mm/gup: migrate device coherent pages when pinning instead of failing

Currently any attempts to pin a device coherent page will fail.  This is
because device coherent pages need to be managed by a device driver, and
pinning them would prevent a driver from migrating them off the device.

However this is no reason to fail pinning of these pages.  These are
coherent and accessible from the CPU so can be migrated just like pinning
ZONE_MOVABLE pages.  So instead of failing all attempts to pin them first
try migrating them out of ZONE_DEVICE.

[hch@lst.de: rebased to the split device memory checks, moved migrate_device_page to migrate_device.c]
Link: https://lkml.kernel.org/r/20220715150521.18165-7-alex.sierra@amd.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/gup.c b/mm/gup.c
index a9940e3b318120c2aff2364a2657e607531ed000..ecf3626882686f001f62792fb297d2d57726aff4 100644 (file)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1913,7 +1913,7 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
        unsigned long isolation_error_count = 0, i;
        struct folio *prev_folio = NULL;
        LIST_HEAD(movable_page_list);
-       bool drain_allow = true;
+       bool drain_allow = true, coherent_pages = false;
        int ret = 0;
 
        for (i = 0; i < nr_pages; i++) {
@@ -1923,9 +1923,38 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
                        continue;
                prev_folio = folio;
 
-               if (folio_is_longterm_pinnable(folio))
+               /*
+                * Device coherent pages are managed by a driver and should not
+                * be pinned indefinitely as it prevents the driver moving the
+                * page. So when trying to pin with FOLL_LONGTERM instead try
+                * to migrate the page out of device memory.
+                */
+               if (folio_is_device_coherent(folio)) {
+                       /*
+                        * We always want a new GUP lookup with device coherent
+                        * pages.
+                        */
+                       pages[i] = 0;
+                       coherent_pages = true;
+
+                       /*
+                        * Migration will fail if the page is pinned, so convert
+                        * the pin on the source page to a normal reference.
+                        */
+                       if (gup_flags & FOLL_PIN) {
+                               get_page(&folio->page);
+                               unpin_user_page(&folio->page);
+                       }
+
+                       ret = migrate_device_coherent_page(&folio->page);
+                       if (ret)
+                               goto unpin_pages;
+
                        continue;
+               }
 
+               if (folio_is_longterm_pinnable(folio))
+                       continue;
                /*
                 * Try to move out any movable page before pinning the range.
                 */
@@ -1951,7 +1980,8 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
                                    folio_nr_pages(folio));
        }
 
-       if (!list_empty(&movable_page_list) || isolation_error_count)
+       if (!list_empty(&movable_page_list) || isolation_error_count
+               || coherent_pages)
                goto unpin_pages;
 
        /*
@@ -1961,10 +1991,16 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
        return nr_pages;
 
 unpin_pages:
-       if (gup_flags & FOLL_PIN) {
-               unpin_user_pages(pages, nr_pages);
-       } else {
-               for (i = 0; i < nr_pages; i++)
+       /*
+        * pages[i] might be NULL if any device coherent pages were found.
+        */
+       for (i = 0; i < nr_pages; i++) {
+               if (!pages[i])
+                       continue;
+
+               if (gup_flags & FOLL_PIN)
+                       unpin_user_page(pages[i]);
+               else
                        put_page(pages[i]);
        }
 

diff --git a/mm/internal.h b/mm/internal.h
index c0f8fbe0445b5f1704c41e2a4f2b664456b9768f..899dab512c5a78d6b001ac010d40b8dd9c1d913f 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -853,6 +853,7 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
                      unsigned long addr, int page_nid, int *flags);
 
 void free_zone_device_page(struct page *page);
+int migrate_device_coherent_page(struct page *page);
 
 /*
  * mm/gup.c

diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 18bc6483f63a2663652209d6c7fd1f57b43831a8..7feeb447e3b9dd1b937d7625221310b2941841e4 100644 (file)
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -686,6 +686,12 @@ void migrate_vma_pages(struct migrate_vma *migrate)
                }
 
                if (!page) {
+                       /*
+                        * The only time there is no vma is when called from
+                        * migrate_device_coherent_page(). However this isn't
+                        * called if the page could not be unmapped.
+                        */
+                       VM_BUG_ON(!migrate->vma);
                        if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE))
                                continue;
                        if (!notified) {
@@ -794,3 +800,49 @@ void migrate_vma_finalize(struct migrate_vma *migrate)
        }
 }
 EXPORT_SYMBOL(migrate_vma_finalize);
+
+/*
+ * Migrate a device coherent page back to normal memory. The caller should have
+ * a reference on page which will be copied to the new page if migration is
+ * successful or dropped on failure.
+ */
+int migrate_device_coherent_page(struct page *page)
+{
+       unsigned long src_pfn, dst_pfn = 0;
+       struct migrate_vma args;
+       struct page *dpage;
+
+       WARN_ON_ONCE(PageCompound(page));
+
+       lock_page(page);
+       src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE;
+       args.src = &src_pfn;
+       args.dst = &dst_pfn;
+       args.cpages = 1;
+       args.npages = 1;
+       args.vma = NULL;
+
+       /*
+        * We don't have a VMA and don't need to walk the page tables to find
+        * the source page. So call migrate_vma_unmap() directly to unmap the
+        * page as migrate_vma_setup() will fail if args.vma == NULL.
+        */
+       migrate_vma_unmap(&args);
+       if (!(src_pfn & MIGRATE_PFN_MIGRATE))
+               return -EBUSY;
+
+       dpage = alloc_page(GFP_USER | __GFP_NOWARN);
+       if (dpage) {
+               lock_page(dpage);
+               dst_pfn = migrate_pfn(page_to_pfn(dpage));
+       }
+
+       migrate_vma_pages(&args);
+       if (src_pfn & MIGRATE_PFN_MIGRATE)
+               copy_highpage(dpage, page);
+       migrate_vma_finalize(&args);
+
+       if (src_pfn & MIGRATE_PFN_MIGRATE)
+               return 0;
+       return -EBUSY;
+}