From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/mm/page_alloc.c | 3810 ++++++++++++++++++++++++++++++++++++-----------------------
1 files changed, 2,317 insertions(+), 1,493 deletions(-)
diff --git a/kernel/mm/page_alloc.c b/kernel/mm/page_alloc.c
index 3b5be03..3bcee27 100644
--- a/kernel/mm/page_alloc.c
+++ b/kernel/mm/page_alloc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/page_alloc.c
*
@@ -16,11 +17,11 @@
#include <linux/stddef.h>
#include <linux/mm.h>
+#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/jiffies.h>
-#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
@@ -43,12 +44,12 @@
#include <linux/mempolicy.h>
#include <linux/memremap.h>
#include <linux/stop_machine.h>
+#include <linux/random.h>
#include <linux/sort.h>
#include <linux/pfn.h>
#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>
@@ -60,20 +61,64 @@
#include <linux/hugetlb.h>
#include <linux/sched/rt.h>
#include <linux/sched/mm.h>
-#include <linux/locallock.h>
#include <linux/page_owner.h>
+#include <linux/page_pinner.h>
#include <linux/kthread.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
#include <linux/lockdep.h>
#include <linux/nmi.h>
-#include <linux/khugepaged.h>
#include <linux/psi.h>
+#include <linux/padata.h>
+#include <linux/khugepaged.h>
+#include <trace/hooks/mm.h>
+#include <trace/hooks/vmscan.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
+#include "shuffle.h"
+#include "page_reporting.h"
+
+/* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */
+typedef int __bitwise fpi_t;
+
+/* No special request */
+#define FPI_NONE ((__force fpi_t)0)
+
+/*
+ * Skip free page reporting notification for the (possibly merged) page.
+ * This does not hinder free page reporting from grabbing the page,
+ * reporting it and marking it "reported" - it only skips notifying
+ * the free page reporting infrastructure about a newly freed page. For
+ * example, used when temporarily pulling a page from a freelist and
+ * putting it back unmodified.
+ */
+#define FPI_SKIP_REPORT_NOTIFY ((__force fpi_t)BIT(0))
+
+/*
+ * Place the (possibly merged) page to the tail of the freelist. Will ignore
+ * page shuffling (relevant code - e.g., memory onlining - is expected to
+ * shuffle the whole zone).
+ *
+ * Note: No code should rely on this flag for correctness - it's purely
+ * to allow for optimizations when handing back either fresh pages
+ * (memory onlining) or untouched pages (page isolation, free page
+ * reporting).
+ */
+#define FPI_TO_TAIL ((__force fpi_t)BIT(1))
+
+/*
+ * Don't poison memory with KASAN (only for the tag-based modes).
+ * During boot, all non-reserved memblock memory is exposed to page_alloc.
+ * Poisoning all that memory lengthens boot time, especially on systems with
+ * large amount of RAM. This flag is used to skip that poisoning.
+ * This is only done for the tag-based KASAN modes, as those are able to
+ * detect memory corruptions with the memory tags assigned by default.
+ * All memory allocated normally after boot gets poisoned as usual.
+ */
+#define FPI_SKIP_KASAN_POISON ((__force fpi_t)BIT(2))
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
@@ -95,12 +140,15 @@
*/
DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */
EXPORT_PER_CPU_SYMBOL(_numa_mem_);
-int _node_numa_mem_[MAX_NUMNODES];
#endif
/* work_structs for global per-cpu drains */
-DEFINE_MUTEX(pcpu_drain_mutex);
-DEFINE_PER_CPU(struct work_struct, pcpu_drain);
+struct pcpu_drain {
+ struct zone *zone;
+ struct work_struct work;
+};
+static DEFINE_MUTEX(pcpu_drain_mutex);
+static DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);
#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
volatile unsigned long latent_entropy __latent_entropy;
@@ -124,62 +172,33 @@
};
EXPORT_SYMBOL(node_states);
-/* Protect totalram_pages and zone->managed_pages */
-static DEFINE_SPINLOCK(managed_page_count_lock);
-
-unsigned long totalram_pages __read_mostly;
+atomic_long_t _totalram_pages __read_mostly;
+EXPORT_SYMBOL(_totalram_pages);
unsigned long totalreserve_pages __read_mostly;
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 bool _init_on_alloc_enabled_early __read_mostly
+ = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON);
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;
+ return kstrtobool(buf, &_init_on_alloc_enabled_early);
}
early_param("init_on_alloc", early_init_on_alloc);
+static bool _init_on_free_enabled_early __read_mostly
+ = IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON);
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;
+ return kstrtobool(buf, &_init_on_free_enabled_early);
}
early_param("init_on_free", early_init_on_free);
@@ -243,7 +262,8 @@
unsigned int pageblock_order __read_mostly;
#endif
-static void __free_pages_ok(struct page *page, unsigned int order);
+static void __free_pages_ok(struct page *page, unsigned int order,
+ fpi_t fpi_flags);
/*
* results with 256, 32 in the lowmem_reserve sysctl:
@@ -270,8 +290,6 @@
[ZONE_MOVABLE] = 0,
};
-EXPORT_SYMBOL(totalram_pages);
-
static char * const zone_names[MAX_NR_ZONES] = {
#ifdef CONFIG_ZONE_DMA
"DMA",
@@ -289,7 +307,7 @@
#endif
};
-char * const migratetype_names[MIGRATE_TYPES] = {
+const char * const migratetype_names[MIGRATE_TYPES] = {
"Unmovable",
"Movable",
"Reclaimable",
@@ -302,14 +320,14 @@
#endif
};
-compound_page_dtor * const compound_page_dtors[] = {
- NULL,
- free_compound_page,
+compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = {
+ [NULL_COMPOUND_DTOR] = NULL,
+ [COMPOUND_PAGE_DTOR] = free_compound_page,
#ifdef CONFIG_HUGETLB_PAGE
- free_huge_page,
+ [HUGETLB_PAGE_DTOR] = free_huge_page,
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- free_transhuge_page,
+ [TRANSHUGE_PAGE_DTOR] = free_transhuge_page,
#endif
};
@@ -320,6 +338,20 @@
*/
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
+#ifdef CONFIG_DISCONTIGMEM
+/*
+ * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges
+ * are not on separate NUMA nodes. Functionally this works but with
+ * watermark_boost_factor, it can reclaim prematurely as the ranges can be
+ * quite small. By default, do not boost watermarks on discontigmem as in
+ * many cases very high-order allocations like THP are likely to be
+ * unsupported and the premature reclaim offsets the advantage of long-term
+ * fragmentation avoidance.
+ */
+int watermark_boost_factor __read_mostly;
+#else
+int watermark_boost_factor __read_mostly = 15000;
+#endif
int watermark_scale_factor = 10;
/*
@@ -329,42 +361,28 @@
*/
int extra_free_kbytes = 0;
-static unsigned long nr_kernel_pages __meminitdata;
-static unsigned long nr_all_pages __meminitdata;
-static unsigned long dma_reserve __meminitdata;
+static unsigned long nr_kernel_pages __initdata;
+static unsigned long nr_all_pages __initdata;
+static unsigned long dma_reserve __initdata;
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __meminitdata;
-static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __meminitdata;
+static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata;
+static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata;
static unsigned long required_kernelcore __initdata;
static unsigned long required_kernelcore_percent __initdata;
static unsigned long required_movablecore __initdata;
static unsigned long required_movablecore_percent __initdata;
-static unsigned long zone_movable_pfn[MAX_NUMNODES] __meminitdata;
+static unsigned long zone_movable_pfn[MAX_NUMNODES] __initdata;
static bool mirrored_kernelcore __meminitdata;
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int movable_zone;
EXPORT_SYMBOL(movable_zone);
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
#if MAX_NUMNODES > 1
-int nr_node_ids __read_mostly = MAX_NUMNODES;
-int nr_online_nodes __read_mostly = 1;
+unsigned int nr_node_ids __read_mostly = MAX_NUMNODES;
+unsigned int nr_online_nodes __read_mostly = 1;
EXPORT_SYMBOL(nr_node_ids);
EXPORT_SYMBOL(nr_online_nodes);
-#endif
-
-static DEFINE_LOCAL_IRQ_LOCK(pa_lock);
-
-#ifdef CONFIG_PREEMPT_RT_BASE
-# define cpu_lock_irqsave(cpu, flags) \
- local_lock_irqsave_on(pa_lock, flags, cpu)
-# define cpu_unlock_irqrestore(cpu, flags) \
- local_unlock_irqrestore_on(pa_lock, flags, cpu)
-#else
-# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags)
-# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags)
#endif
int page_group_by_mobility_disabled __read_mostly;
@@ -378,7 +396,7 @@
static DEFINE_STATIC_KEY_TRUE(deferred_pages);
/*
- * Calling kasan_free_pages() only after deferred memory initialization
+ * Calling kasan_poison_pages() only after deferred memory initialization
* has completed. Poisoning pages during deferred memory init will greatly
* lengthen the process and cause problem in large memory systems as the
* deferred pages initialization is done with interrupt disabled.
@@ -390,10 +408,12 @@
* on-demand allocation and then freed again before the deferred pages
* initialization is done, but this is not likely to happen.
*/
-static inline void kasan_free_nondeferred_pages(struct page *page, int order)
+static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
{
- if (!static_branch_unlikely(&deferred_pages))
- kasan_free_pages(page, order);
+ return static_branch_unlikely(&deferred_pages) ||
+ (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+ (fpi_flags & FPI_SKIP_KASAN_POISON)) ||
+ PageSkipKASanPoison(page);
}
/* Returns true if the struct page for the pfn is uninitialised */
@@ -408,38 +428,57 @@
}
/*
- * Returns false when the remaining initialisation should be deferred until
+ * Returns true when the remaining initialisation should be deferred until
* later in the boot cycle when it can be parallelised.
*/
-static inline bool update_defer_init(pg_data_t *pgdat,
- unsigned long pfn, unsigned long zone_end,
- unsigned long *nr_initialised)
+static bool __meminit
+defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
{
- /* Always populate low zones for address-constrained allocations */
- if (zone_end < pgdat_end_pfn(pgdat))
- return true;
- (*nr_initialised)++;
- if ((*nr_initialised > pgdat->static_init_pgcnt) &&
- (pfn & (PAGES_PER_SECTION - 1)) == 0) {
- pgdat->first_deferred_pfn = pfn;
- return false;
+ static unsigned long prev_end_pfn, nr_initialised;
+
+ /*
+ * prev_end_pfn static that contains the end of previous zone
+ * No need to protect because called very early in boot before smp_init.
+ */
+ if (prev_end_pfn != end_pfn) {
+ prev_end_pfn = end_pfn;
+ nr_initialised = 0;
}
- return true;
+ /* Always populate low zones for address-constrained allocations */
+ if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
+ return false;
+
+ if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
+ return true;
+ /*
+ * We start only with one section of pages, more pages are added as
+ * needed until the rest of deferred pages are initialized.
+ */
+ nr_initialised++;
+ if ((nr_initialised > PAGES_PER_SECTION) &&
+ (pfn & (PAGES_PER_SECTION - 1)) == 0) {
+ NODE_DATA(nid)->first_deferred_pfn = pfn;
+ return true;
+ }
+ return false;
}
#else
-#define kasan_free_nondeferred_pages(p, o) kasan_free_pages(p, o)
+static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
+{
+ return (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+ (fpi_flags & FPI_SKIP_KASAN_POISON)) ||
+ PageSkipKASanPoison(page);
+}
static inline bool early_page_uninitialised(unsigned long pfn)
{
return false;
}
-static inline bool update_defer_init(pg_data_t *pgdat,
- unsigned long pfn, unsigned long zone_end,
- unsigned long *nr_initialised)
+static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
{
- return true;
+ return false;
}
#endif
@@ -448,7 +487,7 @@
unsigned long pfn)
{
#ifdef CONFIG_SPARSEMEM
- return __pfn_to_section(pfn)->pageblock_flags;
+ return section_to_usemap(__pfn_to_section(pfn));
#else
return page_zone(page)->pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
@@ -458,25 +497,23 @@
{
#ifdef CONFIG_SPARSEMEM
pfn &= (PAGES_PER_SECTION-1);
- return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#else
pfn = pfn - round_down(page_zone(page)->zone_start_pfn, pageblock_nr_pages);
- return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#endif /* CONFIG_SPARSEMEM */
+ return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
}
/**
* get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
* @page: The page within the block of interest
* @pfn: The target page frame number
- * @end_bitidx: The last bit of interest to retrieve
* @mask: mask of bits that the caller is interested in
*
* Return: pageblock_bits flags
*/
-static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page,
+static __always_inline
+unsigned long __get_pfnblock_flags_mask(struct page *page,
unsigned long pfn,
- unsigned long end_bitidx,
unsigned long mask)
{
unsigned long *bitmap;
@@ -489,20 +526,36 @@
bitidx &= (BITS_PER_LONG-1);
word = bitmap[word_bitidx];
- bitidx += end_bitidx;
- return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
+ return (word >> bitidx) & mask;
}
unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
- unsigned long end_bitidx,
unsigned long mask)
{
- return __get_pfnblock_flags_mask(page, pfn, end_bitidx, mask);
+ return __get_pfnblock_flags_mask(page, pfn, mask);
}
+EXPORT_SYMBOL_GPL(get_pfnblock_flags_mask);
+
+int isolate_anon_lru_page(struct page *page)
+{
+ int ret;
+
+ if (!PageLRU(page) || !PageAnon(page))
+ return -EINVAL;
+
+ if (!get_page_unless_zero(page))
+ return -EINVAL;
+
+ ret = isolate_lru_page(page);
+ put_page(page);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(isolate_anon_lru_page);
static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn)
{
- return __get_pfnblock_flags_mask(page, pfn, PB_migrate_end, MIGRATETYPE_MASK);
+ return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK);
}
/**
@@ -510,12 +563,10 @@
* @page: The page within the block of interest
* @flags: The flags to set
* @pfn: The target page frame number
- * @end_bitidx: The last bit of interest
* @mask: mask of bits that the caller is interested in
*/
void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
unsigned long pfn,
- unsigned long end_bitidx,
unsigned long mask)
{
unsigned long *bitmap;
@@ -523,6 +574,7 @@
unsigned long old_word, word;
BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
+ BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits));
bitmap = get_pageblock_bitmap(page, pfn);
bitidx = pfn_to_bitidx(page, pfn);
@@ -531,9 +583,8 @@
VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
- bitidx += end_bitidx;
- mask <<= (BITS_PER_LONG - bitidx - 1);
- flags <<= (BITS_PER_LONG - bitidx - 1);
+ mask <<= bitidx;
+ flags <<= bitidx;
word = READ_ONCE(bitmap[word_bitidx]);
for (;;) {
@@ -550,8 +601,8 @@
migratetype < MIGRATE_PCPTYPES))
migratetype = MIGRATE_UNMOVABLE;
- set_pageblock_flags_group(page, (unsigned long)migratetype,
- PB_migrate, PB_migrate_end);
+ set_pfnblock_flags_mask(page, (unsigned long)migratetype,
+ page_to_pfn(page), MIGRATETYPE_MASK);
}
#ifdef CONFIG_DEBUG_VM
@@ -606,8 +657,7 @@
}
#endif
-static void bad_page(struct page *page, const char *reason,
- unsigned long bad_flags)
+static void bad_page(struct page *page, const char *reason)
{
static unsigned long resume;
static unsigned long nr_shown;
@@ -636,10 +686,6 @@
pr_alert("BUG: Bad page state in process %s pfn:%05lx\n",
current->comm, page_to_pfn(page));
__dump_page(page, reason);
- bad_flags &= page->flags;
- if (bad_flags)
- pr_alert("bad because of flags: %#lx(%pGp)\n",
- bad_flags, &bad_flags);
dump_page_owner(page);
print_modules();
@@ -667,7 +713,8 @@
void free_compound_page(struct page *page)
{
- __free_pages_ok(page, compound_order(page));
+ mem_cgroup_uncharge(page);
+ __free_pages_ok(page, compound_order(page), FPI_NONE);
}
void prep_compound_page(struct page *page, unsigned int order)
@@ -675,8 +722,6 @@
int i;
int nr_pages = 1 << order;
- set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
- set_compound_order(page, order);
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
@@ -684,51 +729,30 @@
p->mapping = TAIL_MAPPING;
set_compound_head(p, page);
}
+
+ set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
+ set_compound_order(page, order);
atomic_set(compound_mapcount_ptr(page), -1);
+ if (hpage_pincount_available(page))
+ atomic_set(compound_pincount_ptr(page), 0);
}
#ifdef CONFIG_DEBUG_PAGEALLOC
unsigned int _debug_guardpage_minorder;
-bool _debug_pagealloc_enabled __read_mostly
+
+bool _debug_pagealloc_enabled_early __read_mostly
= IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
+EXPORT_SYMBOL(_debug_pagealloc_enabled_early);
+DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
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)
- return -EINVAL;
- return kstrtobool(buf, &_debug_pagealloc_enabled);
+ return kstrtobool(buf, &_debug_pagealloc_enabled_early);
}
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 (!debug_guardpage_minorder())
- return false;
-
- return true;
-}
-
-static void init_debug_guardpage(void)
-{
- if (!debug_pagealloc_enabled())
- return;
-
- if (!debug_guardpage_minorder())
- return;
-
- _debug_guardpage_enabled = true;
-}
-
-struct page_ext_operations debug_guardpage_ops = {
- .need = need_debug_guardpage,
- .init = init_debug_guardpage,
-};
static int __init debug_guardpage_minorder_setup(char *buf)
{
@@ -747,20 +771,13 @@
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 */
@@ -772,39 +789,77 @@
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,
unsigned int order, int migratetype) {}
#endif
-static inline void set_page_order(struct page *page, unsigned int order)
+/*
+ * Enable static keys related to various memory debugging and hardening options.
+ * Some override others, and depend on early params that are evaluated in the
+ * order of appearance. So we need to first gather the full picture of what was
+ * enabled, and then make decisions.
+ */
+void init_mem_debugging_and_hardening(void)
+{
+ bool page_poisoning_requested = false;
+
+#ifdef CONFIG_PAGE_POISONING
+ /*
+ * Page poisoning is debug page alloc for some arches. If
+ * either of those options are enabled, enable poisoning.
+ */
+ if (page_poisoning_enabled() ||
+ (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) &&
+ debug_pagealloc_enabled())) {
+ static_branch_enable(&_page_poisoning_enabled);
+ page_poisoning_requested = true;
+ }
+#endif
+
+ if (_init_on_alloc_enabled_early) {
+ if (page_poisoning_requested)
+ pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
+ "will take precedence over init_on_alloc\n");
+ else
+ static_branch_enable(&init_on_alloc);
+ }
+ if (_init_on_free_enabled_early) {
+ if (page_poisoning_requested)
+ pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
+ "will take precedence over init_on_free\n");
+ else
+ static_branch_enable(&init_on_free);
+ }
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ if (!debug_pagealloc_enabled())
+ return;
+
+ static_branch_enable(&_debug_pagealloc_enabled);
+
+ if (!debug_guardpage_minorder())
+ return;
+
+ static_branch_enable(&_debug_guardpage_enabled);
+#endif
+}
+
+static inline void set_buddy_order(struct page *page, unsigned int order)
{
set_page_private(page, order);
__SetPageBuddy(page);
-}
-
-static inline void rmv_page_order(struct page *page)
-{
- __ClearPageBuddy(page);
- set_page_private(page, 0);
}
/*
@@ -820,32 +875,151 @@
*
* For recording page's order, we use page_private(page).
*/
-static inline int page_is_buddy(struct page *page, struct page *buddy,
+static inline bool page_is_buddy(struct page *page, struct page *buddy,
unsigned int order)
{
- if (page_is_guard(buddy) && page_order(buddy) == order) {
- if (page_zone_id(page) != page_zone_id(buddy))
- return 0;
+ if (!page_is_guard(buddy) && !PageBuddy(buddy))
+ return false;
- VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
+ if (buddy_order(buddy) != order)
+ return false;
- return 1;
- }
+ /*
+ * zone check is done late to avoid uselessly calculating
+ * zone/node ids for pages that could never merge.
+ */
+ if (page_zone_id(page) != page_zone_id(buddy))
+ return false;
- if (PageBuddy(buddy) && page_order(buddy) == order) {
- /*
- * zone check is done late to avoid uselessly
- * calculating zone/node ids for pages that could
- * never merge.
- */
- if (page_zone_id(page) != page_zone_id(buddy))
- return 0;
+ VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
- VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
+ return true;
+}
- return 1;
- }
- return 0;
+#ifdef CONFIG_COMPACTION
+static inline struct capture_control *task_capc(struct zone *zone)
+{
+ struct capture_control *capc = current->capture_control;
+
+ return unlikely(capc) &&
+ !(current->flags & PF_KTHREAD) &&
+ !capc->page &&
+ capc->cc->zone == zone ? capc : NULL;
+}
+
+static inline bool
+compaction_capture(struct capture_control *capc, struct page *page,
+ int order, int migratetype)
+{
+ if (!capc || order != capc->cc->order)
+ return false;
+
+ /* Do not accidentally pollute CMA or isolated regions*/
+ if (is_migrate_cma(migratetype) ||
+ is_migrate_isolate(migratetype))
+ return false;
+
+ /*
+ * Do not let lower order allocations polluate a movable pageblock.
+ * This might let an unmovable request use a reclaimable pageblock
+ * and vice-versa but no more than normal fallback logic which can
+ * have trouble finding a high-order free page.
+ */
+ if (order < pageblock_order && migratetype == MIGRATE_MOVABLE)
+ return false;
+
+ capc->page = page;
+ return true;
+}
+
+#else
+static inline struct capture_control *task_capc(struct zone *zone)
+{
+ return NULL;
+}
+
+static inline bool
+compaction_capture(struct capture_control *capc, struct page *page,
+ int order, int migratetype)
+{
+ return false;
+}
+#endif /* CONFIG_COMPACTION */
+
+/* Used for pages not on another list */
+static inline void add_to_free_list(struct page *page, struct zone *zone,
+ unsigned int order, int migratetype)
+{
+ struct free_area *area = &zone->free_area[order];
+
+ list_add(&page->lru, &area->free_list[migratetype]);
+ area->nr_free++;
+}
+
+/* Used for pages not on another list */
+static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
+ unsigned int order, int migratetype)
+{
+ struct free_area *area = &zone->free_area[order];
+
+ list_add_tail(&page->lru, &area->free_list[migratetype]);
+ area->nr_free++;
+}
+
+/*
+ * Used for pages which are on another list. Move the pages to the tail
+ * of the list - so the moved pages won't immediately be considered for
+ * allocation again (e.g., optimization for memory onlining).
+ */
+static inline void move_to_free_list(struct page *page, struct zone *zone,
+ unsigned int order, int migratetype)
+{
+ struct free_area *area = &zone->free_area[order];
+
+ list_move_tail(&page->lru, &area->free_list[migratetype]);
+}
+
+static inline void del_page_from_free_list(struct page *page, struct zone *zone,
+ unsigned int order)
+{
+ /* clear reported state and update reported page count */
+ if (page_reported(page))
+ __ClearPageReported(page);
+
+ list_del(&page->lru);
+ __ClearPageBuddy(page);
+ set_page_private(page, 0);
+ zone->free_area[order].nr_free--;
+}
+
+/*
+ * If this is not the largest possible page, check if the buddy
+ * of the next-highest order is free. If it is, it's possible
+ * that pages are being freed that will coalesce soon. In case,
+ * that is happening, add the free page to the tail of the list
+ * so it's less likely to be used soon and more likely to be merged
+ * as a higher order page
+ */
+static inline bool
+buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
+ struct page *page, unsigned int order)
+{
+ struct page *higher_page, *higher_buddy;
+ unsigned long combined_pfn;
+
+ if (order >= MAX_ORDER - 2)
+ return false;
+
+ if (!pfn_valid_within(buddy_pfn))
+ return false;
+
+ combined_pfn = buddy_pfn & pfn;
+ higher_page = page + (combined_pfn - pfn);
+ buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
+ higher_buddy = higher_page + (buddy_pfn - combined_pfn);
+
+ return pfn_valid_within(buddy_pfn) &&
+ page_is_buddy(higher_page, higher_buddy, order + 1);
}
/*
@@ -875,12 +1049,14 @@
static inline void __free_one_page(struct page *page,
unsigned long pfn,
struct zone *zone, unsigned int order,
- int migratetype)
+ int migratetype, fpi_t fpi_flags)
{
+ struct capture_control *capc = task_capc(zone);
+ unsigned long buddy_pfn;
unsigned long combined_pfn;
- unsigned long uninitialized_var(buddy_pfn);
- struct page *buddy;
unsigned int max_order;
+ struct page *buddy;
+ bool to_tail;
max_order = min_t(unsigned int, MAX_ORDER - 1, pageblock_order);
@@ -896,6 +1072,11 @@
continue_merging:
while (order < max_order) {
+ if (compaction_capture(capc, page, order, migratetype)) {
+ __mod_zone_freepage_state(zone, -(1 << order),
+ migratetype);
+ return;
+ }
buddy_pfn = __find_buddy_pfn(pfn, order);
buddy = page + (buddy_pfn - pfn);
@@ -907,13 +1088,10 @@
* Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
* merge with it and move up one order.
*/
- if (page_is_guard(buddy)) {
+ if (page_is_guard(buddy))
clear_page_guard(zone, buddy, order, migratetype);
- } else {
- list_del(&buddy->lru);
- zone->free_area[order].nr_free--;
- rmv_page_order(buddy);
- }
+ else
+ del_page_from_free_list(buddy, zone, order);
combined_pfn = buddy_pfn & pfn;
page = page + (combined_pfn - pfn);
pfn = combined_pfn;
@@ -945,33 +1123,23 @@
}
done_merging:
- set_page_order(page, order);
+ set_buddy_order(page, order);
- /*
- * If this is not the largest possible page, check if the buddy
- * of the next-highest order is free. If it is, it's possible
- * that pages are being freed that will coalesce soon. In case,
- * that is happening, add the free page to the tail of the list
- * so it's less likely to be used soon and more likely to be merged
- * as a higher order page
- */
- if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)) {
- struct page *higher_page, *higher_buddy;
- combined_pfn = buddy_pfn & pfn;
- higher_page = page + (combined_pfn - pfn);
- buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
- higher_buddy = higher_page + (buddy_pfn - combined_pfn);
- if (pfn_valid_within(buddy_pfn) &&
- page_is_buddy(higher_page, higher_buddy, order + 1)) {
- list_add_tail(&page->lru,
- &zone->free_area[order].free_list[migratetype]);
- goto out;
- }
- }
+ if (fpi_flags & FPI_TO_TAIL)
+ to_tail = true;
+ else if (is_shuffle_order(order))
+ to_tail = shuffle_pick_tail();
+ else
+ to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);
- list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
-out:
- zone->free_area[order].nr_free++;
+ if (to_tail)
+ add_to_free_list_tail(page, zone, order, migratetype);
+ else
+ add_to_free_list(page, zone, order, migratetype);
+
+ /* Notify page reporting subsystem of freed page */
+ if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY))
+ page_reporting_notify_free(order);
}
/*
@@ -996,13 +1164,9 @@
return true;
}
-static void free_pages_check_bad(struct page *page)
+static const char *page_bad_reason(struct page *page, unsigned long flags)
{
- const char *bad_reason;
- unsigned long bad_flags;
-
- bad_reason = NULL;
- bad_flags = 0;
+ const char *bad_reason = NULL;
if (unlikely(atomic_read(&page->_mapcount) != -1))
bad_reason = "nonzero mapcount";
@@ -1010,24 +1174,32 @@
bad_reason = "non-NULL mapping";
if (unlikely(page_ref_count(page) != 0))
bad_reason = "nonzero _refcount";
- if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) {
- bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
- bad_flags = PAGE_FLAGS_CHECK_AT_FREE;
+ if (unlikely(page->flags & flags)) {
+ if (flags == PAGE_FLAGS_CHECK_AT_PREP)
+ bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag(s) set";
+ else
+ bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
}
#ifdef CONFIG_MEMCG
if (unlikely(page->mem_cgroup))
bad_reason = "page still charged to cgroup";
#endif
- bad_page(page, bad_reason, bad_flags);
+ return bad_reason;
}
-static inline int free_pages_check(struct page *page)
+static void check_free_page_bad(struct page *page)
+{
+ bad_page(page,
+ page_bad_reason(page, PAGE_FLAGS_CHECK_AT_FREE));
+}
+
+static inline int check_free_page(struct page *page)
{
if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE)))
return 0;
/* Something has gone sideways, find it */
- free_pages_check_bad(page);
+ check_free_page_bad(page);
return 1;
}
@@ -1049,7 +1221,7 @@
case 1:
/* the first tail page: ->mapping may be compound_mapcount() */
if (unlikely(compound_mapcount(page))) {
- bad_page(page, "nonzero compound_mapcount", 0);
+ bad_page(page, "nonzero compound_mapcount");
goto out;
}
break;
@@ -1061,17 +1233,17 @@
break;
default:
if (page->mapping != TAIL_MAPPING) {
- bad_page(page, "corrupted mapping in tail page", 0);
+ bad_page(page, "corrupted mapping in tail page");
goto out;
}
break;
}
if (unlikely(!PageTail(page))) {
- bad_page(page, "PageTail not set", 0);
+ bad_page(page, "PageTail not set");
goto out;
}
if (unlikely(compound_head(page) != head_page)) {
- bad_page(page, "compound_head not consistent", 0);
+ bad_page(page, "compound_head not consistent");
goto out;
}
ret = 0;
@@ -1081,25 +1253,48 @@
return ret;
}
-static void kernel_init_free_pages(struct page *page, int numpages)
+static void kernel_init_free_pages(struct page *page, int numpages, bool zero_tags)
{
int i;
+ if (zero_tags) {
+ for (i = 0; i < numpages; i++)
+ tag_clear_highpage(page + i);
+ return;
+ }
+
/* s390's use of memset() could override KASAN redzones. */
kasan_disable_current();
- for (i = 0; i < numpages; i++)
+ for (i = 0; i < numpages; i++) {
+ u8 tag = page_kasan_tag(page + i);
+ page_kasan_tag_reset(page + i);
clear_highpage(page + i);
+ page_kasan_tag_set(page + i, tag);
+ }
kasan_enable_current();
}
static __always_inline bool free_pages_prepare(struct page *page,
- unsigned int order, bool check_free)
+ unsigned int order, bool check_free, fpi_t fpi_flags)
{
int bad = 0;
+ bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags);
VM_BUG_ON_PAGE(PageTail(page), page);
trace_mm_page_free(page, order);
+
+ if (unlikely(PageHWPoison(page)) && !order) {
+ /*
+ * Do not let hwpoison pages hit pcplists/buddy
+ * Untie memcg state and reset page's owner
+ */
+ if (memcg_kmem_enabled() && PageKmemcg(page))
+ __memcg_kmem_uncharge_page(page, order);
+ reset_page_owner(page, order);
+ free_page_pinner(page, order);
+ return false;
+ }
/*
* Check tail pages before head page information is cleared to
@@ -1116,7 +1311,7 @@
for (i = 1; i < (1 << order); i++) {
if (compound)
bad += free_tail_pages_check(page, page + i);
- if (unlikely(free_pages_check(page + i))) {
+ if (unlikely(check_free_page(page + i))) {
bad++;
continue;
}
@@ -1126,15 +1321,16 @@
if (PageMappingFlags(page))
page->mapping = NULL;
if (memcg_kmem_enabled() && PageKmemcg(page))
- memcg_kmem_uncharge(page, order);
+ __memcg_kmem_uncharge_page(page, order);
if (check_free)
- bad += free_pages_check(page);
+ bad += check_free_page(page);
if (bad)
return false;
page_cpupid_reset_last(page);
page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
reset_page_owner(page, order);
+ free_page_pinner(page, order);
if (!PageHighMem(page)) {
debug_check_no_locks_freed(page_address(page),
@@ -1142,36 +1338,77 @@
debug_check_no_obj_freed(page_address(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);
- kernel_map_pages(page, 1 << order, 0);
- kasan_free_nondeferred_pages(page, order);
+ kernel_poison_pages(page, 1 << order);
+
+ /*
+ * As memory initialization might be integrated into KASAN,
+ * kasan_free_pages and kernel_init_free_pages must be
+ * kept together to avoid discrepancies in behavior.
+ *
+ * With hardware tag-based KASAN, memory tags must be set before the
+ * page becomes unavailable via debug_pagealloc or arch_free_page.
+ */
+ if (kasan_has_integrated_init()) {
+ if (!skip_kasan_poison)
+ kasan_free_pages(page, order);
+ } else {
+ bool init = want_init_on_free();
+
+ if (init)
+ kernel_init_free_pages(page, 1 << order, false);
+ if (!skip_kasan_poison)
+ kasan_poison_pages(page, order, init);
+ }
+
+ /*
+ * arch_free_page() can make the page's contents inaccessible. s390
+ * does this. So nothing which can access the page's contents should
+ * happen after this.
+ */
+ arch_free_page(page, order);
+
+ debug_pagealloc_unmap_pages(page, 1 << order);
return true;
}
#ifdef CONFIG_DEBUG_VM
-static inline bool free_pcp_prepare(struct page *page)
-{
- return free_pages_prepare(page, 0, true);
-}
-
-static inline bool bulkfree_pcp_prepare(struct page *page)
-{
- return false;
-}
-#else
+/*
+ * 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, false);
+ return free_pages_prepare(page, 0, true, FPI_NONE);
}
static bool bulkfree_pcp_prepare(struct page *page)
{
- return free_pages_check(page);
+ if (debug_pagealloc_enabled_static())
+ return check_free_page(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)
+{
+ if (debug_pagealloc_enabled_static())
+ return free_pages_prepare(page, 0, true, FPI_NONE);
+ else
+ return free_pages_prepare(page, 0, false, FPI_NONE);
+}
+
+static bool bulkfree_pcp_prepare(struct page *page)
+{
+ return check_free_page(page);
}
#endif /* CONFIG_DEBUG_VM */
@@ -1185,7 +1422,7 @@
}
/*
- * Frees a number of pages which have been collected from the pcp lists.
+ * Frees a number of pages from the PCP lists
* Assumes all pages on list are in same zone, and of same order.
* count is the number of pages to free.
*
@@ -1195,57 +1432,15 @@
* And clear the zone's pages_scanned counter, to hold off the "all pages are
* pinned" detection logic.
*/
-static void free_pcppages_bulk(struct zone *zone, struct list_head *head,
- bool zone_retry)
-{
- bool isolated_pageblocks;
- struct page *page, *tmp;
- unsigned long flags;
-
- spin_lock_irqsave(&zone->lock, flags);
- isolated_pageblocks = has_isolate_pageblock(zone);
-
- /*
- * Use safe version since after __free_one_page(),
- * page->lru.next will not point to original list.
- */
- list_for_each_entry_safe(page, tmp, head, lru) {
- int mt = get_pcppage_migratetype(page);
-
- if (page_zone(page) != zone) {
- /*
- * free_unref_page_list() sorts pages by zone. If we end
- * up with pages from a different NUMA nodes belonging
- * to the same ZONE index then we need to redo with the
- * correct ZONE pointer. Skip the page for now, redo it
- * on the next iteration.
- */
- WARN_ON_ONCE(zone_retry == false);
- if (zone_retry)
- continue;
- }
-
- /* MIGRATE_ISOLATE page should not go to pcplists */
- VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
- /* Pageblock could have been isolated meanwhile */
- if (unlikely(isolated_pageblocks))
- mt = get_pageblock_migratetype(page);
-
- list_del(&page->lru);
- __free_one_page(page, page_to_pfn(page), zone, 0, mt);
- trace_mm_page_pcpu_drain(page, 0, mt);
- }
- spin_unlock_irqrestore(&zone->lock, flags);
-}
-
-static void isolate_pcp_pages(int count, struct per_cpu_pages *pcp,
- struct list_head *dst)
-
+static void free_pcppages_bulk(struct zone *zone, int count,
+ struct per_cpu_pages *pcp)
{
int migratetype = 0;
int batch_free = 0;
int prefetch_nr = 0;
- struct page *page;
+ bool isolated_pageblocks;
+ struct page *page, *tmp;
+ LIST_HEAD(head);
/*
* Ensure proper count is passed which otherwise would stuck in the
@@ -1282,7 +1477,7 @@
if (bulkfree_pcp_prepare(page))
continue;
- list_add_tail(&page->lru, dst);
+ list_add_tail(&page->lru, &head);
/*
* We are going to put the page back to the global
@@ -1297,19 +1492,39 @@
prefetch_buddy(page);
} while (--count && --batch_free && !list_empty(list));
}
+
+ spin_lock(&zone->lock);
+ isolated_pageblocks = has_isolate_pageblock(zone);
+
+ /*
+ * Use safe version since after __free_one_page(),
+ * page->lru.next will not point to original list.
+ */
+ list_for_each_entry_safe(page, tmp, &head, lru) {
+ int mt = get_pcppage_migratetype(page);
+ /* MIGRATE_ISOLATE page should not go to pcplists */
+ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
+ /* Pageblock could have been isolated meanwhile */
+ if (unlikely(isolated_pageblocks))
+ mt = get_pageblock_migratetype(page);
+
+ __free_one_page(page, page_to_pfn(page), zone, 0, mt, FPI_NONE);
+ trace_mm_page_pcpu_drain(page, 0, mt);
+ }
+ spin_unlock(&zone->lock);
}
static void free_one_page(struct zone *zone,
struct page *page, unsigned long pfn,
unsigned int order,
- int migratetype)
+ int migratetype, fpi_t fpi_flags)
{
spin_lock(&zone->lock);
if (unlikely(has_isolate_pageblock(zone) ||
is_migrate_isolate(migratetype))) {
migratetype = get_pfnblock_migratetype(page, pfn);
}
- __free_one_page(page, pfn, zone, order, migratetype);
+ __free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
spin_unlock(&zone->lock);
}
@@ -1383,33 +1598,50 @@
/* Avoid false-positive PageTail() */
INIT_LIST_HEAD(&page->lru);
- SetPageReserved(page);
+ /*
+ * no need for atomic set_bit because the struct
+ * page is not visible yet so nobody should
+ * access it yet.
+ */
+ __SetPageReserved(page);
}
}
}
-static void __free_pages_ok(struct page *page, unsigned int order)
+static void __free_pages_ok(struct page *page, unsigned int order,
+ fpi_t fpi_flags)
{
unsigned long flags;
int migratetype;
unsigned long pfn = page_to_pfn(page);
+ bool skip_free_unref_page = false;
- if (!free_pages_prepare(page, order, true))
+ if (!free_pages_prepare(page, order, true, fpi_flags))
return;
migratetype = get_pfnblock_migratetype(page, pfn);
- local_lock_irqsave(pa_lock, flags);
+ trace_android_vh_free_unref_page_bypass(page, order, migratetype, &skip_free_unref_page);
+ if (skip_free_unref_page)
+ return;
+
+ local_irq_save(flags);
__count_vm_events(PGFREE, 1 << order);
- free_one_page(page_zone(page), page, pfn, order, migratetype);
- local_unlock_irqrestore(pa_lock, flags);
+ free_one_page(page_zone(page), page, pfn, order, migratetype,
+ fpi_flags);
+ local_irq_restore(flags);
}
-static void __init __free_pages_boot_core(struct page *page, unsigned int order)
+void __free_pages_core(struct page *page, unsigned int order)
{
unsigned int nr_pages = 1 << order;
struct page *p = page;
unsigned int loop;
+ /*
+ * When initializing the memmap, __init_single_page() sets the refcount
+ * of all pages to 1 ("allocated"/"not free"). We have to set the
+ * refcount of all involved pages to 0.
+ */
prefetchw(p);
for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
prefetchw(p + 1);
@@ -1419,15 +1651,43 @@
__ClearPageReserved(p);
set_page_count(p, 0);
- page_zone(page)->managed_pages += nr_pages;
- set_page_refcounted(page);
- __free_pages(page, order);
+ atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
+
+ /*
+ * Bypass PCP and place fresh pages right to the tail, primarily
+ * relevant for memory onlining.
+ */
+ __free_pages_ok(page, order, FPI_TO_TAIL | FPI_SKIP_KASAN_POISON);
}
-#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
- defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
+#ifdef CONFIG_NEED_MULTIPLE_NODES
static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
+
+#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+
+/*
+ * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
+ */
+int __meminit __early_pfn_to_nid(unsigned long pfn,
+ struct mminit_pfnnid_cache *state)
+{
+ unsigned long start_pfn, end_pfn;
+ int nid;
+
+ if (state->last_start <= pfn && pfn < state->last_end)
+ return state->last_nid;
+
+ nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
+ if (nid != NUMA_NO_NODE) {
+ state->last_start = start_pfn;
+ state->last_end = end_pfn;
+ state->last_nid = nid;
+ }
+
+ return nid;
+}
+#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
int __meminit early_pfn_to_nid(unsigned long pfn)
{
@@ -1442,48 +1702,14 @@
return nid;
}
-#endif
+#endif /* CONFIG_NEED_MULTIPLE_NODES */
-#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-static inline bool __meminit __maybe_unused
-meminit_pfn_in_nid(unsigned long pfn, int node,
- struct mminit_pfnnid_cache *state)
-{
- int nid;
-
- nid = __early_pfn_to_nid(pfn, state);
- if (nid >= 0 && nid != node)
- return false;
- return true;
-}
-
-/* Only safe to use early in boot when initialisation is single-threaded */
-static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
-{
- return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache);
-}
-
-#else
-
-static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
-{
- return true;
-}
-static inline bool __meminit __maybe_unused
-meminit_pfn_in_nid(unsigned long pfn, int node,
- struct mminit_pfnnid_cache *state)
-{
- return true;
-}
-#endif
-
-
-void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
+void __init memblock_free_pages(struct page *page, unsigned long pfn,
unsigned int order)
{
if (early_page_uninitialised(pfn))
return;
- return __free_pages_boot_core(page, order);
+ __free_pages_core(page, order);
}
/*
@@ -1574,14 +1800,14 @@
if (nr_pages == pageblock_nr_pages &&
(pfn & (pageblock_nr_pages - 1)) == 0) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- __free_pages_boot_core(page, pageblock_order);
+ __free_pages_core(page, pageblock_order);
return;
}
for (i = 0; i < nr_pages; i++, page++, pfn++) {
if ((pfn & (pageblock_nr_pages - 1)) == 0)
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- __free_pages_boot_core(page, 0);
+ __free_pages_core(page, 0);
}
}
@@ -1604,20 +1830,12 @@
*
* Then, we check if a current large page is valid by only checking the validity
* of the head pfn.
- *
- * Finally, meminit_pfn_in_nid is checked on systems where pfns can interleave
- * within a node: a pfn is between start and end of a node, but does not belong
- * to this memory node.
*/
-static inline bool __init
-deferred_pfn_valid(int nid, unsigned long pfn,
- struct mminit_pfnnid_cache *nid_init_state)
+static inline bool __init deferred_pfn_valid(unsigned long pfn)
{
if (!pfn_valid_within(pfn))
return false;
if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
- return false;
- if (!meminit_pfn_in_nid(pfn, nid, nid_init_state))
return false;
return true;
}
@@ -1626,21 +1844,19 @@
* Free pages to buddy allocator. Try to free aligned pages in
* pageblock_nr_pages sizes.
*/
-static void __init deferred_free_pages(int nid, int zid, unsigned long pfn,
+static void __init deferred_free_pages(unsigned long pfn,
unsigned long end_pfn)
{
- struct mminit_pfnnid_cache nid_init_state = { };
unsigned long nr_pgmask = pageblock_nr_pages - 1;
unsigned long nr_free = 0;
for (; pfn < end_pfn; pfn++) {
- if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) {
+ if (!deferred_pfn_valid(pfn)) {
deferred_free_range(pfn - nr_free, nr_free);
nr_free = 0;
} else if (!(pfn & nr_pgmask)) {
deferred_free_range(pfn - nr_free, nr_free);
nr_free = 1;
- touch_nmi_watchdog();
} else {
nr_free++;
}
@@ -1654,22 +1870,22 @@
* by performing it only once every pageblock_nr_pages.
* Return number of pages initialized.
*/
-static unsigned long __init deferred_init_pages(int nid, int zid,
+static unsigned long __init deferred_init_pages(struct zone *zone,
unsigned long pfn,
unsigned long end_pfn)
{
- struct mminit_pfnnid_cache nid_init_state = { };
unsigned long nr_pgmask = pageblock_nr_pages - 1;
+ int nid = zone_to_nid(zone);
unsigned long nr_pages = 0;
+ int zid = zone_idx(zone);
struct page *page = NULL;
for (; pfn < end_pfn; pfn++) {
- if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) {
+ if (!deferred_pfn_valid(pfn)) {
page = NULL;
continue;
} else if (!page || !(pfn & nr_pgmask)) {
page = pfn_to_page(pfn);
- touch_nmi_watchdog();
} else {
page++;
}
@@ -1679,18 +1895,127 @@
return (nr_pages);
}
+/*
+ * This function is meant to pre-load the iterator for the zone init.
+ * Specifically it walks through the ranges until we are caught up to the
+ * first_init_pfn value and exits there. If we never encounter the value we
+ * return false indicating there are no valid ranges left.
+ */
+static bool __init
+deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone,
+ unsigned long *spfn, unsigned long *epfn,
+ unsigned long first_init_pfn)
+{
+ u64 j;
+
+ /*
+ * Start out by walking through the ranges in this zone that have
+ * already been initialized. We don't need to do anything with them
+ * so we just need to flush them out of the system.
+ */
+ for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) {
+ if (*epfn <= first_init_pfn)
+ continue;
+ if (*spfn < first_init_pfn)
+ *spfn = first_init_pfn;
+ *i = j;
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Initialize and free pages. We do it in two loops: first we initialize
+ * struct page, then free to buddy allocator, because while we are
+ * freeing pages we can access pages that are ahead (computing buddy
+ * page in __free_one_page()).
+ *
+ * In order to try and keep some memory in the cache we have the loop
+ * broken along max page order boundaries. This way we will not cause
+ * any issues with the buddy page computation.
+ */
+static unsigned long __init
+deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn,
+ unsigned long *end_pfn)
+{
+ unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES);
+ unsigned long spfn = *start_pfn, epfn = *end_pfn;
+ unsigned long nr_pages = 0;
+ u64 j = *i;
+
+ /* First we loop through and initialize the page values */
+ for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) {
+ unsigned long t;
+
+ if (mo_pfn <= *start_pfn)
+ break;
+
+ t = min(mo_pfn, *end_pfn);
+ nr_pages += deferred_init_pages(zone, *start_pfn, t);
+
+ if (mo_pfn < *end_pfn) {
+ *start_pfn = mo_pfn;
+ break;
+ }
+ }
+
+ /* Reset values and now loop through freeing pages as needed */
+ swap(j, *i);
+
+ for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) {
+ unsigned long t;
+
+ if (mo_pfn <= spfn)
+ break;
+
+ t = min(mo_pfn, epfn);
+ deferred_free_pages(spfn, t);
+
+ if (mo_pfn <= epfn)
+ break;
+ }
+
+ return nr_pages;
+}
+
+static void __init
+deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
+ void *arg)
+{
+ unsigned long spfn, epfn;
+ struct zone *zone = arg;
+ u64 i;
+
+ deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn);
+
+ /*
+ * Initialize and free pages in MAX_ORDER sized increments so that we
+ * can avoid introducing any issues with the buddy allocator.
+ */
+ while (spfn < end_pfn) {
+ deferred_init_maxorder(&i, zone, &spfn, &epfn);
+ cond_resched();
+ }
+}
+
+/* An arch may override for more concurrency. */
+__weak int __init
+deferred_page_init_max_threads(const struct cpumask *node_cpumask)
+{
+ return 1;
+}
+
/* Initialise remaining memory on a node */
static int __init deferred_init_memmap(void *data)
{
pg_data_t *pgdat = data;
- int nid = pgdat->node_id;
- unsigned long start = jiffies;
- unsigned long nr_pages = 0;
- unsigned long spfn, epfn, first_init_pfn, flags;
- phys_addr_t spa, epa;
- int zid;
- struct zone *zone;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+ unsigned long spfn = 0, epfn = 0;
+ unsigned long first_init_pfn, flags;
+ unsigned long start = jiffies;
+ struct zone *zone;
+ int zid, max_threads;
u64 i;
/* Bind memory initialisation thread to a local node if possible */
@@ -1723,30 +2048,36 @@
if (first_init_pfn < zone_end_pfn(zone))
break;
}
- first_init_pfn = max(zone->zone_start_pfn, first_init_pfn);
- /*
- * Initialize and free pages. We do it in two loops: first we initialize
- * struct page, than free to buddy allocator, because while we are
- * freeing pages we can access pages that are ahead (computing buddy
- * page in __free_one_page()).
- */
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
- nr_pages += deferred_init_pages(nid, zid, spfn, epfn);
- }
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
- deferred_free_pages(nid, zid, spfn, epfn);
- }
+ /* If the zone is empty somebody else may have cleared out the zone */
+ if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
+ first_init_pfn))
+ goto zone_empty;
+ max_threads = deferred_page_init_max_threads(cpumask);
+
+ while (spfn < epfn) {
+ unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION);
+ struct padata_mt_job job = {
+ .thread_fn = deferred_init_memmap_chunk,
+ .fn_arg = zone,
+ .start = spfn,
+ .size = epfn_align - spfn,
+ .align = PAGES_PER_SECTION,
+ .min_chunk = PAGES_PER_SECTION,
+ .max_threads = max_threads,
+ };
+
+ padata_do_multithreaded(&job);
+ deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
+ epfn_align);
+ }
+zone_empty:
/* Sanity check that the next zone really is unpopulated */
WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
- pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
- jiffies_to_msecs(jiffies - start));
+ pr_info("node %d deferred pages initialised in %ums\n",
+ pgdat->node_id, jiffies_to_msecs(jiffies - start));
pgdat_init_report_one_done();
return 0;
@@ -1770,14 +2101,11 @@
static noinline bool __init
deferred_grow_zone(struct zone *zone, unsigned int order)
{
- int zid = zone_idx(zone);
- int nid = zone_to_nid(zone);
- pg_data_t *pgdat = NODE_DATA(nid);
unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
- unsigned long nr_pages = 0;
- unsigned long first_init_pfn, spfn, epfn, t, flags;
+ pg_data_t *pgdat = zone->zone_pgdat;
unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
- phys_addr_t spa, epa;
+ unsigned long spfn, epfn, flags;
+ unsigned long nr_pages = 0;
u64 i;
/* Only the last zone may have deferred pages */
@@ -1795,38 +2123,37 @@
return true;
}
- first_init_pfn = max(zone->zone_start_pfn, first_deferred_pfn);
-
- if (first_init_pfn >= pgdat_end_pfn(pgdat)) {
+ /* If the zone is empty somebody else may have cleared out the zone */
+ if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
+ first_deferred_pfn)) {
+ pgdat->first_deferred_pfn = ULONG_MAX;
pgdat_resize_unlock(pgdat, &flags);
- return false;
+ /* Retry only once. */
+ return first_deferred_pfn != ULONG_MAX;
}
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
+ /*
+ * Initialize and free pages in MAX_ORDER sized increments so
+ * that we can avoid introducing any issues with the buddy
+ * allocator.
+ */
+ while (spfn < epfn) {
+ /* update our first deferred PFN for this section */
+ first_deferred_pfn = spfn;
- while (spfn < epfn && nr_pages < nr_pages_needed) {
- t = ALIGN(spfn + PAGES_PER_SECTION, PAGES_PER_SECTION);
- first_deferred_pfn = min(t, epfn);
- nr_pages += deferred_init_pages(nid, zid, spfn,
- first_deferred_pfn);
- spfn = first_deferred_pfn;
- }
+ nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
+ touch_nmi_watchdog();
+ /* We should only stop along section boundaries */
+ if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION)
+ continue;
+
+ /* If our quota has been met we can stop here */
if (nr_pages >= nr_pages_needed)
break;
}
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, first_deferred_pfn, PFN_DOWN(epa));
- deferred_free_pages(nid, zid, spfn, epfn);
-
- if (first_deferred_pfn == epfn)
- break;
- }
- pgdat->first_deferred_pfn = first_deferred_pfn;
+ pgdat->first_deferred_pfn = spfn;
pgdat_resize_unlock(pgdat, &flags);
return nr_pages > 0;
@@ -1849,9 +2176,9 @@
void __init page_alloc_init_late(void)
{
struct zone *zone;
+ int nid;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
- int nid;
/* There will be num_node_state(N_MEMORY) threads */
atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
@@ -1879,10 +2206,12 @@
/* Reinit limits that are based on free pages after the kernel is up */
files_maxfiles_init();
#endif
-#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+
/* Discard memblock private memory */
memblock_discard();
-#endif
+
+ for_each_node_state(nid, N_MEMORY)
+ shuffle_free_memory(NODE_DATA(nid));
for_each_populated_zone(zone)
set_zone_contiguous(zone);
@@ -1916,6 +2245,7 @@
}
adjust_managed_page_count(page, pageblock_nr_pages);
+ page_zone(page)->cma_pages += pageblock_nr_pages;
}
#endif
@@ -1934,13 +2264,11 @@
* -- nyc
*/
static inline void expand(struct zone *zone, struct page *page,
- int low, int high, struct free_area *area,
- int migratetype)
+ int low, int high, int migratetype)
{
unsigned long size = 1 << high;
while (high > low) {
- area--;
high--;
size >>= 1;
VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
@@ -1954,39 +2282,21 @@
if (set_page_guard(zone, &page[size], high, migratetype))
continue;
- list_add(&page[size].lru, &area->free_list[migratetype]);
- area->nr_free++;
- set_page_order(&page[size], high);
+ add_to_free_list(&page[size], zone, high, migratetype);
+ set_buddy_order(&page[size], high);
}
}
static void check_new_page_bad(struct page *page)
{
- const char *bad_reason = NULL;
- unsigned long bad_flags = 0;
-
- if (unlikely(atomic_read(&page->_mapcount) != -1))
- bad_reason = "nonzero mapcount";
- if (unlikely(page->mapping != NULL))
- bad_reason = "non-NULL mapping";
- if (unlikely(page_ref_count(page) != 0))
- bad_reason = "nonzero _count";
if (unlikely(page->flags & __PG_HWPOISON)) {
- bad_reason = "HWPoisoned (hardware-corrupted)";
- bad_flags = __PG_HWPOISON;
/* Don't complain about hwpoisoned pages */
page_mapcount_reset(page); /* remove PageBuddy */
return;
}
- if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
- bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
- bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
- }
-#ifdef CONFIG_MEMCG
- if (unlikely(page->mem_cgroup))
- bad_reason = "page still charged to cgroup";
-#endif
- bad_page(page, bad_reason, bad_flags);
+
+ bad_page(page,
+ page_bad_reason(page, PAGE_FLAGS_CHECK_AT_PREP));
}
/*
@@ -2002,30 +2312,40 @@
return 1;
}
-static inline bool free_pages_prezeroed(void)
-{
- 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_static())
+ 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_static())
+ return check_new_page(page);
+ else
+ return false;
}
#endif /* CONFIG_DEBUG_VM */
@@ -2049,9 +2369,31 @@
set_page_refcounted(page);
arch_alloc_page(page, order);
- kernel_map_pages(page, 1 << order, 1);
- kasan_alloc_pages(page, order);
- kernel_poison_pages(page, 1 << order, 1);
+ debug_pagealloc_map_pages(page, 1 << order);
+
+ /*
+ * Page unpoisoning must happen before memory initialization.
+ * Otherwise, the poison pattern will be overwritten for __GFP_ZERO
+ * allocations and the page unpoisoning code will complain.
+ */
+ kernel_unpoison_pages(page, 1 << order);
+
+ /*
+ * As memory initialization might be integrated into KASAN,
+ * kasan_alloc_pages and kernel_init_free_pages must be
+ * kept together to avoid discrepancies in behavior.
+ */
+ if (kasan_has_integrated_init()) {
+ kasan_alloc_pages(page, order, gfp_flags);
+ } else {
+ bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags);
+
+ kasan_unpoison_pages(page, order, init);
+ if (init)
+ kernel_init_free_pages(page, 1 << order,
+ gfp_flags & __GFP_ZEROTAGS);
+ }
+
set_page_owner(page, order, gfp_flags);
}
@@ -2059,9 +2401,6 @@
unsigned int alloc_flags)
{
post_alloc_hook(page, order, gfp_flags);
-
- 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);
@@ -2076,6 +2415,7 @@
set_page_pfmemalloc(page);
else
clear_page_pfmemalloc(page);
+ trace_android_vh_test_clear_look_around_ref(page);
}
/*
@@ -2093,14 +2433,11 @@
/* Find a page of the appropriate size in the preferred list */
for (current_order = order; current_order < MAX_ORDER; ++current_order) {
area = &(zone->free_area[current_order]);
- page = list_first_entry_or_null(&area->free_list[migratetype],
- struct page, lru);
+ page = get_page_from_free_area(area, migratetype);
if (!page)
continue;
- list_del(&page->lru);
- rmv_page_order(page);
- area->nr_free--;
- expand(zone, page, order, current_order, area, migratetype);
+ del_page_from_free_list(page, zone, current_order);
+ expand(zone, page, order, current_order, migratetype);
set_pcppage_migratetype(page, migratetype);
return page;
}
@@ -2113,10 +2450,10 @@
* This array describes the order lists are fallen back to when
* the free lists for the desirable migrate type are depleted
*/
-static int fallbacks[MIGRATE_TYPES][4] = {
+static int fallbacks[MIGRATE_TYPES][3] = {
[MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_TYPES },
- [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_TYPES },
[MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES },
+ [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_TYPES },
#ifdef CONFIG_CMA
[MIGRATE_CMA] = { MIGRATE_TYPES }, /* Never used */
#endif
@@ -2137,7 +2474,7 @@
#endif
/*
- * Move the free pages in a range to the free lists of the requested type.
+ * Move the free pages in a range to the freelist tail of the requested type.
* Note that start_page and end_pages are not aligned on a pageblock
* boundary. If alignment is required, use move_freepages_block()
*/
@@ -2149,30 +2486,11 @@
unsigned int order;
int pages_moved = 0;
-#ifndef CONFIG_HOLES_IN_ZONE
- /*
- * page_zone is not safe to call in this context when
- * CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant
- * anyway as we check zone boundaries in move_freepages_block().
- * Remove at a later date when no bug reports exist related to
- * grouping pages by mobility
- */
- VM_BUG_ON(pfn_valid(page_to_pfn(start_page)) &&
- pfn_valid(page_to_pfn(end_page)) &&
- page_zone(start_page) != page_zone(end_page));
-#endif
-
- if (num_movable)
- *num_movable = 0;
-
for (page = start_page; page <= end_page;) {
if (!pfn_valid_within(page_to_pfn(page))) {
page++;
continue;
}
-
- /* Make sure we are not inadvertently changing nodes */
- VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
if (!PageBuddy(page)) {
/*
@@ -2188,9 +2506,12 @@
continue;
}
- order = page_order(page);
- list_move(&page->lru,
- &zone->free_area[order].free_list[migratetype]);
+ /* Make sure we are not inadvertently changing nodes */
+ VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
+ VM_BUG_ON_PAGE(page_zone(page) != zone, page);
+
+ order = buddy_order(page);
+ move_to_free_list(page, zone, order, migratetype);
page += 1 << order;
pages_moved += 1 << order;
}
@@ -2203,6 +2524,9 @@
{
unsigned long start_pfn, end_pfn;
struct page *start_page, *end_page;
+
+ if (num_movable)
+ *num_movable = 0;
start_pfn = page_to_pfn(page);
start_pfn = start_pfn & ~(pageblock_nr_pages-1);
@@ -2264,6 +2588,43 @@
return false;
}
+static inline bool boost_watermark(struct zone *zone)
+{
+ unsigned long max_boost;
+
+ if (!watermark_boost_factor)
+ return false;
+ /*
+ * Don't bother in zones that are unlikely to produce results.
+ * On small machines, including kdump capture kernels running
+ * in a small area, boosting the watermark can cause an out of
+ * memory situation immediately.
+ */
+ if ((pageblock_nr_pages * 4) > zone_managed_pages(zone))
+ return false;
+
+ max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
+ watermark_boost_factor, 10000);
+
+ /*
+ * high watermark may be uninitialised if fragmentation occurs
+ * very early in boot so do not boost. We do not fall
+ * through and boost by pageblock_nr_pages as failing
+ * allocations that early means that reclaim is not going
+ * to help and it may even be impossible to reclaim the
+ * boosted watermark resulting in a hang.
+ */
+ if (!max_boost)
+ return false;
+
+ max_boost = max(pageblock_nr_pages, max_boost);
+
+ zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
+ max_boost);
+
+ return true;
+}
+
/*
* This function implements actual steal behaviour. If order is large enough,
* we can steal whole pageblock. If not, we first move freepages in this
@@ -2273,10 +2634,9 @@
* itself, so pages freed in the future will be put on the correct free list.
*/
static void steal_suitable_fallback(struct zone *zone, struct page *page,
- int start_type, bool whole_block)
+ unsigned int alloc_flags, int start_type, bool whole_block)
{
- unsigned int current_order = page_order(page);
- struct free_area *area;
+ unsigned int current_order = buddy_order(page);
int free_pages, movable_pages, alike_pages;
int old_block_type;
@@ -2294,6 +2654,14 @@
change_pageblock_range(page, current_order, start_type);
goto single_page;
}
+
+ /*
+ * Boost watermarks to increase reclaim pressure to reduce the
+ * likelihood of future fallbacks. Wake kswapd now as the node
+ * may be balanced overall and kswapd will not wake naturally.
+ */
+ if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD))
+ set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);
/* We are not allowed to try stealing from the whole block */
if (!whole_block)
@@ -2338,8 +2706,7 @@
return;
single_page:
- area = &zone->free_area[current_order];
- list_move(&page->lru, &area->free_list[start_type]);
+ move_to_free_list(page, zone, current_order, start_type);
}
/*
@@ -2363,7 +2730,7 @@
if (fallback_mt == MIGRATE_TYPES)
break;
- if (list_empty(&area->free_list[fallback_mt]))
+ if (free_area_empty(area, fallback_mt))
continue;
if (can_steal_fallback(order, migratetype))
@@ -2393,7 +2760,7 @@
* Limit the number reserved to 1 pageblock or roughly 1% of a zone.
* Check is race-prone but harmless.
*/
- max_managed = (zone->managed_pages / 100) + pageblock_nr_pages;
+ max_managed = (zone_managed_pages(zone) / 100) + pageblock_nr_pages;
if (zone->nr_reserved_highatomic >= max_managed)
return;
@@ -2435,8 +2802,9 @@
struct page *page;
int order;
bool ret;
+ bool skip_unreserve_highatomic = false;
- for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx,
+ for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx,
ac->nodemask) {
/*
* Preserve at least one pageblock unless memory pressure
@@ -2446,13 +2814,16 @@
pageblock_nr_pages)
continue;
+ trace_android_vh_unreserve_highatomic_bypass(force, zone,
+ &skip_unreserve_highatomic);
+ if (skip_unreserve_highatomic)
+ continue;
+
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
struct free_area *area = &(zone->free_area[order]);
- page = list_first_entry_or_null(
- &area->free_list[MIGRATE_HIGHATOMIC],
- struct page, lru);
+ page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC);
if (!page)
continue;
@@ -2510,20 +2881,30 @@
* condition simpler.
*/
static __always_inline bool
-__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
+__rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
+ unsigned int alloc_flags)
{
struct free_area *area;
int current_order;
+ int min_order = order;
struct page *page;
int fallback_mt;
bool can_steal;
+
+ /*
+ * Do not steal pages from freelists belonging to other pageblocks
+ * i.e. orders < pageblock_order. If there are no local zones free,
+ * the zonelists will be reiterated without ALLOC_NOFRAGMENT.
+ */
+ if (alloc_flags & ALLOC_NOFRAGMENT)
+ min_order = pageblock_order;
/*
* Find the largest available free page in the other list. This roughly
* approximates finding the pageblock with the most free pages, which
* would be too costly to do exactly.
*/
- for (current_order = MAX_ORDER - 1; current_order >= order;
+ for (current_order = MAX_ORDER - 1; current_order >= min_order;
--current_order) {
area = &(zone->free_area[current_order]);
fallback_mt = find_suitable_fallback(area, current_order,
@@ -2565,10 +2946,10 @@
VM_BUG_ON(current_order == MAX_ORDER);
do_steal:
- page = list_first_entry(&area->free_list[fallback_mt],
- struct page, lru);
+ page = get_page_from_free_area(area, fallback_mt);
- steal_suitable_fallback(zone, page, start_migratetype, can_steal);
+ steal_suitable_fallback(zone, page, alloc_flags, start_migratetype,
+ can_steal);
trace_mm_page_alloc_extfrag(page, order, current_order,
start_migratetype, fallback_mt);
@@ -2582,14 +2963,16 @@
* Call me with the zone->lock already held.
*/
static __always_inline struct page *
-__rmqueue(struct zone *zone, unsigned int order, int migratetype)
+__rmqueue(struct zone *zone, unsigned int order, int migratetype,
+ unsigned int alloc_flags)
{
struct page *page;
retry:
page = __rmqueue_smallest(zone, order, migratetype);
- if (unlikely(!page) && __rmqueue_fallback(zone, order, migratetype))
+ if (unlikely(!page) && __rmqueue_fallback(zone, order, migratetype,
+ alloc_flags))
goto retry;
trace_mm_page_alloc_zone_locked(page, order, migratetype);
@@ -2597,18 +2980,18 @@
}
#ifdef CONFIG_CMA
-static struct page *__rmqueue_cma(struct zone *zone, unsigned int order)
+static struct page *__rmqueue_cma(struct zone *zone, unsigned int order,
+ int migratetype,
+ unsigned int alloc_flags)
{
- struct page *page = 0;
-
- if (IS_ENABLED(CONFIG_CMA))
- if (!zone->cma_alloc)
- page = __rmqueue_cma_fallback(zone, order);
+ struct page *page = __rmqueue_cma_fallback(zone, order);
trace_mm_page_alloc_zone_locked(page, order, MIGRATE_CMA);
return page;
}
#else
-static inline struct page *__rmqueue_cma(struct zone *zone, unsigned int order)
+static inline struct page *__rmqueue_cma(struct zone *zone, unsigned int order,
+ int migratetype,
+ unsigned int alloc_flags)
{
return NULL;
}
@@ -2621,7 +3004,7 @@
*/
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
- int migratetype)
+ int migratetype, unsigned int alloc_flags)
{
int i, alloced = 0;
@@ -2629,15 +3012,11 @@
for (i = 0; i < count; ++i) {
struct page *page;
- /*
- * If migrate type CMA is being requested only try to
- * satisfy the request with CMA pages to try and increase
- * CMA utlization.
- */
if (is_migrate_cma(migratetype))
- page = __rmqueue_cma(zone, order);
+ page = __rmqueue_cma(zone, order, migratetype,
+ alloc_flags);
else
- page = __rmqueue(zone, order, migratetype);
+ page = __rmqueue(zone, order, migratetype, alloc_flags);
if (unlikely(page == NULL))
break;
@@ -2680,14 +3059,18 @@
*/
static struct list_head *get_populated_pcp_list(struct zone *zone,
unsigned int order, struct per_cpu_pages *pcp,
- int migratetype)
+ int migratetype, unsigned int alloc_flags)
{
struct list_head *list = &pcp->lists[migratetype];
if (list_empty(list)) {
+ trace_android_vh_rmqueue_bulk_bypass(order, pcp, migratetype, list);
+ if (!list_empty(list))
+ return list;
+
pcp->count += rmqueue_bulk(zone, order,
pcp->batch, list,
- migratetype);
+ migratetype, alloc_flags);
if (list_empty(list))
list = NULL;
@@ -2708,18 +3091,13 @@
{
unsigned long flags;
int to_drain, batch;
- LIST_HEAD(dst);
- local_lock_irqsave(pa_lock, flags);
+ local_irq_save(flags);
batch = READ_ONCE(pcp->batch);
to_drain = min(pcp->count, batch);
if (to_drain > 0)
- isolate_pcp_pages(to_drain, pcp, &dst);
-
- local_unlock_irqrestore(pa_lock, flags);
-
- if (to_drain > 0)
- free_pcppages_bulk(zone, &dst, false);
+ free_pcppages_bulk(zone, to_drain, pcp);
+ local_irq_restore(flags);
}
#endif
@@ -2735,21 +3113,14 @@
unsigned long flags;
struct per_cpu_pageset *pset;
struct per_cpu_pages *pcp;
- LIST_HEAD(dst);
- int count;
- cpu_lock_irqsave(cpu, flags);
+ local_irq_save(flags);
pset = per_cpu_ptr(zone->pageset, cpu);
pcp = &pset->pcp;
- count = pcp->count;
- if (count)
- isolate_pcp_pages(count, pcp, &dst);
-
- cpu_unlock_irqrestore(cpu, flags);
-
- if (count)
- free_pcppages_bulk(zone, &dst, false);
+ if (pcp->count)
+ free_pcppages_bulk(zone, pcp->count, pcp);
+ local_irq_restore(flags);
}
/*
@@ -2784,9 +3155,12 @@
drain_pages(cpu);
}
-#ifndef CONFIG_PREEMPT_RT_BASE
static void drain_local_pages_wq(struct work_struct *work)
{
+ struct pcpu_drain *drain;
+
+ drain = container_of(work, struct pcpu_drain, work);
+
/*
* drain_all_pages doesn't use proper cpu hotplug protection so
* we can race with cpu offline when the WQ can move this from
@@ -2795,10 +3169,9 @@
* a different one.
*/
preempt_disable();
- drain_local_pages(NULL);
+ drain_local_pages(drain->zone);
preempt_enable();
}
-#endif
/*
* Spill all the per-cpu pages from all CPUs back into the buddy allocator.
@@ -2865,22 +3238,16 @@
else
cpumask_clear_cpu(cpu, &cpus_with_pcps);
}
-#ifdef CONFIG_PREEMPT_RT_BASE
+
for_each_cpu(cpu, &cpus_with_pcps) {
- if (zone)
- drain_pages_zone(cpu, zone);
- else
- drain_pages(cpu);
- }
-#else
- for_each_cpu(cpu, &cpus_with_pcps) {
- struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
- INIT_WORK(work, drain_local_pages_wq);
- queue_work_on(cpu, mm_percpu_wq, work);
+ struct pcpu_drain *drain = per_cpu_ptr(&pcpu_drain, cpu);
+
+ drain->zone = zone;
+ INIT_WORK(&drain->work, drain_local_pages_wq);
+ queue_work_on(cpu, mm_percpu_wq, &drain->work);
}
for_each_cpu(cpu, &cpus_with_pcps)
- flush_work(per_cpu_ptr(&pcpu_drain, cpu));
-#endif
+ flush_work(&per_cpu_ptr(&pcpu_drain, cpu)->work);
mutex_unlock(&pcpu_drain_mutex);
}
@@ -2952,12 +3319,12 @@
return true;
}
-static void free_unref_page_commit(struct page *page, unsigned long pfn,
- struct list_head *dst)
+static void free_unref_page_commit(struct page *page, unsigned long pfn)
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
int migratetype;
+ bool pcp_skip_cma_pages = false;
migratetype = get_pcppage_migratetype(page);
__count_vm_event(PGFREE);
@@ -2970,8 +3337,12 @@
* excessively into the page allocator
*/
if (migratetype >= MIGRATE_PCPTYPES) {
- if (unlikely(is_migrate_isolate(migratetype))) {
- free_one_page(zone, page, pfn, 0, migratetype);
+ trace_android_vh_pcplist_add_cma_pages_bypass(migratetype,
+ &pcp_skip_cma_pages);
+ if (unlikely(is_migrate_isolate(migratetype)) ||
+ pcp_skip_cma_pages) {
+ free_one_page(zone, page, pfn, 0, migratetype,
+ FPI_NONE);
return;
}
migratetype = MIGRATE_MOVABLE;
@@ -2982,8 +3353,7 @@
pcp->count++;
if (pcp->count >= pcp->high) {
unsigned long batch = READ_ONCE(pcp->batch);
-
- isolate_pcp_pages(batch, pcp, dst);
+ free_pcppages_bulk(zone, batch, pcp);
}
}
@@ -2994,17 +3364,20 @@
{
unsigned long flags;
unsigned long pfn = page_to_pfn(page);
- struct zone *zone = page_zone(page);
- LIST_HEAD(dst);
+ int migratetype;
+ bool skip_free_unref_page = false;
if (!free_unref_page_prepare(page, pfn))
return;
- local_lock_irqsave(pa_lock, flags);
- free_unref_page_commit(page, pfn, &dst);
- local_unlock_irqrestore(pa_lock, flags);
- if (!list_empty(&dst))
- free_pcppages_bulk(zone, &dst, false);
+ migratetype = get_pfnblock_migratetype(page, pfn);
+ trace_android_vh_free_unref_page_bypass(page, 0, migratetype, &skip_free_unref_page);
+ if (skip_free_unref_page)
+ return;
+
+ local_irq_save(flags);
+ free_unref_page_commit(page, pfn);
+ local_irq_restore(flags);
}
/*
@@ -3015,11 +3388,6 @@
struct page *page, *next;
unsigned long flags, pfn;
int batch_count = 0;
- struct list_head dsts[__MAX_NR_ZONES];
- int i;
-
- for (i = 0; i < __MAX_NR_ZONES; i++)
- INIT_LIST_HEAD(&dsts[i]);
/* Prepare pages for freeing */
list_for_each_entry_safe(page, next, list, lru) {
@@ -3029,42 +3397,25 @@
set_page_private(page, pfn);
}
- local_lock_irqsave(pa_lock, flags);
+ local_irq_save(flags);
list_for_each_entry_safe(page, next, list, lru) {
unsigned long pfn = page_private(page);
- enum zone_type type;
set_page_private(page, 0);
trace_mm_page_free_batched(page);
- type = page_zonenum(page);
- free_unref_page_commit(page, pfn, &dsts[type]);
+ free_unref_page_commit(page, pfn);
/*
* Guard against excessive IRQ disabled times when we get
* a large list of pages to free.
*/
if (++batch_count == SWAP_CLUSTER_MAX) {
- local_unlock_irqrestore(pa_lock, flags);
+ local_irq_restore(flags);
batch_count = 0;
- local_lock_irqsave(pa_lock, flags);
+ local_irq_save(flags);
}
}
- local_unlock_irqrestore(pa_lock, flags);
-
- for (i = 0; i < __MAX_NR_ZONES; ) {
- struct page *page;
- struct zone *zone;
-
- if (list_empty(&dsts[i])) {
- i++;
- continue;
- }
-
- page = list_first_entry(&dsts[i], struct page, lru);
- zone = page_zone(page);
-
- free_pcppages_bulk(zone, &dsts[i], true);
- }
+ local_irq_restore(flags);
}
/*
@@ -3084,7 +3435,8 @@
for (i = 1; i < (1 << order); i++)
set_page_refcounted(page + i);
- split_page_owner(page, order);
+ split_page_owner(page, 1 << order);
+ split_page_memcg(page, 1 << order);
}
EXPORT_SYMBOL_GPL(split_page);
@@ -3106,7 +3458,7 @@
* watermark, because we already know our high-order page
* exists.
*/
- watermark = min_wmark_pages(zone) + (1UL << order);
+ watermark = zone->_watermark[WMARK_MIN] + (1UL << order);
if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
return 0;
@@ -3114,9 +3466,8 @@
}
/* Remove page from free list */
- list_del(&page->lru);
- zone->free_area[order].nr_free--;
- rmv_page_order(page);
+
+ del_page_from_free_list(page, zone, order);
/*
* Set the pageblock if the isolated page is at least half of a
@@ -3135,6 +3486,27 @@
return 1UL << order;
+}
+
+/**
+ * __putback_isolated_page - Return a now-isolated page back where we got it
+ * @page: Page that was isolated
+ * @order: Order of the isolated page
+ * @mt: The page's pageblock's migratetype
+ *
+ * This function is meant to return a page pulled from the free lists via
+ * __isolate_free_page back to the free lists they were pulled from.
+ */
+void __putback_isolated_page(struct page *page, unsigned int order, int mt)
+{
+ struct zone *zone = page_zone(page);
+
+ /* zone lock should be held when this function is called */
+ lockdep_assert_held(&zone->lock);
+
+ /* Return isolated page to tail of freelist. */
+ __free_one_page(page, page_to_pfn(page), zone, order, mt,
+ FPI_SKIP_REPORT_NOTIFY | FPI_TO_TAIL);
}
/*
@@ -3166,6 +3538,7 @@
/* Remove page from the per-cpu list, caller must protect the list */
static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
+ unsigned int alloc_flags,
struct per_cpu_pages *pcp,
gfp_t gfp_flags)
{
@@ -3175,9 +3548,9 @@
do {
/* First try to get CMA pages */
if (migratetype == MIGRATE_MOVABLE &&
- gfp_flags & __GFP_CMA) {
+ alloc_flags & ALLOC_CMA) {
list = get_populated_pcp_list(zone, 0, pcp,
- get_cma_migrate_type());
+ get_cma_migrate_type(), alloc_flags);
}
if (list == NULL) {
@@ -3186,7 +3559,7 @@
* free CMA pages.
*/
list = get_populated_pcp_list(zone, 0, pcp,
- migratetype);
+ migratetype, alloc_flags);
if (unlikely(list == NULL) ||
unlikely(list_empty(list)))
return NULL;
@@ -3202,22 +3575,22 @@
/* Lock and remove page from the per-cpu list */
static struct page *rmqueue_pcplist(struct zone *preferred_zone,
- struct zone *zone, unsigned int order,
- gfp_t gfp_flags, int migratetype)
+ struct zone *zone, gfp_t gfp_flags,
+ int migratetype, unsigned int alloc_flags)
{
struct per_cpu_pages *pcp;
struct page *page;
unsigned long flags;
- local_lock_irqsave(pa_lock, flags);
+ local_irq_save(flags);
pcp = &this_cpu_ptr(zone->pageset)->pcp;
- page = __rmqueue_pcplist(zone, migratetype, pcp,
+ page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp,
gfp_flags);
if (page) {
- __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
+ __count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
zone_statistics(preferred_zone, zone);
}
- local_unlock_irqrestore(pa_lock, flags);
+ local_irq_restore(flags);
return page;
}
@@ -3234,8 +3607,8 @@
struct page *page;
if (likely(order == 0)) {
- page = rmqueue_pcplist(preferred_zone, zone, order,
- gfp_flags, migratetype);
+ page = rmqueue_pcplist(preferred_zone, zone, gfp_flags,
+ migratetype, alloc_flags);
goto out;
}
@@ -3244,25 +3617,31 @@
* allocate greater than order-1 page units with __GFP_NOFAIL.
*/
WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
- local_spin_lock_irqsave(pa_lock, &zone->lock, flags);
+ spin_lock_irqsave(&zone->lock, flags);
do {
page = NULL;
-
- if (alloc_flags & ALLOC_HARDER) {
+ /*
+ * order-0 request can reach here when the pcplist is skipped
+ * due to non-CMA allocation context. HIGHATOMIC area is
+ * reserved for high-order atomic allocation, so order-0
+ * request should skip it.
+ */
+ if (order > 0 && alloc_flags & ALLOC_HARDER) {
page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
if (page)
trace_mm_page_alloc_zone_locked(page, order, migratetype);
}
-
- if (!page && migratetype == MIGRATE_MOVABLE &&
- gfp_flags & __GFP_CMA)
- page = __rmqueue_cma(zone, order);
-
- if (!page)
- page = __rmqueue(zone, order, migratetype);
+ if (!page) {
+ if (migratetype == MIGRATE_MOVABLE &&
+ alloc_flags & ALLOC_CMA)
+ page = __rmqueue_cma(zone, order, migratetype,
+ alloc_flags);
+ if (!page)
+ page = __rmqueue(zone, order, migratetype,
+ alloc_flags);
+ }
} while (page && check_new_pages(page, order));
-
spin_unlock(&zone->lock);
if (!page)
goto failed;
@@ -3271,14 +3650,22 @@
__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
zone_statistics(preferred_zone, zone);
- local_unlock_irqrestore(pa_lock, flags);
+ trace_android_vh_rmqueue(preferred_zone, zone, order,
+ gfp_flags, alloc_flags, migratetype);
+ local_irq_restore(flags);
out:
+ /* Separate test+clear to avoid unnecessary atomics */
+ if (test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags)) {
+ clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);
+ wakeup_kswapd(zone, 0, 0, zone_idx(zone));
+ }
+
VM_BUG_ON_PAGE(page && bad_range(zone, page), page);
return page;
failed:
- local_unlock_irqrestore(pa_lock, flags);
+ local_irq_restore(flags);
return NULL;
}
@@ -3303,7 +3690,7 @@
}
__setup("fail_page_alloc=", setup_fail_page_alloc);
-static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
if (order < fail_page_alloc.min_order)
return false;
@@ -3327,24 +3714,14 @@
dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
&fail_page_alloc.attr);
- if (IS_ERR(dir))
- return PTR_ERR(dir);
- if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
- &fail_page_alloc.ignore_gfp_reclaim))
- goto fail;
- if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir,
- &fail_page_alloc.ignore_gfp_highmem))
- goto fail;
- if (!debugfs_create_u32("min-order", mode, dir,
- &fail_page_alloc.min_order))
- goto fail;
+ debugfs_create_bool("ignore-gfp-wait", mode, dir,
+ &fail_page_alloc.ignore_gfp_reclaim);
+ debugfs_create_bool("ignore-gfp-highmem", mode, dir,
+ &fail_page_alloc.ignore_gfp_highmem);
+ debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order);
return 0;
-fail:
- debugfs_remove_recursive(dir);
-
- return -ENOMEM;
}
late_initcall(fail_page_alloc_debugfs);
@@ -3353,12 +3730,41 @@
#else /* CONFIG_FAIL_PAGE_ALLOC */
-static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
return false;
}
#endif /* CONFIG_FAIL_PAGE_ALLOC */
+
+noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+{
+ return __should_fail_alloc_page(gfp_mask, order);
+}
+ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
+
+static inline long __zone_watermark_unusable_free(struct zone *z,
+ unsigned int order, unsigned int alloc_flags)
+{
+ const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
+ long unusable_free = (1 << order) - 1;
+
+ /*
+ * If the caller does not have rights to ALLOC_HARDER then subtract
+ * the high-atomic reserves. This will over-estimate the size of the
+ * atomic reserve but it avoids a search.
+ */
+ if (likely(!alloc_harder))
+ unusable_free += z->nr_reserved_highatomic;
+
+#ifdef CONFIG_CMA
+ /* If allocation can't use CMA areas don't use free CMA pages */
+ if (!(alloc_flags & ALLOC_CMA))
+ unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
+
+ return unusable_free;
+}
/*
* Return true if free base pages are above 'mark'. For high-order checks it
@@ -3367,7 +3773,7 @@
* to check in the allocation paths if no pages are free.
*/
bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
- int classzone_idx, unsigned int alloc_flags,
+ int highest_zoneidx, unsigned int alloc_flags,
long free_pages)
{
long min = mark;
@@ -3375,19 +3781,12 @@
const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
/* free_pages may go negative - that's OK */
- free_pages -= (1 << order) - 1;
+ free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
- /*
- * If the caller does not have rights to ALLOC_HARDER then subtract
- * the high-atomic reserves. This will over-estimate the size of the
- * atomic reserve but it avoids a search.
- */
- if (likely(!alloc_harder)) {
- free_pages -= z->nr_reserved_highatomic;
- } else {
+ if (unlikely(alloc_harder)) {
/*
* OOM victims can try even harder than normal ALLOC_HARDER
* users on the grounds that it's definitely going to be in
@@ -3400,19 +3799,12 @@
min -= min / 4;
}
-
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
-
/*
* Check watermarks for an order-0 allocation request. If these
* are not met, then a high-order request also cannot go ahead
* even if a suitable page happened to be free.
*/
- if (free_pages <= min + z->lowmem_reserve[classzone_idx])
+ if (free_pages <= min + z->lowmem_reserve[highest_zoneidx])
return false;
/* If this is an order-0 request then the watermark is fine */
@@ -3436,65 +3828,83 @@
if (mt == MIGRATE_CMA)
continue;
#endif
- if (!list_empty(&area->free_list[mt]))
+ if (!free_area_empty(area, mt))
return true;
}
#ifdef CONFIG_CMA
if ((alloc_flags & ALLOC_CMA) &&
- !list_empty(&area->free_list[MIGRATE_CMA])) {
+ !free_area_empty(area, MIGRATE_CMA)) {
return true;
}
#endif
- if (alloc_harder &&
- !list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+ if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC))
return true;
}
return false;
}
bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
- int classzone_idx, unsigned int alloc_flags)
+ int highest_zoneidx, unsigned int alloc_flags)
{
- return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+ return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
zone_page_state(z, NR_FREE_PAGES));
}
+EXPORT_SYMBOL_GPL(zone_watermark_ok);
static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
- unsigned long mark, int classzone_idx, unsigned int alloc_flags)
+ unsigned long mark, int highest_zoneidx,
+ unsigned int alloc_flags, gfp_t gfp_mask)
{
- long free_pages = zone_page_state(z, NR_FREE_PAGES);
- long cma_pages = 0;
+ long free_pages;
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
+ free_pages = zone_page_state(z, NR_FREE_PAGES);
/*
* Fast check for order-0 only. If this fails then the reserves
- * need to be calculated. There is a corner case where the check
- * passes but only the high-order atomic reserve are free. If
- * the caller is !atomic then it'll uselessly search the free
- * list. That corner case is then slower but it is harmless.
+ * need to be calculated.
*/
- if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
- return true;
+ if (!order) {
+ long usable_free;
+ long reserved;
- return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
- free_pages);
+ usable_free = free_pages;
+ reserved = __zone_watermark_unusable_free(z, 0, alloc_flags);
+
+ /* reserved may over estimate high-atomic reserves. */
+ usable_free -= min(usable_free, reserved);
+ if (usable_free > mark + z->lowmem_reserve[highest_zoneidx])
+ return true;
+ }
+
+ if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
+ free_pages))
+ return true;
+ /*
+ * Ignore watermark boosting for GFP_ATOMIC order-0 allocations
+ * when checking the min watermark. The min watermark is the
+ * point where boosting is ignored so that kswapd is woken up
+ * when below the low watermark.
+ */
+ if (unlikely(!order && (gfp_mask & __GFP_ATOMIC) && z->watermark_boost
+ && ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) {
+ mark = z->_watermark[WMARK_MIN];
+ return __zone_watermark_ok(z, order, mark, highest_zoneidx,
+ alloc_flags, free_pages);
+ }
+
+ return false;
}
bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
- unsigned long mark, int classzone_idx)
+ unsigned long mark, int highest_zoneidx)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
- return __zone_watermark_ok(z, order, mark, classzone_idx, 0,
+ return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0,
free_pages);
}
EXPORT_SYMBOL_GPL(zone_watermark_ok_safe);
@@ -3503,7 +3913,7 @@
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
- RECLAIM_DISTANCE;
+ node_reclaim_distance;
}
#else /* CONFIG_NUMA */
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
@@ -3513,6 +3923,61 @@
#endif /* CONFIG_NUMA */
/*
+ * The restriction on ZONE_DMA32 as being a suitable zone to use to avoid
+ * fragmentation is subtle. If the preferred zone was HIGHMEM then
+ * premature use of a lower zone may cause lowmem pressure problems that
+ * are worse than fragmentation. If the next zone is ZONE_DMA then it is
+ * probably too small. It only makes sense to spread allocations to avoid
+ * fragmentation between the Normal and DMA32 zones.
+ */
+static inline unsigned int
+alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
+{
+ unsigned int alloc_flags;
+
+ /*
+ * __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
+ * to save a branch.
+ */
+ alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM);
+
+#ifdef CONFIG_ZONE_DMA32
+ if (!zone)
+ return alloc_flags;
+
+ if (zone_idx(zone) != ZONE_NORMAL)
+ return alloc_flags;
+
+ /*
+ * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and
+ * the pointer is within zone->zone_pgdat->node_zones[]. Also assume
+ * on UMA that if Normal is populated then so is DMA32.
+ */
+ BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1);
+ if (nr_online_nodes > 1 && !populated_zone(--zone))
+ return alloc_flags;
+
+ alloc_flags |= ALLOC_NOFRAGMENT;
+#endif /* CONFIG_ZONE_DMA32 */
+ return alloc_flags;
+}
+
+static inline unsigned int current_alloc_flags(gfp_t gfp_mask,
+ unsigned int alloc_flags)
+{
+#ifdef CONFIG_CMA
+ unsigned int pflags = current->flags;
+
+ if (!(pflags & PF_MEMALLOC_NOCMA) &&
+ gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE &&
+ gfp_mask & __GFP_CMA)
+ alloc_flags |= ALLOC_CMA;
+
+#endif
+ return alloc_flags;
+}
+
+/*
* get_page_from_freelist goes through the zonelist trying to allocate
* a page.
*/
@@ -3520,16 +3985,20 @@
get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
const struct alloc_context *ac)
{
- struct zoneref *z = ac->preferred_zoneref;
+ struct zoneref *z;
struct zone *zone;
struct pglist_data *last_pgdat_dirty_limit = NULL;
+ bool no_fallback;
+retry:
/*
* Scan zonelist, looking for a zone with enough free.
* See also __cpuset_node_allowed() comment in kernel/cpuset.c.
*/
- for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
- ac->nodemask) {
+ no_fallback = alloc_flags & ALLOC_NOFRAGMENT;
+ z = ac->preferred_zoneref;
+ for_next_zone_zonelist_nodemask(zone, z, ac->highest_zoneidx,
+ ac->nodemask) {
struct page *page;
unsigned long mark;
@@ -3566,9 +4035,26 @@
}
}
- mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
+ if (no_fallback && nr_online_nodes > 1 &&
+ zone != ac->preferred_zoneref->zone) {
+ int local_nid;
+
+ /*
+ * If moving to a remote node, retry but allow
+ * fragmenting fallbacks. Locality is more important
+ * than fragmentation avoidance.
+ */
+ local_nid = zone_to_nid(ac->preferred_zoneref->zone);
+ if (zone_to_nid(zone) != local_nid) {
+ alloc_flags &= ~ALLOC_NOFRAGMENT;
+ goto retry;
+ }
+ }
+
+ mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
if (!zone_watermark_fast(zone, order, mark,
- ac_classzone_idx(ac), alloc_flags)) {
+ ac->highest_zoneidx, alloc_flags,
+ gfp_mask)) {
int ret;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -3601,7 +4087,7 @@
default:
/* did we reclaim enough */
if (zone_watermark_ok(zone, order, mark,
- ac_classzone_idx(ac), alloc_flags))
+ ac->highest_zoneidx, alloc_flags))
goto try_this_zone;
continue;
@@ -3633,30 +4119,21 @@
}
}
+ /*
+ * It's possible on a UMA machine to get through all zones that are
+ * fragmented. If avoiding fragmentation, reset and try again.
+ */
+ if (no_fallback) {
+ alloc_flags &= ~ALLOC_NOFRAGMENT;
+ goto retry;
+ }
+
return NULL;
-}
-
-/*
- * Large machines with many possible nodes should not always dump per-node
- * meminfo in irq context.
- */
-static inline bool should_suppress_show_mem(void)
-{
- bool ret = false;
-
-#if NODES_SHIFT > 8
- ret = in_interrupt();
-#endif
- return ret;
}
static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
{
unsigned int filter = SHOW_MEM_FILTER_NODES;
- static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1);
-
- if (should_suppress_show_mem() || !__ratelimit(&show_mem_rs))
- return;
/*
* This documents exceptions given to allocations in certain
@@ -3677,22 +4154,23 @@
{
struct va_format vaf;
va_list args;
- static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL,
- DEFAULT_RATELIMIT_BURST);
+ static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1);
- if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+ if ((gfp_mask & __GFP_NOWARN) ||
+ !__ratelimit(&nopage_rs) ||
+ ((gfp_mask & __GFP_DMA) && !has_managed_dma()))
return;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
- pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl\n",
+ pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl",
current->comm, &vaf, gfp_mask, &gfp_mask,
nodemask_pr_args(nodemask));
va_end(args);
cpuset_print_current_mems_allowed();
-
+ pr_cont("\n");
dump_stack();
warn_alloc_show_mem(gfp_mask, nodemask);
}
@@ -3766,11 +4244,13 @@
* success so it is time to admit defeat. We will skip the OOM killer
* because it is very likely that the caller has a more reasonable
* fallback than shooting a random task.
+ *
+ * The OOM killer may not free memory on a specific node.
*/
- if (gfp_mask & __GFP_RETRY_MAYFAIL)
+ if (gfp_mask & (__GFP_RETRY_MAYFAIL | __GFP_THISNODE))
goto out;
/* The OOM killer does not needlessly kill tasks for lowmem */
- if (ac->high_zoneidx < ZONE_NORMAL)
+ if (ac->highest_zoneidx < ZONE_NORMAL)
goto out;
if (pm_suspended_storage())
goto out;
@@ -3783,10 +4263,6 @@
* out_of_memory). Once filesystems are ready to handle allocation
* failures more gracefully we should just bail out here.
*/
-
- /* The OOM killer may not free memory on a specific node */
- if (gfp_mask & __GFP_THISNODE)
- goto out;
/* Exhausted what can be done so it's blame time */
if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
@@ -3818,7 +4294,7 @@
unsigned int alloc_flags, const struct alloc_context *ac,
enum compact_priority prio, enum compact_result *compact_result)
{
- struct page *page;
+ struct page *page = NULL;
unsigned long pflags;
unsigned int noreclaim_flag;
@@ -3829,13 +4305,10 @@
noreclaim_flag = memalloc_noreclaim_save();
*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
- prio);
+ prio, &page);
memalloc_noreclaim_restore(noreclaim_flag);
psi_memstall_leave(&pflags);
-
- if (*compact_result <= COMPACT_INACTIVE)
- return NULL;
/*
* At least in one zone compaction wasn't deferred or skipped, so let's
@@ -3843,7 +4316,13 @@
*/
count_vm_event(COMPACTSTALL);
- page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
+ /* Prep a captured page if available */
+ if (page)
+ prep_new_page(page, order, gfp_mask, alloc_flags);
+
+ /* Try get a page from the freelist if available */
+ if (!page)
+ page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
if (page) {
struct zone *zone = page_zone(page);
@@ -3892,14 +4371,22 @@
goto check_priority;
/*
- * make sure the compaction wasn't deferred or didn't bail out early
- * due to locks contention before we declare that we should give up.
- * But do not retry if the given zonelist is not suitable for
- * compaction.
+ * compaction was skipped because there are not enough order-0 pages
+ * to work with, so we retry only if it looks like reclaim can help.
*/
- if (compaction_withdrawn(compact_result)) {
+ if (compaction_needs_reclaim(compact_result)) {
ret = compaction_zonelist_suitable(ac, order, alloc_flags);
goto out;
+ }
+
+ /*
+ * make sure the compaction wasn't deferred or didn't bail out early
+ * due to locks contention before we declare that we should give up.
+ * But the next retry should use a higher priority if allowed, so
+ * we don't just keep bailing out endlessly.
+ */
+ if (compaction_withdrawn(compact_result)) {
+ goto check_priority;
}
/*
@@ -3962,10 +4449,10 @@
* Let's give them a good hope and keep retrying while the order-0
* watermarks are OK.
*/
- for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
- ac->nodemask) {
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
+ ac->highest_zoneidx, ac->nodemask) {
if (zone_watermark_ok(zone, 0, min_wmark_pages(zone),
- ac_classzone_idx(ac), alloc_flags))
+ ac->highest_zoneidx, alloc_flags))
return true;
}
return false;
@@ -4023,33 +4510,50 @@
EXPORT_SYMBOL_GPL(fs_reclaim_release);
#endif
+/*
+ * Zonelists may change due to hotplug during allocation. Detect when zonelists
+ * have been rebuilt so allocation retries. Reader side does not lock and
+ * retries the allocation if zonelist changes. Writer side is protected by the
+ * embedded spin_lock.
+ */
+static DEFINE_SEQLOCK(zonelist_update_seq);
+
+static unsigned int zonelist_iter_begin(void)
+{
+ if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE))
+ return read_seqbegin(&zonelist_update_seq);
+
+ return 0;
+}
+
+static unsigned int check_retry_zonelist(unsigned int seq)
+{
+ if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE))
+ return read_seqretry(&zonelist_update_seq, seq);
+
+ return seq;
+}
+
/* Perform direct synchronous page reclaim */
-static int
+static unsigned long
__perform_reclaim(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac)
{
- struct reclaim_state reclaim_state;
- int progress;
unsigned int noreclaim_flag;
- unsigned long pflags;
+ unsigned long progress;
cond_resched();
/* We now go into synchronous reclaim */
cpuset_memory_pressure_bump();
- psi_memstall_enter(&pflags);
fs_reclaim_acquire(gfp_mask);
noreclaim_flag = memalloc_noreclaim_save();
- reclaim_state.reclaimed_slab = 0;
- current->reclaim_state = &reclaim_state;
progress = try_to_free_pages(ac->zonelist, order, gfp_mask,
ac->nodemask);
- current->reclaim_state = NULL;
memalloc_noreclaim_restore(noreclaim_flag);
fs_reclaim_release(gfp_mask);
- psi_memstall_leave(&pflags);
cond_resched();
@@ -4063,11 +4567,14 @@
unsigned long *did_some_progress)
{
struct page *page = NULL;
+ unsigned long pflags;
bool drained = false;
+ bool skip_pcp_drain = false;
+ psi_memstall_enter(&pflags);
*did_some_progress = __perform_reclaim(gfp_mask, order, ac);
if (unlikely(!(*did_some_progress)))
- return NULL;
+ goto out;
retry:
page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
@@ -4075,14 +4582,19 @@
/*
* If an allocation failed after direct reclaim, it could be because
* pages are pinned on the per-cpu lists or in high alloc reserves.
- * Shrink them them and try again
+ * Shrink them and try again
*/
if (!page && !drained) {
unreserve_highatomic_pageblock(ac, false);
- drain_all_pages(NULL);
+ trace_android_vh_drain_all_pages_bypass(gfp_mask, order,
+ alloc_flags, ac->migratetype, *did_some_progress, &skip_pcp_drain);
+ if (!skip_pcp_drain)
+ drain_all_pages(NULL);
drained = true;
goto retry;
}
+out:
+ psi_memstall_leave(&pflags);
return page;
}
@@ -4093,12 +4605,12 @@
struct zoneref *z;
struct zone *zone;
pg_data_t *last_pgdat = NULL;
- enum zone_type high_zoneidx = ac->high_zoneidx;
+ enum zone_type highest_zoneidx = ac->highest_zoneidx;
- for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, high_zoneidx,
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx,
ac->nodemask) {
if (last_pgdat != zone->zone_pgdat)
- wakeup_kswapd(zone, gfp_mask, order, high_zoneidx);
+ wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx);
last_pgdat = zone->zone_pgdat;
}
}
@@ -4108,8 +4620,13 @@
{
unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
- /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
+ /*
+ * __GFP_HIGH is assumed to be the same as ALLOC_HIGH
+ * and __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
+ * to save two branches.
+ */
BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
+ BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD);
/*
* The caller may dip into page reserves a bit more if the caller
@@ -4117,7 +4634,8 @@
* policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
* set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH).
*/
- alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
+ alloc_flags |= (__force int)
+ (gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM));
if (gfp_mask & __GFP_ATOMIC) {
/*
@@ -4134,10 +4652,8 @@
} else if (unlikely(rt_task(current)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
-#ifdef CONFIG_CMA
- if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
- alloc_flags |= ALLOC_CMA;
-#endif
+ alloc_flags = current_alloc_flags(gfp_mask, alloc_flags);
+
return alloc_flags;
}
@@ -4200,6 +4716,7 @@
{
struct zone *zone;
struct zoneref *z;
+ bool ret = false;
/*
* Costly allocations might have made a progress but this doesn't mean
@@ -4226,8 +4743,8 @@
* request even if all reclaimable pages are considered then we are
* screwed and have to go OOM.
*/
- for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
- ac->nodemask) {
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
+ ac->highest_zoneidx, ac->nodemask) {
unsigned long available;
unsigned long reclaimable;
unsigned long min_wmark = min_wmark_pages(zone);
@@ -4241,7 +4758,7 @@
* reclaimable pages?
*/
wmark = __zone_watermark_ok(zone, order, min_wmark,
- ac_classzone_idx(ac), alloc_flags, available);
+ ac->highest_zoneidx, alloc_flags, available);
trace_reclaim_retry_zone(z, order, reclaimable,
available, min_wmark, *no_progress_loops, wmark);
if (wmark) {
@@ -4263,25 +4780,24 @@
}
}
- /*
- * Memory allocation/reclaim might be called from a WQ
- * context and the current implementation of the WQ
- * concurrency control doesn't recognize that
- * a particular WQ is congested if the worker thread is
- * looping without ever sleeping. Therefore we have to
- * do a short sleep here rather than calling
- * cond_resched().
- */
- if (current->flags & PF_WQ_WORKER)
- schedule_timeout_uninterruptible(1);
- else
- cond_resched();
-
- return true;
+ ret = true;
+ goto out;
}
}
- return false;
+out:
+ /*
+ * Memory allocation/reclaim might be called from a WQ context and the
+ * current implementation of the WQ concurrency control doesn't
+ * recognize that a particular WQ is congested if the worker thread is
+ * looping without ever sleeping. Therefore we have to do a short sleep
+ * here rather than calling cond_resched().
+ */
+ if (current->flags & PF_WQ_WORKER)
+ schedule_timeout_uninterruptible(1);
+ else
+ cond_resched();
+ return ret;
}
static inline bool
@@ -4331,8 +4847,12 @@
int compaction_retries;
int no_progress_loops;
unsigned int cpuset_mems_cookie;
+ unsigned int zonelist_iter_cookie;
int reserve_flags;
+ unsigned long vh_record;
+ bool should_alloc_retry = false;
+ trace_android_vh_alloc_pages_slowpath_begin(gfp_mask, order, &vh_record);
/*
* We also sanity check to catch abuse of atomic reserves being used by
* callers that are not in atomic context.
@@ -4341,11 +4861,12 @@
(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
gfp_mask &= ~__GFP_ATOMIC;
-retry_cpuset:
+restart:
compaction_retries = 0;
no_progress_loops = 0;
compact_priority = DEF_COMPACT_PRIORITY;
cpuset_mems_cookie = read_mems_allowed_begin();
+ zonelist_iter_cookie = zonelist_iter_begin();
/*
* The fast path uses conservative alloc_flags to succeed only until
@@ -4361,11 +4882,11 @@
* could end up iterating over non-eligible zones endlessly.
*/
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
- ac->high_zoneidx, ac->nodemask);
+ ac->highest_zoneidx, ac->nodemask);
if (!ac->preferred_zoneref->zone)
goto nopage;
- if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+ if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac);
/*
@@ -4398,18 +4919,28 @@
/*
* Checks for costly allocations with __GFP_NORETRY, which
- * includes THP page fault allocations
+ * includes some THP page fault allocations
*/
if (costly_order && (gfp_mask & __GFP_NORETRY)) {
/*
- * If compaction is deferred for high-order allocations,
- * it is because sync compaction recently failed. If
- * this is the case and the caller requested a THP
- * allocation, we do not want to heavily disrupt the
- * system, so we fail the allocation instead of entering
- * direct reclaim.
+ * If allocating entire pageblock(s) and compaction
+ * failed because all zones are below low watermarks
+ * or is prohibited because it recently failed at this
+ * order, fail immediately unless the allocator has
+ * requested compaction and reclaim retry.
+ *
+ * Reclaim is
+ * - potentially very expensive because zones are far
+ * below their low watermarks or this is part of very
+ * bursty high order allocations,
+ * - not guaranteed to help because isolate_freepages()
+ * may not iterate over freed pages as part of its
+ * linear scan, and
+ * - unlikely to make entire pageblocks free on its
+ * own.
*/
- if (compact_result == COMPACT_DEFERRED)
+ if (compact_result == COMPACT_SKIPPED ||
+ compact_result == COMPACT_DEFERRED)
goto nopage;
/*
@@ -4423,12 +4954,12 @@
retry:
/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
- if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+ if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac);
reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
if (reserve_flags)
- alloc_flags = reserve_flags;
+ alloc_flags = current_alloc_flags(gfp_mask, reserve_flags);
/*
* Reset the nodemask and zonelist iterators if memory policies can be
@@ -4438,7 +4969,7 @@
if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
ac->nodemask = NULL;
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
- ac->high_zoneidx, ac->nodemask);
+ ac->highest_zoneidx, ac->nodemask);
}
/* Attempt with potentially adjusted zonelist and alloc_flags */
@@ -4453,6 +4984,18 @@
/* Avoid recursion of direct reclaim */
if (current->flags & PF_MEMALLOC)
goto nopage;
+
+ trace_android_vh_alloc_pages_reclaim_bypass(gfp_mask, order,
+ alloc_flags, ac->migratetype, &page);
+
+ if (page)
+ goto got_pg;
+
+ trace_android_vh_should_alloc_pages_retry(gfp_mask, order,
+ &alloc_flags, ac->migratetype, ac->preferred_zoneref->zone,
+ &page, &should_alloc_retry);
+ if (should_alloc_retry)
+ goto retry;
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
@@ -4494,9 +5037,13 @@
goto retry;
- /* Deal with possible cpuset update races before we start OOM killing */
- if (check_retry_cpuset(cpuset_mems_cookie, ac))
- goto retry_cpuset;
+ /*
+ * Deal with possible cpuset update races or zonelist updates to avoid
+ * a unnecessary OOM kill.
+ */
+ if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
+ check_retry_zonelist(zonelist_iter_cookie))
+ goto restart;
/* Reclaim has failed us, start killing things */
page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
@@ -4505,7 +5052,7 @@
/* Avoid allocations with no watermarks from looping endlessly */
if (tsk_is_oom_victim(current) &&
- (alloc_flags == ALLOC_OOM ||
+ (alloc_flags & ALLOC_OOM ||
(gfp_mask & __GFP_NOMEMALLOC)))
goto nopage;
@@ -4516,9 +5063,13 @@
}
nopage:
- /* Deal with possible cpuset update races before we fail */
- if (check_retry_cpuset(cpuset_mems_cookie, ac))
- goto retry_cpuset;
+ /*
+ * Deal with possible cpuset update races or zonelist updates to avoid
+ * a unnecessary OOM kill.
+ */
+ if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
+ check_retry_zonelist(zonelist_iter_cookie))
+ goto restart;
/*
* Make sure that __GFP_NOFAIL request doesn't leak out and make sure
@@ -4561,9 +5112,15 @@
goto retry;
}
fail:
+ trace_android_vh_alloc_pages_failure_bypass(gfp_mask, order,
+ alloc_flags, ac->migratetype, &page);
+ if (page)
+ goto got_pg;
+
warn_alloc(gfp_mask, ac->nodemask,
"page allocation failure: order:%u", order);
got_pg:
+ trace_android_vh_alloc_pages_slowpath_end(gfp_mask, order, vh_record);
return page;
}
@@ -4572,14 +5129,18 @@
struct alloc_context *ac, gfp_t *alloc_mask,
unsigned int *alloc_flags)
{
- ac->high_zoneidx = gfp_zone(gfp_mask);
+ ac->highest_zoneidx = gfp_zone(gfp_mask);
ac->zonelist = node_zonelist(preferred_nid, gfp_mask);
ac->nodemask = nodemask;
- ac->migratetype = gfpflags_to_migratetype(gfp_mask);
+ ac->migratetype = gfp_migratetype(gfp_mask);
if (cpusets_enabled()) {
*alloc_mask |= __GFP_HARDWALL;
- if (!ac->nodemask)
+ /*
+ * When we are in the interrupt context, it is irrelevant
+ * to the current task context. It means that any node ok.
+ */
+ if (!in_interrupt() && !ac->nodemask)
ac->nodemask = &cpuset_current_mems_allowed;
else
*alloc_flags |= ALLOC_CPUSET;
@@ -4593,15 +5154,8 @@
if (should_fail_alloc_page(gfp_mask, order))
return false;
- if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
- *alloc_flags |= ALLOC_CMA;
+ *alloc_flags = current_alloc_flags(gfp_mask, *alloc_flags);
- return true;
-}
-
-/* Determine whether to spread dirty pages and what the first usable zone */
-static inline void finalise_ac(gfp_t gfp_mask, struct alloc_context *ac)
-{
/* Dirty zone balancing only done in the fast path */
ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE);
@@ -4611,7 +5165,9 @@
* may get reset for allocations that ignore memory policies.
*/
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
- ac->high_zoneidx, ac->nodemask);
+ ac->highest_zoneidx, ac->nodemask);
+
+ return true;
}
/*
@@ -4640,7 +5196,11 @@
if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags))
return NULL;
- finalise_ac(gfp_mask, &ac);
+ /*
+ * Forbid the first pass from falling back to types that fragment
+ * memory until all local zones are considered.
+ */
+ alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp_mask);
/* First allocation attempt */
page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
@@ -4660,14 +5220,13 @@
* Restore the original nodemask if it was potentially replaced with
* &cpuset_current_mems_allowed to optimize the fast-path attempt.
*/
- if (unlikely(ac.nodemask != nodemask))
- ac.nodemask = nodemask;
+ ac.nodemask = nodemask;
page = __alloc_pages_slowpath(alloc_mask, order, &ac);
out:
if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
- unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) {
+ unlikely(__memcg_kmem_charge_page(page, gfp_mask, order) != 0)) {
__free_pages(page, order);
page = NULL;
}
@@ -4705,13 +5264,20 @@
if (order == 0) /* Via pcp? */
free_unref_page(page);
else
- __free_pages_ok(page, order);
+ __free_pages_ok(page, order, FPI_NONE);
}
void __free_pages(struct page *page, unsigned int order)
{
+ /* get PageHead before we drop reference */
+ int head = PageHead(page);
+
+ trace_android_vh_free_pages(page, order);
if (put_page_testzero(page))
free_the_page(page, order);
+ else if (!head)
+ while (order-- > 0)
+ free_the_page(page + (1 << order), order);
}
EXPORT_SYMBOL(__free_pages);
@@ -4816,6 +5382,18 @@
/* reset page count bias and offset to start of new frag */
nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
offset = size - fragsz;
+ if (unlikely(offset < 0)) {
+ /*
+ * The caller is trying to allocate a fragment
+ * with fragsz > PAGE_SIZE but the cache isn't big
+ * enough to satisfy the request, this may
+ * happen in low memory conditions.
+ * We don't release the cache page because
+ * it could make memory pressure worse
+ * so we simply return NULL here.
+ */
+ return NULL;
+ }
}
nc->pagecnt_bias--;
@@ -4856,7 +5434,7 @@
/**
* alloc_pages_exact - allocate an exact number physically-contiguous pages.
* @size: the number of bytes to allocate
- * @gfp_mask: GFP flags for the allocation
+ * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP
*
* This function is similar to alloc_pages(), except that it allocates the
* minimum number of pages to satisfy the request. alloc_pages() can only
@@ -4865,11 +5443,16 @@
* This function is also limited by MAX_ORDER.
*
* Memory allocated by this function must be released by free_pages_exact().
+ *
+ * Return: pointer to the allocated area or %NULL in case of error.
*/
void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
{
unsigned int order = get_order(size);
unsigned long addr;
+
+ if (WARN_ON_ONCE(gfp_mask & __GFP_COMP))
+ gfp_mask &= ~__GFP_COMP;
addr = __get_free_pages(gfp_mask, order);
return make_alloc_exact(addr, order, size);
@@ -4881,15 +5464,22 @@
* pages on a node.
* @nid: the preferred node ID where memory should be allocated
* @size: the number of bytes to allocate
- * @gfp_mask: GFP flags for the allocation
+ * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP
*
* Like alloc_pages_exact(), but try to allocate on node nid first before falling
* back.
+ *
+ * Return: pointer to the allocated area or %NULL in case of error.
*/
void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
{
unsigned int order = get_order(size);
- struct page *p = alloc_pages_node(nid, gfp_mask, order);
+ struct page *p;
+
+ if (WARN_ON_ONCE(gfp_mask & __GFP_COMP))
+ gfp_mask &= ~__GFP_COMP;
+
+ p = alloc_pages_node(nid, gfp_mask, order);
if (!p)
return NULL;
return make_alloc_exact((unsigned long)page_address(p), order, size);
@@ -4918,11 +5508,13 @@
* nr_free_zone_pages - count number of pages beyond high watermark
* @offset: The zone index of the highest zone
*
- * nr_free_zone_pages() counts the number of counts pages which are beyond the
+ * nr_free_zone_pages() counts the number of pages which are beyond the
* high watermark within all zones at or below a given zone index. For each
* zone, the number of pages is calculated as:
*
* nr_free_zone_pages = managed_pages - high_pages
+ *
+ * Return: number of pages beyond high watermark.
*/
static unsigned long nr_free_zone_pages(int offset)
{
@@ -4935,7 +5527,7 @@
struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
for_each_zone_zonelist(zone, z, zonelist, offset) {
- unsigned long size = zone->managed_pages;
+ unsigned long size = zone_managed_pages(zone);
unsigned long high = high_wmark_pages(zone);
if (size > high)
sum += size - high;
@@ -4949,23 +5541,15 @@
*
* nr_free_buffer_pages() counts the number of pages which are beyond the high
* watermark within ZONE_DMA and ZONE_NORMAL.
+ *
+ * Return: number of pages beyond high watermark within ZONE_DMA and
+ * ZONE_NORMAL.
*/
unsigned long nr_free_buffer_pages(void)
{
return nr_free_zone_pages(gfp_zone(GFP_USER));
}
EXPORT_SYMBOL_GPL(nr_free_buffer_pages);
-
-/**
- * nr_free_pagecache_pages - count number of pages beyond high watermark
- *
- * nr_free_pagecache_pages() counts the number of pages which are beyond the
- * high watermark within all zones.
- */
-unsigned long nr_free_pagecache_pages(void)
-{
- return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
-}
static inline void show_node(struct zone *zone)
{
@@ -4987,7 +5571,7 @@
pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
for_each_zone(zone)
- wmark_low += zone->watermark[WMARK_LOW];
+ wmark_low += low_wmark_pages(zone);
/*
* Estimate the amount of memory available for userspace allocations,
@@ -5009,8 +5593,8 @@
* items that are in use, and cannot be freed. Cap this estimate at the
* low watermark.
*/
- reclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE) +
- global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
+ reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) +
+ global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
available += reclaimable - min(reclaimable / 2, wmark_low);
if (available < 0)
@@ -5021,11 +5605,11 @@
void si_meminfo(struct sysinfo *val)
{
- val->totalram = totalram_pages;
+ val->totalram = totalram_pages();
val->sharedram = global_node_page_state(NR_SHMEM);
val->freeram = global_zone_page_state(NR_FREE_PAGES);
val->bufferram = nr_blockdev_pages();
- val->totalhigh = totalhigh_pages;
+ val->totalhigh = totalhigh_pages();
val->freehigh = nr_free_highpages();
val->mem_unit = PAGE_SIZE;
}
@@ -5042,7 +5626,7 @@
pg_data_t *pgdat = NODE_DATA(nid);
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
- managed_pages += pgdat->node_zones[zone_type].managed_pages;
+ managed_pages += zone_managed_pages(&pgdat->node_zones[zone_type]);
val->totalram = managed_pages;
val->sharedram = node_page_state(pgdat, NR_SHMEM);
val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES);
@@ -5051,7 +5635,7 @@
struct zone *zone = &pgdat->node_zones[zone_type];
if (is_highmem(zone)) {
- managed_highpages += zone->managed_pages;
+ managed_highpages += zone_managed_pages(zone);
free_highpages += zone_page_state(zone, NR_FREE_PAGES);
}
}
@@ -5140,7 +5724,7 @@
printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
" active_file:%lu inactive_file:%lu isolated_file:%lu\n"
- " unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n"
+ " unevictable:%lu dirty:%lu writeback:%lu\n"
" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
" free:%lu free_pcp:%lu free_cma:%lu\n",
@@ -5153,9 +5737,8 @@
global_node_page_state(NR_UNEVICTABLE),
global_node_page_state(NR_FILE_DIRTY),
global_node_page_state(NR_WRITEBACK),
- global_node_page_state(NR_UNSTABLE_NFS),
- global_node_page_state(NR_SLAB_RECLAIMABLE),
- global_node_page_state(NR_SLAB_UNRECLAIMABLE),
+ global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B),
+ global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B),
global_node_page_state(NR_FILE_MAPPED),
global_node_page_state(NR_SHMEM),
global_zone_page_state(NR_PAGETABLE),
@@ -5164,6 +5747,7 @@
free_pcp,
global_zone_page_state(NR_FREE_CMA_PAGES));
+ trace_android_vh_show_mapcount_pages(NULL);
for_each_online_pgdat(pgdat) {
if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
continue;
@@ -5186,7 +5770,10 @@
" anon_thp: %lukB"
#endif
" writeback_tmp:%lukB"
- " unstable:%lukB"
+ " kernel_stack:%lukB"
+#ifdef CONFIG_SHADOW_CALL_STACK
+ " shadow_call_stack:%lukB"
+#endif
" all_unreclaimable? %s"
"\n",
pgdat->node_id,
@@ -5208,7 +5795,10 @@
K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
#endif
K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
- K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
+ node_page_state(pgdat, NR_KERNEL_STACK_KB),
+#ifdef CONFIG_SHADOW_CALL_STACK
+ node_page_state(pgdat, NR_KERNEL_SCS_KB),
+#endif
pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
"yes" : "no");
}
@@ -5230,6 +5820,7 @@
" min:%lukB"
" low:%lukB"
" high:%lukB"
+ " reserved_highatomic:%luKB"
" active_anon:%lukB"
" inactive_anon:%lukB"
" active_file:%lukB"
@@ -5239,10 +5830,6 @@
" present:%lukB"
" managed:%lukB"
" mlocked:%lukB"
- " kernel_stack:%lukB"
-#ifdef CONFIG_SHADOW_CALL_STACK
- " shadow_call_stack:%lukB"
-#endif
" pagetables:%lukB"
" bounce:%lukB"
" free_pcp:%lukB"
@@ -5254,6 +5841,7 @@
K(min_wmark_pages(zone)),
K(low_wmark_pages(zone)),
K(high_wmark_pages(zone)),
+ K(zone->nr_reserved_highatomic),
K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)),
K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)),
K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)),
@@ -5261,12 +5849,8 @@
K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)),
K(zone_page_state(zone, NR_ZONE_WRITE_PENDING)),
K(zone->present_pages),
- K(zone->managed_pages),
+ K(zone_managed_pages(zone)),
K(zone_page_state(zone, NR_MLOCK)),
- zone_page_state(zone, NR_KERNEL_STACK_KB),
-#ifdef CONFIG_SHADOW_CALL_STACK
- zone_page_state(zone, NR_KERNEL_SCS_BYTES) / 1024,
-#endif
K(zone_page_state(zone, NR_PAGETABLE)),
K(zone_page_state(zone, NR_BOUNCE)),
K(free_pcp),
@@ -5298,7 +5882,7 @@
types[order] = 0;
for (type = 0; type < MIGRATE_TYPES; type++) {
- if (!list_empty(&area->free_list[type]))
+ if (!free_area_empty(area, type))
types[order] |= 1 << type;
}
}
@@ -5339,7 +5923,7 @@
do {
zone_type--;
zone = pgdat->node_zones + zone_type;
- if (managed_zone(zone)) {
+ if (populated_zone(zone)) {
zoneref_set_zone(zone, &zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
@@ -5365,36 +5949,17 @@
return 0;
}
-static __init int setup_numa_zonelist_order(char *s)
-{
- if (!s)
- return 0;
-
- return __parse_numa_zonelist_order(s);
-}
-early_param("numa_zonelist_order", setup_numa_zonelist_order);
-
char numa_zonelist_order[] = "Node";
/*
* sysctl handler for numa_zonelist_order
*/
int numa_zonelist_order_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length,
- loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
- char *str;
- int ret;
-
- if (!write)
- return proc_dostring(table, write, buffer, length, ppos);
- str = memdup_user_nul(buffer, 16);
- if (IS_ERR(str))
- return PTR_ERR(str);
-
- ret = __parse_numa_zonelist_order(str);
- kfree(str);
- return ret;
+ if (write)
+ return __parse_numa_zonelist_order(buffer);
+ return proc_dostring(table, write, buffer, length, ppos);
}
@@ -5413,14 +5978,14 @@
* from each node to each node in the system), and should also prefer nodes
* with no CPUs, since presumably they'll have very little allocation pressure
* on them otherwise.
- * It returns -1 if no node is found.
+ *
+ * Return: node id of the found node or %NUMA_NO_NODE if no node is found.
*/
static int find_next_best_node(int node, nodemask_t *used_node_mask)
{
int n, val;
int min_val = INT_MAX;
int best_node = NUMA_NO_NODE;
- const struct cpumask *tmp = cpumask_of_node(0);
/* Use the local node if we haven't already */
if (!node_isset(node, *used_node_mask)) {
@@ -5441,8 +6006,7 @@
val += (n < node);
/* Give preference to headless and unused nodes */
- tmp = cpumask_of_node(n);
- if (!cpumask_empty(tmp))
+ if (!cpumask_empty(cpumask_of_node(n)))
val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */
@@ -5513,14 +6077,13 @@
{
static int node_order[MAX_NUMNODES];
int node, load, nr_nodes = 0;
- nodemask_t used_mask;
+ nodemask_t used_mask = NODE_MASK_NONE;
int local_node, prev_node;
/* NUMA-aware ordering of nodes */
local_node = pgdat->node_id;
load = nr_online_nodes;
prev_node = local_node;
- nodes_clear(used_mask);
memset(node_order, 0, sizeof(node_order));
while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
@@ -5627,9 +6190,22 @@
int nid;
int __maybe_unused cpu;
pg_data_t *self = data;
- static DEFINE_SPINLOCK(lock);
+ unsigned long flags;
- spin_lock(&lock);
+ /*
+ * Explicitly disable this CPU's interrupts before taking seqlock
+ * to prevent any IRQ handler from calling into the page allocator
+ * (e.g. GFP_ATOMIC) that could hit zonelist_iter_begin and livelock.
+ */
+ local_irq_save(flags);
+ /*
+ * Explicitly disable this CPU's synchronous printk() before taking
+ * seqlock to prevent any printk() from trying to hold port->lock, for
+ * tty_insert_flip_string_and_push_buffer() on other CPU might be
+ * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held.
+ */
+ printk_deferred_enter();
+ write_seqlock(&zonelist_update_seq);
#ifdef CONFIG_NUMA
memset(node_load, 0, sizeof(node_load));
@@ -5662,7 +6238,9 @@
#endif
}
- spin_unlock(&lock);
+ write_sequnlock(&zonelist_update_seq);
+ printk_deferred_exit();
+ local_irq_restore(flags);
}
static noinline void __init
@@ -5700,13 +6278,16 @@
*/
void __ref build_all_zonelists(pg_data_t *pgdat)
{
+ unsigned long vm_total_pages;
+
if (system_state == SYSTEM_BOOTING) {
build_all_zonelists_init();
} else {
__build_all_zonelists(pgdat);
/* cpuset refresh routine should be here */
}
- vm_total_pages = nr_free_pagecache_pages();
+ /* Get the number of free pages beyond high watermark in all zones. */
+ vm_total_pages = nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
/*
* Disable grouping by mobility if the number of pages in the
* system is too low to allow the mechanism to work. It would be
@@ -5719,7 +6300,7 @@
else
page_group_by_mobility_disabled = 0;
- pr_info("Built %i zonelists, mobility grouping %s. Total pages: %ld\n",
+ pr_info("Built %u zonelists, mobility grouping %s. Total pages: %ld\n",
nr_online_nodes,
page_group_by_mobility_disabled ? "off" : "on",
vm_total_pages);
@@ -5728,81 +6309,148 @@
#endif
}
+/* If zone is ZONE_MOVABLE but memory is mirrored, it is an overlapped init */
+static bool __meminit
+overlap_memmap_init(unsigned long zone, unsigned long *pfn)
+{
+ static struct memblock_region *r;
+
+ if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
+ if (!r || *pfn >= memblock_region_memory_end_pfn(r)) {
+ for_each_mem_region(r) {
+ if (*pfn < memblock_region_memory_end_pfn(r))
+ break;
+ }
+ }
+ if (*pfn >= memblock_region_memory_base_pfn(r) &&
+ memblock_is_mirror(r)) {
+ *pfn = memblock_region_memory_end_pfn(r);
+ return true;
+ }
+ }
+ return false;
+}
+
/*
* Initially all pages are reserved - free ones are freed
- * up by free_all_bootmem() once the early boot process is
+ * up by memblock_free_all() once the early boot process is
* done. Non-atomic initialization, single-pass.
+ *
+ * All aligned pageblocks are initialized to the specified migratetype
+ * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
+ * zone stats (e.g., nr_isolate_pageblock) are touched.
*/
void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
- unsigned long start_pfn, enum meminit_context context,
- struct vmem_altmap *altmap)
+ unsigned long start_pfn, unsigned long zone_end_pfn,
+ enum meminit_context context,
+ struct vmem_altmap *altmap, int migratetype)
{
- unsigned long end_pfn = start_pfn + size;
- pg_data_t *pgdat = NODE_DATA(nid);
- unsigned long pfn;
- unsigned long nr_initialised = 0;
+ unsigned long pfn, end_pfn = start_pfn + size;
struct page *page;
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
- struct memblock_region *r = NULL, *tmp;
-#endif
if (highest_memmap_pfn < end_pfn - 1)
highest_memmap_pfn = end_pfn - 1;
+
+#ifdef CONFIG_ZONE_DEVICE
+ /*
+ * Honor reservation requested by the driver for this ZONE_DEVICE
+ * memory. We limit the total number of pages to initialize to just
+ * those that might contain the memory mapping. We will defer the
+ * ZONE_DEVICE page initialization until after we have released
+ * the hotplug lock.
+ */
+ if (zone == ZONE_DEVICE) {
+ if (!altmap)
+ return;
+
+ if (start_pfn == altmap->base_pfn)
+ start_pfn += altmap->reserve;
+ end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
+ }
+#endif
#ifdef CONFIG_ROCKCHIP_THUNDER_BOOT
/* Zero all page struct in advance */
memset(pfn_to_page(start_pfn), 0, sizeof(struct page) * size);
#endif
- /*
- * Honor reservation requested by the driver for this ZONE_DEVICE
- * memory
- */
- if (altmap && start_pfn == altmap->base_pfn)
- start_pfn += altmap->reserve;
-
- for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ for (pfn = start_pfn; pfn < end_pfn; ) {
/*
* There can be holes in boot-time mem_map[]s handed to this
* function. They do not exist on hotplugged memory.
*/
- if (context != MEMINIT_EARLY)
- goto not_early;
-
- if (!early_pfn_valid(pfn))
- continue;
- if (!early_pfn_in_nid(pfn, nid))
- continue;
- if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
- break;
-
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
- /*
- * Check given memblock attribute by firmware which can affect
- * kernel memory layout. If zone==ZONE_MOVABLE but memory is
- * mirrored, it's an overlapped memmap init. skip it.
- */
- if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
- if (!r || pfn >= memblock_region_memory_end_pfn(r)) {
- for_each_memblock(memory, tmp)
- if (pfn < memblock_region_memory_end_pfn(tmp))
- break;
- r = tmp;
- }
- if (pfn >= memblock_region_memory_base_pfn(r) &&
- memblock_is_mirror(r)) {
- /* already initialized as NORMAL */
- pfn = memblock_region_memory_end_pfn(r);
+ if (context == MEMINIT_EARLY) {
+ if (overlap_memmap_init(zone, &pfn))
continue;
- }
+ if (defer_init(nid, pfn, zone_end_pfn))
+ break;
}
-#endif
-not_early:
page = pfn_to_page(pfn);
__init_single_page(page, pfn, zone, nid, false);
if (context == MEMINIT_HOTPLUG)
- SetPageReserved(page);
+ __SetPageReserved(page);
+
+ /*
+ * Usually, we want to mark the pageblock MIGRATE_MOVABLE,
+ * such that unmovable allocations won't be scattered all
+ * over the place during system boot.
+ */
+ if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
+ set_pageblock_migratetype(page, migratetype);
+ cond_resched();
+ }
+ pfn++;
+ }
+}
+
+#ifdef CONFIG_ZONE_DEVICE
+void __ref memmap_init_zone_device(struct zone *zone,
+ unsigned long start_pfn,
+ unsigned long nr_pages,
+ struct dev_pagemap *pgmap)
+{
+ unsigned long pfn, end_pfn = start_pfn + nr_pages;
+ struct pglist_data *pgdat = zone->zone_pgdat;
+ struct vmem_altmap *altmap = pgmap_altmap(pgmap);
+ unsigned long zone_idx = zone_idx(zone);
+ unsigned long start = jiffies;
+ int nid = pgdat->node_id;
+
+ if (WARN_ON_ONCE(!pgmap || zone_idx(zone) != ZONE_DEVICE))
+ return;
+
+ /*
+ * The call to memmap_init should have already taken care
+ * of the pages reserved for the memmap, so we can just jump to
+ * the end of that region and start processing the device pages.
+ */
+ if (altmap) {
+ start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
+ nr_pages = end_pfn - start_pfn;
+ }
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ struct page *page = pfn_to_page(pfn);
+
+ __init_single_page(page, pfn, zone_idx, nid, true);
+
+ /*
+ * Mark page reserved as it will need to wait for onlining
+ * phase for it to be fully associated with a zone.
+ *
+ * We can use the non-atomic __set_bit operation for setting
+ * the flag as we are still initializing the pages.
+ */
+ __SetPageReserved(page);
+
+ /*
+ * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer
+ * and zone_device_data. It is a bug if a ZONE_DEVICE page is
+ * ever freed or placed on a driver-private list.
+ */
+ page->pgmap = pgmap;
+ page->zone_device_data = NULL;
/*
* Mark the block movable so that blocks are reserved for
@@ -5811,21 +6459,20 @@
* the address space during boot when many long-lived
* kernel allocations are made.
*
- * bitmap is created for zone's valid pfn range. but memmap
- * can be created for invalid pages (for alignment)
- * check here not to call set_pageblock_migratetype() against
- * pfn out of zone.
- *
* Please note that MEMINIT_HOTPLUG path doesn't clear memmap
- * because this is done early in sparse_add_one_section
+ * because this is done early in section_activate()
*/
- if (!(pfn & (pageblock_nr_pages - 1))) {
+ if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
cond_resched();
}
}
+
+ pr_info("%s initialised %lu pages in %ums\n", __func__,
+ nr_pages, jiffies_to_msecs(jiffies - start));
}
+#endif
static void __meminit zone_init_free_lists(struct zone *zone)
{
unsigned int order, t;
@@ -5835,11 +6482,118 @@
}
}
-#ifndef __HAVE_ARCH_MEMMAP_INIT
-#define memmap_init(size, nid, zone, start_pfn) \
- memmap_init_zone((size), (nid), (zone), (start_pfn), \
- MEMINIT_EARLY, NULL)
+/*
+ * Only struct pages that correspond to ranges defined by memblock.memory
+ * are zeroed and initialized by going through __init_single_page() during
+ * memmap_init_zone_range().
+ *
+ * But, there could be struct pages that correspond to holes in
+ * memblock.memory. This can happen because of the following reasons:
+ * - physical memory bank size is not necessarily the exact multiple of the
+ * arbitrary section size
+ * - early reserved memory may not be listed in memblock.memory
+ * - memory layouts defined with memmap= kernel parameter may not align
+ * nicely with memmap sections
+ *
+ * Explicitly initialize those struct pages so that:
+ * - PG_Reserved is set
+ * - zone and node links point to zone and node that span the page if the
+ * hole is in the middle of a zone
+ * - zone and node links point to adjacent zone/node if the hole falls on
+ * the zone boundary; the pages in such holes will be prepended to the
+ * zone/node above the hole except for the trailing pages in the last
+ * section that will be appended to the zone/node below.
+ */
+static void __init init_unavailable_range(unsigned long spfn,
+ unsigned long epfn,
+ int zone, int node)
+{
+ unsigned long pfn;
+ u64 pgcnt = 0;
+
+ for (pfn = spfn; pfn < epfn; pfn++) {
+ if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
+ pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
+ + pageblock_nr_pages - 1;
+ continue;
+ }
+ __init_single_page(pfn_to_page(pfn), pfn, zone, node, true);
+ __SetPageReserved(pfn_to_page(pfn));
+ pgcnt++;
+ }
+
+ if (pgcnt)
+ pr_info("On node %d, zone %s: %lld pages in unavailable ranges",
+ node, zone_names[zone], pgcnt);
+}
+
+static void __init memmap_init_zone_range(struct zone *zone,
+ unsigned long start_pfn,
+ unsigned long end_pfn,
+ unsigned long *hole_pfn)
+{
+ unsigned long zone_start_pfn = zone->zone_start_pfn;
+ unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
+ int nid = zone_to_nid(zone), zone_id = zone_idx(zone);
+
+ start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn);
+ end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn);
+
+ if (start_pfn >= end_pfn)
+ return;
+
+ memmap_init_zone(end_pfn - start_pfn, nid, zone_id, start_pfn,
+ zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
+
+ if (*hole_pfn < start_pfn)
+ init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid);
+
+ *hole_pfn = end_pfn;
+}
+
+void __init __weak memmap_init(void)
+{
+ unsigned long start_pfn, end_pfn;
+ unsigned long hole_pfn = 0;
+ int i, j, zone_id, nid;
+
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+ struct pglist_data *node = NODE_DATA(nid);
+
+ for (j = 0; j < MAX_NR_ZONES; j++) {
+ struct zone *zone = node->node_zones + j;
+
+ if (!populated_zone(zone))
+ continue;
+
+ memmap_init_zone_range(zone, start_pfn, end_pfn,
+ &hole_pfn);
+ zone_id = j;
+ }
+ }
+
+#ifdef CONFIG_SPARSEMEM
+ /*
+ * Initialize the memory map for hole in the range [memory_end,
+ * section_end].
+ * Append the pages in this hole to the highest zone in the last
+ * node.
+ * The call to init_unavailable_range() is outside the ifdef to
+ * silence the compiler warining about zone_id set but not used;
+ * for FLATMEM it is a nop anyway
+ */
+ end_pfn = round_up(end_pfn, PAGES_PER_SECTION);
+ if (hole_pfn < end_pfn)
#endif
+ init_unavailable_range(hole_pfn, end_pfn, zone_id, nid);
+}
+
+/* A stub for backwards compatibility with custom implementatin on IA-64 */
+void __meminit __weak arch_memmap_init(unsigned long size, int nid,
+ unsigned long zone,
+ unsigned long range_start_pfn)
+{
+}
static int zone_batchsize(struct zone *zone)
{
@@ -5850,7 +6604,7 @@
* The per-cpu-pages pools are set to around 1000th of the
* size of the zone.
*/
- batch = zone->managed_pages / 1024;
+ batch = zone_managed_pages(zone) / 1024;
/* But no more than a meg. */
if (batch * PAGE_SIZE > 1024 * 1024)
batch = (1024 * 1024) / PAGE_SIZE;
@@ -5897,7 +6651,7 @@
* locking.
*
* Any new users of pcp->batch and pcp->high should ensure they can cope with
- * those fields changing asynchronously (acording the the above rule).
+ * those fields changing asynchronously (acording to the above rule).
*
* mutex_is_locked(&pcp_batch_high_lock) required when calling this function
* outside of boot time (or some other assurance that no concurrent updaters
@@ -5906,6 +6660,7 @@
static void pageset_update(struct per_cpu_pages *pcp, unsigned long high,
unsigned long batch)
{
+ trace_android_vh_pageset_update(&high, &batch);
/* start with a fail safe value for batch */
pcp->batch = 1;
smp_wmb();
@@ -5931,7 +6686,6 @@
memset(p, 0, sizeof(*p));
pcp = &p->pcp;
- pcp->count = 0;
for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
INIT_LIST_HEAD(&pcp->lists[migratetype]);
}
@@ -5961,7 +6715,7 @@
{
if (percpu_pagelist_fraction)
pageset_set_high(pcp,
- (zone->managed_pages /
+ (zone_managed_pages(zone) /
percpu_pagelist_fraction));
else
pageset_set_batch(pcp, zone_batchsize(zone));
@@ -5991,9 +6745,24 @@
{
struct pglist_data *pgdat;
struct zone *zone;
+ int __maybe_unused cpu;
for_each_populated_zone(zone)
setup_zone_pageset(zone);
+
+#ifdef CONFIG_NUMA
+ /*
+ * Unpopulated zones continue using the boot pagesets.
+ * The numa stats for these pagesets need to be reset.
+ * Otherwise, they will end up skewing the stats of
+ * the nodes these zones are associated with.
+ */
+ for_each_possible_cpu(cpu) {
+ struct per_cpu_pageset *pcp = &per_cpu(boot_pageset, cpu);
+ memset(pcp->vm_numa_stat_diff, 0,
+ sizeof(pcp->vm_numa_stat_diff));
+ }
+#endif
for_each_online_pgdat(pgdat)
pgdat->per_cpu_nodestats =
@@ -6037,73 +6806,6 @@
zone->initialized = 1;
}
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
-
-/*
- * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
- */
-int __meminit __early_pfn_to_nid(unsigned long pfn,
- struct mminit_pfnnid_cache *state)
-{
- unsigned long start_pfn, end_pfn;
- int nid;
-
- if (state->last_start <= pfn && pfn < state->last_end)
- return state->last_nid;
-
- nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
- if (nid != -1) {
- state->last_start = start_pfn;
- state->last_end = end_pfn;
- state->last_nid = nid;
- }
-
- return nid;
-}
-#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
-
-/**
- * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range
- * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
- * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid
- *
- * If an architecture guarantees that all ranges registered contain no holes
- * and may be freed, this this function may be used instead of calling
- * memblock_free_early_nid() manually.
- */
-void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
-{
- unsigned long start_pfn, end_pfn;
- int i, this_nid;
-
- for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) {
- start_pfn = min(start_pfn, max_low_pfn);
- end_pfn = min(end_pfn, max_low_pfn);
-
- if (start_pfn < end_pfn)
- memblock_free_early_nid(PFN_PHYS(start_pfn),
- (end_pfn - start_pfn) << PAGE_SHIFT,
- this_nid);
- }
-}
-
-/**
- * sparse_memory_present_with_active_regions - Call memory_present for each active range
- * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
- *
- * If an architecture guarantees that all ranges registered contain no holes and may
- * be freed, this function may be used instead of calling memory_present() manually.
- */
-void __init sparse_memory_present_with_active_regions(int nid)
-{
- unsigned long start_pfn, end_pfn;
- int i, this_nid;
-
- for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid)
- memory_present(this_nid, start_pfn, end_pfn);
-}
-
/**
* get_pfn_range_for_nid - Return the start and end page frames for a node
* @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
@@ -6115,7 +6817,7 @@
* with no available memory, a warning is printed and the start and end
* PFNs will be 0.
*/
-void __meminit get_pfn_range_for_nid(unsigned int nid,
+void __init get_pfn_range_for_nid(unsigned int nid,
unsigned long *start_pfn, unsigned long *end_pfn)
{
unsigned long this_start_pfn, this_end_pfn;
@@ -6164,7 +6866,7 @@
* highest usable zone for ZONE_MOVABLE. This preserves the assumption that
* zones within a node are in order of monotonic increases memory addresses
*/
-static void __meminit adjust_zone_range_for_zone_movable(int nid,
+static void __init adjust_zone_range_for_zone_movable(int nid,
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
@@ -6195,13 +6897,12 @@
* Return the number of pages a zone spans in a node, including holes
* present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node()
*/
-static unsigned long __meminit zone_spanned_pages_in_node(int nid,
+static unsigned long __init zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
unsigned long *zone_start_pfn,
- unsigned long *zone_end_pfn,
- unsigned long *ignored)
+ unsigned long *zone_end_pfn)
{
unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
@@ -6232,7 +6933,7 @@
* Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
* then all holes in the requested range will be accounted for.
*/
-unsigned long __meminit __absent_pages_in_range(int nid,
+unsigned long __init __absent_pages_in_range(int nid,
unsigned long range_start_pfn,
unsigned long range_end_pfn)
{
@@ -6253,7 +6954,7 @@
* @start_pfn: The start PFN to start searching for holes
* @end_pfn: The end PFN to stop searching for holes
*
- * It returns the number of pages frames in memory holes within a range.
+ * Return: the number of pages frames in memory holes within a range.
*/
unsigned long __init absent_pages_in_range(unsigned long start_pfn,
unsigned long end_pfn)
@@ -6262,11 +6963,10 @@
}
/* Return the number of page frames in holes in a zone on a node */
-static unsigned long __meminit zone_absent_pages_in_node(int nid,
+static unsigned long __init zone_absent_pages_in_node(int nid,
unsigned long zone_type,
unsigned long node_start_pfn,
- unsigned long node_end_pfn,
- unsigned long *ignored)
+ unsigned long node_end_pfn)
{
unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
@@ -6294,7 +6994,7 @@
unsigned long start_pfn, end_pfn;
struct memblock_region *r;
- for_each_memblock(memory, r) {
+ for_each_mem_region(r) {
start_pfn = clamp(memblock_region_memory_base_pfn(r),
zone_start_pfn, zone_end_pfn);
end_pfn = clamp(memblock_region_memory_end_pfn(r),
@@ -6313,45 +7013,9 @@
return nr_absent;
}
-#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
- unsigned long zone_type,
- unsigned long node_start_pfn,
- unsigned long node_end_pfn,
- unsigned long *zone_start_pfn,
- unsigned long *zone_end_pfn,
- unsigned long *zones_size)
-{
- unsigned int zone;
-
- *zone_start_pfn = node_start_pfn;
- for (zone = 0; zone < zone_type; zone++)
- *zone_start_pfn += zones_size[zone];
-
- *zone_end_pfn = *zone_start_pfn + zones_size[zone_type];
-
- return zones_size[zone_type];
-}
-
-static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
- unsigned long zone_type,
+static void __init calculate_node_totalpages(struct pglist_data *pgdat,
unsigned long node_start_pfn,
- unsigned long node_end_pfn,
- unsigned long *zholes_size)
-{
- if (!zholes_size)
- return 0;
-
- return zholes_size[zone_type];
-}
-
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-
-static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
- unsigned long node_start_pfn,
- unsigned long node_end_pfn,
- unsigned long *zones_size,
- unsigned long *zholes_size)
+ unsigned long node_end_pfn)
{
unsigned long realtotalpages = 0, totalpages = 0;
enum zone_type i;
@@ -6359,17 +7023,21 @@
for (i = 0; i < MAX_NR_ZONES; i++) {
struct zone *zone = pgdat->node_zones + i;
unsigned long zone_start_pfn, zone_end_pfn;
+ unsigned long spanned, absent;
unsigned long size, real_size;
- size = zone_spanned_pages_in_node(pgdat->node_id, i,
- node_start_pfn,
- node_end_pfn,
- &zone_start_pfn,
- &zone_end_pfn,
- zones_size);
- real_size = size - zone_absent_pages_in_node(pgdat->node_id, i,
- node_start_pfn, node_end_pfn,
- zholes_size);
+ spanned = zone_spanned_pages_in_node(pgdat->node_id, i,
+ node_start_pfn,
+ node_end_pfn,
+ &zone_start_pfn,
+ &zone_end_pfn);
+ absent = zone_absent_pages_in_node(pgdat->node_id, i,
+ node_start_pfn,
+ node_end_pfn);
+
+ size = spanned;
+ real_size = size - absent;
+
if (size)
zone->zone_start_pfn = zone_start_pfn;
else
@@ -6415,10 +7083,14 @@
{
unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
zone->pageblock_flags = NULL;
- if (usemapsize)
+ if (usemapsize) {
zone->pageblock_flags =
- memblock_virt_alloc_node_nopanic(usemapsize,
- pgdat->node_id);
+ memblock_alloc_node(usemapsize, SMP_CACHE_BYTES,
+ pgdat->node_id);
+ if (!zone->pageblock_flags)
+ panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n",
+ usemapsize, zone->name, pgdat->node_id);
+ }
}
#else
static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
@@ -6485,9 +7157,11 @@
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void pgdat_init_split_queue(struct pglist_data *pgdat)
{
- spin_lock_init(&pgdat->split_queue_lock);
- INIT_LIST_HEAD(&pgdat->split_queue);
- pgdat->split_queue_len = 0;
+ struct deferred_split *ds_queue = &pgdat->deferred_split_queue;
+
+ spin_lock_init(&ds_queue->split_queue_lock);
+ INIT_LIST_HEAD(&ds_queue->split_queue);
+ ds_queue->split_queue_len = 0;
}
#else
static void pgdat_init_split_queue(struct pglist_data *pgdat) {}
@@ -6514,13 +7188,13 @@
pgdat_page_ext_init(pgdat);
spin_lock_init(&pgdat->lru_lock);
- lruvec_init(node_lruvec(pgdat));
+ lruvec_init(&pgdat->__lruvec);
}
static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,
unsigned long remaining_pages)
{
- zone->managed_pages = remaining_pages;
+ atomic_long_set(&zone->managed_pages, remaining_pages);
zone_set_nid(zone, nid);
zone->name = zone_names[idx];
zone->zone_pgdat = NODE_DATA(nid);
@@ -6618,7 +7292,7 @@
set_pageblock_order();
setup_usemap(pgdat, zone, zone_start_pfn, size);
init_currently_empty_zone(zone, zone_start_pfn, size);
- memmap_init(size, nid, j, zone_start_pfn);
+ arch_memmap_init(size, nid, j, zone_start_pfn);
}
}
@@ -6647,7 +7321,11 @@
end = pgdat_end_pfn(pgdat);
end = ALIGN(end, MAX_ORDER_NR_PAGES);
size = (end - start) * sizeof(struct page);
- map = memblock_virt_alloc_node_nopanic(size, pgdat->node_id);
+ map = memblock_alloc_node(size, SMP_CACHE_BYTES,
+ pgdat->node_id);
+ if (!map)
+ panic("Failed to allocate %ld bytes for node %d memory map\n",
+ size, pgdat->node_id);
pgdat->node_mem_map = map + offset;
}
pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
@@ -6659,10 +7337,8 @@
*/
if (pgdat == NODE_DATA(0)) {
mem_map = NODE_DATA(0)->node_mem_map;
-#if defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) || defined(CONFIG_FLATMEM)
if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
mem_map -= offset;
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
}
#endif
}
@@ -6673,42 +7349,31 @@
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static inline void pgdat_set_deferred_range(pg_data_t *pgdat)
{
- /*
- * We start only with one section of pages, more pages are added as
- * needed until the rest of deferred pages are initialized.
- */
- pgdat->static_init_pgcnt = min_t(unsigned long, PAGES_PER_SECTION,
- pgdat->node_spanned_pages);
pgdat->first_deferred_pfn = ULONG_MAX;
}
#else
static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}
#endif
-void __init free_area_init_node(int nid, unsigned long *zones_size,
- unsigned long node_start_pfn,
- unsigned long *zholes_size)
+static void __init free_area_init_node(int nid)
{
pg_data_t *pgdat = NODE_DATA(nid);
unsigned long start_pfn = 0;
unsigned long end_pfn = 0;
/* pg_data_t should be reset to zero when it's allocated */
- WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
+ WARN_ON(pgdat->nr_zones || pgdat->kswapd_highest_zoneidx);
+
+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
pgdat->node_id = nid;
- pgdat->node_start_pfn = node_start_pfn;
+ pgdat->node_start_pfn = start_pfn;
pgdat->per_cpu_nodestats = NULL;
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
- get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+
pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
(u64)start_pfn << PAGE_SHIFT,
end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0);
-#else
- start_pfn = node_start_pfn;
-#endif
- calculate_node_totalpages(pgdat, start_pfn, end_pfn,
- zones_size, zholes_size);
+ calculate_node_totalpages(pgdat, start_pfn, end_pfn);
alloc_node_mem_map(pgdat);
pgdat_set_deferred_range(pgdat);
@@ -6716,80 +7381,10 @@
free_area_init_core(pgdat);
}
-#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
-
-/*
- * Zero all valid struct pages in range [spfn, epfn), return number of struct
- * pages zeroed
- */
-static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
+void __init free_area_init_memoryless_node(int nid)
{
- unsigned long pfn;
- u64 pgcnt = 0;
-
- for (pfn = spfn; pfn < epfn; pfn++) {
- if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
- pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
- + pageblock_nr_pages - 1;
- continue;
- }
- mm_zero_struct_page(pfn_to_page(pfn));
- pgcnt++;
- }
-
- return pgcnt;
+ free_area_init_node(nid);
}
-
-/*
- * Only struct pages that are backed by physical memory are zeroed and
- * initialized by going through __init_single_page(). But, there are some
- * struct pages which are reserved in memblock allocator and their fields
- * may be accessed (for example page_to_pfn() on some configuration accesses
- * flags). We must explicitly zero those struct pages.
- *
- * This function also addresses a similar issue where struct pages are left
- * uninitialized because the physical address range is not covered by
- * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=, or when the highest physical
- * address (max_pfn) does not end on a section boundary.
- */
-void __init zero_resv_unavail(void)
-{
- phys_addr_t start, end;
- u64 i, pgcnt;
- phys_addr_t next = 0;
-
- /*
- * Loop through unavailable ranges not covered by memblock.memory.
- */
- pgcnt = 0;
- for_each_mem_range(i, &memblock.memory, NULL,
- NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) {
- if (next < start)
- pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start));
- next = end;
- }
-
- /*
- * Early sections always have a fully populated memmap for the whole
- * section - see pfn_valid(). If the last section has holes at the
- * end and that section is marked "online", the memmap will be
- * considered initialized. Make sure that memmap has a well defined
- * state.
- */
- pgcnt += zero_pfn_range(PFN_DOWN(next),
- round_up(max_pfn, PAGES_PER_SECTION));
-
- /*
- * Struct pages that do not have backing memory. This could be because
- * firmware is using some of this memory, or for some other reasons.
- */
- if (pgcnt)
- pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt);
-}
-#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */
-
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
#if MAX_NUMNODES > 1
/*
@@ -6820,14 +7415,14 @@
* model has fine enough granularity to avoid incorrect mapping for the
* populated node map.
*
- * Returns the determined alignment in pfn's. 0 if there is no alignment
+ * Return: the determined alignment in pfn's. 0 if there is no alignment
* requirement (single node).
*/
unsigned long __init node_map_pfn_alignment(void)
{
unsigned long accl_mask = 0, last_end = 0;
unsigned long start, end, mask;
- int last_nid = -1;
+ int last_nid = NUMA_NO_NODE;
int i, nid;
for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
@@ -6854,33 +7449,15 @@
return ~accl_mask + 1;
}
-/* Find the lowest pfn for a node */
-static unsigned long __init find_min_pfn_for_node(int nid)
-{
- unsigned long min_pfn = ULONG_MAX;
- unsigned long start_pfn;
- int i;
-
- for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL)
- min_pfn = min(min_pfn, start_pfn);
-
- if (min_pfn == ULONG_MAX) {
- pr_warn("Could not find start_pfn for node %d\n", nid);
- return 0;
- }
-
- return min_pfn;
-}
-
/**
* find_min_pfn_with_active_regions - Find the minimum PFN registered
*
- * It returns the minimum PFN based on information provided via
+ * Return: the minimum PFN based on information provided via
* memblock_set_node().
*/
unsigned long __init find_min_pfn_with_active_regions(void)
{
- return find_min_pfn_for_node(MAX_NUMNODES);
+ return PHYS_PFN(memblock_start_of_DRAM());
}
/*
@@ -6929,11 +7506,11 @@
* options.
*/
if (movable_node_is_enabled()) {
- for_each_memblock(memory, r) {
+ for_each_mem_region(r) {
if (!memblock_is_hotpluggable(r))
continue;
- nid = r->nid;
+ nid = memblock_get_region_node(r);
usable_startpfn = PFN_DOWN(r->base);
zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
@@ -6950,11 +7527,11 @@
if (mirrored_kernelcore) {
bool mem_below_4gb_not_mirrored = false;
- for_each_memblock(memory, r) {
+ for_each_mem_region(r) {
if (memblock_is_mirror(r))
continue;
- nid = r->nid;
+ nid = memblock_get_region_node(r);
usable_startpfn = memblock_region_memory_base_pfn(r);
@@ -6969,7 +7546,7 @@
}
if (mem_below_4gb_not_mirrored)
- pr_warn("This configuration results in unmirrored kernel memory.");
+ pr_warn("This configuration results in unmirrored kernel memory.\n");
goto out2;
}
@@ -7108,9 +7685,16 @@
out2:
/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
- for (nid = 0; nid < MAX_NUMNODES; nid++)
+ for (nid = 0; nid < MAX_NUMNODES; nid++) {
+ unsigned long start_pfn, end_pfn;
+
zone_movable_pfn[nid] =
roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
+
+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+ if (zone_movable_pfn[nid] >= end_pfn)
+ zone_movable_pfn[nid] = 0;
+ }
out:
/* restore the node_state */
@@ -7122,23 +7706,29 @@
{
enum zone_type zone_type;
- if (N_MEMORY == N_NORMAL_MEMORY)
- return;
-
for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
struct zone *zone = &pgdat->node_zones[zone_type];
if (populated_zone(zone)) {
- node_set_state(nid, N_HIGH_MEMORY);
- if (N_NORMAL_MEMORY != N_HIGH_MEMORY &&
- zone_type <= ZONE_NORMAL)
+ if (IS_ENABLED(CONFIG_HIGHMEM))
+ node_set_state(nid, N_HIGH_MEMORY);
+ if (zone_type <= ZONE_NORMAL)
node_set_state(nid, N_NORMAL_MEMORY);
break;
}
}
}
+/*
+ * Some architecturs, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For
+ * such cases we allow max_zone_pfn sorted in the descending order
+ */
+bool __weak arch_has_descending_max_zone_pfns(void)
+{
+ return false;
+}
+
/**
- * free_area_init_nodes - Initialise all pg_data_t and zone data
+ * free_area_init - Initialise all pg_data_t and zone data
* @max_zone_pfn: an array of max PFNs for each zone
*
* This will call free_area_init_node() for each active node in the system.
@@ -7150,10 +7740,11 @@
* starts where the previous one ended. For example, ZONE_DMA32 starts
* at arch_max_dma_pfn.
*/
-void __init free_area_init_nodes(unsigned long *max_zone_pfn)
+void __init free_area_init(unsigned long *max_zone_pfn)
{
unsigned long start_pfn, end_pfn;
- int i, nid;
+ int i, nid, zone;
+ bool descending;
/* Record where the zone boundaries are */
memset(arch_zone_lowest_possible_pfn, 0,
@@ -7162,14 +7753,20 @@
sizeof(arch_zone_highest_possible_pfn));
start_pfn = find_min_pfn_with_active_regions();
+ descending = arch_has_descending_max_zone_pfns();
for (i = 0; i < MAX_NR_ZONES; i++) {
- if (i == ZONE_MOVABLE)
+ if (descending)
+ zone = MAX_NR_ZONES - i - 1;
+ else
+ zone = i;
+
+ if (zone == ZONE_MOVABLE)
continue;
- end_pfn = max(max_zone_pfn[i], start_pfn);
- arch_zone_lowest_possible_pfn[i] = start_pfn;
- arch_zone_highest_possible_pfn[i] = end_pfn;
+ end_pfn = max(max_zone_pfn[zone], start_pfn);
+ arch_zone_lowest_possible_pfn[zone] = start_pfn;
+ arch_zone_highest_possible_pfn[zone] = end_pfn;
start_pfn = end_pfn;
}
@@ -7203,27 +7800,33 @@
(u64)zone_movable_pfn[i] << PAGE_SHIFT);
}
- /* Print out the early node map */
+ /*
+ * Print out the early node map, and initialize the
+ * subsection-map relative to active online memory ranges to
+ * enable future "sub-section" extensions of the memory map.
+ */
pr_info("Early memory node ranges\n");
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
pr_info(" node %3d: [mem %#018Lx-%#018Lx]\n", nid,
(u64)start_pfn << PAGE_SHIFT,
((u64)end_pfn << PAGE_SHIFT) - 1);
+ subsection_map_init(start_pfn, end_pfn - start_pfn);
+ }
/* Initialise every node */
mminit_verify_pageflags_layout();
setup_nr_node_ids();
- zero_resv_unavail();
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
- free_area_init_node(nid, NULL,
- find_min_pfn_for_node(nid), NULL);
+ free_area_init_node(nid);
/* Any memory on that node */
if (pgdat->node_present_pages)
node_set_state(nid, N_MEMORY);
check_for_memory(pgdat, nid);
}
+
+ memmap_init();
}
static int __init cmdline_parse_core(char *p, unsigned long *core,
@@ -7282,22 +7885,18 @@
early_param("kernelcore", cmdline_parse_kernelcore);
early_param("movablecore", cmdline_parse_movablecore);
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-
void adjust_managed_page_count(struct page *page, long count)
{
- spin_lock(&managed_page_count_lock);
- page_zone(page)->managed_pages += count;
- totalram_pages += count;
+ atomic_long_add(count, &page_zone(page)->managed_pages);
+ totalram_pages_add(count);
#ifdef CONFIG_HIGHMEM
if (PageHighMem(page))
- totalhigh_pages += count;
+ totalhigh_pages_add(count);
#endif
- spin_unlock(&managed_page_count_lock);
}
EXPORT_SYMBOL(adjust_managed_page_count);
-unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
+unsigned long free_reserved_area(void *start, void *end, int poison, const char *s)
{
void *pos;
unsigned long pages = 0;
@@ -7316,6 +7915,11 @@
* alias for the memset().
*/
direct_map_addr = page_address(page);
+ /*
+ * Perform a kasan-unchecked memset() since this memory
+ * has not been initialized.
+ */
+ direct_map_addr = kasan_reset_tag(direct_map_addr);
if ((unsigned int)poison <= 0xFF)
memset(direct_map_addr, poison, PAGE_SIZE);
@@ -7328,15 +7932,14 @@
return pages;
}
-EXPORT_SYMBOL(free_reserved_area);
#ifdef CONFIG_HIGHMEM
void free_highmem_page(struct page *page)
{
__free_reserved_page(page);
- totalram_pages++;
- page_zone(page)->managed_pages++;
- totalhigh_pages++;
+ totalram_pages_inc();
+ atomic_long_inc(&page_zone(page)->managed_pages);
+ totalhigh_pages_inc();
}
#endif
@@ -7363,7 +7966,7 @@
*/
#define adj_init_size(start, end, size, pos, adj) \
do { \
- if (start <= pos && pos < end && size > adj) \
+ if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \
size -= adj; \
} while (0)
@@ -7385,10 +7988,10 @@
physpages << (PAGE_SHIFT - 10),
codesize >> 10, datasize >> 10, rosize >> 10,
(init_data_size + init_code_size) >> 10, bss_size >> 10,
- (physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT - 10),
+ (physpages - totalram_pages() - totalcma_pages) << (PAGE_SHIFT - 10),
totalcma_pages << (PAGE_SHIFT - 10),
#ifdef CONFIG_HIGHMEM
- totalhigh_pages << (PAGE_SHIFT - 10),
+ totalhigh_pages() << (PAGE_SHIFT - 10),
#endif
str ? ", " : "", str ? str : "");
}
@@ -7409,18 +8012,10 @@
dma_reserve = new_dma_reserve;
}
-void __init free_area_init(unsigned long *zones_size)
-{
- zero_resv_unavail();
- free_area_init_node(0, zones_size,
- __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
-}
-
static int page_alloc_cpu_dead(unsigned int cpu)
{
- local_lock_irq_on(swapvec_lock, cpu);
+
lru_add_drain_cpu(cpu);
- local_unlock_irq_on(swapvec_lock, cpu);
drain_pages(cpu);
/*
@@ -7442,9 +8037,27 @@
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,
@@ -7469,6 +8082,7 @@
for (i = 0; i < MAX_NR_ZONES; i++) {
struct zone *zone = pgdat->node_zones + i;
long max = 0;
+ unsigned long managed_pages = zone_managed_pages(zone);
/* Find valid and maximum lowmem_reserve in the zone */
for (j = i; j < MAX_NR_ZONES; j++) {
@@ -7479,8 +8093,8 @@
/* we treat the high watermark as reserved pages. */
max += high_wmark_pages(zone);
- if (max > zone->managed_pages)
- max = zone->managed_pages;
+ if (max > managed_pages)
+ max = managed_pages;
pgdat->totalreserve_pages += max;
@@ -7499,30 +8113,24 @@
static void setup_per_zone_lowmem_reserve(void)
{
struct pglist_data *pgdat;
- enum zone_type j, idx;
+ enum zone_type i, j;
for_each_online_pgdat(pgdat) {
- for (j = 0; j < MAX_NR_ZONES; j++) {
- struct zone *zone = pgdat->node_zones + j;
- unsigned long managed_pages = zone->managed_pages;
+ for (i = 0; i < MAX_NR_ZONES - 1; i++) {
+ struct zone *zone = &pgdat->node_zones[i];
+ int ratio = sysctl_lowmem_reserve_ratio[i];
+ bool clear = !ratio || !zone_managed_pages(zone);
+ unsigned long managed_pages = 0;
- zone->lowmem_reserve[j] = 0;
+ for (j = i + 1; j < MAX_NR_ZONES; j++) {
+ struct zone *upper_zone = &pgdat->node_zones[j];
- idx = j;
- while (idx) {
- struct zone *lower_zone;
+ managed_pages += zone_managed_pages(upper_zone);
- idx--;
- lower_zone = pgdat->node_zones + idx;
-
- if (sysctl_lowmem_reserve_ratio[idx] < 1) {
- sysctl_lowmem_reserve_ratio[idx] = 0;
- lower_zone->lowmem_reserve[j] = 0;
- } else {
- lower_zone->lowmem_reserve[j] =
- managed_pages / sysctl_lowmem_reserve_ratio[idx];
- }
- managed_pages += lower_zone->managed_pages;
+ if (clear)
+ zone->lowmem_reserve[j] = 0;
+ else
+ zone->lowmem_reserve[j] = managed_pages / ratio;
}
}
}
@@ -7542,18 +8150,17 @@
/* Calculate total number of !ZONE_HIGHMEM pages */
for_each_zone(zone) {
if (!is_highmem(zone))
- lowmem_pages += zone->managed_pages;
+ lowmem_pages += zone_managed_pages(zone);
}
for_each_zone(zone) {
- u64 min, low;
+ u64 tmp, low;
spin_lock_irqsave(&zone->lock, flags);
- min = (u64)pages_min * zone->managed_pages;
- do_div(min, lowmem_pages);
- low = (u64)pages_low * zone->managed_pages;
- do_div(low, vm_total_pages);
-
+ tmp = (u64)pages_min * zone_managed_pages(zone);
+ do_div(tmp, lowmem_pages);
+ low = (u64)pages_low * zone_managed_pages(zone);
+ do_div(low, nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE)));
if (is_highmem(zone)) {
/*
* __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -7561,20 +8168,20 @@
* value here.
*
* The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
- * deltas control asynch page reclaim, and so should
+ * deltas control async page reclaim, and so should
* not be capped for highmem.
*/
unsigned long min_pages;
- min_pages = zone->managed_pages / 1024;
+ min_pages = zone_managed_pages(zone) / 1024;
min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL);
- zone->watermark[WMARK_MIN] = min_pages;
+ zone->_watermark[WMARK_MIN] = min_pages;
} else {
/*
* If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->watermark[WMARK_MIN] = min;
+ zone->_watermark[WMARK_MIN] = tmp;
}
/*
@@ -7582,14 +8189,13 @@
* scale factor in proportion to available memory, but
* ensure a minimum size on small systems.
*/
- min = max_t(u64, min >> 2,
- mult_frac(zone->managed_pages,
+ tmp = max_t(u64, tmp >> 2,
+ mult_frac(zone_managed_pages(zone),
watermark_scale_factor, 10000));
- zone->watermark[WMARK_LOW] = min_wmark_pages(zone) +
- low + min;
- zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) +
- low + min * 2;
+ zone->watermark_boost = 0;
+ zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + low + tmp;
+ zone->_watermark[WMARK_HIGH] = min_wmark_pages(zone) + low + tmp * 2;
spin_unlock_irqrestore(&zone->lock, flags);
}
@@ -7618,7 +8224,7 @@
* Initialise min_free_kbytes.
*
* For small machines we want it small (128k min). For large machines
- * we want it large (64MB max). But it is not linear, because network
+ * we want it large (256MB max). But it is not linear, because network
* bandwidth does not increase linearly with machine size. We use
*
* min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
@@ -7650,8 +8256,8 @@
min_free_kbytes = new_min_free_kbytes;
if (min_free_kbytes < 128)
min_free_kbytes = 128;
- if (min_free_kbytes > 65536)
- min_free_kbytes = 65536;
+ if (min_free_kbytes > 262144)
+ min_free_kbytes = 262144;
} else {
pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n",
new_min_free_kbytes, user_min_free_kbytes);
@@ -7677,7 +8283,7 @@
* or extra_free_kbytes changes.
*/
int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -7693,7 +8299,7 @@
}
int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -7717,13 +8323,13 @@
pgdat->min_unmapped_pages = 0;
for_each_zone(zone)
- zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
- sysctl_min_unmapped_ratio) / 100;
+ zone->zone_pgdat->min_unmapped_pages += (zone_managed_pages(zone) *
+ sysctl_min_unmapped_ratio) / 100;
}
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -7745,12 +8351,12 @@
pgdat->min_slab_pages = 0;
for_each_zone(zone)
- zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
- sysctl_min_slab_ratio) / 100;
+ zone->zone_pgdat->min_slab_pages += (zone_managed_pages(zone) *
+ sysctl_min_slab_ratio) / 100;
}
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -7774,11 +8380,28 @@
* if in function of the boot time zone sizes.
*/
int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
+ int i;
+
proc_dointvec_minmax(table, write, buffer, length, ppos);
+
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ if (sysctl_lowmem_reserve_ratio[i] < 1)
+ sysctl_lowmem_reserve_ratio[i] = 0;
+ }
+
setup_per_zone_lowmem_reserve();
return 0;
+}
+
+static void __zone_pcp_update(struct zone *zone)
+{
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu)
+ pageset_set_high_and_batch(zone,
+ per_cpu_ptr(zone->pageset, cpu));
}
/*
@@ -7787,7 +8410,7 @@
* pagelist can have before it gets flushed back to buddy allocator.
*/
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
int old_percpu_pagelist_fraction;
@@ -7812,30 +8435,12 @@
if (percpu_pagelist_fraction == old_percpu_pagelist_fraction)
goto out;
- for_each_populated_zone(zone) {
- unsigned int cpu;
-
- for_each_possible_cpu(cpu)
- pageset_set_high_and_batch(zone,
- per_cpu_ptr(zone->pageset, cpu));
- }
+ for_each_populated_zone(zone)
+ __zone_pcp_update(zone);
out:
mutex_unlock(&pcp_batch_high_lock);
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
/*
@@ -7883,6 +8488,7 @@
unsigned long log2qty, size;
void *table = NULL;
gfp_t gfp_flags;
+ bool virt;
/* allow the kernel cmdline to have a say */
if (!numentries) {
@@ -7939,32 +8545,34 @@
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)
- table = memblock_virt_alloc_nopanic(size, 0);
+ table = memblock_alloc(size, SMP_CACHE_BYTES);
else
- table = memblock_virt_alloc_raw(size, 0);
- } else if (hashdist) {
- table = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+ table = memblock_alloc_raw(size,
+ SMP_CACHE_BYTES);
+ } else if (get_order(size) >= MAX_ORDER || hashdist) {
+ table = __vmalloc(size, gfp_flags);
+ 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;
@@ -7976,47 +8584,50 @@
/*
* This function checks whether pageblock includes unmovable pages or not.
- * If @count is not zero, it is okay to include less @count unmovable pages
*
* PageLRU check without isolation or lru_lock could race so that
* MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
* check without lock_page also may miss some movable non-lru pages at
* race condition. So you can't expect this function should be exact.
+ *
+ * Returns a page without holding a reference. If the caller wants to
+ * dereference that page (e.g., dumping), it has to make sure that it
+ * cannot get removed (e.g., via memory unplug) concurrently.
+ *
*/
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
- int migratetype,
- bool skip_hwpoisoned_pages)
+struct page *has_unmovable_pages(struct zone *zone, struct page *page,
+ int migratetype, int flags)
{
- unsigned long pfn, iter, found;
+ unsigned long iter = 0;
+ unsigned long pfn = page_to_pfn(page);
+ unsigned long offset = pfn % pageblock_nr_pages;
- /*
- * TODO we could make this much more efficient by not checking every
- * page in the range if we know all of them are in MOVABLE_ZONE and
- * that the movable zone guarantees that pages are migratable but
- * the later is not the case right now unfortunatelly. E.g. movablecore
- * can still lead to having bootmem allocations in zone_movable.
- */
+ if (is_migrate_cma_page(page)) {
+ /*
+ * CMA allocations (alloc_contig_range) really need to mark
+ * isolate CMA pageblocks even when they are not movable in fact
+ * so consider them movable here.
+ */
+ if (is_migrate_cma(migratetype))
+ return NULL;
- /*
- * CMA allocations (alloc_contig_range) really need to mark isolate
- * CMA pageblocks even when they are not movable in fact so consider
- * them movable here.
- */
- if (is_migrate_cma(migratetype) &&
- is_migrate_cma(get_pageblock_migratetype(page)))
- return false;
+ return page;
+ }
- pfn = page_to_pfn(page);
- for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
- unsigned long check = pfn + iter;
-
- if (!pfn_valid_within(check))
+ for (; iter < pageblock_nr_pages - offset; iter++) {
+ if (!pfn_valid_within(pfn + iter))
continue;
- page = pfn_to_page(check);
+ page = pfn_to_page(pfn + iter);
+ /*
+ * Both, bootmem allocations and memory holes are marked
+ * PG_reserved and are unmovable. We can even have unmovable
+ * allocations inside ZONE_MOVABLE, for example when
+ * specifying "movablecore".
+ */
if (PageReserved(page))
- goto unmovable;
+ return page;
/*
* If the zone is movable and we have ruled out all reserved
@@ -8028,17 +8639,22 @@
/*
* Hugepages are not in LRU lists, but they're movable.
- * We need not scan over tail pages bacause we don't
+ * THPs are on the LRU, but need to be counted as #small pages.
+ * We need not scan over tail pages because we don't
* handle each tail page individually in migration.
*/
- if (PageHuge(page)) {
+ if (PageHuge(page) || PageTransCompound(page)) {
struct page *head = compound_head(page);
unsigned int skip_pages;
- if (!hugepage_migration_supported(page_hstate(head)))
- goto unmovable;
+ if (PageHuge(page)) {
+ if (!hugepage_migration_supported(page_hstate(head)))
+ return page;
+ } else if (!PageLRU(head) && !__PageMovable(head)) {
+ return page;
+ }
- skip_pages = (1 << compound_order(head)) - (page - head);
+ skip_pages = compound_nr(head) - (page - head);
iter += skip_pages - 1;
continue;
}
@@ -8051,7 +8667,7 @@
*/
if (!page_ref_count(page)) {
if (PageBuddy(page))
- iter += (1 << page_order(page)) - 1;
+ iter += (1 << buddy_order(page)) - 1;
continue;
}
@@ -8059,61 +8675,100 @@
* The HWPoisoned page may be not in buddy system, and
* page_count() is not 0.
*/
- if (skip_hwpoisoned_pages && PageHWPoison(page))
+ if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
continue;
- if (__PageMovable(page))
+ /*
+ * We treat all PageOffline() pages as movable when offlining
+ * to give drivers a chance to decrement their reference count
+ * in MEM_GOING_OFFLINE in order to indicate that these pages
+ * can be offlined as there are no direct references anymore.
+ * For actually unmovable PageOffline() where the driver does
+ * not support this, we will fail later when trying to actually
+ * move these pages that still have a reference count > 0.
+ * (false negatives in this function only)
+ */
+ if ((flags & MEMORY_OFFLINE) && PageOffline(page))
continue;
- if (!PageLRU(page))
- found++;
+ if (__PageMovable(page) || PageLRU(page))
+ continue;
+
/*
* If there are RECLAIMABLE pages, we need to check
* it. But now, memory offline itself doesn't call
* shrink_node_slabs() and it still to be fixed.
*/
- /*
- * If the page is not RAM, page_count()should be 0.
- * we don't need more check. This is an _used_ not-movable page.
- *
- * The problematic thing here is PG_reserved pages. PG_reserved
- * is set to both of a memory hole page and a _used_ kernel
- * page at boot.
- */
- if (found > count)
- goto unmovable;
+ return page;
}
- return false;
-unmovable:
- WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
- return true;
+ return NULL;
}
-#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
-
+#ifdef CONFIG_CONTIG_ALLOC
static unsigned long pfn_max_align_down(unsigned long pfn)
{
return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
pageblock_nr_pages) - 1);
}
-static unsigned long pfn_max_align_up(unsigned long pfn)
+unsigned long pfn_max_align_up(unsigned long pfn)
{
return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
pageblock_nr_pages));
}
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
+/* Usage: See admin-guide/dynamic-debug-howto.rst */
+static void alloc_contig_dump_pages(struct list_head *page_list)
+{
+ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, "migrate failure");
+
+ if (DYNAMIC_DEBUG_BRANCH(descriptor)) {
+ struct page *page;
+ unsigned long nr_skip = 0;
+ unsigned long nr_pages = 0;
+
+ dump_stack();
+ list_for_each_entry(page, page_list, lru) {
+ nr_pages++;
+ /* The page will be freed by putback_movable_pages soon */
+ if (page_count(page) == 1) {
+ nr_skip++;
+ continue;
+ }
+ dump_page(page, "migration failure");
+ }
+ pr_warn("total dump_pages %lu skipping %lu\n", nr_pages, nr_skip);
+ }
+}
+#else
+static inline void alloc_contig_dump_pages(struct list_head *page_list)
+{
+}
+#endif
+
/* [start, end) must belong to a single zone. */
static int __alloc_contig_migrate_range(struct compact_control *cc,
- unsigned long start, unsigned long end)
+ unsigned long start, unsigned long end,
+ struct acr_info *info)
{
/* This function is based on compact_zone() from compaction.c. */
- unsigned long nr_reclaimed;
+ unsigned int nr_reclaimed;
unsigned long pfn = start;
unsigned int tries = 0;
+ unsigned int max_tries = 5;
int ret = 0;
+ struct page *page;
+ struct migration_target_control mtc = {
+ .nid = zone_to_nid(cc->zone),
+ .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+ };
- migrate_prep();
+ if (cc->alloc_contig && cc->mode == MIGRATE_ASYNC)
+ max_tries = 1;
+
+ lru_cache_disable();
while (pfn < end || !list_empty(&cc->migratepages)) {
if (fatal_signal_pending(current)) {
@@ -8129,20 +8784,39 @@
break;
}
tries = 0;
- } else if (++tries == 5) {
+ } else if (++tries == max_tries) {
ret = ret < 0 ? ret : -EBUSY;
break;
}
nr_reclaimed = reclaim_clean_pages_from_list(cc->zone,
&cc->migratepages);
+ info->nr_reclaimed += nr_reclaimed;
cc->nr_migratepages -= nr_reclaimed;
- ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
- NULL, 0, cc->mode, MR_CONTIG_RANGE);
+ list_for_each_entry(page, &cc->migratepages, lru)
+ info->nr_mapped += page_mapcount(page);
+
+ ret = migrate_pages(&cc->migratepages, alloc_migration_target,
+ NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE);
+ if (!ret)
+ info->nr_migrated += cc->nr_migratepages;
}
+
+ lru_cache_enable();
if (ret < 0) {
+ if (ret == -EBUSY) {
+ alloc_contig_dump_pages(&cc->migratepages);
+ page_pinner_mark_migration_failed_pages(&cc->migratepages);
+ }
+
+ if (!list_empty(&cc->migratepages)) {
+ page = list_first_entry(&cc->migratepages, struct page , lru);
+ info->failed_pfn = page_to_pfn(page);
+ }
+
putback_movable_pages(&cc->migratepages);
+ info->err |= ACR_ERR_MIGRATE;
return ret;
}
return 0;
@@ -8165,25 +8839,28 @@
* pageblocks in the range. Once isolated, the pageblocks should not
* be modified by others.
*
- * Returns zero on success or negative error code. On success all
+ * Return: zero on success or negative error code. On success all
* pages which PFN is in [start, end) are allocated for the caller and
* need to be freed with free_contig_range().
*/
int alloc_contig_range(unsigned long start, unsigned long end,
- unsigned migratetype, gfp_t gfp_mask)
+ unsigned migratetype, gfp_t gfp_mask,
+ struct acr_info *info)
{
unsigned long outer_start, outer_end;
unsigned int order;
int ret = 0;
+ bool skip_drain_all_pages = false;
struct compact_control cc = {
.nr_migratepages = 0,
.order = -1,
.zone = page_zone(pfn_to_page(start)),
- .mode = MIGRATE_SYNC,
+ .mode = gfp_mask & __GFP_NORETRY ? MIGRATE_ASYNC : MIGRATE_SYNC,
.ignore_skip_hint = true,
.no_set_skip_hint = true,
.gfp_mask = current_gfp_context(gfp_mask),
+ .alloc_contig = true,
};
INIT_LIST_HEAD(&cc.migratepages);
@@ -8212,14 +8889,18 @@
*/
ret = start_isolate_page_range(pfn_max_align_down(start),
- pfn_max_align_up(end), migratetype,
- false);
- if (ret)
+ pfn_max_align_up(end), migratetype, 0,
+ &info->failed_pfn);
+ if (ret) {
+ info->err |= ACR_ERR_ISOLATE;
return ret;
+ }
-#ifdef CONFIG_CMA
- cc.zone->cma_alloc = 1;
-#endif
+ trace_android_vh_cma_drain_all_pages_bypass(migratetype,
+ &skip_drain_all_pages);
+ if (!skip_drain_all_pages)
+ drain_all_pages(cc.zone);
+
/*
* In case of -EBUSY, we'd like to know which page causes problem.
* So, just fall through. test_pages_isolated() has a tracepoint
@@ -8230,8 +8911,8 @@
* allocated. So, if we fall through be sure to clear ret so that
* -EBUSY is not accidentally used or returned to caller.
*/
- ret = __alloc_contig_migrate_range(&cc, start, end);
- if (ret && ret != -EBUSY)
+ ret = __alloc_contig_migrate_range(&cc, start, end, info);
+ if (ret && (ret != -EBUSY || (gfp_mask & __GFP_NORETRY)))
goto done;
ret =0;
@@ -8252,9 +8933,6 @@
* isolated thus they won't get removed from buddy.
*/
- lru_add_drain_all();
- drain_all_pages(cc.zone);
-
order = 0;
outer_start = start;
while (!PageBuddy(pfn_to_page(outer_start))) {
@@ -8266,7 +8944,7 @@
}
if (outer_start != start) {
- order = page_order(pfn_to_page(outer_start));
+ order = buddy_order(pfn_to_page(outer_start));
/*
* outer_start page could be small order buddy page and
@@ -8279,10 +8957,11 @@
}
/* Make sure the range is really isolated. */
- if (test_pages_isolated(outer_start, end, false)) {
+ if (test_pages_isolated(outer_start, end, 0, &info->failed_pfn)) {
pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
__func__, outer_start, end);
ret = -EBUSY;
+ info->err |= ACR_ERR_TEST;
goto done;
}
@@ -8302,13 +8981,114 @@
done:
undo_isolate_page_range(pfn_max_align_down(start),
pfn_max_align_up(end), migratetype);
-#ifdef CONFIG_CMA
- cc.zone->cma_alloc = 0;
-#endif
return ret;
}
+EXPORT_SYMBOL(alloc_contig_range);
-void free_contig_range(unsigned long pfn, unsigned nr_pages)
+static int __alloc_contig_pages(unsigned long start_pfn,
+ unsigned long nr_pages, gfp_t gfp_mask)
+{
+ struct acr_info dummy;
+ unsigned long end_pfn = start_pfn + nr_pages;
+
+ return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE,
+ gfp_mask, &dummy);
+}
+
+static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn,
+ unsigned long nr_pages)
+{
+ unsigned long i, end_pfn = start_pfn + nr_pages;
+ struct page *page;
+
+ for (i = start_pfn; i < end_pfn; i++) {
+ page = pfn_to_online_page(i);
+ if (!page)
+ return false;
+
+ if (page_zone(page) != z)
+ return false;
+
+ if (PageReserved(page))
+ return false;
+
+ if (page_count(page) > 0)
+ return false;
+
+ if (PageHuge(page))
+ return false;
+ }
+ return true;
+}
+
+static bool zone_spans_last_pfn(const struct zone *zone,
+ unsigned long start_pfn, unsigned long nr_pages)
+{
+ unsigned long last_pfn = start_pfn + nr_pages - 1;
+
+ return zone_spans_pfn(zone, last_pfn);
+}
+
+/**
+ * alloc_contig_pages() -- tries to find and allocate contiguous range of pages
+ * @nr_pages: Number of contiguous pages to allocate
+ * @gfp_mask: GFP mask to limit search and used during compaction
+ * @nid: Target node
+ * @nodemask: Mask for other possible nodes
+ *
+ * This routine is a wrapper around alloc_contig_range(). It scans over zones
+ * on an applicable zonelist to find a contiguous pfn range which can then be
+ * tried for allocation with alloc_contig_range(). This routine is intended
+ * for allocation requests which can not be fulfilled with the buddy allocator.
+ *
+ * The allocated memory is always aligned to a page boundary. If nr_pages is a
+ * power of two then the alignment is guaranteed to be to the given nr_pages
+ * (e.g. 1GB request would be aligned to 1GB).
+ *
+ * Allocated pages can be freed with free_contig_range() or by manually calling
+ * __free_page() on each allocated page.
+ *
+ * Return: pointer to contiguous pages on success, or NULL if not successful.
+ */
+struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask,
+ int nid, nodemask_t *nodemask)
+{
+ unsigned long ret, pfn, flags;
+ struct zonelist *zonelist;
+ struct zone *zone;
+ struct zoneref *z;
+
+ zonelist = node_zonelist(nid, gfp_mask);
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ gfp_zone(gfp_mask), nodemask) {
+ spin_lock_irqsave(&zone->lock, flags);
+
+ pfn = ALIGN(zone->zone_start_pfn, nr_pages);
+ while (zone_spans_last_pfn(zone, pfn, nr_pages)) {
+ if (pfn_range_valid_contig(zone, pfn, nr_pages)) {
+ /*
+ * We release the zone lock here because
+ * alloc_contig_range() will also lock the zone
+ * at some point. If there's an allocation
+ * spinning on this lock, it may win the race
+ * and cause alloc_contig_range() to fail...
+ */
+ spin_unlock_irqrestore(&zone->lock, flags);
+ ret = __alloc_contig_pages(pfn, nr_pages,
+ gfp_mask);
+ if (!ret)
+ return pfn_to_page(pfn);
+ spin_lock_irqsave(&zone->lock, flags);
+ }
+ pfn += nr_pages;
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+ }
+ return NULL;
+}
+#endif /* CONFIG_CONTIG_ALLOC */
+
+void free_contig_range(unsigned long pfn, unsigned int nr_pages)
{
unsigned int count = 0;
@@ -8320,7 +9100,7 @@
}
WARN(count != 0, "%d pages are still in use!\n", count);
}
-#endif
+EXPORT_SYMBOL(free_contig_range);
/*
* The zone indicated has a new number of managed_pages; batch sizes and percpu
@@ -8328,11 +9108,8 @@
*/
void __meminit zone_pcp_update(struct zone *zone)
{
- unsigned cpu;
mutex_lock(&pcp_batch_high_lock);
- for_each_possible_cpu(cpu)
- pageset_set_high_and_batch(zone,
- per_cpu_ptr(zone->pageset, cpu));
+ __zone_pcp_update(zone);
mutex_unlock(&pcp_batch_high_lock);
}
@@ -8343,7 +9120,7 @@
struct per_cpu_pageset *pset;
/* avoid races with drain_pages() */
- local_lock_irqsave(pa_lock, flags);
+ local_irq_save(flags);
if (zone->pageset != &boot_pageset) {
for_each_online_cpu(cpu) {
pset = per_cpu_ptr(zone->pageset, cpu);
@@ -8352,37 +9129,26 @@
free_percpu(zone->pageset);
zone->pageset = &boot_pageset;
}
- local_unlock_irqrestore(pa_lock, flags);
+ local_irq_restore(flags);
}
#ifdef CONFIG_MEMORY_HOTREMOVE
/*
- * All pages in the range must be in a single zone and isolated
- * before calling this.
+ * All pages in the range must be in a single zone, must not contain holes,
+ * must span full sections, and must be isolated before calling this function.
*/
-void
-__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
+void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
+ unsigned long pfn = start_pfn;
struct page *page;
struct zone *zone;
- unsigned int order, i;
- unsigned long pfn;
+ unsigned int order;
unsigned long flags;
- /* find the first valid pfn */
- for (pfn = start_pfn; pfn < end_pfn; pfn++)
- if (pfn_valid(pfn))
- break;
- if (pfn == end_pfn)
- return;
+
offline_mem_sections(pfn, end_pfn);
zone = page_zone(pfn_to_page(pfn));
spin_lock_irqsave(&zone->lock, flags);
- pfn = start_pfn;
while (pfn < end_pfn) {
- if (!pfn_valid(pfn)) {
- pfn++;
- continue;
- }
page = pfn_to_page(pfn);
/*
* The HWPoisoned page may be not in buddy system, and
@@ -8390,22 +9156,23 @@
*/
if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
pfn++;
- SetPageReserved(page);
+ continue;
+ }
+ /*
+ * At this point all remaining PageOffline() pages have a
+ * reference count of 0 and can simply be skipped.
+ */
+ if (PageOffline(page)) {
+ BUG_ON(page_count(page));
+ BUG_ON(PageBuddy(page));
+ pfn++;
continue;
}
BUG_ON(page_count(page));
BUG_ON(!PageBuddy(page));
- order = page_order(page);
-#ifdef CONFIG_DEBUG_VM
- pr_info("remove from free list %lx %d %lx\n",
- pfn, 1 << order, end_pfn);
-#endif
- list_del(&page->lru);
- rmv_page_order(page);
- zone->free_area[order].nr_free--;
- for (i = 0; i < (1 << order); i++)
- SetPageReserved((page+i));
+ order = buddy_order(page);
+ del_page_from_free_list(page, zone, order);
pfn += (1 << order);
}
spin_unlock_irqrestore(&zone->lock, flags);
@@ -8423,7 +9190,7 @@
for (order = 0; order < MAX_ORDER; order++) {
struct page *page_head = page - (pfn & ((1 << order) - 1));
- if (PageBuddy(page_head) && page_order(page_head) >= order)
+ if (PageBuddy(page_head) && buddy_order(page_head) >= order)
break;
}
spin_unlock_irqrestore(&zone->lock, flags);
@@ -8433,30 +9200,87 @@
#ifdef CONFIG_MEMORY_FAILURE
/*
- * Set PG_hwpoison flag if a given page is confirmed to be a free page. This
- * test is performed under the zone lock to prevent a race against page
- * allocation.
+ * Break down a higher-order page in sub-pages, and keep our target out of
+ * buddy allocator.
*/
-bool set_hwpoison_free_buddy_page(struct page *page)
+static void break_down_buddy_pages(struct zone *zone, struct page *page,
+ struct page *target, int low, int high,
+ int migratetype)
+{
+ unsigned long size = 1 << high;
+ struct page *current_buddy, *next_page;
+
+ while (high > low) {
+ high--;
+ size >>= 1;
+
+ if (target >= &page[size]) {
+ next_page = page + size;
+ current_buddy = page;
+ } else {
+ next_page = page;
+ current_buddy = page + size;
+ }
+
+ if (set_page_guard(zone, current_buddy, high, migratetype))
+ continue;
+
+ if (current_buddy != target) {
+ add_to_free_list(current_buddy, zone, high, migratetype);
+ set_buddy_order(current_buddy, high);
+ page = next_page;
+ }
+ }
+}
+
+/*
+ * Take a page that will be marked as poisoned off the buddy allocator.
+ */
+bool take_page_off_buddy(struct page *page)
{
struct zone *zone = page_zone(page);
unsigned long pfn = page_to_pfn(page);
unsigned long flags;
unsigned int order;
- bool hwpoisoned = false;
+ bool ret = false;
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
struct page *page_head = page - (pfn & ((1 << order) - 1));
+ int page_order = buddy_order(page_head);
- if (PageBuddy(page_head) && page_order(page_head) >= order) {
- if (!TestSetPageHWPoison(page))
- hwpoisoned = true;
+ if (PageBuddy(page_head) && page_order >= order) {
+ unsigned long pfn_head = page_to_pfn(page_head);
+ int migratetype = get_pfnblock_migratetype(page_head,
+ pfn_head);
+
+ del_page_from_free_list(page_head, zone, page_order);
+ break_down_buddy_pages(zone, page_head, page, 0,
+ page_order, migratetype);
+ if (!is_migrate_isolate(migratetype))
+ __mod_zone_freepage_state(zone, -1, migratetype);
+ ret = true;
break;
}
+ if (page_count(page_head) > 0)
+ break;
}
spin_unlock_irqrestore(&zone->lock, flags);
-
- return hwpoisoned;
+ return ret;
}
#endif
+
+#ifdef CONFIG_ZONE_DMA
+bool has_managed_dma(void)
+{
+ struct pglist_data *pgdat;
+
+ for_each_online_pgdat(pgdat) {
+ struct zone *zone = &pgdat->node_zones[ZONE_DMA];
+
+ if (managed_zone(zone))
+ return true;
+ }
+ return false;
+}
+#endif /* CONFIG_ZONE_DMA */
--
Gitblit v1.6.2