Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:
 "Am experimenting with splitting MM up into identifiable subsystems
  perhaps with a view to gitifying it in complex ways. Also with more
  verbose "incoming" emails.

  Most of MM is here and a few other trees.

  Subsystems affected by this patch series:
   - hotfixes
   - iommu
   - scripts
   - arch/sh
   - ocfs2
   - mm:slab-generic
   - mm:slub
   - mm:kmemleak
   - mm:kasan
   - mm:cleanups
   - mm:debug
   - mm:pagecache
   - mm:swap
   - mm:memcg
   - mm:gup
   - mm:pagemap
   - mm:infrastructure
   - mm:vmalloc
   - mm:initialization
   - mm:pagealloc
   - mm:vmscan
   - mm:tools
   - mm:proc
   - mm:ras
   - mm:oom-kill

  hotfixes:
      mm: vmscan: scan anonymous pages on file refaults
      mm/nvdimm: add is_ioremap_addr and use that to check ioremap address
      mm/memcontrol: fix wrong statistics in memory.stat
      mm/z3fold.c: lock z3fold page before  __SetPageMovable()
      nilfs2: do not use unexported cpu_to_le32()/le32_to_cpu() in uapi header
      MAINTAINERS: nilfs2: update email address

  iommu:
      include/linux/dmar.h: replace single-char identifiers in macros

  scripts:
      scripts/decode_stacktrace: match basepath using shell prefix operator, not regex
      scripts/decode_stacktrace: look for modules with .ko.debug extension
      scripts/spelling.txt: drop "sepc" from the misspelling list
      scripts/spelling.txt: add spelling fix for prohibited
      scripts/decode_stacktrace: Accept dash/underscore in modules
      scripts/spelling.txt: add more spellings to spelling.txt

  arch/sh:
      arch/sh/configs/sdk7786_defconfig: remove CONFIG_LOGFS
      sh: config: remove left-over BACKLIGHT_LCD_SUPPORT
      sh: prevent warnings when using iounmap

  ocfs2:
      fs: ocfs: fix spelling mistake "hearbeating" -> "heartbeat"
      ocfs2/dlm: use struct_size() helper
      ocfs2: add last unlock times in locking_state
      ocfs2: add locking filter debugfs file
      ocfs2: add first lock wait time in locking_state
      ocfs: no need to check return value of debugfs_create functions
      fs/ocfs2/dlmglue.c: unneeded variable: "status"
      ocfs2: use kmemdup rather than duplicating its implementation

  mm:slab-generic:
    Patch series "mm/slab: Improved sanity checking":
      mm/slab: validate cache membership under freelist hardening
      mm/slab: sanity-check page type when looking up cache
      lkdtm/heap: add tests for freelist hardening

  mm:slub:
      mm/slub.c: avoid double string traverse in kmem_cache_flags()
      slub: don't panic for memcg kmem cache creation failure

  mm:kmemleak:
      mm/kmemleak.c: fix check for softirq context
      mm/kmemleak.c: change error at _write when kmemleak is disabled
      docs: kmemleak: add more documentation details

  mm:kasan:
      mm/kasan: print frame description for stack bugs
      Patch series "Bitops instrumentation for KASAN", v5:
        lib/test_kasan: add bitops tests
        x86: use static_cpu_has in uaccess region to avoid instrumentation
        asm-generic, x86: add bitops instrumentation for KASAN
      Patch series "mm/kasan: Add object validation in ksize()", v3:
        mm/kasan: introduce __kasan_check_{read,write}
        mm/kasan: change kasan_check_{read,write} to return boolean
        lib/test_kasan: Add test for double-kzfree detection
        mm/slab: refactor common ksize KASAN logic into slab_common.c
        mm/kasan: add object validation in ksize()

  mm:cleanups:
      include/linux/pfn_t.h: remove pfn_t_to_virt()
      Patch series "remove ARCH_SELECT_MEMORY_MODEL where it has no effect":
        arm: remove ARCH_SELECT_MEMORY_MODEL
        s390: remove ARCH_SELECT_MEMORY_MODEL
        sparc: remove ARCH_SELECT_MEMORY_MODEL
      mm/gup.c: make follow_page_mask() static
      mm/memory.c: trivial clean up in insert_page()
      mm: make !CONFIG_HUGE_PAGE wrappers into static inlines
      include/linux/mm_types.h: ifdef struct vm_area_struct::swap_readahead_info
      mm: remove the account_page_dirtied export
      mm/page_isolation.c: change the prototype of undo_isolate_page_range()
      include/linux/vmpressure.h: use spinlock_t instead of struct spinlock
      mm: remove the exporting of totalram_pages
      include/linux/pagemap.h: document trylock_page() return value

  mm:debug:
      mm/failslab.c: by default, do not fail allocations with direct reclaim only
      Patch series "debug_pagealloc improvements":
        mm, debug_pagelloc: use static keys to enable debugging
        mm, page_alloc: more extensive free page checking with debug_pagealloc
        mm, debug_pagealloc: use a page type instead of page_ext flag

  mm:pagecache:
      Patch series "fix filler_t callback type mismatches", v2:
        mm/filemap.c: fix an overly long line in read_cache_page
        mm/filemap: don't cast ->readpage to filler_t for do_read_cache_page
        jffs2: pass the correct prototype to read_cache_page
        9p: pass the correct prototype to read_cache_page
      mm/filemap.c: correct the comment about VM_FAULT_RETRY

  mm:swap:
      mm, swap: fix race between swapoff and some swap operations
      mm/swap_state.c: simplify total_swapcache_pages() with get_swap_device()
      mm, swap: use rbtree for swap_extent
      mm/mincore.c: fix race between swapoff and mincore

  mm:memcg:
      memcg, oom: no oom-kill for __GFP_RETRY_MAYFAIL
      memcg, fsnotify: no oom-kill for remote memcg charging
      mm, memcg: introduce memory.events.local
      mm: memcontrol: dump memory.stat during cgroup OOM
      Patch series "mm: reparent slab memory on cgroup removal", v7:
        mm: memcg/slab: postpone kmem_cache memcg pointer initialization to memcg_link_cache()
        mm: memcg/slab: rename slab delayed deactivation functions and fields
        mm: memcg/slab: generalize postponed non-root kmem_cache deactivation
        mm: memcg/slab: introduce __memcg_kmem_uncharge_memcg()
        mm: memcg/slab: unify SLAB and SLUB page accounting
        mm: memcg/slab: don't check the dying flag on kmem_cache creation
        mm: memcg/slab: synchronize access to kmem_cache dying flag using a spinlock
        mm: memcg/slab: rework non-root kmem_cache lifecycle management
        mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages
        mm: memcg/slab: reparent memcg kmem_caches on cgroup removal
      mm, memcg: add a memcg_slabinfo debugfs file

  mm:gup:
      Patch series "switch the remaining architectures to use generic GUP", v4:
        mm: use untagged_addr() for get_user_pages_fast addresses
        mm: simplify gup_fast_permitted
        mm: lift the x86_32 PAE version of gup_get_pte to common code
        MIPS: use the generic get_user_pages_fast code
        sh: add the missing pud_page definition
        sh: use the generic get_user_pages_fast code
        sparc64: add the missing pgd_page definition
        sparc64: define untagged_addr()
        sparc64: use the generic get_user_pages_fast code
        mm: rename CONFIG_HAVE_GENERIC_GUP to CONFIG_HAVE_FAST_GUP
        mm: reorder code blocks in gup.c
        mm: consolidate the get_user_pages* implementations
        mm: validate get_user_pages_fast flags
        mm: move the powerpc hugepd code to mm/gup.c
        mm: switch gup_hugepte to use try_get_compound_head
        mm: mark the page referenced in gup_hugepte
      mm/gup: speed up check_and_migrate_cma_pages() on huge page
      mm/gup.c: remove some BUG_ONs from get_gate_page()
      mm/gup.c: mark undo_dev_pagemap as __maybe_unused

  mm:pagemap:
      asm-generic, x86: introduce generic pte_{alloc,free}_one[_kernel]
      alpha: switch to generic version of pte allocation
      arm: switch to generic version of pte allocation
      arm64: switch to generic version of pte allocation
      csky: switch to generic version of pte allocation
      m68k: sun3: switch to generic version of pte allocation
      mips: switch to generic version of pte allocation
      nds32: switch to generic version of pte allocation
      nios2: switch to generic version of pte allocation
      parisc: switch to generic version of pte allocation
      riscv: switch to generic version of pte allocation
      um: switch to generic version of pte allocation
      unicore32: switch to generic version of pte allocation
      mm/pgtable: drop pgtable_t variable from pte_fn_t functions
      mm/memory.c: fail when offset == num in first check of __vm_map_pages()

  mm:infrastructure:
      mm/mmu_notifier: use hlist_add_head_rcu()

  mm:vmalloc:
      Patch series "Some cleanups for the KVA/vmalloc", v5:
        mm/vmalloc.c: remove "node" argument
        mm/vmalloc.c: preload a CPU with one object for split purpose
        mm/vmalloc.c: get rid of one single unlink_va() when merge
        mm/vmalloc.c: switch to WARN_ON() and move it under unlink_va()
      mm/vmalloc.c: spelling> s/informaion/information/

  mm:initialization:
      mm/large system hash: use vmalloc for size > MAX_ORDER when !hashdist
      mm/large system hash: clear hashdist when only one node with memory is booted

  mm:pagealloc:
      arm64: move jump_label_init() before parse_early_param()
      Patch series "add init_on_alloc/init_on_free boot options", v10:
        mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options
        mm: init: report memory auto-initialization features at boot time

  mm:vmscan:
      mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
      mm: vmscan: correct some vmscan counters for THP swapout

  mm:tools:
      tools/vm/slabinfo: order command line options
      tools/vm/slabinfo: add partial slab listing to -X
      tools/vm/slabinfo: add option to sort by partial slabs
      tools/vm/slabinfo: add sorting info to help menu

  mm:proc:
      proc: use down_read_killable mmap_sem for /proc/pid/maps
      proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
      proc: use down_read_killable mmap_sem for /proc/pid/pagemap
      proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
      proc: use down_read_killable mmap_sem for /proc/pid/map_files
      mm: use down_read_killable for locking mmap_sem in access_remote_vm
      mm: smaps: split PSS into components
      mm: vmalloc: show number of vmalloc pages in /proc/meminfo

  mm:ras:
      mm/memory-failure.c: clarify error message

  mm:oom-kill:
      mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
      mm, oom: refactor dump_tasks for memcg OOMs
      mm, oom: remove redundant task_in_mem_cgroup() check
      oom: decouple mems_allowed from oom_unkillable_task
      mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()"

* akpm: (147 commits)
  mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()
  oom: decouple mems_allowed from oom_unkillable_task
  mm, oom: remove redundant task_in_mem_cgroup() check
  mm, oom: refactor dump_tasks for memcg OOMs
  mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
  mm/memory-failure.c: clarify error message
  mm: vmalloc: show number of vmalloc pages in /proc/meminfo
  mm: smaps: split PSS into components
  mm: use down_read_killable for locking mmap_sem in access_remote_vm
  proc: use down_read_killable mmap_sem for /proc/pid/map_files
  proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
  proc: use down_read_killable mmap_sem for /proc/pid/pagemap
  proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
  proc: use down_read_killable mmap_sem for /proc/pid/maps
  tools/vm/slabinfo: add sorting info to help menu
  tools/vm/slabinfo: add option to sort by partial slabs
  tools/vm/slabinfo: add partial slab listing to -X
  tools/vm/slabinfo: order command line options
  mm: vmscan: correct some vmscan counters for THP swapout
  mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
  ...

1 files changed, 156 insertions, 78 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8e3bc949ebcc..dbd0d5cbbcbb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -50,7 +50,6 @@
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
-#include <linux/page_ext.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
 #include <linux/compaction.h>
@@ -136,6 +135,55 @@ unsigned long totalcma_pages __read_mostly;
 
 int percpu_pagelist_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
+#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON
+DEFINE_STATIC_KEY_TRUE(init_on_alloc);
+#else
+DEFINE_STATIC_KEY_FALSE(init_on_alloc);
+#endif
+EXPORT_SYMBOL(init_on_alloc);
+
+#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON
+DEFINE_STATIC_KEY_TRUE(init_on_free);
+#else
+DEFINE_STATIC_KEY_FALSE(init_on_free);
+#endif
+EXPORT_SYMBOL(init_on_free);
+
+static int __init early_init_on_alloc(char *buf)
+{
+	int ret;
+	bool bool_result;
+
+	if (!buf)
+		return -EINVAL;
+	ret = kstrtobool(buf, &bool_result);
+	if (bool_result && page_poisoning_enabled())
+		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_alloc\n");
+	if (bool_result)
+		static_branch_enable(&init_on_alloc);
+	else
+		static_branch_disable(&init_on_alloc);
+	return ret;
+}
+early_param("init_on_alloc", early_init_on_alloc);
+
+static int __init early_init_on_free(char *buf)
+{
+	int ret;
+	bool bool_result;
+
+	if (!buf)
+		return -EINVAL;
+	ret = kstrtobool(buf, &bool_result);
+	if (bool_result && page_poisoning_enabled())
+		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_free\n");
+	if (bool_result)
+		static_branch_enable(&init_on_free);
+	else
+		static_branch_disable(&init_on_free);
+	return ret;
+}
+early_param("init_on_free", early_init_on_free);
 
 /*
  * A cached value of the page's pageblock's migratetype, used when the page is
@@ -224,8 +272,6 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {
 	[ZONE_MOVABLE] = 0,
 };
 
-EXPORT_SYMBOL(totalram_pages);
-
 static char * const zone_names[MAX_NR_ZONES] = {
 #ifdef CONFIG_ZONE_DMA
 	 "DMA",
@@ -646,30 +692,29 @@ void prep_compound_page(struct page *page, unsigned int order)
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 unsigned int _debug_guardpage_minorder;
-bool _debug_pagealloc_enabled __read_mostly
-			= IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
+
+#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT
+DEFINE_STATIC_KEY_TRUE(_debug_pagealloc_enabled);
+#else
+DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
+#endif
 EXPORT_SYMBOL(_debug_pagealloc_enabled);
-bool _debug_guardpage_enabled __read_mostly;
+
+DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
 
 static int __init early_debug_pagealloc(char *buf)
 {
-	if (!buf)
+	bool enable = false;
+
+	if (kstrtobool(buf, &enable))
 		return -EINVAL;
-	return kstrtobool(buf, &_debug_pagealloc_enabled);
-}
-early_param("debug_pagealloc", early_debug_pagealloc);
 
-static bool need_debug_guardpage(void)
-{
-	/* If we don't use debug_pagealloc, we don't need guard page */
-	if (!debug_pagealloc_enabled())
-		return false;
+	if (enable)
+		static_branch_enable(&_debug_pagealloc_enabled);
 
-	if (!debug_guardpage_minorder())
-		return false;
-
-	return true;
+	return 0;
 }
+early_param("debug_pagealloc", early_debug_pagealloc);
 
 static void init_debug_guardpage(void)
 {
@@ -679,14 +724,9 @@ static void init_debug_guardpage(void)
 	if (!debug_guardpage_minorder())
 		return;
 
-	_debug_guardpage_enabled = true;
+	static_branch_enable(&_debug_guardpage_enabled);
 }
 
-struct page_ext_operations debug_guardpage_ops = {
-	.need = need_debug_guardpage,
-	.init = init_debug_guardpage,
-};
-
 static int __init debug_guardpage_minorder_setup(char *buf)
 {
 	unsigned long res;
@@ -704,20 +744,13 @@ early_param("debug_guardpage_minorder", debug_guardpage_minorder_setup);
 static inline bool set_page_guard(struct zone *zone, struct page *page,
 				unsigned int order, int migratetype)
 {
-	struct page_ext *page_ext;
-
 	if (!debug_guardpage_enabled())
 		return false;
 
 	if (order >= debug_guardpage_minorder())
 		return false;
 
-	page_ext = lookup_page_ext(page);
-	if (unlikely(!page_ext))
-		return false;
-
-	__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
-
+	__SetPageGuard(page);
 	INIT_LIST_HEAD(&page->lru);
 	set_page_private(page, order);
 	/* Guard pages are not available for any usage */
@@ -729,23 +762,16 @@ static inline bool set_page_guard(struct zone *zone, struct page *page,
 static inline void clear_page_guard(struct zone *zone, struct page *page,
 				unsigned int order, int migratetype)
 {
-	struct page_ext *page_ext;
-
 	if (!debug_guardpage_enabled())
 		return;
 
-	page_ext = lookup_page_ext(page);
-	if (unlikely(!page_ext))
-		return;
-
-	__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
+	__ClearPageGuard(page);
 
 	set_page_private(page, 0);
 	if (!is_migrate_isolate(migratetype))
 		__mod_zone_freepage_state(zone, (1 << order), migratetype);
 }
 #else
-struct page_ext_operations debug_guardpage_ops;
 static inline bool set_page_guard(struct zone *zone, struct page *page,
 			unsigned int order, int migratetype) { return false; }
 static inline void clear_page_guard(struct zone *zone, struct page *page,
@@ -1090,6 +1116,14 @@ out:
 	return ret;
 }
 
+static void kernel_init_free_pages(struct page *page, int numpages)
+{
+	int i;
+
+	for (i = 0; i < numpages; i++)
+		clear_highpage(page + i);
+}
+
 static __always_inline bool free_pages_prepare(struct page *page,
 					unsigned int order, bool check_free)
 {
@@ -1141,6 +1175,9 @@ static __always_inline bool free_pages_prepare(struct page *page,
 					   PAGE_SIZE << order);
 	}
 	arch_free_page(page, order);
+	if (want_init_on_free())
+		kernel_init_free_pages(page, 1 << order);
+
 	kernel_poison_pages(page, 1 << order, 0);
 	if (debug_pagealloc_enabled())
 		kernel_map_pages(page, 1 << order, 0);
@@ -1151,19 +1188,36 @@ static __always_inline bool free_pages_prepare(struct page *page,
 }
 
 #ifdef CONFIG_DEBUG_VM
-static inline bool free_pcp_prepare(struct page *page)
+/*
+ * With DEBUG_VM enabled, order-0 pages are checked immediately when being freed
+ * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when
+ * moved from pcp lists to free lists.
+ */
+static bool free_pcp_prepare(struct page *page)
 {
 	return free_pages_prepare(page, 0, true);
 }
 
-static inline bool bulkfree_pcp_prepare(struct page *page)
+static bool bulkfree_pcp_prepare(struct page *page)
 {
-	return false;
+	if (debug_pagealloc_enabled())
+		return free_pages_check(page);
+	else
+		return false;
 }
 #else
+/*
+ * With DEBUG_VM disabled, order-0 pages being freed are checked only when
+ * moving from pcp lists to free list in order to reduce overhead. With
+ * debug_pagealloc enabled, they are checked also immediately when being freed
+ * to the pcp lists.
+ */
 static bool free_pcp_prepare(struct page *page)
 {
-	return free_pages_prepare(page, 0, false);
+	if (debug_pagealloc_enabled())
+		return free_pages_prepare(page, 0, true);
+	else
+		return free_pages_prepare(page, 0, false);
 }
 
 static bool bulkfree_pcp_prepare(struct page *page)
@@ -1904,6 +1958,10 @@ void __init page_alloc_init_late(void)
 
 	for_each_populated_zone(zone)
 		set_zone_contiguous(zone);
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	init_debug_guardpage();
+#endif
 }
 
 #ifdef CONFIG_CMA
@@ -2021,28 +2079,44 @@ static inline int check_new_page(struct page *page)
 
 static inline bool free_pages_prezeroed(void)
 {
-	return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) &&
-		page_poisoning_enabled();
+	return (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) &&
+		page_poisoning_enabled()) || want_init_on_free();
 }
 
 #ifdef CONFIG_DEBUG_VM
-static bool check_pcp_refill(struct page *page)
+/*
+ * With DEBUG_VM enabled, order-0 pages are checked for expected state when
+ * being allocated from pcp lists. With debug_pagealloc also enabled, they are
+ * also checked when pcp lists are refilled from the free lists.
+ */
+static inline bool check_pcp_refill(struct page *page)
 {
-	return false;
+	if (debug_pagealloc_enabled())
+		return check_new_page(page);
+	else
+		return false;
 }
 
-static bool check_new_pcp(struct page *page)
+static inline bool check_new_pcp(struct page *page)
 {
 	return check_new_page(page);
 }
 #else
-static bool check_pcp_refill(struct page *page)
+/*
+ * With DEBUG_VM disabled, free order-0 pages are checked for expected state
+ * when pcp lists are being refilled from the free lists. With debug_pagealloc
+ * enabled, they are also checked when being allocated from the pcp lists.
+ */
+static inline bool check_pcp_refill(struct page *page)
 {
 	return check_new_page(page);
 }
-static bool check_new_pcp(struct page *page)
+static inline bool check_new_pcp(struct page *page)
 {
-	return false;
+	if (debug_pagealloc_enabled())
+		return check_new_page(page);
+	else
+		return false;
 }
 #endif /* CONFIG_DEBUG_VM */
 
@@ -2076,13 +2150,10 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
 							unsigned int alloc_flags)
 {
-	int i;
-
 	post_alloc_hook(page, order, gfp_flags);
 
-	if (!free_pages_prezeroed() && (gfp_flags & __GFP_ZERO))
-		for (i = 0; i < (1 << order); i++)
-			clear_highpage(page + i);
+	if (!free_pages_prezeroed() && want_init_on_alloc(gfp_flags))
+		kernel_init_free_pages(page, 1 << order);
 
 	if (order && (gfp_flags & __GFP_COMP))
 		prep_compound_page(page, order);
@@ -7520,10 +7591,28 @@ static int page_alloc_cpu_dead(unsigned int cpu)
 	return 0;
 }
 
+#ifdef CONFIG_NUMA
+int hashdist = HASHDIST_DEFAULT;
+
+static int __init set_hashdist(char *str)
+{
+	if (!str)
+		return 0;
+	hashdist = simple_strtoul(str, &str, 0);
+	return 1;
+}
+__setup("hashdist=", set_hashdist);
+#endif
+
 void __init page_alloc_init(void)
 {
 	int ret;
 
+#ifdef CONFIG_NUMA
+	if (num_node_state(N_MEMORY) == 1)
+		hashdist = 0;
+#endif
+
 	ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC_DEAD,
 					"mm/page_alloc:dead", NULL,
 					page_alloc_cpu_dead);
@@ -7908,19 +7997,6 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_NUMA
-int hashdist = HASHDIST_DEFAULT;
-
-static int __init set_hashdist(char *str)
-{
-	if (!str)
-		return 0;
-	hashdist = simple_strtoul(str, &str, 0);
-	return 1;
-}
-__setup("hashdist=", set_hashdist);
-#endif
-
 #ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES
 /*
  * Returns the number of pages that arch has reserved but
@@ -7967,6 +8043,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 	unsigned long log2qty, size;
 	void *table = NULL;
 	gfp_t gfp_flags;
+	bool virt;
 
 	/* allow the kernel cmdline to have a say */
 	if (!numentries) {
@@ -8023,6 +8100,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 
 	gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC;
 	do {
+		virt = false;
 		size = bucketsize << log2qty;
 		if (flags & HASH_EARLY) {
 			if (flags & HASH_ZERO)
@@ -8030,26 +8108,26 @@ void *__init alloc_large_system_hash(const char *tablename,
 			else
 				table = memblock_alloc_raw(size,
 							   SMP_CACHE_BYTES);
-		} else if (hashdist) {
+		} else if (get_order(size) >= MAX_ORDER || hashdist) {
 			table = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+			virt = true;
 		} else {
 			/*
 			 * If bucketsize is not a power-of-two, we may free
 			 * some pages at the end of hash table which
 			 * alloc_pages_exact() automatically does
 			 */
-			if (get_order(size) < MAX_ORDER) {
-				table = alloc_pages_exact(size, gfp_flags);
-				kmemleak_alloc(table, size, 1, gfp_flags);
-			}
+			table = alloc_pages_exact(size, gfp_flags);
+			kmemleak_alloc(table, size, 1, gfp_flags);
 		}
 	} while (!table && size > PAGE_SIZE && --log2qty);
 
 	if (!table)
 		panic("Failed to allocate %s hash table\n", tablename);
 
-	pr_info("%s hash table entries: %ld (order: %d, %lu bytes)\n",
-		tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size);
+	pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n",
+		tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size,
+		virt ? "vmalloc" : "linear");
 
 	if (_hash_shift)
 		*_hash_shift = log2qty;