Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d4b0c79..bda2028 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -18,6 +18,8 @@
#include <linux/pageblock-flags.h>
#include <linux/page-flags-layout.h>
#include <linux/atomic.h>
+#include <linux/mm_types.h>
+#include <linux/page-flags.h>
#include <asm/page.h>
/* Free memory management - zoned buddy allocator. */
@@ -65,7 +67,7 @@
};
/* In mm/page_alloc.c; keep in sync also with show_migration_types() there */
-extern char * const migratetype_names[MIGRATE_TYPES];
+extern const char * const migratetype_names[MIGRATE_TYPES];
#ifdef CONFIG_CMA
# define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
@@ -98,6 +100,62 @@
unsigned long nr_free;
};
+/* Used for pages not on another list */
+static inline void add_to_free_area(struct page *page, struct free_area *area,
+ int migratetype)
+{
+ list_add(&page->lru, &area->free_list[migratetype]);
+ area->nr_free++;
+}
+
+/* Used for pages not on another list */
+static inline void add_to_free_area_tail(struct page *page, struct free_area *area,
+ int migratetype)
+{
+ list_add_tail(&page->lru, &area->free_list[migratetype]);
+ area->nr_free++;
+}
+
+#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
+/* Used to preserve page allocation order entropy */
+void add_to_free_area_random(struct page *page, struct free_area *area,
+ int migratetype);
+#else
+static inline void add_to_free_area_random(struct page *page,
+ struct free_area *area, int migratetype)
+{
+ add_to_free_area(page, area, migratetype);
+}
+#endif
+
+/* Used for pages which are on another list */
+static inline void move_to_free_area(struct page *page, struct free_area *area,
+ int migratetype)
+{
+ list_move(&page->lru, &area->free_list[migratetype]);
+}
+
+static inline struct page *get_page_from_free_area(struct free_area *area,
+ int migratetype)
+{
+ return list_first_entry_or_null(&area->free_list[migratetype],
+ struct page, lru);
+}
+
+static inline void del_page_from_free_area(struct page *page,
+ struct free_area *area)
+{
+ list_del(&page->lru);
+ __ClearPageBuddy(page);
+ set_page_private(page, 0);
+ area->nr_free--;
+}
+
+static inline bool free_area_empty(struct free_area *area, int migratetype)
+{
+ return list_empty(&area->free_list[migratetype]);
+}
+
struct pglist_data;
/*
@@ -157,12 +215,15 @@
NR_INACTIVE_FILE, /* " " " " " */
NR_ACTIVE_FILE, /* " " " " " */
NR_UNEVICTABLE, /* " " " " " */
- NR_SLAB_RECLAIMABLE,
- NR_SLAB_UNRECLAIMABLE,
+ NR_SLAB_RECLAIMABLE, /* Please do not reorder this item */
+ NR_SLAB_UNRECLAIMABLE, /* and this one without looking at
+ * memcg_flush_percpu_vmstats() first. */
NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
+ WORKINGSET_NODES,
WORKINGSET_REFAULT,
WORKINGSET_ACTIVATE,
+ WORKINGSET_RESTORE,
WORKINGSET_NODERECLAIM,
NR_ANON_MAPPED, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
@@ -174,13 +235,15 @@
NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */
NR_SHMEM_THPS,
NR_SHMEM_PMDMAPPED,
+ NR_FILE_THPS,
+ NR_FILE_PMDMAPPED,
NR_ANON_THPS,
NR_UNSTABLE_NFS, /* NFS unstable pages */
NR_VMSCAN_WRITE,
NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */
NR_DIRTIED, /* page dirtyings since bootup */
NR_WRITTEN, /* page writings since bootup */
- NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */
+ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */
NR_VM_NODE_STAT_ITEMS
};
@@ -245,11 +308,6 @@
#endif
};
-/* Mask used at gathering information at once (see memcontrol.c) */
-#define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE))
-#define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON))
-#define LRU_ALL ((1 << NR_LRU_LISTS) - 1)
-
/* Isolate unmapped file */
#define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2)
/* Isolate for asynchronous migration */
@@ -267,9 +325,10 @@
NR_WMARK
};
-#define min_wmark_pages(z) (z->watermark[WMARK_MIN])
-#define low_wmark_pages(z) (z->watermark[WMARK_LOW])
-#define high_wmark_pages(z) (z->watermark[WMARK_HIGH])
+#define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost)
+#define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost)
+#define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost)
+#define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost)
struct per_cpu_pages {
int count; /* number of pages in the list */
@@ -312,7 +371,7 @@
* Architecture Limit
* ---------------------------
* parisc, ia64, sparc <4G
- * s390 <2G
+ * s390, powerpc <2G
* arm Various
* alpha Unlimited or 0-16MB.
*
@@ -360,7 +419,8 @@
/* Read-mostly fields */
/* zone watermarks, access with *_wmark_pages(zone) macros */
- unsigned long watermark[NR_WMARK];
+ unsigned long _watermark[NR_WMARK];
+ unsigned long watermark_boost;
unsigned long nr_reserved_highatomic;
@@ -426,14 +486,8 @@
* Write access to present_pages at runtime should be protected by
* mem_hotplug_begin/end(). Any reader who can't tolerant drift of
* present_pages should get_online_mems() to get a stable value.
- *
- * Read access to managed_pages should be safe because it's unsigned
- * long. Write access to zone->managed_pages and totalram_pages are
- * protected by managed_page_count_lock at runtime. Idealy only
- * adjust_managed_page_count() should be used instead of directly
- * touching zone->managed_pages and totalram_pages.
*/
- unsigned long managed_pages;
+ atomic_long_t managed_pages;
unsigned long spanned_pages;
unsigned long present_pages;
@@ -482,6 +536,8 @@
unsigned long compact_cached_free_pfn;
/* pfn where async and sync compaction migration scanner should start */
unsigned long compact_cached_migrate_pfn[2];
+ unsigned long compact_init_migrate_pfn;
+ unsigned long compact_init_free_pfn;
#endif
#ifdef CONFIG_COMPACTION
@@ -522,6 +578,17 @@
PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */
};
+enum zone_flags {
+ ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks.
+ * Cleared when kswapd is woken.
+ */
+};
+
+static inline unsigned long zone_managed_pages(struct zone *zone)
+{
+ return (unsigned long)atomic_long_read(&zone->managed_pages);
+}
+
static inline unsigned long zone_end_pfn(const struct zone *zone)
{
return zone->zone_start_pfn + zone->spanned_pages;
@@ -612,6 +679,14 @@
extern struct page *mem_map;
#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+struct deferred_split {
+ spinlock_t split_queue_lock;
+ struct list_head split_queue;
+ unsigned long split_queue_len;
+};
+#endif
+
/*
* On NUMA machines, each NUMA node would have a pg_data_t to describe
* it's memory layout. On UMA machines there is a single pglist_data which
@@ -631,14 +706,10 @@
struct page_ext *node_page_ext;
#endif
#endif
-#ifndef CONFIG_NO_BOOTMEM
- struct bootmem_data *bdata;
-#endif
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
/*
- * Must be held any time you expect node_start_pfn, node_present_pages
- * or node_spanned_pages stay constant. Holding this will also
- * guarantee that any pfn_valid() stays that way.
+ * Must be held any time you expect node_start_pfn,
+ * node_present_pages, node_spanned_pages or nr_zones to stay constant.
*
* pgdat_resize_lock() and pgdat_resize_unlock() are provided to
* manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
@@ -692,14 +763,10 @@
* is the first PFN that needs to be initialised.
*/
unsigned long first_deferred_pfn;
- /* Number of non-deferred pages */
- unsigned long static_init_pgcnt;
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- spinlock_t split_queue_lock;
- struct list_head split_queue;
- unsigned long split_queue_len;
+ struct deferred_split deferred_split_queue;
#endif
/* Fields commonly accessed by the page reclaim scanner */
@@ -725,10 +792,6 @@
#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn)
#define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
-static inline spinlock_t *zone_lru_lock(struct zone *zone)
-{
- return &zone->zone_pgdat->lru_lock;
-}
static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
{
@@ -784,6 +847,12 @@
static inline void memory_present(int nid, unsigned long start, unsigned long end) {}
#endif
+#if defined(CONFIG_SPARSEMEM)
+void memblocks_present(void);
+#else
+static inline void memblocks_present(void) {}
+#endif
+
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
int local_memory_node(int node_id);
#else
@@ -795,18 +864,6 @@
*/
#define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones)
-#ifdef CONFIG_ZONE_DEVICE
-static inline bool is_dev_zone(const struct zone *zone)
-{
- return zone_idx(zone) == ZONE_DEVICE;
-}
-#else
-static inline bool is_dev_zone(const struct zone *zone)
-{
- return false;
-}
-#endif
-
/*
* Returns true if a zone has pages managed by the buddy allocator.
* All the reclaim decisions have to use this function rather than
@@ -815,7 +872,7 @@
*/
static inline bool managed_zone(struct zone *zone)
{
- return zone->managed_pages;
+ return zone_managed_pages(zone);
}
/* Returns true if a zone has memory */
@@ -867,7 +924,7 @@
}
/**
- * is_highmem - helper function to quickly check if a struct zone is a
+ * is_highmem - helper function to quickly check if a struct zone is a
* highmem zone or not. This is an attempt to keep references
* to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum.
* @zone - pointer to struct zone variable
@@ -885,6 +942,8 @@
struct ctl_table;
int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
+int watermark_boost_factor_sysctl_handler(struct ctl_table *, int,
+ void __user *, size_t *, loff_t *);
int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
@@ -1098,6 +1157,29 @@
#define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK)
#define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK)
+#define SUBSECTION_SHIFT 21
+
+#define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT)
+#define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT)
+#define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1))
+
+#if SUBSECTION_SHIFT > SECTION_SIZE_BITS
+#error Subsection size exceeds section size
+#else
+#define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT))
+#endif
+
+#define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION)
+#define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
+
+struct mem_section_usage {
+ DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
+ /* See declaration of similar field in struct zone */
+ unsigned long pageblock_flags[0];
+};
+
+void subsection_map_init(unsigned long pfn, unsigned long nr_pages);
+
struct page;
struct page_ext;
struct mem_section {
@@ -1115,8 +1197,7 @@
*/
unsigned long section_mem_map;
- /* See declaration of similar field in struct zone */
- unsigned long *pageblock_flags;
+ struct mem_section_usage *usage;
#ifdef CONFIG_PAGE_EXTENSION
/*
* If SPARSEMEM, pgdat doesn't have page_ext pointer. We use
@@ -1147,6 +1228,11 @@
extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
#endif
+static inline unsigned long *section_to_usemap(struct mem_section *ms)
+{
+ return ms->usage->pageblock_flags;
+}
+
static inline struct mem_section *__nr_to_section(unsigned long nr)
{
#ifdef CONFIG_SPARSEMEM_EXTREME
@@ -1157,8 +1243,8 @@
return NULL;
return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
}
-extern int __section_nr(struct mem_section* ms);
-extern unsigned long usemap_size(void);
+extern unsigned long __section_nr(struct mem_section *ms);
+extern size_t mem_section_usage_size(void);
/*
* We use the lower bits of the mem_map pointer to store
@@ -1176,7 +1262,8 @@
#define SECTION_MARKED_PRESENT (1UL<<0)
#define SECTION_HAS_MEM_MAP (1UL<<1)
#define SECTION_IS_ONLINE (1UL<<2)
-#define SECTION_MAP_LAST_BIT (1UL<<3)
+#define SECTION_IS_EARLY (1UL<<3)
+#define SECTION_MAP_LAST_BIT (1UL<<4)
#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1))
#define SECTION_NID_SHIFT 3
@@ -1202,6 +1289,11 @@
return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP));
}
+static inline int early_section(struct mem_section *section)
+{
+ return (section && (section->section_mem_map & SECTION_IS_EARLY));
+}
+
static inline int valid_section_nr(unsigned long nr)
{
return valid_section(__nr_to_section(nr));
@@ -1229,14 +1321,42 @@
return __nr_to_section(pfn_to_section_nr(pfn));
}
-extern int __highest_present_section_nr;
+extern unsigned long __highest_present_section_nr;
+
+static inline int subsection_map_index(unsigned long pfn)
+{
+ return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION;
+}
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
+{
+ int idx = subsection_map_index(pfn);
+
+ return test_bit(idx, ms->usage->subsection_map);
+}
+#else
+static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
+{
+ return 1;
+}
+#endif
#ifndef CONFIG_HAVE_ARCH_PFN_VALID
static inline int pfn_valid(unsigned long pfn)
{
+ struct mem_section *ms;
+
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
- return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
+ ms = __nr_to_section(pfn_to_section_nr(pfn));
+ if (!valid_section(ms))
+ return 0;
+ /*
+ * Traditionally early sections always returned pfn_valid() for
+ * the entire section-sized span.
+ */
+ return early_section(ms) || pfn_section_valid(ms, pfn);
}
#endif
@@ -1267,6 +1387,8 @@
#else
#define sparse_init() do {} while (0)
#define sparse_index_init(_sec, _nid) do {} while (0)
+#define pfn_present pfn_valid
+#define subsection_map_init(_pfn, _nr_pages) do {} while (0)
#endif /* CONFIG_SPARSEMEM */
/*
@@ -1288,7 +1410,7 @@
/*
* If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
- * need to check pfn validility within that MAX_ORDER_NR_PAGES block.
+ * need to check pfn validity within that MAX_ORDER_NR_PAGES block.
* pfn_valid_within() should be used in this case; we optimise this away
* when we have no holes within a MAX_ORDER_NR_PAGES block.
*/