summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/compaction.c12
-rw-r--r--mm/debug.c4
-rw-r--r--mm/filemap.c26
-rw-r--r--mm/gup.c14
-rw-r--r--mm/huge_memory.c13
-rw-r--r--mm/hugetlb.c110
-rw-r--r--mm/madvise.c4
-rw-r--r--mm/memcontrol.c173
-rw-r--r--mm/memory-failure.c36
-rw-r--r--mm/memory_hotplug.c18
-rw-r--r--mm/mempolicy.c6
-rw-r--r--mm/memremap.c39
-rw-r--r--mm/migrate.c44
-rw-r--r--mm/page-writeback.c6
-rw-r--r--mm/page_alloc.c13
-rw-r--r--mm/page_io.c6
-rw-r--r--mm/percpu.c8
-rw-r--r--mm/process_vm_access.c4
-rw-r--r--mm/rmap.c5
-rw-r--r--mm/slab.h38
-rw-r--r--mm/slub.c2
-rw-r--r--mm/truncate.c2
-rw-r--r--mm/vmscan.c5
-rw-r--r--mm/workingset.c2
24 files changed, 248 insertions, 342 deletions
diff --git a/mm/compaction.c b/mm/compaction.c
index 6e0ee5641788..13cb7a961b31 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -817,6 +817,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
* delay for some time until fewer pages are isolated
*/
while (unlikely(too_many_isolated(pgdat))) {
+ /* stop isolation if there are still pages not migrated */
+ if (cc->nr_migratepages)
+ return 0;
+
/* async migration should just abort */
if (cc->mode == MIGRATE_ASYNC)
return 0;
@@ -1012,8 +1016,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
isolate_success:
list_add(&page->lru, &cc->migratepages);
- cc->nr_migratepages++;
- nr_isolated++;
+ cc->nr_migratepages += compound_nr(page);
+ nr_isolated += compound_nr(page);
/*
* Avoid isolating too much unless this block is being
@@ -1021,7 +1025,7 @@ isolate_success:
* or a lock is contended. For contention, isolate quickly to
* potentially remove one source of contention.
*/
- if (cc->nr_migratepages == COMPACT_CLUSTER_MAX &&
+ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX &&
!cc->rescan && !cc->contended) {
++low_pfn;
break;
@@ -1132,7 +1136,7 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
if (!pfn)
break;
- if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX)
break;
}
diff --git a/mm/debug.c b/mm/debug.c
index ccca576b2899..8a40b3fefbeb 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -182,8 +182,8 @@ hex_only:
pr_warn("page dumped because: %s\n", reason);
#ifdef CONFIG_MEMCG
- if (!page_poisoned && page->mem_cgroup)
- pr_warn("page->mem_cgroup:%px\n", page->mem_cgroup);
+ if (!page_poisoned && page->memcg_data)
+ pr_warn("pages's memcg:%lx\n", page->memcg_data);
#endif
}
diff --git a/mm/filemap.c b/mm/filemap.c
index d5e7c2029d16..0b2067b3c328 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1484,11 +1484,19 @@ void end_page_writeback(struct page *page)
rotate_reclaimable_page(page);
}
+ /*
+ * Writeback does not hold a page reference of its own, relying
+ * on truncation to wait for the clearing of PG_writeback.
+ * But here we must make sure that the page is not freed and
+ * reused before the wake_up_page().
+ */
+ get_page(page);
if (!test_clear_page_writeback(page))
BUG();
smp_mb__after_atomic();
wake_up_page(page, PG_writeback);
+ put_page(page);
}
EXPORT_SYMBOL(end_page_writeback);
@@ -2347,10 +2355,15 @@ page_ok:
page_not_up_to_date:
/* Get exclusive access to the page ... */
- if (iocb->ki_flags & IOCB_WAITQ)
+ if (iocb->ki_flags & IOCB_WAITQ) {
+ if (written) {
+ put_page(page);
+ goto out;
+ }
error = lock_page_async(page, iocb->ki_waitq);
- else
+ } else {
error = lock_page_killable(page);
+ }
if (unlikely(error))
goto readpage_error;
@@ -2393,10 +2406,15 @@ readpage:
}
if (!PageUptodate(page)) {
- if (iocb->ki_flags & IOCB_WAITQ)
+ if (iocb->ki_flags & IOCB_WAITQ) {
+ if (written) {
+ put_page(page);
+ goto out;
+ }
error = lock_page_async(page, iocb->ki_waitq);
- else
+ } else {
error = lock_page_killable(page);
+ }
if (unlikely(error))
goto readpage_error;
diff --git a/mm/gup.c b/mm/gup.c
index 102877ed77a4..98eb8e6d2609 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1647,8 +1647,11 @@ check_again:
/*
* drop the above get_user_pages reference.
*/
- for (i = 0; i < nr_pages; i++)
- put_page(pages[i]);
+ if (gup_flags & FOLL_PIN)
+ unpin_user_pages(pages, nr_pages);
+ else
+ for (i = 0; i < nr_pages; i++)
+ put_page(pages[i]);
if (migrate_pages(&cma_page_list, alloc_migration_target, NULL,
(unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
@@ -1728,8 +1731,11 @@ static long __gup_longterm_locked(struct mm_struct *mm,
goto out;
if (check_dax_vmas(vmas_tmp, rc)) {
- for (i = 0; i < rc; i++)
- put_page(pages[i]);
+ if (gup_flags & FOLL_PIN)
+ unpin_user_pages(pages, rc);
+ else
+ for (i = 0; i < rc; i++)
+ put_page(pages[i]);
rc = -EOPNOTSUPP;
goto out;
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9474dbc150ed..8bbf1c1affde 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -470,7 +470,7 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
#ifdef CONFIG_MEMCG
static inline struct deferred_split *get_deferred_split_queue(struct page *page)
{
- struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+ struct mem_cgroup *memcg = page_memcg(compound_head(page));
struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
if (memcg)
@@ -710,7 +710,6 @@ 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);
if (unlikely(!pgtable))
@@ -723,25 +722,25 @@ 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);
@@ -2765,7 +2764,7 @@ void deferred_split_huge_page(struct page *page)
{
struct deferred_split *ds_queue = get_deferred_split_queue(page);
#ifdef CONFIG_MEMCG
- struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+ struct mem_cgroup *memcg = page_memcg(compound_head(page));
#endif
unsigned long flags;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fe76f8fd5a73..37f15c3c24dc 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -648,6 +648,8 @@ retry:
}
del += t - f;
+ hugetlb_cgroup_uncharge_file_region(
+ resv, rg, t - f);
/* New entry for end of split region */
nrg->from = t;
@@ -660,9 +662,6 @@ retry:
/* Original entry is trimmed */
rg->to = f;
- hugetlb_cgroup_uncharge_file_region(
- resv, rg, nrg->to - nrg->from);
-
list_add(&nrg->link, &rg->link);
nrg = NULL;
break;
@@ -678,17 +677,17 @@ retry:
}
if (f <= rg->from) { /* Trim beginning of region */
- del += t - rg->from;
- rg->from = t;
-
hugetlb_cgroup_uncharge_file_region(resv, rg,
t - rg->from);
- } else { /* Trim end of region */
- del += rg->to - f;
- rg->to = f;
+ del += t - rg->from;
+ rg->from = t;
+ } else { /* Trim end of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
rg->to - f);
+
+ del += rg->to - f;
+ rg->to = f;
}
}
@@ -1569,103 +1568,23 @@ int PageHeadHuge(struct page *page_head)
}
/*
- * Find address_space associated with hugetlbfs page.
- * Upon entry page is locked and page 'was' mapped although mapped state
- * could change. If necessary, use anon_vma to find vma and associated
- * address space. The returned mapping may be stale, but it can not be
- * invalid as page lock (which is held) is required to destroy mapping.
- */
-static struct address_space *_get_hugetlb_page_mapping(struct page *hpage)
-{
- struct anon_vma *anon_vma;
- pgoff_t pgoff_start, pgoff_end;
- struct anon_vma_chain *avc;
- struct address_space *mapping = page_mapping(hpage);
-
- /* Simple file based mapping */
- if (mapping)
- return mapping;
-
- /*
- * Even anonymous hugetlbfs mappings are associated with an
- * underlying hugetlbfs file (see hugetlb_file_setup in mmap
- * code). Find a vma associated with the anonymous vma, and
- * use the file pointer to get address_space.
- */
- anon_vma = page_lock_anon_vma_read(hpage);
- if (!anon_vma)
- return mapping; /* NULL */
-
- /* Use first found vma */
- pgoff_start = page_to_pgoff(hpage);
- pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1;
- anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
- pgoff_start, pgoff_end) {
- struct vm_area_struct *vma = avc->vma;
-
- mapping = vma->vm_file->f_mapping;
- break;
- }
-
- anon_vma_unlock_read(anon_vma);
- return mapping;
-}
-
-/*
* Find and lock address space (mapping) in write mode.
*
- * Upon entry, the page is locked which allows us to find the mapping
- * even in the case of an anon page. However, locking order dictates
- * the i_mmap_rwsem be acquired BEFORE the page lock. This is hugetlbfs
- * specific. So, we first try to lock the sema while still holding the
- * page lock. If this works, great! If not, then we need to drop the
- * page lock and then acquire i_mmap_rwsem and reacquire page lock. Of
- * course, need to revalidate state along the way.
+ * Upon entry, the page is locked which means that page_mapping() is
+ * stable. Due to locking order, we can only trylock_write. If we can
+ * not get the lock, simply return NULL to caller.
*/
struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
{
- struct address_space *mapping, *mapping2;
+ struct address_space *mapping = page_mapping(hpage);
- mapping = _get_hugetlb_page_mapping(hpage);
-retry:
if (!mapping)
return mapping;
- /*
- * If no contention, take lock and return
- */
if (i_mmap_trylock_write(mapping))
return mapping;
- /*
- * Must drop page lock and wait on mapping sema.
- * Note: Once page lock is dropped, mapping could become invalid.
- * As a hack, increase map count until we lock page again.
- */
- atomic_inc(&hpage->_mapcount);
- unlock_page(hpage);
- i_mmap_lock_write(mapping);
- lock_page(hpage);
- atomic_add_negative(-1, &hpage->_mapcount);
-
- /* verify page is still mapped */
- if (!page_mapped(hpage)) {
- i_mmap_unlock_write(mapping);
- return NULL;
- }
-
- /*
- * Get address space again and verify it is the same one
- * we locked. If not, drop lock and retry.
- */
- mapping2 = _get_hugetlb_page_mapping(hpage);
- if (mapping2 != mapping) {
- i_mmap_unlock_write(mapping);
- mapping = mapping2;
- goto retry;
- }
-
- return mapping;
+ return NULL;
}
pgoff_t __basepage_index(struct page *page)
@@ -2443,6 +2362,9 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
rsv_adjust = hugepage_subpool_put_pages(spool, 1);
hugetlb_acct_memory(h, -rsv_adjust);
+ if (deferred_reserve)
+ hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
+ pages_per_huge_page(h), page);
}
return page;
diff --git a/mm/madvise.c b/mm/madvise.c
index 416a56b8e757..a8d8d48a57fe 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -226,7 +226,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
struct address_space *mapping)
{
XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
- pgoff_t end_index = end / PAGE_SIZE;
+ pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1);
struct page *page;
rcu_read_lock();
@@ -1231,8 +1231,6 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
ret = total_len - iov_iter_count(&iter);
mmput(mm);
- return ret;
-
release_task:
put_task_struct(task);
put_pid:
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3a24e3b619f5..7535042ac1ec 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -533,7 +533,7 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
{
struct mem_cgroup *memcg;
- memcg = page->mem_cgroup;
+ memcg = page_memcg(page);
if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
memcg = root_mem_cgroup;
@@ -560,16 +560,7 @@ ino_t page_cgroup_ino(struct page *page)
unsigned long ino = 0;
rcu_read_lock();
- memcg = page->mem_cgroup;
-
- /*
- * The lowest bit set means that memcg isn't a valid
- * memcg pointer, but a obj_cgroups pointer.
- * In this case the page is shared and doesn't belong
- * to any specific memory cgroup.
- */
- if ((unsigned long) memcg & 0x1UL)
- memcg = NULL;
+ memcg = page_memcg_check(page);
while (memcg && !(memcg->css.flags & CSS_ONLINE))
memcg = parent_mem_cgroup(memcg);
@@ -867,8 +858,13 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
rcu_read_lock();
memcg = mem_cgroup_from_obj(p);
- /* Untracked pages have no memcg, no lruvec. Update only the node */
- if (!memcg || memcg == root_mem_cgroup) {
+ /*
+ * Untracked pages have no memcg, no lruvec. Update only the
+ * node. If we reparent the slab objects to the root memcg,
+ * when we free the slab object, we need to update the per-memcg
+ * vmstats to keep it correct for the root memcg.
+ */
+ if (!memcg) {
__mod_node_page_state(pgdat, idx, val);
} else {
lruvec = mem_cgroup_lruvec(memcg, pgdat);
@@ -1050,7 +1046,7 @@ EXPORT_SYMBOL(get_mem_cgroup_from_mm);
*/
struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
{
- struct mem_cgroup *memcg = page->mem_cgroup;
+ struct mem_cgroup *memcg = page_memcg(page);
if (mem_cgroup_disabled())
return NULL;
@@ -1349,7 +1345,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd
goto out;
}
- memcg = page->mem_cgroup;
+ memcg = page_memcg(page);
/*
* Swapcache readahead pages are added to the LRU - and
* possibly migrated - before they are charged.
@@ -2109,7 +2105,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
}
/**
- * lock_page_memcg - lock a page->mem_cgroup binding
+ * lock_page_memcg - lock a page and memcg binding
* @page: the page
*
* This function protects unlocked LRU pages from being moved to
@@ -2141,7 +2137,7 @@ struct mem_cgroup *lock_page_memcg(struct page *page)
if (mem_cgroup_disabled())
return NULL;
again:
- memcg = head->mem_cgroup;
+ memcg = page_memcg(head);
if (unlikely(!memcg))
return NULL;
@@ -2149,7 +2145,7 @@ again:
return memcg;
spin_lock_irqsave(&memcg->move_lock, flags);
- if (memcg != head->mem_cgroup) {
+ if (memcg != page_memcg(head)) {
spin_unlock_irqrestore(&memcg->move_lock, flags);
goto again;
}
@@ -2187,14 +2183,14 @@ void __unlock_page_memcg(struct mem_cgroup *memcg)
}
/**
- * unlock_page_memcg - unlock a page->mem_cgroup binding
+ * unlock_page_memcg - unlock a page and memcg binding
* @page: the page
*/
void unlock_page_memcg(struct page *page)
{
struct page *head = compound_head(page);
- __unlock_page_memcg(head->mem_cgroup);
+ __unlock_page_memcg(page_memcg(head));
}
EXPORT_SYMBOL(unlock_page_memcg);
@@ -2884,7 +2880,7 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
static void commit_charge(struct page *page, struct mem_cgroup *memcg)
{
- VM_BUG_ON_PAGE(page->mem_cgroup, page);
+ VM_BUG_ON_PAGE(page_memcg(page), page);
/*
* Any of the following ensures page->mem_cgroup stability:
*
@@ -2893,7 +2889,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
* - lock_page_memcg()
* - exclusive reference
*/
- page->mem_cgroup = memcg;
+ page->memcg_data = (unsigned long)memcg;
}
#ifdef CONFIG_MEMCG_KMEM
@@ -2908,8 +2904,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
if (!vec)
return -ENOMEM;
- if (cmpxchg(&page->obj_cgroups, NULL,
- (struct obj_cgroup **) ((unsigned long)vec | 0x1UL)))
+ if (!set_page_objcgs(page, vec))
kfree(vec);
else
kmemleak_not_leak(vec);
@@ -2920,6 +2915,12 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
/*
* Returns a pointer to the memory cgroup to which the kernel object is charged.
*
+ * A passed kernel object can be a slab object or a generic kernel page, so
+ * different mechanisms for getting the memory cgroup pointer should be used.
+ * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller
+ * can not know for sure how the kernel object is implemented.
+ * mem_cgroup_from_obj() can be safely used in such cases.
+ *
* The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
* cgroup_mutex, etc.
*/
@@ -2933,35 +2934,30 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
page = virt_to_head_page(p);
/*
- * If page->mem_cgroup is set, it's either a simple mem_cgroup pointer
- * or a pointer to obj_cgroup vector. In the latter case the lowest
- * bit of the pointer is set.
- * The page->mem_cgroup pointer can be asynchronously changed
- * from NULL to (obj_cgroup_vec | 0x1UL), but can't be changed
- * from a valid memcg pointer to objcg vector or back.
- */
- if (!page->mem_cgroup)
- return NULL;
-
- /*
* Slab objects are accounted individually, not per-page.
* Memcg membership data for each individual object is saved in
* the page->obj_cgroups.
*/
- if (page_has_obj_cgroups(page)) {
+ if (page_objcgs_check(page)) {
struct obj_cgroup *objcg;
unsigned int off;
off = obj_to_index(page->slab_cache, page, p);
- objcg = page_obj_cgroups(page)[off];
+ objcg = page_objcgs(page)[off];
if (objcg)
return obj_cgroup_memcg(objcg);
return NULL;
}
- /* All other pages use page->mem_cgroup */
- return page->mem_cgroup;
+ /*
+ * page_memcg_check() is used here, because page_has_obj_cgroups()
+ * check above could fail because the object cgroups vector wasn't set
+ * at that moment, but it can be set concurrently.
+ * page_memcg_check(page) will guarantee that a proper memory
+ * cgroup pointer or NULL will be returned.
+ */
+ return page_memcg_check(page);
}
__always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
@@ -3099,8 +3095,8 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
if (memcg && !mem_cgroup_is_root(memcg)) {
ret = __memcg_kmem_charge(memcg, gfp, 1 << order);
if (!ret) {
- page->mem_cgroup = memcg;
- __SetPageKmemcg(page);
+ page->memcg_data = (unsigned long)memcg |
+ MEMCG_DATA_KMEM;
return 0;
}
css_put(&memcg->css);
@@ -3115,7 +3111,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
*/
void __memcg_kmem_uncharge_page(struct page *page, int order)
{
- struct mem_cgroup *memcg = page->mem_cgroup;
+ struct mem_cgroup *memcg = page_memcg(page);
unsigned int nr_pages = 1 << order;
if (!memcg)
@@ -3123,12 +3119,8 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
__memcg_kmem_uncharge(memcg, nr_pages);
- page->mem_cgroup = NULL;
+ page->memcg_data = 0;
css_put(&memcg->css);
-
- /* slab pages do not have PageKmemcg flag set */
- if (PageKmemcg(page))
- __ClearPageKmemcg(page);
}
static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
@@ -3274,7 +3266,7 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
*/
void mem_cgroup_split_huge_fixup(struct page *head)
{
- struct mem_cgroup *memcg = head->mem_cgroup;
+ struct mem_cgroup *memcg = page_memcg(head);
int i;
if (mem_cgroup_disabled())
@@ -3282,7 +3274,7 @@ void mem_cgroup_split_huge_fixup(struct page *head)
for (i = 1; i < HPAGE_PMD_NR; i++) {
css_get(&memcg->css);
- head[i].mem_cgroup = memcg;
+ head[i].memcg_data = (unsigned long)memcg;
}
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -4110,11 +4102,17 @@ static int memcg_stat_show(struct seq_file *m, void *v)
(u64)memsw * PAGE_SIZE);
for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
+ unsigned long nr;
+
if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
continue;
+ nr = memcg_page_state(memcg, memcg1_stats[i]);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (memcg1_stats[i] == NR_ANON_THPS)
+ nr *= HPAGE_PMD_NR;
+#endif
seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
- (u64)memcg_page_state(memcg, memcg1_stats[i]) *
- PAGE_SIZE);
+ (u64)nr * PAGE_SIZE);
}
for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
@@ -4658,7 +4656,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
struct bdi_writeback *wb)
{
- struct mem_cgroup *memcg = page->mem_cgroup;
+ struct mem_cgroup *memcg = page_memcg(page);
struct memcg_cgwb_frn *frn;
u64 now = get_jiffies_64();
u64 oldest_at = now;
@@ -5339,17 +5337,22 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
memcg->swappiness = mem_cgroup_swappiness(parent);
memcg->oom_kill_disable = parent->oom_kill_disable;
}
- if (parent && parent->use_hierarchy) {
+ if (!parent) {
+ page_counter_init(&memcg->memory, NULL);
+ page_counter_init(&memcg->swap, NULL);
+ page_counter_init(&memcg->kmem, NULL);
+ page_counter_init(&memcg->tcpmem, NULL);
+ } else if (parent->use_hierarchy) {
memcg->use_hierarchy = true;
page_counter_init(&memcg->memory, &parent->memory);
page_counter_init(&memcg->swap, &parent->swap);
page_counter_init(&memcg->kmem, &parent->kmem);
page_counter_init(&memcg->tcpmem, &parent->tcpmem);
} else {
- page_counter_init(&memcg->memory, NULL);
- page_counter_init(&memcg->swap, NULL);
- page_counter_init(&memcg->kmem, NULL);
- page_counter_init(&memcg->tcpmem, NULL);
+ page_counter_init(&memcg->memory, &root_mem_cgroup->memory);
+ page_counter_init(&memcg->swap, &root_mem_cgroup->swap);
+ page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
+ page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem);
/*
* Deeper hierachy with use_hierarchy == false doesn't make
* much sense so let cgroup subsystem know about this
@@ -5630,14 +5633,14 @@ static int mem_cgroup_move_account(struct page *page,
/*
* Prevent mem_cgroup_migrate() from looking at
- * page->mem_cgroup of its source page while we change it.
+ * page's memory cgroup of its source page while we change it.
*/
ret = -EBUSY;
if (!trylock_page(page))
goto out;
ret = -EINVAL;
- if (page->mem_cgroup != from)
+ if (page_memcg(page) != from)
goto out_unlock;
pgdat = page_pgdat(page);
@@ -5692,13 +5695,13 @@ static int mem_cgroup_move_account(struct page *page,
/*
* All state has been migrated, let's switch to the new memcg.
*
- * It is safe to change page->mem_cgroup here because the page
+ * It is safe to change page's memcg here because the page
* is referenced, charged, isolated, and locked: we can't race
* with (un)charging, migration, LRU putback, or anything else
- * that would rely on a stable page->mem_cgroup.
+ * that would rely on a stable page's memory cgroup.
*
* Note that lock_page_memcg is a memcg lock, not a page lock,
- * to save space. As soon as we switch page->mem_cgroup to a
+ * to save space. As soon as we switch page's memory cgroup to a
* new memcg that isn't locked, the above state can change
* concurrently again. Make sure we're truly done with it.
*/
@@ -5707,7 +5710,7 @@ static int mem_cgroup_move_account(struct page *page,
css_get(&to->css);
css_put(&from->css);
- page->mem_cgroup = to;
+ page->memcg_data = (unsigned long)to;
__unlock_page_memcg(from);
@@ -5773,7 +5776,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
* mem_cgroup_move_account() checks the page is valid or
* not under LRU exclusion.
*/
- if (page->mem_cgroup == mc.from) {
+ if (page_memcg(page) == mc.from) {
ret = MC_TARGET_PAGE;
if (is_device_private_page(page))
ret = MC_TARGET_DEVICE;
@@ -5817,7 +5820,7 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
VM_BUG_ON_PAGE(!page || !PageHead(page), page);
if (!(mc.flags & MOVE_ANON))
return ret;
- if (page->mem_cgroup == mc.from) {
+ if (page_memcg(page) == mc.from) {
ret = MC_TARGET_PAGE;
if (target) {
get_page(page);
@@ -6763,12 +6766,12 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
/*
* Every swap fault against a single page tries to charge the
* page, bail as early as possible. shmem_unuse() encounters
- * already charged pages, too. page->mem_cgroup is protected
- * by the page lock, which serializes swap cache removal, which
- * in turn serializes uncharging.
+ * already charged pages, too. page and memcg binding is
+ * protected by the page lock, which serializes swap cache
+ * removal, which in turn serializes uncharging.
*/
VM_BUG_ON_PAGE(!PageLocked(page), page);
- if (compound_head(page)->mem_cgroup)
+ if (page_memcg(compound_head(page)))
goto out;
id = lookup_swap_cgroup_id(ent);
@@ -6852,21 +6855,21 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
VM_BUG_ON_PAGE(PageLRU(page), page);
- if (!page->mem_cgroup)
+ if (!page_memcg(page))
return;
/*
* Nobody should be changing or seriously looking at
- * page->mem_cgroup at this point, we have fully
+ * page_memcg(page) at this point, we have fully
* exclusive access to the page.
*/
- if (ug->memcg != page->mem_cgroup) {
+ if (ug->memcg != page_memcg(page)) {
if (ug->memcg) {
uncharge_batch(ug);
uncharge_gather_clear(ug);
}
- ug->memcg = page->mem_cgroup;
+ ug->memcg = page_memcg(page);
/* pairs with css_put in uncharge_batch */
css_get(&ug->memcg->css);
@@ -6875,15 +6878,13 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
nr_pages = compound_nr(page);
ug->nr_pages += nr_pages;
- if (!PageKmemcg(page)) {
- ug->pgpgout++;
- } else {
+ if (PageMemcgKmem(page))
ug->nr_kmem += nr_pages;
- __ClearPageKmemcg(page);
- }
+ else
+ ug->pgpgout++;
ug->dummy_page = page;
- page->mem_cgroup = NULL;
+ page->memcg_data = 0;
css_put(&ug->memcg->css);
}
@@ -6926,7 +6927,7 @@ void mem_cgroup_uncharge(struct page *page)
return;
/* Don't touch page->lru of any random page, pre-check: */
- if (!page->mem_cgroup)
+ if (!page_memcg(page))
return;
uncharge_gather_clear(&ug);
@@ -6976,11 +6977,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
return;
/* Page cache replacement: new page already charged? */
- if (newpage->mem_cgroup)
+ if (page_memcg(newpage))
return;
/* Swapcache readahead pages can get replaced before being charged */
- memcg = oldpage->mem_cgroup;
+ memcg = page_memcg(oldpage);
if (!memcg)
return;
@@ -7175,7 +7176,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
return;
- memcg = page->mem_cgroup;
+ memcg = page_memcg(page);
/* Readahead page, never charged */
if (!memcg)
@@ -7196,7 +7197,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
VM_BUG_ON_PAGE(oldid, page);
mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
- page->mem_cgroup = NULL;
+ page->memcg_data = 0;
if (!mem_cgroup_is_root(memcg))
page_counter_uncharge(&memcg->memory, nr_entries);
@@ -7239,7 +7240,7 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
return 0;
- memcg = page->mem_cgroup;
+ memcg = page_memcg(page);
/* Readahead page, never charged */
if (!memcg)
@@ -7320,7 +7321,7 @@ bool mem_cgroup_swap_full(struct page *page)
if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
return false;
- memcg = page->mem_cgroup;
+ memcg = page_memcg(page);
if (!memcg)
return false;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c0bb186bba62..5d880d4eb9a2 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1057,27 +1057,25 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
if (!PageHuge(hpage)) {
unmap_success = try_to_unmap(hpage, ttu);
} else {
- /*
- * For hugetlb pages, try_to_unmap could potentially call
- * huge_pmd_unshare. Because of this, take semaphore in
- * write mode here and set TTU_RMAP_LOCKED to indicate we
- * have taken the lock at this higer level.
- *
- * Note that the call to hugetlb_page_mapping_lock_write
- * is necessary even if mapping is already set. It handles
- * ugliness of potentially having to drop page lock to obtain
- * i_mmap_rwsem.
- */
- mapping = hugetlb_page_mapping_lock_write(hpage);
-
- if (mapping) {
- unmap_success = try_to_unmap(hpage,
+ if (!PageAnon(hpage)) {
+ /*
+ * For hugetlb pages in shared mappings, try_to_unmap
+ * could potentially call huge_pmd_unshare. Because of
+ * this, take semaphore in write mode here and set
+ * TTU_RMAP_LOCKED to indicate we have taken the lock
+ * at this higer level.
+ */
+ mapping = hugetlb_page_mapping_lock_write(hpage);
+ if (mapping) {
+ unmap_success = try_to_unmap(hpage,
ttu|TTU_RMAP_LOCKED);
- i_mmap_unlock_write(mapping);
+ i_mmap_unlock_write(mapping);
+ } else {
+ pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn);
+ unmap_success = false;
+ }
} else {
- pr_info("Memory failure: %#lx: could not find mapping for mapped huge page\n",
- pfn);
- unmap_success = false;
+ unmap_success = try_to_unmap(hpage, ttu);
}
}
if (!unmap_success)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b44d4c7ba73b..63b2e46b6555 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -350,24 +350,6 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
return err;
}
-#ifdef CONFIG_NUMA
-int __weak memory_add_physaddr_to_nid(u64 start)
-{
- pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
- start);
- return 0;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-
-int __weak phys_to_target_node(u64 start)
-{
- pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
- start);
- return 0;
-}
-EXPORT_SYMBOL_GPL(phys_to_target_node);
-#endif
-
/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
unsigned long start_pfn,
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 3fde772ef5ef..3ca4898f3f24 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -525,7 +525,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long flags = qp->flags;
int ret;
bool has_unmovable = false;
- pte_t *pte;
+ pte_t *pte, *mapped_pte;
spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmd, vma);
@@ -539,7 +539,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
if (pmd_trans_unstable(pmd))
return 0;
- pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
@@ -571,7 +571,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
} else
break;
}
- pte_unmap_unlock(pte - 1, ptl);
+ pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
if (has_unmovable)
diff --git a/mm/memremap.c b/mm/memremap.c
index 73a206d0f645..16b2fb482da1 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -41,28 +41,24 @@ EXPORT_SYMBOL_GPL(memremap_compat_align);
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
- static_branch_dec(&devmap_managed_key);
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_dec(&devmap_managed_key);
}
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- if (pgmap->type == MEMORY_DEVICE_PRIVATE &&
- (!pgmap->ops || !pgmap->ops->page_free)) {
- WARN(1, "Missing page_free method\n");
- return -EINVAL;
- }
-
- static_branch_inc(&devmap_managed_key);
- return 0;
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_inc(&devmap_managed_key);
}
#else
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- return -EINVAL;
}
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
@@ -169,7 +165,7 @@ void memunmap_pages(struct dev_pagemap *pgmap)
pageunmap_range(pgmap, i);
WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
- devmap_managed_enable_put();
+ devmap_managed_enable_put(pgmap);
}
EXPORT_SYMBOL_GPL(memunmap_pages);
@@ -307,7 +303,6 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
.pgprot = PAGE_KERNEL,
};
const int nr_range = pgmap->nr_range;
- bool need_devmap_managed = true;
int error, i;
if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
@@ -323,6 +318,10 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
WARN(1, "Missing migrate_to_ram method\n");
return ERR_PTR(-EINVAL);
}
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
if (!pgmap->owner) {
WARN(1, "Missing owner\n");
return ERR_PTR(-EINVAL);
@@ -336,11 +335,9 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
}
break;
case MEMORY_DEVICE_GENERIC:
- need_devmap_managed = false;
break;
case MEMORY_DEVICE_PCI_P2PDMA:
params.pgprot = pgprot_noncached(params.pgprot);
- need_devmap_managed = false;
break;
default:
WARN(1, "Invalid pgmap type %d\n", pgmap->type);
@@ -364,11 +361,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
}
}
- if (need_devmap_managed) {
- error = devmap_managed_enable_get(pgmap);
- if (error)
- return ERR_PTR(error);
- }
+ devmap_managed_enable_get(pgmap);
/*
* Clear the pgmap nr_range as it will be incremented for each
diff --git a/mm/migrate.c b/mm/migrate.c
index 5ca5842df5db..5795cb82e27c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1328,34 +1328,38 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
goto put_anon;
if (page_mapped(hpage)) {
- /*
- * try_to_unmap could potentially call huge_pmd_unshare.
- * Because of this, take semaphore in write mode here and
- * set TTU_RMAP_LOCKED to let lower levels know we have
- * taken the lock.
- */
- mapping = hugetlb_page_mapping_lock_write(hpage);
- if (unlikely(!mapping))
- goto unlock_put_anon;
+ bool mapping_locked = false;
+ enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK|
+ TTU_IGNORE_ACCESS;
+
+ if (!PageAnon(hpage)) {
+ /*
+ * In shared mappings, try_to_unmap could potentially
+ * call huge_pmd_unshare. Because of this, take
+ * semaphore in write mode here and set TTU_RMAP_LOCKED
+ * to let lower levels know we have taken the lock.
+ */
+ mapping = hugetlb_page_mapping_lock_write(hpage);
+ if (unlikely(!mapping))
+ goto unlock_put_anon;
+
+ mapping_locked = true;
+ ttu |= TTU_RMAP_LOCKED;
+ }
- try_to_unmap(hpage,
- TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS|
- TTU_RMAP_LOCKED);
+ try_to_unmap(hpage, ttu);
page_was_mapped = 1;
- /*
- * Leave mapping locked until after subsequent call to
- * remove_migration_ptes()
- */
+
+ if (mapping_locked)
+ i_mmap_unlock_write(mapping);
}
if (!page_mapped(hpage))
rc = move_to_new_page(new_hpage, hpage, mode);
- if (page_was_mapped) {
+ if (page_was_mapped)
remove_migration_ptes(hpage,
- rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, true);
- i_mmap_unlock_write(mapping);
- }
+ rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false);
unlock_put_anon:
unlock_page(new_hpage);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7709f0e223f5..586042472ac9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2754,12 +2754,6 @@ int test_clear_page_writeback(struct page *page)
} else {
ret = TestClearPageWriteback(page);
}
- /*
- * NOTE: Page might be free now! Writeback doesn't hold a page
- * reference on its own, it relies on truncation to wait for
- * the clearing of PG_writeback. The below can only access
- * page state that is static across allocation cycles.
- */
if (ret) {
dec_lruvec_state(lruvec, NR_WRITEBACK);
dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 23f5066bd4a5..ad423950d01c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1092,7 +1092,7 @@ static inline bool page_expected_state(struct page *page,
if (unlikely((unsigned long)page->mapping |
page_ref_count(page) |
#ifdef CONFIG_MEMCG
- (unsigned long)page->mem_cgroup |
+ (unsigned long)page_memcg(page) |
#endif
(page->flags & check_flags)))
return false;
@@ -1117,7 +1117,7 @@ static const char *page_bad_reason(struct page *page, unsigned long flags)
bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
}
#ifdef CONFIG_MEMCG
- if (unlikely(page->mem_cgroup))
+ if (unlikely(page_memcg(page)))
bad_reason = "page still charged to cgroup";
#endif
return bad_reason;
@@ -1214,7 +1214,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
* Do not let hwpoison pages hit pcplists/buddy
* Untie memcg state and reset page's owner
*/
- if (memcg_kmem_enabled() && PageKmemcg(page))
+ if (memcg_kmem_enabled() && PageMemcgKmem(page))
__memcg_kmem_uncharge_page(page, order);
reset_page_owner(page, order);
return false;
@@ -1244,7 +1244,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
}
if (PageMappingFlags(page))
page->mapping = NULL;
- if (memcg_kmem_enabled() && PageKmemcg(page))
+ if (memcg_kmem_enabled() && PageMemcgKmem(page))
__memcg_kmem_uncharge_page(page, order);
if (check_free)
bad += check_free_page(page);
@@ -5103,6 +5103,11 @@ refill:
if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
goto refill;
+ if (unlikely(nc->pfmemalloc)) {
+ free_the_page(page, compound_order(page));
+ goto refill;
+ }
+
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
/* if size can vary use size else just use PAGE_SIZE */
size = nc->size;
diff --git a/mm/page_io.c b/mm/page_io.c
index 433df1263349..9bca17ecc4df 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -291,12 +291,14 @@ static inline void count_swpout_vm_event(struct page *page)
static void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
{
struct cgroup_subsys_state *css;
+ struct mem_cgroup *memcg;
- if (!page->mem_cgroup)
+ memcg = page_memcg(page);
+ if (!memcg)
return;
rcu_read_lock();
- css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys);
+ css = cgroup_e_css(memcg->css.cgroup, &io_cgrp_subsys);
bio_associate_blkg_from_css(bio, css);
rcu_read_unlock();
}
diff --git a/mm/percpu.c b/mm/percpu.c
index 66a93f096394..ad7a37ee74ef 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1315,8 +1315,8 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
region_size = ALIGN(start_offset + map_size, lcm_align);
/* allocate chunk */
- alloc_size = sizeof(struct pcpu_chunk) +
- BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long);
+ alloc_size = struct_size(chunk, populated,
+ BITS_TO_LONGS(region_size >> PAGE_SHIFT));
chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
if (!chunk)
panic("%s: Failed to allocate %zu bytes\n", __func__,
@@ -2521,8 +2521,8 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
pcpu_atom_size = ai->atom_size;
- pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
- BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
+ pcpu_chunk_struct_size = struct_size(chunk, populated,
+ BITS_TO_LONGS(pcpu_unit_pages));
pcpu_stats_save_ai(ai);
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index fd12da80b6f2..702250f148e7 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -5,6 +5,7 @@
* Copyright (C) 2010-2011 Christopher Yeoh <cyeoh@au1.ibm.com>, IBM Corp.
*/
+#include <linux/compat.h>
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/sched.h>
@@ -273,7 +274,8 @@ static ssize_t process_vm_rw(pid_t pid,
return rc;
if (!iov_iter_count(&iter))
goto free_iov_l;
- iov_r = iovec_from_user(rvec, riovcnt, UIO_FASTIOV, iovstack_r, false);
+ iov_r = iovec_from_user(rvec, riovcnt, UIO_FASTIOV, iovstack_r,
+ in_compat_syscall());
if (IS_ERR(iov_r)) {
rc = PTR_ERR(iov_r);
goto free_iov_l;
diff --git a/mm/rmap.c b/mm/rmap.c
index 1b84945d655c..31b29321adfe 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1413,9 +1413,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
/*
* If sharing is possible, start and end will be adjusted
* accordingly.
- *
- * If called for a huge page, caller must hold i_mmap_rwsem
- * in write mode as it is possible to call huge_pmd_unshare.
*/
adjust_range_if_pmd_sharing_possible(vma, &range.start,
&range.end);
@@ -1462,7 +1459,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
address = pvmw.address;
- if (PageHuge(page)) {
+ if (PageHuge(page) && !PageAnon(page)) {
/*
* To call huge_pmd_unshare, i_mmap_rwsem must be
* held in write mode. Caller needs to explicitly
diff --git a/mm/slab.h b/mm/slab.h
index 6d7c6a5056ba..9a54a0cb5cca 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -239,30 +239,13 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
}
#ifdef CONFIG_MEMCG_KMEM
-static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
-{
- /*
- * page->mem_cgroup and page->obj_cgroups are sharing the same
- * space. To distinguish between them in case we don't know for sure
- * that the page is a slab page (e.g. page_cgroup_ino()), let's
- * always set the lowest bit of obj_cgroups.
- */
- return (struct obj_cgroup **)
- ((unsigned long)page->obj_cgroups & ~0x1UL);
-}
-
-static inline bool page_has_obj_cgroups(struct page *page)
-{
- return ((unsigned long)page->obj_cgroups & 0x1UL);
-}
-
int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
gfp_t gfp);
static inline void memcg_free_page_obj_cgroups(struct page *page)
{
- kfree(page_obj_cgroups(page));
- page->obj_cgroups = NULL;
+ kfree(page_objcgs(page));
+ page->memcg_data = 0;
}
static inline size_t obj_full_size(struct kmem_cache *s)
@@ -323,7 +306,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
if (likely(p[i])) {
page = virt_to_head_page(p[i]);
- if (!page_has_obj_cgroups(page) &&
+ if (!page_objcgs(page) &&
memcg_alloc_page_obj_cgroups(page, s, flags)) {
obj_cgroup_uncharge(objcg, obj_full_size(s));
continue;
@@ -331,7 +314,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
off = obj_to_index(s, page, p[i]);
obj_cgroup_get(objcg);
- page_obj_cgroups(page)[off] = objcg;
+ page_objcgs(page)[off] = objcg;
mod_objcg_state(objcg, page_pgdat(page),
cache_vmstat_idx(s), obj_full_size(s));
} else {
@@ -345,6 +328,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
void **p, int objects)
{
struct kmem_cache *s;
+ struct obj_cgroup **objcgs;
struct obj_cgroup *objcg;
struct page *page;
unsigned int off;
@@ -358,7 +342,8 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
continue;
page = virt_to_head_page(p[i]);
- if (!page_has_obj_cgroups(page))
+ objcgs = page_objcgs(page);
+ if (!objcgs)
continue;
if (!s_orig)
@@ -367,11 +352,11 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
s = s_orig;
off = obj_to_index(s, page, p[i]);
- objcg = page_obj_cgroups(page)[off];
+ objcg = objcgs[off];
if (!objcg)
continue;
- page_obj_cgroups(page)[off] = NULL;
+ objcgs[off] = NULL;
obj_cgroup_uncharge(objcg, obj_full_size(s));
mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
-obj_full_size(s));
@@ -380,11 +365,6 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
}
#else /* CONFIG_MEMCG_KMEM */
-static inline bool page_has_obj_cgroups(struct page *page)
-{
- return false;
-}
-
static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
{
return NULL;
diff --git a/mm/slub.c b/mm/slub.c
index b30be2385d1c..34dcc09e2ec9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2852,7 +2852,7 @@ redo:
object = c->freelist;
page = c->page;
- if (unlikely(!object || !node_match(page, node))) {
+ if (unlikely(!object || !page || !node_match(page, node))) {
object = __slab_alloc(s, gfpflags, node, addr, c);
} else {
void *next_object = get_freepointer_safe(s, object);
diff --git a/mm/truncate.c b/mm/truncate.c
index 18cec39a9f53..960edf5803ca 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -528,7 +528,7 @@ void truncate_inode_pages_final(struct address_space *mapping)
}
EXPORT_SYMBOL(truncate_inode_pages_final);
-unsigned long __invalidate_mapping_pages(struct address_space *mapping,
+static unsigned long __invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
{
pgoff_t indices[PAGEVEC_SIZE];
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1b8f0e059767..7b4e31eac2cf 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1516,7 +1516,8 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
TTU_IGNORE_ACCESS, &stat, true);
list_splice(&clean_pages, page_list);
- mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -nr_reclaimed);
+ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
+ -(long)nr_reclaimed);
/*
* Since lazyfree pages are isolated from file LRU from the beginning,
* they will rotate back to anonymous LRU in the end if it failed to
@@ -1526,7 +1527,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
stat.nr_lazyfree_fail);
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
- -stat.nr_lazyfree_fail);
+ -(long)stat.nr_lazyfree_fail);
return nr_reclaimed;
}
diff --git a/mm/workingset.c b/mm/workingset.c
index 975a4d2dd02e..130348cbf40a 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -257,7 +257,7 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
struct lruvec *lruvec;
int memcgid;
- /* Page is fully exclusive and pins page->mem_cgroup */
+ /* Page is fully exclusive and pins page's memory cgroup pointer */
VM_BUG_ON_PAGE(PageLRU(page), page);
VM_BUG_ON_PAGE(page_count(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
generated by cgit v1.2.3 (git 2.39.1) at 2025-02-04 14:40:57 +0100