linux/mm/page_alloc.c
David Rientjes 3f36d86694 mm, hugetlb: allow hugepage allocations to reclaim as needed
Commit b39d0ee263 ("mm, page_alloc: avoid expensive reclaim when
compaction may not succeed") has chnaged the allocator to bail out from
the allocator early to prevent from a potentially excessive memory
reclaim.  __GFP_RETRY_MAYFAIL is designed to retry the allocation,
reclaim and compaction loop as long as there is a reasonable chance to
make forward progress.  Neither COMPACT_SKIPPED nor COMPACT_DEFERRED at
the INIT_COMPACT_PRIORITY compaction attempt gives this feedback.

The most obvious affected subsystem is hugetlbfs which allocates huge
pages based on an admin request (or via admin configured overcommit).  I
have done a simple test which tries to allocate half of the memory for
hugetlb pages while the memory is full of a clean page cache.  This is
not an unusual situation because we try to cache as much of the memory
as possible and sysctl/sysfs interface to allocate huge pages is there
for flexibility to allocate hugetlb pages at any time.

System has 1GB of RAM and we are requesting 515MB worth of hugetlb pages
after the memory is prefilled by a clean page cache:

  root@test1:~# cat hugetlb_test.sh

  set -x
  echo 0 > /proc/sys/vm/nr_hugepages
  echo 3 > /proc/sys/vm/drop_caches
  echo 1 > /proc/sys/vm/compact_memory
  dd if=/mnt/data/file-1G of=/dev/null bs=$((4<<10))
  TS=$(date +%s)
  echo 256 > /proc/sys/vm/nr_hugepages
  cat /proc/sys/vm/nr_hugepages

The results for 2 consecutive runs on clean 5.3

  root@test1:~# sh hugetlb_test.sh
  + echo 0
  + echo 3
  + echo 1
  + dd if=/mnt/data/file-1G of=/dev/null bs=4096
  262144+0 records in
  262144+0 records out
  1073741824 bytes (1.1 GB) copied, 21.0694 s, 51.0 MB/s
  + date +%s
  + TS=1569905284
  + echo 256
  + cat /proc/sys/vm/nr_hugepages
  256
  root@test1:~# sh hugetlb_test.sh
  + echo 0
  + echo 3
  + echo 1
  + dd if=/mnt/data/file-1G of=/dev/null bs=4096
  262144+0 records in
  262144+0 records out
  1073741824 bytes (1.1 GB) copied, 21.7548 s, 49.4 MB/s
  + date +%s
  + TS=1569905311
  + echo 256
  + cat /proc/sys/vm/nr_hugepages
  256

Now with b39d0ee263 applied

  root@test1:~# sh hugetlb_test.sh
  + echo 0
  + echo 3
  + echo 1
  + dd if=/mnt/data/file-1G of=/dev/null bs=4096
  262144+0 records in
  262144+0 records out
  1073741824 bytes (1.1 GB) copied, 20.1815 s, 53.2 MB/s
  + date +%s
  + TS=1569905516
  + echo 256
  + cat /proc/sys/vm/nr_hugepages
  11
  root@test1:~# sh hugetlb_test.sh
  + echo 0
  + echo 3
  + echo 1
  + dd if=/mnt/data/file-1G of=/dev/null bs=4096
  262144+0 records in
  262144+0 records out
  1073741824 bytes (1.1 GB) copied, 21.9485 s, 48.9 MB/s
  + date +%s
  + TS=1569905541
  + echo 256
  + cat /proc/sys/vm/nr_hugepages
  12

The success rate went down by factor of 20!

Although hugetlb allocation requests might fail and it is reasonable to
expect them to under extremely fragmented memory or when the memory is
under a heavy pressure but the above situation is not that case.

Fix the regression by reverting back to the previous behavior for
__GFP_RETRY_MAYFAIL requests and disable the beail out heuristic for
those requests.

Mike said:

: hugetlbfs allocations are commonly done via sysctl/sysfs shortly after
: boot where this may not be as much of an issue.  However, I am aware of at
: least three use cases where allocations are made after the system has been
: up and running for quite some time:
:
: - DB reconfiguration.  If sysctl/sysfs fails to get required number of
:   huge pages, system is rebooted to perform allocation after boot.
:
: - VM provisioning.  If unable get required number of huge pages, fall
:   back to base pages.
:
: - An application that does not preallocate pool, but rather allocates
:   pages at fault time for optimal NUMA locality.
:
: In all cases, I would expect b39d0ee263 to cause regressions and
: noticable behavior changes.
:
: My quick/limited testing in
: https://lkml.kernel.org/r/3468b605-a3a9-6978-9699-57c52a90bd7e@oracle.com
: was insufficient.  It was also mentioned that if something like
: b39d0ee263 went forward, I would like exemptions for __GFP_RETRY_MAYFAIL
: requests as in this patch.

[mhocko@suse.com: reworded changelog]
Link: http://lkml.kernel.org/r/20191007075548.12456-1-mhocko@kernel.org
Fixes: b39d0ee263 ("mm, page_alloc: avoid expensive reclaim when compaction may not succeed")
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-14 15:04:01 -07:00

8662 lines
238 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/page_alloc.c
*
* Manages the free list, the system allocates free pages here.
* Note that kmalloc() lives in slab.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
* Swap reorganised 29.12.95, Stephen Tweedie
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
* Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
* Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
* Zone balancing, Kanoj Sarcar, SGI, Jan 2000
* Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
* (lots of bits borrowed from Ingo Molnar & Andrew Morton)
*/
#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/memblock.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/kasan.h>
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/oom.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>
#include <linux/vmstat.h>
#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/debugobjects.h>
#include <linux/kmemleak.h>
#include <linux/compaction.h>
#include <trace/events/kmem.h>
#include <trace/events/oom.h>
#include <linux/prefetch.h>
#include <linux/mm_inline.h>
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/sched/rt.h>
#include <linux/sched/mm.h>
#include <linux/page_owner.h>
#include <linux/kthread.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
#include <linux/lockdep.h>
#include <linux/nmi.h>
#include <linux/psi.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
#include "shuffle.h"
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
#define MIN_PERCPU_PAGELIST_FRACTION (8)
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DEFINE_PER_CPU(int, numa_node);
EXPORT_PER_CPU_SYMBOL(numa_node);
#endif
DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key);
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
* N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
* It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
* Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem()
* defined in <linux/topology.h>.
*/
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 */
struct pcpu_drain {
struct zone *zone;
struct work_struct work;
};
DEFINE_MUTEX(pcpu_drain_mutex);
DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);
#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
volatile unsigned long latent_entropy __latent_entropy;
EXPORT_SYMBOL(latent_entropy);
#endif
/*
* Array of node states.
*/
nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
[N_POSSIBLE] = NODE_MASK_ALL,
[N_ONLINE] = { { [0] = 1UL } },
#ifndef CONFIG_NUMA
[N_NORMAL_MEMORY] = { { [0] = 1UL } },
#ifdef CONFIG_HIGHMEM
[N_HIGH_MEMORY] = { { [0] = 1UL } },
#endif
[N_MEMORY] = { { [0] = 1UL } },
[N_CPU] = { { [0] = 1UL } },
#endif /* NUMA */
};
EXPORT_SYMBOL(node_states);
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 int __init early_init_on_alloc(char *buf)
{
int ret;
bool bool_result;
if (!buf)
return -EINVAL;
ret = kstrtobool(buf, &bool_result);
if (bool_result && page_poisoning_enabled())
pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_alloc\n");
if (bool_result)
static_branch_enable(&init_on_alloc);
else
static_branch_disable(&init_on_alloc);
return ret;
}
early_param("init_on_alloc", early_init_on_alloc);
static int __init early_init_on_free(char *buf)
{
int ret;
bool bool_result;
if (!buf)
return -EINVAL;
ret = kstrtobool(buf, &bool_result);
if (bool_result && page_poisoning_enabled())
pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_free\n");
if (bool_result)
static_branch_enable(&init_on_free);
else
static_branch_disable(&init_on_free);
return ret;
}
early_param("init_on_free", early_init_on_free);
/*
* A cached value of the page's pageblock's migratetype, used when the page is
* put on a pcplist. Used to avoid the pageblock migratetype lookup when
* freeing from pcplists in most cases, at the cost of possibly becoming stale.
* Also the migratetype set in the page does not necessarily match the pcplist
* index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any
* other index - this ensures that it will be put on the correct CMA freelist.
*/
static inline int get_pcppage_migratetype(struct page *page)
{
return page->index;
}
static inline void set_pcppage_migratetype(struct page *page, int migratetype)
{
page->index = migratetype;
}
#ifdef CONFIG_PM_SLEEP
/*
* The following functions are used by the suspend/hibernate code to temporarily
* change gfp_allowed_mask in order to avoid using I/O during memory allocations
* while devices are suspended. To avoid races with the suspend/hibernate code,
* they should always be called with system_transition_mutex held
* (gfp_allowed_mask also should only be modified with system_transition_mutex
* held, unless the suspend/hibernate code is guaranteed not to run in parallel
* with that modification).
*/
static gfp_t saved_gfp_mask;
void pm_restore_gfp_mask(void)
{
WARN_ON(!mutex_is_locked(&system_transition_mutex));
if (saved_gfp_mask) {
gfp_allowed_mask = saved_gfp_mask;
saved_gfp_mask = 0;
}
}
void pm_restrict_gfp_mask(void)
{
WARN_ON(!mutex_is_locked(&system_transition_mutex));
WARN_ON(saved_gfp_mask);
saved_gfp_mask = gfp_allowed_mask;
gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
}
bool pm_suspended_storage(void)
{
if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
return false;
return true;
}
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
unsigned int pageblock_order __read_mostly;
#endif
static void __free_pages_ok(struct page *page, unsigned int order);
/*
* results with 256, 32 in the lowmem_reserve sysctl:
* 1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
* 1G machine -> (16M dma, 784M normal, 224M high)
* NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
* HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
* HIGHMEM allocation will leave (224M+784M)/256 of ram reserved in ZONE_DMA
*
* TBD: should special case ZONE_DMA32 machines here - in those we normally
* don't need any ZONE_NORMAL reservation
*/
int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {
#ifdef CONFIG_ZONE_DMA
[ZONE_DMA] = 256,
#endif
#ifdef CONFIG_ZONE_DMA32
[ZONE_DMA32] = 256,
#endif
[ZONE_NORMAL] = 32,
#ifdef CONFIG_HIGHMEM
[ZONE_HIGHMEM] = 0,
#endif
[ZONE_MOVABLE] = 0,
};
static char * const zone_names[MAX_NR_ZONES] = {
#ifdef CONFIG_ZONE_DMA
"DMA",
#endif
#ifdef CONFIG_ZONE_DMA32
"DMA32",
#endif
"Normal",
#ifdef CONFIG_HIGHMEM
"HighMem",
#endif
"Movable",
#ifdef CONFIG_ZONE_DEVICE
"Device",
#endif
};
const char * const migratetype_names[MIGRATE_TYPES] = {
"Unmovable",
"Movable",
"Reclaimable",
"HighAtomic",
#ifdef CONFIG_CMA
"CMA",
#endif
#ifdef CONFIG_MEMORY_ISOLATION
"Isolate",
#endif
};
compound_page_dtor * const compound_page_dtors[] = {
NULL,
free_compound_page,
#ifdef CONFIG_HUGETLB_PAGE
free_huge_page,
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
free_transhuge_page,
#endif
};
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;
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] __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] __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
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
int page_group_by_mobility_disabled __read_mostly;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
* During boot we initialize deferred pages on-demand, as needed, but once
* page_alloc_init_late() has finished, the deferred pages are all initialized,
* and we can permanently disable that path.
*/
static DEFINE_STATIC_KEY_TRUE(deferred_pages);
/*
* Calling kasan_free_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.
*
* Assuming that there will be no reference to those newly initialized
* pages before they are ever allocated, this should have no effect on
* KASAN memory tracking as the poison will be properly inserted at page
* allocation time. The only corner case is when pages are allocated by
* 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)
{
if (!static_branch_unlikely(&deferred_pages))
kasan_free_pages(page, order);
}
/* Returns true if the struct page for the pfn is uninitialised */
static inline bool __meminit early_page_uninitialised(unsigned long pfn)
{
int nid = early_pfn_to_nid(pfn);
if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
return true;
return false;
}
/*
* Returns true when the remaining initialisation should be deferred until
* later in the boot cycle when it can be parallelised.
*/
static bool __meminit
defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
{
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;
}
/* Always populate low zones for address-constrained allocations */
if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
return false;
/*
* 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 early_page_uninitialised(unsigned long pfn)
{
return false;
}
static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
{
return false;
}
#endif
/* Return a pointer to the bitmap storing bits affecting a block of pages */
static inline unsigned long *get_pageblock_bitmap(struct page *page,
unsigned long pfn)
{
#ifdef CONFIG_SPARSEMEM
return section_to_usemap(__pfn_to_section(pfn));
#else
return page_zone(page)->pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
}
static inline int pfn_to_bitidx(struct page *page, unsigned long pfn)
{
#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 */
}
/**
* 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,
unsigned long pfn,
unsigned long end_bitidx,
unsigned long mask)
{
unsigned long *bitmap;
unsigned long bitidx, word_bitidx;
unsigned long word;
bitmap = get_pageblock_bitmap(page, pfn);
bitidx = pfn_to_bitidx(page, pfn);
word_bitidx = bitidx / BITS_PER_LONG;
bitidx &= (BITS_PER_LONG-1);
word = bitmap[word_bitidx];
bitidx += end_bitidx;
return (word >> (BITS_PER_LONG - bitidx - 1)) & 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);
}
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);
}
/**
* set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
* @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;
unsigned long bitidx, word_bitidx;
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);
word_bitidx = bitidx / BITS_PER_LONG;
bitidx &= (BITS_PER_LONG-1);
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);
word = READ_ONCE(bitmap[word_bitidx]);
for (;;) {
old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags);
if (word == old_word)
break;
word = old_word;
}
}
void set_pageblock_migratetype(struct page *page, int migratetype)
{
if (unlikely(page_group_by_mobility_disabled &&
migratetype < MIGRATE_PCPTYPES))
migratetype = MIGRATE_UNMOVABLE;
set_pageblock_flags_group(page, (unsigned long)migratetype,
PB_migrate, PB_migrate_end);
}
#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
{
int ret = 0;
unsigned seq;
unsigned long pfn = page_to_pfn(page);
unsigned long sp, start_pfn;
do {
seq = zone_span_seqbegin(zone);
start_pfn = zone->zone_start_pfn;
sp = zone->spanned_pages;
if (!zone_spans_pfn(zone, pfn))
ret = 1;
} while (zone_span_seqretry(zone, seq));
if (ret)
pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n",
pfn, zone_to_nid(zone), zone->name,
start_pfn, start_pfn + sp);
return ret;
}
static int page_is_consistent(struct zone *zone, struct page *page)
{
if (!pfn_valid_within(page_to_pfn(page)))
return 0;
if (zone != page_zone(page))
return 0;
return 1;
}
/*
* Temporary debugging check for pages not lying within a given zone.
*/
static int __maybe_unused bad_range(struct zone *zone, struct page *page)
{
if (page_outside_zone_boundaries(zone, page))
return 1;
if (!page_is_consistent(zone, page))
return 1;
return 0;
}
#else
static inline int __maybe_unused bad_range(struct zone *zone, struct page *page)
{
return 0;
}
#endif
static void bad_page(struct page *page, const char *reason,
unsigned long bad_flags)
{
static unsigned long resume;
static unsigned long nr_shown;
static unsigned long nr_unshown;
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
*/
if (nr_shown == 60) {
if (time_before(jiffies, resume)) {
nr_unshown++;
goto out;
}
if (nr_unshown) {
pr_alert(
"BUG: Bad page state: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
}
nr_shown = 0;
}
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
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();
dump_stack();
out:
/* Leave bad fields for debug, except PageBuddy could make trouble */
page_mapcount_reset(page); /* remove PageBuddy */
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
/*
* Higher-order pages are called "compound pages". They are structured thusly:
*
* The first PAGE_SIZE page is called the "head page" and have PG_head set.
*
* The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded
* in bit 0 of page->compound_head. The rest of bits is pointer to head page.
*
* The first tail page's ->compound_dtor holds the offset in array of compound
* page destructors. See compound_page_dtors.
*
* The first tail page's ->compound_order holds the order of allocation.
* This usage means that zero-order pages may not be compound.
*/
void free_compound_page(struct page *page)
{
mem_cgroup_uncharge(page);
__free_pages_ok(page, compound_order(page));
}
void prep_compound_page(struct page *page, unsigned int order)
{
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;
set_page_count(p, 0);
p->mapping = TAIL_MAPPING;
set_compound_head(p, page);
}
atomic_set(compound_mapcount_ptr(page), -1);
}
#ifdef CONFIG_DEBUG_PAGEALLOC
unsigned int _debug_guardpage_minorder;
#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT
DEFINE_STATIC_KEY_TRUE(_debug_pagealloc_enabled);
#else
DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
#endif
EXPORT_SYMBOL(_debug_pagealloc_enabled);
DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
static int __init early_debug_pagealloc(char *buf)
{
bool enable = false;
if (kstrtobool(buf, &enable))
return -EINVAL;
if (enable)
static_branch_enable(&_debug_pagealloc_enabled);
return 0;
}
early_param("debug_pagealloc", early_debug_pagealloc);
static void init_debug_guardpage(void)
{
if (!debug_pagealloc_enabled())
return;
if (!debug_guardpage_minorder())
return;
static_branch_enable(&_debug_guardpage_enabled);
}
static int __init debug_guardpage_minorder_setup(char *buf)
{
unsigned long res;
if (kstrtoul(buf, 10, &res) < 0 || res > MAX_ORDER / 2) {
pr_err("Bad debug_guardpage_minorder value\n");
return 0;
}
_debug_guardpage_minorder = res;
pr_info("Setting debug_guardpage_minorder to %lu\n", res);
return 0;
}
early_param("debug_guardpage_minorder", debug_guardpage_minorder_setup);
static inline bool set_page_guard(struct zone *zone, struct page *page,
unsigned int order, int migratetype)
{
if (!debug_guardpage_enabled())
return false;
if (order >= debug_guardpage_minorder())
return false;
__SetPageGuard(page);
INIT_LIST_HEAD(&page->lru);
set_page_private(page, order);
/* Guard pages are not available for any usage */
__mod_zone_freepage_state(zone, -(1 << order), migratetype);
return true;
}
static inline void clear_page_guard(struct zone *zone, struct page *page,
unsigned int order, int migratetype)
{
if (!debug_guardpage_enabled())
return;
__ClearPageGuard(page);
set_page_private(page, 0);
if (!is_migrate_isolate(migratetype))
__mod_zone_freepage_state(zone, (1 << order), migratetype);
}
#else
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)
{
set_page_private(page, order);
__SetPageBuddy(page);
}
/*
* This function checks whether a page is free && is the buddy
* we can coalesce a page and its buddy if
* (a) the buddy is not in a hole (check before calling!) &&
* (b) the buddy is in the buddy system &&
* (c) a page and its buddy have the same order &&
* (d) a page and its buddy are in the same zone.
*
* For recording whether a page is in the buddy system, we set PageBuddy.
* Setting, clearing, and testing PageBuddy is serialized by zone->lock.
*
* For recording page's order, we use page_private(page).
*/
static inline int 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;
VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
return 1;
}
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);
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 capc &&
!(current->flags & PF_KTHREAD) &&
!capc->page &&
capc->cc->zone == zone &&
capc->cc->direct_compaction ? 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 */
/*
* Freeing function for a buddy system allocator.
*
* The concept of a buddy system is to maintain direct-mapped table
* (containing bit values) for memory blocks of various "orders".
* The bottom level table contains the map for the smallest allocatable
* units of memory (here, pages), and each level above it describes
* pairs of units from the levels below, hence, "buddies".
* At a high level, all that happens here is marking the table entry
* at the bottom level available, and propagating the changes upward
* as necessary, plus some accounting needed to play nicely with other
* parts of the VM system.
* At each level, we keep a list of pages, which are heads of continuous
* free pages of length of (1 << order) and marked with PageBuddy.
* Page's order is recorded in page_private(page) field.
* So when we are allocating or freeing one, we can derive the state of the
* other. That is, if we allocate a small block, and both were
* free, the remainder of the region must be split into blocks.
* If a block is freed, and its buddy is also free, then this
* triggers coalescing into a block of larger size.
*
* -- nyc
*/
static inline void __free_one_page(struct page *page,
unsigned long pfn,
struct zone *zone, unsigned int order,
int migratetype)
{
unsigned long combined_pfn;
unsigned long uninitialized_var(buddy_pfn);
struct page *buddy;
unsigned int max_order;
struct capture_control *capc = task_capc(zone);
max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
VM_BUG_ON(!zone_is_initialized(zone));
VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
VM_BUG_ON(migratetype == -1);
if (likely(!is_migrate_isolate(migratetype)))
__mod_zone_freepage_state(zone, 1 << order, migratetype);
VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
VM_BUG_ON_PAGE(bad_range(zone, page), page);
continue_merging:
while (order < max_order - 1) {
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);
if (!pfn_valid_within(buddy_pfn))
goto done_merging;
if (!page_is_buddy(page, buddy, order))
goto done_merging;
/*
* 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))
clear_page_guard(zone, buddy, order, migratetype);
else
del_page_from_free_area(buddy, &zone->free_area[order]);
combined_pfn = buddy_pfn & pfn;
page = page + (combined_pfn - pfn);
pfn = combined_pfn;
order++;
}
if (max_order < MAX_ORDER) {
/* If we are here, it means order is >= pageblock_order.
* We want to prevent merge between freepages on isolate
* pageblock and normal pageblock. Without this, pageblock
* isolation could cause incorrect freepage or CMA accounting.
*
* We don't want to hit this code for the more frequent
* low-order merging.
*/
if (unlikely(has_isolate_pageblock(zone))) {
int buddy_mt;
buddy_pfn = __find_buddy_pfn(pfn, order);
buddy = page + (buddy_pfn - pfn);
buddy_mt = get_pageblock_migratetype(buddy);
if (migratetype != buddy_mt
&& (is_migrate_isolate(migratetype) ||
is_migrate_isolate(buddy_mt)))
goto done_merging;
}
max_order++;
goto continue_merging;
}
done_merging:
set_page_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)
&& !is_shuffle_order(order)) {
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)) {
add_to_free_area_tail(page, &zone->free_area[order],
migratetype);
return;
}
}
if (is_shuffle_order(order))
add_to_free_area_random(page, &zone->free_area[order],
migratetype);
else
add_to_free_area(page, &zone->free_area[order], migratetype);
}
/*
* A bad page could be due to a number of fields. Instead of multiple branches,
* try and check multiple fields with one check. The caller must do a detailed
* check if necessary.
*/
static inline bool page_expected_state(struct page *page,
unsigned long check_flags)
{
if (unlikely(atomic_read(&page->_mapcount) != -1))
return false;
if (unlikely((unsigned long)page->mapping |
page_ref_count(page) |
#ifdef CONFIG_MEMCG
(unsigned long)page->mem_cgroup |
#endif
(page->flags & check_flags)))
return false;
return true;
}
static void free_pages_check_bad(struct page *page)
{
const char *bad_reason;
unsigned long bad_flags;
bad_reason = NULL;
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 _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;
}
#ifdef CONFIG_MEMCG
if (unlikely(page->mem_cgroup))
bad_reason = "page still charged to cgroup";
#endif
bad_page(page, bad_reason, bad_flags);
}
static inline int free_pages_check(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);
return 1;
}
static int free_tail_pages_check(struct page *head_page, struct page *page)
{
int ret = 1;
/*
* We rely page->lru.next never has bit 0 set, unless the page
* is PageTail(). Let's make sure that's true even for poisoned ->lru.
*/
BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1);
if (!IS_ENABLED(CONFIG_DEBUG_VM)) {
ret = 0;
goto out;
}
switch (page - head_page) {
case 1:
/* the first tail page: ->mapping may be compound_mapcount() */
if (unlikely(compound_mapcount(page))) {
bad_page(page, "nonzero compound_mapcount", 0);
goto out;
}
break;
case 2:
/*
* the second tail page: ->mapping is
* deferred_list.next -- ignore value.
*/
break;
default:
if (page->mapping != TAIL_MAPPING) {
bad_page(page, "corrupted mapping in tail page", 0);
goto out;
}
break;
}
if (unlikely(!PageTail(page))) {
bad_page(page, "PageTail not set", 0);
goto out;
}
if (unlikely(compound_head(page) != head_page)) {
bad_page(page, "compound_head not consistent", 0);
goto out;
}
ret = 0;
out:
page->mapping = NULL;
clear_compound_head(page);
return ret;
}
static void kernel_init_free_pages(struct page *page, int numpages)
{
int i;
for (i = 0; i < numpages; i++)
clear_highpage(page + i);
}
static __always_inline bool free_pages_prepare(struct page *page,
unsigned int order, bool check_free)
{
int bad = 0;
VM_BUG_ON_PAGE(PageTail(page), page);
trace_mm_page_free(page, order);
/*
* Check tail pages before head page information is cleared to
* avoid checking PageCompound for order-0 pages.
*/
if (unlikely(order)) {
bool compound = PageCompound(page);
int i;
VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);
if (compound)
ClearPageDoubleMap(page);
for (i = 1; i < (1 << order); i++) {
if (compound)
bad += free_tail_pages_check(page, page + i);
if (unlikely(free_pages_check(page + i))) {
bad++;
continue;
}
(page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
}
}
if (PageMappingFlags(page))
page->mapping = NULL;
if (memcg_kmem_enabled() && PageKmemcg(page))
__memcg_kmem_uncharge(page, order);
if (check_free)
bad += free_pages_check(page);
if (bad)
return false;
page_cpupid_reset_last(page);
page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
reset_page_owner(page, order);
if (!PageHighMem(page)) {
debug_check_no_locks_freed(page_address(page),
PAGE_SIZE << order);
debug_check_no_obj_freed(page_address(page),
PAGE_SIZE << order);
}
if (want_init_on_free())
kernel_init_free_pages(page, 1 << order);
kernel_poison_pages(page, 1 << order, 0);
/*
* 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);
if (debug_pagealloc_enabled())
kernel_map_pages(page, 1 << order, 0);
kasan_free_nondeferred_pages(page, order);
return true;
}
#ifdef CONFIG_DEBUG_VM
/*
* With DEBUG_VM enabled, order-0 pages are checked immediately when being freed
* to pcp lists. With debug_pagealloc also enabled, they are also rechecked when
* moved from pcp lists to free lists.
*/
static bool free_pcp_prepare(struct page *page)
{
return free_pages_prepare(page, 0, true);
}
static bool bulkfree_pcp_prepare(struct page *page)
{
if (debug_pagealloc_enabled())
return free_pages_check(page);
else
return false;
}
#else
/*
* With DEBUG_VM disabled, order-0 pages being freed are checked only when
* moving from pcp lists to free list in order to reduce overhead. With
* debug_pagealloc enabled, they are checked also immediately when being freed
* to the pcp lists.
*/
static bool free_pcp_prepare(struct page *page)
{
if (debug_pagealloc_enabled())
return free_pages_prepare(page, 0, true);
else
return free_pages_prepare(page, 0, false);
}
static bool bulkfree_pcp_prepare(struct page *page)
{
return free_pages_check(page);
}
#endif /* CONFIG_DEBUG_VM */
static inline void prefetch_buddy(struct page *page)
{
unsigned long pfn = page_to_pfn(page);
unsigned long buddy_pfn = __find_buddy_pfn(pfn, 0);
struct page *buddy = page + (buddy_pfn - pfn);
prefetch(buddy);
}
/*
* 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.
*
* If the zone was previously in an "all pages pinned" state then look to
* see if this freeing clears that state.
*
* 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, int count,
struct per_cpu_pages *pcp)
{
int migratetype = 0;
int batch_free = 0;
int prefetch_nr = 0;
bool isolated_pageblocks;
struct page *page, *tmp;
LIST_HEAD(head);
while (count) {
struct list_head *list;
/*
* Remove pages from lists in a round-robin fashion. A
* batch_free count is maintained that is incremented when an
* empty list is encountered. This is so more pages are freed
* off fuller lists instead of spinning excessively around empty
* lists
*/
do {
batch_free++;
if (++migratetype == MIGRATE_PCPTYPES)
migratetype = 0;
list = &pcp->lists[migratetype];
} while (list_empty(list));
/* This is the only non-empty list. Free them all. */
if (batch_free == MIGRATE_PCPTYPES)
batch_free = count;
do {
page = list_last_entry(list, struct page, lru);
/* must delete to avoid corrupting pcp list */
list_del(&page->lru);
pcp->count--;
if (bulkfree_pcp_prepare(page))
continue;
list_add_tail(&page->lru, &head);
/*
* We are going to put the page back to the global
* pool, prefetch its buddy to speed up later access
* under zone->lock. It is believed the overhead of
* an additional test and calculating buddy_pfn here
* can be offset by reduced memory latency later. To
* avoid excessive prefetching due to large count, only
* prefetch buddy for the first pcp->batch nr of pages.
*/
if (prefetch_nr++ < pcp->batch)
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);
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)
{
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);
spin_unlock(&zone->lock);
}
static void __meminit __init_single_page(struct page *page, unsigned long pfn,
unsigned long zone, int nid)
{
mm_zero_struct_page(page);
set_page_links(page, zone, nid, pfn);
init_page_count(page);
page_mapcount_reset(page);
page_cpupid_reset_last(page);
page_kasan_tag_reset(page);
INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
/* The shift won't overflow because ZONE_NORMAL is below 4G. */
if (!is_highmem_idx(zone))
set_page_address(page, __va(pfn << PAGE_SHIFT));
#endif
}
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __meminit init_reserved_page(unsigned long pfn)
{
pg_data_t *pgdat;
int nid, zid;
if (!early_page_uninitialised(pfn))
return;
nid = early_pfn_to_nid(pfn);
pgdat = NODE_DATA(nid);
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
struct zone *zone = &pgdat->node_zones[zid];
if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
break;
}
__init_single_page(pfn_to_page(pfn), pfn, zid, nid);
}
#else
static inline void init_reserved_page(unsigned long pfn)
{
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
/*
* Initialised pages do not have PageReserved set. This function is
* called for each range allocated by the bootmem allocator and
* marks the pages PageReserved. The remaining valid pages are later
* sent to the buddy page allocator.
*/
void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long end_pfn = PFN_UP(end);
for (; start_pfn < end_pfn; start_pfn++) {
if (pfn_valid(start_pfn)) {
struct page *page = pfn_to_page(start_pfn);
init_reserved_page(start_pfn);
/* Avoid false-positive PageTail() */
INIT_LIST_HEAD(&page->lru);
/*
* 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)
{
unsigned long flags;
int migratetype;
unsigned long pfn = page_to_pfn(page);
if (!free_pages_prepare(page, order, true))
return;
migratetype = get_pfnblock_migratetype(page, pfn);
local_irq_save(flags);
__count_vm_events(PGFREE, 1 << order);
free_one_page(page_zone(page), page, pfn, order, migratetype);
local_irq_restore(flags);
}
void __free_pages_core(struct page *page, unsigned int order)
{
unsigned int nr_pages = 1 << order;
struct page *p = page;
unsigned int loop;
prefetchw(p);
for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
prefetchw(p + 1);
__ClearPageReserved(p);
set_page_count(p, 0);
}
__ClearPageReserved(p);
set_page_count(p, 0);
atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
set_page_refcounted(page);
__free_pages(page, order);
}
#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
int __meminit early_pfn_to_nid(unsigned long pfn)
{
static DEFINE_SPINLOCK(early_pfn_lock);
int nid;
spin_lock(&early_pfn_lock);
nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
if (nid < 0)
nid = first_online_node;
spin_unlock(&early_pfn_lock);
return nid;
}
#endif
#ifdef CONFIG_NODES_SPAN_OTHER_NODES
/* 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)
{
int nid;
nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
if (nid >= 0 && nid != node)
return false;
return true;
}
#else
static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
return true;
}
#endif
void __init memblock_free_pages(struct page *page, unsigned long pfn,
unsigned int order)
{
if (early_page_uninitialised(pfn))
return;
__free_pages_core(page, order);
}
/*
* Check that the whole (or subset of) a pageblock given by the interval of
* [start_pfn, end_pfn) is valid and within the same zone, before scanning it
* with the migration of free compaction scanner. The scanners then need to
* use only pfn_valid_within() check for arches that allow holes within
* pageblocks.
*
* Return struct page pointer of start_pfn, or NULL if checks were not passed.
*
* It's possible on some configurations to have a setup like node0 node1 node0
* i.e. it's possible that all pages within a zones range of pages do not
* belong to a single zone. We assume that a border between node0 and node1
* can occur within a single pageblock, but not a node0 node1 node0
* interleaving within a single pageblock. It is therefore sufficient to check
* the first and last page of a pageblock and avoid checking each individual
* page in a pageblock.
*/
struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
unsigned long end_pfn, struct zone *zone)
{
struct page *start_page;
struct page *end_page;
/* end_pfn is one past the range we are checking */
end_pfn--;
if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
return NULL;
start_page = pfn_to_online_page(start_pfn);
if (!start_page)
return NULL;
if (page_zone(start_page) != zone)
return NULL;
end_page = pfn_to_page(end_pfn);
/* This gives a shorter code than deriving page_zone(end_page) */
if (page_zone_id(start_page) != page_zone_id(end_page))
return NULL;
return start_page;
}
void set_zone_contiguous(struct zone *zone)
{
unsigned long block_start_pfn = zone->zone_start_pfn;
unsigned long block_end_pfn;
block_end_pfn = ALIGN(block_start_pfn + 1, pageblock_nr_pages);
for (; block_start_pfn < zone_end_pfn(zone);
block_start_pfn = block_end_pfn,
block_end_pfn += pageblock_nr_pages) {
block_end_pfn = min(block_end_pfn, zone_end_pfn(zone));
if (!__pageblock_pfn_to_page(block_start_pfn,
block_end_pfn, zone))
return;
}
/* We confirm that there is no hole */
zone->contiguous = true;
}
void clear_zone_contiguous(struct zone *zone)
{
zone->contiguous = false;
}
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __init deferred_free_range(unsigned long pfn,
unsigned long nr_pages)
{
struct page *page;
unsigned long i;
if (!nr_pages)
return;
page = pfn_to_page(pfn);
/* Free a large naturally-aligned chunk if possible */
if (nr_pages == pageblock_nr_pages &&
(pfn & (pageblock_nr_pages - 1)) == 0) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
__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_core(page, 0);
}
}
/* Completion tracking for deferred_init_memmap() threads */
static atomic_t pgdat_init_n_undone __initdata;
static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);
static inline void __init pgdat_init_report_one_done(void)
{
if (atomic_dec_and_test(&pgdat_init_n_undone))
complete(&pgdat_init_all_done_comp);
}
/*
* Returns true if page needs to be initialized or freed to buddy allocator.
*
* First we check if pfn is valid on architectures where it is possible to have
* holes within pageblock_nr_pages. On systems where it is not possible, this
* function is optimized out.
*
* Then, we check if a current large page is valid by only checking the validity
* of the head pfn.
*/
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;
return true;
}
/*
* Free pages to buddy allocator. Try to free aligned pages in
* pageblock_nr_pages sizes.
*/
static void __init deferred_free_pages(unsigned long pfn,
unsigned long end_pfn)
{
unsigned long nr_pgmask = pageblock_nr_pages - 1;
unsigned long nr_free = 0;
for (; pfn < end_pfn; pfn++) {
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++;
}
}
/* Free the last block of pages to allocator */
deferred_free_range(pfn - nr_free, nr_free);
}
/*
* Initialize struct pages. We minimize pfn page lookups and scheduler checks
* by performing it only once every pageblock_nr_pages.
* Return number of pages initialized.
*/
static unsigned long __init deferred_init_pages(struct zone *zone,
unsigned long pfn,
unsigned long end_pfn)
{
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(pfn)) {
page = NULL;
continue;
} else if (!page || !(pfn & nr_pgmask)) {
page = pfn_to_page(pfn);
touch_nmi_watchdog();
} else {
page++;
}
__init_single_page(page, pfn, zid, nid);
nr_pages++;
}
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;
}
/* Initialise remaining memory on a node */
static int __init deferred_init_memmap(void *data)
{
pg_data_t *pgdat = data;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
unsigned long spfn = 0, epfn = 0, nr_pages = 0;
unsigned long first_init_pfn, flags;
unsigned long start = jiffies;
struct zone *zone;
int zid;
u64 i;
/* Bind memory initialisation thread to a local node if possible */
if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(current, cpumask);
pgdat_resize_lock(pgdat, &flags);
first_init_pfn = pgdat->first_deferred_pfn;
if (first_init_pfn == ULONG_MAX) {
pgdat_resize_unlock(pgdat, &flags);
pgdat_init_report_one_done();
return 0;
}
/* Sanity check boundaries */
BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
pgdat->first_deferred_pfn = ULONG_MAX;
/* Only the highest zone is deferred so find it */
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
zone = pgdat->node_zones + zid;
if (first_init_pfn < zone_end_pfn(zone))
break;
}
/* 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;
/*
* Initialize and free pages in MAX_ORDER sized increments so
* that we can avoid introducing any issues with the buddy
* allocator.
*/
while (spfn < epfn)
nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
zone_empty:
pgdat_resize_unlock(pgdat, &flags);
/* 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",
pgdat->node_id, nr_pages, jiffies_to_msecs(jiffies - start));
pgdat_init_report_one_done();
return 0;
}
/*
* If this zone has deferred pages, try to grow it by initializing enough
* deferred pages to satisfy the allocation specified by order, rounded up to
* the nearest PAGES_PER_SECTION boundary. So we're adding memory in increments
* of SECTION_SIZE bytes by initializing struct pages in increments of
* PAGES_PER_SECTION * sizeof(struct page) bytes.
*
* Return true when zone was grown, otherwise return false. We return true even
* when we grow less than requested, to let the caller decide if there are
* enough pages to satisfy the allocation.
*
* Note: We use noinline because this function is needed only during boot, and
* it is called from a __ref function _deferred_grow_zone. This way we are
* making sure that it is not inlined into permanent text section.
*/
static noinline bool __init
deferred_grow_zone(struct zone *zone, unsigned int order)
{
unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
pg_data_t *pgdat = zone->zone_pgdat;
unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
unsigned long spfn, epfn, flags;
unsigned long nr_pages = 0;
u64 i;
/* Only the last zone may have deferred pages */
if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat))
return false;
pgdat_resize_lock(pgdat, &flags);
/*
* If deferred pages have been initialized while we were waiting for
* the lock, return true, as the zone was grown. The caller will retry
* this zone. We won't return to this function since the caller also
* has this static branch.
*/
if (!static_branch_unlikely(&deferred_pages)) {
pgdat_resize_unlock(pgdat, &flags);
return true;
}
/*
* If someone grew this zone while we were waiting for spinlock, return
* true, as there might be enough pages already.
*/
if (first_deferred_pfn != pgdat->first_deferred_pfn) {
pgdat_resize_unlock(pgdat, &flags);
return true;
}
/* 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);
/* Retry only once. */
return first_deferred_pfn != ULONG_MAX;
}
/*
* 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;
nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
/* 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;
}
pgdat->first_deferred_pfn = spfn;
pgdat_resize_unlock(pgdat, &flags);
return nr_pages > 0;
}
/*
* deferred_grow_zone() is __init, but it is called from
* get_page_from_freelist() during early boot until deferred_pages permanently
* disables this call. This is why we have refdata wrapper to avoid warning,
* and to ensure that the function body gets unloaded.
*/
static bool __ref
_deferred_grow_zone(struct zone *zone, unsigned int order)
{
return deferred_grow_zone(zone, order);
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
void __init page_alloc_init_late(void)
{
struct zone *zone;
int nid;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/* There will be num_node_state(N_MEMORY) threads */
atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
for_each_node_state(nid, N_MEMORY) {
kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
}
/* Block until all are initialised */
wait_for_completion(&pgdat_init_all_done_comp);
/*
* We initialized the rest of the deferred pages. Permanently disable
* on-demand struct page initialization.
*/
static_branch_disable(&deferred_pages);
/* Reinit limits that are based on free pages after the kernel is up */
files_maxfiles_init();
#endif
/* Discard memblock private memory */
memblock_discard();
for_each_node_state(nid, N_MEMORY)
shuffle_free_memory(NODE_DATA(nid));
for_each_populated_zone(zone)
set_zone_contiguous(zone);
#ifdef CONFIG_DEBUG_PAGEALLOC
init_debug_guardpage();
#endif
}
#ifdef CONFIG_CMA
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void __init init_cma_reserved_pageblock(struct page *page)
{
unsigned i = pageblock_nr_pages;
struct page *p = page;
do {
__ClearPageReserved(p);
set_page_count(p, 0);
} while (++p, --i);
set_pageblock_migratetype(page, MIGRATE_CMA);
if (pageblock_order >= MAX_ORDER) {
i = pageblock_nr_pages;
p = page;
do {
set_page_refcounted(p);
__free_pages(p, MAX_ORDER - 1);
p += MAX_ORDER_NR_PAGES;
} while (i -= MAX_ORDER_NR_PAGES);
} else {
set_page_refcounted(page);
__free_pages(page, pageblock_order);
}
adjust_managed_page_count(page, pageblock_nr_pages);
}
#endif
/*
* The order of subdivision here is critical for the IO subsystem.
* Please do not alter this order without good reasons and regression
* testing. Specifically, as large blocks of memory are subdivided,
* the order in which smaller blocks are delivered depends on the order
* they're subdivided in this function. This is the primary factor
* influencing the order in which pages are delivered to the IO
* subsystem according to empirical testing, and this is also justified
* by considering the behavior of a buddy system containing a single
* large block of memory acted on by a series of small allocations.
* This behavior is a critical factor in sglist merging's success.
*
* -- nyc
*/
static inline void expand(struct zone *zone, struct page *page,
int low, int high, struct free_area *area,
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]);
/*
* Mark as guard pages (or page), that will allow to
* merge back to allocator when buddy will be freed.
* Corresponding page table entries will not be touched,
* pages will stay not present in virtual address space
*/
if (set_page_guard(zone, &page[size], high, migratetype))
continue;
add_to_free_area(&page[size], area, migratetype);
set_page_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 _refcount";
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);
}
/*
* This page is about to be returned from the page allocator
*/
static inline int check_new_page(struct page *page)
{
if (likely(page_expected_state(page,
PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON)))
return 0;
check_new_page_bad(page);
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
/*
* 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)
{
if (debug_pagealloc_enabled())
return check_new_page(page);
else
return false;
}
static inline bool check_new_pcp(struct page *page)
{
return check_new_page(page);
}
#else
/*
* 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 inline bool check_new_pcp(struct page *page)
{
if (debug_pagealloc_enabled())
return check_new_page(page);
else
return false;
}
#endif /* CONFIG_DEBUG_VM */
static bool check_new_pages(struct page *page, unsigned int order)
{
int i;
for (i = 0; i < (1 << order); i++) {
struct page *p = page + i;
if (unlikely(check_new_page(p)))
return true;
}
return false;
}
inline void post_alloc_hook(struct page *page, unsigned int order,
gfp_t gfp_flags)
{
set_page_private(page, 0);
set_page_refcounted(page);
arch_alloc_page(page, order);
if (debug_pagealloc_enabled())
kernel_map_pages(page, 1 << order, 1);
kasan_alloc_pages(page, order);
kernel_poison_pages(page, 1 << order, 1);
set_page_owner(page, order, gfp_flags);
}
static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
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);
/*
* page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to
* allocate the page. The expectation is that the caller is taking
* steps that will free more memory. The caller should avoid the page
* being used for !PFMEMALLOC purposes.
*/
if (alloc_flags & ALLOC_NO_WATERMARKS)
set_page_pfmemalloc(page);
else
clear_page_pfmemalloc(page);
}
/*
* Go through the free lists for the given migratetype and remove
* the smallest available page from the freelists
*/
static __always_inline
struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
int migratetype)
{
unsigned int current_order;
struct free_area *area;
struct page *page;
/* 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 = get_page_from_free_area(area, migratetype);
if (!page)
continue;
del_page_from_free_area(page, area);
expand(zone, page, order, current_order, area, migratetype);
set_pcppage_migratetype(page, migratetype);
return page;
}
return NULL;
}
/*
* 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] = {
[MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, 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
#ifdef CONFIG_MEMORY_ISOLATION
[MIGRATE_ISOLATE] = { MIGRATE_TYPES }, /* Never used */
#endif
};
#ifdef CONFIG_CMA
static __always_inline struct page *__rmqueue_cma_fallback(struct zone *zone,
unsigned int order)
{
return __rmqueue_smallest(zone, order, MIGRATE_CMA);
}
#else
static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
unsigned int order) { return NULL; }
#endif
/*
* Move the free pages in a range to the free lists 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()
*/
static int move_freepages(struct zone *zone,
struct page *start_page, struct page *end_page,
int migratetype, int *num_movable)
{
struct page *page;
unsigned int order;
int pages_moved = 0;
for (page = start_page; page <= end_page;) {
if (!pfn_valid_within(page_to_pfn(page))) {
page++;
continue;
}
if (!PageBuddy(page)) {
/*
* We assume that pages that could be isolated for
* migration are movable. But we don't actually try
* isolating, as that would be expensive.
*/
if (num_movable &&
(PageLRU(page) || __PageMovable(page)))
(*num_movable)++;
page++;
continue;
}
/* 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 = page_order(page);
move_to_free_area(page, &zone->free_area[order], migratetype);
page += 1 << order;
pages_moved += 1 << order;
}
return pages_moved;
}
int move_freepages_block(struct zone *zone, struct page *page,
int migratetype, int *num_movable)
{
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);
start_page = pfn_to_page(start_pfn);
end_page = start_page + pageblock_nr_pages - 1;
end_pfn = start_pfn + pageblock_nr_pages - 1;
/* Do not cross zone boundaries */
if (!zone_spans_pfn(zone, start_pfn))
start_page = page;
if (!zone_spans_pfn(zone, end_pfn))
return 0;
return move_freepages(zone, start_page, end_page, migratetype,
num_movable);
}
static void change_pageblock_range(struct page *pageblock_page,
int start_order, int migratetype)
{
int nr_pageblocks = 1 << (start_order - pageblock_order);
while (nr_pageblocks--) {
set_pageblock_migratetype(pageblock_page, migratetype);
pageblock_page += pageblock_nr_pages;
}
}
/*
* When we are falling back to another migratetype during allocation, try to
* steal extra free pages from the same pageblocks to satisfy further
* allocations, instead of polluting multiple pageblocks.
*
* If we are stealing a relatively large buddy page, it is likely there will
* be more free pages in the pageblock, so try to steal them all. For
* reclaimable and unmovable allocations, we steal regardless of page size,
* as fragmentation caused by those allocations polluting movable pageblocks
* is worse than movable allocations stealing from unmovable and reclaimable
* pageblocks.
*/
static bool can_steal_fallback(unsigned int order, int start_mt)
{
/*
* Leaving this order check is intended, although there is
* relaxed order check in next check. The reason is that
* we can actually steal whole pageblock if this condition met,
* but, below check doesn't guarantee it and that is just heuristic
* so could be changed anytime.
*/
if (order >= pageblock_order)
return true;
if (order >= pageblock_order / 2 ||
start_mt == MIGRATE_RECLAIMABLE ||
start_mt == MIGRATE_UNMOVABLE ||
page_group_by_mobility_disabled)
return true;
return false;
}
static inline void boost_watermark(struct zone *zone)
{
unsigned long max_boost;
if (!watermark_boost_factor)
return;
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;
max_boost = max(pageblock_nr_pages, max_boost);
zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
max_boost);
}
/*
* This function implements actual steal behaviour. If order is large enough,
* we can steal whole pageblock. If not, we first move freepages in this
* pageblock to our migratetype and determine how many already-allocated pages
* are there in the pageblock with a compatible migratetype. If at least half
* of pages are free or compatible, we can change migratetype of the pageblock
* 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,
unsigned int alloc_flags, int start_type, bool whole_block)
{
unsigned int current_order = page_order(page);
struct free_area *area;
int free_pages, movable_pages, alike_pages;
int old_block_type;
old_block_type = get_pageblock_migratetype(page);
/*
* This can happen due to races and we want to prevent broken
* highatomic accounting.
*/
if (is_migrate_highatomic(old_block_type))
goto single_page;
/* Take ownership for orders >= pageblock_order */
if (current_order >= pageblock_order) {
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.
*/
boost_watermark(zone);
if (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)
goto single_page;
free_pages = move_freepages_block(zone, page, start_type,
&movable_pages);
/*
* Determine how many pages are compatible with our allocation.
* For movable allocation, it's the number of movable pages which
* we just obtained. For other types it's a bit more tricky.
*/
if (start_type == MIGRATE_MOVABLE) {
alike_pages = movable_pages;
} else {
/*
* If we are falling back a RECLAIMABLE or UNMOVABLE allocation
* to MOVABLE pageblock, consider all non-movable pages as
* compatible. If it's UNMOVABLE falling back to RECLAIMABLE or
* vice versa, be conservative since we can't distinguish the
* exact migratetype of non-movable pages.
*/
if (old_block_type == MIGRATE_MOVABLE)
alike_pages = pageblock_nr_pages
- (free_pages + movable_pages);
else
alike_pages = 0;
}
/* moving whole block can fail due to zone boundary conditions */
if (!free_pages)
goto single_page;
/*
* If a sufficient number of pages in the block are either free or of
* comparable migratability as our allocation, claim the whole block.
*/
if (free_pages + alike_pages >= (1 << (pageblock_order-1)) ||
page_group_by_mobility_disabled)
set_pageblock_migratetype(page, start_type);
return;
single_page:
area = &zone->free_area[current_order];
move_to_free_area(page, area, start_type);
}
/*
* Check whether there is a suitable fallback freepage with requested order.
* If only_stealable is true, this function returns fallback_mt only if
* we can steal other freepages all together. This would help to reduce
* fragmentation due to mixed migratetype pages in one pageblock.
*/
int find_suitable_fallback(struct free_area *area, unsigned int order,
int migratetype, bool only_stealable, bool *can_steal)
{
int i;
int fallback_mt;
if (area->nr_free == 0)
return -1;
*can_steal = false;
for (i = 0;; i++) {
fallback_mt = fallbacks[migratetype][i];
if (fallback_mt == MIGRATE_TYPES)
break;
if (free_area_empty(area, fallback_mt))
continue;
if (can_steal_fallback(order, migratetype))
*can_steal = true;
if (!only_stealable)
return fallback_mt;
if (*can_steal)
return fallback_mt;
}
return -1;
}
/*
* Reserve a pageblock for exclusive use of high-order atomic allocations if
* there are no empty page blocks that contain a page with a suitable order
*/
static void reserve_highatomic_pageblock(struct page *page, struct zone *zone,
unsigned int alloc_order)
{
int mt;
unsigned long max_managed, flags;
/*
* Limit the number reserved to 1 pageblock or roughly 1% of a zone.
* Check is race-prone but harmless.
*/
max_managed = (zone_managed_pages(zone) / 100) + pageblock_nr_pages;
if (zone->nr_reserved_highatomic >= max_managed)
return;
spin_lock_irqsave(&zone->lock, flags);
/* Recheck the nr_reserved_highatomic limit under the lock */
if (zone->nr_reserved_highatomic >= max_managed)
goto out_unlock;
/* Yoink! */
mt = get_pageblock_migratetype(page);
if (!is_migrate_highatomic(mt) && !is_migrate_isolate(mt)
&& !is_migrate_cma(mt)) {
zone->nr_reserved_highatomic += pageblock_nr_pages;
set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC);
move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL);
}
out_unlock:
spin_unlock_irqrestore(&zone->lock, flags);
}
/*
* Used when an allocation is about to fail under memory pressure. This
* potentially hurts the reliability of high-order allocations when under
* intense memory pressure but failed atomic allocations should be easier
* to recover from than an OOM.
*
* If @force is true, try to unreserve a pageblock even though highatomic
* pageblock is exhausted.
*/
static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
bool force)
{
struct zonelist *zonelist = ac->zonelist;
unsigned long flags;
struct zoneref *z;
struct zone *zone;
struct page *page;
int order;
bool ret;
for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx,
ac->nodemask) {
/*
* Preserve at least one pageblock unless memory pressure
* is really high.
*/
if (!force && zone->nr_reserved_highatomic <=
pageblock_nr_pages)
continue;
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
struct free_area *area = &(zone->free_area[order]);
page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC);
if (!page)
continue;
/*
* In page freeing path, migratetype change is racy so
* we can counter several free pages in a pageblock
* in this loop althoug we changed the pageblock type
* from highatomic to ac->migratetype. So we should
* adjust the count once.
*/
if (is_migrate_highatomic_page(page)) {
/*
* It should never happen but changes to
* locking could inadvertently allow a per-cpu
* drain to add pages to MIGRATE_HIGHATOMIC
* while unreserving so be safe and watch for
* underflows.
*/
zone->nr_reserved_highatomic -= min(
pageblock_nr_pages,
zone->nr_reserved_highatomic);
}
/*
* Convert to ac->migratetype and avoid the normal
* pageblock stealing heuristics. Minimally, the caller
* is doing the work and needs the pages. More
* importantly, if the block was always converted to
* MIGRATE_UNMOVABLE or another type then the number
* of pageblocks that cannot be completely freed
* may increase.
*/
set_pageblock_migratetype(page, ac->migratetype);
ret = move_freepages_block(zone, page, ac->migratetype,
NULL);
if (ret) {
spin_unlock_irqrestore(&zone->lock, flags);
return ret;
}
}
spin_unlock_irqrestore(&zone->lock, flags);
}
return false;
}
/*
* Try finding a free buddy page on the fallback list and put it on the free
* list of requested migratetype, possibly along with other pages from the same
* block, depending on fragmentation avoidance heuristics. Returns true if
* fallback was found so that __rmqueue_smallest() can grab it.
*
* The use of signed ints for order and current_order is a deliberate
* deviation from the rest of this file, to make the for loop
* condition simpler.
*/
static __always_inline bool
__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 >= min_order;
--current_order) {
area = &(zone->free_area[current_order]);
fallback_mt = find_suitable_fallback(area, current_order,
start_migratetype, false, &can_steal);
if (fallback_mt == -1)
continue;
/*
* We cannot steal all free pages from the pageblock and the
* requested migratetype is movable. In that case it's better to
* steal and split the smallest available page instead of the
* largest available page, because even if the next movable
* allocation falls back into a different pageblock than this
* one, it won't cause permanent fragmentation.
*/
if (!can_steal && start_migratetype == MIGRATE_MOVABLE
&& current_order > order)
goto find_smallest;
goto do_steal;
}
return false;
find_smallest:
for (current_order = order; current_order < MAX_ORDER;
current_order++) {
area = &(zone->free_area[current_order]);
fallback_mt = find_suitable_fallback(area, current_order,
start_migratetype, false, &can_steal);
if (fallback_mt != -1)
break;
}
/*
* This should not happen - we already found a suitable fallback
* when looking for the largest page.
*/
VM_BUG_ON(current_order == MAX_ORDER);
do_steal:
page = get_page_from_free_area(area, fallback_mt);
steal_suitable_fallback(zone, page, alloc_flags, start_migratetype,
can_steal);
trace_mm_page_alloc_extfrag(page, order, current_order,
start_migratetype, fallback_mt);
return true;
}
/*
* Do the hard work of removing an element from the buddy allocator.
* Call me with the zone->lock already held.
*/
static __always_inline struct page *
__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)) {
if (migratetype == MIGRATE_MOVABLE)
page = __rmqueue_cma_fallback(zone, order);
if (!page && __rmqueue_fallback(zone, order, migratetype,
alloc_flags))
goto retry;
}
trace_mm_page_alloc_zone_locked(page, order, migratetype);
return page;
}
/*
* Obtain a specified number of elements from the buddy allocator, all under
* a single hold of the lock, for efficiency. Add them to the supplied list.
* Returns the number of new pages which were placed at *list.
*/
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
int migratetype, unsigned int alloc_flags)
{
int i, alloced = 0;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
struct page *page = __rmqueue(zone, order, migratetype,
alloc_flags);
if (unlikely(page == NULL))
break;
if (unlikely(check_pcp_refill(page)))
continue;
/*
* Split buddy pages returned by expand() are received here in
* physical page order. The page is added to the tail of
* caller's list. From the callers perspective, the linked list
* is ordered by page number under some conditions. This is
* useful for IO devices that can forward direction from the
* head, thus also in the physical page order. This is useful
* for IO devices that can merge IO requests if the physical
* pages are ordered properly.
*/
list_add_tail(&page->lru, list);
alloced++;
if (is_migrate_cma(get_pcppage_migratetype(page)))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
-(1 << order));
}
/*
* i pages were removed from the buddy list even if some leak due
* to check_pcp_refill failing so adjust NR_FREE_PAGES based
* on i. Do not confuse with 'alloced' which is the number of
* pages added to the pcp list.
*/
__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
spin_unlock(&zone->lock);
return alloced;
}
#ifdef CONFIG_NUMA
/*
* Called from the vmstat counter updater to drain pagesets of this
* currently executing processor on remote nodes after they have
* expired.
*
* Note that this function must be called with the thread pinned to
* a single processor.
*/
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
{
unsigned long flags;
int to_drain, batch;
local_irq_save(flags);
batch = READ_ONCE(pcp->batch);
to_drain = min(pcp->count, batch);
if (to_drain > 0)
free_pcppages_bulk(zone, to_drain, pcp);
local_irq_restore(flags);
}
#endif
/*
* Drain pcplists of the indicated processor and zone.
*
* The processor must either be the current processor and the
* thread pinned to the current processor or a processor that
* is not online.
*/
static void drain_pages_zone(unsigned int cpu, struct zone *zone)
{
unsigned long flags;
struct per_cpu_pageset *pset;
struct per_cpu_pages *pcp;
local_irq_save(flags);
pset = per_cpu_ptr(zone->pageset, cpu);
pcp = &pset->pcp;
if (pcp->count)
free_pcppages_bulk(zone, pcp->count, pcp);
local_irq_restore(flags);
}
/*
* Drain pcplists of all zones on the indicated processor.
*
* The processor must either be the current processor and the
* thread pinned to the current processor or a processor that
* is not online.
*/
static void drain_pages(unsigned int cpu)
{
struct zone *zone;
for_each_populated_zone(zone) {
drain_pages_zone(cpu, zone);
}
}
/*
* Spill all of this CPU's per-cpu pages back into the buddy allocator.
*
* The CPU has to be pinned. When zone parameter is non-NULL, spill just
* the single zone's pages.
*/
void drain_local_pages(struct zone *zone)
{
int cpu = smp_processor_id();
if (zone)
drain_pages_zone(cpu, zone);
else
drain_pages(cpu);
}
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
* a cpu pinned worker to an unbound one. We can operate on a different
* cpu which is allright but we also have to make sure to not move to
* a different one.
*/
preempt_disable();
drain_local_pages(drain->zone);
preempt_enable();
}
/*
* Spill all the per-cpu pages from all CPUs back into the buddy allocator.
*
* When zone parameter is non-NULL, spill just the single zone's pages.
*
* Note that this can be extremely slow as the draining happens in a workqueue.
*/
void drain_all_pages(struct zone *zone)
{
int cpu;
/*
* Allocate in the BSS so we wont require allocation in
* direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
*/
static cpumask_t cpus_with_pcps;
/*
* Make sure nobody triggers this path before mm_percpu_wq is fully
* initialized.
*/
if (WARN_ON_ONCE(!mm_percpu_wq))
return;
/*
* Do not drain if one is already in progress unless it's specific to
* a zone. Such callers are primarily CMA and memory hotplug and need
* the drain to be complete when the call returns.
*/
if (unlikely(!mutex_trylock(&pcpu_drain_mutex))) {
if (!zone)
return;
mutex_lock(&pcpu_drain_mutex);
}
/*
* We don't care about racing with CPU hotplug event
* as offline notification will cause the notified
* cpu to drain that CPU pcps and on_each_cpu_mask
* disables preemption as part of its processing
*/
for_each_online_cpu(cpu) {
struct per_cpu_pageset *pcp;
struct zone *z;
bool has_pcps = false;
if (zone) {
pcp = per_cpu_ptr(zone->pageset, cpu);
if (pcp->pcp.count)
has_pcps = true;
} else {
for_each_populated_zone(z) {
pcp = per_cpu_ptr(z->pageset, cpu);
if (pcp->pcp.count) {
has_pcps = true;
break;
}
}
}
if (has_pcps)
cpumask_set_cpu(cpu, &cpus_with_pcps);
else
cpumask_clear_cpu(cpu, &cpus_with_pcps);
}
for_each_cpu(cpu, &cpus_with_pcps) {
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)->work);
mutex_unlock(&pcpu_drain_mutex);
}
#ifdef CONFIG_HIBERNATION
/*
* Touch the watchdog for every WD_PAGE_COUNT pages.
*/
#define WD_PAGE_COUNT (128*1024)
void mark_free_pages(struct zone *zone)
{
unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT;
unsigned long flags;
unsigned int order, t;
struct page *page;
if (zone_is_empty(zone))
return;
spin_lock_irqsave(&zone->lock, flags);
max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
if (!--page_count) {
touch_nmi_watchdog();
page_count = WD_PAGE_COUNT;
}
if (page_zone(page) != zone)
continue;
if (!swsusp_page_is_forbidden(page))
swsusp_unset_page_free(page);
}
for_each_migratetype_order(order, t) {
list_for_each_entry(page,
&zone->free_area[order].free_list[t], lru) {
unsigned long i;
pfn = page_to_pfn(page);
for (i = 0; i < (1UL << order); i++) {
if (!--page_count) {
touch_nmi_watchdog();
page_count = WD_PAGE_COUNT;
}
swsusp_set_page_free(pfn_to_page(pfn + i));
}
}
}
spin_unlock_irqrestore(&zone->lock, flags);
}
#endif /* CONFIG_PM */
static bool free_unref_page_prepare(struct page *page, unsigned long pfn)
{
int migratetype;
if (!free_pcp_prepare(page))
return false;
migratetype = get_pfnblock_migratetype(page, pfn);
set_pcppage_migratetype(page, migratetype);
return true;
}
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;
migratetype = get_pcppage_migratetype(page);
__count_vm_event(PGFREE);
/*
* We only track unmovable, reclaimable and movable on pcp lists.
* Free ISOLATE pages back to the allocator because they are being
* offlined but treat HIGHATOMIC as movable pages so we can get those
* areas back if necessary. Otherwise, we may have to free
* excessively into the page allocator
*/
if (migratetype >= MIGRATE_PCPTYPES) {
if (unlikely(is_migrate_isolate(migratetype))) {
free_one_page(zone, page, pfn, 0, migratetype);
return;
}
migratetype = MIGRATE_MOVABLE;
}
pcp = &this_cpu_ptr(zone->pageset)->pcp;
list_add(&page->lru, &pcp->lists[migratetype]);
pcp->count++;
if (pcp->count >= pcp->high) {
unsigned long batch = READ_ONCE(pcp->batch);
free_pcppages_bulk(zone, batch, pcp);
}
}
/*
* Free a 0-order page
*/
void free_unref_page(struct page *page)
{
unsigned long flags;
unsigned long pfn = page_to_pfn(page);
if (!free_unref_page_prepare(page, pfn))
return;
local_irq_save(flags);
free_unref_page_commit(page, pfn);
local_irq_restore(flags);
}
/*
* Free a list of 0-order pages
*/
void free_unref_page_list(struct list_head *list)
{
struct page *page, *next;
unsigned long flags, pfn;
int batch_count = 0;
/* Prepare pages for freeing */
list_for_each_entry_safe(page, next, list, lru) {
pfn = page_to_pfn(page);
if (!free_unref_page_prepare(page, pfn))
list_del(&page->lru);
set_page_private(page, pfn);
}
local_irq_save(flags);
list_for_each_entry_safe(page, next, list, lru) {
unsigned long pfn = page_private(page);
set_page_private(page, 0);
trace_mm_page_free_batched(page);
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_irq_restore(flags);
batch_count = 0;
local_irq_save(flags);
}
}
local_irq_restore(flags);
}
/*
* split_page takes a non-compound higher-order page, and splits it into
* n (1<<order) sub-pages: page[0..n]
* Each sub-page must be freed individually.
*
* Note: this is probably too low level an operation for use in drivers.
* Please consult with lkml before using this in your driver.
*/
void split_page(struct page *page, unsigned int order)
{
int i;
VM_BUG_ON_PAGE(PageCompound(page), page);
VM_BUG_ON_PAGE(!page_count(page), page);
for (i = 1; i < (1 << order); i++)
set_page_refcounted(page + i);
split_page_owner(page, order);
}
EXPORT_SYMBOL_GPL(split_page);
int __isolate_free_page(struct page *page, unsigned int order)
{
struct free_area *area = &page_zone(page)->free_area[order];
unsigned long watermark;
struct zone *zone;
int mt;
BUG_ON(!PageBuddy(page));
zone = page_zone(page);
mt = get_pageblock_migratetype(page);
if (!is_migrate_isolate(mt)) {
/*
* Obey watermarks as if the page was being allocated. We can
* emulate a high-order watermark check with a raised order-0
* watermark, because we already know our high-order page
* exists.
*/
watermark = zone->_watermark[WMARK_MIN] + (1UL << order);
if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
return 0;
__mod_zone_freepage_state(zone, -(1UL << order), mt);
}
/* Remove page from free list */
del_page_from_free_area(page, area);
/*
* Set the pageblock if the isolated page is at least half of a
* pageblock
*/
if (order >= pageblock_order - 1) {
struct page *endpage = page + (1 << order) - 1;
for (; page < endpage; page += pageblock_nr_pages) {
int mt = get_pageblock_migratetype(page);
if (!is_migrate_isolate(mt) && !is_migrate_cma(mt)
&& !is_migrate_highatomic(mt))
set_pageblock_migratetype(page,
MIGRATE_MOVABLE);
}
}
return 1UL << order;
}
/*
* Update NUMA hit/miss statistics
*
* Must be called with interrupts disabled.
*/
static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
{
#ifdef CONFIG_NUMA
enum numa_stat_item local_stat = NUMA_LOCAL;
/* skip numa counters update if numa stats is disabled */
if (!static_branch_likely(&vm_numa_stat_key))
return;
if (zone_to_nid(z) != numa_node_id())
local_stat = NUMA_OTHER;
if (zone_to_nid(z) == zone_to_nid(preferred_zone))
__inc_numa_state(z, NUMA_HIT);
else {
__inc_numa_state(z, NUMA_MISS);
__inc_numa_state(preferred_zone, NUMA_FOREIGN);
}
__inc_numa_state(z, local_stat);
#endif
}
/* 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,
struct list_head *list)
{
struct page *page;
do {
if (list_empty(list)) {
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, list,
migratetype, alloc_flags);
if (unlikely(list_empty(list)))
return NULL;
}
page = list_first_entry(list, struct page, lru);
list_del(&page->lru);
pcp->count--;
} while (check_new_pcp(page));
return page;
}
/* Lock and remove page from the per-cpu list */
static struct page *rmqueue_pcplist(struct zone *preferred_zone,
struct zone *zone, gfp_t gfp_flags,
int migratetype, unsigned int alloc_flags)
{
struct per_cpu_pages *pcp;
struct list_head *list;
struct page *page;
unsigned long flags;
local_irq_save(flags);
pcp = &this_cpu_ptr(zone->pageset)->pcp;
list = &pcp->lists[migratetype];
page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list);
if (page) {
__count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
zone_statistics(preferred_zone, zone);
}
local_irq_restore(flags);
return page;
}
/*
* Allocate a page from the given zone. Use pcplists for order-0 allocations.
*/
static inline
struct page *rmqueue(struct zone *preferred_zone,
struct zone *zone, unsigned int order,
gfp_t gfp_flags, unsigned int alloc_flags,
int migratetype)
{
unsigned long flags;
struct page *page;
if (likely(order == 0)) {
page = rmqueue_pcplist(preferred_zone, zone, gfp_flags,
migratetype, alloc_flags);
goto out;
}
/*
* We most definitely don't want callers attempting to
* allocate greater than order-1 page units with __GFP_NOFAIL.
*/
WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
spin_lock_irqsave(&zone->lock, flags);
do {
page = NULL;
if (alloc_flags & ALLOC_HARDER) {
page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
if (page)
trace_mm_page_alloc_zone_locked(page, order, migratetype);
}
if (!page)
page = __rmqueue(zone, order, migratetype, alloc_flags);
} while (page && check_new_pages(page, order));
spin_unlock(&zone->lock);
if (!page)
goto failed;
__mod_zone_freepage_state(zone, -(1 << order),
get_pcppage_migratetype(page));
__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
zone_statistics(preferred_zone, zone);
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_irq_restore(flags);
return NULL;
}
#ifdef CONFIG_FAIL_PAGE_ALLOC
static struct {
struct fault_attr attr;
bool ignore_gfp_highmem;
bool ignore_gfp_reclaim;
u32 min_order;
} fail_page_alloc = {
.attr = FAULT_ATTR_INITIALIZER,
.ignore_gfp_reclaim = true,
.ignore_gfp_highmem = true,
.min_order = 1,
};
static int __init setup_fail_page_alloc(char *str)
{
return setup_fault_attr(&fail_page_alloc.attr, str);
}
__setup("fail_page_alloc=", setup_fail_page_alloc);
static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
if (order < fail_page_alloc.min_order)
return false;
if (gfp_mask & __GFP_NOFAIL)
return false;
if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
return false;
if (fail_page_alloc.ignore_gfp_reclaim &&
(gfp_mask & __GFP_DIRECT_RECLAIM))
return false;
return should_fail(&fail_page_alloc.attr, 1 << order);
}
#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
static int __init fail_page_alloc_debugfs(void)
{
umode_t mode = S_IFREG | 0600;
struct dentry *dir;
dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
&fail_page_alloc.attr);
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;
}
late_initcall(fail_page_alloc_debugfs);
#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
#else /* CONFIG_FAIL_PAGE_ALLOC */
static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
return false;
}
#endif /* CONFIG_FAIL_PAGE_ALLOC */
static 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);
/*
* Return true if free base pages are above 'mark'. For high-order checks it
* will return true of the order-0 watermark is reached and there is at least
* one free page of a suitable size. Checking now avoids taking the zone lock
* 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,
long free_pages)
{
long min = mark;
int o;
const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
/* free_pages may go negative - that's OK */
free_pages -= (1 << order) - 1;
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 {
/*
* OOM victims can try even harder than normal ALLOC_HARDER
* users on the grounds that it's definitely going to be in
* the exit path shortly and free memory. Any allocation it
* makes during the free path will be small and short-lived.
*/
if (alloc_flags & ALLOC_OOM)
min -= min / 2;
else
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])
return false;
/* If this is an order-0 request then the watermark is fine */
if (!order)
return true;
/* For a high-order request, check at least one suitable page is free */
for (o = order; o < MAX_ORDER; o++) {
struct free_area *area = &z->free_area[o];
int mt;
if (!area->nr_free)
continue;
for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
if (!free_area_empty(area, mt))
return true;
}
#ifdef CONFIG_CMA
if ((alloc_flags & ALLOC_CMA) &&
!free_area_empty(area, MIGRATE_CMA)) {
return true;
}
#endif
if (alloc_harder &&
!list_empty(&area->free_list[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)
{
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
zone_page_state(z, NR_FREE_PAGES));
}
static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx, unsigned int alloc_flags)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
long cma_pages = 0;
#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
/*
* 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.
*/
if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
return true;
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
free_pages);
}
bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx)
{
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,
free_pages);
}
#ifdef CONFIG_NUMA
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
node_reclaim_distance;
}
#else /* CONFIG_NUMA */
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return true;
}
#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 = 0;
if (gfp_mask & __GFP_KSWAPD_RECLAIM)
alloc_flags |= ALLOC_KSWAPD;
#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;
}
/*
* get_page_from_freelist goes through the zonelist trying to allocate
* a page.
*/
static struct page *
get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
const struct alloc_context *ac)
{
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.
*/
no_fallback = alloc_flags & ALLOC_NOFRAGMENT;
z = ac->preferred_zoneref;
for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
ac->nodemask) {
struct page *page;
unsigned long mark;
if (cpusets_enabled() &&
(alloc_flags & ALLOC_CPUSET) &&
!__cpuset_zone_allowed(zone, gfp_mask))
continue;
/*
* When allocating a page cache page for writing, we
* want to get it from a node that is within its dirty
* limit, such that no single node holds more than its
* proportional share of globally allowed dirty pages.
* The dirty limits take into account the node's
* lowmem reserves and high watermark so that kswapd
* should be able to balance it without having to
* write pages from its LRU list.
*
* XXX: For now, allow allocations to potentially
* exceed the per-node dirty limit in the slowpath
* (spread_dirty_pages unset) before going into reclaim,
* which is important when on a NUMA setup the allowed
* nodes are together not big enough to reach the
* global limit. The proper fix for these situations
* will require awareness of nodes in the
* dirty-throttling and the flusher threads.
*/
if (ac->spread_dirty_pages) {
if (last_pgdat_dirty_limit == zone->zone_pgdat)
continue;
if (!node_dirty_ok(zone->zone_pgdat)) {
last_pgdat_dirty_limit = zone->zone_pgdat;
continue;
}
}
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)) {
int ret;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
* Watermark failed for this zone, but see if we can
* grow this zone if it contains deferred pages.
*/
if (static_branch_unlikely(&deferred_pages)) {
if (_deferred_grow_zone(zone, order))
goto try_this_zone;
}
#endif
/* Checked here to keep the fast path fast */
BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
if (alloc_flags & ALLOC_NO_WATERMARKS)
goto try_this_zone;
if (node_reclaim_mode == 0 ||
!zone_allows_reclaim(ac->preferred_zoneref->zone, zone))
continue;
ret = node_reclaim(zone->zone_pgdat, gfp_mask, order);
switch (ret) {
case NODE_RECLAIM_NOSCAN:
/* did not scan */
continue;
case NODE_RECLAIM_FULL:
/* scanned but unreclaimable */
continue;
default:
/* did we reclaim enough */
if (zone_watermark_ok(zone, order, mark,
ac_classzone_idx(ac), alloc_flags))
goto try_this_zone;
continue;
}
}
try_this_zone:
page = rmqueue(ac->preferred_zoneref->zone, zone, order,
gfp_mask, alloc_flags, ac->migratetype);
if (page) {
prep_new_page(page, order, gfp_mask, alloc_flags);
/*
* If this is a high-order atomic allocation then check
* if the pageblock should be reserved for the future
*/
if (unlikely(order && (alloc_flags & ALLOC_HARDER)))
reserve_highatomic_pageblock(page, zone, order);
return page;
} else {
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/* Try again if zone has deferred pages */
if (static_branch_unlikely(&deferred_pages)) {
if (_deferred_grow_zone(zone, order))
goto try_this_zone;
}
#endif
}
}
/*
* 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;
}
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 (!__ratelimit(&show_mem_rs))
return;
/*
* This documents exceptions given to allocations in certain
* contexts that are allowed to allocate outside current's set
* of allowed nodes.
*/
if (!(gfp_mask & __GFP_NOMEMALLOC))
if (tsk_is_oom_victim(current) ||
(current->flags & (PF_MEMALLOC | PF_EXITING)))
filter &= ~SHOW_MEM_FILTER_NODES;
if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
filter &= ~SHOW_MEM_FILTER_NODES;
show_mem(filter, nodemask);
}
void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
return;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
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);
}
static inline struct page *
__alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order,
unsigned int alloc_flags,
const struct alloc_context *ac)
{
struct page *page;
page = get_page_from_freelist(gfp_mask, order,
alloc_flags|ALLOC_CPUSET, ac);
/*
* fallback to ignore cpuset restriction if our nodes
* are depleted
*/
if (!page)
page = get_page_from_freelist(gfp_mask, order,
alloc_flags, ac);
return page;
}
static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac, unsigned long *did_some_progress)
{
struct oom_control oc = {
.zonelist = ac->zonelist,
.nodemask = ac->nodemask,
.memcg = NULL,
.gfp_mask = gfp_mask,
.order = order,
};
struct page *page;
*did_some_progress = 0;
/*
* Acquire the oom lock. If that fails, somebody else is
* making progress for us.
*/
if (!mutex_trylock(&oom_lock)) {
*did_some_progress = 1;
schedule_timeout_uninterruptible(1);
return NULL;
}
/*
* Go through the zonelist yet one more time, keep very high watermark
* here, this is only to catch a parallel oom killing, we must fail if
* we're still under heavy pressure. But make sure that this reclaim
* attempt shall not depend on __GFP_DIRECT_RECLAIM && !__GFP_NORETRY
* allocation which will never fail due to oom_lock already held.
*/
page = get_page_from_freelist((gfp_mask | __GFP_HARDWALL) &
~__GFP_DIRECT_RECLAIM, order,
ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);
if (page)
goto out;
/* Coredumps can quickly deplete all memory reserves */
if (current->flags & PF_DUMPCORE)
goto out;
/* The OOM killer will not help higher order allocs */
if (order > PAGE_ALLOC_COSTLY_ORDER)
goto out;
/*
* We have already exhausted all our reclaim opportunities without any
* 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.
*/
if (gfp_mask & __GFP_RETRY_MAYFAIL)
goto out;
/* The OOM killer does not needlessly kill tasks for lowmem */
if (ac->high_zoneidx < ZONE_NORMAL)
goto out;
if (pm_suspended_storage())
goto out;
/*
* XXX: GFP_NOFS allocations should rather fail than rely on
* other request to make a forward progress.
* We are in an unfortunate situation where out_of_memory cannot
* do much for this context but let's try it to at least get
* access to memory reserved if the current task is killed (see
* 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)) {
*did_some_progress = 1;
/*
* Help non-failing allocations by giving them access to memory
* reserves
*/
if (gfp_mask & __GFP_NOFAIL)
page = __alloc_pages_cpuset_fallback(gfp_mask, order,
ALLOC_NO_WATERMARKS, ac);
}
out:
mutex_unlock(&oom_lock);
return page;
}
/*
* Maximum number of compaction retries wit a progress before OOM
* killer is consider as the only way to move forward.
*/
#define MAX_COMPACT_RETRIES 16
#ifdef CONFIG_COMPACTION
/* Try memory compaction for high-order allocations before reclaim */
static struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
unsigned int alloc_flags, const struct alloc_context *ac,
enum compact_priority prio, enum compact_result *compact_result)
{
struct page *page = NULL;
unsigned long pflags;
unsigned int noreclaim_flag;
if (!order)
return NULL;
psi_memstall_enter(&pflags);
noreclaim_flag = memalloc_noreclaim_save();
*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
prio, &page);
memalloc_noreclaim_restore(noreclaim_flag);
psi_memstall_leave(&pflags);
/*
* At least in one zone compaction wasn't deferred or skipped, so let's
* count a compaction stall
*/
count_vm_event(COMPACTSTALL);
/* 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);
zone->compact_blockskip_flush = false;
compaction_defer_reset(zone, order, true);
count_vm_event(COMPACTSUCCESS);
return page;
}
/*
* It's bad if compaction run occurs and fails. The most likely reason
* is that pages exist, but not enough to satisfy watermarks.
*/
count_vm_event(COMPACTFAIL);
cond_resched();
return NULL;
}
static inline bool
should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
enum compact_result compact_result,
enum compact_priority *compact_priority,
int *compaction_retries)
{
int max_retries = MAX_COMPACT_RETRIES;
int min_priority;
bool ret = false;
int retries = *compaction_retries;
enum compact_priority priority = *compact_priority;
if (!order)
return false;
if (compaction_made_progress(compact_result))
(*compaction_retries)++;
/*
* compaction considers all the zone as desperately out of memory
* so it doesn't really make much sense to retry except when the
* failure could be caused by insufficient priority
*/
if (compaction_failed(compact_result))
goto check_priority;
/*
* 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_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;
}
/*
* !costly requests are much more important than __GFP_RETRY_MAYFAIL
* costly ones because they are de facto nofail and invoke OOM
* killer to move on while costly can fail and users are ready
* to cope with that. 1/4 retries is rather arbitrary but we
* would need much more detailed feedback from compaction to
* make a better decision.
*/
if (order > PAGE_ALLOC_COSTLY_ORDER)
max_retries /= 4;
if (*compaction_retries <= max_retries) {
ret = true;
goto out;
}
/*
* Make sure there are attempts at the highest priority if we exhausted
* all retries or failed at the lower priorities.
*/
check_priority:
min_priority = (order > PAGE_ALLOC_COSTLY_ORDER) ?
MIN_COMPACT_COSTLY_PRIORITY : MIN_COMPACT_PRIORITY;
if (*compact_priority > min_priority) {
(*compact_priority)--;
*compaction_retries = 0;
ret = true;
}
out:
trace_compact_retry(order, priority, compact_result, retries, max_retries, ret);
return ret;
}
#else
static inline struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
unsigned int alloc_flags, const struct alloc_context *ac,
enum compact_priority prio, enum compact_result *compact_result)
{
*compact_result = COMPACT_SKIPPED;
return NULL;
}
static inline bool
should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags,
enum compact_result compact_result,
enum compact_priority *compact_priority,
int *compaction_retries)
{
struct zone *zone;
struct zoneref *z;
if (!order || order > PAGE_ALLOC_COSTLY_ORDER)
return false;
/*
* There are setups with compaction disabled which would prefer to loop
* inside the allocator rather than hit the oom killer prematurely.
* 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) {
if (zone_watermark_ok(zone, 0, min_wmark_pages(zone),
ac_classzone_idx(ac), alloc_flags))
return true;
}
return false;
}
#endif /* CONFIG_COMPACTION */
#ifdef CONFIG_LOCKDEP
static struct lockdep_map __fs_reclaim_map =
STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
static bool __need_fs_reclaim(gfp_t gfp_mask)
{
gfp_mask = current_gfp_context(gfp_mask);
/* no reclaim without waiting on it */
if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
return false;
/* this guy won't enter reclaim */
if (current->flags & PF_MEMALLOC)
return false;
/* We're only interested __GFP_FS allocations for now */
if (!(gfp_mask & __GFP_FS))
return false;
if (gfp_mask & __GFP_NOLOCKDEP)
return false;
return true;
}
void __fs_reclaim_acquire(void)
{
lock_map_acquire(&__fs_reclaim_map);
}
void __fs_reclaim_release(void)
{
lock_map_release(&__fs_reclaim_map);
}
void fs_reclaim_acquire(gfp_t gfp_mask)
{
if (__need_fs_reclaim(gfp_mask))
__fs_reclaim_acquire();
}
EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
void fs_reclaim_release(gfp_t gfp_mask)
{
if (__need_fs_reclaim(gfp_mask))
__fs_reclaim_release();
}
EXPORT_SYMBOL_GPL(fs_reclaim_release);
#endif
/* Perform direct synchronous page reclaim */
static int
__perform_reclaim(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac)
{
int progress;
unsigned int noreclaim_flag;
unsigned long pflags;
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();
progress = try_to_free_pages(ac->zonelist, order, gfp_mask,
ac->nodemask);
memalloc_noreclaim_restore(noreclaim_flag);
fs_reclaim_release(gfp_mask);
psi_memstall_leave(&pflags);
cond_resched();
return progress;
}
/* The really slow allocator path where we enter direct reclaim */
static inline struct page *
__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
unsigned int alloc_flags, const struct alloc_context *ac,
unsigned long *did_some_progress)
{
struct page *page = NULL;
bool drained = false;
*did_some_progress = __perform_reclaim(gfp_mask, order, ac);
if (unlikely(!(*did_some_progress)))
return NULL;
retry:
page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
/*
* 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
*/
if (!page && !drained) {
unreserve_highatomic_pageblock(ac, false);
drain_all_pages(NULL);
drained = true;
goto retry;
}
return page;
}
static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
const struct alloc_context *ac)
{
struct zoneref *z;
struct zone *zone;
pg_data_t *last_pgdat = NULL;
enum zone_type high_zoneidx = ac->high_zoneidx;
for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, high_zoneidx,
ac->nodemask) {
if (last_pgdat != zone->zone_pgdat)
wakeup_kswapd(zone, gfp_mask, order, high_zoneidx);
last_pgdat = zone->zone_pgdat;
}
}
static inline unsigned int
gfp_to_alloc_flags(gfp_t gfp_mask)
{
unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
/*
* The caller may dip into page reserves a bit more if the caller
* cannot run direct reclaim, or if the caller has realtime scheduling
* 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);
if (gfp_mask & __GFP_ATOMIC) {
/*
* Not worth trying to allocate harder for __GFP_NOMEMALLOC even
* if it can't schedule.
*/
if (!(gfp_mask & __GFP_NOMEMALLOC))
alloc_flags |= ALLOC_HARDER;
/*
* Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
* comment for __cpuset_node_allowed().
*/
alloc_flags &= ~ALLOC_CPUSET;
} else if (unlikely(rt_task(current)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
if (gfp_mask & __GFP_KSWAPD_RECLAIM)
alloc_flags |= ALLOC_KSWAPD;
#ifdef CONFIG_CMA
if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
#endif
return alloc_flags;
}
static bool oom_reserves_allowed(struct task_struct *tsk)
{
if (!tsk_is_oom_victim(tsk))
return false;
/*
* !MMU doesn't have oom reaper so give access to memory reserves
* only to the thread with TIF_MEMDIE set
*/
if (!IS_ENABLED(CONFIG_MMU) && !test_thread_flag(TIF_MEMDIE))
return false;
return true;
}
/*
* Distinguish requests which really need access to full memory
* reserves from oom victims which can live with a portion of it
*/
static inline int __gfp_pfmemalloc_flags(gfp_t gfp_mask)
{
if (unlikely(gfp_mask & __GFP_NOMEMALLOC))
return 0;
if (gfp_mask & __GFP_MEMALLOC)
return ALLOC_NO_WATERMARKS;
if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
return ALLOC_NO_WATERMARKS;
if (!in_interrupt()) {
if (current->flags & PF_MEMALLOC)
return ALLOC_NO_WATERMARKS;
else if (oom_reserves_allowed(current))
return ALLOC_OOM;
}
return 0;
}
bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
{
return !!__gfp_pfmemalloc_flags(gfp_mask);
}
/*
* Checks whether it makes sense to retry the reclaim to make a forward progress
* for the given allocation request.
*
* We give up when we either have tried MAX_RECLAIM_RETRIES in a row
* without success, or when we couldn't even meet the watermark if we
* reclaimed all remaining pages on the LRU lists.
*
* Returns true if a retry is viable or false to enter the oom path.
*/
static inline bool
should_reclaim_retry(gfp_t gfp_mask, unsigned order,
struct alloc_context *ac, int alloc_flags,
bool did_some_progress, int *no_progress_loops)
{
struct zone *zone;
struct zoneref *z;
bool ret = false;
/*
* Costly allocations might have made a progress but this doesn't mean
* their order will become available due to high fragmentation so
* always increment the no progress counter for them
*/
if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER)
*no_progress_loops = 0;
else
(*no_progress_loops)++;
/*
* Make sure we converge to OOM if we cannot make any progress
* several times in the row.
*/
if (*no_progress_loops > MAX_RECLAIM_RETRIES) {
/* Before OOM, exhaust highatomic_reserve */
return unreserve_highatomic_pageblock(ac, true);
}
/*
* Keep reclaiming pages while there is a chance this will lead
* somewhere. If none of the target zones can satisfy our allocation
* 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) {
unsigned long available;
unsigned long reclaimable;
unsigned long min_wmark = min_wmark_pages(zone);
bool wmark;
available = reclaimable = zone_reclaimable_pages(zone);
available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
/*
* Would the allocation succeed if we reclaimed all
* reclaimable pages?
*/
wmark = __zone_watermark_ok(zone, order, min_wmark,
ac_classzone_idx(ac), alloc_flags, available);
trace_reclaim_retry_zone(z, order, reclaimable,
available, min_wmark, *no_progress_loops, wmark);
if (wmark) {
/*
* If we didn't make any progress and have a lot of
* dirty + writeback pages then we should wait for
* an IO to complete to slow down the reclaim and
* prevent from pre mature OOM
*/
if (!did_some_progress) {
unsigned long write_pending;
write_pending = zone_page_state_snapshot(zone,
NR_ZONE_WRITE_PENDING);
if (2 * write_pending > reclaimable) {
congestion_wait(BLK_RW_ASYNC, HZ/10);
return true;
}
}
ret = true;
goto out;
}
}
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
check_retry_cpuset(int cpuset_mems_cookie, struct alloc_context *ac)
{
/*
* It's possible that cpuset's mems_allowed and the nodemask from
* mempolicy don't intersect. This should be normally dealt with by
* policy_nodemask(), but it's possible to race with cpuset update in
* such a way the check therein was true, and then it became false
* before we got our cpuset_mems_cookie here.
* This assumes that for all allocations, ac->nodemask can come only
* from MPOL_BIND mempolicy (whose documented semantics is to be ignored
* when it does not intersect with the cpuset restrictions) or the
* caller can deal with a violated nodemask.
*/
if (cpusets_enabled() && ac->nodemask &&
!cpuset_nodemask_valid_mems_allowed(ac->nodemask)) {
ac->nodemask = NULL;
return true;
}
/*
* When updating a task's mems_allowed or mempolicy nodemask, it is
* possible to race with parallel threads in such a way that our
* allocation can fail while the mask is being updated. If we are about
* to fail, check if the cpuset changed during allocation and if so,
* retry.
*/
if (read_mems_allowed_retry(cpuset_mems_cookie))
return true;
return false;
}
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct alloc_context *ac)
{
bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
struct page *page = NULL;
unsigned int alloc_flags;
unsigned long did_some_progress;
enum compact_priority compact_priority;
enum compact_result compact_result;
int compaction_retries;
int no_progress_loops;
unsigned int cpuset_mems_cookie;
int reserve_flags;
/*
* We also sanity check to catch abuse of atomic reserves being used by
* callers that are not in atomic context.
*/
if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) ==
(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
gfp_mask &= ~__GFP_ATOMIC;
retry_cpuset:
compaction_retries = 0;
no_progress_loops = 0;
compact_priority = DEF_COMPACT_PRIORITY;
cpuset_mems_cookie = read_mems_allowed_begin();
/*
* The fast path uses conservative alloc_flags to succeed only until
* kswapd needs to be woken up, and to avoid the cost of setting up
* alloc_flags precisely. So we do that now.
*/
alloc_flags = gfp_to_alloc_flags(gfp_mask);
/*
* We need to recalculate the starting point for the zonelist iterator
* because we might have used different nodemask in the fast path, or
* there was a cpuset modification and we are retrying - otherwise we
* could end up iterating over non-eligible zones endlessly.
*/
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->high_zoneidx, ac->nodemask);
if (!ac->preferred_zoneref->zone)
goto nopage;
if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac);
/*
* The adjusted alloc_flags might result in immediate success, so try
* that first
*/
page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
if (page)
goto got_pg;
/*
* For costly allocations, try direct compaction first, as it's likely
* that we have enough base pages and don't need to reclaim. For non-
* movable high-order allocations, do that as well, as compaction will
* try prevent permanent fragmentation by migrating from blocks of the
* same migratetype.
* Don't try this for allocations that are allowed to ignore
* watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen.
*/
if (can_direct_reclaim &&
(costly_order ||
(order > 0 && ac->migratetype != MIGRATE_MOVABLE))
&& !gfp_pfmemalloc_allowed(gfp_mask)) {
page = __alloc_pages_direct_compact(gfp_mask, order,
alloc_flags, ac,
INIT_COMPACT_PRIORITY,
&compact_result);
if (page)
goto got_pg;
if (order >= pageblock_order && (gfp_mask & __GFP_IO) &&
!(gfp_mask & __GFP_RETRY_MAYFAIL)) {
/*
* 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_SKIPPED ||
compact_result == COMPACT_DEFERRED)
goto nopage;
}
/*
* Checks for costly allocations with __GFP_NORETRY, which
* includes 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 (compact_result == COMPACT_DEFERRED)
goto nopage;
/*
* Looks like reclaim/compaction is worth trying, but
* sync compaction could be very expensive, so keep
* using async compaction.
*/
compact_priority = INIT_COMPACT_PRIORITY;
}
}
retry:
/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
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;
/*
* Reset the nodemask and zonelist iterators if memory policies can be
* ignored. These allocations are high priority and system rather than
* user oriented.
*/
if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
ac->nodemask = NULL;
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->high_zoneidx, ac->nodemask);
}
/* Attempt with potentially adjusted zonelist and alloc_flags */
page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
if (page)
goto got_pg;
/* Caller is not willing to reclaim, we can't balance anything */
if (!can_direct_reclaim)
goto nopage;
/* Avoid recursion of direct reclaim */
if (current->flags & PF_MEMALLOC)
goto nopage;
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
&did_some_progress);
if (page)
goto got_pg;
/* Try direct compaction and then allocating */
page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac,
compact_priority, &compact_result);
if (page)
goto got_pg;
/* Do not loop if specifically requested */
if (gfp_mask & __GFP_NORETRY)
goto nopage;
/*
* Do not retry costly high order allocations unless they are
* __GFP_RETRY_MAYFAIL
*/
if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
goto nopage;
if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
did_some_progress > 0, &no_progress_loops))
goto retry;
/*
* It doesn't make any sense to retry for the compaction if the order-0
* reclaim is not able to make any progress because the current
* implementation of the compaction depends on the sufficient amount
* of free memory (see __compaction_suitable)
*/
if (did_some_progress > 0 &&
should_compact_retry(ac, order, alloc_flags,
compact_result, &compact_priority,
&compaction_retries))
goto retry;
/* Deal with possible cpuset update races before we start OOM killing */
if (check_retry_cpuset(cpuset_mems_cookie, ac))
goto retry_cpuset;
/* Reclaim has failed us, start killing things */
page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
if (page)
goto got_pg;
/* Avoid allocations with no watermarks from looping endlessly */
if (tsk_is_oom_victim(current) &&
(alloc_flags == ALLOC_OOM ||
(gfp_mask & __GFP_NOMEMALLOC)))
goto nopage;
/* Retry as long as the OOM killer is making progress */
if (did_some_progress) {
no_progress_loops = 0;
goto retry;
}
nopage:
/* Deal with possible cpuset update races before we fail */
if (check_retry_cpuset(cpuset_mems_cookie, ac))
goto retry_cpuset;
/*
* Make sure that __GFP_NOFAIL request doesn't leak out and make sure
* we always retry
*/
if (gfp_mask & __GFP_NOFAIL) {
/*
* All existing users of the __GFP_NOFAIL are blockable, so warn
* of any new users that actually require GFP_NOWAIT
*/
if (WARN_ON_ONCE(!can_direct_reclaim))
goto fail;
/*
* PF_MEMALLOC request from this context is rather bizarre
* because we cannot reclaim anything and only can loop waiting
* for somebody to do a work for us
*/
WARN_ON_ONCE(current->flags & PF_MEMALLOC);
/*
* non failing costly orders are a hard requirement which we
* are not prepared for much so let's warn about these users
* so that we can identify them and convert them to something
* else.
*/
WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER);
/*
* Help non-failing allocations by giving them access to memory
* reserves but do not use ALLOC_NO_WATERMARKS because this
* could deplete whole memory reserves which would just make
* the situation worse
*/
page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
if (page)
goto got_pg;
cond_resched();
goto retry;
}
fail:
warn_alloc(gfp_mask, ac->nodemask,
"page allocation failure: order:%u", order);
got_pg:
return page;
}
static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
int preferred_nid, nodemask_t *nodemask,
struct alloc_context *ac, gfp_t *alloc_mask,
unsigned int *alloc_flags)
{
ac->high_zoneidx = gfp_zone(gfp_mask);
ac->zonelist = node_zonelist(preferred_nid, gfp_mask);
ac->nodemask = nodemask;
ac->migratetype = gfpflags_to_migratetype(gfp_mask);
if (cpusets_enabled()) {
*alloc_mask |= __GFP_HARDWALL;
if (!ac->nodemask)
ac->nodemask = &cpuset_current_mems_allowed;
else
*alloc_flags |= ALLOC_CPUSET;
}
fs_reclaim_acquire(gfp_mask);
fs_reclaim_release(gfp_mask);
might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
if (should_fail_alloc_page(gfp_mask, order))
return false;
if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
*alloc_flags |= ALLOC_CMA;
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);
/*
* The preferred zone is used for statistics but crucially it is
* also used as the starting point for the zonelist iterator. It
* may get reset for allocations that ignore memory policies.
*/
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->high_zoneidx, ac->nodemask);
}
/*
* This is the 'heart' of the zoned buddy allocator.
*/
struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
nodemask_t *nodemask)
{
struct page *page;
unsigned int alloc_flags = ALLOC_WMARK_LOW;
gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */
struct alloc_context ac = { };
/*
* There are several places where we assume that the order value is sane
* so bail out early if the request is out of bound.
*/
if (unlikely(order >= MAX_ORDER)) {
WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
return NULL;
}
gfp_mask &= gfp_allowed_mask;
alloc_mask = gfp_mask;
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);
if (likely(page))
goto out;
/*
* Apply scoped allocation constraints. This is mainly about GFP_NOFS
* resp. GFP_NOIO which has to be inherited for all allocation requests
* from a particular context which has been marked by
* memalloc_no{fs,io}_{save,restore}.
*/
alloc_mask = current_gfp_context(gfp_mask);
ac.spread_dirty_pages = false;
/*
* 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;
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)) {
__free_pages(page, order);
page = NULL;
}
trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype);
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
/*
* Common helper functions. Never use with __GFP_HIGHMEM because the returned
* address cannot represent highmem pages. Use alloc_pages and then kmap if
* you need to access high mem.
*/
unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
struct page *page;
page = alloc_pages(gfp_mask & ~__GFP_HIGHMEM, order);
if (!page)
return 0;
return (unsigned long) page_address(page);
}
EXPORT_SYMBOL(__get_free_pages);
unsigned long get_zeroed_page(gfp_t gfp_mask)
{
return __get_free_pages(gfp_mask | __GFP_ZERO, 0);
}
EXPORT_SYMBOL(get_zeroed_page);
static inline void free_the_page(struct page *page, unsigned int order)
{
if (order == 0) /* Via pcp? */
free_unref_page(page);
else
__free_pages_ok(page, order);
}
void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page))
free_the_page(page, order);
}
EXPORT_SYMBOL(__free_pages);
void free_pages(unsigned long addr, unsigned int order)
{
if (addr != 0) {
VM_BUG_ON(!virt_addr_valid((void *)addr));
__free_pages(virt_to_page((void *)addr), order);
}
}
EXPORT_SYMBOL(free_pages);
/*
* Page Fragment:
* An arbitrary-length arbitrary-offset area of memory which resides
* within a 0 or higher order page. Multiple fragments within that page
* are individually refcounted, in the page's reference counter.
*
* The page_frag functions below provide a simple allocation framework for
* page fragments. This is used by the network stack and network device
* drivers to provide a backing region of memory for use as either an
* sk_buff->head, or to be used in the "frags" portion of skb_shared_info.
*/
static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
gfp_t gfp_mask)
{
struct page *page = NULL;
gfp_t gfp = gfp_mask;
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
__GFP_NOMEMALLOC;
page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
PAGE_FRAG_CACHE_MAX_ORDER);
nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
#endif
if (unlikely(!page))
page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
nc->va = page ? page_address(page) : NULL;
return page;
}
void __page_frag_cache_drain(struct page *page, unsigned int count)
{
VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
if (page_ref_sub_and_test(page, count))
free_the_page(page, compound_order(page));
}
EXPORT_SYMBOL(__page_frag_cache_drain);
void *page_frag_alloc(struct page_frag_cache *nc,
unsigned int fragsz, gfp_t gfp_mask)
{
unsigned int size = PAGE_SIZE;
struct page *page;
int offset;
if (unlikely(!nc->va)) {
refill:
page = __page_frag_cache_refill(nc, gfp_mask);
if (!page)
return NULL;
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
/* if size can vary use size else just use PAGE_SIZE */
size = nc->size;
#endif
/* Even if we own the page, we do not use atomic_set().
* This would break get_page_unless_zero() users.
*/
page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
/* reset page count bias and offset to start of new frag */
nc->pfmemalloc = page_is_pfmemalloc(page);
nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
nc->offset = size;
}
offset = nc->offset - fragsz;
if (unlikely(offset < 0)) {
page = virt_to_page(nc->va);
if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
goto refill;
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
/* if size can vary use size else just use PAGE_SIZE */
size = nc->size;
#endif
/* OK, page count is 0, we can safely set it */
set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
/* reset page count bias and offset to start of new frag */
nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
offset = size - fragsz;
}
nc->pagecnt_bias--;
nc->offset = offset;
return nc->va + offset;
}
EXPORT_SYMBOL(page_frag_alloc);
/*
* Frees a page fragment allocated out of either a compound or order 0 page.
*/
void page_frag_free(void *addr)
{
struct page *page = virt_to_head_page(addr);
if (unlikely(put_page_testzero(page)))
free_the_page(page, compound_order(page));
}
EXPORT_SYMBOL(page_frag_free);
static void *make_alloc_exact(unsigned long addr, unsigned int order,
size_t size)
{
if (addr) {
unsigned long alloc_end = addr + (PAGE_SIZE << order);
unsigned long used = addr + PAGE_ALIGN(size);
split_page(virt_to_page((void *)addr), order);
while (used < alloc_end) {
free_page(used);
used += PAGE_SIZE;
}
}
return (void *)addr;
}
/**
* alloc_pages_exact - allocate an exact number physically-contiguous pages.
* @size: the number of bytes to allocate
* @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
* allocate memory in power-of-two pages.
*
* 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);
}
EXPORT_SYMBOL(alloc_pages_exact);
/**
* alloc_pages_exact_nid - allocate an exact number of physically-contiguous
* 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, 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;
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);
}
/**
* free_pages_exact - release memory allocated via alloc_pages_exact()
* @virt: the value returned by alloc_pages_exact.
* @size: size of allocation, same value as passed to alloc_pages_exact().
*
* Release the memory allocated by a previous call to alloc_pages_exact.
*/
void free_pages_exact(void *virt, size_t size)
{
unsigned long addr = (unsigned long)virt;
unsigned long end = addr + PAGE_ALIGN(size);
while (addr < end) {
free_page(addr);
addr += PAGE_SIZE;
}
}
EXPORT_SYMBOL(free_pages_exact);
/**
* 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 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)
{
struct zoneref *z;
struct zone *zone;
/* Just pick one node, since fallback list is circular */
unsigned long sum = 0;
struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
for_each_zone_zonelist(zone, z, zonelist, offset) {
unsigned long size = zone_managed_pages(zone);
unsigned long high = high_wmark_pages(zone);
if (size > high)
sum += size - high;
}
return sum;
}
/**
* nr_free_buffer_pages - count number of pages beyond high watermark
*
* 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.
*
* Return: number of pages beyond 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)
{
if (IS_ENABLED(CONFIG_NUMA))
printk("Node %d ", zone_to_nid(zone));
}
long si_mem_available(void)
{
long available;
unsigned long pagecache;
unsigned long wmark_low = 0;
unsigned long pages[NR_LRU_LISTS];
unsigned long reclaimable;
struct zone *zone;
int lru;
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
for_each_zone(zone)
wmark_low += low_wmark_pages(zone);
/*
* Estimate the amount of memory available for userspace allocations,
* without causing swapping.
*/
available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages;
/*
* Not all the page cache can be freed, otherwise the system will
* start swapping. Assume at least half of the page cache, or the
* low watermark worth of cache, needs to stay.
*/
pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
pagecache -= min(pagecache / 2, wmark_low);
available += pagecache;
/*
* Part of the reclaimable slab and other kernel memory consists of
* 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);
available += reclaimable - min(reclaimable / 2, wmark_low);
if (available < 0)
available = 0;
return available;
}
EXPORT_SYMBOL_GPL(si_mem_available);
void si_meminfo(struct sysinfo *val)
{
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->freehigh = nr_free_highpages();
val->mem_unit = PAGE_SIZE;
}
EXPORT_SYMBOL(si_meminfo);
#ifdef CONFIG_NUMA
void si_meminfo_node(struct sysinfo *val, int nid)
{
int zone_type; /* needs to be signed */
unsigned long managed_pages = 0;
unsigned long managed_highpages = 0;
unsigned long free_highpages = 0;
pg_data_t *pgdat = NODE_DATA(nid);
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
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);
#ifdef CONFIG_HIGHMEM
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
struct zone *zone = &pgdat->node_zones[zone_type];
if (is_highmem(zone)) {
managed_highpages += zone_managed_pages(zone);
free_highpages += zone_page_state(zone, NR_FREE_PAGES);
}
}
val->totalhigh = managed_highpages;
val->freehigh = free_highpages;
#else
val->totalhigh = managed_highpages;
val->freehigh = free_highpages;
#endif
val->mem_unit = PAGE_SIZE;
}
#endif
/*
* Determine whether the node should be displayed or not, depending on whether
* SHOW_MEM_FILTER_NODES was passed to show_free_areas().
*/
static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask)
{
if (!(flags & SHOW_MEM_FILTER_NODES))
return false;
/*
* no node mask - aka implicit memory numa policy. Do not bother with
* the synchronization - read_mems_allowed_begin - because we do not
* have to be precise here.
*/
if (!nodemask)
nodemask = &cpuset_current_mems_allowed;
return !node_isset(nid, *nodemask);
}
#define K(x) ((x) << (PAGE_SHIFT-10))
static void show_migration_types(unsigned char type)
{
static const char types[MIGRATE_TYPES] = {
[MIGRATE_UNMOVABLE] = 'U',
[MIGRATE_MOVABLE] = 'M',
[MIGRATE_RECLAIMABLE] = 'E',
[MIGRATE_HIGHATOMIC] = 'H',
#ifdef CONFIG_CMA
[MIGRATE_CMA] = 'C',
#endif
#ifdef CONFIG_MEMORY_ISOLATION
[MIGRATE_ISOLATE] = 'I',
#endif
};
char tmp[MIGRATE_TYPES + 1];
char *p = tmp;
int i;
for (i = 0; i < MIGRATE_TYPES; i++) {
if (type & (1 << i))
*p++ = types[i];
}
*p = '\0';
printk(KERN_CONT "(%s) ", tmp);
}
/*
* Show free area list (used inside shift_scroll-lock stuff)
* We also calculate the percentage fragmentation. We do this by counting the
* memory on each free list with the exception of the first item on the list.
*
* Bits in @filter:
* SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's
* cpuset.
*/
void show_free_areas(unsigned int filter, nodemask_t *nodemask)
{
unsigned long free_pcp = 0;
int cpu;
struct zone *zone;
pg_data_t *pgdat;
for_each_populated_zone(zone) {
if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
continue;
for_each_online_cpu(cpu)
free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count;
}
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"
" 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",
global_node_page_state(NR_ACTIVE_ANON),
global_node_page_state(NR_INACTIVE_ANON),
global_node_page_state(NR_ISOLATED_ANON),
global_node_page_state(NR_ACTIVE_FILE),
global_node_page_state(NR_INACTIVE_FILE),
global_node_page_state(NR_ISOLATED_FILE),
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(NR_FILE_MAPPED),
global_node_page_state(NR_SHMEM),
global_zone_page_state(NR_PAGETABLE),
global_zone_page_state(NR_BOUNCE),
global_zone_page_state(NR_FREE_PAGES),
free_pcp,
global_zone_page_state(NR_FREE_CMA_PAGES));
for_each_online_pgdat(pgdat) {
if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
continue;
printk("Node %d"
" active_anon:%lukB"
" inactive_anon:%lukB"
" active_file:%lukB"
" inactive_file:%lukB"
" unevictable:%lukB"
" isolated(anon):%lukB"
" isolated(file):%lukB"
" mapped:%lukB"
" dirty:%lukB"
" writeback:%lukB"
" shmem:%lukB"
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
" shmem_thp: %lukB"
" shmem_pmdmapped: %lukB"
" anon_thp: %lukB"
#endif
" writeback_tmp:%lukB"
" unstable:%lukB"
" all_unreclaimable? %s"
"\n",
pgdat->node_id,
K(node_page_state(pgdat, NR_ACTIVE_ANON)),
K(node_page_state(pgdat, NR_INACTIVE_ANON)),
K(node_page_state(pgdat, NR_ACTIVE_FILE)),
K(node_page_state(pgdat, NR_INACTIVE_FILE)),
K(node_page_state(pgdat, NR_UNEVICTABLE)),
K(node_page_state(pgdat, NR_ISOLATED_ANON)),
K(node_page_state(pgdat, NR_ISOLATED_FILE)),
K(node_page_state(pgdat, NR_FILE_MAPPED)),
K(node_page_state(pgdat, NR_FILE_DIRTY)),
K(node_page_state(pgdat, NR_WRITEBACK)),
K(node_page_state(pgdat, NR_SHMEM)),
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
* HPAGE_PMD_NR),
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)),
pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
"yes" : "no");
}
for_each_populated_zone(zone) {
int i;
if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
continue;
free_pcp = 0;
for_each_online_cpu(cpu)
free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count;
show_node(zone);
printk(KERN_CONT
"%s"
" free:%lukB"
" min:%lukB"
" low:%lukB"
" high:%lukB"
" active_anon:%lukB"
" inactive_anon:%lukB"
" active_file:%lukB"
" inactive_file:%lukB"
" unevictable:%lukB"
" writepending:%lukB"
" present:%lukB"
" managed:%lukB"
" mlocked:%lukB"
" kernel_stack:%lukB"
" pagetables:%lukB"
" bounce:%lukB"
" free_pcp:%lukB"
" local_pcp:%ukB"
" free_cma:%lukB"
"\n",
zone->name,
K(zone_page_state(zone, NR_FREE_PAGES)),
K(min_wmark_pages(zone)),
K(low_wmark_pages(zone)),
K(high_wmark_pages(zone)),
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)),
K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)),
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(zone)),
K(zone_page_state(zone, NR_MLOCK)),
zone_page_state(zone, NR_KERNEL_STACK_KB),
K(zone_page_state(zone, NR_PAGETABLE)),
K(zone_page_state(zone, NR_BOUNCE)),
K(free_pcp),
K(this_cpu_read(zone->pageset->pcp.count)),
K(zone_page_state(zone, NR_FREE_CMA_PAGES)));
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
printk(KERN_CONT " %ld", zone->lowmem_reserve[i]);
printk(KERN_CONT "\n");
}
for_each_populated_zone(zone) {
unsigned int order;
unsigned long nr[MAX_ORDER], flags, total = 0;
unsigned char types[MAX_ORDER];
if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
continue;
show_node(zone);
printk(KERN_CONT "%s: ", zone->name);
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
struct free_area *area = &zone->free_area[order];
int type;
nr[order] = area->nr_free;
total += nr[order] << order;
types[order] = 0;
for (type = 0; type < MIGRATE_TYPES; type++) {
if (!free_area_empty(area, type))
types[order] |= 1 << type;
}
}
spin_unlock_irqrestore(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
printk(KERN_CONT "%lu*%lukB ",
nr[order], K(1UL) << order);
if (nr[order])
show_migration_types(types[order]);
}
printk(KERN_CONT "= %lukB\n", K(total));
}
hugetlb_show_meminfo();
printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES));
show_swap_cache_info();
}
static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
{
zoneref->zone = zone;
zoneref->zone_idx = zone_idx(zone);
}
/*
* Builds allocation fallback zone lists.
*
* Add all populated zones of a node to the zonelist.
*/
static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs)
{
struct zone *zone;
enum zone_type zone_type = MAX_NR_ZONES;
int nr_zones = 0;
do {
zone_type--;
zone = pgdat->node_zones + zone_type;
if (managed_zone(zone)) {
zoneref_set_zone(zone, &zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
} while (zone_type);
return nr_zones;
}
#ifdef CONFIG_NUMA
static int __parse_numa_zonelist_order(char *s)
{
/*
* We used to support different zonlists modes but they turned
* out to be just not useful. Let's keep the warning in place
* if somebody still use the cmd line parameter so that we do
* not fail it silently
*/
if (!(*s == 'd' || *s == 'D' || *s == 'n' || *s == 'N')) {
pr_warn("Ignoring unsupported numa_zonelist_order value: %s\n", s);
return -EINVAL;
}
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)
{
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;
}
#define MAX_NODE_LOAD (nr_online_nodes)
static int node_load[MAX_NUMNODES];
/**
* find_next_best_node - find the next node that should appear in a given node's fallback list
* @node: node whose fallback list we're appending
* @used_node_mask: nodemask_t of already used nodes
*
* We use a number of factors to determine which is the next node that should
* appear on a given node's fallback list. The node should not have appeared
* already in @node's fallback list, and it should be the next closest node
* according to the distance array (which contains arbitrary distance values
* 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.
*
* 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)) {
node_set(node, *used_node_mask);
return node;
}
for_each_node_state(n, N_MEMORY) {
/* Don't want a node to appear more than once */
if (node_isset(n, *used_node_mask))
continue;
/* Use the distance array to find the distance */
val = node_distance(node, n);
/* Penalize nodes under us ("prefer the next node") */
val += (n < node);
/* Give preference to headless and unused nodes */
tmp = cpumask_of_node(n);
if (!cpumask_empty(tmp))
val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */
val *= (MAX_NODE_LOAD*MAX_NUMNODES);
val += node_load[n];
if (val < min_val) {
min_val = val;
best_node = n;
}
}
if (best_node >= 0)
node_set(best_node, *used_node_mask);
return best_node;
}
/*
* Build zonelists ordered by node and zones within node.
* This results in maximum locality--normal zone overflows into local
* DMA zone, if any--but risks exhausting DMA zone.
*/
static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order,
unsigned nr_nodes)
{
struct zoneref *zonerefs;
int i;
zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
for (i = 0; i < nr_nodes; i++) {
int nr_zones;
pg_data_t *node = NODE_DATA(node_order[i]);
nr_zones = build_zonerefs_node(node, zonerefs);
zonerefs += nr_zones;
}
zonerefs->zone = NULL;
zonerefs->zone_idx = 0;
}
/*
* Build gfp_thisnode zonelists
*/
static void build_thisnode_zonelists(pg_data_t *pgdat)
{
struct zoneref *zonerefs;
int nr_zones;
zonerefs = pgdat->node_zonelists[ZONELIST_NOFALLBACK]._zonerefs;
nr_zones = build_zonerefs_node(pgdat, zonerefs);
zonerefs += nr_zones;
zonerefs->zone = NULL;
zonerefs->zone_idx = 0;
}
/*
* Build zonelists ordered by zone and nodes within zones.
* This results in conserving DMA zone[s] until all Normal memory is
* exhausted, but results in overflowing to remote node while memory
* may still exist in local DMA zone.
*/
static void build_zonelists(pg_data_t *pgdat)
{
static int node_order[MAX_NUMNODES];
int node, load, nr_nodes = 0;
nodemask_t used_mask;
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) {
/*
* We don't want to pressure a particular node.
* So adding penalty to the first node in same
* distance group to make it round-robin.
*/
if (node_distance(local_node, node) !=
node_distance(local_node, prev_node))
node_load[node] = load;
node_order[nr_nodes++] = node;
prev_node = node;
load--;
}
build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
build_thisnode_zonelists(pgdat);
}
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
* Return node id of node used for "local" allocations.
* I.e., first node id of first zone in arg node's generic zonelist.
* Used for initializing percpu 'numa_mem', which is used primarily
* for kernel allocations, so use GFP_KERNEL flags to locate zonelist.
*/
int local_memory_node(int node)
{
struct zoneref *z;
z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
gfp_zone(GFP_KERNEL),
NULL);
return zone_to_nid(z->zone);
}
#endif
static void setup_min_unmapped_ratio(void);
static void setup_min_slab_ratio(void);
#else /* CONFIG_NUMA */
static void build_zonelists(pg_data_t *pgdat)
{
int node, local_node;
struct zoneref *zonerefs;
int nr_zones;
local_node = pgdat->node_id;
zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
nr_zones = build_zonerefs_node(pgdat, zonerefs);
zonerefs += nr_zones;
/*
* Now we build the zonelist so that it contains the zones
* of all the other nodes.
* We don't want to pressure a particular node, so when
* building the zones for node N, we make sure that the
* zones coming right after the local ones are those from
* node N+1 (modulo N)
*/
for (node = local_node + 1; node < MAX_NUMNODES; node++) {
if (!node_online(node))
continue;
nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
zonerefs += nr_zones;
}
for (node = 0; node < local_node; node++) {
if (!node_online(node))
continue;
nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
zonerefs += nr_zones;
}
zonerefs->zone = NULL;
zonerefs->zone_idx = 0;
}
#endif /* CONFIG_NUMA */
/*
* Boot pageset table. One per cpu which is going to be used for all
* zones and all nodes. The parameters will be set in such a way
* that an item put on a list will immediately be handed over to
* the buddy list. This is safe since pageset manipulation is done
* with interrupts disabled.
*
* The boot_pagesets must be kept even after bootup is complete for
* unused processors and/or zones. They do play a role for bootstrapping
* hotplugged processors.
*
* zoneinfo_show() and maybe other functions do
* not check if the processor is online before following the pageset pointer.
* Other parts of the kernel may not check if the zone is available.
*/
static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);
static void __build_all_zonelists(void *data)
{
int nid;
int __maybe_unused cpu;
pg_data_t *self = data;
static DEFINE_SPINLOCK(lock);
spin_lock(&lock);
#ifdef CONFIG_NUMA
memset(node_load, 0, sizeof(node_load));
#endif
/*
* This node is hotadded and no memory is yet present. So just
* building zonelists is fine - no need to touch other nodes.
*/
if (self && !node_online(self->node_id)) {
build_zonelists(self);
} else {
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
build_zonelists(pgdat);
}
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
* We now know the "local memory node" for each node--
* i.e., the node of the first zone in the generic zonelist.
* Set up numa_mem percpu variable for on-line cpus. During
* boot, only the boot cpu should be on-line; we'll init the
* secondary cpus' numa_mem as they come on-line. During
* node/memory hotplug, we'll fixup all on-line cpus.
*/
for_each_online_cpu(cpu)
set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
#endif
}
spin_unlock(&lock);
}
static noinline void __init
build_all_zonelists_init(void)
{
int cpu;
__build_all_zonelists(NULL);
/*
* Initialize the boot_pagesets that are going to be used
* for bootstrapping processors. The real pagesets for
* each zone will be allocated later when the per cpu
* allocator is available.
*
* boot_pagesets are used also for bootstrapping offline
* cpus if the system is already booted because the pagesets
* are needed to initialize allocators on a specific cpu too.
* F.e. the percpu allocator needs the page allocator which
* needs the percpu allocator in order to allocate its pagesets
* (a chicken-egg dilemma).
*/
for_each_possible_cpu(cpu)
setup_pageset(&per_cpu(boot_pageset, cpu), 0);
mminit_verify_zonelist();
cpuset_init_current_mems_allowed();
}
/*
* unless system_state == SYSTEM_BOOTING.
*
* __ref due to call of __init annotated helper build_all_zonelists_init
* [protected by SYSTEM_BOOTING].
*/
void __ref build_all_zonelists(pg_data_t *pgdat)
{
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();
/*
* Disable grouping by mobility if the number of pages in the
* system is too low to allow the mechanism to work. It would be
* more accurate, but expensive to check per-zone. This check is
* made on memory-hotadd so a system can start with mobility
* disabled and enable it later
*/
if (vm_total_pages < (pageblock_nr_pages * MIGRATE_TYPES))
page_group_by_mobility_disabled = 1;
else
page_group_by_mobility_disabled = 0;
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);
#ifdef CONFIG_NUMA
pr_info("Policy zone: %s\n", zone_names[policy_zone]);
#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)
{
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
static struct memblock_region *r;
if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
if (!r || *pfn >= memblock_region_memory_end_pfn(r)) {
for_each_memblock(memory, 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;
}
}
#endif
return false;
}
/*
* Initially all pages are reserved - free ones are freed
* up by memblock_free_all() once the early boot process is
* done. Non-atomic initialization, single-pass.
*/
void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
unsigned long start_pfn, enum memmap_context context,
struct vmem_altmap *altmap)
{
unsigned long pfn, end_pfn = start_pfn + size;
struct page *page;
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
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
/*
* There can be holes in boot-time mem_map[]s handed to this
* function. They do not exist on hotplugged memory.
*/
if (context == MEMMAP_EARLY) {
if (!early_pfn_valid(pfn))
continue;
if (!early_pfn_in_nid(pfn, nid))
continue;
if (overlap_memmap_init(zone, &pfn))
continue;
if (defer_init(nid, pfn, end_pfn))
break;
}
page = pfn_to_page(pfn);
__init_single_page(page, pfn, zone, nid);
if (context == MEMMAP_HOTPLUG)
__SetPageReserved(page);
/*
* Mark the block movable so that blocks are reserved for
* movable at startup. This will force kernel allocations
* to reserve their blocks rather than leaking throughout
* 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.
*/
if (!(pfn & (pageblock_nr_pages - 1))) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
cond_resched();
}
}
}
#ifdef CONFIG_ZONE_DEVICE
void __ref memmap_init_zone_device(struct zone *zone,
unsigned long start_pfn,
unsigned long size,
struct dev_pagemap *pgmap)
{
unsigned long pfn, end_pfn = start_pfn + size;
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_zone 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);
size = 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);
/*
* 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
* movable at startup. This will force kernel allocations
* to reserve their blocks rather than leaking throughout
* 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 MEMMAP_HOTPLUG path doesn't clear memmap
* because this is done early in section_activate()
*/
if (!(pfn & (pageblock_nr_pages - 1))) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
cond_resched();
}
}
pr_info("%s initialised %lu pages in %ums\n", __func__,
size, jiffies_to_msecs(jiffies - start));
}
#endif
static void __meminit zone_init_free_lists(struct zone *zone)
{
unsigned int order, t;
for_each_migratetype_order(order, t) {
INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
zone->free_area[order].nr_free = 0;
}
}
void __meminit __weak memmap_init(unsigned long size, int nid,
unsigned long zone, unsigned long start_pfn)
{
memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, NULL);
}
static int zone_batchsize(struct zone *zone)
{
#ifdef CONFIG_MMU
int batch;
/*
* The per-cpu-pages pools are set to around 1000th of the
* size of the zone.
*/
batch = zone_managed_pages(zone) / 1024;
/* But no more than a meg. */
if (batch * PAGE_SIZE > 1024 * 1024)
batch = (1024 * 1024) / PAGE_SIZE;
batch /= 4; /* We effectively *= 4 below */
if (batch < 1)
batch = 1;
/*
* Clamp the batch to a 2^n - 1 value. Having a power
* of 2 value was found to be more likely to have
* suboptimal cache aliasing properties in some cases.
*
* For example if 2 tasks are alternately allocating
* batches of pages, one task can end up with a lot
* of pages of one half of the possible page colors
* and the other with pages of the other colors.
*/
batch = rounddown_pow_of_two(batch + batch/2) - 1;
return batch;
#else
/* The deferral and batching of frees should be suppressed under NOMMU
* conditions.
*
* The problem is that NOMMU needs to be able to allocate large chunks
* of contiguous memory as there's no hardware page translation to
* assemble apparent contiguous memory from discontiguous pages.
*
* Queueing large contiguous runs of pages for batching, however,
* causes the pages to actually be freed in smaller chunks. As there
* can be a significant delay between the individual batches being
* recycled, this leads to the once large chunks of space being
* fragmented and becoming unavailable for high-order allocations.
*/
return 0;
#endif
}
/*
* pcp->high and pcp->batch values are related and dependent on one another:
* ->batch must never be higher then ->high.
* The following function updates them in a safe manner without read side
* 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).
*
* mutex_is_locked(&pcp_batch_high_lock) required when calling this function
* outside of boot time (or some other assurance that no concurrent updaters
* exist).
*/
static void pageset_update(struct per_cpu_pages *pcp, unsigned long high,
unsigned long batch)
{
/* start with a fail safe value for batch */
pcp->batch = 1;
smp_wmb();
/* Update high, then batch, in order */
pcp->high = high;
smp_wmb();
pcp->batch = batch;
}
/* a companion to pageset_set_high() */
static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch)
{
pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch));
}
static void pageset_init(struct per_cpu_pageset *p)
{
struct per_cpu_pages *pcp;
int migratetype;
memset(p, 0, sizeof(*p));
pcp = &p->pcp;
for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
INIT_LIST_HEAD(&pcp->lists[migratetype]);
}
static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
pageset_init(p);
pageset_set_batch(p, batch);
}
/*
* pageset_set_high() sets the high water mark for hot per_cpu_pagelist
* to the value high for the pageset p.
*/
static void pageset_set_high(struct per_cpu_pageset *p,
unsigned long high)
{
unsigned long batch = max(1UL, high / 4);
if ((high / 4) > (PAGE_SHIFT * 8))
batch = PAGE_SHIFT * 8;
pageset_update(&p->pcp, high, batch);
}
static void pageset_set_high_and_batch(struct zone *zone,
struct per_cpu_pageset *pcp)
{
if (percpu_pagelist_fraction)
pageset_set_high(pcp,
(zone_managed_pages(zone) /
percpu_pagelist_fraction));
else
pageset_set_batch(pcp, zone_batchsize(zone));
}
static void __meminit zone_pageset_init(struct zone *zone, int cpu)
{
struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
pageset_init(pcp);
pageset_set_high_and_batch(zone, pcp);
}
void __meminit setup_zone_pageset(struct zone *zone)
{
int cpu;
zone->pageset = alloc_percpu(struct per_cpu_pageset);
for_each_possible_cpu(cpu)
zone_pageset_init(zone, cpu);
}
/*
* Allocate per cpu pagesets and initialize them.
* Before this call only boot pagesets were available.
*/
void __init setup_per_cpu_pageset(void)
{
struct pglist_data *pgdat;
struct zone *zone;
for_each_populated_zone(zone)
setup_zone_pageset(zone);
for_each_online_pgdat(pgdat)
pgdat->per_cpu_nodestats =
alloc_percpu(struct per_cpu_nodestat);
}
static __meminit void zone_pcp_init(struct zone *zone)
{
/*
* per cpu subsystem is not up at this point. The following code
* relies on the ability of the linker to provide the
* offset of a (static) per cpu variable into the per cpu area.
*/
zone->pageset = &boot_pageset;
if (populated_zone(zone))
printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n",
zone->name, zone->present_pages,
zone_batchsize(zone));
}
void __meminit init_currently_empty_zone(struct zone *zone,
unsigned long zone_start_pfn,
unsigned long size)
{
struct pglist_data *pgdat = zone->zone_pgdat;
int zone_idx = zone_idx(zone) + 1;
if (zone_idx > pgdat->nr_zones)
pgdat->nr_zones = zone_idx;
zone->zone_start_pfn = zone_start_pfn;
mminit_dprintk(MMINIT_TRACE, "memmap_init",
"Initialising map node %d zone %lu pfns %lu -> %lu\n",
pgdat->node_id,
(unsigned long)zone_idx(zone),
zone_start_pfn, (zone_start_pfn + size));
zone_init_free_lists(zone);
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 != 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 */
/**
* 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.
* @start_pfn: Passed by reference. On return, it will have the node start_pfn.
* @end_pfn: Passed by reference. On return, it will have the node end_pfn.
*
* It returns the start and end page frame of a node based on information
* provided by memblock_set_node(). If called for a node
* with no available memory, a warning is printed and the start and end
* PFNs will be 0.
*/
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;
int i;
*start_pfn = -1UL;
*end_pfn = 0;
for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) {
*start_pfn = min(*start_pfn, this_start_pfn);
*end_pfn = max(*end_pfn, this_end_pfn);
}
if (*start_pfn == -1UL)
*start_pfn = 0;
}
/*
* This finds a zone that can be used for ZONE_MOVABLE pages. The
* assumption is made that zones within a node are ordered in monotonic
* increasing memory addresses so that the "highest" populated zone is used
*/
static void __init find_usable_zone_for_movable(void)
{
int zone_index;
for (zone_index = MAX_NR_ZONES - 1; zone_index >= 0; zone_index--) {
if (zone_index == ZONE_MOVABLE)
continue;
if (arch_zone_highest_possible_pfn[zone_index] >
arch_zone_lowest_possible_pfn[zone_index])
break;
}
VM_BUG_ON(zone_index == -1);
movable_zone = zone_index;
}
/*
* The zone ranges provided by the architecture do not include ZONE_MOVABLE
* because it is sized independent of architecture. Unlike the other zones,
* the starting point for ZONE_MOVABLE is not fixed. It may be different
* in each node depending on the size of each node and how evenly kernelcore
* is distributed. This helper function adjusts the zone ranges
* provided by the architecture for a given node by using the end of the
* 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 __init adjust_zone_range_for_zone_movable(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)
{
/* Only adjust if ZONE_MOVABLE is on this node */
if (zone_movable_pfn[nid]) {
/* Size ZONE_MOVABLE */
if (zone_type == ZONE_MOVABLE) {
*zone_start_pfn = zone_movable_pfn[nid];
*zone_end_pfn = min(node_end_pfn,
arch_zone_highest_possible_pfn[movable_zone]);
/* Adjust for ZONE_MOVABLE starting within this range */
} else if (!mirrored_kernelcore &&
*zone_start_pfn < zone_movable_pfn[nid] &&
*zone_end_pfn > zone_movable_pfn[nid]) {
*zone_end_pfn = zone_movable_pfn[nid];
/* Check if this whole range is within ZONE_MOVABLE */
} else if (*zone_start_pfn >= zone_movable_pfn[nid])
*zone_start_pfn = *zone_end_pfn;
}
}
/*
* 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 __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_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
/* When hotadd a new node from cpu_up(), the node should be empty */
if (!node_start_pfn && !node_end_pfn)
return 0;
/* Get the start and end of the zone */
*zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
*zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
adjust_zone_range_for_zone_movable(nid, zone_type,
node_start_pfn, node_end_pfn,
zone_start_pfn, zone_end_pfn);
/* Check that this node has pages within the zone's required range */
if (*zone_end_pfn < node_start_pfn || *zone_start_pfn > node_end_pfn)
return 0;
/* Move the zone boundaries inside the node if necessary */
*zone_end_pfn = min(*zone_end_pfn, node_end_pfn);
*zone_start_pfn = max(*zone_start_pfn, node_start_pfn);
/* Return the spanned pages */
return *zone_end_pfn - *zone_start_pfn;
}
/*
* 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 __init __absent_pages_in_range(int nid,
unsigned long range_start_pfn,
unsigned long range_end_pfn)
{
unsigned long nr_absent = range_end_pfn - range_start_pfn;
unsigned long start_pfn, end_pfn;
int i;
for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn);
end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn);
nr_absent -= end_pfn - start_pfn;
}
return nr_absent;
}
/**
* absent_pages_in_range - Return number of page frames in holes within a range
* @start_pfn: The start PFN to start searching for holes
* @end_pfn: The end PFN to stop searching for holes
*
* 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)
{
return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn);
}
/* Return the number of page frames in holes in a zone on a node */
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 zone_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
unsigned long zone_start_pfn, zone_end_pfn;
unsigned long nr_absent;
/* When hotadd a new node from cpu_up(), the node should be empty */
if (!node_start_pfn && !node_end_pfn)
return 0;
zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
adjust_zone_range_for_zone_movable(nid, zone_type,
node_start_pfn, node_end_pfn,
&zone_start_pfn, &zone_end_pfn);
nr_absent = __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
/*
* ZONE_MOVABLE handling.
* Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages
* and vice versa.
*/
if (mirrored_kernelcore && zone_movable_pfn[nid]) {
unsigned long start_pfn, end_pfn;
struct memblock_region *r;
for_each_memblock(memory, 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),
zone_start_pfn, zone_end_pfn);
if (zone_type == ZONE_MOVABLE &&
memblock_is_mirror(r))
nr_absent += end_pfn - start_pfn;
if (zone_type == ZONE_NORMAL &&
!memblock_is_mirror(r))
nr_absent += end_pfn - start_pfn;
}
}
return nr_absent;
}
#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static inline 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 *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 __init zone_absent_pages_in_node(int nid,
unsigned long zone_type,
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 __init 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 realtotalpages = 0, totalpages = 0;
enum zone_type i;
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 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);
if (size)
zone->zone_start_pfn = zone_start_pfn;
else
zone->zone_start_pfn = 0;
zone->spanned_pages = size;
zone->present_pages = real_size;
totalpages += size;
realtotalpages += real_size;
}
pgdat->node_spanned_pages = totalpages;
pgdat->node_present_pages = realtotalpages;
printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id,
realtotalpages);
}
#ifndef CONFIG_SPARSEMEM
/*
* Calculate the size of the zone->blockflags rounded to an unsigned long
* Start by making sure zonesize is a multiple of pageblock_order by rounding
* up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally
* round what is now in bits to nearest long in bits, then return it in
* bytes.
*/
static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize)
{
unsigned long usemapsize;
zonesize += zone_start_pfn & (pageblock_nr_pages-1);
usemapsize = roundup(zonesize, pageblock_nr_pages);
usemapsize = usemapsize >> pageblock_order;
usemapsize *= NR_PAGEBLOCK_BITS;
usemapsize = roundup(usemapsize, 8 * sizeof(unsigned long));
return usemapsize / 8;
}
static void __ref setup_usemap(struct pglist_data *pgdat,
struct zone *zone,
unsigned long zone_start_pfn,
unsigned long zonesize)
{
unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
zone->pageblock_flags = NULL;
if (usemapsize) {
zone->pageblock_flags =
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,
unsigned long zone_start_pfn, unsigned long zonesize) {}
#endif /* CONFIG_SPARSEMEM */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
void __init set_pageblock_order(void)
{
unsigned int order;
/* Check that pageblock_nr_pages has not already been setup */
if (pageblock_order)
return;
if (HPAGE_SHIFT > PAGE_SHIFT)
order = HUGETLB_PAGE_ORDER;
else
order = MAX_ORDER - 1;
/*
* Assume the largest contiguous order of interest is a huge page.
* This value may be variable depending on boot parameters on IA64 and
* powerpc.
*/
pageblock_order = order;
}
#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
/*
* When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
* is unused as pageblock_order is set at compile-time. See
* include/linux/pageblock-flags.h for the values of pageblock_order based on
* the kernel config
*/
void __init set_pageblock_order(void)
{
}
#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
static unsigned long __init calc_memmap_size(unsigned long spanned_pages,
unsigned long present_pages)
{
unsigned long pages = spanned_pages;
/*
* Provide a more accurate estimation if there are holes within
* the zone and SPARSEMEM is in use. If there are holes within the
* zone, each populated memory region may cost us one or two extra
* memmap pages due to alignment because memmap pages for each
* populated regions may not be naturally aligned on page boundary.
* So the (present_pages >> 4) heuristic is a tradeoff for that.
*/
if (spanned_pages > present_pages + (present_pages >> 4) &&
IS_ENABLED(CONFIG_SPARSEMEM))
pages = present_pages;
return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void pgdat_init_split_queue(struct pglist_data *pgdat)
{
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) {}
#endif
#ifdef CONFIG_COMPACTION
static void pgdat_init_kcompactd(struct pglist_data *pgdat)
{
init_waitqueue_head(&pgdat->kcompactd_wait);
}
#else
static void pgdat_init_kcompactd(struct pglist_data *pgdat) {}
#endif
static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
{
pgdat_resize_init(pgdat);
pgdat_init_split_queue(pgdat);
pgdat_init_kcompactd(pgdat);
init_waitqueue_head(&pgdat->kswapd_wait);
init_waitqueue_head(&pgdat->pfmemalloc_wait);
pgdat_page_ext_init(pgdat);
spin_lock_init(&pgdat->lru_lock);
lruvec_init(node_lruvec(pgdat));
}
static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,
unsigned long 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);
spin_lock_init(&zone->lock);
zone_seqlock_init(zone);
zone_pcp_init(zone);
}
/*
* Set up the zone data structures
* - init pgdat internals
* - init all zones belonging to this node
*
* NOTE: this function is only called during memory hotplug
*/
#ifdef CONFIG_MEMORY_HOTPLUG
void __ref free_area_init_core_hotplug(int nid)
{
enum zone_type z;
pg_data_t *pgdat = NODE_DATA(nid);
pgdat_init_internals(pgdat);
for (z = 0; z < MAX_NR_ZONES; z++)
zone_init_internals(&pgdat->node_zones[z], z, nid, 0);
}
#endif
/*
* Set up the zone data structures:
* - mark all pages reserved
* - mark all memory queues empty
* - clear the memory bitmaps
*
* NOTE: pgdat should get zeroed by caller.
* NOTE: this function is only called during early init.
*/
static void __init free_area_init_core(struct pglist_data *pgdat)
{
enum zone_type j;
int nid = pgdat->node_id;
pgdat_init_internals(pgdat);
pgdat->per_cpu_nodestats = &boot_nodestats;
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, freesize, memmap_pages;
unsigned long zone_start_pfn = zone->zone_start_pfn;
size = zone->spanned_pages;
freesize = zone->present_pages;
/*
* Adjust freesize so that it accounts for how much memory
* is used by this zone for memmap. This affects the watermark
* and per-cpu initialisations
*/
memmap_pages = calc_memmap_size(size, freesize);
if (!is_highmem_idx(j)) {
if (freesize >= memmap_pages) {
freesize -= memmap_pages;
if (memmap_pages)
printk(KERN_DEBUG
" %s zone: %lu pages used for memmap\n",
zone_names[j], memmap_pages);
} else
pr_warn(" %s zone: %lu pages exceeds freesize %lu\n",
zone_names[j], memmap_pages, freesize);
}
/* Account for reserved pages */
if (j == 0 && freesize > dma_reserve) {
freesize -= dma_reserve;
printk(KERN_DEBUG " %s zone: %lu pages reserved\n",
zone_names[0], dma_reserve);
}
if (!is_highmem_idx(j))
nr_kernel_pages += freesize;
/* Charge for highmem memmap if there are enough kernel pages */
else if (nr_kernel_pages > memmap_pages * 2)
nr_kernel_pages -= memmap_pages;
nr_all_pages += freesize;
/*
* Set an approximate value for lowmem here, it will be adjusted
* when the bootmem allocator frees pages into the buddy system.
* And all highmem pages will be managed by the buddy system.
*/
zone_init_internals(zone, j, nid, freesize);
if (!size)
continue;
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);
}
}
#ifdef CONFIG_FLAT_NODE_MEM_MAP
static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
{
unsigned long __maybe_unused start = 0;
unsigned long __maybe_unused offset = 0;
/* Skip empty nodes */
if (!pgdat->node_spanned_pages)
return;
start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
offset = pgdat->node_start_pfn - start;
/* ia64 gets its own node_mem_map, before this, without bootmem */
if (!pgdat->node_mem_map) {
unsigned long size, end;
struct page *map;
/*
* The zone's endpoints aren't required to be MAX_ORDER
* aligned but the node_mem_map endpoints must be in order
* for the buddy allocator to function correctly.
*/
end = pgdat_end_pfn(pgdat);
end = ALIGN(end, MAX_ORDER_NR_PAGES);
size = (end - start) * sizeof(struct page);
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",
__func__, pgdat->node_id, (unsigned long)pgdat,
(unsigned long)pgdat->node_mem_map);
#ifndef CONFIG_NEED_MULTIPLE_NODES
/*
* With no DISCONTIG, the global mem_map is just set as node 0's
*/
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
}
#else
static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { }
#endif /* CONFIG_FLAT_NODE_MEM_MAP */
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static inline void pgdat_set_deferred_range(pg_data_t *pgdat)
{
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)
{
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);
pgdat->node_id = nid;
pgdat->node_start_pfn = node_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);
alloc_node_mem_map(pgdat);
pgdat_set_deferred_range(pgdat);
free_area_init_core(pgdat);
}
#if !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)
{
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;
}
/*
* 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=.
*/
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;
}
pgcnt += zero_pfn_range(PFN_DOWN(next), max_pfn);
/*
* 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_FLAT_NODE_MEM_MAP */
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
#if MAX_NUMNODES > 1
/*
* Figure out the number of possible node ids.
*/
void __init setup_nr_node_ids(void)
{
unsigned int highest;
highest = find_last_bit(node_possible_map.bits, MAX_NUMNODES);
nr_node_ids = highest + 1;
}
#endif
/**
* node_map_pfn_alignment - determine the maximum internode alignment
*
* This function should be called after node map is populated and sorted.
* It calculates the maximum power of two alignment which can distinguish
* all the nodes.
*
* For example, if all nodes are 1GiB and aligned to 1GiB, the return value
* would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the
* nodes are shifted by 256MiB, 256MiB. Note that if only the last node is
* shifted, 1GiB is enough and this function will indicate so.
*
* This is used to test whether pfn -> nid mapping of the chosen memory
* model has fine enough granularity to avoid incorrect mapping for the
* populated node map.
*
* 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 = NUMA_NO_NODE;
int i, nid;
for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
if (!start || last_nid < 0 || last_nid == nid) {
last_nid = nid;
last_end = end;
continue;
}
/*
* Start with a mask granular enough to pin-point to the
* start pfn and tick off bits one-by-one until it becomes
* too coarse to separate the current node from the last.
*/
mask = ~((1 << __ffs(start)) - 1);
while (mask && last_end <= (start & (mask << 1)))
mask <<= 1;
/* accumulate all internode masks */
accl_mask |= mask;
}
/* convert mask to number of pages */
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
*
* 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);
}
/*
* early_calculate_totalpages()
* Sum pages in active regions for movable zone.
* Populate N_MEMORY for calculating usable_nodes.
*/
static unsigned long __init early_calculate_totalpages(void)
{
unsigned long totalpages = 0;
unsigned long start_pfn, end_pfn;
int i, nid;
for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
unsigned long pages = end_pfn - start_pfn;
totalpages += pages;
if (pages)
node_set_state(nid, N_MEMORY);
}
return totalpages;
}
/*
* Find the PFN the Movable zone begins in each node. Kernel memory
* is spread evenly between nodes as long as the nodes have enough
* memory. When they don't, some nodes will have more kernelcore than
* others
*/
static void __init find_zone_movable_pfns_for_nodes(void)
{
int i, nid;
unsigned long usable_startpfn;
unsigned long kernelcore_node, kernelcore_remaining;
/* save the state before borrow the nodemask */
nodemask_t saved_node_state = node_states[N_MEMORY];
unsigned long totalpages = early_calculate_totalpages();
int usable_nodes = nodes_weight(node_states[N_MEMORY]);
struct memblock_region *r;
/* Need to find movable_zone earlier when movable_node is specified. */
find_usable_zone_for_movable();
/*
* If movable_node is specified, ignore kernelcore and movablecore
* options.
*/
if (movable_node_is_enabled()) {
for_each_memblock(memory, r) {
if (!memblock_is_hotpluggable(r))
continue;
nid = r->nid;
usable_startpfn = PFN_DOWN(r->base);
zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
min(usable_startpfn, zone_movable_pfn[nid]) :
usable_startpfn;
}
goto out2;
}
/*
* If kernelcore=mirror is specified, ignore movablecore option
*/
if (mirrored_kernelcore) {
bool mem_below_4gb_not_mirrored = false;
for_each_memblock(memory, r) {
if (memblock_is_mirror(r))
continue;
nid = r->nid;
usable_startpfn = memblock_region_memory_base_pfn(r);
if (usable_startpfn < 0x100000) {
mem_below_4gb_not_mirrored = true;
continue;
}
zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
min(usable_startpfn, zone_movable_pfn[nid]) :
usable_startpfn;
}
if (mem_below_4gb_not_mirrored)
pr_warn("This configuration results in unmirrored kernel memory.");
goto out2;
}
/*
* If kernelcore=nn% or movablecore=nn% was specified, calculate the
* amount of necessary memory.
*/
if (required_kernelcore_percent)
required_kernelcore = (totalpages * 100 * required_kernelcore_percent) /
10000UL;
if (required_movablecore_percent)
required_movablecore = (totalpages * 100 * required_movablecore_percent) /
10000UL;
/*
* If movablecore= was specified, calculate what size of
* kernelcore that corresponds so that memory usable for
* any allocation type is evenly spread. If both kernelcore
* and movablecore are specified, then the value of kernelcore
* will be used for required_kernelcore if it's greater than
* what movablecore would have allowed.
*/
if (required_movablecore) {
unsigned long corepages;
/*
* Round-up so that ZONE_MOVABLE is at least as large as what
* was requested by the user
*/
required_movablecore =
roundup(required_movablecore, MAX_ORDER_NR_PAGES);
required_movablecore = min(totalpages, required_movablecore);
corepages = totalpages - required_movablecore;
required_kernelcore = max(required_kernelcore, corepages);
}
/*
* If kernelcore was not specified or kernelcore size is larger
* than totalpages, there is no ZONE_MOVABLE.
*/
if (!required_kernelcore || required_kernelcore >= totalpages)
goto out;
/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];
restart:
/* Spread kernelcore memory as evenly as possible throughout nodes */
kernelcore_node = required_kernelcore / usable_nodes;
for_each_node_state(nid, N_MEMORY) {
unsigned long start_pfn, end_pfn;
/*
* Recalculate kernelcore_node if the division per node
* now exceeds what is necessary to satisfy the requested
* amount of memory for the kernel
*/
if (required_kernelcore < kernelcore_node)
kernelcore_node = required_kernelcore / usable_nodes;
/*
* As the map is walked, we track how much memory is usable
* by the kernel using kernelcore_remaining. When it is
* 0, the rest of the node is usable by ZONE_MOVABLE
*/
kernelcore_remaining = kernelcore_node;
/* Go through each range of PFNs within this node */
for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
unsigned long size_pages;
start_pfn = max(start_pfn, zone_movable_pfn[nid]);
if (start_pfn >= end_pfn)
continue;
/* Account for what is only usable for kernelcore */
if (start_pfn < usable_startpfn) {
unsigned long kernel_pages;
kernel_pages = min(end_pfn, usable_startpfn)
- start_pfn;
kernelcore_remaining -= min(kernel_pages,
kernelcore_remaining);
required_kernelcore -= min(kernel_pages,
required_kernelcore);
/* Continue if range is now fully accounted */
if (end_pfn <= usable_startpfn) {
/*
* Push zone_movable_pfn to the end so
* that if we have to rebalance
* kernelcore across nodes, we will
* not double account here
*/
zone_movable_pfn[nid] = end_pfn;
continue;
}
start_pfn = usable_startpfn;
}
/*
* The usable PFN range for ZONE_MOVABLE is from
* start_pfn->end_pfn. Calculate size_pages as the
* number of pages used as kernelcore
*/
size_pages = end_pfn - start_pfn;
if (size_pages > kernelcore_remaining)
size_pages = kernelcore_remaining;
zone_movable_pfn[nid] = start_pfn + size_pages;
/*
* Some kernelcore has been met, update counts and
* break if the kernelcore for this node has been
* satisfied
*/
required_kernelcore -= min(required_kernelcore,
size_pages);
kernelcore_remaining -= size_pages;
if (!kernelcore_remaining)
break;
}
}
/*
* If there is still required_kernelcore, we do another pass with one
* less node in the count. This will push zone_movable_pfn[nid] further
* along on the nodes that still have memory until kernelcore is
* satisfied
*/
usable_nodes--;
if (usable_nodes && required_kernelcore > usable_nodes)
goto restart;
out2:
/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
for (nid = 0; nid < MAX_NUMNODES; nid++)
zone_movable_pfn[nid] =
roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
out:
/* restore the node_state */
node_states[N_MEMORY] = saved_node_state;
}
/* Any regular or high memory on that node ? */
static void check_for_memory(pg_data_t *pgdat, int nid)
{
enum zone_type zone_type;
for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
struct zone *zone = &pgdat->node_zones[zone_type];
if (populated_zone(zone)) {
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;
}
}
}
/**
* free_area_init_nodes - 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.
* Using the page ranges provided by memblock_set_node(), the size of each
* zone in each node and their holes is calculated. If the maximum PFN
* between two adjacent zones match, it is assumed that the zone is empty.
* For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed
* that arch_max_dma32_pfn has no pages. It is also assumed that a zone
* 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)
{
unsigned long start_pfn, end_pfn;
int i, nid;
/* Record where the zone boundaries are */
memset(arch_zone_lowest_possible_pfn, 0,
sizeof(arch_zone_lowest_possible_pfn));
memset(arch_zone_highest_possible_pfn, 0,
sizeof(arch_zone_highest_possible_pfn));
start_pfn = find_min_pfn_with_active_regions();
for (i = 0; i < MAX_NR_ZONES; i++) {
if (i == 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;
start_pfn = end_pfn;
}
/* Find the PFNs that ZONE_MOVABLE begins at in each node */
memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
find_zone_movable_pfns_for_nodes();
/* Print out the zone ranges */
pr_info("Zone ranges:\n");
for (i = 0; i < MAX_NR_ZONES; i++) {
if (i == ZONE_MOVABLE)
continue;
pr_info(" %-8s ", zone_names[i]);
if (arch_zone_lowest_possible_pfn[i] ==
arch_zone_highest_possible_pfn[i])
pr_cont("empty\n");
else
pr_cont("[mem %#018Lx-%#018Lx]\n",
(u64)arch_zone_lowest_possible_pfn[i]
<< PAGE_SHIFT,
((u64)arch_zone_highest_possible_pfn[i]
<< PAGE_SHIFT) - 1);
}
/* Print out the PFNs ZONE_MOVABLE begins at in each node */
pr_info("Movable zone start for each node\n");
for (i = 0; i < MAX_NUMNODES; i++) {
if (zone_movable_pfn[i])
pr_info(" Node %d: %#018Lx\n", i,
(u64)zone_movable_pfn[i] << PAGE_SHIFT);
}
/*
* 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) {
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);
/* Any memory on that node */
if (pgdat->node_present_pages)
node_set_state(nid, N_MEMORY);
check_for_memory(pgdat, nid);
}
}
static int __init cmdline_parse_core(char *p, unsigned long *core,
unsigned long *percent)
{
unsigned long long coremem;
char *endptr;
if (!p)
return -EINVAL;
/* Value may be a percentage of total memory, otherwise bytes */
coremem = simple_strtoull(p, &endptr, 0);
if (*endptr == '%') {
/* Paranoid check for percent values greater than 100 */
WARN_ON(coremem > 100);
*percent = coremem;
} else {
coremem = memparse(p, &p);
/* Paranoid check that UL is enough for the coremem value */
WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);
*core = coremem >> PAGE_SHIFT;
*percent = 0UL;
}
return 0;
}
/*
* kernelcore=size sets the amount of memory for use for allocations that
* cannot be reclaimed or migrated.
*/
static int __init cmdline_parse_kernelcore(char *p)
{
/* parse kernelcore=mirror */
if (parse_option_str(p, "mirror")) {
mirrored_kernelcore = true;
return 0;
}
return cmdline_parse_core(p, &required_kernelcore,
&required_kernelcore_percent);
}
/*
* movablecore=size sets the amount of memory for use for allocations that
* can be reclaimed or migrated.
*/
static int __init cmdline_parse_movablecore(char *p)
{
return cmdline_parse_core(p, &required_movablecore,
&required_movablecore_percent);
}
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)
{
atomic_long_add(count, &page_zone(page)->managed_pages);
totalram_pages_add(count);
#ifdef CONFIG_HIGHMEM
if (PageHighMem(page))
totalhigh_pages_add(count);
#endif
}
EXPORT_SYMBOL(adjust_managed_page_count);
unsigned long free_reserved_area(void *start, void *end, int poison, const char *s)
{
void *pos;
unsigned long pages = 0;
start = (void *)PAGE_ALIGN((unsigned long)start);
end = (void *)((unsigned long)end & PAGE_MASK);
for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
struct page *page = virt_to_page(pos);
void *direct_map_addr;
/*
* 'direct_map_addr' might be different from 'pos'
* because some architectures' virt_to_page()
* work with aliases. Getting the direct map
* address ensures that we get a _writeable_
* alias for the memset().
*/
direct_map_addr = page_address(page);
if ((unsigned int)poison <= 0xFF)
memset(direct_map_addr, poison, PAGE_SIZE);
free_reserved_page(page);
}
if (pages && s)
pr_info("Freeing %s memory: %ldK\n",
s, pages << (PAGE_SHIFT - 10));
return pages;
}
#ifdef CONFIG_HIGHMEM
void free_highmem_page(struct page *page)
{
__free_reserved_page(page);
totalram_pages_inc();
atomic_long_inc(&page_zone(page)->managed_pages);
totalhigh_pages_inc();
}
#endif
void __init mem_init_print_info(const char *str)
{
unsigned long physpages, codesize, datasize, rosize, bss_size;
unsigned long init_code_size, init_data_size;
physpages = get_num_physpages();
codesize = _etext - _stext;
datasize = _edata - _sdata;
rosize = __end_rodata - __start_rodata;
bss_size = __bss_stop - __bss_start;
init_data_size = __init_end - __init_begin;
init_code_size = _einittext - _sinittext;
/*
* Detect special cases and adjust section sizes accordingly:
* 1) .init.* may be embedded into .data sections
* 2) .init.text.* may be out of [__init_begin, __init_end],
* please refer to arch/tile/kernel/vmlinux.lds.S.
* 3) .rodata.* may be embedded into .text or .data sections.
*/
#define adj_init_size(start, end, size, pos, adj) \
do { \
if (start <= pos && pos < end && size > adj) \
size -= adj; \
} while (0)
adj_init_size(__init_begin, __init_end, init_data_size,
_sinittext, init_code_size);
adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size);
adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size);
adj_init_size(_stext, _etext, codesize, __start_rodata, rosize);
adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize);
#undef adj_init_size
pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved"
#ifdef CONFIG_HIGHMEM
", %luK highmem"
#endif
"%s%s)\n",
nr_free_pages() << (PAGE_SHIFT - 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),
totalcma_pages << (PAGE_SHIFT - 10),
#ifdef CONFIG_HIGHMEM
totalhigh_pages() << (PAGE_SHIFT - 10),
#endif
str ? ", " : "", str ? str : "");
}
/**
* set_dma_reserve - set the specified number of pages reserved in the first zone
* @new_dma_reserve: The number of pages to mark reserved
*
* The per-cpu batchsize and zone watermarks are determined by managed_pages.
* In the DMA zone, a significant percentage may be consumed by kernel image
* and other unfreeable allocations which can skew the watermarks badly. This
* function may optionally be used to account for unfreeable pages in the
* first zone (e.g., ZONE_DMA). The effect will be lower watermarks and
* smaller per-cpu batchsize.
*/
void __init set_dma_reserve(unsigned long new_dma_reserve)
{
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)
{
lru_add_drain_cpu(cpu);
drain_pages(cpu);
/*
* Spill the event counters of the dead processor
* into the current processors event counters.
* This artificially elevates the count of the current
* processor.
*/
vm_events_fold_cpu(cpu);
/*
* Zero the differential counters of the dead processor
* so that the vm statistics are consistent.
*
* This is only okay since the processor is dead and cannot
* race with what we are doing.
*/
cpu_vm_stats_fold(cpu);
return 0;
}
#ifdef CONFIG_NUMA
int hashdist = HASHDIST_DEFAULT;
static int __init set_hashdist(char *str)
{
if (!str)
return 0;
hashdist = simple_strtoul(str, &str, 0);
return 1;
}
__setup("hashdist=", set_hashdist);
#endif
void __init page_alloc_init(void)
{
int ret;
#ifdef CONFIG_NUMA
if (num_node_state(N_MEMORY) == 1)
hashdist = 0;
#endif
ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC_DEAD,
"mm/page_alloc:dead", NULL,
page_alloc_cpu_dead);
WARN_ON(ret < 0);
}
/*
* calculate_totalreserve_pages - called when sysctl_lowmem_reserve_ratio
* or min_free_kbytes changes.
*/
static void calculate_totalreserve_pages(void)
{
struct pglist_data *pgdat;
unsigned long reserve_pages = 0;
enum zone_type i, j;
for_each_online_pgdat(pgdat) {
pgdat->totalreserve_pages = 0;
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++) {
if (zone->lowmem_reserve[j] > max)
max = zone->lowmem_reserve[j];
}
/* we treat the high watermark as reserved pages. */
max += high_wmark_pages(zone);
if (max > managed_pages)
max = managed_pages;
pgdat->totalreserve_pages += max;
reserve_pages += max;
}
}
totalreserve_pages = reserve_pages;
}
/*
* setup_per_zone_lowmem_reserve - called whenever
* sysctl_lowmem_reserve_ratio changes. Ensures that each zone
* has a correct pages reserved value, so an adequate number of
* pages are left in the zone after a successful __alloc_pages().
*/
static void setup_per_zone_lowmem_reserve(void)
{
struct pglist_data *pgdat;
enum zone_type j, idx;
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(zone);
zone->lowmem_reserve[j] = 0;
idx = j;
while (idx) {
struct zone *lower_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 += zone_managed_pages(lower_zone);
}
}
}
/* update totalreserve_pages */
calculate_totalreserve_pages();
}
static void __setup_per_zone_wmarks(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
struct zone *zone;
unsigned long flags;
/* Calculate total number of !ZONE_HIGHMEM pages */
for_each_zone(zone) {
if (!is_highmem(zone))
lowmem_pages += zone_managed_pages(zone);
}
for_each_zone(zone) {
u64 tmp;
spin_lock_irqsave(&zone->lock, flags);
tmp = (u64)pages_min * zone_managed_pages(zone);
do_div(tmp, lowmem_pages);
if (is_highmem(zone)) {
/*
* __GFP_HIGH and PF_MEMALLOC allocations usually don't
* need highmem pages, so cap pages_min to a small
* value here.
*
* The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
* deltas control async page reclaim, and so should
* not be capped for highmem.
*/
unsigned long min_pages;
min_pages = zone_managed_pages(zone) / 1024;
min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL);
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] = tmp;
}
/*
* Set the kswapd watermarks distance according to the
* scale factor in proportion to available memory, but
* ensure a minimum size on small systems.
*/
tmp = max_t(u64, tmp >> 2,
mult_frac(zone_managed_pages(zone),
watermark_scale_factor, 10000));
zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp;
zone->_watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
zone->watermark_boost = 0;
spin_unlock_irqrestore(&zone->lock, flags);
}
/* update totalreserve_pages */
calculate_totalreserve_pages();
}
/**
* setup_per_zone_wmarks - called when min_free_kbytes changes
* or when memory is hot-{added|removed}
*
* Ensures that the watermark[min,low,high] values for each zone are set
* correctly with respect to min_free_kbytes.
*/
void setup_per_zone_wmarks(void)
{
static DEFINE_SPINLOCK(lock);
spin_lock(&lock);
__setup_per_zone_wmarks();
spin_unlock(&lock);
}
/*
* 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
* bandwidth does not increase linearly with machine size. We use
*
* min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
* min_free_kbytes = sqrt(lowmem_kbytes * 16)
*
* which yields
*
* 16MB: 512k
* 32MB: 724k
* 64MB: 1024k
* 128MB: 1448k
* 256MB: 2048k
* 512MB: 2896k
* 1024MB: 4096k
* 2048MB: 5792k
* 4096MB: 8192k
* 8192MB: 11584k
* 16384MB: 16384k
*/
int __meminit init_per_zone_wmark_min(void)
{
unsigned long lowmem_kbytes;
int new_min_free_kbytes;
lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
if (new_min_free_kbytes > user_min_free_kbytes) {
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;
} 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);
}
setup_per_zone_wmarks();
refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
#ifdef CONFIG_NUMA
setup_min_unmapped_ratio();
setup_min_slab_ratio();
#endif
return 0;
}
core_initcall(init_per_zone_wmark_min)
/*
* min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
* that we can call two helper functions whenever min_free_kbytes
* changes.
*/
int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
if (write) {
user_min_free_kbytes = min_free_kbytes;
setup_per_zone_wmarks();
}
return 0;
}
int watermark_boost_factor_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
return 0;
}
int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
if (write)
setup_per_zone_wmarks();
return 0;
}
#ifdef CONFIG_NUMA
static void setup_min_unmapped_ratio(void)
{
pg_data_t *pgdat;
struct zone *zone;
for_each_online_pgdat(pgdat)
pgdat->min_unmapped_pages = 0;
for_each_zone(zone)
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)
{
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
setup_min_unmapped_ratio();
return 0;
}
static void setup_min_slab_ratio(void)
{
pg_data_t *pgdat;
struct zone *zone;
for_each_online_pgdat(pgdat)
pgdat->min_slab_pages = 0;
for_each_zone(zone)
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)
{
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
setup_min_slab_ratio();
return 0;
}
#endif
/*
* lowmem_reserve_ratio_sysctl_handler - just a wrapper around
* proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
* whenever sysctl_lowmem_reserve_ratio changes.
*
* The reserve ratio obviously has absolutely no relation with the
* minimum watermarks. The lowmem reserve ratio can only make sense
* 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)
{
proc_dointvec_minmax(table, write, buffer, length, ppos);
setup_per_zone_lowmem_reserve();
return 0;
}
/*
* percpu_pagelist_fraction - changes the pcp->high for each zone on each
* cpu. It is the fraction of total pages in each zone that a hot per cpu
* 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)
{
struct zone *zone;
int old_percpu_pagelist_fraction;
int ret;
mutex_lock(&pcp_batch_high_lock);
old_percpu_pagelist_fraction = percpu_pagelist_fraction;
ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (!write || ret < 0)
goto out;
/* Sanity checking to avoid pcp imbalance */
if (percpu_pagelist_fraction &&
percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) {
percpu_pagelist_fraction = old_percpu_pagelist_fraction;
ret = -EINVAL;
goto out;
}
/* No change? */
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));
}
out:
mutex_unlock(&pcp_batch_high_lock);
return ret;
}
#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES
/*
* Returns the number of pages that arch has reserved but
* is not known to alloc_large_system_hash().
*/
static unsigned long __init arch_reserved_kernel_pages(void)
{
return 0;
}
#endif
/*
* Adaptive scale is meant to reduce sizes of hash tables on large memory
* machines. As memory size is increased the scale is also increased but at
* slower pace. Starting from ADAPT_SCALE_BASE (64G), every time memory
* quadruples the scale is increased by one, which means the size of hash table
* only doubles, instead of quadrupling as well.
* Because 32-bit systems cannot have large physical memory, where this scaling
* makes sense, it is disabled on such platforms.
*/
#if __BITS_PER_LONG > 32
#define ADAPT_SCALE_BASE (64ul << 30)
#define ADAPT_SCALE_SHIFT 2
#define ADAPT_SCALE_NPAGES (ADAPT_SCALE_BASE >> PAGE_SHIFT)
#endif
/*
* allocate a large system hash table from bootmem
* - it is assumed that the hash table must contain an exact power-of-2
* quantity of entries
* - limit is the number of hash buckets, not the total allocation size
*/
void *__init alloc_large_system_hash(const char *tablename,
unsigned long bucketsize,
unsigned long numentries,
int scale,
int flags,
unsigned int *_hash_shift,
unsigned int *_hash_mask,
unsigned long low_limit,
unsigned long high_limit)
{
unsigned long long max = high_limit;
unsigned long log2qty, size;
void *table = NULL;
gfp_t gfp_flags;
bool virt;
/* allow the kernel cmdline to have a say */
if (!numentries) {
/* round applicable memory size up to nearest megabyte */
numentries = nr_kernel_pages;
numentries -= arch_reserved_kernel_pages();
/* It isn't necessary when PAGE_SIZE >= 1MB */
if (PAGE_SHIFT < 20)
numentries = round_up(numentries, (1<<20)/PAGE_SIZE);
#if __BITS_PER_LONG > 32
if (!high_limit) {
unsigned long adapt;
for (adapt = ADAPT_SCALE_NPAGES; adapt < numentries;
adapt <<= ADAPT_SCALE_SHIFT)
scale++;
}
#endif
/* limit to 1 bucket per 2^scale bytes of low memory */
if (scale > PAGE_SHIFT)
numentries >>= (scale - PAGE_SHIFT);
else
numentries <<= (PAGE_SHIFT - scale);
/* Make sure we've got at least a 0-order allocation.. */
if (unlikely(flags & HASH_SMALL)) {
/* Makes no sense without HASH_EARLY */
WARN_ON(!(flags & HASH_EARLY));
if (!(numentries >> *_hash_shift)) {
numentries = 1UL << *_hash_shift;
BUG_ON(!numentries);
}
} else if (unlikely((numentries * bucketsize) < PAGE_SIZE))
numentries = PAGE_SIZE / bucketsize;
}
numentries = roundup_pow_of_two(numentries);
/* limit allocation size to 1/16 total memory by default */
if (max == 0) {
max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
do_div(max, bucketsize);
}
max = min(max, 0x80000000ULL);
if (numentries < low_limit)
numentries = low_limit;
if (numentries > max)
numentries = max;
log2qty = ilog2(numentries);
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_alloc(size, SMP_CACHE_BYTES);
else
table = memblock_alloc_raw(size,
SMP_CACHE_BYTES);
} else if (get_order(size) >= MAX_ORDER || hashdist) {
table = __vmalloc(size, gfp_flags, PAGE_KERNEL);
virt = true;
} else {
/*
* If bucketsize is not a power-of-two, we may free
* some pages at the end of hash table which
* alloc_pages_exact() automatically does
*/
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, %s)\n",
tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size,
virt ? "vmalloc" : "linear");
if (_hash_shift)
*_hash_shift = log2qty;
if (_hash_mask)
*_hash_mask = (1 << log2qty) - 1;
return table;
}
/*
* 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.
*/
bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
int migratetype, int flags)
{
unsigned long found;
unsigned long iter = 0;
unsigned long pfn = page_to_pfn(page);
const char *reason = "unmovable page";
/*
* 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 false;
reason = "CMA page";
goto unmovable;
}
for (found = 0; iter < pageblock_nr_pages; iter++) {
unsigned long check = pfn + iter;
if (!pfn_valid_within(check))
continue;
page = pfn_to_page(check);
if (PageReserved(page))
goto unmovable;
/*
* If the zone is movable and we have ruled out all reserved
* pages then it should be reasonably safe to assume the rest
* is movable.
*/
if (zone_idx(zone) == ZONE_MOVABLE)
continue;
/*
* Hugepages are not in LRU lists, but they're movable.
* We need not scan over tail pages because we don't
* handle each tail page individually in migration.
*/
if (PageHuge(page)) {
struct page *head = compound_head(page);
unsigned int skip_pages;
if (!hugepage_migration_supported(page_hstate(head)))
goto unmovable;
skip_pages = compound_nr(head) - (page - head);
iter += skip_pages - 1;
continue;
}
/*
* We can't use page_count without pin a page
* because another CPU can free compound page.
* This check already skips compound tails of THP
* because their page->_refcount is zero at all time.
*/
if (!page_ref_count(page)) {
if (PageBuddy(page))
iter += (1 << page_order(page)) - 1;
continue;
}
/*
* The HWPoisoned page may be not in buddy system, and
* page_count() is not 0.
*/
if ((flags & SKIP_HWPOISON) && PageHWPoison(page))
continue;
if (__PageMovable(page))
continue;
if (!PageLRU(page))
found++;
/*
* 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 false;
unmovable:
WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
if (flags & REPORT_FAILURE)
dump_page(pfn_to_page(pfn + iter), reason);
return true;
}
#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)
{
return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
pageblock_nr_pages));
}
/* [start, end) must belong to a single zone. */
static int __alloc_contig_migrate_range(struct compact_control *cc,
unsigned long start, unsigned long end)
{
/* This function is based on compact_zone() from compaction.c. */
unsigned long nr_reclaimed;
unsigned long pfn = start;
unsigned int tries = 0;
int ret = 0;
migrate_prep();
while (pfn < end || !list_empty(&cc->migratepages)) {
if (fatal_signal_pending(current)) {
ret = -EINTR;
break;
}
if (list_empty(&cc->migratepages)) {
cc->nr_migratepages = 0;
pfn = isolate_migratepages_range(cc, pfn, end);
if (!pfn) {
ret = -EINTR;
break;
}
tries = 0;
} else if (++tries == 5) {
ret = ret < 0 ? ret : -EBUSY;
break;
}
nr_reclaimed = reclaim_clean_pages_from_list(cc->zone,
&cc->migratepages);
cc->nr_migratepages -= nr_reclaimed;
ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
NULL, 0, cc->mode, MR_CONTIG_RANGE);
}
if (ret < 0) {
putback_movable_pages(&cc->migratepages);
return ret;
}
return 0;
}
/**
* alloc_contig_range() -- tries to allocate given range of pages
* @start: start PFN to allocate
* @end: one-past-the-last PFN to allocate
* @migratetype: migratetype of the underlaying pageblocks (either
* #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks
* in range must have the same migratetype and it must
* be either of the two.
* @gfp_mask: GFP mask to use during compaction
*
* The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
* aligned. The PFN range must belong to a single zone.
*
* The first thing this routine does is attempt to MIGRATE_ISOLATE all
* pageblocks in the range. Once isolated, the pageblocks should not
* be modified by others.
*
* 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 long outer_start, outer_end;
unsigned int order;
int ret = 0;
struct compact_control cc = {
.nr_migratepages = 0,
.order = -1,
.zone = page_zone(pfn_to_page(start)),
.mode = MIGRATE_SYNC,
.ignore_skip_hint = true,
.no_set_skip_hint = true,
.gfp_mask = current_gfp_context(gfp_mask),
};
INIT_LIST_HEAD(&cc.migratepages);
/*
* What we do here is we mark all pageblocks in range as
* MIGRATE_ISOLATE. Because pageblock and max order pages may
* have different sizes, and due to the way page allocator
* work, we align the range to biggest of the two pages so
* that page allocator won't try to merge buddies from
* different pageblocks and change MIGRATE_ISOLATE to some
* other migration type.
*
* Once the pageblocks are marked as MIGRATE_ISOLATE, we
* migrate the pages from an unaligned range (ie. pages that
* we are interested in). This will put all the pages in
* range back to page allocator as MIGRATE_ISOLATE.
*
* When this is done, we take the pages in range from page
* allocator removing them from the buddy system. This way
* page allocator will never consider using them.
*
* This lets us mark the pageblocks back as
* MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the
* aligned range but not in the unaligned, original range are
* put back to page allocator so that buddy can use them.
*/
ret = start_isolate_page_range(pfn_max_align_down(start),
pfn_max_align_up(end), migratetype, 0);
if (ret < 0)
return ret;
/*
* In case of -EBUSY, we'd like to know which page causes problem.
* So, just fall through. test_pages_isolated() has a tracepoint
* which will report the busy page.
*
* It is possible that busy pages could become available before
* the call to test_pages_isolated, and the range will actually be
* 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)
goto done;
ret =0;
/*
* Pages from [start, end) are within a MAX_ORDER_NR_PAGES
* aligned blocks that are marked as MIGRATE_ISOLATE. What's
* more, all pages in [start, end) are free in page allocator.
* What we are going to do is to allocate all pages from
* [start, end) (that is remove them from page allocator).
*
* The only problem is that pages at the beginning and at the
* end of interesting range may be not aligned with pages that
* page allocator holds, ie. they can be part of higher order
* pages. Because of this, we reserve the bigger range and
* once this is done free the pages we are not interested in.
*
* We don't have to hold zone->lock here because the pages are
* isolated thus they won't get removed from buddy.
*/
lru_add_drain_all();
order = 0;
outer_start = start;
while (!PageBuddy(pfn_to_page(outer_start))) {
if (++order >= MAX_ORDER) {
outer_start = start;
break;
}
outer_start &= ~0UL << order;
}
if (outer_start != start) {
order = page_order(pfn_to_page(outer_start));
/*
* outer_start page could be small order buddy page and
* it doesn't include start page. Adjust outer_start
* in this case to report failed page properly
* on tracepoint in test_pages_isolated()
*/
if (outer_start + (1UL << order) <= start)
outer_start = start;
}
/* Make sure the range is really isolated. */
if (test_pages_isolated(outer_start, end, false)) {
pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
__func__, outer_start, end);
ret = -EBUSY;
goto done;
}
/* Grab isolated pages from freelists. */
outer_end = isolate_freepages_range(&cc, outer_start, end);
if (!outer_end) {
ret = -EBUSY;
goto done;
}
/* Free head and tail (if any) */
if (start != outer_start)
free_contig_range(outer_start, start - outer_start);
if (end != outer_end)
free_contig_range(end, outer_end - end);
done:
undo_isolate_page_range(pfn_max_align_down(start),
pfn_max_align_up(end), migratetype);
return ret;
}
#endif /* CONFIG_CONTIG_ALLOC */
void free_contig_range(unsigned long pfn, unsigned int nr_pages)
{
unsigned int count = 0;
for (; nr_pages--; pfn++) {
struct page *page = pfn_to_page(pfn);
count += page_count(page) != 1;
__free_page(page);
}
WARN(count != 0, "%d pages are still in use!\n", count);
}
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* The zone indicated has a new number of managed_pages; batch sizes and percpu
* page high values need to be recalulated.
*/
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));
mutex_unlock(&pcp_batch_high_lock);
}
#endif
void zone_pcp_reset(struct zone *zone)
{
unsigned long flags;
int cpu;
struct per_cpu_pageset *pset;
/* avoid races with drain_pages() */
local_irq_save(flags);
if (zone->pageset != &boot_pageset) {
for_each_online_cpu(cpu) {
pset = per_cpu_ptr(zone->pageset, cpu);
drain_zonestat(zone, pset);
}
free_percpu(zone->pageset);
zone->pageset = &boot_pageset;
}
local_irq_restore(flags);
}
#ifdef CONFIG_MEMORY_HOTREMOVE
/*
* All pages in the range must be in a single zone and isolated
* before calling this.
*/
unsigned long
__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
struct page *page;
struct zone *zone;
unsigned int order, i;
unsigned long pfn;
unsigned long flags;
unsigned long offlined_pages = 0;
/* find the first valid pfn */
for (pfn = start_pfn; pfn < end_pfn; pfn++)
if (pfn_valid(pfn))
break;
if (pfn == end_pfn)
return offlined_pages;
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
* page_count() is not 0.
*/
if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
pfn++;
SetPageReserved(page);
offlined_pages++;
continue;
}
BUG_ON(page_count(page));
BUG_ON(!PageBuddy(page));
order = page_order(page);
offlined_pages += 1 << order;
#ifdef CONFIG_DEBUG_VM
pr_info("remove from free list %lx %d %lx\n",
pfn, 1 << order, end_pfn);
#endif
del_page_from_free_area(page, &zone->free_area[order]);
for (i = 0; i < (1 << order); i++)
SetPageReserved((page+i));
pfn += (1 << order);
}
spin_unlock_irqrestore(&zone->lock, flags);
return offlined_pages;
}
#endif
bool is_free_buddy_page(struct page *page)
{
struct zone *zone = page_zone(page);
unsigned long pfn = page_to_pfn(page);
unsigned long flags;
unsigned int order;
spin_lock_irqsave(&zone->lock, flags);
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)
break;
}
spin_unlock_irqrestore(&zone->lock, flags);
return order < MAX_ORDER;
}
#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.
*/
bool set_hwpoison_free_buddy_page(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;
spin_lock_irqsave(&zone->lock, flags);
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 (!TestSetPageHWPoison(page))
hwpoisoned = true;
break;
}
}
spin_unlock_irqrestore(&zone->lock, flags);
return hwpoisoned;
}
#endif