summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorStephen Rothwell <sfr@canb.auug.org.au>2015-02-03 17:30:52 +1100
committerStephen Rothwell <sfr@canb.auug.org.au>2015-02-03 17:30:52 +1100
commit68a9462de925abe75a9e347d5af9d12a60a314a1 (patch)
treed01facbd1070ecc739237cb40f6331cf227fdc39 /include
parent2ef7f2b717bf8d70650fedef29d177c36da164b3 (diff)
parent78ccbbfb50bf6ad3415760fec43c5808ac9b3b26 (diff)
Merge branch 'akpm-current/current'
Conflicts: arch/powerpc/include/asm/pgtable-ppc32.h include/linux/mm.h mm/swap.c
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/4level-fixup.h1
-rw-r--r--include/asm-generic/pgtable.h168
-rw-r--r--include/linux/bitmap.h59
-rw-r--r--include/linux/compaction.h86
-rw-r--r--include/linux/cpumask.h71
-rw-r--r--include/linux/crc64_ecma.h56
-rw-r--r--include/linux/cryptohash.h2
-rw-r--r--include/linux/fs.h12
-rw-r--r--include/linux/gfp.h4
-rw-r--r--include/linux/huge_mm.h16
-rw-r--r--include/linux/hugetlb.h10
-rw-r--r--include/linux/init_task.h3
-rw-r--r--include/linux/input.h28
-rw-r--r--include/linux/kernfs.h7
-rw-r--r--include/linux/kexec.h24
-rw-r--r--include/linux/kvm_host.h11
-rw-r--r--include/linux/list_lru.h82
-rw-r--r--include/linux/memcontrol.h92
-rw-r--r--include/linux/migrate.h4
-rw-r--r--include/linux/mm.h133
-rw-r--r--include/linux/mm_types.h23
-rw-r--r--include/linux/mmzone.h15
-rw-r--r--include/linux/nodemask.h67
-rw-r--r--include/linux/oom.h18
-rw-r--r--include/linux/page_counter.h3
-rw-r--r--include/linux/page_ext.h2
-rw-r--r--include/linux/printk.h6
-rw-r--r--include/linux/rbtree.h2
-rw-r--r--include/linux/rmap.h11
-rw-r--r--include/linux/rtc.h4
-rw-r--r--include/linux/sched.h2
-rw-r--r--include/linux/seq_buf.h3
-rw-r--r--include/linux/seq_file.h25
-rw-r--r--include/linux/shrinker.h6
-rw-r--r--include/linux/slab.h34
-rw-r--r--include/linux/slab_def.h2
-rw-r--r--include/linux/slub_def.h2
-rw-r--r--include/linux/string.h7
-rw-r--r--include/linux/string_helpers.h4
-rw-r--r--include/linux/swap.h15
-rw-r--r--include/linux/swapops.h8
-rw-r--r--include/linux/types.h5
-rw-r--r--include/linux/vm_event_item.h1
-rw-r--r--include/linux/zpool.h5
-rw-r--r--include/linux/zsmalloc.h2
-rw-r--r--include/trace/events/compaction.h209
-rw-r--r--include/trace/events/kmem.h7
-rw-r--r--include/uapi/asm-generic/mman-common.h1
-rw-r--r--include/uapi/linux/kernel-page-flags.h1
-rw-r--r--include/uapi/linux/kexec.h6
-rw-r--r--include/uapi/linux/mempolicy.h2
51 files changed, 769 insertions, 598 deletions
diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index 77ff547730af..5bdab6bffd23 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -4,6 +4,7 @@
#define __ARCH_HAS_4LEVEL_HACK
#define __PAGETABLE_PUD_FOLDED
+#define PUD_SHIFT PGDIR_SHIFT
#define PUD_SIZE PGDIR_SIZE
#define PUD_MASK PGDIR_MASK
#define PTRS_PER_PUD 1
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 177d5973b132..4d46085c1b90 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -244,10 +244,6 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
# define pte_accessible(mm, pte) ((void)(pte), 1)
#endif
-#ifndef pte_present_nonuma
-#define pte_present_nonuma(pte) pte_present(pte)
-#endif
-
#ifndef flush_tlb_fix_spurious_fault
#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
#endif
@@ -474,21 +470,6 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
return pte;
}
-
-static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
-{
- return pte;
-}
-
-static inline pte_t pte_file_mksoft_dirty(pte_t pte)
-{
- return pte;
-}
-
-static inline int pte_file_soft_dirty(pte_t pte)
-{
- return 0;
-}
#endif
#ifndef __HAVE_PFNMAP_TRACKING
@@ -688,155 +669,24 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
#endif
}
-#ifdef CONFIG_NUMA_BALANCING
-/*
- * _PAGE_NUMA distinguishes between an unmapped page table entry, an entry that
- * is protected for PROT_NONE and a NUMA hinting fault entry. If the
- * architecture defines __PAGE_PROTNONE then it should take that into account
- * but those that do not can rely on the fact that the NUMA hinting scanner
- * skips inaccessible VMAs.
- *
- * pte/pmd_present() returns true if pte/pmd_numa returns true. Page
- * fault triggers on those regions if pte/pmd_numa returns true
- * (because _PAGE_PRESENT is not set).
- */
-#ifndef pte_numa
-static inline int pte_numa(pte_t pte)
-{
- return ptenuma_flags(pte) == _PAGE_NUMA;
-}
-#endif
-
-#ifndef pmd_numa
-static inline int pmd_numa(pmd_t pmd)
-{
- return pmdnuma_flags(pmd) == _PAGE_NUMA;
-}
-#endif
-
+#ifndef CONFIG_NUMA_BALANCING
/*
- * pte/pmd_mknuma sets the _PAGE_ACCESSED bitflag automatically
- * because they're called by the NUMA hinting minor page fault. If we
- * wouldn't set the _PAGE_ACCESSED bitflag here, the TLB miss handler
- * would be forced to set it later while filling the TLB after we
- * return to userland. That would trigger a second write to memory
- * that we optimize away by setting _PAGE_ACCESSED here.
+ * Technically a PTE can be PROTNONE even when not doing NUMA balancing but
+ * the only case the kernel cares is for NUMA balancing and is only ever set
+ * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked
+ * _PAGE_PROTNONE so by by default, implement the helper as "always no". It
+ * is the responsibility of the caller to distinguish between PROT_NONE
+ * protections and NUMA hinting fault protections.
*/
-#ifndef pte_mknonnuma
-static inline pte_t pte_mknonnuma(pte_t pte)
-{
- pteval_t val = pte_val(pte);
-
- val &= ~_PAGE_NUMA;
- val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
- return __pte(val);
-}
-#endif
-
-#ifndef pmd_mknonnuma
-static inline pmd_t pmd_mknonnuma(pmd_t pmd)
-{
- pmdval_t val = pmd_val(pmd);
-
- val &= ~_PAGE_NUMA;
- val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
-
- return __pmd(val);
-}
-#endif
-
-#ifndef pte_mknuma
-static inline pte_t pte_mknuma(pte_t pte)
-{
- pteval_t val = pte_val(pte);
-
- VM_BUG_ON(!(val & _PAGE_PRESENT));
-
- val &= ~_PAGE_PRESENT;
- val |= _PAGE_NUMA;
-
- return __pte(val);
-}
-#endif
-
-#ifndef ptep_set_numa
-static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep)
-{
- pte_t ptent = *ptep;
-
- ptent = pte_mknuma(ptent);
- set_pte_at(mm, addr, ptep, ptent);
- return;
-}
-#endif
-
-#ifndef pmd_mknuma
-static inline pmd_t pmd_mknuma(pmd_t pmd)
-{
- pmdval_t val = pmd_val(pmd);
-
- val &= ~_PAGE_PRESENT;
- val |= _PAGE_NUMA;
-
- return __pmd(val);
-}
-#endif
-
-#ifndef pmdp_set_numa
-static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmdp)
-{
- pmd_t pmd = *pmdp;
-
- pmd = pmd_mknuma(pmd);
- set_pmd_at(mm, addr, pmdp, pmd);
- return;
-}
-#endif
-#else
-static inline int pmd_numa(pmd_t pmd)
+static inline int pte_protnone(pte_t pte)
{
return 0;
}
-static inline int pte_numa(pte_t pte)
+static inline int pmd_protnone(pmd_t pmd)
{
return 0;
}
-
-static inline pte_t pte_mknonnuma(pte_t pte)
-{
- return pte;
-}
-
-static inline pmd_t pmd_mknonnuma(pmd_t pmd)
-{
- return pmd;
-}
-
-static inline pte_t pte_mknuma(pte_t pte)
-{
- return pte;
-}
-
-static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep)
-{
- return;
-}
-
-
-static inline pmd_t pmd_mknuma(pmd_t pmd)
-{
- return pmd;
-}
-
-static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmdp)
-{
- return ;
-}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_MMU */
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 202e4034fe26..dbfbf4990005 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -52,16 +52,13 @@
* bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit)
* bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap
* bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz
- * bitmap_scnprintf(buf, len, src, nbits) Print bitmap src to buf
* bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf
* bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf
- * bitmap_scnlistprintf(buf, len, src, nbits) Print bitmap src as list to buf
* bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf
* bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf
* bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region
* bitmap_release_region(bitmap, pos, order) Free specified bit region
* bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region
- * bitmap_print_to_pagebuf(list, buf, mask, nbits) Print bitmap src as list/hex
*/
/*
@@ -96,10 +93,10 @@ extern int __bitmap_equal(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
extern void __bitmap_complement(unsigned long *dst, const unsigned long *src,
unsigned int nbits);
-extern void __bitmap_shift_right(unsigned long *dst,
- const unsigned long *src, int shift, int bits);
-extern void __bitmap_shift_left(unsigned long *dst,
- const unsigned long *src, int shift, int bits);
+extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src,
+ unsigned int shift, unsigned int nbits);
+extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src,
+ unsigned int shift, unsigned int nbits);
extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
@@ -147,31 +144,31 @@ bitmap_find_next_zero_area(unsigned long *map,
align_mask, 0);
}
-extern int bitmap_scnprintf(char *buf, unsigned int len,
- const unsigned long *src, int nbits);
extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user,
unsigned long *dst, int nbits);
extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen,
unsigned long *dst, int nbits);
-extern int bitmap_scnlistprintf(char *buf, unsigned int len,
- const unsigned long *src, int nbits);
extern int bitmap_parselist(const char *buf, unsigned long *maskp,
int nmaskbits);
extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen,
unsigned long *dst, int nbits);
extern void bitmap_remap(unsigned long *dst, const unsigned long *src,
- const unsigned long *old, const unsigned long *new, int bits);
+ const unsigned long *old, const unsigned long *new, unsigned int nbits);
extern int bitmap_bitremap(int oldbit,
const unsigned long *old, const unsigned long *new, int bits);
extern void bitmap_onto(unsigned long *dst, const unsigned long *orig,
- const unsigned long *relmap, int bits);
+ const unsigned long *relmap, unsigned int bits);
extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
- int sz, int bits);
+ unsigned int sz, unsigned int nbits);
extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order);
extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order);
extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order);
-extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
-extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits);
+#ifdef __BIG_ENDIAN
+extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits);
+#else
+#define bitmap_copy_le bitmap_copy
+#endif
+extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits);
extern int bitmap_print_to_pagebuf(bool list, char *buf,
const unsigned long *maskp, int nmaskbits);
@@ -185,33 +182,33 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf,
#define small_const_nbits(nbits) \
(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
-static inline void bitmap_zero(unsigned long *dst, int nbits)
+static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
{
if (small_const_nbits(nbits))
*dst = 0UL;
else {
- int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
memset(dst, 0, len);
}
}
-static inline void bitmap_fill(unsigned long *dst, int nbits)
+static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
{
- size_t nlongs = BITS_TO_LONGS(nbits);
+ unsigned int nlongs = BITS_TO_LONGS(nbits);
if (!small_const_nbits(nbits)) {
- int len = (nlongs - 1) * sizeof(unsigned long);
+ unsigned int len = (nlongs - 1) * sizeof(unsigned long);
memset(dst, 0xff, len);
}
dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
}
static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
- int nbits)
+ unsigned int nbits)
{
if (small_const_nbits(nbits))
*dst = *src;
else {
- int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
memcpy(dst, src, len);
}
}
@@ -309,22 +306,22 @@ static inline int bitmap_weight(const unsigned long *src, unsigned int nbits)
return __bitmap_weight(src, nbits);
}
-static inline void bitmap_shift_right(unsigned long *dst,
- const unsigned long *src, int n, int nbits)
+static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
+ unsigned int shift, int nbits)
{
if (small_const_nbits(nbits))
- *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> n;
+ *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift;
else
- __bitmap_shift_right(dst, src, n, nbits);
+ __bitmap_shift_right(dst, src, shift, nbits);
}
-static inline void bitmap_shift_left(unsigned long *dst,
- const unsigned long *src, int n, int nbits)
+static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src,
+ unsigned int shift, unsigned int nbits)
{
if (small_const_nbits(nbits))
- *dst = (*src << n) & BITMAP_LAST_WORD_MASK(nbits);
+ *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits);
else
- __bitmap_shift_left(dst, src, n, nbits);
+ __bitmap_shift_left(dst, src, shift, nbits);
}
static inline int bitmap_parse(const char *buf, unsigned int buflen,
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 3238ffa33f68..a014559e4a49 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -12,6 +12,10 @@
#define COMPACT_PARTIAL 3
/* The full zone was compacted */
#define COMPACT_COMPLETE 4
+/* For more detailed tracepoint output */
+#define COMPACT_NO_SUITABLE_PAGE 5
+#define COMPACT_NOT_SUITABLE_ZONE 6
+/* When adding new state, please change compaction_status_string, too */
/* Used to signal whether compaction detected need_sched() or lock contention */
/* No contention detected */
@@ -21,6 +25,8 @@
/* Zone lock or lru_lock was contended in async compaction */
#define COMPACT_CONTENDED_LOCK 2
+struct alloc_context; /* in mm/internal.h */
+
#ifdef CONFIG_COMPACTION
extern int sysctl_compact_memory;
extern int sysctl_compaction_handler(struct ctl_table *table, int write,
@@ -30,81 +36,25 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos);
extern int fragmentation_index(struct zone *zone, unsigned int order);
-extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
- int order, gfp_t gfp_mask, nodemask_t *mask,
- enum migrate_mode mode, int *contended,
- int alloc_flags, int classzone_idx);
+extern unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
+ int alloc_flags, const struct alloc_context *ac,
+ enum migrate_mode mode, int *contended);
extern void compact_pgdat(pg_data_t *pgdat, int order);
extern void reset_isolation_suitable(pg_data_t *pgdat);
extern unsigned long compaction_suitable(struct zone *zone, int order,
int alloc_flags, int classzone_idx);
-/* Do not skip compaction more than 64 times */
-#define COMPACT_MAX_DEFER_SHIFT 6
-
-/*
- * Compaction is deferred when compaction fails to result in a page
- * allocation success. 1 << compact_defer_limit compactions are skipped up
- * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
- */
-static inline void defer_compaction(struct zone *zone, int order)
-{
- zone->compact_considered = 0;
- zone->compact_defer_shift++;
-
- if (order < zone->compact_order_failed)
- zone->compact_order_failed = order;
-
- if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
- zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
-}
-
-/* Returns true if compaction should be skipped this time */
-static inline bool compaction_deferred(struct zone *zone, int order)
-{
- unsigned long defer_limit = 1UL << zone->compact_defer_shift;
-
- if (order < zone->compact_order_failed)
- return false;
-
- /* Avoid possible overflow */
- if (++zone->compact_considered > defer_limit)
- zone->compact_considered = defer_limit;
-
- return zone->compact_considered < defer_limit;
-}
-
-/*
- * Update defer tracking counters after successful compaction of given order,
- * which means an allocation either succeeded (alloc_success == true) or is
- * expected to succeed.
- */
-static inline void compaction_defer_reset(struct zone *zone, int order,
- bool alloc_success)
-{
- if (alloc_success) {
- zone->compact_considered = 0;
- zone->compact_defer_shift = 0;
- }
- if (order >= zone->compact_order_failed)
- zone->compact_order_failed = order + 1;
-}
-
-/* Returns true if restarting compaction after many failures */
-static inline bool compaction_restarting(struct zone *zone, int order)
-{
- if (order < zone->compact_order_failed)
- return false;
-
- return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
- zone->compact_considered >= 1UL << zone->compact_defer_shift;
-}
+extern void defer_compaction(struct zone *zone, int order);
+extern bool compaction_deferred(struct zone *zone, int order);
+extern void compaction_defer_reset(struct zone *zone, int order,
+ bool alloc_success);
+extern bool compaction_restarting(struct zone *zone, int order);
#else
-static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
- int order, gfp_t gfp_mask, nodemask_t *nodemask,
- enum migrate_mode mode, int *contended,
- int alloc_flags, int classzone_idx)
+static inline unsigned long try_to_compact_pages(gfp_t gfp_mask,
+ unsigned int order, int alloc_flags,
+ const struct alloc_context *ac,
+ enum migrate_mode mode, int *contended)
{
return COMPACT_CONTINUE;
}
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index b950e9d6008b..086549a665e2 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -22,6 +22,14 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
*/
#define cpumask_bits(maskp) ((maskp)->bits)
+/**
+ * cpumask_pr_args - printf args to output a cpumask
+ * @maskp: cpumask to be printed
+ *
+ * Can be used to provide arguments for '%*pb[l]' when printing a cpumask.
+ */
+#define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp)
+
#if NR_CPUS == 1
#define nr_cpu_ids 1
#else
@@ -539,21 +547,6 @@ static inline void cpumask_copy(struct cpumask *dstp,
#define cpumask_of(cpu) (get_cpu_mask(cpu))
/**
- * cpumask_scnprintf - print a cpumask into a string as comma-separated hex
- * @buf: the buffer to sprintf into
- * @len: the length of the buffer
- * @srcp: the cpumask to print
- *
- * If len is zero, returns zero. Otherwise returns the length of the
- * (nul-terminated) @buf string.
- */
-static inline int cpumask_scnprintf(char *buf, int len,
- const struct cpumask *srcp)
-{
- return bitmap_scnprintf(buf, len, cpumask_bits(srcp), nr_cpumask_bits);
-}
-
-/**
* cpumask_parse_user - extract a cpumask from a user string
* @buf: the buffer to extract from
* @len: the length of the buffer
@@ -564,7 +557,7 @@ static inline int cpumask_scnprintf(char *buf, int len,
static inline int cpumask_parse_user(const char __user *buf, int len,
struct cpumask *dstp)
{
- return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
+ return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpu_ids);
}
/**
@@ -579,23 +572,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
struct cpumask *dstp)
{
return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
- nr_cpumask_bits);
-}
-
-/**
- * cpulist_scnprintf - print a cpumask into a string as comma-separated list
- * @buf: the buffer to sprintf into
- * @len: the length of the buffer
- * @srcp: the cpumask to print
- *
- * If len is zero, returns zero. Otherwise returns the length of the
- * (nul-terminated) @buf string.
- */
-static inline int cpulist_scnprintf(char *buf, int len,
- const struct cpumask *srcp)
-{
- return bitmap_scnlistprintf(buf, len, cpumask_bits(srcp),
- nr_cpumask_bits);
+ nr_cpu_ids);
}
/**
@@ -610,7 +587,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
char *nl = strchr(buf, '\n');
unsigned int len = nl ? (unsigned int)(nl - buf) : strlen(buf);
- return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
+ return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpu_ids);
}
/**
@@ -622,7 +599,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
*/
static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
{
- return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
+ return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpu_ids);
}
/**
@@ -817,7 +794,7 @@ static inline ssize_t
cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
{
return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask),
- nr_cpumask_bits);
+ nr_cpu_ids);
}
/*
@@ -905,13 +882,13 @@ static inline void __cpu_clear(int cpu, volatile cpumask_t *dstp)
}
#define cpus_setall(dst) __cpus_setall(&(dst), NR_CPUS)
-static inline void __cpus_setall(cpumask_t *dstp, int nbits)
+static inline void __cpus_setall(cpumask_t *dstp, unsigned int nbits)
{
bitmap_fill(dstp->bits, nbits);
}
#define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS)
-static inline void __cpus_clear(cpumask_t *dstp, int nbits)
+static inline void __cpus_clear(cpumask_t *dstp, unsigned int nbits)
{
bitmap_zero(dstp->bits, nbits);
}
@@ -927,21 +904,21 @@ static inline int __cpu_test_and_set(int cpu, cpumask_t *addr)
#define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS)
static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p,
- const cpumask_t *src2p, int nbits)
+ const cpumask_t *src2p, unsigned int nbits)
{
return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
}
#define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS)
static inline void __cpus_or(cpumask_t *dstp, const cpumask_t *src1p,
- const cpumask_t *src2p, int nbits)
+ const cpumask_t *src2p, unsigned int nbits)
{
bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
}
#define cpus_xor(dst, src1, src2) __cpus_xor(&(dst), &(src1), &(src2), NR_CPUS)
static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p,
- const cpumask_t *src2p, int nbits)
+ const cpumask_t *src2p, unsigned int nbits)
{
bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
}
@@ -949,40 +926,40 @@ static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p,
#define cpus_andnot(dst, src1, src2) \
__cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS)
static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p,
- const cpumask_t *src2p, int nbits)
+ const cpumask_t *src2p, unsigned int nbits)
{
return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
}
#define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS)
static inline int __cpus_equal(const cpumask_t *src1p,
- const cpumask_t *src2p, int nbits)
+ const cpumask_t *src2p, unsigned int nbits)
{
return bitmap_equal(src1p->bits, src2p->bits, nbits);
}
#define cpus_intersects(src1, src2) __cpus_intersects(&(src1), &(src2), NR_CPUS)
static inline int __cpus_intersects(const cpumask_t *src1p,
- const cpumask_t *src2p, int nbits)
+ const cpumask_t *src2p, unsigned int nbits)
{
return bitmap_intersects(src1p->bits, src2p->bits, nbits);
}
#define cpus_subset(src1, src2) __cpus_subset(&(src1), &(src2), NR_CPUS)
static inline int __cpus_subset(const cpumask_t *src1p,
- const cpumask_t *src2p, int nbits)
+ const cpumask_t *src2p, unsigned int nbits)
{
return bitmap_subset(src1p->bits, src2p->bits, nbits);
}
#define cpus_empty(src) __cpus_empty(&(src), NR_CPUS)
-static inline int __cpus_empty(const cpumask_t *srcp, int nbits)
+static inline int __cpus_empty(const cpumask_t *srcp, unsigned int nbits)
{
return bitmap_empty(srcp->bits, nbits);
}
#define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS)
-static inline int __cpus_weight(const cpumask_t *srcp, int nbits)
+static inline int __cpus_weight(const cpumask_t *srcp, unsigned int nbits)
{
return bitmap_weight(srcp->bits, nbits);
}
diff --git a/include/linux/crc64_ecma.h b/include/linux/crc64_ecma.h
new file mode 100644
index 000000000000..bba7a4d692b3
--- /dev/null
+++ b/include/linux/crc64_ecma.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __CRC64_ECMA_H_
+#define __CRC64_ECMA_H_
+
+#include <linux/types.h>
+
+
+#define CRC64_DEFAULT_INITVAL 0xFFFFFFFFFFFFFFFFULL
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * @pdata: pointer to the data to compute checksum for.
+ * @nbytes: number of bytes in data buffer.
+ * @seed: CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed);
+
+#endif /* __CRC64_ECMA_H_ */
diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h
index 2cd9f1cf9fa3..f4754282c9c2 100644
--- a/include/linux/cryptohash.h
+++ b/include/linux/cryptohash.h
@@ -1,6 +1,8 @@
#ifndef __CRYPTOHASH_H
#define __CRYPTOHASH_H
+#include <uapi/linux/types.h>
+
#define SHA_DIGEST_WORDS 5
#define SHA_MESSAGE_BYTES (512 /*bits*/ / 8)
#define SHA_WORKSPACE_WORDS 16
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 59d294cdd6e5..aeb9dc3082d5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -401,7 +401,6 @@ struct address_space {
spinlock_t tree_lock; /* and lock protecting it */
atomic_t i_mmap_writable;/* count VM_SHARED mappings */
struct rb_root i_mmap; /* tree of private and shared mappings */
- struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */
/* Protected by tree_lock together with the radix tree */
unsigned long nrpages; /* number of total pages */
@@ -492,8 +491,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping)
*/
static inline int mapping_mapped(struct address_space *mapping)
{
- return !RB_EMPTY_ROOT(&mapping->i_mmap) ||
- !list_empty(&mapping->i_mmap_nonlinear);
+ return !RB_EMPTY_ROOT(&mapping->i_mmap);
}
/*
@@ -1656,8 +1654,10 @@ struct super_operations {
struct dquot **(*get_dquots)(struct inode *);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
- long (*nr_cached_objects)(struct super_block *, int);
- long (*free_cached_objects)(struct super_block *, long, int);
+ long (*nr_cached_objects)(struct super_block *,
+ struct shrink_control *);
+ long (*free_cached_objects)(struct super_block *,
+ struct shrink_control *);
};
/*
@@ -2526,8 +2526,6 @@ extern int sb_min_blocksize(struct super_block *, int);
extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
-extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
- unsigned long size, pgoff_t pgoff);
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index b840e3b2770d..60110e06419d 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -335,11 +335,15 @@ alloc_pages(gfp_t gfp_mask, unsigned int order)
extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
struct vm_area_struct *vma, unsigned long addr,
int node);
+extern struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma,
+ unsigned long addr, int order);
#else
#define alloc_pages(gfp_mask, order) \
alloc_pages_node(numa_node_id(), gfp_mask, order)
#define alloc_pages_vma(gfp_mask, order, vma, addr, node) \
alloc_pages(gfp_mask, order)
+#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
+ alloc_pages(gfp_mask, order)
#endif
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
#define alloc_page_vma(gfp_mask, vma, addr) \
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ad9051bab267..44a840a53974 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
unsigned long addr,
pmd_t *pmd,
unsigned int flags);
+extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ pmd_t *pmd, unsigned long addr);
extern int zap_huge_pmd(struct mmu_gather *tlb,
struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr);
@@ -56,6 +59,7 @@ extern pmd_t *page_check_address_pmd(struct page *page,
unsigned long address,
enum page_check_address_pmd_flag flag,
spinlock_t **ptl);
+extern int pmd_freeable(pmd_t pmd);
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
@@ -157,6 +161,13 @@ static inline int hpage_nr_pages(struct page *page)
extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pmd_t pmd, pmd_t *pmdp);
+extern struct page *huge_zero_page;
+
+static inline bool is_huge_zero_page(struct page *page)
+{
+ return ACCESS_ONCE(huge_zero_page) == page;
+}
+
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
@@ -206,6 +217,11 @@ static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_str
return 0;
}
+static inline bool is_huge_zero_page(struct page *page)
+{
+ return false;
+}
+
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* _LINUX_HUGE_MM_H */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 431b7fc605c9..7b5785032049 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -86,7 +86,7 @@ void free_huge_page(struct page *page);
pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
#endif
-extern unsigned long hugepages_treat_as_movable;
+extern int hugepages_treat_as_movable;
extern int sysctl_hugetlb_shm_group;
extern struct list_head huge_boot_pages;
@@ -99,9 +99,9 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
int write);
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
- pmd_t *pmd, int write);
+ pmd_t *pmd, int flags);
struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
- pud_t *pud, int write);
+ pud_t *pud, int flags);
int pmd_huge(pmd_t pmd);
int pud_huge(pud_t pmd);
unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
@@ -133,8 +133,8 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
static inline void hugetlb_show_meminfo(void)
{
}
-#define follow_huge_pmd(mm, addr, pmd, write) NULL
-#define follow_huge_pud(mm, addr, pud, write) NULL
+#define follow_huge_pmd(mm, addr, pmd, flags) NULL
+#define follow_huge_pud(mm, addr, pud, flags) NULL
#define prepare_hugepage_range(file, addr, len) (-EINVAL)
#define pmd_huge(x) 0
#define pud_huge(x) 0
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 3037fc085e8e..d3d43ecf148c 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -193,6 +193,9 @@ extern struct task_group root_task_group;
.nr_cpus_allowed= NR_CPUS, \
.mm = NULL, \
.active_mm = &init_mm, \
+ .restart_block = { \
+ .fn = do_no_restart_syscall, \
+ }, \
.se = { \
.group_node = LIST_HEAD_INIT(tsk.se.group_node), \
}, \
diff --git a/include/linux/input.h b/include/linux/input.h
index 82ce323b9986..3b4c32f7312a 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -79,6 +79,7 @@ struct input_value {
* @led: reflects current state of device's LEDs
* @snd: reflects current state of sound effects
* @sw: reflects current state of device's switches
+ * @leds: leds objects for the device's LEDs
* @open: this method is called when the very first user calls
* input_open_device(). The driver must prepare the device
* to start generating events (start polling thread,
@@ -164,6 +165,8 @@ struct input_dev {
unsigned long snd[BITS_TO_LONGS(SND_CNT)];
unsigned long sw[BITS_TO_LONGS(SW_CNT)];
+ struct led_classdev *leds;
+
int (*open)(struct input_dev *dev);
void (*close)(struct input_dev *dev);
int (*flush)(struct input_dev *dev, struct file *file);
@@ -531,4 +534,29 @@ int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file);
int input_ff_create_memless(struct input_dev *dev, void *data,
int (*play_effect)(struct input_dev *, void *, struct ff_effect *));
+#ifdef CONFIG_INPUT_LEDS
+
+void input_led_init(void);
+void input_led_exit(void);
+
+int input_led_connect(struct input_dev *dev);
+void input_led_disconnect(struct input_dev *dev);
+
+#else
+
+static inline void input_led_init(void) { }
+
+static inline void input_led_exit(void) { }
+
+static inline int input_led_connect(struct input_dev *dev)
+{
+ return 0;
+}
+
+static inline void input_led_disconnect(struct input_dev *dev)
+{
+}
+
+#endif
+
#endif
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index d4e01b358341..71ecdab1671b 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -43,7 +43,6 @@ enum kernfs_node_flag {
KERNFS_HAS_SEQ_SHOW = 0x0040,
KERNFS_HAS_MMAP = 0x0080,
KERNFS_LOCKDEP = 0x0100,
- KERNFS_STATIC_NAME = 0x0200,
KERNFS_SUICIDAL = 0x0400,
KERNFS_SUICIDED = 0x0800,
};
@@ -291,7 +290,6 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
umode_t mode, loff_t size,
const struct kernfs_ops *ops,
void *priv, const void *ns,
- bool name_is_static,
struct lock_class_key *key);
struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
const char *name,
@@ -369,8 +367,7 @@ kernfs_create_dir_ns(struct kernfs_node *parent, const char *name,
static inline struct kernfs_node *
__kernfs_create_file(struct kernfs_node *parent, const char *name,
umode_t mode, loff_t size, const struct kernfs_ops *ops,
- void *priv, const void *ns, bool name_is_static,
- struct lock_class_key *key)
+ void *priv, const void *ns, struct lock_class_key *key)
{ return ERR_PTR(-ENOSYS); }
static inline struct kernfs_node *
@@ -439,7 +436,7 @@ kernfs_create_file_ns(struct kernfs_node *parent, const char *name,
key = (struct lock_class_key *)&ops->lockdep_key;
#endif
return __kernfs_create_file(parent, name, mode, size, ops, priv, ns,
- false, key);
+ key);
}
static inline struct kernfs_node *
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 9d957b7ae095..87e37264d464 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -1,6 +1,19 @@
#ifndef LINUX_KEXEC_H
#define LINUX_KEXEC_H
+#define IND_DESTINATION_BIT 0
+#define IND_INDIRECTION_BIT 1
+#define IND_DONE_BIT 2
+#define IND_SOURCE_BIT 3
+
+#define IND_DESTINATION (1 << IND_DESTINATION_BIT)
+#define IND_INDIRECTION (1 << IND_INDIRECTION_BIT)
+#define IND_DONE (1 << IND_DONE_BIT)
+#define IND_SOURCE (1 << IND_SOURCE_BIT)
+#define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE)
+
+#if !defined(__ASSEMBLY__)
+
#include <uapi/linux/kexec.h>
#ifdef CONFIG_KEXEC
@@ -64,10 +77,6 @@
*/
typedef unsigned long kimage_entry_t;
-#define IND_DESTINATION 0x1
-#define IND_INDIRECTION 0x2
-#define IND_DONE 0x4
-#define IND_SOURCE 0x8
struct kexec_segment {
/*
@@ -122,8 +131,6 @@ struct kimage {
kimage_entry_t *entry;
kimage_entry_t *last_entry;
- unsigned long destination;
-
unsigned long start;
struct page *control_code_page;
struct page *swap_page;
@@ -258,6 +265,8 @@ unsigned long paddr_vmcoreinfo_note(void);
vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name)
#define VMCOREINFO_CONFIG(name) \
vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
+#define VMCOREINFO_PHYS_BASE(value) \
+ vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
extern struct kimage *kexec_image;
extern struct kimage *kexec_crash_image;
@@ -313,4 +322,7 @@ struct task_struct;
static inline void crash_kexec(struct pt_regs *regs) { }
static inline int kexec_should_crash(struct task_struct *p) { return 0; }
#endif /* CONFIG_KEXEC */
+
+#endif /* !defined(__ASSEBMLY__) */
+
#endif /* LINUX_KEXEC_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7d6719522f1f..dec62787c000 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -200,17 +200,6 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
#endif
-/*
- * Carry out a gup that requires IO. Allow the mm to relinquish the mmap
- * semaphore if the filemap/swap has to wait on a page lock. pagep == NULL
- * controls whether we retry the gup one more time to completion in that case.
- * Typically this is called after a FAULT_FLAG_RETRY_NOWAIT in the main tdp
- * handler.
- */
-int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long addr, bool write_fault,
- struct page **pagep);
-
enum {
OUTSIDE_GUEST_MODE,
IN_GUEST_MODE,
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index f3434533fbf8..2a6b9947aaa3 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -9,6 +9,9 @@
#include <linux/list.h>
#include <linux/nodemask.h>
+#include <linux/shrinker.h>
+
+struct mem_cgroup;
/* list_lru_walk_cb has to always return one of those */
enum lru_status {
@@ -21,24 +24,45 @@ enum lru_status {
internally, but has to return locked. */
};
-struct list_lru_node {
- spinlock_t lock;
+struct list_lru_one {
struct list_head list;
- /* kept as signed so we can catch imbalance bugs */
+ /* may become negative during memcg reparenting */
long nr_items;
+};
+
+struct list_lru_memcg {
+ /* array of per cgroup lists, indexed by memcg_cache_id */
+ struct list_lru_one *lru[0];
+};
+
+struct list_lru_node {
+ /* protects all lists on the node, including per cgroup */
+ spinlock_t lock;
+ /* global list, used for the root cgroup in cgroup aware lrus */
+ struct list_lru_one lru;
+#ifdef CONFIG_MEMCG_KMEM
+ /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
+ struct list_lru_memcg *memcg_lrus;
+#endif
} ____cacheline_aligned_in_smp;
struct list_lru {
struct list_lru_node *node;
- nodemask_t active_nodes;
+#ifdef CONFIG_MEMCG_KMEM
+ struct list_head list;
+#endif
};
void list_lru_destroy(struct list_lru *lru);
-int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key);
-static inline int list_lru_init(struct list_lru *lru)
-{
- return list_lru_init_key(lru, NULL);
-}
+int __list_lru_init(struct list_lru *lru, bool memcg_aware,
+ struct lock_class_key *key);
+
+#define list_lru_init(lru) __list_lru_init((lru), false, NULL)
+#define list_lru_init_key(lru, key) __list_lru_init((lru), false, (key))
+#define list_lru_init_memcg(lru) __list_lru_init((lru), true, NULL)
+
+int memcg_update_all_list_lrus(int num_memcgs);
+void memcg_drain_all_list_lrus(int src_idx, int dst_idx);
/**
* list_lru_add: add an element to the lru list's tail
@@ -72,32 +96,48 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item);
bool list_lru_del(struct list_lru *lru, struct list_head *item);
/**
- * list_lru_count_node: return the number of objects currently held by @lru
+ * list_lru_count_one: return the number of objects currently held by @lru
* @lru: the lru pointer.
* @nid: the node id to count from.
+ * @memcg: the cgroup to count from.
*
* Always return a non-negative number, 0 for empty lists. There is no
* guarantee that the list is not updated while the count is being computed.
* Callers that want such a guarantee need to provide an outer lock.
*/
+unsigned long list_lru_count_one(struct list_lru *lru,
+ int nid, struct mem_cgroup *memcg);
unsigned long list_lru_count_node(struct list_lru *lru, int nid);
+
+static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
+ struct shrink_control *sc)
+{
+ return list_lru_count_one(lru, sc->nid, sc->memcg);
+}
+
static inline unsigned long list_lru_count(struct list_lru *lru)
{
long count = 0;
int nid;
- for_each_node_mask(nid, lru->active_nodes)
+ for_each_node_state(nid, N_NORMAL_MEMORY)
count += list_lru_count_node(lru, nid);
return count;
}
-typedef enum lru_status
-(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
+void list_lru_isolate(struct list_lru_one *list, struct list_head *item);
+void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
+ struct list_head *head);
+
+typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
+ struct list_lru_one *list, spinlock_t *lock, void *cb_arg);
+
/**
- * list_lru_walk_node: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items.
* @lru: the lru pointer.
* @nid: the node id to scan from.
+ * @memcg: the cgroup to scan from.
* @isolate: callback function that is resposible for deciding what to do with
* the item currently being scanned
* @cb_arg: opaque type that will be passed to @isolate
@@ -115,18 +155,30 @@ typedef enum lru_status
*
* Return value: the number of objects effectively removed from the LRU.
*/
+unsigned long list_lru_walk_one(struct list_lru *lru,
+ int nid, struct mem_cgroup *memcg,
+ list_lru_walk_cb isolate, void *cb_arg,
+ unsigned long *nr_to_walk);
unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
list_lru_walk_cb isolate, void *cb_arg,
unsigned long *nr_to_walk);
static inline unsigned long
+list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
+ list_lru_walk_cb isolate, void *cb_arg)
+{
+ return list_lru_walk_one(lru, sc->nid, sc->memcg, isolate, cb_arg,
+ &sc->nr_to_scan);
+}
+
+static inline unsigned long
list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
void *cb_arg, unsigned long nr_to_walk)
{
long isolated = 0;
int nid;
- for_each_node_mask(nid, lru->active_nodes) {
+ for_each_node_state(nid, N_NORMAL_MEMORY) {
isolated += list_lru_walk_node(lru, nid, isolate,
cb_arg, &nr_to_walk);
if (nr_to_walk <= 0)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 7c95af8d552c..72dff5fb0d0c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -52,7 +52,27 @@ struct mem_cgroup_reclaim_cookie {
unsigned int generation;
};
+enum mem_cgroup_events_index {
+ MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */
+ MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */
+ MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */
+ MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */
+ MEM_CGROUP_EVENTS_NSTATS,
+ /* default hierarchy events */
+ MEMCG_LOW = MEM_CGROUP_EVENTS_NSTATS,
+ MEMCG_HIGH,
+ MEMCG_MAX,
+ MEMCG_OOM,
+ MEMCG_NR_EVENTS,
+};
+
#ifdef CONFIG_MEMCG
+void mem_cgroup_events(struct mem_cgroup *memcg,
+ enum mem_cgroup_events_index idx,
+ unsigned int nr);
+
+bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
+
int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask, struct mem_cgroup **memcgp);
void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
@@ -102,6 +122,7 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
* For memory reclaim.
*/
int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec);
+bool mem_cgroup_lruvec_online(struct lruvec *lruvec);
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list);
void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int);
@@ -138,12 +159,10 @@ static inline bool mem_cgroup_disabled(void)
return false;
}
-struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked,
- unsigned long *flags);
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked,
- unsigned long *flags);
+struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page);
void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
enum mem_cgroup_stat_index idx, int val);
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg);
static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
enum mem_cgroup_stat_index idx)
@@ -176,6 +195,18 @@ void mem_cgroup_split_huge_fixup(struct page *head);
#else /* CONFIG_MEMCG */
struct mem_cgroup;
+static inline void mem_cgroup_events(struct mem_cgroup *memcg,
+ enum mem_cgroup_events_index idx,
+ unsigned int nr)
+{
+}
+
+static inline bool mem_cgroup_low(struct mem_cgroup *root,
+ struct mem_cgroup *memcg)
+{
+ return false;
+}
+
static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask,
struct mem_cgroup **memcgp)
@@ -268,6 +299,11 @@ mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
return 1;
}
+static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
+{
+ return true;
+}
+
static inline unsigned long
mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
@@ -285,14 +321,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
{
}
-static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
- bool *locked, unsigned long *flags)
+static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page)
{
return NULL;
}
-static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg,
- bool *locked, unsigned long *flags)
+static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
{
}
@@ -364,7 +398,9 @@ static inline void sock_release_memcg(struct sock *sk)
#ifdef CONFIG_MEMCG_KMEM
extern struct static_key memcg_kmem_enabled_key;
-extern int memcg_limited_groups_array_size;
+extern int memcg_nr_cache_ids;
+extern void memcg_get_cache_ids(void);
+extern void memcg_put_cache_ids(void);
/*
* Helper macro to loop through all memcg-specific caches. Callers must still
@@ -372,13 +408,15 @@ extern int memcg_limited_groups_array_size;
* the slab_mutex must be held when looping through those caches
*/
#define for_each_memcg_cache_index(_idx) \
- for ((_idx) = 0; (_idx) < memcg_limited_groups_array_size; (_idx)++)
+ for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)
static inline bool memcg_kmem_enabled(void)
{
return static_key_false(&memcg_kmem_enabled_key);
}
+bool memcg_kmem_is_active(struct mem_cgroup *memcg);
+
/*
* In general, we'll do everything in our power to not incur in any overhead
* for non-memcg users for the kmem functions. Not even a function call, if we
@@ -398,15 +436,14 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order);
int memcg_cache_id(struct mem_cgroup *memcg);
-void memcg_update_array_size(int num_groups);
-
struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
void __memcg_kmem_put_cache(struct kmem_cache *cachep);
-int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order);
-void __memcg_uncharge_slab(struct kmem_cache *cachep, int order);
+struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr);
-int __memcg_cleanup_cache_params(struct kmem_cache *s);
+int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
+ unsigned long nr_pages);
+void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages);
/**
* memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
@@ -500,6 +537,13 @@ static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
if (memcg_kmem_enabled())
__memcg_kmem_put_cache(cachep);
}
+
+static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
+{
+ if (!memcg_kmem_enabled())
+ return NULL;
+ return __mem_cgroup_from_kmem(ptr);
+}
#else
#define for_each_memcg_cache_index(_idx) \
for (; NULL; )
@@ -509,6 +553,11 @@ static inline bool memcg_kmem_enabled(void)
return false;
}
+static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+ return false;
+}
+
static inline bool
memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
{
@@ -529,6 +578,14 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
return -1;
}
+static inline void memcg_get_cache_ids(void)
+{
+}
+
+static inline void memcg_put_cache_ids(void)
+{
+}
+
static inline struct kmem_cache *
memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
{
@@ -538,6 +595,11 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
{
}
+
+static inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
+{
+ return NULL;
+}
#endif /* CONFIG_MEMCG_KMEM */
#endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index fab9b32ace8e..78baed5f2952 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -67,7 +67,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
#ifdef CONFIG_NUMA_BALANCING
extern bool pmd_trans_migrating(pmd_t pmd);
-extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd);
extern int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node);
extern bool migrate_ratelimited(int node);
@@ -76,9 +75,6 @@ static inline bool pmd_trans_migrating(pmd_t pmd)
{
return false;
}
-static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
-{
-}
static inline int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node)
{
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 237b3ba29225..a2a348866719 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -138,7 +138,6 @@ extern unsigned int kobjsize(const void *objp);
#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */
#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */
#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
-#define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */
#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */
#define VM_ARCH_2 0x02000000
#define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */
@@ -206,21 +205,19 @@ extern unsigned int kobjsize(const void *objp);
extern pgprot_t protection_map[16];
#define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */
-#define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */
-#define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */
-#define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */
-#define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */
-#define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */
-#define FAULT_FLAG_TRIED 0x40 /* second try */
-#define FAULT_FLAG_USER 0x80 /* The fault originated in userspace */
+#define FAULT_FLAG_MKWRITE 0x02 /* Fault was mkwrite of existing pte */
+#define FAULT_FLAG_ALLOW_RETRY 0x04 /* Retry fault if blocking */
+#define FAULT_FLAG_RETRY_NOWAIT 0x08 /* Don't drop mmap_sem and wait when retrying */
+#define FAULT_FLAG_KILLABLE 0x10 /* The fault task is in SIGKILL killable region */
+#define FAULT_FLAG_TRIED 0x20 /* Second try */
+#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */
/*
* vm_fault is filled by the the pagefault handler and passed to the vma's
* ->fault function. The vma's ->fault is responsible for returning a bitmask
* of VM_FAULT_xxx flags that give details about how the fault was handled.
*
- * pgoff should be used in favour of virtual_address, if possible. If pgoff
- * is used, one may implement ->remap_pages to get nonlinear mapping support.
+ * pgoff should be used in favour of virtual_address, if possible.
*/
struct vm_fault {
unsigned int flags; /* FAULT_FLAG_xxx flags */
@@ -287,9 +284,6 @@ struct vm_operations_struct {
struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
unsigned long addr);
#endif
- /* called by sys_remap_file_pages() to populate non-linear mapping */
- int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr,
- unsigned long size, pgoff_t pgoff);
/*
* Called by vm_normal_page() for special PTEs to find the
@@ -454,6 +448,12 @@ static inline struct page *compound_head_by_tail(struct page *tail)
return tail;
}
+/*
+ * Since either compound page could be dismantled asynchronously in THP
+ * or we access asynchronously arbitrary positioned struct page, there
+ * would be tail flag race. To handle this race, we should call
+ * smp_rmb() before checking tail flag. compound_head_by_tail() did it.
+ */
static inline struct page *compound_head(struct page *page)
{
if (unlikely(PageTail(page)))
@@ -462,6 +462,18 @@ static inline struct page *compound_head(struct page *page)
}
/*
+ * If we access compound page synchronously such as access to
+ * allocated page, there is no need to handle tail flag race, so we can
+ * check tail flag directly without any synchronization primitive.
+ */
+static inline struct page *compound_head_fast(struct page *page)
+{
+ if (unlikely(PageTail(page)))
+ return page->first_page;
+ return page;
+}
+
+/*
* The atomic page->_mapcount, starts from -1: so that transitions
* both from it and to it can be tracked, using atomic_inc_and_test
* and atomic_add_negative(-1).
@@ -473,7 +485,8 @@ static inline void page_mapcount_reset(struct page *page)
static inline int page_mapcount(struct page *page)
{
- return atomic_read(&(page)->_mapcount) + 1;
+ VM_BUG_ON_PAGE(PageSlab(page), page);
+ return atomic_read(&page->_mapcount) + 1;
}
static inline int page_count(struct page *page)
@@ -539,7 +552,14 @@ static inline void get_page(struct page *page)
static inline struct page *virt_to_head_page(const void *x)
{
struct page *page = virt_to_page(x);
- return compound_head(page);
+
+ /*
+ * We don't need to worry about synchronization of tail flag
+ * when we call virt_to_head_page() since it is only called for
+ * already allocated page and this page won't be freed until
+ * this virt_to_head_page() is finished. So use _fast variant.
+ */
+ return compound_head_fast(page);
}
/*
@@ -609,29 +629,28 @@ int split_free_page(struct page *page);
* prototype for that function and accessor functions.
* These are _only_ valid on the head of a PG_compound page.
*/
-typedef void compound_page_dtor(struct page *);
static inline void set_compound_page_dtor(struct page *page,
compound_page_dtor *dtor)
{
- page[1].lru.next = (void *)dtor;
+ page[1].compound_dtor = dtor;
}
static inline compound_page_dtor *get_compound_page_dtor(struct page *page)
{
- return (compound_page_dtor *)page[1].lru.next;
+ return page[1].compound_dtor;
}
static inline int compound_order(struct page *page)
{
if (!PageHead(page))
return 0;
- return (unsigned long)page[1].lru.prev;
+ return page[1].compound_order;
}
static inline void set_compound_order(struct page *page, unsigned long order)
{
- page[1].lru.prev = (void *)order;
+ page[1].compound_order = order;
}
#ifdef CONFIG_MMU
@@ -1129,7 +1148,6 @@ extern void user_shm_unlock(size_t, struct user_struct *);
* Parameter block passed down to zap_pte_range in exceptional cases.
*/
struct zap_details {
- struct vm_area_struct *nonlinear_vma; /* Check page->index if set */
struct address_space *check_mapping; /* Check page->mapping if set */
pgoff_t first_index; /* Lowest page->index to unmap */
pgoff_t last_index; /* Highest page->index to unmap */
@@ -1147,8 +1165,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
/**
* mm_walk - callbacks for walk_page_range
- * @pgd_entry: if set, called for each non-empty PGD (top-level) entry
- * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
* @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
* this handler is required to be able to handle
* pmd_trans_huge() pmds. They may simply choose to
@@ -1156,16 +1172,18 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
* @pte_entry: if set, called for each non-empty PTE (4th-level) entry
* @pte_hole: if set, called for each hole at all levels
* @hugetlb_entry: if set, called for each hugetlb entry
- * *Caution*: The caller must hold mmap_sem() if @hugetlb_entry
- * is used.
+ * @test_walk: caller specific callback function to determine whether
+ * we walk over the current vma or not. A positive returned
+ * value means "do page table walk over the current vma,"
+ * and a negative one means "abort current page table walk
+ * right now." 0 means "skip the current vma."
+ * @mm: mm_struct representing the target process of page table walk
+ * @vma: vma currently walked (NULL if walking outside vmas)
+ * @private: private data for callbacks' usage
*
- * (see walk_page_range for more details)
+ * (see the comment on walk_page_range() for more details)
*/
struct mm_walk {
- int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
- unsigned long next, struct mm_walk *walk);
- int (*pud_entry)(pud_t *pud, unsigned long addr,
- unsigned long next, struct mm_walk *walk);
int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
unsigned long next, struct mm_walk *walk);
int (*pte_entry)(pte_t *pte, unsigned long addr,
@@ -1175,12 +1193,16 @@ struct mm_walk {
int (*hugetlb_entry)(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long next,
struct mm_walk *walk);
+ int (*test_walk)(unsigned long addr, unsigned long next,
+ struct mm_walk *walk);
struct mm_struct *mm;
+ struct vm_area_struct *vma;
void *private;
};
int walk_page_range(unsigned long addr, unsigned long end,
struct mm_walk *walk);
+int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk);
void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
unsigned long end, unsigned long floor, unsigned long ceiling);
int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
@@ -1244,6 +1266,17 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
int write, int force, struct page **pages,
struct vm_area_struct **vmas);
+long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages,
+ int *locked);
+long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages,
+ unsigned int gup_flags);
+long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages);
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
struct kvec;
@@ -1376,6 +1409,11 @@ static inline void update_hiwater_vm(struct mm_struct *mm)
mm->hiwater_vm = mm->total_vm;
}
+static inline void reset_mm_hiwater_rss(struct mm_struct *mm)
+{
+ mm->hiwater_rss = get_mm_rss(mm);
+}
+
static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
struct mm_struct *mm)
{
@@ -1421,8 +1459,32 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
{
return 0;
}
+
+static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline void mm_inc_nr_pmds(struct mm_struct *mm) {}
+static inline void mm_dec_nr_pmds(struct mm_struct *mm) {}
+
#else
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
+
+static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
+{
+ return atomic_long_read(&mm->nr_pmds);
+}
+
+static inline void mm_inc_nr_pmds(struct mm_struct *mm)
+{
+ atomic_long_inc(&mm->nr_pmds);
+}
+
+static inline void mm_dec_nr_pmds(struct mm_struct *mm)
+{
+ atomic_long_dec(&mm->nr_pmds);
+}
#endif
int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -1785,12 +1847,6 @@ struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node,
for (vma = vma_interval_tree_iter_first(root, start, last); \
vma; vma = vma_interval_tree_iter_next(vma, start, last))
-static inline void vma_nonlinear_insert(struct vm_area_struct *vma,
- struct list_head *list)
-{
- list_add_tail(&vma->shared.nonlinear, list);
-}
-
void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
struct rb_root *root);
void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
@@ -2118,9 +2174,8 @@ int drop_caches_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
#endif
-unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
- unsigned long nr_scanned,
- unsigned long nr_eligible);
+void drop_slab(void);
+void drop_slab_node(int nid);
#ifndef CONFIG_MMU
#define randomize_va_space 0
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6d34aa266a8c..199a03aab8dc 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -28,6 +28,8 @@ struct mem_cgroup;
IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8)
+typedef void compound_page_dtor(struct page *);
+
/*
* Each physical page in the system has a struct page associated with
* it to keep track of whatever it is we are using the page for at the
@@ -142,6 +144,12 @@ struct page {
struct rcu_head rcu_head; /* Used by SLAB
* when destroying via RCU
*/
+ /* First tail page of compound page */
+ struct {
+ compound_page_dtor *compound_dtor;
+ unsigned long compound_order;
+ };
+
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
pgtable_t pmd_huge_pte; /* protected by page->ptl */
#endif
@@ -273,15 +281,11 @@ struct vm_area_struct {
/*
* For areas with an address space and backing store,
- * linkage into the address_space->i_mmap interval tree, or
- * linkage of vma in the address_space->i_mmap_nonlinear list.
+ * linkage into the address_space->i_mmap interval tree.
*/
- union {
- struct {
- struct rb_node rb;
- unsigned long rb_subtree_last;
- } linear;
- struct list_head nonlinear;
+ struct {
+ struct rb_node rb;
+ unsigned long rb_subtree_last;
} shared;
/*
@@ -359,7 +363,8 @@ struct mm_struct {
pgd_t * pgd;
atomic_t mm_users; /* How many users with user space? */
atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */
- atomic_long_t nr_ptes; /* Page table pages */
+ atomic_long_t nr_ptes; /* PTE page table pages */
+ atomic_long_t nr_pmds; /* PMD page table pages */
int map_count; /* number of VMAs */
spinlock_t page_table_lock; /* Protects page tables and some counters */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 2f0856d14b21..f279d9c158cd 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -426,7 +426,7 @@ struct zone {
const char *name;
/*
- * Number of MIGRATE_RESEVE page block. To maintain for just
+ * Number of MIGRATE_RESERVE page block. To maintain for just
* optimization. Protected by zone->lock.
*/
int nr_migrate_reserve_block;
@@ -970,7 +970,6 @@ static inline int zonelist_node_idx(struct zoneref *zoneref)
* @z - The cursor used as a starting point for the search
* @highest_zoneidx - The zone index of the highest zone to return
* @nodes - An optional nodemask to filter the zonelist with
- * @zone - The first suitable zone found is returned via this parameter
*
* This function returns the next zone at or below a given zone index that is
* within the allowed nodemask using a cursor as the starting point for the
@@ -980,8 +979,7 @@ static inline int zonelist_node_idx(struct zoneref *zoneref)
*/
struct zoneref *next_zones_zonelist(struct zoneref *z,
enum zone_type highest_zoneidx,
- nodemask_t *nodes,
- struct zone **zone);
+ nodemask_t *nodes);
/**
* first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist
@@ -1000,8 +998,10 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
nodemask_t *nodes,
struct zone **zone)
{
- return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes,
- zone);
+ struct zoneref *z = next_zones_zonelist(zonelist->_zonerefs,
+ highest_zoneidx, nodes);
+ *zone = zonelist_zone(z);
+ return z;
}
/**
@@ -1018,7 +1018,8 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
#define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone); \
zone; \
- z = next_zones_zonelist(++z, highidx, nodemask, &zone)) \
+ z = next_zones_zonelist(++z, highidx, nodemask), \
+ zone = zonelist_zone(z)) \
/**
* for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 83a6aeda899d..6e85889cf9ab 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -8,14 +8,13 @@
* See detailed comments in the file linux/bitmap.h describing the
* data type on which these nodemasks are based.
*
- * For details of nodemask_scnprintf() and nodemask_parse_user(),
- * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c.
- * For details of nodelist_scnprintf() and nodelist_parse(), see
- * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c.
- * For details of node_remap(), see bitmap_bitremap in lib/bitmap.c.
- * For details of nodes_remap(), see bitmap_remap in lib/bitmap.c.
- * For details of nodes_onto(), see bitmap_onto in lib/bitmap.c.
- * For details of nodes_fold(), see bitmap_fold in lib/bitmap.c.
+ * For details of nodemask_parse_user(), see bitmap_parse_user() in
+ * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(),
+ * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in
+ * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in
+ * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in
+ * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in
+ * lib/bitmap.c.
*
* The available nodemask operations are:
*
@@ -52,9 +51,7 @@
* NODE_MASK_NONE Initializer - no bits set
* unsigned long *nodes_addr(mask) Array of unsigned long's in mask
*
- * int nodemask_scnprintf(buf, len, mask) Format nodemask for printing
* int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask
- * int nodelist_scnprintf(buf, len, mask) Format nodemask as list for printing
* int nodelist_parse(buf, map) Parse ascii string as nodelist
* int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit)
* void nodes_remap(dst, src, old, new) *dst = map(old, new)(src)
@@ -98,6 +95,14 @@
typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
extern nodemask_t _unused_nodemask_arg_;
+/**
+ * nodemask_pr_args - printf args to output a nodemask
+ * @maskp: nodemask to be printed
+ *
+ * Can be used to provide arguments for '%*pb[l]' when printing a nodemask.
+ */
+#define nodemask_pr_args(maskp) MAX_NUMNODES, (maskp)->bits
+
/*
* The inline keyword gives the compiler room to decide to inline, or
* not inline a function as it sees best. However, as these functions
@@ -120,13 +125,13 @@ static inline void __node_clear(int node, volatile nodemask_t *dstp)
}
#define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES)
-static inline void __nodes_setall(nodemask_t *dstp, int nbits)
+static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
{
bitmap_fill(dstp->bits, nbits);
}
#define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES)
-static inline void __nodes_clear(nodemask_t *dstp, int nbits)
+static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
{
bitmap_zero(dstp->bits, nbits);
}
@@ -144,7 +149,7 @@ static inline int __node_test_and_set(int node, nodemask_t *addr)
#define nodes_and(dst, src1, src2) \
__nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES)
static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
- const nodemask_t *src2p, int nbits)
+ const nodemask_t *src2p, unsigned int nbits)
{
bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
}
@@ -152,7 +157,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
#define nodes_or(dst, src1, src2) \
__nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES)
static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
- const nodemask_t *src2p, int nbits)
+ const nodemask_t *src2p, unsigned int nbits)
{
bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
}
@@ -160,7 +165,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
#define nodes_xor(dst, src1, src2) \
__nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES)
static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
- const nodemask_t *src2p, int nbits)
+ const nodemask_t *src2p, unsigned int nbits)
{
bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
}
@@ -168,7 +173,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
#define nodes_andnot(dst, src1, src2) \
__nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES)
static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
- const nodemask_t *src2p, int nbits)
+ const nodemask_t *src2p, unsigned int nbits)
{
bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
}
@@ -176,7 +181,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
#define nodes_complement(dst, src) \
__nodes_complement(&(dst), &(src), MAX_NUMNODES)
static inline void __nodes_complement(nodemask_t *dstp,
- const nodemask_t *srcp, int nbits)
+ const nodemask_t *srcp, unsigned int nbits)
{
bitmap_complement(dstp->bits, srcp->bits, nbits);
}
@@ -184,7 +189,7 @@ static inline void __nodes_complement(nodemask_t *dstp,
#define nodes_equal(src1, src2) \
__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
static inline int __nodes_equal(const nodemask_t *src1p,
- const nodemask_t *src2p, int nbits)
+ const nodemask_t *src2p, unsigned int nbits)
{
return bitmap_equal(src1p->bits, src2p->bits, nbits);
}
@@ -192,7 +197,7 @@ static inline int __nodes_equal(const nodemask_t *src1p,
#define nodes_intersects(src1, src2) \
__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
static inline int __nodes_intersects(const nodemask_t *src1p,
- const nodemask_t *src2p, int nbits)
+ const nodemask_t *src2p, unsigned int nbits)
{
return bitmap_intersects(src1p->bits, src2p->bits, nbits);
}
@@ -200,25 +205,25 @@ static inline int __nodes_intersects(const nodemask_t *src1p,
#define nodes_subset(src1, src2) \
__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
static inline int __nodes_subset(const nodemask_t *src1p,
- const nodemask_t *src2p, int nbits)
+ const nodemask_t *src2p, unsigned int nbits)
{
return bitmap_subset(src1p->bits, src2p->bits, nbits);
}
#define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
-static inline int __nodes_empty(const nodemask_t *srcp, int nbits)
+static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
{
return bitmap_empty(srcp->bits, nbits);
}
#define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_full(const nodemask_t *srcp, int nbits)
+static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits)
{
return bitmap_full(srcp->bits, nbits);
}
#define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_weight(const nodemask_t *srcp, int nbits)
+static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
{
return bitmap_weight(srcp->bits, nbits);
}
@@ -304,14 +309,6 @@ static inline int __first_unset_node(const nodemask_t *maskp)
#define nodes_addr(src) ((src).bits)
-#define nodemask_scnprintf(buf, len, src) \
- __nodemask_scnprintf((buf), (len), &(src), MAX_NUMNODES)
-static inline int __nodemask_scnprintf(char *buf, int len,
- const nodemask_t *srcp, int nbits)
-{
- return bitmap_scnprintf(buf, len, srcp->bits, nbits);
-}
-
#define nodemask_parse_user(ubuf, ulen, dst) \
__nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES)
static inline int __nodemask_parse_user(const char __user *buf, int len,
@@ -320,14 +317,6 @@ static inline int __nodemask_parse_user(const char __user *buf, int len,
return bitmap_parse_user(buf, len, dstp->bits, nbits);
}
-#define nodelist_scnprintf(buf, len, src) \
- __nodelist_scnprintf((buf), (len), &(src), MAX_NUMNODES)
-static inline int __nodelist_scnprintf(char *buf, int len,
- const nodemask_t *srcp, int nbits)
-{
- return bitmap_scnlistprintf(buf, len, srcp->bits, nbits);
-}
-
#define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES)
static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits)
{
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 76200984d1e2..d5771bed59c9 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -47,6 +47,10 @@ static inline bool oom_task_origin(const struct task_struct *p)
return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN);
}
+extern void mark_tsk_oom_victim(struct task_struct *tsk);
+
+extern void unmark_oom_victim(void);
+
extern unsigned long oom_badness(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask,
unsigned long totalpages);
@@ -68,22 +72,14 @@ extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
unsigned long totalpages, const nodemask_t *nodemask,
bool force_kill);
-extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
int order, nodemask_t *mask, bool force_kill);
extern int register_oom_notifier(struct notifier_block *nb);
extern int unregister_oom_notifier(struct notifier_block *nb);
extern bool oom_killer_disabled;
-
-static inline void oom_killer_disable(void)
-{
- oom_killer_disabled = true;
-}
-
-static inline void oom_killer_enable(void)
-{
- oom_killer_disabled = false;
-}
+extern bool oom_killer_disable(void);
+extern void oom_killer_enable(void);
extern struct task_struct *find_lock_task_mm(struct task_struct *p);
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index 955421575d16..17fa4f8de3a6 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -41,7 +41,8 @@ int page_counter_try_charge(struct page_counter *counter,
struct page_counter **fail);
void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
int page_counter_limit(struct page_counter *counter, unsigned long limit);
-int page_counter_memparse(const char *buf, unsigned long *nr_pages);
+int page_counter_memparse(const char *buf, const char *max,
+ unsigned long *nr_pages);
static inline void page_counter_reset_watermark(struct page_counter *counter)
{
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index d2a2c84c72d0..c42981cd99aa 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -40,7 +40,7 @@ struct page_ext {
#ifdef CONFIG_PAGE_OWNER
unsigned int order;
gfp_t gfp_mask;
- struct stack_trace trace;
+ unsigned int nr_entries;
unsigned long trace_entries[8];
#endif
};
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 4d5bf5726578..baa3f97d8ce8 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -417,9 +417,9 @@ enum {
DUMP_PREFIX_ADDRESS,
DUMP_PREFIX_OFFSET
};
-extern void hex_dump_to_buffer(const void *buf, size_t len,
- int rowsize, int groupsize,
- char *linebuf, size_t linebuflen, bool ascii);
+extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
+ int groupsize, char *linebuf, size_t linebuflen,
+ bool ascii);
#ifdef CONFIG_PRINTK
extern void print_hex_dump(const char *level, const char *prefix_str,
int prefix_type, int rowsize, int groupsize,
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 57e75ae9910f..fb31765e935a 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -51,7 +51,7 @@ struct rb_root {
#define RB_EMPTY_ROOT(root) ((root)->rb_node == NULL)
-/* 'empty' nodes are nodes that are known not to be inserted in an rbree */
+/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
#define RB_EMPTY_NODE(node) \
((node)->__rb_parent_color == (unsigned long)(node))
#define RB_CLEAR_NODE(node) \
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index d9d7e7e56352..dbcd5ec3f291 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -85,6 +85,7 @@ enum ttu_flags {
TTU_UNMAP = 1, /* unmap mode */
TTU_MIGRATION = 2, /* migration mode */
TTU_MUNLOCK = 4, /* munlock mode */
+ TTU_FREE = 8, /* free mode */
TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */
TTU_IGNORE_ACCESS = (1 << 9), /* don't age */
@@ -191,7 +192,8 @@ static inline void page_dup_rmap(struct page *page)
* Called from mm/vmscan.c to handle paging out
*/
int page_referenced(struct page *, int is_locked,
- struct mem_cgroup *memcg, unsigned long *vm_flags);
+ struct mem_cgroup *memcg, unsigned long *vm_flags,
+ int *is_pte_dirty);
#define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
@@ -246,7 +248,6 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
* arg: passed to rmap_one() and invalid_vma()
* rmap_one: executed on each vma where page is mapped
* done: for checking traversing termination condition
- * file_nonlinear: for handling file nonlinear mapping
* anon_lock: for getting anon_lock by optimized way rather than default
* invalid_vma: for skipping uninterested vma
*/
@@ -255,7 +256,6 @@ struct rmap_walk_control {
int (*rmap_one)(struct page *page, struct vm_area_struct *vma,
unsigned long addr, void *arg);
int (*done)(struct page *page);
- int (*file_nonlinear)(struct page *, struct address_space *, void *arg);
struct anon_vma *(*anon_lock)(struct page *page);
bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
};
@@ -270,9 +270,12 @@ int rmap_walk(struct page *page, struct rmap_walk_control *rwc);
static inline int page_referenced(struct page *page, int is_locked,
struct mem_cgroup *memcg,
- unsigned long *vm_flags)
+ unsigned long *vm_flags,
+ int *is_pte_dirty)
{
*vm_flags = 0;
+ if (is_pte_dirty)
+ *is_pte_dirty = 0;
return 0;
}
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index dcad7ee0d746..38e0b4d1591a 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -133,6 +133,10 @@ struct rtc_device
/* Some hardware can't support UIE mode */
int uie_unsupported;
+#ifdef CONFIG_PM_SLEEP
+ struct rtc_wkalrm alarm;
+ bool valid_alarm;
+#endif
#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
struct work_struct uie_task;
struct timer_list uie_timer;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8db31ef98d2f..22ee0d5d7f8c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1370,6 +1370,8 @@ struct task_struct {
unsigned long atomic_flags; /* Flags needing atomic access. */
+ struct restart_block restart_block;
+
pid_t pid;
pid_t tgid;
diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 9aafe0e24c68..fb7eb9ccb1cd 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -125,9 +125,6 @@ extern int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
unsigned int len);
extern int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc);
-extern int seq_buf_bitmask(struct seq_buf *s, const unsigned long *maskp,
- int nmaskbits);
-
#ifdef CONFIG_BINARY_PRINTF
extern int
seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary);
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index cf6a9daaaf6d..afbb1fd77c77 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -126,31 +126,6 @@ int seq_path(struct seq_file *, const struct path *, const char *);
int seq_dentry(struct seq_file *, struct dentry *, const char *);
int seq_path_root(struct seq_file *m, const struct path *path,
const struct path *root, const char *esc);
-int seq_bitmap(struct seq_file *m, const unsigned long *bits,
- unsigned int nr_bits);
-static inline int seq_cpumask(struct seq_file *m, const struct cpumask *mask)
-{
- return seq_bitmap(m, cpumask_bits(mask), nr_cpu_ids);
-}
-
-static inline int seq_nodemask(struct seq_file *m, nodemask_t *mask)
-{
- return seq_bitmap(m, mask->bits, MAX_NUMNODES);
-}
-
-int seq_bitmap_list(struct seq_file *m, const unsigned long *bits,
- unsigned int nr_bits);
-
-static inline int seq_cpumask_list(struct seq_file *m,
- const struct cpumask *mask)
-{
- return seq_bitmap_list(m, cpumask_bits(mask), nr_cpu_ids);
-}
-
-static inline int seq_nodemask_list(struct seq_file *m, nodemask_t *mask)
-{
- return seq_bitmap_list(m, mask->bits, MAX_NUMNODES);
-}
int single_open(struct file *, int (*)(struct seq_file *, void *), void *);
int single_open_size(struct file *, int (*)(struct seq_file *, void *), void *, size_t);
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index f4aee75f00b1..4fcacd915d45 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -20,6 +20,9 @@ struct shrink_control {
/* current node being shrunk (for NUMA aware shrinkers) */
int nid;
+
+ /* current memcg being shrunk (for memcg aware shrinkers) */
+ struct mem_cgroup *memcg;
};
#define SHRINK_STOP (~0UL)
@@ -61,7 +64,8 @@ struct shrinker {
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
/* Flags */
-#define SHRINKER_NUMA_AWARE (1 << 0)
+#define SHRINKER_NUMA_AWARE (1 << 0)
+#define SHRINKER_MEMCG_AWARE (1 << 1)
extern int register_shrinker(struct shrinker *);
extern void unregister_shrinker(struct shrinker *);
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9a139b637069..ed2ffaab59ea 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -115,14 +115,12 @@ int slab_is_available(void);
struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
unsigned long,
void (*)(void *));
-#ifdef CONFIG_MEMCG_KMEM
-struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *,
- struct kmem_cache *,
- const char *);
-#endif
void kmem_cache_destroy(struct kmem_cache *);
int kmem_cache_shrink(struct kmem_cache *);
-void kmem_cache_free(struct kmem_cache *, void *);
+
+void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
+void memcg_deactivate_kmem_caches(struct mem_cgroup *);
+void memcg_destroy_kmem_caches(struct mem_cgroup *);
/*
* Please use this macro to create slab caches. Simply specify the
@@ -289,6 +287,7 @@ static __always_inline int kmalloc_index(size_t size)
void *__kmalloc(size_t size, gfp_t flags);
void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags);
+void kmem_cache_free(struct kmem_cache *, void *);
#ifdef CONFIG_NUMA
void *__kmalloc_node(size_t size, gfp_t flags, int node);
@@ -474,14 +473,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
#ifndef ARCH_SLAB_MINALIGN
#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
#endif
+
+struct memcg_cache_array {
+ struct rcu_head rcu;
+ struct kmem_cache *entries[0];
+};
+
/*
* This is the main placeholder for memcg-related information in kmem caches.
- * struct kmem_cache will hold a pointer to it, so the memory cost while
- * disabled is 1 pointer. The runtime cost while enabled, gets bigger than it
- * would otherwise be if that would be bundled in kmem_cache: we'll need an
- * extra pointer chase. But the trade off clearly lays in favor of not
- * penalizing non-users.
- *
* Both the root cache and the child caches will have it. For the root cache,
* this will hold a dynamically allocated array large enough to hold
* information about the currently limited memcgs in the system. To allow the
@@ -491,19 +490,18 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
* Child caches will hold extra metadata needed for its operation. Fields are:
*
* @memcg: pointer to the memcg this cache belongs to
- * @list: list_head for the list of all caches in this memcg
* @root_cache: pointer to the global, root cache, this cache was derived from
+ *
+ * Both root and child caches of the same kind are linked into a list chained
+ * through @list.
*/
struct memcg_cache_params {
bool is_root_cache;
+ struct list_head list;
union {
- struct {
- struct rcu_head rcu_head;
- struct kmem_cache *memcg_caches[0];
- };
+ struct memcg_cache_array __rcu *memcg_caches;
struct {
struct mem_cgroup *memcg;
- struct list_head list;
struct kmem_cache *root_cache;
};
};
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index b869d1662ba3..33d049066c3d 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -70,7 +70,7 @@ struct kmem_cache {
int obj_offset;
#endif /* CONFIG_DEBUG_SLAB */
#ifdef CONFIG_MEMCG_KMEM
- struct memcg_cache_params *memcg_params;
+ struct memcg_cache_params memcg_params;
#endif
struct kmem_cache_node *node[MAX_NUMNODES];
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index d82abd40a3c0..9abf04ed0999 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -85,7 +85,7 @@ struct kmem_cache {
struct kobject kobj; /* For sysfs */
#endif
#ifdef CONFIG_MEMCG_KMEM
- struct memcg_cache_params *memcg_params;
+ struct memcg_cache_params memcg_params;
int max_attr_size; /* for propagation, maximum size of a stored attr */
#ifdef CONFIG_SYSFS
struct kset *memcg_kset;
diff --git a/include/linux/string.h b/include/linux/string.h
index 2e22a2e58f3a..12a5a60f1f3b 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -40,9 +40,6 @@ extern int strcmp(const char *,const char *);
#ifndef __HAVE_ARCH_STRNCMP
extern int strncmp(const char *,const char *,__kernel_size_t);
#endif
-#ifndef __HAVE_ARCH_STRNICMP
-#define strnicmp strncasecmp
-#endif
#ifndef __HAVE_ARCH_STRCASECMP
extern int strcasecmp(const char *s1, const char *s2);
#endif
@@ -115,8 +112,12 @@ extern void * memchr(const void *,int,__kernel_size_t);
#endif
void *memchr_inv(const void *s, int c, size_t n);
+extern void kfree_const(const void *x);
+
extern char *kstrdup(const char *s, gfp_t gfp);
+extern const char *kstrdup_const(const char *s, gfp_t gfp);
extern char *kstrndup(const char *s, size_t len, gfp_t gfp);
+extern char *kstrimdup(const char *s, gfp_t gfp);
extern void *kmemdup(const void *src, size_t len, gfp_t gfp);
extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index 6eb567ac56bc..657571817260 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -10,8 +10,8 @@ enum string_size_units {
STRING_UNITS_2, /* use binary powers of 2^10 */
};
-int string_get_size(u64 size, enum string_size_units units,
- char *buf, int len);
+void string_get_size(u64 size, enum string_size_units units,
+ char *buf, int len);
#define UNESCAPE_SPACE 0x01
#define UNESCAPE_OCTAL 0x02
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 34e8b60ab973..7067eca501e2 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -437,16 +437,6 @@ extern int reuse_swap_page(struct page *);
extern int try_to_free_swap(struct page *);
struct backing_dev_info;
-#ifdef CONFIG_MEMCG
-extern void
-mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout);
-#else
-static inline void
-mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
-{
-}
-#endif
-
#else /* CONFIG_SWAP */
#define swap_address_space(entry) (NULL)
@@ -547,11 +537,6 @@ static inline swp_entry_t get_swap_page(void)
return entry;
}
-static inline void
-mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
-{
-}
-
#endif /* CONFIG_SWAP */
#endif /* __KERNEL__*/
#endif /* _LINUX_SWAP_H */
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 6adfb7bfbf44..cedf3d3c373f 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -54,7 +54,7 @@ static inline pgoff_t swp_offset(swp_entry_t entry)
/* check whether a pte points to a swap entry */
static inline int is_swap_pte(pte_t pte)
{
- return !pte_none(pte) && !pte_present_nonuma(pte) && !pte_file(pte);
+ return !pte_none(pte) && !pte_present(pte);
}
#endif
@@ -66,7 +66,6 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte)
{
swp_entry_t arch_entry;
- BUG_ON(pte_file(pte));
if (pte_swp_soft_dirty(pte))
pte = pte_swp_clear_soft_dirty(pte);
arch_entry = __pte_to_swp_entry(pte);
@@ -82,7 +81,6 @@ static inline pte_t swp_entry_to_pte(swp_entry_t entry)
swp_entry_t arch_entry;
arch_entry = __swp_entry(swp_type(entry), swp_offset(entry));
- BUG_ON(pte_file(__swp_entry_to_pte(arch_entry)));
return __swp_entry_to_pte(arch_entry);
}
@@ -137,6 +135,8 @@ static inline void make_migration_entry_read(swp_entry_t *entry)
*entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry));
}
+extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+ spinlock_t *ptl);
extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
unsigned long address);
extern void migration_entry_wait_huge(struct vm_area_struct *vma,
@@ -150,6 +150,8 @@ static inline int is_migration_entry(swp_entry_t swp)
}
#define migration_entry_to_page(swp) NULL
static inline void make_migration_entry_read(swp_entry_t *entryp) { }
+static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+ spinlock_t *ptl) { }
static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
unsigned long address) { }
static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
diff --git a/include/linux/types.h b/include/linux/types.h
index 62323825cff9..6747247e3f9f 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -135,12 +135,9 @@ typedef unsigned long blkcnt_t;
#endif
/*
- * The type of an index into the pagecache. Use a #define so asm/types.h
- * can override it.
+ * The type of an index into the pagecache.
*/
-#ifndef pgoff_t
#define pgoff_t unsigned long
-#endif
/* A dma_addr_t can hold any valid DMA or bus address for the platform */
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 9246d32dc973..2b1cef88b827 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
FOR_ALL_ZONES(PGALLOC),
PGFREE, PGACTIVATE, PGDEACTIVATE,
PGFAULT, PGMAJFAULT,
+ PGLAZYFREED,
FOR_ALL_ZONES(PGREFILL),
FOR_ALL_ZONES(PGSTEAL_KSWAPD),
FOR_ALL_ZONES(PGSTEAL_DIRECT),
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
index f14bd75f08b3..56529b34dc63 100644
--- a/include/linux/zpool.h
+++ b/include/linux/zpool.h
@@ -36,7 +36,8 @@ enum zpool_mapmode {
ZPOOL_MM_DEFAULT = ZPOOL_MM_RW
};
-struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops);
+struct zpool *zpool_create_pool(char *type, char *name,
+ gfp_t gfp, struct zpool_ops *ops);
char *zpool_get_type(struct zpool *pool);
@@ -80,7 +81,7 @@ struct zpool_driver {
atomic_t refcount;
struct list_head list;
- void *(*create)(gfp_t gfp, struct zpool_ops *ops);
+ void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops);
void (*destroy)(void *pool);
int (*malloc)(void *pool, size_t size, gfp_t gfp,
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 05c214760977..3283c6a55425 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -36,7 +36,7 @@ enum zs_mapmode {
struct zs_pool;
-struct zs_pool *zs_create_pool(gfp_t flags);
+struct zs_pool *zs_create_pool(char *name, gfp_t flags);
void zs_destroy_pool(struct zs_pool *pool);
unsigned long zs_malloc(struct zs_pool *pool, size_t size);
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index c6814b917bdf..9a6a3fe0fb51 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -11,39 +11,55 @@
DECLARE_EVENT_CLASS(mm_compaction_isolate_template,
- TP_PROTO(unsigned long nr_scanned,
+ TP_PROTO(
+ unsigned long start_pfn,
+ unsigned long end_pfn,
+ unsigned long nr_scanned,
unsigned long nr_taken),
- TP_ARGS(nr_scanned, nr_taken),
+ TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken),
TP_STRUCT__entry(
+ __field(unsigned long, start_pfn)
+ __field(unsigned long, end_pfn)
__field(unsigned long, nr_scanned)
__field(unsigned long, nr_taken)
),
TP_fast_assign(
+ __entry->start_pfn = start_pfn;
+ __entry->end_pfn = end_pfn;
__entry->nr_scanned = nr_scanned;
__entry->nr_taken = nr_taken;
),
- TP_printk("nr_scanned=%lu nr_taken=%lu",
+ TP_printk("range=(0x%lx ~ 0x%lx) nr_scanned=%lu nr_taken=%lu",
+ __entry->start_pfn,
+ __entry->end_pfn,
__entry->nr_scanned,
__entry->nr_taken)
);
DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_migratepages,
- TP_PROTO(unsigned long nr_scanned,
+ TP_PROTO(
+ unsigned long start_pfn,
+ unsigned long end_pfn,
+ unsigned long nr_scanned,
unsigned long nr_taken),
- TP_ARGS(nr_scanned, nr_taken)
+ TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken)
);
DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages,
- TP_PROTO(unsigned long nr_scanned,
+
+ TP_PROTO(
+ unsigned long start_pfn,
+ unsigned long end_pfn,
+ unsigned long nr_scanned,
unsigned long nr_taken),
- TP_ARGS(nr_scanned, nr_taken)
+ TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken)
);
TRACE_EVENT(mm_compaction_migratepages,
@@ -85,47 +101,198 @@ TRACE_EVENT(mm_compaction_migratepages,
);
TRACE_EVENT(mm_compaction_begin,
- TP_PROTO(unsigned long zone_start, unsigned long migrate_start,
- unsigned long free_start, unsigned long zone_end),
+ TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn,
+ unsigned long free_pfn, unsigned long zone_end, bool sync),
- TP_ARGS(zone_start, migrate_start, free_start, zone_end),
+ TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync),
TP_STRUCT__entry(
__field(unsigned long, zone_start)
- __field(unsigned long, migrate_start)
- __field(unsigned long, free_start)
+ __field(unsigned long, migrate_pfn)
+ __field(unsigned long, free_pfn)
__field(unsigned long, zone_end)
+ __field(bool, sync)
),
TP_fast_assign(
__entry->zone_start = zone_start;
- __entry->migrate_start = migrate_start;
- __entry->free_start = free_start;
+ __entry->migrate_pfn = migrate_pfn;
+ __entry->free_pfn = free_pfn;
__entry->zone_end = zone_end;
+ __entry->sync = sync;
),
- TP_printk("zone_start=%lu migrate_start=%lu free_start=%lu zone_end=%lu",
+ TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s",
__entry->zone_start,
- __entry->migrate_start,
- __entry->free_start,
- __entry->zone_end)
+ __entry->migrate_pfn,
+ __entry->free_pfn,
+ __entry->zone_end,
+ __entry->sync ? "sync" : "async")
);
TRACE_EVENT(mm_compaction_end,
- TP_PROTO(int status),
+ TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn,
+ unsigned long free_pfn, unsigned long zone_end, bool sync,
+ int status),
- TP_ARGS(status),
+ TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync, status),
TP_STRUCT__entry(
+ __field(unsigned long, zone_start)
+ __field(unsigned long, migrate_pfn)
+ __field(unsigned long, free_pfn)
+ __field(unsigned long, zone_end)
+ __field(bool, sync)
__field(int, status)
),
TP_fast_assign(
+ __entry->zone_start = zone_start;
+ __entry->migrate_pfn = migrate_pfn;
+ __entry->free_pfn = free_pfn;
+ __entry->zone_end = zone_end;
+ __entry->sync = sync;
__entry->status = status;
),
- TP_printk("status=%d", __entry->status)
+ TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s status=%s",
+ __entry->zone_start,
+ __entry->migrate_pfn,
+ __entry->free_pfn,
+ __entry->zone_end,
+ __entry->sync ? "sync" : "async",
+ compaction_status_string[__entry->status])
+);
+
+TRACE_EVENT(mm_compaction_try_to_compact_pages,
+
+ TP_PROTO(
+ int order,
+ gfp_t gfp_mask,
+ enum migrate_mode mode),
+
+ TP_ARGS(order, gfp_mask, mode),
+
+ TP_STRUCT__entry(
+ __field(int, order)
+ __field(gfp_t, gfp_mask)
+ __field(enum migrate_mode, mode)
+ ),
+
+ TP_fast_assign(
+ __entry->order = order;
+ __entry->gfp_mask = gfp_mask;
+ __entry->mode = mode;
+ ),
+
+ TP_printk("order=%d gfp_mask=0x%x mode=%d",
+ __entry->order,
+ __entry->gfp_mask,
+ (int)__entry->mode)
+);
+
+DECLARE_EVENT_CLASS(mm_compaction_suitable_template,
+
+ TP_PROTO(struct zone *zone,
+ int order,
+ int ret),
+
+ TP_ARGS(zone, order, ret),
+
+ TP_STRUCT__entry(
+ __field(int, nid)
+ __field(char *, name)
+ __field(int, order)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->nid = zone_to_nid(zone);
+ __entry->name = (char *)zone->name;
+ __entry->order = order;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("node=%d zone=%-8s order=%d ret=%s",
+ __entry->nid,
+ __entry->name,
+ __entry->order,
+ compaction_status_string[__entry->ret])
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_finished,
+
+ TP_PROTO(struct zone *zone,
+ int order,
+ int ret),
+
+ TP_ARGS(zone, order, ret)
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable,
+
+ TP_PROTO(struct zone *zone,
+ int order,
+ int ret),
+
+ TP_ARGS(zone, order, ret)
+);
+
+#ifdef CONFIG_COMPACTION
+DECLARE_EVENT_CLASS(mm_compaction_defer_template,
+
+ TP_PROTO(struct zone *zone, int order),
+
+ TP_ARGS(zone, order),
+
+ TP_STRUCT__entry(
+ __field(int, nid)
+ __field(char *, name)
+ __field(int, order)
+ __field(unsigned int, considered)
+ __field(unsigned int, defer_shift)
+ __field(int, order_failed)
+ ),
+
+ TP_fast_assign(
+ __entry->nid = zone_to_nid(zone);
+ __entry->name = (char *)zone->name;
+ __entry->order = order;
+ __entry->considered = zone->compact_considered;
+ __entry->defer_shift = zone->compact_defer_shift;
+ __entry->order_failed = zone->compact_order_failed;
+ ),
+
+ TP_printk("node=%d zone=%-8s order=%d order_failed=%d consider=%u limit=%lu",
+ __entry->nid,
+ __entry->name,
+ __entry->order,
+ __entry->order_failed,
+ __entry->considered,
+ 1UL << __entry->defer_shift)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_deferred,
+
+ TP_PROTO(struct zone *zone, int order),
+
+ TP_ARGS(zone, order)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_compaction,
+
+ TP_PROTO(struct zone *zone, int order),
+
+ TP_ARGS(zone, order)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_reset,
+
+ TP_PROTO(struct zone *zone, int order),
+
+ TP_ARGS(zone, order)
);
+#endif
#endif /* _TRACE_COMPACTION_H */
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index aece1346ceb7..4ad10baecd4d 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -268,11 +268,11 @@ TRACE_EVENT(mm_page_alloc_extfrag,
TP_PROTO(struct page *page,
int alloc_order, int fallback_order,
- int alloc_migratetype, int fallback_migratetype, int new_migratetype),
+ int alloc_migratetype, int fallback_migratetype),
TP_ARGS(page,
alloc_order, fallback_order,
- alloc_migratetype, fallback_migratetype, new_migratetype),
+ alloc_migratetype, fallback_migratetype),
TP_STRUCT__entry(
__field( struct page *, page )
@@ -289,7 +289,8 @@ TRACE_EVENT(mm_page_alloc_extfrag,
__entry->fallback_order = fallback_order;
__entry->alloc_migratetype = alloc_migratetype;
__entry->fallback_migratetype = fallback_migratetype;
- __entry->change_ownership = (new_migratetype == alloc_migratetype);
+ __entry->change_ownership = (alloc_migratetype ==
+ get_pageblock_migratetype(page));
),
TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index ddc3b36f1046..7a94102b7a02 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -34,6 +34,7 @@
#define MADV_SEQUENTIAL 2 /* expect sequential page references */
#define MADV_WILLNEED 3 /* will need these pages */
#define MADV_DONTNEED 4 /* don't need these pages */
+#define MADV_FREE 5 /* free pages only if memory pressure */
/* common parameters: try to keep these consistent across architectures */
#define MADV_REMOVE 9 /* remove these pages & resources */
diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h
index 2f96d233c980..a6c4962e5d46 100644
--- a/include/uapi/linux/kernel-page-flags.h
+++ b/include/uapi/linux/kernel-page-flags.h
@@ -32,6 +32,7 @@
#define KPF_KSM 21
#define KPF_THP 22
#define KPF_BALLOON 23
+#define KPF_ZERO_PAGE 24
#endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h
index 6925f5b42f89..99048e501b88 100644
--- a/include/uapi/linux/kexec.h
+++ b/include/uapi/linux/kexec.h
@@ -55,12 +55,6 @@ struct kexec_segment {
size_t memsz;
};
-/* Load a new kernel image as described by the kexec_segment array
- * consisting of passed number of segments at the entry-point address.
- * The flags allow different useage types.
- */
-extern int kexec_load(void *, size_t, struct kexec_segment *,
- unsigned long int);
#endif /* __KERNEL__ */
#endif /* _UAPILINUX_KEXEC_H */
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 0d11c3dcd3a1..9cd8b21dddbe 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -67,7 +67,7 @@ enum mpol_rebind_step {
#define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */
#define MPOL_F_REBINDING (1 << 2) /* identify policies in rebinding */
#define MPOL_F_MOF (1 << 3) /* this policy wants migrate on fault */
-#define MPOL_F_MORON (1 << 4) /* Migrate On pte_numa Reference On Node */
+#define MPOL_F_MORON (1 << 4) /* Migrate On protnone Reference On Node */
#endif /* _UAPI_LINUX_MEMPOLICY_H */