summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/backing-dev.c43
-rw-r--r--mm/gup.c46
-rw-r--r--mm/huge_memory.c9
-rw-r--r--mm/hugetlb.c29
-rw-r--r--mm/kasan/kasan_init.c44
-rw-r--r--mm/kasan/quarantine.c51
-rw-r--r--mm/madvise.c44
-rw-r--r--mm/memblock.c5
-rw-r--r--mm/memcontrol.c18
-rw-r--r--mm/memory.c230
-rw-r--r--mm/mlock.c10
-rw-r--r--mm/mprotect.c26
-rw-r--r--mm/mremap.c13
-rw-r--r--mm/page_alloc.c3
-rw-r--r--mm/page_vma_mapped.c6
-rw-r--r--mm/pagewalk.c32
-rw-r--r--mm/pgtable-generic.c6
-rw-r--r--mm/rmap.c20
-rw-r--r--mm/sparse-vmemmap.c22
-rw-r--r--mm/swapfile.c26
-rw-r--r--mm/userfaultfd.c23
-rw-r--r--mm/vmalloc.c81
-rw-r--r--mm/vmstat.c3
23 files changed, 642 insertions, 148 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 6d861d090e9f..c6f2a37028c2 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -683,33 +683,26 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
{
struct radix_tree_iter iter;
- struct rb_node *rbn;
void **slot;
WARN_ON(test_bit(WB_registered, &bdi->wb.state));
spin_lock_irq(&cgwb_lock);
-
radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
cgwb_kill(*slot);
-
- while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
- struct bdi_writeback_congested *congested =
- rb_entry(rbn, struct bdi_writeback_congested, rb_node);
-
- rb_erase(rbn, &bdi->cgwb_congested_tree);
- congested->bdi = NULL; /* mark @congested unlinked */
- }
-
spin_unlock_irq(&cgwb_lock);
/*
- * All cgwb's and their congested states must be shutdown and
- * released before returning. Drain the usage counter to wait for
- * all cgwb's and cgwb_congested's ever created on @bdi.
+ * All cgwb's must be shutdown and released before returning. Drain
+ * the usage counter to wait for all cgwb's ever created on @bdi.
*/
atomic_dec(&bdi->usage_cnt);
wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt));
+ /*
+ * Grab back our reference so that we hold it when @bdi gets
+ * re-registered.
+ */
+ atomic_inc(&bdi->usage_cnt);
}
/**
@@ -749,6 +742,21 @@ void wb_blkcg_offline(struct blkcg *blkcg)
spin_unlock_irq(&cgwb_lock);
}
+static void cgwb_bdi_exit(struct backing_dev_info *bdi)
+{
+ struct rb_node *rbn;
+
+ spin_lock_irq(&cgwb_lock);
+ while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
+ struct bdi_writeback_congested *congested =
+ rb_entry(rbn, struct bdi_writeback_congested, rb_node);
+
+ rb_erase(rbn, &bdi->cgwb_congested_tree);
+ congested->bdi = NULL; /* mark @congested unlinked */
+ }
+ spin_unlock_irq(&cgwb_lock);
+}
+
#else /* CONFIG_CGROUP_WRITEBACK */
static int cgwb_bdi_init(struct backing_dev_info *bdi)
@@ -769,7 +777,9 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
return 0;
}
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
+static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
+
+static void cgwb_bdi_exit(struct backing_dev_info *bdi)
{
wb_congested_put(bdi->wb_congested);
}
@@ -857,6 +867,8 @@ int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner)
MINOR(owner->devt));
if (rc)
return rc;
+ /* Leaking owner reference... */
+ WARN_ON(bdi->owner);
bdi->owner = owner;
get_device(owner);
return 0;
@@ -898,6 +910,7 @@ static void bdi_exit(struct backing_dev_info *bdi)
{
WARN_ON_ONCE(bdi->dev);
wb_exit(&bdi->wb);
+ cgwb_bdi_exit(bdi);
}
static void release_bdi(struct kref *ref)
diff --git a/mm/gup.c b/mm/gup.c
index 9c047e951aa3..04aa405350dc 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -226,6 +226,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned int *page_mask)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
spinlock_t *ptl;
@@ -243,8 +244,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
return no_page_table(vma, flags);
-
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ if (p4d_none(*p4d))
+ return no_page_table(vma, flags);
+ BUILD_BUG_ON(p4d_huge(*p4d));
+ if (unlikely(p4d_bad(*p4d)))
+ return no_page_table(vma, flags);
+ pud = pud_offset(p4d, address);
if (pud_none(*pud))
return no_page_table(vma, flags);
if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
@@ -325,6 +331,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
struct page **page)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
@@ -338,7 +345,9 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
else
pgd = pgd_offset_gate(mm, address);
BUG_ON(pgd_none(*pgd));
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ BUG_ON(p4d_none(*p4d));
+ pud = pud_offset(p4d, address);
BUG_ON(pud_none(*pud));
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd))
@@ -1400,13 +1409,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
return 1;
}
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
- pudp = pud_offset(&pgd, addr);
+ pudp = pud_offset(&p4d, addr);
do {
pud_t pud = READ_ONCE(*pudp);
@@ -1428,6 +1437,31 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
return 1;
}
+static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
+ int write, struct page **pages, int *nr)
+{
+ unsigned long next;
+ p4d_t *p4dp;
+
+ p4dp = p4d_offset(&pgd, addr);
+ do {
+ p4d_t p4d = READ_ONCE(*p4dp);
+
+ next = p4d_addr_end(addr, end);
+ if (p4d_none(p4d))
+ return 0;
+ BUILD_BUG_ON(p4d_huge(p4d));
+ if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
+ if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
+ P4D_SHIFT, next, write, pages, nr))
+ return 0;
+ } else if (!gup_pud_range(p4d, addr, next, write, pages, nr))
+ return 0;
+ } while (p4dp++, addr = next, addr != end);
+
+ return 1;
+}
+
/*
* Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
* the regular GUP. It will only return non-negative values.
@@ -1478,7 +1512,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
PGDIR_SHIFT, next, write, pages, &nr))
break;
- } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ } else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
break;
} while (pgdp++, addr = next, addr != end);
local_irq_restore(flags);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d36b2af4d1bf..1ebc93e179f3 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1828,7 +1828,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
- count_vm_event(THP_SPLIT_PMD);
+ count_vm_event(THP_SPLIT_PUD);
pudp_huge_clear_flush_notify(vma, haddr, pud);
}
@@ -2048,6 +2048,7 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
bool freeze, struct page *page)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
@@ -2055,7 +2056,11 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
if (!pgd_present(*pgd))
return;
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ if (!p4d_present(*p4d))
+ return;
+
+ pud = pud_offset(p4d, address);
if (!pud_present(*pud))
return;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a7aa811b7d14..3d0aab9ee80d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4555,7 +4555,8 @@ out:
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
{
pgd_t *pgd = pgd_offset(mm, *addr);
- pud_t *pud = pud_offset(pgd, *addr);
+ p4d_t *p4d = p4d_offset(pgd, *addr);
+ pud_t *pud = pud_offset(p4d, *addr);
BUG_ON(page_count(virt_to_page(ptep)) == 0);
if (page_count(virt_to_page(ptep)) == 1)
@@ -4586,11 +4587,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pte_t *pte = NULL;
pgd = pgd_offset(mm, addr);
- pud = pud_alloc(mm, pgd, addr);
+ p4d = p4d_offset(pgd, addr);
+ pud = pud_alloc(mm, p4d, addr);
if (pud) {
if (sz == PUD_SIZE) {
pte = (pte_t *)pud;
@@ -4610,18 +4613,22 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
- pmd_t *pmd = NULL;
+ pmd_t *pmd;
pgd = pgd_offset(mm, addr);
- if (pgd_present(*pgd)) {
- pud = pud_offset(pgd, addr);
- if (pud_present(*pud)) {
- if (pud_huge(*pud))
- return (pte_t *)pud;
- pmd = pmd_offset(pud, addr);
- }
- }
+ if (!pgd_present(*pgd))
+ return NULL;
+ p4d = p4d_offset(pgd, addr);
+ if (!p4d_present(*p4d))
+ return NULL;
+ pud = pud_offset(p4d, addr);
+ if (!pud_present(*pud))
+ return NULL;
+ if (pud_huge(*pud))
+ return (pte_t *)pud;
+ pmd = pmd_offset(pud, addr);
return (pte_t *) pmd;
}
diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c
index 31238dad85fb..b96a5f773d88 100644
--- a/mm/kasan/kasan_init.c
+++ b/mm/kasan/kasan_init.c
@@ -30,6 +30,9 @@
*/
unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
+#if CONFIG_PGTABLE_LEVELS > 4
+p4d_t kasan_zero_p4d[PTRS_PER_P4D] __page_aligned_bss;
+#endif
#if CONFIG_PGTABLE_LEVELS > 3
pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
#endif
@@ -82,10 +85,10 @@ static void __init zero_pmd_populate(pud_t *pud, unsigned long addr,
} while (pmd++, addr = next, addr != end);
}
-static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
+static void __init zero_pud_populate(p4d_t *p4d, unsigned long addr,
unsigned long end)
{
- pud_t *pud = pud_offset(pgd, addr);
+ pud_t *pud = pud_offset(p4d, addr);
unsigned long next;
do {
@@ -107,6 +110,23 @@ static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
} while (pud++, addr = next, addr != end);
}
+static void __init zero_p4d_populate(pgd_t *pgd, unsigned long addr,
+ unsigned long end)
+{
+ p4d_t *p4d = p4d_offset(pgd, addr);
+ unsigned long next;
+
+ do {
+ next = p4d_addr_end(addr, end);
+
+ if (p4d_none(*p4d)) {
+ p4d_populate(&init_mm, p4d,
+ early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+ }
+ zero_pud_populate(p4d, addr, next);
+ } while (p4d++, addr = next, addr != end);
+}
+
/**
* kasan_populate_zero_shadow - populate shadow memory region with
* kasan_zero_page
@@ -125,6 +145,7 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
next = pgd_addr_end(addr, end);
if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) {
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
@@ -135,9 +156,22 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
* 3,2 - level page tables where we don't have
* puds,pmds, so pgd_populate(), pud_populate()
* is noops.
+ *
+ * The ifndef is required to avoid build breakage.
+ *
+ * With 5level-fixup.h, pgd_populate() is not nop and
+ * we reference kasan_zero_p4d. It's not defined
+ * unless 5-level paging enabled.
+ *
+ * The ifndef can be dropped once all KASAN-enabled
+ * architectures will switch to pgtable-nop4d.h.
*/
- pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_pud));
- pud = pud_offset(pgd, addr);
+#ifndef __ARCH_HAS_5LEVEL_HACK
+ pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_p4d));
+#endif
+ p4d = p4d_offset(pgd, addr);
+ p4d_populate(&init_mm, p4d, lm_alias(kasan_zero_pud));
+ pud = pud_offset(p4d, addr);
pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd));
pmd = pmd_offset(pud, addr);
pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte));
@@ -148,6 +182,6 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
pgd_populate(&init_mm, pgd,
early_alloc(PAGE_SIZE, NUMA_NO_NODE));
}
- zero_pud_populate(pgd, addr, next);
+ zero_p4d_populate(pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 6f1ed1630873..3a8ddf8baf7d 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -25,6 +25,7 @@
#include <linux/printk.h>
#include <linux/shrinker.h>
#include <linux/slab.h>
+#include <linux/srcu.h>
#include <linux/string.h>
#include <linux/types.h>
@@ -103,6 +104,7 @@ static int quarantine_tail;
/* Total size of all objects in global_quarantine across all batches. */
static unsigned long quarantine_size;
static DEFINE_SPINLOCK(quarantine_lock);
+DEFINE_STATIC_SRCU(remove_cache_srcu);
/* Maximum size of the global queue. */
static unsigned long quarantine_max_size;
@@ -173,17 +175,22 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
struct qlist_head *q;
struct qlist_head temp = QLIST_INIT;
+ /*
+ * Note: irq must be disabled until after we move the batch to the
+ * global quarantine. Otherwise quarantine_remove_cache() can miss
+ * some objects belonging to the cache if they are in our local temp
+ * list. quarantine_remove_cache() executes on_each_cpu() at the
+ * beginning which ensures that it either sees the objects in per-cpu
+ * lists or in the global quarantine.
+ */
local_irq_save(flags);
q = this_cpu_ptr(&cpu_quarantine);
qlist_put(q, &info->quarantine_link, cache->size);
- if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE))
+ if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
qlist_move_all(q, &temp);
- local_irq_restore(flags);
-
- if (unlikely(!qlist_empty(&temp))) {
- spin_lock_irqsave(&quarantine_lock, flags);
+ spin_lock(&quarantine_lock);
WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes);
qlist_move_all(&temp, &global_quarantine[quarantine_tail]);
if (global_quarantine[quarantine_tail].bytes >=
@@ -196,20 +203,33 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
if (new_tail != quarantine_head)
quarantine_tail = new_tail;
}
- spin_unlock_irqrestore(&quarantine_lock, flags);
+ spin_unlock(&quarantine_lock);
}
+
+ local_irq_restore(flags);
}
void quarantine_reduce(void)
{
size_t total_size, new_quarantine_size, percpu_quarantines;
unsigned long flags;
+ int srcu_idx;
struct qlist_head to_free = QLIST_INIT;
if (likely(READ_ONCE(quarantine_size) <=
READ_ONCE(quarantine_max_size)))
return;
+ /*
+ * srcu critical section ensures that quarantine_remove_cache()
+ * will not miss objects belonging to the cache while they are in our
+ * local to_free list. srcu is chosen because (1) it gives us private
+ * grace period domain that does not interfere with anything else,
+ * and (2) it allows synchronize_srcu() to return without waiting
+ * if there are no pending read critical sections (which is the
+ * expected case).
+ */
+ srcu_idx = srcu_read_lock(&remove_cache_srcu);
spin_lock_irqsave(&quarantine_lock, flags);
/*
@@ -237,6 +257,7 @@ void quarantine_reduce(void)
spin_unlock_irqrestore(&quarantine_lock, flags);
qlist_free_all(&to_free, NULL);
+ srcu_read_unlock(&remove_cache_srcu, srcu_idx);
}
static void qlist_move_cache(struct qlist_head *from,
@@ -280,12 +301,28 @@ void quarantine_remove_cache(struct kmem_cache *cache)
unsigned long flags, i;
struct qlist_head to_free = QLIST_INIT;
+ /*
+ * Must be careful to not miss any objects that are being moved from
+ * per-cpu list to the global quarantine in quarantine_put(),
+ * nor objects being freed in quarantine_reduce(). on_each_cpu()
+ * achieves the first goal, while synchronize_srcu() achieves the
+ * second.
+ */
on_each_cpu(per_cpu_remove_cache, cache, 1);
spin_lock_irqsave(&quarantine_lock, flags);
- for (i = 0; i < QUARANTINE_BATCHES; i++)
+ for (i = 0; i < QUARANTINE_BATCHES; i++) {
+ if (qlist_empty(&global_quarantine[i]))
+ continue;
qlist_move_cache(&global_quarantine[i], &to_free, cache);
+ /* Scanning whole quarantine can take a while. */
+ spin_unlock_irqrestore(&quarantine_lock, flags);
+ cond_resched();
+ spin_lock_irqsave(&quarantine_lock, flags);
+ }
spin_unlock_irqrestore(&quarantine_lock, flags);
qlist_free_all(&to_free, cache);
+
+ synchronize_srcu(&remove_cache_srcu);
}
diff --git a/mm/madvise.c b/mm/madvise.c
index dc5927c812d3..7a2abf0127ae 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -513,7 +513,43 @@ static long madvise_dontneed(struct vm_area_struct *vma,
if (!can_madv_dontneed_vma(vma))
return -EINVAL;
- userfaultfd_remove(vma, prev, start, end);
+ if (!userfaultfd_remove(vma, start, end)) {
+ *prev = NULL; /* mmap_sem has been dropped, prev is stale */
+
+ down_read(&current->mm->mmap_sem);
+ vma = find_vma(current->mm, start);
+ if (!vma)
+ return -ENOMEM;
+ if (start < vma->vm_start) {
+ /*
+ * This "vma" under revalidation is the one
+ * with the lowest vma->vm_start where start
+ * is also < vma->vm_end. If start <
+ * vma->vm_start it means an hole materialized
+ * in the user address space within the
+ * virtual range passed to MADV_DONTNEED.
+ */
+ return -ENOMEM;
+ }
+ if (!can_madv_dontneed_vma(vma))
+ return -EINVAL;
+ if (end > vma->vm_end) {
+ /*
+ * Don't fail if end > vma->vm_end. If the old
+ * vma was splitted while the mmap_sem was
+ * released the effect of the concurrent
+ * operation may not cause MADV_DONTNEED to
+ * have an undefined result. There may be an
+ * adjacent next vma that we'll walk
+ * next. userfaultfd_remove() will generate an
+ * UFFD_EVENT_REMOVE repetition on the
+ * end-vma->vm_end range, but the manager can
+ * handle a repetition fine.
+ */
+ end = vma->vm_end;
+ }
+ VM_WARN_ON(start >= end);
+ }
zap_page_range(vma, start, end - start);
return 0;
}
@@ -554,8 +590,10 @@ static long madvise_remove(struct vm_area_struct *vma,
* mmap_sem.
*/
get_file(f);
- userfaultfd_remove(vma, prev, start, end);
- up_read(&current->mm->mmap_sem);
+ if (userfaultfd_remove(vma, start, end)) {
+ /* mmap_sem was not released by userfaultfd_remove() */
+ up_read(&current->mm->mmap_sem);
+ }
error = vfs_fallocate(f,
FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
offset, end - start);
diff --git a/mm/memblock.c b/mm/memblock.c
index b64b47803e52..696f06d17c4e 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1118,7 +1118,10 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
}
} while (left < right);
- return min(PHYS_PFN(type->regions[right].base), max_pfn);
+ if (right == type->cnt)
+ return max_pfn;
+ else
+ return min(PHYS_PFN(type->regions[right].base), max_pfn);
}
/**
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c52ec893e241..2bd7541d7c11 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -466,6 +466,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
struct mem_cgroup_tree_per_node *mctz;
mctz = soft_limit_tree_from_page(page);
+ if (!mctz)
+ return;
/*
* Necessary to update all ancestors when hierarchy is used.
* because their event counter is not touched.
@@ -503,7 +505,8 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
for_each_node(nid) {
mz = mem_cgroup_nodeinfo(memcg, nid);
mctz = soft_limit_tree_node(nid);
- mem_cgroup_remove_exceeded(mz, mctz);
+ if (mctz)
+ mem_cgroup_remove_exceeded(mz, mctz);
}
}
@@ -2558,7 +2561,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
* is empty. Do it lockless to prevent lock bouncing. Races
* are acceptable as soft limit is best effort anyway.
*/
- if (RB_EMPTY_ROOT(&mctz->rb_root))
+ if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
return 0;
/*
@@ -4135,17 +4138,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
kfree(memcg->nodeinfo[node]);
}
-static void mem_cgroup_free(struct mem_cgroup *memcg)
+static void __mem_cgroup_free(struct mem_cgroup *memcg)
{
int node;
- memcg_wb_domain_exit(memcg);
for_each_node(node)
free_mem_cgroup_per_node_info(memcg, node);
free_percpu(memcg->stat);
kfree(memcg);
}
+static void mem_cgroup_free(struct mem_cgroup *memcg)
+{
+ memcg_wb_domain_exit(memcg);
+ __mem_cgroup_free(memcg);
+}
+
static struct mem_cgroup *mem_cgroup_alloc(void)
{
struct mem_cgroup *memcg;
@@ -4196,7 +4204,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
fail:
if (memcg->id.id > 0)
idr_remove(&mem_cgroup_idr, memcg->id.id);
- mem_cgroup_free(memcg);
+ __mem_cgroup_free(memcg);
return NULL;
}
diff --git a/mm/memory.c b/mm/memory.c
index a97a4cec2e1f..235ba51b2fbf 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -445,7 +445,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
mm_dec_nr_pmds(tlb->mm);
}
-static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
@@ -454,7 +454,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long start;
start = addr;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
@@ -462,6 +462,39 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
free_pmd_range(tlb, pud, addr, next, floor, ceiling);
} while (pud++, addr = next, addr != end);
+ start &= P4D_MASK;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= P4D_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ return;
+
+ pud = pud_offset(p4d, start);
+ p4d_clear(p4d);
+ pud_free_tlb(tlb, pud, start);
+}
+
+static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ unsigned long start;
+
+ start = addr;
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ free_pud_range(tlb, p4d, addr, next, floor, ceiling);
+ } while (p4d++, addr = next, addr != end);
+
start &= PGDIR_MASK;
if (start < floor)
return;
@@ -473,9 +506,9 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
if (end - 1 > ceiling - 1)
return;
- pud = pud_offset(pgd, start);
+ p4d = p4d_offset(pgd, start);
pgd_clear(pgd);
- pud_free_tlb(tlb, pud, start);
+ p4d_free_tlb(tlb, p4d, start);
}
/*
@@ -539,7 +572,7 @@ void free_pgd_range(struct mmu_gather *tlb,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+ free_p4d_range(tlb, pgd, addr, next, floor, ceiling);
} while (pgd++, addr = next, addr != end);
}
@@ -658,7 +691,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
pte_t pte, struct page *page)
{
pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
- pud_t *pud = pud_offset(pgd, addr);
+ p4d_t *p4d = p4d_offset(pgd, addr);
+ pud_t *pud = pud_offset(p4d, addr);
pmd_t *pmd = pmd_offset(pud, addr);
struct address_space *mapping;
pgoff_t index;
@@ -1023,16 +1057,16 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
}
static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
- pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+ p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pud_t *src_pud, *dst_pud;
unsigned long next;
- dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
+ dst_pud = pud_alloc(dst_mm, dst_p4d, addr);
if (!dst_pud)
return -ENOMEM;
- src_pud = pud_offset(src_pgd, addr);
+ src_pud = pud_offset(src_p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
@@ -1056,6 +1090,28 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
return 0;
}
+static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ p4d_t *src_p4d, *dst_p4d;
+ unsigned long next;
+
+ dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr);
+ if (!dst_p4d)
+ return -ENOMEM;
+ src_p4d = p4d_offset(src_pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(src_p4d))
+ continue;
+ if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
+ vma, addr, next))
+ return -ENOMEM;
+ } while (dst_p4d++, src_p4d++, addr = next, addr != end);
+ return 0;
+}
+
int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
struct vm_area_struct *vma)
{
@@ -1111,7 +1167,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(src_pgd))
continue;
- if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+ if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
vma, addr, next))) {
ret = -ENOMEM;
break;
@@ -1267,14 +1323,14 @@ next:
}
static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
- struct vm_area_struct *vma, pgd_t *pgd,
+ struct vm_area_struct *vma, p4d_t *p4d,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pud_t *pud;
unsigned long next;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
@@ -1295,6 +1351,25 @@ next:
return addr;
}
+static inline unsigned long zap_p4d_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ struct zap_details *details)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ next = zap_pud_range(tlb, vma, p4d, addr, next, details);
+ } while (p4d++, addr = next, addr != end);
+
+ return addr;
+}
+
void unmap_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
@@ -1310,7 +1385,7 @@ void unmap_page_range(struct mmu_gather *tlb,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- next = zap_pud_range(tlb, vma, pgd, addr, next, details);
+ next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
} while (pgd++, addr = next, addr != end);
tlb_end_vma(tlb, vma);
}
@@ -1465,16 +1540,24 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
spinlock_t **ptl)
{
- pgd_t *pgd = pgd_offset(mm, addr);
- pud_t *pud = pud_alloc(mm, pgd, addr);
- if (pud) {
- pmd_t *pmd = pmd_alloc(mm, pud, addr);
- if (pmd) {
- VM_BUG_ON(pmd_trans_huge(*pmd));
- return pte_alloc_map_lock(mm, pmd, addr, ptl);
- }
- }
- return NULL;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pgd = pgd_offset(mm, addr);
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return NULL;
+ pud = pud_alloc(mm, p4d, addr);
+ if (!pud)
+ return NULL;
+ pmd = pmd_alloc(mm, pud, addr);
+ if (!pmd)
+ return NULL;
+
+ VM_BUG_ON(pmd_trans_huge(*pmd));
+ return pte_alloc_map_lock(mm, pmd, addr, ptl);
}
/*
@@ -1740,7 +1823,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
return 0;
}
-static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
@@ -1748,7 +1831,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long next;
pfn -= addr >> PAGE_SHIFT;
- pud = pud_alloc(mm, pgd, addr);
+ pud = pud_alloc(mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
@@ -1760,6 +1843,26 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
return 0;
}
+static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ unsigned long pfn, pgprot_t prot)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ pfn -= addr >> PAGE_SHIFT;
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return -ENOMEM;
+ do {
+ next = p4d_addr_end(addr, end);
+ if (remap_pud_range(mm, p4d, addr, next,
+ pfn + (addr >> PAGE_SHIFT), prot))
+ return -ENOMEM;
+ } while (p4d++, addr = next, addr != end);
+ return 0;
+}
+
/**
* remap_pfn_range - remap kernel memory to userspace
* @vma: user vma to map to
@@ -1816,7 +1919,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
flush_cache_range(vma, addr, end);
do {
next = pgd_addr_end(addr, end);
- err = remap_pud_range(mm, pgd, addr, next,
+ err = remap_p4d_range(mm, pgd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
break;
@@ -1932,7 +2035,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
return err;
}
-static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data)
{
@@ -1940,7 +2043,7 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long next;
int err;
- pud = pud_alloc(mm, pgd, addr);
+ pud = pud_alloc(mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
@@ -1952,6 +2055,26 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
return err;
}
+static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ pte_fn_t fn, void *data)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ int err;
+
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return -ENOMEM;
+ do {
+ next = p4d_addr_end(addr, end);
+ err = apply_to_pud_range(mm, p4d, addr, next, fn, data);
+ if (err)
+ break;
+ } while (p4d++, addr = next, addr != end);
+ return err;
+}
+
/*
* Scan a region of virtual memory, filling in page tables as necessary
* and calling a provided function on each leaf page table.
@@ -1970,7 +2093,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
pgd = pgd_offset(mm, addr);
do {
next = pgd_addr_end(addr, end);
- err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
+ err = apply_to_p4d_range(mm, pgd, addr, next, fn, data);
if (err)
break;
} while (pgd++, addr = next, addr != end);
@@ -3653,11 +3776,15 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
};
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
+ p4d_t *p4d;
int ret;
pgd = pgd_offset(mm, address);
+ p4d = p4d_alloc(mm, pgd, address);
+ if (!p4d)
+ return VM_FAULT_OOM;
- vmf.pud = pud_alloc(mm, pgd, address);
+ vmf.pud = pud_alloc(mm, p4d, address);
if (!vmf.pud)
return VM_FAULT_OOM;
if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
@@ -3779,12 +3906,35 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
}
EXPORT_SYMBOL_GPL(handle_mm_fault);
+#ifndef __PAGETABLE_P4D_FOLDED
+/*
+ * Allocate p4d page table.
+ * We've already handled the fast-path in-line.
+ */
+int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+ p4d_t *new = p4d_alloc_one(mm, address);
+ if (!new)
+ return -ENOMEM;
+
+ smp_wmb(); /* See comment in __pte_alloc */
+
+ spin_lock(&mm->page_table_lock);
+ if (pgd_present(*pgd)) /* Another has populated it */
+ p4d_free(mm, new);
+ else
+ pgd_populate(mm, pgd, new);
+ spin_unlock(&mm->page_table_lock);
+ return 0;
+}
+#endif /* __PAGETABLE_P4D_FOLDED */
+
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
* We've already handled the fast-path in-line.
*/
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address)
{
pud_t *new = pud_alloc_one(mm, address);
if (!new)
@@ -3793,10 +3943,17 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
smp_wmb(); /* See comment in __pte_alloc */
spin_lock(&mm->page_table_lock);
- if (pgd_present(*pgd)) /* Another has populated it */
+#ifndef __ARCH_HAS_5LEVEL_HACK
+ if (p4d_present(*p4d)) /* Another has populated it */
pud_free(mm, new);
else
- pgd_populate(mm, pgd, new);
+ p4d_populate(mm, p4d, new);
+#else
+ if (pgd_present(*p4d)) /* Another has populated it */
+ pud_free(mm, new);
+ else
+ pgd_populate(mm, p4d, new);
+#endif /* __ARCH_HAS_5LEVEL_HACK */
spin_unlock(&mm->page_table_lock);
return 0;
}
@@ -3839,6 +3996,7 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep;
@@ -3847,7 +4005,11 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
goto out;
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d)))
+ goto out;
+
+ pud = pud_offset(p4d, address);
if (pud_none(*pud) || unlikely(pud_bad(*pud)))
goto out;
diff --git a/mm/mlock.c b/mm/mlock.c
index 1050511f8b2b..0dd9ca18e19e 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -380,6 +380,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
pte = get_locked_pte(vma->vm_mm, start, &ptl);
/* Make sure we do not cross the page table boundary */
end = pgd_addr_end(start, end);
+ end = p4d_addr_end(start, end);
end = pud_addr_end(start, end);
end = pmd_addr_end(start, end);
@@ -442,7 +443,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
while (start < end) {
struct page *page;
- unsigned int page_mask;
+ unsigned int page_mask = 0;
unsigned long page_increm;
struct pagevec pvec;
struct zone *zone;
@@ -456,8 +457,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
* suits munlock very well (and if somehow an abnormal page
* has sneaked into the range, we won't oops here: great).
*/
- page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
- &page_mask);
+ page = follow_page(vma, start, FOLL_GET | FOLL_DUMP);
if (page && !IS_ERR(page)) {
if (PageTransTail(page)) {
@@ -468,8 +468,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
/*
* Any THP page found by follow_page_mask() may
* have gotten split before reaching
- * munlock_vma_page(), so we need to recompute
- * the page_mask here.
+ * munlock_vma_page(), so we need to compute
+ * the page_mask here instead.
*/
page_mask = munlock_vma_page(page);
unlock_page(page);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 848e946b08e5..8edd0d576254 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -193,14 +193,14 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
}
static inline unsigned long change_pud_range(struct vm_area_struct *vma,
- pgd_t *pgd, unsigned long addr, unsigned long end,
+ p4d_t *p4d, unsigned long addr, unsigned long end,
pgprot_t newprot, int dirty_accountable, int prot_numa)
{
pud_t *pud;
unsigned long next;
unsigned long pages = 0;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
@@ -212,6 +212,26 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
return pages;
}
+static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
+ pgd_t *pgd, unsigned long addr, unsigned long end,
+ pgprot_t newprot, int dirty_accountable, int prot_numa)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ unsigned long pages = 0;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ pages += change_pud_range(vma, p4d, addr, next, newprot,
+ dirty_accountable, prot_numa);
+ } while (p4d++, addr = next, addr != end);
+
+ return pages;
+}
+
static unsigned long change_protection_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
@@ -230,7 +250,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- pages += change_pud_range(vma, pgd, addr, next, newprot,
+ pages += change_p4d_range(vma, pgd, addr, next, newprot,
dirty_accountable, prot_numa);
} while (pgd++, addr = next, addr != end);
diff --git a/mm/mremap.c b/mm/mremap.c
index 8233b0105c82..cd8a1b199ef9 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -32,6 +32,7 @@
static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
@@ -39,7 +40,11 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
if (pgd_none_or_clear_bad(pgd))
return NULL;
- pud = pud_offset(pgd, addr);
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none_or_clear_bad(p4d))
+ return NULL;
+
+ pud = pud_offset(p4d, addr);
if (pud_none_or_clear_bad(pud))
return NULL;
@@ -54,11 +59,15 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pgd = pgd_offset(mm, addr);
- pud = pud_alloc(mm, pgd, addr);
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return NULL;
+ pud = pud_alloc(mm, p4d, addr);
if (!pud)
return NULL;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eaa64d2ffdc5..6cbde310abed 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -873,7 +873,8 @@ done_merging:
higher_page = page + (combined_pfn - pfn);
buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
higher_buddy = higher_page + (buddy_pfn - combined_pfn);
- if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
+ if (pfn_valid_within(buddy_pfn) &&
+ page_is_buddy(higher_page, higher_buddy, order + 1)) {
list_add_tail(&page->lru,
&zone->free_area[order].free_list[migratetype]);
goto out;
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index a23001a22c15..c4c9def8ffea 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -104,6 +104,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
struct mm_struct *mm = pvmw->vma->vm_mm;
struct page *page = pvmw->page;
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
/* The only possible pmd mapping has been handled on last iteration */
@@ -133,7 +134,10 @@ restart:
pgd = pgd_offset(mm, pvmw->address);
if (!pgd_present(*pgd))
return false;
- pud = pud_offset(pgd, pvmw->address);
+ p4d = p4d_offset(pgd, pvmw->address);
+ if (!p4d_present(*p4d))
+ return false;
+ pud = pud_offset(p4d, pvmw->address);
if (!pud_present(*pud))
return false;
pvmw->pmd = pmd_offset(pud, pvmw->address);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 03761577ae86..60f7856e508f 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -69,14 +69,14 @@ again:
return err;
}
-static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pud_t *pud;
unsigned long next;
int err = 0;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
again:
next = pud_addr_end(addr, end);
@@ -113,6 +113,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
return err;
}
+static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ int err = 0;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d)) {
+ if (walk->pte_hole)
+ err = walk->pte_hole(addr, next, walk);
+ if (err)
+ break;
+ continue;
+ }
+ if (walk->pmd_entry || walk->pte_entry)
+ err = walk_pud_range(p4d, addr, next, walk);
+ if (err)
+ break;
+ } while (p4d++, addr = next, addr != end);
+
+ return err;
+}
+
static int walk_pgd_range(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -131,7 +157,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
continue;
}
if (walk->pmd_entry || walk->pte_entry)
- err = walk_pud_range(pgd, addr, next, walk);
+ err = walk_p4d_range(pgd, addr, next, walk);
if (err)
break;
} while (pgd++, addr = next, addr != end);
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 4ed5908c65b0..c99d9512a45b 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -22,6 +22,12 @@ void pgd_clear_bad(pgd_t *pgd)
pgd_clear(pgd);
}
+void p4d_clear_bad(p4d_t *p4d)
+{
+ p4d_ERROR(*p4d);
+ p4d_clear(p4d);
+}
+
void pud_clear_bad(pud_t *pud)
{
pud_ERROR(*pud);
diff --git a/mm/rmap.c b/mm/rmap.c
index 2da487d6cea8..49ed681ccc7b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -684,6 +684,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd = NULL;
pmd_t pmde;
@@ -692,7 +693,11 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
if (!pgd_present(*pgd))
goto out;
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ if (!p4d_present(*p4d))
+ goto out;
+
+ pud = pud_offset(p4d, address);
if (!pud_present(*pud))
goto out;
@@ -1316,12 +1321,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
}
while (page_vma_mapped_walk(&pvmw)) {
- subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
- address = pvmw.address;
-
- /* Unexpected PMD-mapped THP? */
- VM_BUG_ON_PAGE(!pvmw.pte, page);
-
/*
* If the page is mlock()d, we cannot swap it out.
* If it's recently referenced (perhaps page_referenced
@@ -1345,6 +1344,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
continue;
}
+ /* Unexpected PMD-mapped THP? */
+ VM_BUG_ON_PAGE(!pvmw.pte, page);
+
+ subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+ address = pvmw.address;
+
+
if (!(flags & TTU_IGNORE_ACCESS)) {
if (ptep_clear_flush_young_notify(vma, address,
pvmw.pte)) {
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 574c67b663fe..a56c3989f773 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -196,9 +196,9 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
return pmd;
}
-pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
+pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
{
- pud_t *pud = pud_offset(pgd, addr);
+ pud_t *pud = pud_offset(p4d, addr);
if (pud_none(*pud)) {
void *p = vmemmap_alloc_block(PAGE_SIZE, node);
if (!p)
@@ -208,6 +208,18 @@ pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
return pud;
}
+p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
+{
+ p4d_t *p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d)) {
+ void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+ if (!p)
+ return NULL;
+ p4d_populate(&init_mm, p4d, p);
+ }
+ return p4d;
+}
+
pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
{
pgd_t *pgd = pgd_offset_k(addr);
@@ -225,6 +237,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
{
unsigned long addr = start;
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
@@ -233,7 +246,10 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
pgd = vmemmap_pgd_populate(addr, node);
if (!pgd)
return -ENOMEM;
- pud = vmemmap_pud_populate(pgd, addr, node);
+ p4d = vmemmap_p4d_populate(pgd, addr, node);
+ if (!p4d)
+ return -ENOMEM;
+ pud = vmemmap_pud_populate(p4d, addr, node);
if (!pud)
return -ENOMEM;
pmd = vmemmap_pmd_populate(pud, addr, node);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 521ef9b6064f..178130880b90 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1517,7 +1517,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
return 0;
}
-static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
@@ -1525,7 +1525,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long next;
int ret;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
@@ -1537,6 +1537,26 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
return 0;
}
+static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ swp_entry_t entry, struct page *page)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ int ret;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ ret = unuse_pud_range(vma, p4d, addr, next, entry, page);
+ if (ret)
+ return ret;
+ } while (p4d++, addr = next, addr != end);
+ return 0;
+}
+
static int unuse_vma(struct vm_area_struct *vma,
swp_entry_t entry, struct page *page)
{
@@ -1560,7 +1580,7 @@ static int unuse_vma(struct vm_area_struct *vma,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- ret = unuse_pud_range(vma, pgd, addr, next, entry, page);
+ ret = unuse_p4d_range(vma, pgd, addr, next, entry, page);
if (ret)
return ret;
} while (pgd++, addr = next, addr != end);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 479e631d43c2..8bcb501bce60 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -128,19 +128,22 @@ out_unlock:
static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
- pmd_t *pmd = NULL;
pgd = pgd_offset(mm, address);
- pud = pud_alloc(mm, pgd, address);
- if (pud)
- /*
- * Note that we didn't run this because the pmd was
- * missing, the *pmd may be already established and in
- * turn it may also be a trans_huge_pmd.
- */
- pmd = pmd_alloc(mm, pud, address);
- return pmd;
+ p4d = p4d_alloc(mm, pgd, address);
+ if (!p4d)
+ return NULL;
+ pud = pud_alloc(mm, p4d, address);
+ if (!pud)
+ return NULL;
+ /*
+ * Note that we didn't run this because the pmd was
+ * missing, the *pmd may be already established and in
+ * turn it may also be a trans_huge_pmd.
+ */
+ return pmd_alloc(mm, pud, address);
}
#ifdef CONFIG_HUGETLB_PAGE
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b4024d688f38..0dd80222b20b 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -86,12 +86,12 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end)
} while (pmd++, addr = next, addr != end);
}
-static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
+static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end)
{
pud_t *pud;
unsigned long next;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_clear_huge(pud))
@@ -102,6 +102,22 @@ static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
} while (pud++, addr = next, addr != end);
}
+static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_clear_huge(p4d))
+ continue;
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ vunmap_pud_range(p4d, addr, next);
+ } while (p4d++, addr = next, addr != end);
+}
+
static void vunmap_page_range(unsigned long addr, unsigned long end)
{
pgd_t *pgd;
@@ -113,7 +129,7 @@ static void vunmap_page_range(unsigned long addr, unsigned long end)
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- vunmap_pud_range(pgd, addr, next);
+ vunmap_p4d_range(pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
@@ -160,13 +176,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr,
return 0;
}
-static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
+static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
pud_t *pud;
unsigned long next;
- pud = pud_alloc(&init_mm, pgd, addr);
+ pud = pud_alloc(&init_mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
@@ -177,6 +193,23 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
return 0;
}
+static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
+ unsigned long end, pgprot_t prot, struct page **pages, int *nr)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ p4d = p4d_alloc(&init_mm, pgd, addr);
+ if (!p4d)
+ return -ENOMEM;
+ do {
+ next = p4d_addr_end(addr, end);
+ if (vmap_pud_range(p4d, addr, next, prot, pages, nr))
+ return -ENOMEM;
+ } while (p4d++, addr = next, addr != end);
+ return 0;
+}
+
/*
* Set up page tables in kva (addr, end). The ptes shall have prot "prot", and
* will have pfns corresponding to the "pages" array.
@@ -196,7 +229,7 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end,
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
- err = vmap_pud_range(pgd, addr, next, prot, pages, &nr);
+ err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr);
if (err)
return err;
} while (pgd++, addr = next, addr != end);
@@ -237,6 +270,10 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
unsigned long addr = (unsigned long) vmalloc_addr;
struct page *page = NULL;
pgd_t *pgd = pgd_offset_k(addr);
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *ptep, pte;
/*
* XXX we might need to change this if we add VIRTUAL_BUG_ON for
@@ -244,21 +281,23 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
*/
VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));
- if (!pgd_none(*pgd)) {
- pud_t *pud = pud_offset(pgd, addr);
- if (!pud_none(*pud)) {
- pmd_t *pmd = pmd_offset(pud, addr);
- if (!pmd_none(*pmd)) {
- pte_t *ptep, pte;
-
- ptep = pte_offset_map(pmd, addr);
- pte = *ptep;
- if (pte_present(pte))
- page = pte_page(pte);
- pte_unmap(ptep);
- }
- }
- }
+ if (pgd_none(*pgd))
+ return NULL;
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d))
+ return NULL;
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ return NULL;
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ return NULL;
+
+ ptep = pte_offset_map(pmd, addr);
+ pte = *ptep;
+ if (pte_present(pte))
+ page = pte_page(pte);
+ pte_unmap(ptep);
return page;
}
EXPORT_SYMBOL(vmalloc_to_page);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 69f9aff39a2e..b1947f0cbee2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1065,6 +1065,9 @@ const char * const vmstat_text[] = {
"thp_split_page_failed",
"thp_deferred_split_page",
"thp_split_pmd",
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ "thp_split_pud",
+#endif
"thp_zero_page_alloc",
"thp_zero_page_alloc_failed",
#endif
generated by cgit (git 2.34.1) at 2024-05-19 22:29:40 +0000