aboutsummaryrefslogtreecommitdiffstats
path: root/mm/huge_memory.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r--mm/huge_memory.c111
1 files changed, 60 insertions, 51 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8b137248b146..800d7de32af8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -62,6 +62,7 @@ static struct shrinker deferred_split_shrinker;
static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
+unsigned long huge_zero_pfn __read_mostly = ~0UL;
bool transparent_hugepage_enabled(struct vm_area_struct *vma)
{
@@ -93,6 +94,7 @@ retry:
__free_pages(zero_page, compound_order(zero_page));
goto retry;
}
+ WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));
/* We take additional reference here. It will be put back by shrinker */
atomic_set(&huge_zero_refcount, 2);
@@ -142,6 +144,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
struct page *zero_page = xchg(&huge_zero_page, NULL);
BUG_ON(zero_page == NULL);
+ WRITE_ONCE(huge_zero_pfn, ~0UL);
__free_pages(zero_page, compound_order(zero_page));
return HPAGE_PMD_NR;
}
@@ -694,7 +697,6 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
transparent_hugepage_use_zero_page()) {
pgtable_t pgtable;
struct page *zero_page;
- bool set;
vm_fault_t ret;
pgtable = pte_alloc_one(vma->vm_mm, haddr);
if (unlikely(!pgtable))
@@ -707,25 +709,25 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
}
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
ret = 0;
- set = false;
if (pmd_none(*vmf->pmd)) {
ret = check_stable_address_space(vma->vm_mm);
if (ret) {
spin_unlock(vmf->ptl);
+ pte_free(vma->vm_mm, pgtable);
} else if (userfaultfd_missing(vma)) {
spin_unlock(vmf->ptl);
+ pte_free(vma->vm_mm, pgtable);
ret = handle_userfault(vmf, VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
} else {
set_huge_zero_page(pgtable, vma->vm_mm, vma,
haddr, vmf->pmd, zero_page);
spin_unlock(vmf->ptl);
- set = true;
}
- } else
+ } else {
spin_unlock(vmf->ptl);
- if (!set)
pte_free(vma->vm_mm, pgtable);
+ }
return ret;
}
gfp = alloc_hugepage_direct_gfpmask(vma);
@@ -1433,13 +1435,12 @@ out_unlock:
}
/*
- * FOLL_FORCE can write to even unwritable pmd's, but only
- * after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE or a forced COW break can write even to unwritable pmd's,
+ * but only after we've gone through a COW cycle and they are dirty.
*/
static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
{
- return pmd_write(pmd) ||
- ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+ return pmd_write(pmd) || ((flags & FOLL_COW) && pmd_dirty(pmd));
}
struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
@@ -1691,7 +1692,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
* If other processes are mapping this page, we couldn't discard
* the page unless they all do MADV_FREE so let's skip the page.
*/
- if (page_mapcount(page) != 1)
+ if (total_mapcount(page) != 1)
goto out;
if (!trylock_page(page))
@@ -2127,7 +2128,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
count_vm_event(THP_SPLIT_PMD);
if (!vma_is_anonymous(vma)) {
- _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+ old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
/*
* We are going to unmap this huge page. So
* just go ahead and zap it
@@ -2136,16 +2137,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
zap_deposited_table(mm, pmd);
if (vma_is_dax(vma))
return;
- page = pmd_page(_pmd);
- if (!PageDirty(page) && pmd_dirty(_pmd))
- set_page_dirty(page);
- if (!PageReferenced(page) && pmd_young(_pmd))
- SetPageReferenced(page);
- page_remove_rmap(page, true);
- put_page(page);
+ if (unlikely(is_pmd_migration_entry(old_pmd))) {
+ swp_entry_t entry;
+
+ entry = pmd_to_swp_entry(old_pmd);
+ page = migration_entry_to_page(entry);
+ } else {
+ page = pmd_page(old_pmd);
+ if (!PageDirty(page) && pmd_dirty(old_pmd))
+ set_page_dirty(page);
+ if (!PageReferenced(page) && pmd_young(old_pmd))
+ SetPageReferenced(page);
+ page_remove_rmap(page, true);
+ put_page(page);
+ }
add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
return;
- } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
+ }
+
+ if (is_huge_zero_pmd(*pmd)) {
/*
* FIXME: Do we want to invalidate secondary mmu by calling
* mmu_notifier_invalidate_range() see comments below inside
@@ -2279,7 +2289,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
spinlock_t *ptl;
struct mm_struct *mm = vma->vm_mm;
unsigned long haddr = address & HPAGE_PMD_MASK;
- bool was_locked = false;
+ bool do_unlock_page = false;
pmd_t _pmd;
mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
@@ -2292,7 +2302,6 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
VM_BUG_ON(freeze && !page);
if (page) {
VM_WARN_ON_ONCE(!PageLocked(page));
- was_locked = true;
if (page != pmd_page(*pmd))
goto out;
}
@@ -2301,19 +2310,29 @@ repeat:
if (pmd_trans_huge(*pmd)) {
if (!page) {
page = pmd_page(*pmd);
- if (unlikely(!trylock_page(page))) {
- get_page(page);
- _pmd = *pmd;
- spin_unlock(ptl);
- lock_page(page);
- spin_lock(ptl);
- if (unlikely(!pmd_same(*pmd, _pmd))) {
- unlock_page(page);
+ /*
+ * An anonymous page must be locked, to ensure that a
+ * concurrent reuse_swap_page() sees stable mapcount;
+ * but reuse_swap_page() is not used on shmem or file,
+ * and page lock must not be taken when zap_pmd_range()
+ * calls __split_huge_pmd() while i_mmap_lock is held.
+ */
+ if (PageAnon(page)) {
+ if (unlikely(!trylock_page(page))) {
+ get_page(page);
+ _pmd = *pmd;
+ spin_unlock(ptl);
+ lock_page(page);
+ spin_lock(ptl);
+ if (unlikely(!pmd_same(*pmd, _pmd))) {
+ unlock_page(page);
+ put_page(page);
+ page = NULL;
+ goto repeat;
+ }
put_page(page);
- page = NULL;
- goto repeat;
}
- put_page(page);
+ do_unlock_page = true;
}
}
if (PageMlocked(page))
@@ -2323,7 +2342,7 @@ repeat:
__split_huge_pmd_locked(vma, pmd, haddr, freeze);
out:
spin_unlock(ptl);
- if (!was_locked && page)
+ if (do_unlock_page)
unlock_page(page);
/*
* No need to double call mmu_notifier->invalidate_range() callback.
@@ -2411,16 +2430,16 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
static void unmap_page(struct page *page)
{
enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
- TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
- bool unmap_success;
+ TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC;
VM_BUG_ON_PAGE(!PageHead(page), page);
if (PageAnon(page))
ttu_flags |= TTU_SPLIT_FREEZE;
- unmap_success = try_to_unmap(page, ttu_flags);
- VM_BUG_ON_PAGE(!unmap_success, page);
+ try_to_unmap(page, ttu_flags);
+
+ VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
}
static void remap_page(struct page *page)
@@ -2679,7 +2698,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
struct anon_vma *anon_vma = NULL;
struct address_space *mapping = NULL;
- int count, mapcount, extra_pins, ret;
+ int extra_pins, ret;
bool mlocked;
unsigned long flags;
pgoff_t end;
@@ -2741,7 +2760,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
mlocked = PageMlocked(page);
unmap_page(head);
- VM_BUG_ON_PAGE(compound_mapcount(head), head);
/* Make sure the page is not on per-CPU pagevec as it takes pin */
if (mlocked)
@@ -2767,9 +2785,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
/* Prevent deferred_split_scan() touching ->_refcount */
spin_lock(&pgdata->split_queue_lock);
- count = page_count(head);
- mapcount = total_mapcount(head);
- if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
+ if (page_ref_freeze(head, 1 + extra_pins)) {
if (!list_empty(page_deferred_list(head))) {
pgdata->split_queue_len--;
list_del(page_deferred_list(head));
@@ -2785,16 +2801,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
} else
ret = 0;
} else {
- if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
- pr_alert("total_mapcount: %u, page_count(): %u\n",
- mapcount, count);
- if (PageTail(page))
- dump_page(head, NULL);
- dump_page(page, "total_mapcount(head) > 0");
- BUG();
- }
spin_unlock(&pgdata->split_queue_lock);
-fail: if (mapping)
+fail:
+ if (mapping)
xa_unlock(&mapping->i_pages);
spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
remap_page(head);
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-24 07:18:17 +0000