Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "146 patches.

  Subsystems affected by this patch series: kthread, ia64, scripts,
  ntfs, squashfs, ocfs2, vfs, and mm (slab-generic, slab, kmemleak,
  dax, kasan, debug, pagecache, gup, shmem, frontswap, memremap,
  memcg, selftests, pagemap, dma, vmalloc, memory-failure, hugetlb,
  userfaultfd, vmscan, mempolicy, oom-kill, hugetlbfs, migration, thp,
  ksm, page-poison, percpu, rmap, zswap, zram, cleanups, hmm, and
  damon)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (146 commits)
  mm/damon: hide kernel pointer from tracepoint event
  mm/damon/vaddr: hide kernel pointer from damon_va_three_regions() failure log
  mm/damon/vaddr: use pr_debug() for damon_va_three_regions() failure logging
  mm/damon/dbgfs: remove an unnecessary variable
  mm/damon: move the implementation of damon_insert_region to damon.h
  mm/damon: add access checking for hugetlb pages
  Docs/admin-guide/mm/damon/usage: update for schemes statistics
  mm/damon/dbgfs: support all DAMOS stats
  Docs/admin-guide/mm/damon/reclaim: document statistics parameters
  mm/damon/reclaim: provide reclamation statistics
  mm/damon/schemes: account how many times quota limit has exceeded
  mm/damon/schemes: account scheme actions that successfully applied
  mm/damon: remove a mistakenly added comment for a future feature
  Docs/admin-guide/mm/damon/usage: update for kdamond_pid and (mk|rm)_contexts
  Docs/admin-guide/mm/damon/usage: mention tracepoint at the beginning
  Docs/admin-guide/mm/damon/usage: remove redundant information
  Docs/admin-guide/mm/damon/usage: update for scheme quotas and watermarks
  mm/damon: convert macro functions to static inline functions
  mm/damon: modify damon_rand() macro to static inline function
  mm/damon: move damon_rand() definition into damon.h
  ...

1 files changed, 58 insertions, 15 deletions

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d2a00ad4e1dd..4165304d3547 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -31,6 +31,7 @@
 #include <linux/kmemleak.h>
 #include <linux/atomic.h>
 #include <linux/compiler.h>
+#include <linux/memcontrol.h>
 #include <linux/llist.h>
 #include <linux/bitops.h>
 #include <linux/rbtree_augmented.h>
@@ -38,6 +39,7 @@
 #include <linux/pgtable.h>
 #include <linux/uaccess.h>
 #include <linux/hugetlb.h>
+#include <linux/sched/mm.h>
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
 
@@ -2623,12 +2625,13 @@ static void __vunmap(const void *addr, int deallocate_pages)
 
 	if (deallocate_pages) {
 		unsigned int page_order = vm_area_page_order(area);
-		int i;
+		int i, step = 1U << page_order;
 
-		for (i = 0; i < area->nr_pages; i += 1U << page_order) {
+		for (i = 0; i < area->nr_pages; i += step) {
 			struct page *page = area->pages[i];
 
 			BUG_ON(!page);
+			mod_memcg_page_state(page, MEMCG_VMALLOC, -step);
 			__free_pages(page, page_order);
 			cond_resched();
 		}
@@ -2844,6 +2847,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	 * more permissive.
 	 */
 	if (!order) {
+		gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL;
+
 		while (nr_allocated < nr_pages) {
 			unsigned int nr, nr_pages_request;
 
@@ -2861,12 +2866,12 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			 * but mempolcy want to alloc memory by interleaving.
 			 */
 			if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
-				nr = alloc_pages_bulk_array_mempolicy(gfp,
+				nr = alloc_pages_bulk_array_mempolicy(bulk_gfp,
 							nr_pages_request,
 							pages + nr_allocated);
 
 			else
-				nr = alloc_pages_bulk_array_node(gfp, nid,
+				nr = alloc_pages_bulk_array_node(bulk_gfp, nid,
 							nr_pages_request,
 							pages + nr_allocated);
 
@@ -2921,11 +2926,14 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 {
 	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
 	const gfp_t orig_gfp_mask = gfp_mask;
+	bool nofail = gfp_mask & __GFP_NOFAIL;
 	unsigned long addr = (unsigned long)area->addr;
 	unsigned long size = get_vm_area_size(area);
 	unsigned long array_size;
 	unsigned int nr_small_pages = size >> PAGE_SHIFT;
 	unsigned int page_order;
+	unsigned int flags;
+	int ret;
 
 	array_size = (unsigned long)nr_small_pages * sizeof(struct page *);
 	gfp_mask |= __GFP_NOWARN;
@@ -2955,6 +2963,13 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		page_order, nr_small_pages, area->pages);
 
 	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
+	if (gfp_mask & __GFP_ACCOUNT) {
+		int i, step = 1U << page_order;
+
+		for (i = 0; i < area->nr_pages; i += step)
+			mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC,
+					     step);
+	}
 
 	/*
 	 * If not enough pages were obtained to accomplish an
@@ -2967,8 +2982,28 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		goto fail;
 	}
 
-	if (vmap_pages_range(addr, addr + size, prot, area->pages,
-			page_shift) < 0) {
+	/*
+	 * page tables allocations ignore external gfp mask, enforce it
+	 * by the scope API
+	 */
+	if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+		flags = memalloc_nofs_save();
+	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+		flags = memalloc_noio_save();
+
+	do {
+		ret = vmap_pages_range(addr, addr + size, prot, area->pages,
+			page_shift);
+		if (nofail && (ret < 0))
+			schedule_timeout_uninterruptible(1);
+	} while (nofail && (ret < 0));
+
+	if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+		memalloc_nofs_restore(flags);
+	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+		memalloc_noio_restore(flags);
+
+	if (ret < 0) {
 		warn_alloc(orig_gfp_mask, NULL,
 			"vmalloc error: size %lu, failed to map pages",
 			area->nr_pages * PAGE_SIZE);
@@ -2996,12 +3031,14 @@ fail:
  *
  * Allocate enough pages to cover @size from the page level
  * allocator with @gfp_mask flags. Please note that the full set of gfp
- * flags are not supported. GFP_KERNEL would be a preferred allocation mode
- * but GFP_NOFS and GFP_NOIO are supported as well. Zone modifiers are not
- * supported. From the reclaim modifiers__GFP_DIRECT_RECLAIM is required (aka
- * GFP_NOWAIT is not supported) and only __GFP_NOFAIL is supported (aka
- * __GFP_NORETRY and __GFP_RETRY_MAYFAIL are not supported).
- * __GFP_NOWARN can be used to suppress error messages about failures.
+ * flags are not supported. GFP_KERNEL, GFP_NOFS and GFP_NOIO are all
+ * supported.
+ * Zone modifiers are not supported. From the reclaim modifiers
+ * __GFP_DIRECT_RECLAIM is required (aka GFP_NOWAIT is not supported)
+ * and only __GFP_NOFAIL is supported (i.e. __GFP_NORETRY and
+ * __GFP_RETRY_MAYFAIL are not supported).
+ *
+ * __GFP_NOWARN can be used to suppress failures messages.
  *
  * Map them into contiguous kernel virtual space, using a pagetable
  * protection of @prot.
@@ -3056,9 +3093,14 @@ again:
 				  VM_UNINITIALIZED | vm_flags, start, end, node,
 				  gfp_mask, caller);
 	if (!area) {
+		bool nofail = gfp_mask & __GFP_NOFAIL;
 		warn_alloc(gfp_mask, NULL,
-			"vmalloc error: size %lu, vm_struct allocation failed",
-			real_size);
+			"vmalloc error: size %lu, vm_struct allocation failed%s",
+			real_size, (nofail) ? ". Retrying." : "");
+		if (nofail) {
+			schedule_timeout_uninterruptible(1);
+			goto again;
+		}
 		goto fail;
 	}
 
@@ -3074,7 +3116,8 @@ again:
 	clear_vm_uninitialized_flag(area);
 
 	size = PAGE_ALIGN(size);
-	kmemleak_vmalloc(area, size, gfp_mask);
+	if (!(vm_flags & VM_DEFER_KMEMLEAK))
+		kmemleak_vmalloc(area, size, gfp_mask);
 
 	return addr;