summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/fremap.c8
-rw-r--r--mm/huge_memory.c9
-rw-r--r--mm/memcontrol.c2
-rw-r--r--mm/memory-failure.c10
-rw-r--r--mm/mlock.c44
-rw-r--r--mm/util.c5
6 files changed, 55 insertions, 23 deletions
diff --git a/mm/fremap.c b/mm/fremap.c
index 5bff0814776..bbc4d660221 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -208,9 +208,10 @@ get_write_lock:
if (mapping_cap_account_dirty(mapping)) {
unsigned long addr;
struct file *file = get_file(vma->vm_file);
+ /* mmap_region may free vma; grab the info now */
+ vm_flags = vma->vm_flags;
- addr = mmap_region(file, start, size,
- vma->vm_flags, pgoff);
+ addr = mmap_region(file, start, size, vm_flags, pgoff);
fput(file);
if (IS_ERR_VALUE(addr)) {
err = addr;
@@ -218,7 +219,7 @@ get_write_lock:
BUG_ON(addr != start);
err = 0;
}
- goto out;
+ goto out_freed;
}
mutex_lock(&mapping->i_mmap_mutex);
flush_dcache_mmap_lock(mapping);
@@ -253,6 +254,7 @@ get_write_lock:
out:
if (vma)
vm_flags = vma->vm_flags;
+out_freed:
if (likely(!has_write_lock))
up_read(&mm->mmap_sem);
else
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7de1bf85f68..95d1acb0f3d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -883,9 +883,6 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
goto out_unlock;
}
- /* mmap_sem prevents this happening but warn if that changes */
- WARN_ON(pmd_trans_migrating(pmd));
-
if (unlikely(pmd_trans_splitting(pmd))) {
/* split huge page running from under us */
spin_unlock(src_ptl);
@@ -1157,7 +1154,7 @@ alloc:
new_page = NULL;
if (unlikely(!new_page)) {
- if (is_huge_zero_pmd(orig_pmd)) {
+ if (!page) {
ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
address, pmd, orig_pmd, haddr);
} else {
@@ -1184,7 +1181,7 @@ alloc:
count_vm_event(THP_FAULT_ALLOC);
- if (is_huge_zero_pmd(orig_pmd))
+ if (!page)
clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
else
copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
@@ -1210,7 +1207,7 @@ alloc:
page_add_new_anon_rmap(new_page, vma, haddr);
set_pmd_at(mm, haddr, pmd, entry);
update_mmu_cache_pmd(vma, address, pmd);
- if (is_huge_zero_pmd(orig_pmd)) {
+ if (!page) {
add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
put_huge_zero_page();
} else {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bf5e8945714..7f1a356153c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -338,7 +338,7 @@ struct mem_cgroup {
static size_t memcg_size(void)
{
return sizeof(struct mem_cgroup) +
- nr_node_ids * sizeof(struct mem_cgroup_per_node);
+ nr_node_ids * sizeof(struct mem_cgroup_per_node *);
}
/* internal only representation about the status of kmem accounting. */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index db08af92c6f..fabe55046c1 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -938,6 +938,16 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
BUG_ON(!PageHWPoison(p));
return SWAP_FAIL;
}
+ /*
+ * We pinned the head page for hwpoison handling,
+ * now we split the thp and we are interested in
+ * the hwpoisoned raw page, so move the refcount
+ * to it.
+ */
+ if (hpage != p) {
+ put_page(hpage);
+ get_page(p);
+ }
/* THP is split, so ppage should be the real poisoned page. */
ppage = p;
}
diff --git a/mm/mlock.c b/mm/mlock.c
index d480cd6fc47..192e6eebe4f 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -133,7 +133,10 @@ static void __munlock_isolation_failed(struct page *page)
/**
* munlock_vma_page - munlock a vma page
- * @page - page to be unlocked
+ * @page - page to be unlocked, either a normal page or THP page head
+ *
+ * returns the size of the page as a page mask (0 for normal page,
+ * HPAGE_PMD_NR - 1 for THP head page)
*
* called from munlock()/munmap() path with page supposedly on the LRU.
* When we munlock a page, because the vma where we found the page is being
@@ -148,21 +151,30 @@ static void __munlock_isolation_failed(struct page *page)
*/
unsigned int munlock_vma_page(struct page *page)
{
- unsigned int page_mask = 0;
+ unsigned int nr_pages;
BUG_ON(!PageLocked(page));
if (TestClearPageMlocked(page)) {
- unsigned int nr_pages = hpage_nr_pages(page);
+ nr_pages = hpage_nr_pages(page);
mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
- page_mask = nr_pages - 1;
if (!isolate_lru_page(page))
__munlock_isolated_page(page);
else
__munlock_isolation_failed(page);
+ } else {
+ nr_pages = hpage_nr_pages(page);
}
- return page_mask;
+ /*
+ * Regardless of the original PageMlocked flag, we determine nr_pages
+ * after touching the flag. This leaves a possible race with a THP page
+ * split, such that a whole THP page was munlocked, but nr_pages == 1.
+ * Returning a smaller mask due to that is OK, the worst that can
+ * happen is subsequent useless scanning of the former tail pages.
+ * The NR_MLOCK accounting can however become broken.
+ */
+ return nr_pages - 1;
}
/**
@@ -286,10 +298,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
{
int i;
int nr = pagevec_count(pvec);
- int delta_munlocked = -nr;
+ int delta_munlocked;
struct pagevec pvec_putback;
int pgrescued = 0;
+ pagevec_init(&pvec_putback, 0);
+
/* Phase 1: page isolation */
spin_lock_irq(&zone->lru_lock);
for (i = 0; i < nr; i++) {
@@ -318,18 +332,21 @@ skip_munlock:
/*
* We won't be munlocking this page in the next phase
* but we still need to release the follow_page_mask()
- * pin.
+ * pin. We cannot do it under lru_lock however. If it's
+ * the last pin, __page_cache_release would deadlock.
*/
+ pagevec_add(&pvec_putback, pvec->pages[i]);
pvec->pages[i] = NULL;
- put_page(page);
- delta_munlocked++;
}
}
+ delta_munlocked = -nr + pagevec_count(&pvec_putback);
__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
spin_unlock_irq(&zone->lru_lock);
+ /* Now we can release pins of pages that we are not munlocking */
+ pagevec_release(&pvec_putback);
+
/* Phase 2: page munlock */
- pagevec_init(&pvec_putback, 0);
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
@@ -440,7 +457,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
while (start < end) {
struct page *page = NULL;
- unsigned int page_mask, page_increm;
+ unsigned int page_mask;
+ unsigned long page_increm;
struct pagevec pvec;
struct zone *zone;
int zoneid;
@@ -490,7 +508,9 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
goto next;
}
}
- page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+ /* It's a bug to munlock in the middle of a THP page */
+ VM_BUG_ON((start >> PAGE_SHIFT) & page_mask);
+ page_increm = 1 + page_mask;
start += page_increm * PAGE_SIZE;
next:
cond_resched();
diff --git a/mm/util.c b/mm/util.c
index f7bc2096071..808f375648e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -390,7 +390,10 @@ struct address_space *page_mapping(struct page *page)
{
struct address_space *mapping = page->mapping;
- VM_BUG_ON(PageSlab(page));
+ /* This happens if someone calls flush_dcache_page on slab page */
+ if (unlikely(PageSlab(page)))
+ return NULL;
+
if (unlikely(PageSwapCache(page))) {
swp_entry_t entry;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-12 04:04:05 +0000