsigned long start,
 				    unsigned long end,
 				    struct mm_walk *walk)
@@ -2578,6 +2568,110 @@ restore:
 	}
 }
 
+/**
+ * migrate_vma_setup() - prepare to migrate a range of memory
+ * @args: contains the vma, start, and and pfns arrays for the migration
+ *
+ * Returns: negative errno on failures, 0 when 0 or more pages were migrated
+ * without an error.
+ *
+ * Prepare to migrate a range of memory virtual address range by collecting all
+ * the pages backing each virtual address in the range, saving them inside the
+ * src array.  Then lock those pages and unmap them. Once the pages are locked
+ * and unmapped, check whether each page is pinned or not.  Pages that aren't
+ * pinned have the MIGRATE_PFN_MIGRATE flag set (by this function) in the
+ * corresponding src array entry.  Then restores any pages that are pinned, by
+ * remapping and unlocking those pages.
+ *
+ * The caller should then allocate destination memory and copy source memory to
+ * it for all those entries (ie with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE
+ * flag set).  Once these are allocated and copied, the caller must update each
+ * corresponding entry in the dst array with the pfn value of the destination
+ * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_LOCKED flags set
+ * (destination pages must have their struct pages locked, via lock_page()).
+ *
+ * Note that the caller does not have to migrate all the pages that are marked
+ * with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration from
+ * device memory to system memory.  If the caller cannot migrate a device page
+ * back to system memory, then it must return VM_FAULT_SIGBUS, which has severe
+ * consequences for the userspace process, so it must be avoided if at all
+ * possible.
+ *
+ * For empty entries inside CPU page table (pte_none() or pmd_none() is true) we
+ * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus
+ * allowing the caller to allocate device memory for those unback virtual
+ * address.  For this the caller simply has to allocate device memory and
+ * properly set the destination entry like for regular migration.  Note that
+ * this can still fails and thus inside the device driver must check if the
+ * migration was successful for those entries after calling migrate_vma_pages()
+ * just like for regular migration.
+ *
+ * After that, the callers must call migrate_vma_pages() to go over each entry
+ * in the src array that has the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag
+ * set. If the corresponding entry in dst array has MIGRATE_PFN_VALID flag set,
+ * then migrate_vma_pages() to migrate struct page information from the source
+ * struct page to the destination struct page.  If it fails to migrate the
+ * struct page information, then it clears the MIGRATE_PFN_MIGRATE flag in the
+ * src array.
+ *
+ * At this point all successfully migrated pages have an entry in the src
+ * array with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set and the dst
+ * array entry with MIGRATE_PFN_VALID flag set.
+ *
+ * Once migrate_vma_pages() returns the caller may inspect which pages were
+ * successfully migrated, and which were not.  Successfully migrated pages will
+ * have the MIGRATE_PFN_MIGRATE flag set for their src array entry.
+ *
+ * It is safe to update device page table after migrate_vma_pages() because
+ * both destination and source page are still locked, and the mmap_sem is held
+ * in read mode (hence no one can unmap the range being migrated).
+ *
+ * Once the caller is done cleaning up things and updating its page table (if it
+ * chose to do so, this is not an obligation) it finally calls
+ * migrate_vma_finalize() to update the CPU page table to point to new pages
+ * for successfully migrated pages or otherwise restore the CPU page table to
+ * point to the original source pages.
+ */
+int migrate_vma_setup(struct migrate_vma *args)
+{
+	long nr_pages = (args->end - args->start) >> PAGE_SHIFT;
+
+	args->start &= PAGE_MASK;
+	args->end &= PAGE_MASK;
+	if (!args->vma || is_vm_hugetlb_page(args->vma) ||
+	    (args->vma->vm_flags & VM_SPECIAL) || vma_is_dax(args->vma))
+		return -EINVAL;
+	if (nr_pages <= 0)
+		return -EINVAL;
+	if (args->start < args->vma->vm_start ||
+	    args->start >= args->vma->vm_end)
+		return -EINVAL;
+	if (args->end <= args->vma->vm_start || args->end > args->vma->vm_end)
+		return -EINVAL;
+	if (!args->src || !args->dst)
+		return -EINVAL;
+
+	memset(args->src, 0, sizeof(*args->src) * nr_pages);
+	args->cpages = 0;
+	args->npages = 0;
+
+	migrate_vma_collect(args);
+
+	if (args->cpages)
+		migrate_vma_prepare(args);
+	if (args->cpages)
+		migrate_vma_unmap(args);
+
+	/*
+	 * At this point pages are locked and unmapped, and thus they have
+	 * stable content and can safely be copied to destination memory that
+	 * is allocated by the drivers.
+	 */
+	return 0;
+
+}
+EXPORT_SYMBOL(migrate_vma_setup);
+
 static void migrate_vma_insert_page(struct migrate_vma *migrate,
 				    unsigned long addr,
 				    struct page *page,
@@ -2709,7 +2803,7 @@ abort:
 	*src &= ~MIGRATE_PFN_MIGRATE;
 }
 
-/*
+/**
  * migrate_vma_pages() - migrate meta-data from src page to dst page
  * @migrate: migrate struct containing all migration information
  *
@@ -2717,7 +2811,7 @@ abort:
  * struct page. This effectively finishes the migration from source page to the
  * destination page.
  */
-static void migrate_vma_pages(struct migrate_vma *migrate)
+void migrate_vma_pages(struct migrate_vma *migrate)
 {
 	const unsigned long npages = migrate->npages;
 	const unsigned long start = migrate->start;
@@ -2791,8 +2885,9 @@ static void migrate_vma_pages(struct migrate_vma *migrate)
 	if (notified)
 		mmu_notifier_invalidate_range_only_end(&range);
 }
+EXPORT_SYMBOL(migrate_vma_pages);
 
-/*
+/**
  * migrate_vma_finalize() - restore CPU page table entry
  * @migrate: migrate struct containing all migration information
  *
@@ -2803,7 +2898,7 @@ static void migrate_vma_pages(struct migrate_vma *migrate)
  * This also unlocks the pages and puts them back on the lru, or drops the extra
  * refcount, for device pages.
  */
-static void migrate_vma_finalize(struct migrate_vma *migrate)
+void migrate_vma_finalize(struct migrate_vma *migrate)
 {
 	const unsigned long npages = migrate->npages;
 	unsigned long i;
@@ -2846,124 +2941,5 @@ static void migrate_vma_finalize(struct migrate_vma *migrate)
 		}
 	}
 }
-
-/*
- * migrate_vma() - migrate a range of memory inside vma
- *
- * @ops: migration callback for allocating destination memory and copying
- * @vma: virtual memory area containing the range to be migrated
- * @start: start address of the range to migrate (inclusive)
- * @end: end address of the range to migrate (exclusive)
- * @src: array of hmm_pfn_t containing source pfns
- * @dst: array of hmm_pfn_t containing destination pfns
- * @private: pointer passed back to each of the callback
- * Returns: 0 on success, error code otherwise
- *
- * This function tries to migrate a range of memory virtual address range, using
- * callbacks to allocate and copy memory from source to destination. First it
- * collects all the pages backing each virtual address in the range, saving this
- * inside the src array. Then it locks those pages and unmaps them. Once the pages
- * are locked and unmapped, it checks whether each page is pinned or not. Pages
- * that aren't pinned have the MIGRATE_PFN_MIGRATE flag set (by this function)
- * in the corresponding src array entry. It then restores any pages that are
- * pinned, by remapping and unlocking those pages.
- *
- * At this point it calls the alloc_and_copy() callback. For documentation on
- * what is expected from that callback, see struct migrate_vma_ops comments in
- * include/linux/migrate.h
- *
- * After the alloc_and_copy() callback, this function goes over each entry in
- * the src array that has the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag
- * set. If the corresponding entry in dst array has MIGRATE_PFN_VALID flag set,
- * then the function tries to migrate struct page information from the source
- * struct page to the destination struct page. If it fails to migrate the struct
- * page information, then it clears the MIGRATE_PFN_MIGRATE flag in the src
- * array.
- *
- * At this point all successfully migrated pages have an entry in the src
- * array with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set and the dst
- * array entry with MIGRATE_PFN_VALID flag set.
- *
- * It then calls the finalize_and_map() callback. See comments for "struct
- * migrate_vma_ops", in include/linux/migrate.h for details about
- * finalize_and_map() behavior.
- *
- * After the finalize_and_map() callback, for successfully migrated pages, this
- * function updates the CPU page table to point to new pages, otherwise it
- * restores the CPU page table to point to the original source pages.
- *
- * Function returns 0 after the above steps, even if no pages were migrated
- * (The function only returns an error if any of the arguments are invalid.)
- *
- * Both src and dst array must be big enough for (end - start) >> PAGE_SHIFT
- * unsigned long entries.
- */
-int migrate_vma(const struct migrate_vma_ops *ops,
-		struct vm_area_struct *vma,
-		unsigned long start,
-		unsigned long end,
-		unsigned long *src,
-		unsigned long *dst,
-		void *private)
-{
-	struct migrate_vma migrate;
-
-	/* Sanity check the arguments */
-	start &= PAGE_MASK;
-	end &= PAGE_MASK;
-	if (!vma || is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) ||
-			vma_is_dax(vma))
-		return -EINVAL;
-	if (start < vma->vm_start || start >= vma->vm_end)
-		return -EINVAL;
-	if (end <= vma->vm_start || end > vma->vm_end)
-		return -EINVAL;
-	if (!ops || !src || !dst || start >= end)
-		return -EINVAL;
-
-	memset(src, 0, sizeof(*src) * ((end - start) >> PAGE_SHIFT));
-	migrate.src = src;
-	migrate.dst = dst;
-	migrate.start = start;
-	migrate.npages = 0;
-	migrate.cpages = 0;
-	migrate.end = end;
-	migrate.vma = vma;
-
-	/* Collect, and try to unmap source pages */
-	migrate_vma_collect(&migrate);
-	if (!migrate.cpages)
-		return 0;
-
-	/* Lock and isolate page */
-	migrate_vma_prepare(&migrate);
-	if (!migrate.cpages)
-		return 0;
-
-	/* Unmap pages */
-	migrate_vma_unmap(&migrate);
-	if (!migrate.cpages)
-		return 0;
-
-	/*
-	 * At this point pages are locked and unmapped, and thus they have
-	 * stable content and can safely be copied to destination memory that
-	 * is allocated by the callback.
-	 *
-	 * Note that migration can fail in migrate_vma_struct_page() for each
-	 * individual page.
-	 */
-	ops->alloc_and_copy(vma, src, dst, start, end, private);
-
-	/* This does the real migration of struct page */
-	migrate_vma_pages(&migrate);
-
-	ops->finalize_and_map(vma, src, dst, start, end, private);
-
-	/* Unlock and remap pages */
-	migrate_vma_finalize(&migrate);
-
-	return 0;
-}
-EXPORT_SYMBOL(migrate_vma);
+EXPORT_SYMBOL(migrate_vma_finalize);
 #endif /* defined(MIGRATE_VMA_HELPER) */