Commit 3fea5a49 authored by Johannes Weiner's avatar Johannes Weiner Committed by Linus Torvalds

mm: memcontrol: convert page cache to a new mem_cgroup_charge() API

The try/commit/cancel protocol that memcg uses dates back to when pages
used to be uncharged upon removal from the page cache, and thus couldn't
be committed before the insertion had succeeded.  Nowadays, pages are
uncharged when they are physically freed; it doesn't matter whether the
insertion was successful or not.  For the page cache, the transaction
dance has become unnecessary.

Introduce a mem_cgroup_charge() function that simply charges a newly
allocated page to a cgroup and sets up page->mem_cgroup in one single
step.  If the insertion fails, the caller doesn't have to do anything but
free/put the page.

Then switch the page cache over to this new API.

Subsequent patches will also convert anon pages, but it needs a bit more
prep work.  Right now, memcg depends on page->mapping being already set up
at the time of charging, so that it can maintain its own MEMCG_CACHE and
MEMCG_RSS counters.  For anon, page->mapping is set under the same pte
lock under which the page is publishd, so a single charge point that can
block doesn't work there just yet.

The following prep patches will replace the private memcg counters with
the generic vmstat counters, thus removing the page->mapping dependency,
then complete the transition to the new single-point charge API and delete
the old transactional scheme.

v2: leave shmem swapcache when charging fails to avoid double IO (Joonsoo)
v3: rebase on preceeding shmem simplification patch
Signed-off-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Reviewed-by: default avatarAlex Shi <alex.shi@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Link: http://lkml.kernel.org/r/20200508183105.225460-6-hannes@cmpxchg.orgSigned-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 6caa6a07
...@@ -365,6 +365,10 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, ...@@ -365,6 +365,10 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
bool lrucare); bool lrucare);
void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg);
int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask,
bool lrucare);
void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge(struct page *page);
void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_uncharge_list(struct list_head *page_list);
...@@ -872,6 +876,12 @@ static inline void mem_cgroup_cancel_charge(struct page *page, ...@@ -872,6 +876,12 @@ static inline void mem_cgroup_cancel_charge(struct page *page,
{ {
} }
static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask, bool lrucare)
{
return 0;
}
static inline void mem_cgroup_uncharge(struct page *page) static inline void mem_cgroup_uncharge(struct page *page)
{ {
} }
......
...@@ -832,7 +832,6 @@ static int __add_to_page_cache_locked(struct page *page, ...@@ -832,7 +832,6 @@ static int __add_to_page_cache_locked(struct page *page,
{ {
XA_STATE(xas, &mapping->i_pages, offset); XA_STATE(xas, &mapping->i_pages, offset);
int huge = PageHuge(page); int huge = PageHuge(page);
struct mem_cgroup *memcg;
int error; int error;
void *old; void *old;
...@@ -840,17 +839,16 @@ static int __add_to_page_cache_locked(struct page *page, ...@@ -840,17 +839,16 @@ static int __add_to_page_cache_locked(struct page *page,
VM_BUG_ON_PAGE(PageSwapBacked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page);
mapping_set_update(&xas, mapping); mapping_set_update(&xas, mapping);
if (!huge) {
error = mem_cgroup_try_charge(page, current->mm,
gfp_mask, &memcg);
if (error)
return error;
}
get_page(page); get_page(page);
page->mapping = mapping; page->mapping = mapping;
page->index = offset; page->index = offset;
if (!huge) {
error = mem_cgroup_charge(page, current->mm, gfp_mask, false);
if (error)
goto error;
}
do { do {
xas_lock_irq(&xas); xas_lock_irq(&xas);
old = xas_load(&xas); old = xas_load(&xas);
...@@ -874,20 +872,18 @@ static int __add_to_page_cache_locked(struct page *page, ...@@ -874,20 +872,18 @@ static int __add_to_page_cache_locked(struct page *page,
xas_unlock_irq(&xas); xas_unlock_irq(&xas);
} while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK)); } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK));
if (xas_error(&xas)) if (xas_error(&xas)) {
error = xas_error(&xas);
goto error; goto error;
}
if (!huge)
mem_cgroup_commit_charge(page, memcg, false);
trace_mm_filemap_add_to_page_cache(page); trace_mm_filemap_add_to_page_cache(page);
return 0; return 0;
error: error:
page->mapping = NULL; page->mapping = NULL;
/* Leave page->index set: truncation relies upon it */ /* Leave page->index set: truncation relies upon it */
if (!huge)
mem_cgroup_cancel_charge(page, memcg);
put_page(page); put_page(page);
return xas_error(&xas); return error;
} }
ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
......
...@@ -6637,6 +6637,33 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) ...@@ -6637,6 +6637,33 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg)
cancel_charge(memcg, nr_pages); cancel_charge(memcg, nr_pages);
} }
/**
* mem_cgroup_charge - charge a newly allocated page to a cgroup
* @page: page to charge
* @mm: mm context of the victim
* @gfp_mask: reclaim mode
* @lrucare: page might be on the LRU already
*
* Try to charge @page to the memcg that @mm belongs to, reclaiming
* pages according to @gfp_mask if necessary.
*
* Returns 0 on success. Otherwise, an error code is returned.
*/
int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask,
bool lrucare)
{
struct mem_cgroup *memcg;
int ret;
VM_BUG_ON_PAGE(!page->mapping, page);
ret = mem_cgroup_try_charge(page, mm, gfp_mask, &memcg);
if (ret)
return ret;
mem_cgroup_commit_charge(page, memcg, lrucare);
return 0;
}
struct uncharge_gather { struct uncharge_gather {
struct mem_cgroup *memcg; struct mem_cgroup *memcg;
unsigned long pgpgout; unsigned long pgpgout;
...@@ -6684,8 +6711,6 @@ static void uncharge_batch(const struct uncharge_gather *ug) ...@@ -6684,8 +6711,6 @@ static void uncharge_batch(const struct uncharge_gather *ug)
static void uncharge_page(struct page *page, struct uncharge_gather *ug) static void uncharge_page(struct page *page, struct uncharge_gather *ug)
{ {
VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(PageLRU(page), page);
VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) &&
!PageHWPoison(page) , page);
if (!page->mem_cgroup) if (!page->mem_cgroup)
return; return;
......
...@@ -605,11 +605,13 @@ static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo) ...@@ -605,11 +605,13 @@ static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo)
*/ */
static int shmem_add_to_page_cache(struct page *page, static int shmem_add_to_page_cache(struct page *page,
struct address_space *mapping, struct address_space *mapping,
pgoff_t index, void *expected, gfp_t gfp) pgoff_t index, void *expected, gfp_t gfp,
struct mm_struct *charge_mm)
{ {
XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page));
unsigned long i = 0; unsigned long i = 0;
unsigned long nr = compound_nr(page); unsigned long nr = compound_nr(page);
int error;
VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(index != round_down(index, nr), page); VM_BUG_ON_PAGE(index != round_down(index, nr), page);
...@@ -621,6 +623,16 @@ static int shmem_add_to_page_cache(struct page *page, ...@@ -621,6 +623,16 @@ static int shmem_add_to_page_cache(struct page *page,
page->mapping = mapping; page->mapping = mapping;
page->index = index; page->index = index;
error = mem_cgroup_charge(page, charge_mm, gfp, PageSwapCache(page));
if (error) {
if (!PageSwapCache(page) && PageTransHuge(page)) {
count_vm_event(THP_FILE_FALLBACK);
count_vm_event(THP_FILE_FALLBACK_CHARGE);
}
goto error;
}
cgroup_throttle_swaprate(page, gfp);
do { do {
void *entry; void *entry;
xas_lock_irq(&xas); xas_lock_irq(&xas);
...@@ -648,12 +660,15 @@ static int shmem_add_to_page_cache(struct page *page, ...@@ -648,12 +660,15 @@ static int shmem_add_to_page_cache(struct page *page,
} while (xas_nomem(&xas, gfp)); } while (xas_nomem(&xas, gfp));
if (xas_error(&xas)) { if (xas_error(&xas)) {
page->mapping = NULL; error = xas_error(&xas);
page_ref_sub(page, nr); goto error;
return xas_error(&xas);
} }
return 0; return 0;
error:
page->mapping = NULL;
page_ref_sub(page, nr);
return error;
} }
/* /*
...@@ -1619,7 +1634,6 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, ...@@ -1619,7 +1634,6 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
struct address_space *mapping = inode->i_mapping; struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_inode_info *info = SHMEM_I(inode);
struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm; struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm;
struct mem_cgroup *memcg;
struct page *page; struct page *page;
swp_entry_t swap; swp_entry_t swap;
int error; int error;
...@@ -1664,18 +1678,11 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, ...@@ -1664,18 +1678,11 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
goto failed; goto failed;
} }
error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg);
if (error)
goto failed;
error = shmem_add_to_page_cache(page, mapping, index, error = shmem_add_to_page_cache(page, mapping, index,
swp_to_radix_entry(swap), gfp); swp_to_radix_entry(swap), gfp,
if (error) { charge_mm);
mem_cgroup_cancel_charge(page, memcg); if (error)
goto failed; goto failed;
}
mem_cgroup_commit_charge(page, memcg, true);
spin_lock_irq(&info->lock); spin_lock_irq(&info->lock);
info->swapped--; info->swapped--;
...@@ -1722,7 +1729,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, ...@@ -1722,7 +1729,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo; struct shmem_sb_info *sbinfo;
struct mm_struct *charge_mm; struct mm_struct *charge_mm;
struct mem_cgroup *memcg;
struct page *page; struct page *page;
enum sgp_type sgp_huge = sgp; enum sgp_type sgp_huge = sgp;
pgoff_t hindex = index; pgoff_t hindex = index;
...@@ -1847,21 +1853,11 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, ...@@ -1847,21 +1853,11 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
if (sgp == SGP_WRITE) if (sgp == SGP_WRITE)
__SetPageReferenced(page); __SetPageReferenced(page);
error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg);
if (error) {
if (PageTransHuge(page)) {
count_vm_event(THP_FILE_FALLBACK);
count_vm_event(THP_FILE_FALLBACK_CHARGE);
}
goto unacct;
}
error = shmem_add_to_page_cache(page, mapping, hindex, error = shmem_add_to_page_cache(page, mapping, hindex,
NULL, gfp & GFP_RECLAIM_MASK); NULL, gfp & GFP_RECLAIM_MASK,
if (error) { charge_mm);
mem_cgroup_cancel_charge(page, memcg); if (error)
goto unacct; goto unacct;
}
mem_cgroup_commit_charge(page, memcg, false);
lru_cache_add_anon(page); lru_cache_add_anon(page);
spin_lock_irq(&info->lock); spin_lock_irq(&info->lock);
...@@ -2299,7 +2295,6 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, ...@@ -2299,7 +2295,6 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
struct address_space *mapping = inode->i_mapping; struct address_space *mapping = inode->i_mapping;
gfp_t gfp = mapping_gfp_mask(mapping); gfp_t gfp = mapping_gfp_mask(mapping);
pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
struct mem_cgroup *memcg;
spinlock_t *ptl; spinlock_t *ptl;
void *page_kaddr; void *page_kaddr;
struct page *page; struct page *page;
...@@ -2349,16 +2344,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, ...@@ -2349,16 +2344,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
if (unlikely(offset >= max_off)) if (unlikely(offset >= max_off))
goto out_release; goto out_release;
ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg);
if (ret)
goto out_release;
ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL,
gfp & GFP_RECLAIM_MASK); gfp & GFP_RECLAIM_MASK, dst_mm);
if (ret) if (ret)
goto out_release_uncharge; goto out_release;
mem_cgroup_commit_charge(page, memcg, false);
_dst_pte = mk_pte(page, dst_vma->vm_page_prot); _dst_pte = mk_pte(page, dst_vma->vm_page_prot);
if (dst_vma->vm_flags & VM_WRITE) if (dst_vma->vm_flags & VM_WRITE)
...@@ -2379,11 +2368,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, ...@@ -2379,11 +2368,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
ret = -EFAULT; ret = -EFAULT;
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(offset >= max_off)) if (unlikely(offset >= max_off))
goto out_release_uncharge_unlock; goto out_release_unlock;
ret = -EEXIST; ret = -EEXIST;
if (!pte_none(*dst_pte)) if (!pte_none(*dst_pte))
goto out_release_uncharge_unlock; goto out_release_unlock;
lru_cache_add_anon(page); lru_cache_add_anon(page);
...@@ -2404,12 +2393,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, ...@@ -2404,12 +2393,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
ret = 0; ret = 0;
out: out:
return ret; return ret;
out_release_uncharge_unlock: out_release_unlock:
pte_unmap_unlock(dst_pte, ptl); pte_unmap_unlock(dst_pte, ptl);
ClearPageDirty(page); ClearPageDirty(page);
delete_from_page_cache(page); delete_from_page_cache(page);
out_release_uncharge:
mem_cgroup_cancel_charge(page, memcg);
out_release: out_release:
unlock_page(page); unlock_page(page);
put_page(page); put_page(page);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment