mm: memcontrol: convert anon and file-thp to new mem_cgroup_charge() API

With the page->mapping requirement gone from memcg, we can charge anon and
file-thp pages in one single step, right after they're allocated.

This removes two out of three API calls - especially the tricky commit
step that needed to happen at just the right time between when the page is
"set up" and when it's "published" - somewhat vague and fluid concepts
that varied by page type.  All we need is a freshly allocated page and a
memcg context to charge.

v2: prevent double charges on pre-allocated hugepages in khugepaged

[[email protected]: Fix crash - *hpage could be ERR_PTR instead of NULL]
  Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Johannes Weiner <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Reviewed-by: Joonsoo Kim <[email protected]>
Cc: Alex Shi <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Roman Gushchin <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Balbir Singh <[email protected]>
Cc: Qian Cai <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>

Author: hnaz

include/linux/mm.h

@@ -501,7 +501,6 @@ struct vm_fault {
 	pte_t orig_pte;			/* Value of PTE at the time of fault */
 
 	struct page *cow_page;		/* Page handler may use for COW fault */
-	struct mem_cgroup *memcg;	/* Cgroup cow_page belongs to */
 	struct page *page;		/* ->fault handlers should return a
 					 * page here, unless VM_FAULT_NOPAGE
 					 * is set (which is also implied by
@@ -946,8 +945,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 	return pte;
 }
 
-vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
-		struct page *page);
+vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page);
 vm_fault_t finish_fault(struct vm_fault *vmf);
 vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
 #endif

kernel/events/uprobes.c

@@ -162,14 +162,13 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	};
 	int err;
 	struct mmu_notifier_range range;
-	struct mem_cgroup *memcg;
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr,
 				addr + PAGE_SIZE);
 
 	if (new_page) {
-		err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL,
-					    &memcg);
+		err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL,
+					false);
 		if (err)
 			return err;
 	}
@@ -179,16 +178,12 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	mmu_notifier_invalidate_range_start(&range);
 	err = -EAGAIN;
-	if (!page_vma_mapped_walk(&pvmw)) {
-		if (new_page)
-			mem_cgroup_cancel_charge(new_page, memcg);
+	if (!page_vma_mapped_walk(&pvmw))
 		goto unlock;
-	}
 	VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
 
 	if (new_page) {
 		get_page(new_page);
-		mem_cgroup_commit_charge(new_page, memcg, false);
 		page_add_new_anon_rmap(new_page, vma, addr, false);
 		lru_cache_add_active_or_unevictable(new_page, vma);
 	} else

mm/filemap.c

@@ -2633,7 +2633,7 @@ void filemap_map_pages(struct vm_fault *vmf,
 		if (vmf->pte)
 			vmf->pte += xas.xa_index - last_pgoff;
 		last_pgoff = xas.xa_index;
-		if (alloc_set_pte(vmf, NULL, page))
+		if (alloc_set_pte(vmf, page))
 			goto unlock;
 		unlock_page(page);
 		goto next;

mm/huge_memory.c

@@ -587,19 +587,19 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 			struct page *page, gfp_t gfp)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct mem_cgroup *memcg;
 	pgtable_t pgtable;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	vm_fault_t ret = 0;
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg)) {
+	if (mem_cgroup_charge(page, vma->vm_mm, gfp, false)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		return VM_FAULT_FALLBACK;
 	}
+	cgroup_throttle_swaprate(page, gfp);
 
 	pgtable = pte_alloc_one(vma->vm_mm);
 	if (unlikely(!pgtable)) {
@@ -630,7 +630,6 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 			vm_fault_t ret2;
 
 			spin_unlock(vmf->ptl);
-			mem_cgroup_cancel_charge(page, memcg);
 			put_page(page);
 			pte_free(vma->vm_mm, pgtable);
 			ret2 = handle_userfault(vmf, VM_UFFD_MISSING);
@@ -640,7 +639,6 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		mem_cgroup_commit_charge(page, memcg, false);
 		page_add_new_anon_rmap(page, vma, haddr, true);
 		lru_cache_add_active_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
@@ -649,7 +647,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		mm_inc_nr_ptes(vma->vm_mm);
 		spin_unlock(vmf->ptl);
 		count_vm_event(THP_FAULT_ALLOC);
-		count_memcg_events(memcg, THP_FAULT_ALLOC, 1);
+		count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
 	}
 
 	return 0;
@@ -658,7 +656,6 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 release:
 	if (pgtable)
 		pte_free(vma->vm_mm, pgtable);
-	mem_cgroup_cancel_charge(page, memcg);
 	put_page(page);
 	return ret;
 

mm/khugepaged.c

@@ -1037,7 +1037,6 @@ static void collapse_huge_page(struct mm_struct *mm,
 	struct page *new_page;
 	spinlock_t *pmd_ptl, *pte_ptl;
 	int isolated = 0, result = 0;
-	struct mem_cgroup *memcg;
 	struct vm_area_struct *vma;
 	struct mmu_notifier_range range;
 	gfp_t gfp;
@@ -1060,23 +1059,22 @@ static void collapse_huge_page(struct mm_struct *mm,
 		goto out_nolock;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) {
+	if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out_nolock;
 	}
+	count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
 
 	down_read(&mm->mmap_sem);
 	result = hugepage_vma_revalidate(mm, address, &vma);
 	if (result) {
-		mem_cgroup_cancel_charge(new_page, memcg);
 		up_read(&mm->mmap_sem);
 		goto out_nolock;
 	}
 
 	pmd = mm_find_pmd(mm, address);
 	if (!pmd) {
 		result = SCAN_PMD_NULL;
-		mem_cgroup_cancel_charge(new_page, memcg);
 		up_read(&mm->mmap_sem);
 		goto out_nolock;
 	}
@@ -1088,7 +1086,6 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 */
 	if (unmapped && !__collapse_huge_page_swapin(mm, vma, address,
 						     pmd, referenced)) {
-		mem_cgroup_cancel_charge(new_page, memcg);
 		up_read(&mm->mmap_sem);
 		goto out_nolock;
 	}
@@ -1175,9 +1172,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 
 	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
-	mem_cgroup_commit_charge(new_page, memcg, false);
 	page_add_new_anon_rmap(new_page, vma, address, true);
-	count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1);
 	lru_cache_add_active_or_unevictable(new_page, vma);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
@@ -1191,10 +1186,11 @@ static void collapse_huge_page(struct mm_struct *mm,
 out_up_write:
 	up_write(&mm->mmap_sem);
 out_nolock:
+	if (!IS_ERR_OR_NULL(*hpage))
+		mem_cgroup_uncharge(*hpage);
 	trace_mm_collapse_huge_page(mm, isolated, result);
 	return;
 out:
-	mem_cgroup_cancel_charge(new_page, memcg);
 	goto out_up_write;
 }
 
@@ -1618,7 +1614,6 @@ static void collapse_file(struct mm_struct *mm,
 	struct address_space *mapping = file->f_mapping;
 	gfp_t gfp;
 	struct page *new_page;
-	struct mem_cgroup *memcg;
 	pgoff_t index, end = start + HPAGE_PMD_NR;
 	LIST_HEAD(pagelist);
 	XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
@@ -1637,10 +1632,11 @@ static void collapse_file(struct mm_struct *mm,
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) {
+	if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out;
 	}
+	count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
 
 	/* This will be less messy when we use multi-index entries */
 	do {
@@ -1650,7 +1646,6 @@ static void collapse_file(struct mm_struct *mm,
 			break;
 		xas_unlock_irq(&xas);
 		if (!xas_nomem(&xas, GFP_KERNEL)) {
-			mem_cgroup_cancel_charge(new_page, memcg);
 			result = SCAN_FAIL;
 			goto out;
 		}
@@ -1844,18 +1839,9 @@ static void collapse_file(struct mm_struct *mm,
 	}
 
 	if (nr_none) {
-		struct lruvec *lruvec;
-		/*
-		 * XXX: We have started try_charge and pinned the
-		 * memcg, but the page isn't committed yet so we
-		 * cannot use mod_lruvec_page_state(). This hackery
-		 * will be cleaned up when remove the page->mapping
-		 * dependency from memcg and fully charge above.
-		 */
-		lruvec = mem_cgroup_lruvec(memcg, page_pgdat(new_page));
-		__mod_lruvec_state(lruvec, NR_FILE_PAGES, nr_none);
+		__mod_lruvec_page_state(new_page, NR_FILE_PAGES, nr_none);
 		if (is_shmem)
-			__mod_lruvec_state(lruvec, NR_SHMEM, nr_none);
+			__mod_lruvec_page_state(new_page, NR_SHMEM, nr_none);
 	}
 
 xa_locked:
@@ -1893,15 +1879,13 @@ static void collapse_file(struct mm_struct *mm,
 
 		SetPageUptodate(new_page);
 		page_ref_add(new_page, HPAGE_PMD_NR - 1);
-		mem_cgroup_commit_charge(new_page, memcg, false);
 
 		if (is_shmem) {
 			set_page_dirty(new_page);
 			lru_cache_add_anon(new_page);
 		} else {
 			lru_cache_add_file(new_page);
 		}
-		count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1);
 
 		/*
 		 * Remove pte page tables, so we can re-fault the page as huge.
@@ -1948,13 +1932,14 @@ static void collapse_file(struct mm_struct *mm,
 		VM_BUG_ON(nr_none);
 		xas_unlock_irq(&xas);
 
-		mem_cgroup_cancel_charge(new_page, memcg);
 		new_page->mapping = NULL;
 	}
 
 	unlock_page(new_page);
 out:
 	VM_BUG_ON(!list_empty(&pagelist));
+	if (!IS_ERR_OR_NULL(*hpage))
+		mem_cgroup_uncharge(*hpage);
 	/* TODO: tracepoints */
 }