// 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)
*/
/* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */ typedefint __bitwise fpi_t;
/* No special request */ #define FPI_NONE ((__force fpi_t)0)
/* * Skip free page reporting notification for the (possibly merged) page. * This does not hinder free page reporting from grabbing the page, * reporting it and marking it "reported" - it only skips notifying * the free page reporting infrastructure about a newly freed page. For * example, used when temporarily pulling a page from a freelist and * putting it back unmodified.
*/ #define FPI_SKIP_REPORT_NOTIFY ((__force fpi_t)BIT(0))
/* * Place the (possibly merged) page to the tail of the freelist. Will ignore * page shuffling (relevant code - e.g., memory onlining - is expected to * shuffle the whole zone). * * Note: No code should rely on this flag for correctness - it's purely * to allow for optimizations when handing back either fresh pages * (memory onlining) or untouched pages (page isolation, free page * reporting).
*/ #define FPI_TO_TAIL ((__force fpi_t)BIT(1))
/* Free the page without taking locks. Rely on trylock only. */ #define FPI_TRYLOCK ((__force fpi_t)BIT(2))
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8)
#ifdefined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) /* * On SMP, spin_trylock is sufficient protection. * On PREEMPT_RT, spin_trylock is equivalent on both SMP and UP.
*/ #define pcp_trylock_prepare(flags) do { } while (0) #define pcp_trylock_finish(flag) do { } while (0) #else
/* UP spin_trylock always succeeds so disable IRQs to prevent re-entrancy. */ #define pcp_trylock_prepare(flags) local_irq_save(flags) #define pcp_trylock_finish(flags) local_irq_restore(flags) #endif
/* * Locking a pcp requires a PCP lookup followed by a spinlock. To avoid * a migration causing the wrong PCP to be locked and remote memory being * potentially allocated, pin the task to the CPU for the lookup+lock. * preempt_disable is used on !RT because it is faster than migrate_disable. * migrate_disable is used on RT because otherwise RT spinlock usage is * interfered with and a high priority task cannot preempt the allocator.
*/ #ifndef CONFIG_PREEMPT_RT #define pcpu_task_pin() preempt_disable() #define pcpu_task_unpin() preempt_enable() #else #define pcpu_task_pin() migrate_disable() #define pcpu_task_unpin() migrate_enable() #endif
/* * Generic helper to lookup and a per-cpu variable with an embedded spinlock. * Return value should be used with equivalent unlock helper.
*/ #define pcpu_spin_lock(type, member, ptr) \
({ \
type *_ret; \
pcpu_task_pin(); \
_ret = this_cpu_ptr(ptr); \
spin_lock(&_ret->member); \
_ret; \
})
#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_); #endif
/* * 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
*/ staticint 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,
};
staticbool page_contains_unaccepted(struct page *page, unsignedint order); staticbool cond_accept_memory(struct zone *zone, unsignedint order, int alloc_flags); staticbool __free_unaccepted(struct page *page);
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.
*/
DEFINE_STATIC_KEY_TRUE(deferred_pages);
/* * 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.
*/ staticbool __ref
_deferred_grow_zone(struct zone *zone, unsignedint order)
{ return deferred_grow_zone(zone, order);
} #else staticinlinebool deferred_pages_enabled(void)
{ returnfalse;
}
/** * __get_pfnblock_flags_mask - Return the requested group of flags for * a pageblock_nr_pages block of pages * @page: The page within the block of interest * @pfn: The target page frame number * @mask: mask of bits that the caller is interested in * * Return: pageblock_bits flags
*/ staticunsignedlong __get_pfnblock_flags_mask(conststruct page *page, unsignedlong pfn, unsignedlong mask)
{ unsignedlong *bitmap_word; unsignedlong bitidx; unsignedlong word;
get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx); /* * This races, without locks, with set_pfnblock_migratetype(). Ensure * a consistent read of the memory array, so that results, even though * racy, are not corrupted.
*/
word = READ_ONCE(*bitmap_word); return (word >> bitidx) & mask;
}
/** * get_pfnblock_bit - Check if a standalone bit of a pageblock is set * @page: The page within the block of interest * @pfn: The target page frame number * @pb_bit: pageblock bit to check * * Return: true if the bit is set, otherwise false
*/ bool get_pfnblock_bit(conststruct page *page, unsignedlong pfn, enum pageblock_bits pb_bit)
{ unsignedlong *bitmap_word; unsignedlong bitidx;
if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit))) returnfalse;
/** * get_pfnblock_migratetype - Return the migratetype of a pageblock * @page: The page within the block of interest * @pfn: The target page frame number * * Return: The migratetype of the pageblock * * Use get_pfnblock_migratetype() if caller already has both @page and @pfn * to save a call to page_to_pfn().
*/
__always_inline enum migratetype
get_pfnblock_migratetype(conststruct page *page, unsignedlong pfn)
{ unsignedlong mask = MIGRATETYPE_AND_ISO_MASK; unsignedlong flags;
/** * __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 * @pfn: The target page frame number * @flags: The flags to set * @mask: mask of bits that the caller is interested in
*/ staticvoid __set_pfnblock_flags_mask(struct page *page, unsignedlong pfn, unsignedlong flags, unsignedlong mask)
{ unsignedlong *bitmap_word; unsignedlong bitidx; unsignedlong word;
word = READ_ONCE(*bitmap_word); do {
} while (!try_cmpxchg(bitmap_word, &word, (word & ~mask) | flags));
}
/** * set_pfnblock_bit - Set a standalone bit of a pageblock * @page: The page within the block of interest * @pfn: The target page frame number * @pb_bit: pageblock bit to set
*/ void set_pfnblock_bit(conststruct page *page, unsignedlong pfn, enum pageblock_bits pb_bit)
{ unsignedlong *bitmap_word; unsignedlong bitidx;
if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit))) return;
/** * clear_pfnblock_bit - Clear a standalone bit of a pageblock * @page: The page within the block of interest * @pfn: The target page frame number * @pb_bit: pageblock bit to clear
*/ void clear_pfnblock_bit(conststruct page *page, unsignedlong pfn, enum pageblock_bits pb_bit)
{ unsignedlong *bitmap_word; unsignedlong bitidx;
if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit))) return;
/** * set_pageblock_migratetype - Set the migratetype of a pageblock * @page: The page within the block of interest * @migratetype: migratetype to set
*/ staticvoid set_pageblock_migratetype(struct page *page, enum migratetype migratetype)
{ if (unlikely(page_group_by_mobility_disabled &&
migratetype < MIGRATE_PCPTYPES))
migratetype = MIGRATE_UNMOVABLE;
#ifdef CONFIG_MEMORY_ISOLATION if (migratetype == MIGRATE_ISOLATE) {
VM_WARN_ONCE(1, "Use set_pageblock_isolate() for pageblock isolation"); return;
}
VM_WARN_ONCE(get_pfnblock_bit(page, page_to_pfn(page),
PB_migrate_isolate), "Use clear_pageblock_isolate() to unisolate pageblock"); /* MIGRATETYPE_AND_ISO_MASK clears PB_migrate_isolate if it is set */ #endif
__set_pfnblock_flags_mask(page, page_to_pfn(page),
(unsignedlong)migratetype,
MIGRATETYPE_AND_ISO_MASK);
}
/* * Temporary debugging check for pages not lying within a given zone.
*/ staticbool __maybe_unused bad_range(struct zone *zone, struct page *page)
{ if (page_outside_zone_boundaries(zone, page)) returntrue; if (zone != page_zone(page)) returntrue;
/* * 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);
print_modules();
dump_stack();
out: /* Leave bad fields for debug, except PageBuddy could make trouble */ if (PageBuddy(page))
__ClearPageBuddy(page);
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
staticinlineunsignedint order_to_pindex(int migratetype, int order)
{
staticinlineint pindex_to_order(unsignedint pindex)
{ int order = pindex / MIGRATE_PCPTYPES;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pindex >= NR_LOWORDER_PCP_LISTS)
order = HPAGE_PMD_ORDER; #else
VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); #endif
return order;
}
staticinlinebool pcp_allowed_order(unsignedint order)
{ if (order <= PAGE_ALLOC_COSTLY_ORDER) returntrue; #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (order == HPAGE_PMD_ORDER) returntrue; #endif returnfalse;
}
/* * 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_order holds the order of allocation. * This usage means that zero-order pages may not be compound.
*/
void prep_compound_page(struct page *page, unsignedint order)
{ int i; int nr_pages = 1 << order;
__SetPageHead(page); for (i = 1; i < nr_pages; i++)
prep_compound_tail(page, i);
staticinlinebool
compaction_capture(struct capture_control *capc, struct page *page, int order, int migratetype)
{ if (!capc || order != capc->cc->order) returnfalse;
/* Do not accidentally pollute CMA or isolated regions*/ if (is_migrate_cma(migratetype) ||
is_migrate_isolate(migratetype)) returnfalse;
/* * Do not let lower order allocations pollute a movable pageblock * unless compaction is also requesting movable pages. * 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 &&
capc->cc->migratetype != MIGRATE_MOVABLE) returnfalse;
if (migratetype != capc->cc->migratetype)
trace_mm_page_alloc_extfrag(page, capc->cc->order, order,
capc->cc->migratetype, migratetype);
capc->page = page; returntrue;
}
#else staticinlinestruct capture_control *task_capc(struct zone *zone)
{ return NULL;
}
staticinlinebool
compaction_capture(struct capture_control *capc, struct page *page, int order, int migratetype)
{ returnfalse;
} #endif/* CONFIG_COMPACTION */
staticinlinevoid account_freepages(struct zone *zone, int nr_pages, int migratetype)
{
lockdep_assert_held(&zone->lock);
/* Used for pages not on another list */ staticinlinevoid __add_to_free_list(struct page *page, struct zone *zone, unsignedint order, int migratetype, bool tail)
{ struct free_area *area = &zone->free_area[order]; int nr_pages = 1 << order;
VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype, "page type is %d, passed migratetype is %d (nr=%d)\n",
get_pageblock_migratetype(page), migratetype, nr_pages);
if (tail)
list_add_tail(&page->buddy_list, &area->free_list[migratetype]); else
list_add(&page->buddy_list, &area->free_list[migratetype]);
area->nr_free++;
if (order >= pageblock_order && !is_migrate_isolate(migratetype))
__mod_zone_page_state(zone, NR_FREE_PAGES_BLOCKS, nr_pages);
}
/* * Used for pages which are on another list. Move the pages to the tail * of the list - so the moved pages won't immediately be considered for * allocation again (e.g., optimization for memory onlining).
*/ staticinlinevoid move_to_free_list(struct page *page, struct zone *zone, unsignedint order, int old_mt, int new_mt)
{ struct free_area *area = &zone->free_area[order]; int nr_pages = 1 << order;
/* Free page moving can fail, so it happens before the type update */
VM_WARN_ONCE(get_pageblock_migratetype(page) != old_mt, "page type is %d, passed migratetype is %d (nr=%d)\n",
get_pageblock_migratetype(page), old_mt, nr_pages);
if (order >= pageblock_order &&
is_migrate_isolate(old_mt) != is_migrate_isolate(new_mt)) { if (!is_migrate_isolate(old_mt))
nr_pages = -nr_pages;
__mod_zone_page_state(zone, NR_FREE_PAGES_BLOCKS, nr_pages);
}
}
staticinlinevoid __del_page_from_free_list(struct page *page, struct zone *zone, unsignedint order, int migratetype)
{ int nr_pages = 1 << order;
VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype, "page type is %d, passed migratetype is %d (nr=%d)\n",
get_pageblock_migratetype(page), migratetype, nr_pages);
/* clear reported state and update reported page count */ if (page_reported(page))
__ClearPageReported(page);
/* * If this is less than the 2nd largest possible page, check if the buddy * of the next-higher 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 2-level higher order page
*/ staticinlinebool
buddy_merge_likely(unsignedlong pfn, unsignedlong buddy_pfn, struct page *page, unsignedint order)
{ unsignedlong higher_page_pfn; struct page *higher_page;
return find_buddy_page_pfn(higher_page, higher_page_pfn, order + 1,
NULL) != NULL;
}
/* * 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
*/
buddy = find_buddy_page_pfn(page, pfn, order, &buddy_pfn); if (!buddy) goto done_merging;
if (unlikely(order >= pageblock_order)) { /* * We want to prevent merge between freepages on pageblock * without fallbacks and normal pageblock. Without this, * pageblock isolation could cause incorrect freepage or CMA * accounting or HIGHATOMIC accounting.
*/
buddy_mt = get_pfnblock_migratetype(buddy, buddy_pfn);
/* * 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); else
__del_page_from_free_list(buddy, zone, order, buddy_mt);
if (unlikely(buddy_mt != migratetype)) { /* * Match buddy type. This ensures that an * expand() down the line puts the sub-blocks * on the right freelists.
*/
set_pageblock_migratetype(buddy, migratetype);
}
/* Notify page reporting subsystem of freed page */ if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY))
page_reporting_notify_free(order);
}
/* * 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.
*/ staticinlinebool page_expected_state(struct page *page, unsignedlong check_flags)
{ if (unlikely(atomic_read(&page->_mapcount) != -1)) returnfalse;
staticint free_tail_page_prepare(struct page *head_page, struct page *page)
{ struct folio *folio = (struct folio *)head_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((unsignedlong)LIST_POISON1 & 1);
if (!is_check_pages_enabled()) {
ret = 0; goto out;
} switch (page - head_page) { case 1: /* the first tail page: these may be in place of ->mapping */ if (unlikely(folio_large_mapcount(folio))) {
bad_page(page, "nonzero large_mapcount"); goto out;
} if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT) &&
unlikely(atomic_read(&folio->_nr_pages_mapped))) {
bad_page(page, "nonzero nr_pages_mapped"); goto out;
} if (IS_ENABLED(CONFIG_MM_ID)) { if (unlikely(folio->_mm_id_mapcount[0] != -1)) {
bad_page(page, "nonzero mm mapcount 0"); goto out;
} if (unlikely(folio->_mm_id_mapcount[1] != -1)) {
bad_page(page, "nonzero mm mapcount 1"); goto out;
}
} if (IS_ENABLED(CONFIG_64BIT)) { if (unlikely(atomic_read(&folio->_entire_mapcount) + 1)) {
bad_page(page, "nonzero entire_mapcount"); goto out;
} if (unlikely(atomic_read(&folio->_pincount))) {
bad_page(page, "nonzero pincount"); goto out;
}
} break; case 2: /* the second tail page: deferred_list overlaps ->mapping */ if (unlikely(!list_empty(&folio->_deferred_list))) {
bad_page(page, "on deferred list"); goto out;
} if (!IS_ENABLED(CONFIG_64BIT)) { if (unlikely(atomic_read(&folio->_entire_mapcount) + 1)) {
bad_page(page, "nonzero entire_mapcount"); goto out;
} if (unlikely(atomic_read(&folio->_pincount))) {
bad_page(page, "nonzero pincount"); goto out;
}
} break; case 3: /* the third tail page: hugetlb specifics overlap ->mappings */ if (IS_ENABLED(CONFIG_HUGETLB_PAGE)) break;
fallthrough; default: if (page->mapping != TAIL_MAPPING) {
bad_page(page, "corrupted mapping in tail page"); goto out;
} break;
} if (unlikely(!PageTail(page))) {
bad_page(page, "PageTail not set"); goto out;
} if (unlikely(compound_head(page) != head_page)) {
bad_page(page, "compound_head not consistent"); goto out;
}
ret = 0;
out:
page->mapping = NULL;
clear_compound_head(page); return ret;
}
/* * Skip KASAN memory poisoning when either: * * 1. For generic KASAN: deferred memory initialization has not yet completed. * Tag-based KASAN modes skip pages freed via deferred memory initialization * using page tags instead (see below). * 2. For tag-based KASAN modes: the page has a match-all KASAN tag, indicating * that error detection is disabled for accesses via the page address. * * Pages will have match-all tags in the following circumstances: * * 1. Pages are being initialized for the first time, including during deferred * memory init; see the call to page_kasan_tag_reset in __init_single_page. * 2. The allocation was not unpoisoned due to __GFP_SKIP_KASAN, with the * exception of pages unpoisoned by kasan_unpoison_vmalloc. * 3. The allocation was excluded from being checked due to sampling, * see the call to kasan_unpoison_pages. * * 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.
*/ staticinlinebool should_skip_kasan_poison(struct page *page)
{ if (IS_ENABLED(CONFIG_KASAN_GENERIC)) return deferred_pages_enabled();
staticvoid kernel_init_pages(struct page *page, int numpages)
{ int i;
/* s390's use of memset() could override KASAN redzones. */
kasan_disable_current(); for (i = 0; i < numpages; i++)
clear_highpage_kasan_tagged(page + i);
kasan_enable_current();
}
#ifdef CONFIG_MEM_ALLOC_PROFILING
/* Should be called only if mem_alloc_profiling_enabled() */ void __clear_page_tag_ref(struct page *page)
{ union pgtag_ref_handle handle; union codetag_ref ref;
/* Should be called only if mem_alloc_profiling_enabled() */ static noinline void __pgalloc_tag_add(struct page *page, struct task_struct *task, unsignedint nr)
{ union pgtag_ref_handle handle; union codetag_ref ref;
/* Should be called only if mem_alloc_profiling_enabled() */ static noinline void __pgalloc_tag_sub(struct page *page, unsignedint nr)
{ union pgtag_ref_handle handle; union codetag_ref ref;
/* When tag is not NULL, assuming mem_alloc_profiling_enabled */ staticinlinevoid pgalloc_tag_sub_pages(struct alloc_tag *tag, unsignedint nr)
{ if (tag)
this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr);
}
if (memcg_kmem_online() && PageMemcgKmem(page))
__memcg_kmem_uncharge_page(page, order);
/* * In rare cases, when truncation or holepunching raced with * munlock after VM_LOCKED was cleared, Mlocked may still be * found set here. This does not indicate a problem, unless * "unevictable_pgs_cleared" appears worryingly large.
*/ if (unlikely(folio_test_mlocked(folio))) { long nr_pages = folio_nr_pages(folio);
if (unlikely(PageHWPoison(page)) && !order) { /* Do not let hwpoison pages hit pcplists/buddy */
reset_page_owner(page, order);
page_table_check_free(page, order);
pgalloc_tag_sub(page, 1 << order);
/* * The page is isolated and accounted for. * Mark the codetag as empty to avoid accounting error * when the page is freed by unpoison_memory().
*/
clear_page_tag_ref(page); returnfalse;
}
/* * As memory initialization might be integrated into KASAN, * KASAN poisoning and memory initialization code must be * kept together to avoid discrepancies in behavior. * * With hardware tag-based KASAN, memory tags must be set before the * page becomes unavailable via debug_pagealloc or arch_free_page.
*/ if (!skip_kasan_poison) {
kasan_poison_pages(page, order, init);
/* Memory is already initialized if KASAN did it internally. */ if (kasan_has_integrated_init())
init = false;
} if (init)
kernel_init_pages(page, 1 << order);
/* * arch_free_page() can make the page's contents inaccessible. s390 * does this. So nothing which can access the page's contents should * happen after this.
*/
arch_free_page(page, order);
debug_pagealloc_unmap_pages(page, 1 << order);
returntrue;
}
/* * Frees a number of pages from the PCP lists * Assumes all pages on list are in same zone. * count is the number of pages to free.
*/ staticvoid free_pcppages_bulk(struct zone *zone, int count, struct per_cpu_pages *pcp, int pindex)
{ unsignedlong flags; unsignedint order; struct page *page;
/* * Ensure proper count is passed which otherwise would stuck in the * below while (list_empty(list)) loop.
*/
count = min(pcp->count, count);
while (count > 0) { struct list_head *list; int nr_pages;
/* Remove pages from lists in a round-robin fashion. */ do { if (++pindex > NR_PCP_LISTS - 1)
pindex = 0;
list = &pcp->lists[pindex];
} while (list_empty(list));
order = pindex_to_order(pindex);
nr_pages = 1 << order; do { unsignedlong pfn; int mt;
staticvoid add_page_to_zone_llist(struct zone *zone, struct page *page, unsignedint order)
{ /* Remember the order */
page->order = order; /* Add the page to the free list */
llist_add(&page->pcp_llist, &zone->trylock_free_pages);
}
/* * When initializing the memmap, __init_single_page() sets the refcount * of all pages to 1 ("allocated"/"not free"). We have to set the * refcount of all involved pages to 0. * * Note that hotplugged memory pages are initialized to PageOffline(). * Pages freed from memblock might be marked as reserved.
*/ if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) &&
unlikely(context == MEMINIT_HOTPLUG)) { for (loop = 0; loop < nr_pages; loop++, p++) {
VM_WARN_ON_ONCE(PageReserved(p));
__ClearPageOffline(p);
set_page_count(p, 0);
}
/* * Bypass PCP and place fresh pages right to the tail, primarily * relevant for memory onlining.
*/
__free_pages_ok(page, order, FPI_TO_TAIL);
}
/* * 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. * * 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. * * Note: the function may return non-NULL struct page even for a page block * which contains a memory hole (i.e. there is no physical memory for a subset * of the pfn range). For example, if the pageblock order is MAX_PAGE_ORDER, which * will fall into 2 sub-sections, and the end pfn of the pageblock may be hole * even though the start pfn is online and valid. This should be safe most of * the time because struct pages are still initialized via init_unavailable_range() * and pfn walkers shouldn't touch any physical memory range for which they do * not recognize any specific metadata in struct pages.
*/ struct page *__pageblock_pfn_to_page(unsignedlong start_pfn, unsignedlong 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(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;
}
/* * 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
*/ staticinlineunsignedint expand(struct zone *zone, struct page *page, int low, int high, int migratetype)
{ unsignedint size = 1 << high; unsignedint nr_added = 0;
/* * 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)) continue;
/* * This page is about to be returned from the page allocator
*/ staticbool check_new_page(struct page *page)
{ if (likely(page_expected_state(page,
PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON))) returnfalse;
check_new_page_bad(page); returntrue;
}
staticinlinebool check_new_pages(struct page *page, unsignedint order)
{ if (is_check_pages_enabled()) { for (int i = 0; i < (1 << order); i++) { struct page *p = page + i;
if (check_new_page(p)) returntrue;
}
}
returnfalse;
}
staticinlinebool should_skip_kasan_unpoison(gfp_t flags)
{ /* Don't skip if a software KASAN mode is enabled. */ if (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
IS_ENABLED(CONFIG_KASAN_SW_TAGS)) returnfalse;
/* Skip, if hardware tag-based KASAN is not enabled. */ if (!kasan_hw_tags_enabled()) returntrue;
/* * With hardware tag-based KASAN enabled, skip if this has been * requested via __GFP_SKIP_KASAN.
*/ return flags & __GFP_SKIP_KASAN;
}
staticinlinebool should_skip_init(gfp_t flags)
{ /* Don't skip, if hardware tag-based KASAN is not enabled. */ if (!kasan_hw_tags_enabled()) returnfalse;
/* For hardware tag-based KASAN, skip if requested. */ return (flags & __GFP_SKIP_ZERO);
}
/* * Page unpoisoning must happen before memory initialization. * Otherwise, the poison pattern will be overwritten for __GFP_ZERO * allocations and the page unpoisoning code will complain.
*/
kernel_unpoison_pages(page, 1 << order);
/* * As memory initialization might be integrated into KASAN, * KASAN unpoisoning and memory initializion code must be * kept together to avoid discrepancies in behavior.
*/
/* * If memory tags should be zeroed * (which happens only when memory should be initialized as well).
*/ if (zero_tags) { /* Initialize both memory and memory tags. */ for (i = 0; i != 1 << order; ++i)
tag_clear_highpage(page + i);
/* Take note that memory was initialized by the loop above. */
init = false;
} if (!should_skip_kasan_unpoison(gfp_flags) &&
kasan_unpoison_pages(page, order, init)) { /* Take note that memory was initialized by KASAN. */ if (kasan_has_integrated_init())
init = false;
} else { /* * If memory tags have not been set by KASAN, reset the page * tags to ensure page_address() dereferencing does not fault.
*/ for (i = 0; i != 1 << order; ++i)
page_kasan_tag_reset(page + i);
} /* If memory is still not initialized, initialize it now. */ if (init)
kernel_init_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, unsignedint order, int migratetype)
{ unsignedint 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 < NR_PAGE_ORDERS; ++current_order) {
area = &(zone->free_area[current_order]);
page = get_page_from_free_area(area, migratetype); if (!page) continue;
/* * This array describes the order lists are fallen back to when * the free lists for the desirable migrate type are depleted * * The other migratetypes do not have fallbacks.
*/ staticint fallbacks[MIGRATE_PCPTYPES][MIGRATE_PCPTYPES - 1] = {
[MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE },
[MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE },
[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE },
};
/* * Move all free pages of a block to new type's freelist. Caller needs to * change the block type.
*/ staticint __move_freepages_block(struct zone *zone, unsignedlong start_pfn, int old_mt, int new_mt)
{ struct page *page; unsignedlong pfn, end_pfn; unsignedint order; int pages_moved = 0;
for (pfn = start_pfn; pfn < end_pfn;) {
page = pfn_to_page(pfn); if (!PageBuddy(page)) {
pfn++; 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);
staticbool prep_move_freepages_block(struct zone *zone, struct page *page, unsignedlong *start_pfn, int *num_free, int *num_movable)
{ unsignedlong pfn, start, end;
pfn = page_to_pfn(page);
start = pageblock_start_pfn(pfn);
end = pageblock_end_pfn(pfn);
/* * The caller only has the lock for @zone, don't touch ranges * that straddle into other zones. While we could move part of * the range that's inside the zone, this call is usually * accompanied by other operations such as migratetype updates * which also should be locked.
*/ if (!zone_spans_pfn(zone, start)) returnfalse; if (!zone_spans_pfn(zone, end - 1)) returnfalse;
*start_pfn = start;
if (num_free) {
*num_free = 0;
*num_movable = 0; for (pfn = start; pfn < end;) {
page = pfn_to_page(pfn); if (PageBuddy(page)) { int nr = 1 << buddy_order(page);
*num_free += nr;
pfn += nr; continue;
} /* * 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 (PageLRU(page) || page_has_movable_ops(page))
(*num_movable)++;
pfn++;
}
}
returntrue;
}
staticint move_freepages_block(struct zone *zone, struct page *page, int old_mt, int new_mt)
{ unsignedlong start_pfn; int res;
if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL)) return -1;
res = __move_freepages_block(zone, start_pfn, old_mt, new_mt);
set_pageblock_migratetype(pfn_to_page(start_pfn), new_mt);
return res;
}
#ifdef CONFIG_MEMORY_ISOLATION /* Look for a buddy that straddles start_pfn */ staticunsignedlong find_large_buddy(unsignedlong start_pfn)
{ int order = 0; struct page *page; unsignedlong pfn = start_pfn;
while (!PageBuddy(page = pfn_to_page(pfn))) { /* Nothing found */ if (++order > MAX_PAGE_ORDER) return start_pfn;
pfn &= ~0UL << order;
}
/* * Found a preceding buddy, but does it straddle?
*/ if (pfn + (1 << buddy_order(page)) > start_pfn) return pfn;
/** * __move_freepages_block_isolate - move free pages in block for page isolation * @zone: the zone * @page: the pageblock page * @isolate: to isolate the given pageblock or unisolate it * * This is similar to move_freepages_block(), but handles the special * case encountered in page isolation, where the block of interest * might be part of a larger buddy spanning multiple pageblocks. * * Unlike the regular page allocator path, which moves pages while * stealing buddies off the freelist, page isolation is interested in * arbitrary pfn ranges that may have overlapping buddies on both ends. * * This function handles that. Straddling buddies are split into * individual pageblocks. Only the block of interest is moved. * * Returns %true if pages could be moved, %false otherwise.
*/ staticbool __move_freepages_block_isolate(struct zone *zone, struct page *page, bool isolate)
{ unsignedlong start_pfn, pfn; int from_mt; int to_mt;
if (isolate == get_pageblock_isolate(page)) {
VM_WARN_ONCE(1, "%s a pageblock that is already in that state",
isolate ? "Isolate" : "Unisolate"); returnfalse;
}
if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL)) returnfalse;
/* No splits needed if buddies can't span multiple blocks */ if (pageblock_order == MAX_PAGE_ORDER) goto move;
/* We're a tail block in a larger buddy */
pfn = find_large_buddy(start_pfn); if (pfn != start_pfn) { struct page *buddy = pfn_to_page(pfn); int order = buddy_order(buddy);
staticvoid 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;
}
}
staticinlinebool boost_watermark(struct zone *zone)
{ unsignedlong max_boost;
if (!watermark_boost_factor) returnfalse; /* * Don't bother in zones that are unlikely to produce results. * On small machines, including kdump capture kernels running * in a small area, boosting the watermark can cause an out of * memory situation immediately.
*/ if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) returnfalse;
/* * 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) returnfalse;
/* * When we are falling back to another migratetype during allocation, should we * try to claim an entire block to satisfy further allocations, instead of * polluting multiple pageblocks?
*/ staticbool should_try_claim_block(unsignedint 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 claim the 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) returntrue;
/* * Above a certain threshold, always try to claim, as it's likely there * will be more free pages in the pageblock.
*/ if (order >= pageblock_order / 2) returntrue;
/* * Unmovable/reclaimable allocations would cause permanent * fragmentations if they fell back to allocating from a movable block * (polluting it), so we try to claim the whole block regardless of the * allocation size. Later movable allocations can always steal from this * block, which is less problematic.
*/ if (start_mt == MIGRATE_RECLAIMABLE || start_mt == MIGRATE_UNMOVABLE) returntrue;
if (page_group_by_mobility_disabled) returntrue;
/* * Movable pages won't cause permanent fragmentation, so when you alloc * small pages, we just need to temporarily steal unmovable or * reclaimable pages that are closest to the request size. After a * while, memory compaction may occur to form large contiguous pages, * and the next movable allocation may not need to steal.
*/ returnfalse;
}
/* * Check whether there is a suitable fallback freepage with requested order. * If claimable is true, this function returns fallback_mt only if * we would do this whole-block claiming. This would help to reduce * fragmentation due to mixed migratetype pages in one pageblock.
*/ int find_suitable_fallback(struct free_area *area, unsignedint order, int migratetype, bool claimable)
{ int i;
if (claimable && !should_try_claim_block(order, migratetype)) return -2;
if (area->nr_free == 0) return -1;
for (i = 0; i < MIGRATE_PCPTYPES - 1 ; i++) { int fallback_mt = fallbacks[migratetype][i];
if (!free_area_empty(area, fallback_mt)) return fallback_mt;
}
return -1;
}
/* * This function implements actual block claiming behaviour. If order is large * enough, we can claim the whole pageblock for the requested migratetype. If * not, we check the pageblock for constituent pages; if at least half of the * pages are free or compatible, we can still claim the whole block, so pages * freed in the future will be put on the correct free list.
*/ staticstruct page *
try_to_claim_block(struct zone *zone, struct page *page, int current_order, int order, int start_type, int block_type, unsignedint alloc_flags)
{ int free_pages, movable_pages, alike_pages; unsignedlong start_pfn;
/* Take ownership for orders >= pageblock_order */ if (current_order >= pageblock_order) { unsignedint nr_added;
/* * Boost watermarks to increase reclaim pressure to reduce the * likelihood of future fallbacks. Wake kswapd now as the node * may be balanced overall and kswapd will not wake naturally.
*/ if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD))
set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);
/* moving whole block can fail due to zone boundary conditions */ if (!prep_move_freepages_block(zone, page, &start_pfn, &free_pages,
&movable_pages)) return NULL;
/* * 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 (block_type == MIGRATE_MOVABLE)
alike_pages = pageblock_nr_pages
- (free_pages + movable_pages); else
alike_pages = 0;
} /* * If a sufficient number of pages in the block are either free or of * compatible migratability as our allocation, claim the whole block.
*/ if (free_pages + alike_pages >= (1 << (pageblock_order-1)) ||
page_group_by_mobility_disabled) {
__move_freepages_block(zone, start_pfn, block_type, start_type);
set_pageblock_migratetype(pfn_to_page(start_pfn), start_type); return __rmqueue_smallest(zone, order, start_type);
}
return NULL;
}
/* * Try to allocate from some fallback migratetype by claiming the entire block, * i.e. converting it to the allocation's start migratetype. * * 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 struct page *
__rmqueue_claim(struct zone *zone, int order, int start_migratetype, unsignedint alloc_flags)
{ struct free_area *area; int current_order; int min_order = order; struct page *page; int fallback_mt;
/* * 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 (order < pageblock_order && 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_PAGE_ORDER; current_order >= min_order;
--current_order) {
area = &(zone->free_area[current_order]);
fallback_mt = find_suitable_fallback(area, current_order,
start_migratetype, true);
/* No block in that order */ if (fallback_mt == -1) continue;
/* Advanced into orders too low to claim, abort */ if (fallback_mt == -2) break;
/* * Try to steal a single page from some fallback migratetype. Leave the rest of * the block as its current migratetype, potentially causing fragmentation.
*/ static __always_inline struct page *
__rmqueue_steal(struct zone *zone, int order, int start_migratetype)
{ struct free_area *area; int current_order; struct page *page; int fallback_mt;
for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) {
area = &(zone->free_area[current_order]);
fallback_mt = find_suitable_fallback(area, current_order,
start_migratetype, false); if (fallback_mt == -1) continue;
/* * 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, unsignedint order, int migratetype, unsignedint alloc_flags, enum rmqueue_mode *mode)
{ struct page *page;
if (IS_ENABLED(CONFIG_CMA)) { /* * Balance movable allocations between regular and CMA areas by * allocating from CMA when over half of the zone's free memory * is in the CMA area.
*/ if (alloc_flags & ALLOC_CMA &&
zone_page_state(zone, NR_FREE_CMA_PAGES) >
zone_page_state(zone, NR_FREE_PAGES) / 2) {
page = __rmqueue_cma_fallback(zone, order); if (page) return page;
}
}
/* * First try the freelists of the requested migratetype, then try * fallbacks modes with increasing levels of fragmentation risk. * * The fallback logic is expensive and rmqueue_bulk() calls in * a loop with the zone->lock held, meaning the freelists are * not subject to any outside changes. Remember in *mode where * we found pay dirt, to save us the search on the next call.
*/ switch (*mode) { case RMQUEUE_NORMAL:
page = __rmqueue_smallest(zone, order, migratetype); if (page) return page;
fallthrough; case RMQUEUE_CMA: if (alloc_flags & ALLOC_CMA) {
page = __rmqueue_cma_fallback(zone, order); if (page) {
*mode = RMQUEUE_CMA; return page;
}
}
fallthrough; case RMQUEUE_CLAIM:
page = __rmqueue_claim(zone, order, migratetype, alloc_flags); if (page) { /* Replenished preferred freelist, back to normal mode. */
*mode = RMQUEUE_NORMAL; return page;
}
fallthrough; case RMQUEUE_STEAL: if (!(alloc_flags & ALLOC_NOFRAGMENT)) {
page = __rmqueue_steal(zone, order, migratetype); if (page) {
*mode = RMQUEUE_STEAL; return page;
}
}
} return NULL;
}
/* * 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.
*/ staticint rmqueue_bulk(struct zone *zone, unsignedint order, unsignedlong count, struct list_head *list, int migratetype, unsignedint alloc_flags)
{ enum rmqueue_mode rmqm = RMQUEUE_NORMAL; unsignedlong flags; int i;
if (unlikely(alloc_flags & ALLOC_TRYLOCK)) { if (!spin_trylock_irqsave(&zone->lock, flags)) return 0;
} else {
spin_lock_irqsave(&zone->lock, flags);
} for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype,
alloc_flags, &rmqm); if (unlikely(page == NULL)) break;
/* * 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->pcp_list, list);
}
spin_unlock_irqrestore(&zone->lock, flags);
return i;
}
/* * Called from the vmstat counter updater to decay the PCP high. * Return whether there are addition works to do.
*/ int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp)
{ int high_min, to_drain, batch; int todo = 0;
high_min = READ_ONCE(pcp->high_min);
batch = READ_ONCE(pcp->batch); /* * Decrease pcp->high periodically to try to free possible * idle PCP pages. And, avoid to free too many pages to * control latency. This caps pcp->high decrement too.
*/ if (pcp->high > high_min) {
pcp->high = max3(pcp->count - (batch << CONFIG_PCP_BATCH_SCALE_MAX),
pcp->high - (pcp->high >> 3), high_min); if (pcp->high > high_min)
todo++;
}
#ifdef CONFIG_NUMA /* * Called from the vmstat counter updater to drain pagesets of this * currently executing processor on remote nodes after they have * expired.
*/ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
{ int to_drain, batch;
/* * Spill all of this CPU's per-cpu pages back into the buddy allocator.
*/ void drain_local_pages(struct zone *zone)
{ int cpu = smp_processor_id();
if (zone)
drain_pages_zone(cpu, zone); else
drain_pages(cpu);
}
/* * The implementation of drain_all_pages(), exposing an extra parameter to * drain on all cpus. * * drain_all_pages() is optimized to only execute on cpus where pcplists are * not empty. The check for non-emptiness can however race with a free to * pcplist that has not yet increased the pcp->count from 0 to 1. Callers * that need the guarantee that every CPU has drained can disable the * optimizing racy check.
*/ staticvoid __drain_all_pages(struct zone *zone, bool force_all_cpus)
{ int cpu;
/* * Allocate in the BSS so we won't require allocation in * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
*/ static cpumask_t cpus_with_pcps;
/* * 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_pages *pcp; struct zone *z; bool has_pcps = false;
if (force_all_cpus) { /* * The pcp.count check is racy, some callers need a * guarantee that no cpu is missed.
*/
has_pcps = true;
} elseif (zone) {
pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); if (pcp->count)
has_pcps = true;
} else {
for_each_populated_zone(z) {
pcp = per_cpu_ptr(z->per_cpu_pageset, cpu); if (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) { if (zone)
drain_pages_zone(cpu, zone); else
drain_pages(cpu);
}
mutex_unlock(&pcpu_drain_mutex);
}
/* * 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.
*/ void drain_all_pages(struct zone *zone)
{
__drain_all_pages(zone, false);
}
staticint nr_pcp_free(struct per_cpu_pages *pcp, int batch, int high, bool free_high)
{ int min_nr_free, max_nr_free;
/* Free as much as possible if batch freeing high-order pages. */ if (unlikely(free_high)) return min(pcp->count, batch << CONFIG_PCP_BATCH_SCALE_MAX);
/* Check for PCP disabled or boot pageset */ if (unlikely(high < batch)) return 1;
/* Leave at least pcp->batch pages on the list */
min_nr_free = batch;
max_nr_free = high - batch;
/* * Increase the batch number to the number of the consecutive * freed pages to reduce zone lock contention.
*/
batch = clamp_t(int, pcp->free_count, min_nr_free, max_nr_free);
return batch;
}
staticint nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone, int batch, bool free_high)
{ int high, high_min, high_max;
/* * If reclaim is active, limit the number of pages that can be * stored on pcp lists
*/ if (test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags)) { int free_count = max_t(int, pcp->free_count, batch);
/* pcp->high should be large enough to hold batch freed pages */ if (pcp->high < need_high)
pcp->high = clamp(need_high, high_min, high_max);
}
return high;
}
staticvoid free_frozen_page_commit(struct zone *zone, struct per_cpu_pages *pcp, struct page *page, int migratetype, unsignedint order, fpi_t fpi_flags)
{ int high, batch; int pindex; bool free_high = false;
/* * On freeing, reduce the number of pages that are batch allocated. * See nr_pcp_alloc() where alloc_factor is increased for subsequent * allocations.
*/
pcp->alloc_factor >>= 1;
__count_vm_events(PGFREE, 1 << order);
pindex = order_to_pindex(migratetype, order);
list_add(&page->pcp_list, &pcp->lists[pindex]);
pcp->count += 1 << order;
batch = READ_ONCE(pcp->batch); /* * As high-order pages other than THP's stored on PCP can contribute * to fragmentation, limit the number stored when PCP is heavily * freeing without allocation. The remainder after bulk freeing * stops will be drained from vmstat refresh context.
*/ if (order && order <= PAGE_ALLOC_COSTLY_ORDER) {
free_high = (pcp->free_count >= (batch + pcp->high_min / 2) &&
(pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) &&
(!(pcp->flags & PCPF_FREE_HIGH_BATCH) ||
pcp->count >= batch));
pcp->flags |= PCPF_PREV_FREE_HIGH_ORDER;
} elseif (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) {
pcp->flags &= ~PCPF_PREV_FREE_HIGH_ORDER;
} if (pcp->free_count < (batch << CONFIG_PCP_BATCH_SCALE_MAX))
pcp->free_count += (1 << order);
if (unlikely(fpi_flags & FPI_TRYLOCK)) { /* * Do not attempt to take a zone lock. Let pcp->count get * over high mark temporarily.
*/ return;
}
high = nr_pcp_high(pcp, zone, batch, free_high); if (pcp->count >= high) {
free_pcppages_bulk(zone, nr_pcp_free(pcp, batch, high, free_high),
pcp, pindex); if (test_bit(ZONE_BELOW_HIGH, &zone->flags) &&
zone_watermark_ok(zone, 0, high_wmark_pages(zone),
ZONE_MOVABLE, 0))
clear_bit(ZONE_BELOW_HIGH, &zone->flags);
}
}
if (!pcp_allowed_order(order)) {
__free_pages_ok(page, order, fpi_flags); return;
}
if (!free_pages_prepare(page, order)) return;
/* * We only track unmovable, reclaimable and movable on pcp lists. * Place ISOLATE pages on the isolated list because they are being * offlined but treat HIGHATOMIC and CMA as movable pages so we can * get those areas back if necessary. Otherwise, we may have to free * excessively into the page allocator
*/
zone = page_zone(page);
migratetype = get_pfnblock_migratetype(page, pfn); if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) {
free_one_page(zone, page, pfn, order, fpi_flags); return;
}
migratetype = MIGRATE_MOVABLE;
}
/* * Free a batch of folios
*/ void free_unref_folios(struct folio_batch *folios)
{ unsignedlong __maybe_unused UP_flags; struct per_cpu_pages *pcp = NULL; struct zone *locked_zone = NULL; int i, j;
/* Prepare folios for freeing */ for (i = 0, j = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; unsignedlong pfn = folio_pfn(folio); unsignedint order = folio_order(folio);
if (!free_pages_prepare(&folio->page, order)) continue; /* * Free orders not handled on the PCP directly to the * allocator.
*/ if (!pcp_allowed_order(order)) {
free_one_page(folio_zone(folio), &folio->page,
pfn, order, FPI_NONE); continue;
}
folio->private = (void *)(unsignedlong)order; if (j != i)
folios->folios[j] = folio;
j++;
}
folios->nr = j;
for (i = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; struct zone *zone = folio_zone(folio); unsignedlong pfn = folio_pfn(folio); unsignedint order = (unsignedlong)folio->private; int migratetype;
/* Different zone requires a different pcp lock */ if (zone != locked_zone ||
is_migrate_isolate(migratetype)) { if (pcp) {
pcp_spin_unlock(pcp);
pcp_trylock_finish(UP_flags);
locked_zone = NULL;
pcp = NULL;
}
/* * Free isolated pages directly to the * allocator, see comment in free_frozen_pages.
*/ if (is_migrate_isolate(migratetype)) {
free_one_page(zone, &folio->page, pfn,
order, FPI_NONE); continue;
}
/* * trylock is necessary as folios may be getting freed * from IRQ or SoftIRQ context after an IO completion.
*/
pcp_trylock_prepare(UP_flags);
pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (unlikely(!pcp)) {
pcp_trylock_finish(UP_flags);
free_one_page(zone, &folio->page, pfn,
order, FPI_NONE); continue;
}
locked_zone = zone;
}
/* * Non-isolated types over MIGRATE_PCPTYPES get added * to the MIGRATE_MOVABLE pcp list.
*/ if (unlikely(migratetype >= MIGRATE_PCPTYPES))
migratetype = MIGRATE_MOVABLE;
if (pcp) {
pcp_spin_unlock(pcp);
pcp_trylock_finish(UP_flags);
}
folio_batch_reinit(folios);
}
/* * 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, unsignedint order)
{ int i;
for (i = 1; i < (1 << order); i++)
set_page_refcounted(page + i);
split_page_owner(page, order, 0);
pgalloc_tag_split(page_folio(page), order, 0);
split_page_memcg(page, order);
}
EXPORT_SYMBOL_GPL(split_page);
int __isolate_free_page(struct page *page, unsignedint order)
{ struct zone *zone = page_zone(page); int mt = get_pageblock_migratetype(page);
if (!is_migrate_isolate(mt)) { unsignedlong watermark; /* * 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;
}
del_page_from_free_list(page, zone, order, mt);
/* * 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); /* * Only change normal pageblocks (i.e., they can merge * with others)
*/ if (migratetype_is_mergeable(mt))
move_freepages_block(zone, page, mt,
MIGRATE_MOVABLE);
}
}
return 1UL << order;
}
/** * __putback_isolated_page - Return a now-isolated page back where we got it * @page: Page that was isolated * @order: Order of the isolated page * @mt: The page's pageblock's migratetype * * This function is meant to return a page pulled from the free lists via * __isolate_free_page back to the free lists they were pulled from.
*/ void __putback_isolated_page(struct page *page, unsignedint order, int mt)
{ struct zone *zone = page_zone(page);
/* zone lock should be held when this function is called */
lockdep_assert_held(&zone->lock);
/* Return isolated page to tail of freelist. */
__free_one_page(page, page_to_pfn(page), zone, order, mt,
FPI_SKIP_REPORT_NOTIFY | FPI_TO_TAIL);
}
/* * Update NUMA hit/miss statistics
*/ staticinlinevoid zone_statistics(struct zone *preferred_zone, struct zone *z, long nr_account)
{ #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 the allocation fails, allow OOM handling and * order-0 (atomic) allocs access to HIGHATOMIC * reserves as failing now is worse than failing a * high-order atomic allocation in the future.
*/ if (!page && (alloc_flags & (ALLOC_OOM|ALLOC_NON_BLOCK)))
page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
if (!page) {
spin_unlock_irqrestore(&zone->lock, flags); return NULL;
}
}
spin_unlock_irqrestore(&zone->lock, flags);
} while (check_new_pages(page, order));
/* * If we had larger pcp->high, we could avoid to allocate from * zone.
*/ if (high_min != high_max && !test_bit(ZONE_BELOW_HIGH, &zone->flags))
high = pcp->high = min(high + batch, high_max);
if (!order) {
max_nr_alloc = max(high - pcp->count - base_batch, base_batch); /* * Double the number of pages allocated each time there is * subsequent allocation of order-0 pages without any freeing.
*/ if (batch <= max_nr_alloc &&
pcp->alloc_factor < CONFIG_PCP_BATCH_SCALE_MAX)
pcp->alloc_factor++;
batch = min(batch, max_nr_alloc);
}
/* * Scale batch relative to order if batch implies free pages * can be stored on the PCP. Batch can be 1 for small zones or * for boot pagesets which should never store free pages as * the pages may belong to arbitrary zones.
*/ if (batch > 1)
batch = max(batch >> order, 2);
return batch;
}
/* Remove page from the per-cpu list, caller must protect the list */ staticinline struct page *__rmqueue_pcplist(struct zone *zone, unsignedint order, int migratetype, unsignedint alloc_flags, struct per_cpu_pages *pcp, struct list_head *list)
{ struct page *page;
do { if (list_empty(list)) { int batch = nr_pcp_alloc(pcp, zone, order); int alloced;
/* Lock and remove page from the per-cpu list */ staticstruct page *rmqueue_pcplist(struct zone *preferred_zone, struct zone *zone, unsignedint order, int migratetype, unsignedint alloc_flags)
{ struct per_cpu_pages *pcp; struct list_head *list; struct page *page; unsignedlong __maybe_unused UP_flags;
/* spin_trylock may fail due to a parallel drain or IRQ reentrancy. */
pcp_trylock_prepare(UP_flags);
pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (!pcp) {
pcp_trylock_finish(UP_flags); return NULL;
}
/* * On allocation, reduce the number of pages that are batch freed. * See nr_pcp_free() where free_factor is increased for subsequent * frees.
*/
pcp->free_count >>= 1;
list = &pcp->lists[order_to_pindex(migratetype, order)];
page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list);
pcp_spin_unlock(pcp);
pcp_trylock_finish(UP_flags); if (page) {
__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
zone_statistics(preferred_zone, zone, 1);
} return page;
}
/* * Allocate a page from the given zone. * Use pcplists for THP or "cheap" high-order allocations.
*/
/* * Do not instrument rmqueue() with KMSAN. This function may call * __msan_poison_alloca() through a call to set_pfnblock_migratetype(). * If __msan_poison_alloca() attempts to allocate pages for the stack depot, it * may call rmqueue() again, which will result in a deadlock.
*/
__no_sanitize_memory staticinline struct page *rmqueue(struct zone *preferred_zone, struct zone *zone, unsignedint order,
gfp_t gfp_flags, unsignedint alloc_flags, int migratetype)
{ struct page *page;
if (likely(pcp_allowed_order(order))) {
page = rmqueue_pcplist(preferred_zone, zone, order,
migratetype, alloc_flags); if (likely(page)) goto out;
}
/* * Reserve the pageblock(s) surrounding an allocation request for * exclusive use of high-order atomic allocations if there are no * empty page blocks that contain a page with a suitable order
*/ staticvoid reserve_highatomic_pageblock(struct page *page, int order, struct zone *zone)
{ int mt; unsignedlong max_managed, flags;
/* * The number reserved as: minimum is 1 pageblock, maximum is * roughly 1% of a zone. But if 1% of a zone falls below a * pageblock size, then don't reserve any pageblocks. * Check is race-prone but harmless.
*/ if ((zone_managed_pages(zone) / 100) < pageblock_nr_pages) return;
max_managed = ALIGN((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); /* Only reserve normal pageblocks (i.e., they can merge with others) */ if (!migratetype_is_mergeable(mt)) goto out_unlock;
/* * 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 pageblocks even though highatomic * pageblock is exhausted.
*/ staticbool unreserve_highatomic_pageblock(conststruct alloc_context *ac, bool force)
{ struct zonelist *zonelist = ac->zonelist; unsignedlong flags; struct zoneref *z; struct zone *zone; struct page *page; int order; int ret;
for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_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 < NR_PAGE_ORDERS; order++) { struct free_area *area = &(zone->free_area[order]); unsignedlong size;
page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC); if (!page) continue;
size = max(pageblock_nr_pages, 1UL << order); /* * 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.
*/ if (WARN_ON_ONCE(size > zone->nr_reserved_highatomic))
size = zone->nr_reserved_highatomic;
zone->nr_reserved_highatomic -= size;
/* * 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.
*/ if (order < pageblock_order)
ret = move_freepages_block(zone, page,
MIGRATE_HIGHATOMIC,
ac->migratetype); else {
move_to_free_list(page, zone, order,
MIGRATE_HIGHATOMIC,
ac->migratetype);
change_pageblock_range(page, order,
ac->migratetype);
ret = 1;
} /* * Reserving the block(s) already succeeded, * so this should not fail on zone boundaries.
*/
WARN_ON_ONCE(ret == -1); if (ret > 0) {
spin_unlock_irqrestore(&zone->lock, flags); return ret;
}
}
spin_unlock_irqrestore(&zone->lock, flags);
}
returnfalse;
}
staticinlinelong __zone_watermark_unusable_free(struct zone *z, unsignedint order, unsignedint alloc_flags)
{ long unusable_free = (1 << order) - 1;
/* * If the caller does not have rights to reserves below the min * watermark then subtract the free pages reserved for highatomic.
*/ if (likely(!(alloc_flags & ALLOC_RESERVES)))
unusable_free += READ_ONCE(z->nr_free_highatomic);
#ifdef CONFIG_CMA /* If allocation can't use CMA areas don't use free CMA pages */ if (!(alloc_flags & ALLOC_CMA))
unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES); #endif
return unusable_free;
}
/* * Return true if free base pages are above 'mark'. For high-order checks it * 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, unsignedint order, unsignedlong mark, int highest_zoneidx, unsignedint alloc_flags, long free_pages)
{ long min = mark; int o;
/* free_pages may go negative - that's OK */
free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
if (unlikely(alloc_flags & ALLOC_RESERVES)) { /* * __GFP_HIGH allows access to 50% of the min reserve as well * as OOM.
*/ if (alloc_flags & ALLOC_MIN_RESERVE) {
min -= min / 2;
/* * Non-blocking allocations (e.g. GFP_ATOMIC) can * access more reserves than just __GFP_HIGH. Other * non-blocking allocations requests such as GFP_NOWAIT * or (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) do not get * access to the min reserve.
*/ if (alloc_flags & ALLOC_NON_BLOCK)
min -= min / 4;
}
/* * OOM victims can try even harder than the normal reserve * 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;
}
/* * 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[highest_zoneidx]) returnfalse;
/* If this is an order-0 request then the watermark is fine */ if (!order) returntrue;
/* For a high-order request, check at least one suitable page is free */ for (o = order; o < NR_PAGE_ORDERS; 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)) returntrue;
}
/* reserved may over estimate high-atomic reserves. */
usable_free -= min(usable_free, reserved); if (usable_free > mark + z->lowmem_reserve[highest_zoneidx]) returntrue;
}
if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
free_pages)) returntrue;
/* * Ignore watermark boosting for __GFP_HIGH order-0 allocations * when checking the min watermark. The min watermark is the * point where boosting is ignored so that kswapd is woken up * when below the low watermark.
*/ if (unlikely(!order && (alloc_flags & ALLOC_MIN_RESERVE) && z->watermark_boost
&& ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) {
mark = z->_watermark[WMARK_MIN]; return __zone_watermark_ok(z, order, mark, highest_zoneidx,
alloc_flags, free_pages);
}
returnfalse;
}
#ifdef CONFIG_NUMA int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
staticbool 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 */ staticbool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{ returntrue;
} #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.
*/ staticinlineunsignedint
alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
{ unsignedint alloc_flags;
/* * __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD * to save a branch.
*/
alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM);
if (defrag_mode) {
alloc_flags |= ALLOC_NOFRAGMENT; return alloc_flags;
}
#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;
/* Must be called after current_gfp_context() which can change gfp_mask */ staticinlineunsignedint gfp_to_alloc_flags_cma(gfp_t gfp_mask, unsignedint alloc_flags)
{ #ifdef CONFIG_CMA if (gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA; #endif return alloc_flags;
}
/* * get_page_from_freelist goes through the zonelist trying to allocate * a page.
*/ staticstruct page *
get_page_from_freelist(gfp_t gfp_mask, unsignedint order, int alloc_flags, conststruct alloc_context *ac)
{ struct zoneref *z; struct zone *zone; struct pglist_data *last_pgdat = NULL; bool last_pgdat_dirty_ok = false; bool no_fallback;
retry: /* * Scan zonelist, looking for a zone with enough free. * See also cpuset_current_node_allowed() comment in kernel/cgroup/cpuset.c.
*/
no_fallback = alloc_flags & ALLOC_NOFRAGMENT;
z = ac->preferred_zoneref;
for_next_zone_zonelist_nodemask(zone, z, ac->highest_zoneidx,
ac->nodemask) { struct page *page; unsignedlong 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 != zone->zone_pgdat) {
last_pgdat = zone->zone_pgdat;
last_pgdat_dirty_ok = node_dirty_ok(zone->zone_pgdat);
}
if (!last_pgdat_dirty_ok) continue;
}
if (no_fallback && !defrag_mode && nr_online_nodes > 1 &&
zone != zonelist_zone(ac->preferred_zoneref)) { int local_nid;
/* * If moving to a remote node, retry but allow * fragmenting fallbacks. Locality is more important * than fragmentation avoidance.
*/
local_nid = zonelist_node_idx(ac->preferred_zoneref); if (zone_to_nid(zone) != local_nid) {
alloc_flags &= ~ALLOC_NOFRAGMENT; goto retry;
}
}
cond_accept_memory(zone, order, alloc_flags);
/* * Detect whether the number of free pages is below high * watermark. If so, we will decrease pcp->high and free * PCP pages in free path to reduce the possibility of * premature page reclaiming. Detection is done here to * avoid to do that in hotter free path.
*/ if (test_bit(ZONE_BELOW_HIGH, &zone->flags)) goto check_alloc_wmark;
mark = high_wmark_pages(zone); if (zone_watermark_fast(zone, order, mark,
ac->highest_zoneidx, alloc_flags,
gfp_mask)) goto try_this_zone; else
set_bit(ZONE_BELOW_HIGH, &zone->flags);
check_alloc_wmark:
mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); if (!zone_watermark_fast(zone, order, mark,
ac->highest_zoneidx, alloc_flags,
gfp_mask)) { int ret;
if (cond_accept_memory(zone, order, alloc_flags)) goto try_this_zone;
/* * Watermark failed for this zone, but see if we can * grow this zone if it contains deferred pages.
*/ if (deferred_pages_enabled()) { if (_deferred_grow_zone(zone, order)) goto try_this_zone;
} /* 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_enabled() ||
!zone_allows_reclaim(zonelist_zone(ac->preferred_zoneref), 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->highest_zoneidx, alloc_flags)) goto try_this_zone;
/* * If this is a high-order atomic allocation then check * if the pageblock should be reserved for the future
*/ if (unlikely(alloc_flags & ALLOC_HIGHATOMIC))
reserve_highatomic_pageblock(page, order, zone);
/* Try again if zone has deferred pages */ if (deferred_pages_enabled()) { if (_deferred_grow_zone(zone, order)) goto try_this_zone;
}
}
}
/* * 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 && !defrag_mode) {
alloc_flags &= ~ALLOC_NOFRAGMENT; goto retry;
}
/* * 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_task() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
filter &= ~SHOW_MEM_FILTER_NODES;
/* * 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. * * The OOM killer may not free memory on a specific node.
*/ if (gfp_mask & (__GFP_RETRY_MAYFAIL | __GFP_THISNODE)) goto out; /* The OOM killer does not needlessly kill tasks for lowmem */ if (ac->highest_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.
*/
/* Exhausted what can be done so it's blame time */ if (out_of_memory(&oc) ||
WARN_ON_ONCE_GFP(gfp_mask & __GFP_NOFAIL, gfp_mask)) {
*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 with a progress before OOM * killer is consider as the only way to move forward.
*/ #define MAX_COMPACT_RETRIES 16
if (*compact_result == COMPACT_SKIPPED) return NULL; /* * 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);
/* * 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;
}
staticinlinebool
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) returnfalse;
if (fatal_signal_pending(current)) returnfalse;
/* * Compaction was skipped due to a lack of free order-0 * migration targets. Continue if reclaim can help.
*/ if (compact_result == COMPACT_SKIPPED) {
ret = compaction_zonelist_suitable(ac, order, alloc_flags); goto out;
}
/* * Compaction managed to coalesce some page blocks, but the * allocation failed presumably due to a race. Retry some.
*/ if (compact_result == COMPACT_SUCCESS) { /* * !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;
}
}
staticinlinebool
should_compact_retry(struct alloc_context *ac, unsignedint 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) returnfalse;
/* * 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->highest_zoneidx, ac->nodemask) { if (zone_watermark_ok(zone, 0, min_wmark_pages(zone),
ac->highest_zoneidx, alloc_flags)) returntrue;
} returnfalse;
} #endif/* CONFIG_COMPACTION */
if (__need_reclaim(gfp_mask)) { if (gfp_mask & __GFP_FS)
__fs_reclaim_release(_RET_IP_);
}
}
EXPORT_SYMBOL_GPL(fs_reclaim_release); #endif
/* * Zonelists may change due to hotplug during allocation. Detect when zonelists * have been rebuilt so allocation retries. Reader side does not lock and * retries the allocation if zonelist changes. Writer side is protected by the * embedded spin_lock.
*/ static DEFINE_SEQLOCK(zonelist_update_seq);
staticunsignedint zonelist_iter_begin(void)
{ if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) return read_seqbegin(&zonelist_update_seq);
return 0;
}
staticunsignedint check_retry_zonelist(unsignedint seq)
{ if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) return read_seqretry(&zonelist_update_seq, seq);
/* * 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 and try again
*/ if (!page && !drained) {
unreserve_highatomic_pageblock(ac, false);
drain_all_pages(NULL);
drained = true; goto retry;
}
out:
psi_memstall_leave(&pflags);
/* * __GFP_HIGH is assumed to be the same as ALLOC_MIN_RESERVE * and __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD * to save two branches.
*/
BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_MIN_RESERVE);
BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD);
/* * 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_NON_BLOCK and ALLOC_MIN_RESERVE(__GFP_HIGH).
*/
alloc_flags |= (__force int)
(gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM));
if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) { /* * Not worth trying to allocate harder for __GFP_NOMEMALLOC even * if it can't schedule.
*/ if (!(gfp_mask & __GFP_NOMEMALLOC)) {
alloc_flags |= ALLOC_NON_BLOCK;
staticbool oom_reserves_allowed(struct task_struct *tsk)
{ if (!tsk_is_oom_victim(tsk)) returnfalse;
/* * !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)) returnfalse;
returntrue;
}
/* * Distinguish requests which really need access to full memory * reserves from oom victims which can live with a portion of it
*/ staticinlineint __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; elseif (oom_reserves_allowed(current)) return ALLOC_OOM;
}
/* * 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.
*/ staticinlinebool
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)++;
if (*no_progress_loops > MAX_RECLAIM_RETRIES) goto out;
/* * 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->highest_zoneidx, ac->nodemask) { unsignedlong available; unsignedlong reclaimable; unsignedlong min_wmark = min_wmark_pages(zone); bool wmark;
if (cpusets_enabled() &&
(alloc_flags & ALLOC_CPUSET) &&
!__cpuset_zone_allowed(zone, gfp_mask)) continue;
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->highest_zoneidx, alloc_flags, available);
trace_reclaim_retry_zone(z, order, reclaimable,
available, min_wmark, *no_progress_loops, wmark); if (wmark) {
ret = true; break;
}
}
/* * 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();
out: /* Before OOM, exhaust highatomic_reserve */ if (!ret) return unreserve_highatomic_pageblock(ac, true);
return ret;
}
staticinlinebool
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; returntrue;
}
/* * 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)) returntrue;
if (unlikely(nofail)) { /* * We most definitely don't want callers attempting to * allocate greater than order-1 page units with __GFP_NOFAIL.
*/
WARN_ON_ONCE(order > 1); /* * Also we don't support __GFP_NOFAIL without __GFP_DIRECT_RECLAIM, * otherwise, we may result in lockup.
*/
WARN_ON_ONCE(!can_direct_reclaim); /* * 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);
}
/* * 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, order);
/* * 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->highest_zoneidx, ac->nodemask); if (!zonelist_zone(ac->preferred_zoneref)) goto nopage;
/* * Check for insane configurations where the cpuset doesn't contain * any suitable zone to satisfy the request - e.g. non-movable * GFP_HIGHUSER allocations from MOVABLE nodes only.
*/ if (cpusets_insane_config() && (gfp_mask & __GFP_HARDWALL)) { struct zoneref *z = first_zones_zonelist(ac->zonelist,
ac->highest_zoneidx,
&cpuset_current_mems_allowed); if (!zonelist_zone(z)) 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 && can_compact &&
(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;
/* * Checks for costly allocations with __GFP_NORETRY, which * includes some THP page fault allocations
*/ if (costly_order && (gfp_mask & __GFP_NORETRY)) { /* * 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;
/* * 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: /* * Deal with possible cpuset update races or zonelist updates to avoid * infinite retries.
*/ if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
check_retry_zonelist(zonelist_iter_cookie)) goto restart;
/* 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);
/* * 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->highest_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 and we can compact
*/ if (costly_order && (!can_compact ||
!(gfp_mask & __GFP_RETRY_MAYFAIL))) goto nopage;
/* * 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 && can_compact &&
should_compact_retry(ac, order, alloc_flags,
compact_result, &compact_priority,
&compaction_retries)) goto retry;
/* Reclaim/compaction failed to prevent the fallback */ if (defrag_mode && (alloc_flags & ALLOC_NOFRAGMENT)) {
alloc_flags &= ~ALLOC_NOFRAGMENT; goto retry;
}
/* * Deal with possible cpuset update races or zonelist updates to avoid * a unnecessary OOM kill.
*/ if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
check_retry_zonelist(zonelist_iter_cookie)) goto restart;
/* Reclaim has failed us, start killing things */
page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); 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 or zonelist updates to avoid * a unnecessary OOM kill.
*/ if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
check_retry_zonelist(zonelist_iter_cookie)) goto restart;
/* * Make sure that __GFP_NOFAIL request doesn't leak out and make sure * we always retry
*/ if (unlikely(nofail)) { /* * Lacking direct_reclaim we can't do anything to reclaim memory, * we disregard these unreasonable nofail requests and still * return NULL
*/ if (!can_direct_reclaim) goto fail;
/* * Help non-failing allocations by giving some access to memory * reserves normally used for high priority non-blocking * allocations 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_MIN_RESERVE, ac); if (page) goto got_pg;
if (cpusets_enabled()) {
*alloc_gfp |= __GFP_HARDWALL; /* * When we are in the interrupt context, it is irrelevant * to the current task context. It means that any node ok.
*/ if (in_task() && !ac->nodemask)
ac->nodemask = &cpuset_current_mems_allowed; else
*alloc_flags |= ALLOC_CPUSET;
}
might_alloc(gfp_mask);
/* * Don't invoke should_fail logic, since it may call * get_random_u32() and printk() which need to spin_lock.
*/ if (!(*alloc_flags & ALLOC_TRYLOCK) &&
should_fail_alloc_page(gfp_mask, order)) returnfalse;
/* 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->highest_zoneidx, ac->nodemask);
returntrue;
}
/* * __alloc_pages_bulk - Allocate a number of order-0 pages to an array * @gfp: GFP flags for the allocation * @preferred_nid: The preferred NUMA node ID to allocate from * @nodemask: Set of nodes to allocate from, may be NULL * @nr_pages: The number of pages desired in the array * @page_array: Array to store the pages * * This is a batched version of the page allocator that attempts to * allocate nr_pages quickly. Pages are added to the page_array. * * Note that only NULL elements are populated with pages and nr_pages * is the maximum number of pages that will be stored in the array. * * Returns the number of pages in the array.
*/ unsignedlong alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
nodemask_t *nodemask, int nr_pages, struct page **page_array)
{ struct page *page; unsignedlong __maybe_unused UP_flags; struct zone *zone; struct zoneref *z; struct per_cpu_pages *pcp; struct list_head *pcp_list; struct alloc_context ac;
gfp_t alloc_gfp; unsignedint alloc_flags = ALLOC_WMARK_LOW; int nr_populated = 0, nr_account = 0;
/* * Skip populated array elements to determine if any pages need * to be allocated before disabling IRQs.
*/ while (nr_populated < nr_pages && page_array[nr_populated])
nr_populated++;
/* No pages requested? */ if (unlikely(nr_pages <= 0)) goto out;
/* Bulk allocator does not support memcg accounting. */ if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT)) goto failed;
/* Use the single page allocator for one page. */ if (nr_pages - nr_populated == 1) goto failed;
#ifdef CONFIG_PAGE_OWNER /* * PAGE_OWNER may recurse into the allocator to allocate space to * save the stack with pagesets.lock held. Releasing/reacquiring * removes much of the performance benefit of bulk allocation so * force the caller to allocate one page at a time as it'll have * similar performance to added complexity to the bulk allocator.
*/ if (static_branch_unlikely(&page_owner_inited)) goto failed; #endif
/* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
gfp &= gfp_allowed_mask;
alloc_gfp = gfp; if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags)) goto out;
gfp = alloc_gfp;
/* Find an allowed local zone that meets the low watermark. */
z = ac.preferred_zoneref;
for_next_zone_zonelist_nodemask(zone, z, ac.highest_zoneidx, ac.nodemask) { unsignedlong mark;
if (cond_accept_memory(zone, 0, alloc_flags)) goto retry_this_zone;
/* Try again if zone has deferred pages */ if (deferred_pages_enabled()) { if (_deferred_grow_zone(zone, 0)) goto retry_this_zone;
}
}
/* * If there are no allowed local zones that meets the watermarks then * try to allocate a single page and reclaim if necessary.
*/ if (unlikely(!zone)) goto failed;
/* spin_trylock may fail due to a parallel drain or IRQ reentrancy. */
pcp_trylock_prepare(UP_flags);
pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (!pcp) goto failed_irq;
/* Attempt the batch allocation */
pcp_list = &pcp->lists[order_to_pindex(ac.migratetype, 0)]; while (nr_populated < nr_pages) {
page = __rmqueue_pcplist(zone, 0, ac.migratetype, alloc_flags,
pcp, pcp_list); if (unlikely(!page)) { /* Try and allocate at least one page */ if (!nr_account) {
pcp_spin_unlock(pcp); goto failed_irq;
} break;
}
nr_account++;
/* * This is the 'heart' of the zoned buddy allocator.
*/ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsignedint order, int preferred_nid, nodemask_t *nodemask)
{ struct page *page; unsignedint alloc_flags = ALLOC_WMARK_LOW;
gfp_t alloc_gfp; /* 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 (WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp)) return NULL;
gfp &= gfp_allowed_mask; /* * 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}. And PF_MEMALLOC_PIN which ensures * movable zones are not used during allocation.
*/
gfp = current_gfp_context(gfp);
alloc_gfp = gfp; if (!prepare_alloc_pages(gfp, order, preferred_nid, nodemask, &ac,
&alloc_gfp, &alloc_flags)) return NULL;
/* * Forbid the first pass from falling back to types that fragment * memory until all local zones are considered.
*/
alloc_flags |= alloc_flags_nofragment(zonelist_zone(ac.preferred_zoneref), gfp);
/* First allocation attempt */
page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac); if (likely(page)) goto out;
alloc_gfp = gfp;
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.
*/
ac.nodemask = 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.
*/ unsignedlong get_free_pages_noprof(gfp_t gfp_mask, unsignedint order)
{ struct page *page;
staticvoid ___free_pages(struct page *page, unsignedint order,
fpi_t fpi_flags)
{ /* get PageHead before we drop reference */ int head = PageHead(page); /* get alloc tag in case the page is released by others */ struct alloc_tag *tag = pgalloc_tag_get(page);
/** * __free_pages - Free pages allocated with alloc_pages(). * @page: The page pointer returned from alloc_pages(). * @order: The order of the allocation. * * This function can free multi-page allocations that are not compound * pages. It does not check that the @order passed in matches that of * the allocation, so it is easy to leak memory. Freeing more memory * than was allocated will probably emit a warning. * * If the last reference to this page is speculative, it will be released * by put_page() which only frees the first page of a non-compound * allocation. To prevent the remaining pages from being leaked, we free * the subsequent pages here. If you want to use the page's reference * count to decide when to free the allocation, you should allocate a * compound page, and use put_page() instead of __free_pages(). * * Context: May be called in interrupt context or while holding a normal * spinlock, but not in NMI context or while holding a raw spinlock.
*/ void __free_pages(struct page *page, unsignedint order)
{
___free_pages(page, order, FPI_NONE);
}
EXPORT_SYMBOL(__free_pages);
/* * Can be called while holding raw_spin_lock or from IRQ and NMI for any * page type (not only those that came from alloc_pages_nolock)
*/ void free_pages_nolock(struct page *page, unsignedint order)
{
___free_pages(page, order, FPI_TRYLOCK);
}
/** * 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_PAGE_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_noprof(size_t size, gfp_t gfp_mask)
{ unsignedint order = get_order(size); unsignedlong addr;
/** * 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_noprof(int nid, size_t size, gfp_t gfp_mask)
{ unsignedint order = get_order(size); struct page *p;
p = alloc_pages_node_noprof(nid, gfp_mask, order); if (!p) return NULL; return make_alloc_exact((unsignedlong)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)
{ unsignedlong addr = (unsignedlong)virt; unsignedlong end = addr + PAGE_ALIGN(size);
/** * 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.
*/ staticunsignedlong nr_free_zone_pages(int offset)
{ struct zoneref *z; struct zone *zone;
/* Just pick one node, since fallback list is circular */ unsignedlong sum = 0;
for_each_zone_zonelist(zone, z, zonelist, offset) { unsignedlong size = zone_managed_pages(zone); unsignedlong 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.
*/ unsignedlong nr_free_buffer_pages(void)
{ return nr_free_zone_pages(gfp_zone(GFP_USER));
}
EXPORT_SYMBOL_GPL(nr_free_buffer_pages);
/* * Builds allocation fallback zone lists. * * Add all populated zones of a node to the zonelist.
*/ staticint 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 (populated_zone(zone)) {
zoneref_set_zone(zone, &zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
} while (zone_type);
return nr_zones;
}
#ifdef CONFIG_NUMA
staticint __parse_numa_zonelist_order(char *s)
{ /* * We used to support different zonelists 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;
}
/** * 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.
*/ 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;
/* * Use the local node if we haven't already, but for memoryless local * node, we should skip it and fall back to other nodes.
*/ if (!node_isset(node, *used_node_mask) && node_state(node, N_MEMORY)) {
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 */ if (!cpumask_empty(cpumask_of_node(n)))
val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */
val *= MAX_NUMNODES;
val += node_load[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.
*/ staticvoid build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order, unsigned nr_nodes)
{ struct zoneref *zonerefs; int i;
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] += 1;
build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
build_thisnode_zonelists(pgdat);
pr_info("Fallback order for Node %d: ", local_node); for (node = 0; node < nr_nodes; node++)
pr_cont("%d ", node_order[node]);
pr_cont("\n");
}
#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 zonelist_node_idx(z);
} #endif
/* * 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.
*/ staticvoid per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats); /* These effectively disable the pcplists in the boot pageset completely */ #define BOOT_PAGESET_HIGH 0 #define BOOT_PAGESET_BATCH 1 static DEFINE_PER_CPU(struct per_cpu_pages, boot_pageset); static DEFINE_PER_CPU(struct per_cpu_zonestat, boot_zonestats);
staticvoid __build_all_zonelists(void *data)
{ int nid; int __maybe_unused cpu;
pg_data_t *self = data; unsignedlong flags;
/* * The zonelist_update_seq must be acquired with irqsave because the * reader can be invoked from IRQ with GFP_ATOMIC.
*/
write_seqlock_irqsave(&zonelist_update_seq, flags); /* * Also disable synchronous printk() to prevent any printk() from * trying to hold port->lock, for * tty_insert_flip_string_and_push_buffer() on other CPU might be * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held.
*/
printk_deferred_enter();
/* * 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 { /* * All possible nodes have pgdat preallocated * in free_area_init
*/
for_each_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
}
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)
per_cpu_pages_init(&per_cpu(boot_pageset, cpu), &per_cpu(boot_zonestats, cpu));
/* * 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)
{ unsignedlong vm_total_pages;
if (system_state == SYSTEM_BOOTING) {
build_all_zonelists_init();
} else {
__build_all_zonelists(pgdat); /* cpuset refresh routine should be here */
} /* Get the number of free pages beyond high watermark in all zones. */
vm_total_pages = nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE)); /* * Disable grouping by mobility if the number of pages in the * system is too low to allow the mechanism to work. It would be * 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;
staticint zone_batchsize(struct zone *zone)
{ #ifdef CONFIG_MMU int batch;
/* * The number of pages to batch allocate is either ~0.1% * of the zone or 1MB, whichever is smaller. The batch * size is striking a balance between allocation latency * and zone lock contention.
*/
batch = min(zone_managed_pages(zone) >> 10, SZ_1M / 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
}
staticint percpu_pagelist_high_fraction; staticint zone_highsize(struct zone *zone, int batch, int cpu_online, int high_fraction)
{ #ifdef CONFIG_MMU int high; int nr_split_cpus; unsignedlong total_pages;
if (!high_fraction) { /* * By default, the high value of the pcp is based on the zone * low watermark so that if they are full then background * reclaim will not be started prematurely.
*/
total_pages = low_wmark_pages(zone);
} else { /* * If percpu_pagelist_high_fraction is configured, the high * value is based on a fraction of the managed pages in the * zone.
*/
total_pages = zone_managed_pages(zone) / high_fraction;
}
/* * Split the high value across all online CPUs local to the zone. Note * that early in boot that CPUs may not be online yet and that during * CPU hotplug that the cpumask is not yet updated when a CPU is being * onlined. For memory nodes that have no CPUs, split the high value * across all online CPUs to mitigate the risk that reclaim is triggered * prematurely due to pages stored on pcp lists.
*/
nr_split_cpus = cpumask_weight(cpumask_of_node(zone_to_nid(zone))) + cpu_online; if (!nr_split_cpus)
nr_split_cpus = num_online_cpus();
high = total_pages / nr_split_cpus;
/* * Ensure high is at least batch*4. The multiple is based on the * historical relationship between high and batch.
*/
high = max(high, batch << 2);
return high; #else return 0; #endif
}
/* * pcp->high and pcp->batch values are related and generally batch is lower * than high. They are also related to pcp->count such that count is lower * than high, and as soon as it reaches high, the pcplist is flushed. * * However, guaranteeing these relations at all times would require e.g. write * barriers here but also careful usage of read barriers at the read side, and * thus be prone to error and bad for performance. Thus the update only prevents * store tearing. Any new users of pcp->batch, pcp->high_min and pcp->high_max * should ensure they can cope with those fields changing asynchronously, and * fully trust only the pcp->count field on the local CPU with interrupts * disabled. * * 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).
*/ staticvoid pageset_update(struct per_cpu_pages *pcp, unsignedlong high_min, unsignedlong high_max, unsignedlong batch)
{
WRITE_ONCE(pcp->batch, batch);
WRITE_ONCE(pcp->high_min, high_min);
WRITE_ONCE(pcp->high_max, high_max);
}
staticvoid per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats)
{ int pindex;
spin_lock_init(&pcp->lock); for (pindex = 0; pindex < NR_PCP_LISTS; pindex++)
INIT_LIST_HEAD(&pcp->lists[pindex]);
/* * Set batch and high values safe for a boot pageset. A true percpu * pageset's initialization will update them subsequently. Here we don't * need to be as careful as pageset_update() as nobody can access the * pageset yet.
*/
pcp->high_min = BOOT_PAGESET_HIGH;
pcp->high_max = BOOT_PAGESET_HIGH;
pcp->batch = BOOT_PAGESET_BATCH;
pcp->free_count = 0;
}
staticvoid __zone_set_pageset_high_and_batch(struct zone *zone, unsignedlong high_min, unsignedlong high_max, unsignedlong batch)
{ struct per_cpu_pages *pcp; int cpu;
/* * Calculate and set new high and batch values for all per-cpu pagesets of a * zone based on the zone's size.
*/ staticvoid zone_set_pageset_high_and_batch(struct zone *zone, int cpu_online)
{ int new_high_min, new_high_max, new_batch;
new_batch = max(1, zone_batchsize(zone)); if (percpu_pagelist_high_fraction) {
new_high_min = zone_highsize(zone, new_batch, cpu_online,
percpu_pagelist_high_fraction); /* * PCP high is tuned manually, disable auto-tuning via * setting high_min and high_max to the manual value.
*/
new_high_max = new_high_min;
} else {
new_high_min = zone_highsize(zone, new_batch, cpu_online, 0);
new_high_max = zone_highsize(zone, new_batch, cpu_online,
MIN_PERCPU_PAGELIST_HIGH_FRACTION);
}
/* * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalculated.
*/ staticvoid zone_pcp_update(struct zone *zone, int cpu_online)
{
mutex_lock(&pcp_batch_high_lock);
zone_set_pageset_high_and_batch(zone, cpu_online);
mutex_unlock(&pcp_batch_high_lock);
}
pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
cci = get_cpu_cacheinfo(cpu); /* * If data cache slice of CPU is large enough, "pcp->batch" * pages can be preserved in PCP before draining PCP for * consecutive high-order pages freeing without allocation. * This can reduce zone lock contention without hurting * cache-hot pages sharing.
*/
spin_lock(&pcp->lock); if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch)
pcp->flags |= PCPF_FREE_HIGH_BATCH; else
pcp->flags &= ~PCPF_FREE_HIGH_BATCH;
spin_unlock(&pcp->lock);
}
void setup_pcp_cacheinfo(unsignedint cpu)
{ struct zone *zone;
/* * 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; int __maybe_unused cpu;
#ifdef CONFIG_NUMA /* * Unpopulated zones continue using the boot pagesets. * The numa stats for these pagesets need to be reset. * Otherwise, they will end up skewing the stats of * the nodes these zones are associated with.
*/
for_each_possible_cpu(cpu) { struct per_cpu_zonestat *pzstats = &per_cpu(boot_zonestats, cpu);
memset(pzstats->vm_numa_event, 0, sizeof(pzstats->vm_numa_event));
} #endif
__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->per_cpu_pageset = &boot_pageset;
zone->per_cpu_zonestats = &boot_zonestats;
zone->pageset_high_min = BOOT_PAGESET_HIGH;
zone->pageset_high_max = BOOT_PAGESET_HIGH;
zone->pageset_batch = BOOT_PAGESET_BATCH;
/* * '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); /* * Perform a kasan-unchecked memset() since this memory * has not been initialized.
*/
direct_map_addr = kasan_reset_tag(direct_map_addr); if ((unsignedint)poison <= 0xFF)
memset(direct_map_addr, poison, PAGE_SIZE);
free_reserved_page(page);
}
if (pages && s)
pr_info("Freeing %s memory: %ldK\n", s, K(pages));
/* * 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);
void __init page_alloc_init_cpuhp(void)
{ int ret;
ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC, "mm/page_alloc:pcp",
page_alloc_cpu_online,
page_alloc_cpu_dead);
WARN_ON(ret < 0);
}
/* * calculate_totalreserve_pages - called when sysctl_lowmem_reserve_ratio * or min_free_kbytes changes.
*/ staticvoid calculate_totalreserve_pages(void)
{ struct pglist_data *pgdat; unsignedlong 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; unsignedlong 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);
/* * 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().
*/ staticvoid setup_per_zone_lowmem_reserve(void)
{ struct pglist_data *pgdat; enum zone_type i, j;
for_each_online_pgdat(pgdat) { for (i = 0; i < MAX_NR_ZONES - 1; i++) { struct zone *zone = &pgdat->node_zones[i]; int ratio = sysctl_lowmem_reserve_ratio[i]; bool clear = !ratio || !zone_managed_pages(zone); unsignedlong managed_pages = 0;
for (j = i + 1; j < MAX_NR_ZONES; j++) { struct zone *upper_zone = &pgdat->node_zones[j];
/* Calculate total number of !ZONE_HIGHMEM and !ZONE_MOVABLE pages */
for_each_zone(zone) { if (!is_highmem(zone) && zone_idx(zone) != ZONE_MOVABLE)
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);
tmp = div64_ul(tmp, lowmem_pages); if (is_highmem(zone) || zone_idx(zone) == ZONE_MOVABLE) { /* * __GFP_HIGH and PF_MEMALLOC allocations usually don't * need highmem and movable zones 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 and movable zones.
*/ unsignedlong 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));
/** * 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)
{ struct zone *zone; static DEFINE_SPINLOCK(lock);
/* * The watermark size have changed so update the pcpu batch * and high limits or the limits may be inappropriate.
*/
for_each_zone(zone)
zone_pcp_update(zone, 0);
}
/* * Initialise min_free_kbytes. * * For small machines we want it small (128k min). For large machines * we want it large (256MB max). But it is not linear, because network * bandwidth does not increase linearly with machine size. We use * * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: * 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
*/ void calculate_min_free_kbytes(void)
{ unsignedlong lowmem_kbytes; int new_min_free_kbytes;
if (new_min_free_kbytes > user_min_free_kbytes)
min_free_kbytes = clamp(new_min_free_kbytes, 128, 262144); else
pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n",
new_min_free_kbytes, user_min_free_kbytes);
}
int __meminit init_per_zone_wmark_min(void)
{
calculate_min_free_kbytes();
setup_per_zone_wmarks();
refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
/* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so * that we can call two helper functions whenever min_free_kbytes * changes.
*/ staticint min_free_kbytes_sysctl_handler(conststruct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos)
{ int rc;
/* * 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.
*/ staticint lowmem_reserve_ratio_sysctl_handler(conststruct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos)
{ int i;
for (i = 0; i < MAX_NR_ZONES; i++) { if (sysctl_lowmem_reserve_ratio[i] < 1)
sysctl_lowmem_reserve_ratio[i] = 0;
}
setup_per_zone_lowmem_reserve(); return 0;
}
/* * percpu_pagelist_high_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.
*/ staticint percpu_pagelist_high_fraction_sysctl_handler(conststruct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos)
{ struct zone *zone; int old_percpu_pagelist_high_fraction; int ret;
/* [start, end) must belong to a single zone. */ staticint __alloc_contig_migrate_range(struct compact_control *cc, unsignedlong start, unsignedlong end)
{ /* This function is based on compact_zone() from compaction.c. */ unsignedint nr_reclaimed; unsignedlong pfn = start; unsignedint tries = 0; int ret = 0; struct migration_target_control mtc = {
.nid = zone_to_nid(cc->zone),
.gfp_mask = cc->gfp_mask,
.reason = MR_CONTIG_RANGE,
};
lru_cache_disable();
while (pfn < end || !list_empty(&cc->migratepages)) { if (fatal_signal_pending(current)) {
ret = -EINTR; break;
}
if (list_empty(&cc->migratepages)) {
cc->nr_migratepages = 0;
ret = isolate_migratepages_range(cc, pfn, end); if (ret && ret != -EAGAIN) break;
pfn = cc->migrate_pfn;
tries = 0;
} elseif (++tries == 5) {
ret = -EBUSY; break;
}
ret = migrate_pages(&cc->migratepages, alloc_migration_target,
NULL, (unsignedlong)&mtc, cc->mode, MR_CONTIG_RANGE, NULL);
/* * On -ENOMEM, migrate_pages() bails out right away. It is pointless * to retry again over this error, so do the same here.
*/ if (ret == -ENOMEM) break;
}
lru_cache_enable(); if (ret < 0) { if (!(cc->gfp_mask & __GFP_NOWARN) && ret == -EBUSY)
alloc_contig_dump_pages(&cc->migratepages);
putback_movable_pages(&cc->migratepages);
}
return (ret < 0) ? ret : 0;
}
staticvoid split_free_pages(struct list_head *list, gfp_t gfp_mask)
{ int order;
for (order = 0; order < NR_PAGE_ORDERS; order++) { struct page *page, *next; int nr_pages = 1 << order;
list_for_each_entry_safe(page, next, &list[order], lru) { int i;
post_alloc_hook(page, order, gfp_mask);
set_page_refcounted(page); if (!order) continue;
split_page(page, order);
/* Add all subpages to the order-0 head, in sequence. */
list_del(&page->lru); for (i = 0; i < nr_pages; i++)
list_add_tail(&page[i].lru, &list[0]);
}
}
}
/* * We are given the range to allocate; node, mobility and placement * hints are irrelevant at this point. We'll simply ignore them.
*/
gfp_mask &= ~(GFP_ZONEMASK | __GFP_RECLAIMABLE | __GFP_WRITE |
__GFP_HARDWALL | __GFP_THISNODE | __GFP_MOVABLE);
/* * We only support most reclaim flags (but not NOFAIL/NORETRY), and * selected action flags.
*/ if (gfp_mask & ~(reclaim_mask | action_mask)) return -EINVAL;
/* * Flags to control page compaction/migration/reclaim, to free up our * page range. Migratable pages are movable, __GFP_MOVABLE is implied * for them. * * Traditionally we always had __GFP_RETRY_MAYFAIL set, keep doing that * to not degrade callers.
*/
*gfp_cc_mask = (gfp_mask & (reclaim_mask | cc_action_mask)) |
__GFP_MOVABLE | __GFP_RETRY_MAYFAIL; 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 * @alloc_flags: allocation information * @gfp_mask: GFP mask. Node/zone/placement hints are ignored; only some * action and reclaim modifiers are supported. Reclaim modifiers * control allocation behavior during compaction/migration/reclaim. * * The PFN range does not have to be pageblock 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_noprof(unsignedlong start, unsignedlong end,
acr_flags_t alloc_flags, gfp_t gfp_mask)
{ unsignedlong outer_start, outer_end; int ret = 0;
gfp_mask = current_gfp_context(gfp_mask); if (__alloc_contig_verify_gfp_mask(gfp_mask, (gfp_t *)&cc.gfp_mask)) return -EINVAL;
/* * 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, start_isolate_page_range() has special handlings for this. * * 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(start, end, mode); if (ret) goto done;
drain_all_pages(cc.zone);
/* * In case of -EBUSY, we'd like to know which page causes problem. * So, just fall through. test_pages_isolated() has a tracepoint * 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;
/* * When in-use hugetlb pages are migrated, they may simply be released * back into the free hugepage pool instead of being returned to the * buddy system. After the migration of in-use huge pages is completed, * we will invoke replace_free_hugepage_folios() to ensure that these * hugepages are properly released to the buddy system.
*/
ret = replace_free_hugepage_folios(start, end); if (ret) goto done;
/* * Pages from [start, end) are within a pageblock_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.
*/
outer_start = find_large_buddy(start);
/* Make sure the range is really isolated. */ if (test_pages_isolated(outer_start, end, mode)) {
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;
}
if (!(gfp_mask & __GFP_COMP)) {
split_free_pages(cc.freepages, gfp_mask);
/* 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);
} elseif (start == outer_start && end == outer_end && is_power_of_2(end - start)) { struct page *head = pfn_to_page(start); int order = ilog2(end - start);
/** * alloc_contig_pages() -- tries to find and allocate contiguous range of pages * @nr_pages: Number of contiguous pages to allocate * @gfp_mask: GFP mask. Node/zone/placement hints limit the search; only some * action and reclaim modifiers are supported. Reclaim modifiers * control allocation behavior during compaction/migration/reclaim. * @nid: Target node * @nodemask: Mask for other possible nodes * * This routine is a wrapper around alloc_contig_range(). It scans over zones * on an applicable zonelist to find a contiguous pfn range which can then be * tried for allocation with alloc_contig_range(). This routine is intended * for allocation requests which can not be fulfilled with the buddy allocator. * * The allocated memory is always aligned to a page boundary. If nr_pages is a * power of two, then allocated range is also guaranteed to be aligned to same * nr_pages (e.g. 1GB request would be aligned to 1GB). * * Allocated pages can be freed with free_contig_range() or by manually calling * __free_page() on each allocated page. * * Return: pointer to contiguous pages on success, or NULL if not successful.
*/ struct page *alloc_contig_pages_noprof(unsignedlong nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask)
{ unsignedlong ret, pfn, flags; struct zonelist *zonelist; struct zone *zone; struct zoneref *z;
pfn = ALIGN(zone->zone_start_pfn, nr_pages); while (zone_spans_last_pfn(zone, pfn, nr_pages)) { if (pfn_range_valid_contig(zone, pfn, nr_pages)) { /* * We release the zone lock here because * alloc_contig_range() will also lock the zone * at some point. If there's an allocation * spinning on this lock, it may win the race * and cause alloc_contig_range() to fail...
*/
spin_unlock_irqrestore(&zone->lock, flags);
ret = __alloc_contig_pages(pfn, nr_pages,
gfp_mask); if (!ret) return pfn_to_page(pfn);
spin_lock_irqsave(&zone->lock, flags);
}
pfn += nr_pages;
}
spin_unlock_irqrestore(&zone->lock, flags);
} return NULL;
} #endif/* CONFIG_CONTIG_ALLOC */
for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn);
count += page_count(page) != 1;
__free_page(page);
}
WARN(count != 0, "%lu pages are still in use!\n", count);
}
EXPORT_SYMBOL(free_contig_range);
/* * Effectively disable pcplists for the zone by setting the high limit to 0 * and draining all cpus. A concurrent page freeing on another CPU that's about * to put the page on pcplist will either finish before the drain and the page * will be drained, or observe the new high limit and skip the pcplist. * * Must be paired with a call to zone_pcp_enable().
*/ void zone_pcp_disable(struct zone *zone)
{
mutex_lock(&pcp_batch_high_lock);
__zone_set_pageset_high_and_batch(zone, 0, 0, 1);
__drain_all_pages(zone, true);
}
#ifdef CONFIG_MEMORY_HOTREMOVE /* * All pages in the range must be in a single zone, must not contain holes, * must span full sections, and must be isolated before calling this function. * * Returns the number of managed (non-PageOffline()) pages in the range: the * number of pages for which memory offlining code must adjust managed page * counters using adjust_managed_page_count().
*/ unsignedlong __offline_isolated_pages(unsignedlong start_pfn, unsignedlong end_pfn)
{ unsignedlong already_offline = 0, flags; unsignedlong pfn = start_pfn; struct page *page; struct zone *zone; unsignedint order;
offline_mem_sections(pfn, end_pfn);
zone = page_zone(pfn_to_page(pfn));
spin_lock_irqsave(&zone->lock, flags); while (pfn < end_pfn) {
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++; continue;
} /* * At this point all remaining PageOffline() pages have a * reference count of 0 and can simply be skipped.
*/ if (PageOffline(page)) {
BUG_ON(page_count(page));
BUG_ON(PageBuddy(page));
already_offline++;
pfn++; continue;
}
/* * This function returns a stable result only if called under zone lock.
*/ bool is_free_buddy_page(conststruct page *page)
{ unsignedlong pfn = page_to_pfn(page); unsignedint order;
/* * Break down a higher-order page in sub-pages, and keep our target out of * buddy allocator.
*/ staticvoid break_down_buddy_pages(struct zone *zone, struct page *page, struct page *target, int low, int high, int migratetype)
{ unsignedlong size = 1 << high; struct page *current_buddy;
/* * Take a page that will be marked as poisoned off the buddy allocator.
*/ bool take_page_off_buddy(struct page *page)
{ struct zone *zone = page_zone(page); unsignedlong pfn = page_to_pfn(page); unsignedlong flags; unsignedint order; bool ret = false;
spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < NR_PAGE_ORDERS; order++) { struct page *page_head = page - (pfn & ((1 << order) - 1)); int page_order = buddy_order(page_head);
if (PageBuddy(page_head) && page_order >= order) { unsignedlong pfn_head = page_to_pfn(page_head); int migratetype = get_pfnblock_migratetype(page_head,
pfn_head);
staticbool cond_accept_memory(struct zone *zone, unsignedint order, int alloc_flags)
{ long to_accept, wmark; bool ret = false;
if (list_empty(&zone->unaccepted_pages)) returnfalse;
/* Bailout, since try_to_accept_memory_one() needs to take a lock */ if (alloc_flags & ALLOC_TRYLOCK) returnfalse;
wmark = promo_wmark_pages(zone);
/* * Watermarks have not been initialized yet. * * Accepting one MAX_ORDER page to ensure progress.
*/ if (!wmark) return try_to_accept_memory_one(zone);
/* How much to accept to get to promo watermark? */
to_accept = wmark -
(zone_page_state(zone, NR_FREE_PAGES) -
__zone_watermark_unusable_free(zone, order, 0) -
zone_page_state(zone, NR_UNACCEPTED));
while (to_accept > 0) { if (!try_to_accept_memory_one(zone)) break;
ret = true;
to_accept -= MAX_ORDER_NR_PAGES;
}
/** * alloc_pages_nolock - opportunistic reentrant allocation from any context * @nid: node to allocate from * @order: allocation order size * * Allocates pages of a given order from the given node. This is safe to * call from any context (from atomic, NMI, and also reentrant * allocator -> tracepoint -> alloc_pages_nolock_noprof). * Allocation is best effort and to be expected to fail easily so nobody should * rely on the success. Failures are not reported via warn_alloc(). * See always fail conditions below. * * Return: allocated page or NULL on failure. NULL does not mean EBUSY or EAGAIN. * It means ENOMEM. There is no reason to call it again and expect !NULL.
*/ struct page *alloc_pages_nolock_noprof(int nid, unsignedint order)
{ /* * Do not specify __GFP_DIRECT_RECLAIM, since direct claim is not allowed. * Do not specify __GFP_KSWAPD_RECLAIM either, since wake up of kswapd * is not safe in arbitrary context. * * These two are the conditions for gfpflags_allow_spinning() being true. * * Specify __GFP_NOWARN since failing alloc_pages_nolock() is not a reason * to warn. Also warn would trigger printk() which is unsafe from * various contexts. We cannot use printk_deferred_enter() to mitigate, * since the running context is unknown. * * Specify __GFP_ZERO to make sure that call to kmsan_alloc_page() below * is safe in any context. Also zeroing the page is mandatory for * BPF use cases. * * Though __GFP_NOMEMALLOC is not checked in the code path below, * specify it here to highlight that alloc_pages_nolock() * doesn't want to deplete reserves.
*/
gfp_t alloc_gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_NOMEMALLOC
| __GFP_ACCOUNT; unsignedint alloc_flags = ALLOC_TRYLOCK; struct alloc_context ac = { }; struct page *page;
/* * In PREEMPT_RT spin_trylock() will call raw_spin_lock() which is * unsafe in NMI. If spin_trylock() is called from hard IRQ the current * task may be waiting for one rt_spin_lock, but rt_spin_trylock() will * mark the task as the owner of another rt_spin_lock which will * confuse PI logic, so return immediately if called form hard IRQ or * NMI. * * Note, irqs_disabled() case is ok. This function can be called * from raw_spin_lock_irqsave region.
*/ if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) return NULL; if (!pcp_allowed_order(order)) return NULL;
/* Bailout, since _deferred_grow_zone() needs to take a lock */ if (deferred_pages_enabled()) return NULL;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.
