memcg: adjust to support new THP refcounting

As with rmap, with new refcounting we cannot rely on PageTransHuge() to
check if we need to charge size of huge page form the cgroup.  We need
to get information from caller to know whether it was mapped with PMD or
PTE.

We do uncharge when last reference on the page gone.  At that point if
we see PageTransHuge() it means we need to unchange whole huge page.

The tricky part is partial unmap -- when we try to unmap part of huge
page.  We don't do a special handing of this situation, meaning we don't
uncharge the part of huge page unless last user is gone or
split_huge_page() is triggered.  In case of cgroup memory pressure
happens the partial unmapped page will be split through shrinker.  This
should be good enough.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 17 insertions, 15 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b7669cfe9dc9..4211682f223b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -751,7 +751,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, mm, gfp, &memcg)) {
+	if (mem_cgroup_try_charge(page, mm, gfp, &memcg, true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -759,7 +759,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 
 	pgtable = pte_alloc_one(mm, haddr);
 	if (unlikely(!pgtable)) {
-		mem_cgroup_cancel_charge(page, memcg);
+		mem_cgroup_cancel_charge(page, memcg, true);
 		put_page(page);
 		return VM_FAULT_OOM;
 	}
@@ -775,7 +775,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_none(*pmd))) {
 		spin_unlock(ptl);
-		mem_cgroup_cancel_charge(page, memcg);
+		mem_cgroup_cancel_charge(page, memcg, true);
 		put_page(page);
 		pte_free(mm, pgtable);
 	} else {
@@ -786,7 +786,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 			int ret;
 
 			spin_unlock(ptl);
-			mem_cgroup_cancel_charge(page, memcg);
+			mem_cgroup_cancel_charge(page, memcg, true);
 			put_page(page);
 			pte_free(mm, pgtable);
 			ret = handle_userfault(vma, address, flags,
@@ -798,7 +798,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		page_add_new_anon_rmap(page, vma, haddr, true);
-		mem_cgroup_commit_charge(page, memcg, false);
+		mem_cgroup_commit_charge(page, memcg, false, true);
 		lru_cache_add_active_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		set_pmd_at(mm, haddr, pmd, entry);
@@ -1095,13 +1095,14 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					       vma, address, page_to_nid(page));
 		if (unlikely(!pages[i] ||
 			     mem_cgroup_try_charge(pages[i], mm, GFP_KERNEL,
-						   &memcg))) {
+						   &memcg, false))) {
 			if (pages[i])
 				put_page(pages[i]);
 			while (--i >= 0) {
 				memcg = (void *)page_private(pages[i]);
 				set_page_private(pages[i], 0);
-				mem_cgroup_cancel_charge(pages[i], memcg);
+				mem_cgroup_cancel_charge(pages[i], memcg,
+						false);
 				put_page(pages[i]);
 			}
 			kfree(pages);
@@ -1140,7 +1141,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 		memcg = (void *)page_private(pages[i]);
 		set_page_private(pages[i], 0);
 		page_add_new_anon_rmap(pages[i], vma, haddr, false);
-		mem_cgroup_commit_charge(pages[i], memcg, false);
+		mem_cgroup_commit_charge(pages[i], memcg, false, false);
 		lru_cache_add_active_or_unevictable(pages[i], vma);
 		pte = pte_offset_map(&_pmd, haddr);
 		VM_BUG_ON(!pte_none(*pte));
@@ -1168,7 +1169,7 @@ out_free_pages:
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		memcg = (void *)page_private(pages[i]);
 		set_page_private(pages[i], 0);
-		mem_cgroup_cancel_charge(pages[i], memcg);
+		mem_cgroup_cancel_charge(pages[i], memcg, false);
 		put_page(pages[i]);
 	}
 	kfree(pages);
@@ -1234,7 +1235,8 @@ alloc:
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg))) {
+	if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg,
+					   true))) {
 		put_page(new_page);
 		if (page) {
 			split_huge_page(page);
@@ -1263,7 +1265,7 @@ alloc:
 		put_user_huge_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
 		spin_unlock(ptl);
-		mem_cgroup_cancel_charge(new_page, memcg);
+		mem_cgroup_cancel_charge(new_page, memcg, true);
 		put_page(new_page);
 		goto out_mn;
 	} else {
@@ -1272,7 +1274,7 @@ alloc:
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		pmdp_huge_clear_flush_notify(vma, haddr, pmd);
 		page_add_new_anon_rmap(new_page, vma, haddr, true);
-		mem_cgroup_commit_charge(new_page, memcg, false);
+		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_active_or_unevictable(new_page, vma);
 		set_pmd_at(mm, haddr, pmd, entry);
 		update_mmu_cache_pmd(vma, address, pmd);
@@ -2583,7 +2585,7 @@ 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_try_charge(new_page, mm, gfp, &memcg, true))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out_nolock;
 	}
@@ -2683,7 +2685,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
 	page_add_new_anon_rmap(new_page, vma, address, true);
-	mem_cgroup_commit_charge(new_page, memcg, false);
+	mem_cgroup_commit_charge(new_page, memcg, false, true);
 	lru_cache_add_active_or_unevictable(new_page, vma);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
@@ -2703,7 +2705,7 @@ out_nolock:
 	trace_mm_collapse_huge_page(mm, isolated, result);
 	return;
 out:
-	mem_cgroup_cancel_charge(new_page, memcg);
+	mem_cgroup_cancel_charge(new_page, memcg, true);
 	goto out_up_write;
 }