mm: vmalloc: refactor vm_area_alloc_pages() function

The aim is to simplify and making the vm_area_alloc_pages()
function less confusing as it became more clogged nowadays:

- eliminate a "bulk_gfp" variable and do not overwrite a gfp
  flag for bulk allocator;
- drop __GFP_NOFAIL flag for high-order-page requests on upper
  layer. It becomes less spread between levels when it comes to
  __GFP_NOFAIL allocations;
- add a comment about a fallback path if high-order attempt is
  unsuccessful because for such cases __GFP_NOFAIL is dropped;
- fix a typo in a commit message.

Link: https://lkml.kernel.org/r/20240827190916.34242-1-urezki@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sony.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index dfa8f09e7e9dd0f297f4a68f1a8ae3fddfce4049..264a2627bea4e7222fe8d0c884ca194a8165a129 100644 (file)
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3515,8 +3515,6 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
                unsigned int order, unsigned int nr_pages, struct page **pages)
 {
        unsigned int nr_allocated = 0;
-       gfp_t alloc_gfp = gfp;
-       bool nofail = gfp & __GFP_NOFAIL;
        struct page *page;
        int i;
 
@@ -3527,9 +3525,6 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
         * more permissive.
         */
        if (!order) {
-               /* bulk allocator doesn't support nofail req. officially */
-               gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL;
-
                while (nr_allocated < nr_pages) {
                        unsigned int nr, nr_pages_request;
 
@@ -3547,12 +3542,11 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
                         * but mempolicy wants to alloc memory by interleaving.
                         */
                        if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
-                               nr = alloc_pages_bulk_array_mempolicy_noprof(bulk_gfp,
+                               nr = alloc_pages_bulk_array_mempolicy_noprof(gfp,
                                                        nr_pages_request,
                                                        pages + nr_allocated);
-
                        else
-                               nr = alloc_pages_bulk_array_node_noprof(bulk_gfp, nid,
+                               nr = alloc_pages_bulk_array_node_noprof(gfp, nid,
                                                        nr_pages_request,
                                                        pages + nr_allocated);
 
@@ -3566,30 +3560,24 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
                        if (nr != nr_pages_request)
                                break;
                }
-       } else if (gfp & __GFP_NOFAIL) {
-               /*
-                * Higher order nofail allocations are really expensive and
-                * potentially dangerous (pre-mature OOM, disruptive reclaim
-                * and compaction etc.
-                */
-               alloc_gfp &= ~__GFP_NOFAIL;
        }
 
        /* High-order pages or fallback path if "bulk" fails. */
        while (nr_allocated < nr_pages) {
-               if (!nofail && fatal_signal_pending(current))
+               if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current))
                        break;
 
                if (nid == NUMA_NO_NODE)
-                       page = alloc_pages_noprof(alloc_gfp, order);
+                       page = alloc_pages_noprof(gfp, order);
                else
-                       page = alloc_pages_node_noprof(nid, alloc_gfp, order);
+                       page = alloc_pages_node_noprof(nid, gfp, order);
+
                if (unlikely(!page))
                        break;
 
                /*
                 * Higher order allocations must be able to be treated as
-                * indepdenent small pages by callers (as they can with
+                * independent small pages by callers (as they can with
                 * small-page vmallocs). Some drivers do their own refcounting
                 * on vmalloc_to_page() pages, some use page->mapping,
                 * page->lru, etc.
@@ -3650,7 +3638,16 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
        set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
        page_order = vm_area_page_order(area);
 
-       area->nr_pages = vm_area_alloc_pages(gfp_mask | __GFP_NOWARN,
+       /*
+        * Higher order nofail allocations are really expensive and
+        * potentially dangerous (pre-mature OOM, disruptive reclaim
+        * and compaction etc.
+        *
+        * Please note, the __vmalloc_node_range_noprof() falls-back
+        * to order-0 pages if high-order attempt is unsuccessful.
+        */
+       area->nr_pages = vm_area_alloc_pages((page_order ?
+               gfp_mask & ~__GFP_NOFAIL : gfp_mask) | __GFP_NOWARN,
                node, page_order, nr_small_pages, area->pages);
 
        atomic_long_add(area->nr_pages, &nr_vmalloc_pages);