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: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Alex 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.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 30 insertions, 43 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 729bbb3513cd..0d9615723152 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -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,
 				   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));
 	unsigned long i = 0;
 	unsigned long nr = compound_nr(page);
+	int error;
 
 	VM_BUG_ON_PAGE(PageTail(page), 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,
 	page->mapping = mapping;
 	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 {
 		void *entry;
 		xas_lock_irq(&xas);
@@ -648,12 +660,15 @@ unlock:
 	} while (xas_nomem(&xas, gfp));
 
 	if (xas_error(&xas)) {
-		page->mapping = NULL;
-		page_ref_sub(page, nr);
-		return xas_error(&xas);
+		error = xas_error(&xas);
+		goto error;
 	}
 
 	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,
 	struct address_space *mapping = inode->i_mapping;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm;
-	struct mem_cgroup *memcg;
 	struct page *page;
 	swp_entry_t swap;
 	int error;
@@ -1664,18 +1678,11 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 			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,
-					swp_to_radix_entry(swap), gfp);
-	if (error) {
-		mem_cgroup_cancel_charge(page, memcg);
+					swp_to_radix_entry(swap), gfp,
+					charge_mm);
+	if (error)
 		goto failed;
-	}
-
-	mem_cgroup_commit_charge(page, memcg, true);
 
 	spin_lock_irq(&info->lock);
 	info->swapped--;
@@ -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_sb_info *sbinfo;
 	struct mm_struct *charge_mm;
-	struct mem_cgroup *memcg;
 	struct page *page;
 	enum sgp_type sgp_huge = sgp;
 	pgoff_t hindex = index;
@@ -1847,21 +1853,11 @@ alloc_nohuge:
 	if (sgp == SGP_WRITE)
 		__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,
-					NULL, gfp & GFP_RECLAIM_MASK);
-	if (error) {
-		mem_cgroup_cancel_charge(page, memcg);
+					NULL, gfp & GFP_RECLAIM_MASK,
+					charge_mm);
+	if (error)
 		goto unacct;
-	}
-	mem_cgroup_commit_charge(page, memcg, false);
 	lru_cache_add_anon(page);
 
 	spin_lock_irq(&info->lock);
@@ -2299,7 +2295,6 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	struct address_space *mapping = inode->i_mapping;
 	gfp_t gfp = mapping_gfp_mask(mapping);
 	pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
-	struct mem_cgroup *memcg;
 	spinlock_t *ptl;
 	void *page_kaddr;
 	struct page *page;
@@ -2349,16 +2344,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	if (unlikely(offset >= max_off))
 		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,
-						gfp & GFP_RECLAIM_MASK);
+				      gfp & GFP_RECLAIM_MASK, dst_mm);
 	if (ret)
-		goto out_release_uncharge;
-
-	mem_cgroup_commit_charge(page, memcg, false);
+		goto out_release;
 
 	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
 	if (dst_vma->vm_flags & VM_WRITE)
@@ -2379,11 +2368,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	ret = -EFAULT;
 	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 	if (unlikely(offset >= max_off))
-		goto out_release_uncharge_unlock;
+		goto out_release_unlock;
 
 	ret = -EEXIST;
 	if (!pte_none(*dst_pte))
-		goto out_release_uncharge_unlock;
+		goto out_release_unlock;
 
 	lru_cache_add_anon(page);
 
@@ -2404,12 +2393,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	ret = 0;
 out:
 	return ret;
-out_release_uncharge_unlock:
+out_release_unlock:
 	pte_unmap_unlock(dst_pte, ptl);
 	ClearPageDirty(page);
 	delete_from_page_cache(page);
-out_release_uncharge:
-	mem_cgroup_cancel_charge(page, memcg);
 out_release:
 	unlock_page(page);
 	put_page(page);