Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Just several instances of overlapping changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 132 insertions, 90 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 79bfe0e..7bc0477 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1009,8 +1009,6 @@ static void isolate_freepages(struct compact_control *cc)
 				block_end_pfn = block_start_pfn,
 				block_start_pfn -= pageblock_nr_pages,
 				isolate_start_pfn = block_start_pfn) {
-		unsigned long isolated;
-
 		/*
 		 * This can iterate a massively long zone without finding any
 		 * suitable migration targets, so periodically check if we need
@@ -1034,36 +1032,30 @@ static void isolate_freepages(struct compact_control *cc)
 			continue;
 
 		/* Found a block suitable for isolating free pages from. */
-		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
-						block_end_pfn, freelist, false);
-		/* If isolation failed early, do not continue needlessly */
-		if (!isolated && isolate_start_pfn < block_end_pfn &&
-		    cc->nr_migratepages > cc->nr_freepages)
-			break;
+		isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn,
+					freelist, false);
 
 		/*
-		 * If we isolated enough freepages, or aborted due to async
-		 * compaction being contended, terminate the loop.
-		 * Remember where the free scanner should restart next time,
-		 * which is where isolate_freepages_block() left off.
-		 * But if it scanned the whole pageblock, isolate_start_pfn
-		 * now points at block_end_pfn, which is the start of the next
-		 * pageblock.
-		 * In that case we will however want to restart at the start
-		 * of the previous pageblock.
+		 * If we isolated enough freepages, or aborted due to lock
+		 * contention, terminate.
 		 */
 		if ((cc->nr_freepages >= cc->nr_migratepages)
 							|| cc->contended) {
-			if (isolate_start_pfn >= block_end_pfn)
+			if (isolate_start_pfn >= block_end_pfn) {
+				/*
+				 * Restart at previous pageblock if more
+				 * freepages can be isolated next time.
+				 */
 				isolate_start_pfn =
 					block_start_pfn - pageblock_nr_pages;
+			}
 			break;
-		} else {
+		} else if (isolate_start_pfn < block_end_pfn) {
 			/*
-			 * isolate_freepages_block() should not terminate
-			 * prematurely unless contended, or isolated enough
+			 * If isolation failed early, do not continue
+			 * needlessly.
 			 */
-			VM_BUG_ON(isolate_start_pfn < block_end_pfn);
+			break;
 		}
 	}
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9ed5853..343a2b7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1624,14 +1624,9 @@ int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	if (next - addr != HPAGE_PMD_SIZE) {
 		get_page(page);
 		spin_unlock(ptl);
-		if (split_huge_page(page)) {
-			put_page(page);
-			unlock_page(page);
-			goto out_unlocked;
-		}
+		split_huge_page(page);
 		put_page(page);
 		unlock_page(page);
-		ret = 1;
 		goto out_unlocked;
 	}
 
@@ -2989,7 +2984,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 }
 
 void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long address, bool freeze)
+		unsigned long address, bool freeze, struct page *page)
 {
 	spinlock_t *ptl;
 	struct mm_struct *mm = vma->vm_mm;
@@ -2997,8 +2992,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 
 	mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
 	ptl = pmd_lock(mm, pmd);
+
+	/*
+	 * If caller asks to setup a migration entries, we need a page to check
+	 * pmd against. Otherwise we can end up replacing wrong page.
+	 */
+	VM_BUG_ON(freeze && !page);
+	if (page && page != pmd_page(*pmd))
+	        goto out;
+
 	if (pmd_trans_huge(*pmd)) {
-		struct page *page = pmd_page(*pmd);
+		page = pmd_page(*pmd);
 		if (PageMlocked(page))
 			clear_page_mlock(page);
 	} else if (!pmd_devmap(*pmd))
@@ -3025,24 +3029,8 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
 		return;
 
 	pmd = pmd_offset(pud, address);
-	if (!pmd_present(*pmd) || (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)))
-		return;
 
-	/*
-	 * If caller asks to setup a migration entries, we need a page to check
-	 * pmd against. Otherwise we can end up replacing wrong page.
-	 */
-	VM_BUG_ON(freeze && !page);
-	if (page && page != pmd_page(*pmd))
-		return;
-
-	/*
-	 * Caller holds the mmap_sem write mode or the anon_vma lock,
-	 * so a huge pmd cannot materialize from under us (khugepaged
-	 * holds both the mmap_sem write mode and the anon_vma lock
-	 * write mode).
-	 */
-	__split_huge_pmd(vma, pmd, address, freeze);
+	__split_huge_pmd(vma, pmd, address, freeze, page);
 }
 
 void vma_adjust_trans_huge(struct vm_area_struct *vma,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c1f3c0b..addfe4ac 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3383,7 +3383,7 @@ retry_avoidcopy:
 	/* If no-one else is actually using this page, avoid the copy
 	 * and just make the page writable */
 	if (page_mapcount(old_page) == 1 && PageAnon(old_page)) {
-		page_move_anon_rmap(old_page, vma, address);
+		page_move_anon_rmap(old_page, vma);
 		set_huge_ptep_writable(vma, address, ptep);
 		return 0;
 	}
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 4973505..65793f1 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -238,30 +238,23 @@ static void qlist_move_cache(struct qlist_head *from,
 				   struct qlist_head *to,
 				   struct kmem_cache *cache)
 {
-	struct qlist_node *prev = NULL, *curr;
+	struct qlist_node *curr;
 
 	if (unlikely(qlist_empty(from)))
 		return;
 
 	curr = from->head;
+	qlist_init(from);
 	while (curr) {
-		struct qlist_node *qlink = curr;
-		struct kmem_cache *obj_cache = qlink_to_cache(qlink);
-
-		if (obj_cache == cache) {
-			if (unlikely(from->head == qlink)) {
-				from->head = curr->next;
-				prev = curr;
-			} else
-				prev->next = curr->next;
-			if (unlikely(from->tail == qlink))
-				from->tail = curr->next;
-			from->bytes -= cache->size;
-			qlist_put(to, qlink, cache->size);
-		} else {
-			prev = curr;
-		}
-		curr = curr->next;
+		struct qlist_node *next = curr->next;
+		struct kmem_cache *obj_cache = qlink_to_cache(curr);
+
+		if (obj_cache == cache)
+			qlist_put(to, curr, obj_cache->size);
+		else
+			qlist_put(from, curr, obj_cache->size);
+
+		curr = next;
 	}
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ac8664db..5339c89 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4057,6 +4057,60 @@ static struct cftype mem_cgroup_legacy_files[] = {
 	{ },	/* terminate */
 };
 
+/*
+ * Private memory cgroup IDR
+ *
+ * Swap-out records and page cache shadow entries need to store memcg
+ * references in constrained space, so we maintain an ID space that is
+ * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of
+ * memory-controlled cgroups to 64k.
+ *
+ * However, there usually are many references to the oflline CSS after
+ * the cgroup has been destroyed, such as page cache or reclaimable
+ * slab objects, that don't need to hang on to the ID. We want to keep
+ * those dead CSS from occupying IDs, or we might quickly exhaust the
+ * relatively small ID space and prevent the creation of new cgroups
+ * even when there are much fewer than 64k cgroups - possibly none.
+ *
+ * Maintain a private 16-bit ID space for memcg, and allow the ID to
+ * be freed and recycled when it's no longer needed, which is usually
+ * when the CSS is offlined.
+ *
+ * The only exception to that are records of swapped out tmpfs/shmem
+ * pages that need to be attributed to live ancestors on swapin. But
+ * those references are manageable from userspace.
+ */
+
+static DEFINE_IDR(mem_cgroup_idr);
+
+static void mem_cgroup_id_get(struct mem_cgroup *memcg)
+{
+	atomic_inc(&memcg->id.ref);
+}
+
+static void mem_cgroup_id_put(struct mem_cgroup *memcg)
+{
+	if (atomic_dec_and_test(&memcg->id.ref)) {
+		idr_remove(&mem_cgroup_idr, memcg->id.id);
+		memcg->id.id = 0;
+
+		/* Memcg ID pins CSS */
+		css_put(&memcg->css);
+	}
+}
+
+/**
+ * mem_cgroup_from_id - look up a memcg from a memcg id
+ * @id: the memcg id to look up
+ *
+ * Caller must hold rcu_read_lock().
+ */
+struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return idr_find(&mem_cgroup_idr, id);
+}
+
 static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
@@ -4116,6 +4170,12 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (!memcg)
 		return NULL;
 
+	memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
+				 1, MEM_CGROUP_ID_MAX,
+				 GFP_KERNEL);
+	if (memcg->id.id < 0)
+		goto fail;
+
 	memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
 	if (!memcg->stat)
 		goto fail;
@@ -4142,8 +4202,11 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&memcg->cgwb_list);
 #endif
+	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
 	return memcg;
 fail:
+	if (memcg->id.id > 0)
+		idr_remove(&mem_cgroup_idr, memcg->id.id);
 	mem_cgroup_free(memcg);
 	return NULL;
 }
@@ -4206,12 +4269,11 @@ fail:
 	return ERR_PTR(-ENOMEM);
 }
 
-static int
-mem_cgroup_css_online(struct cgroup_subsys_state *css)
+static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 {
-	if (css->id > MEM_CGROUP_ID_MAX)
-		return -ENOSPC;
-
+	/* Online state pins memcg ID, memcg ID pins CSS */
+	mem_cgroup_id_get(mem_cgroup_from_css(css));
+	css_get(css);
 	return 0;
 }
 
@@ -4234,6 +4296,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 
 	memcg_offline_kmem(memcg);
 	wb_memcg_offline(memcg);
+
+	mem_cgroup_id_put(memcg);
 }
 
 static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
@@ -5756,6 +5820,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	if (!memcg)
 		return;
 
+	mem_cgroup_id_get(memcg);
 	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
 	VM_BUG_ON_PAGE(oldid, page);
 	mem_cgroup_swap_statistics(memcg, true);
@@ -5774,6 +5839,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	VM_BUG_ON(!irqs_disabled());
 	mem_cgroup_charge_statistics(memcg, page, false, -1);
 	memcg_check_events(memcg, page);
+
+	if (!mem_cgroup_is_root(memcg))
+		css_put(&memcg->css);
 }
 
 /*
@@ -5804,11 +5872,11 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 	    !page_counter_try_charge(&memcg->swap, 1, &counter))
 		return -ENOMEM;
 
+	mem_cgroup_id_get(memcg);
 	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
 	VM_BUG_ON_PAGE(oldid, page);
 	mem_cgroup_swap_statistics(memcg, true);
 
-	css_get(&memcg->css);
 	return 0;
 }
 
@@ -5837,7 +5905,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
 				page_counter_uncharge(&memcg->memsw, 1);
 		}
 		mem_cgroup_swap_statistics(memcg, false);
-		css_put(&memcg->css);
+		mem_cgroup_id_put(memcg);
 	}
 	rcu_read_unlock();
 }
diff --git a/mm/memory.c b/mm/memory.c
index cd1f29e..9e04681 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2399,8 +2399,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				 * Protected against the rmap code by
 				 * the page lock.
 				 */
-				page_move_anon_rmap(compound_head(old_page),
-						    vma, address);
+				page_move_anon_rmap(old_page, vma);
 			}
 			unlock_page(old_page);
 			return wp_page_reuse(mm, vma, address, page_table, ptl,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6903b69..8b3e134 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -286,7 +286,9 @@ static inline void reset_deferred_meminit(pg_data_t *pgdat)
 /* Returns true if the struct page for the pfn is uninitialised */
 static inline bool __meminit early_page_uninitialised(unsigned long pfn)
 {
-	if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn)
+	int nid = early_pfn_to_nid(pfn);
+
+	if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
 		return true;
 
 	return false;
@@ -1273,7 +1275,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn)
 	spin_lock(&early_pfn_lock);
 	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
 	if (nid < 0)
-		nid = 0;
+		nid = first_online_node;
 	spin_unlock(&early_pfn_lock);
 
 	return nid;
diff --git a/mm/rmap.c b/mm/rmap.c
index 0ea5d90..701b93f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1084,23 +1084,20 @@ EXPORT_SYMBOL_GPL(page_mkclean);
  * page_move_anon_rmap - move a page to our anon_vma
  * @page:	the page to move to our anon_vma
  * @vma:	the vma the page belongs to
- * @address:	the user virtual address mapped
  *
  * When a page belongs exclusively to one process after a COW event,
  * that page can be moved into the anon_vma that belongs to just that
  * process, so the rmap code will not search the parent or sibling
  * processes.
  */
-void page_move_anon_rmap(struct page *page,
-	struct vm_area_struct *vma, unsigned long address)
+void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 
+	page = compound_head(page);
+
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_VMA(!anon_vma, vma);
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && PageTransHuge(page))
-		address &= HPAGE_PMD_MASK;
-	VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page);
 
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
 	/*
@@ -1427,7 +1424,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			goto out;
 	}
 
-	pte = page_check_address(page, mm, address, &ptl, 0);
+	pte = page_check_address(page, mm, address, &ptl,
+				 PageTransCompound(page));
 	if (!pte)
 		goto out;
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 24463b6..171dee7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2225,9 +2225,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 			error = shmem_getpage(inode, index, &page, SGP_FALLOC);
 		if (error) {
 			/* Remove the !PageUptodate pages we added */
-			shmem_undo_range(inode,
-				(loff_t)start << PAGE_SHIFT,
-				((loff_t)index << PAGE_SHIFT) - 1, true);
+			if (index > start) {
+				shmem_undo_range(inode,
+				    (loff_t)start << PAGE_SHIFT,
+				    ((loff_t)index << PAGE_SHIFT) - 1, true);
+			}
 			goto undone;
 		}
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index a65dad7..82317ab 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -526,8 +526,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 		goto out_unlock;
 
 	cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
-	cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
-			       css->id, memcg_name_buf);
+	cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name,
+			       css->serial_nr, memcg_name_buf);
 	if (!cache_name)
 		goto out_unlock;
 
diff --git a/mm/workingset.c b/mm/workingset.c
index 8a75f8d..5772775 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -491,7 +491,7 @@ static int __init workingset_init(void)
 	max_order = fls_long(totalram_pages - 1);
 	if (max_order > timestamp_bits)
 		bucket_order = max_order - timestamp_bits;
-	printk("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
+	pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
 	       timestamp_bits, max_order, bucket_order);
 
 	ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key);