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

Conflicts:
	drivers/net/ethernet/emulex/benet/be.h
	drivers/net/netconsole.c
	net/bridge/br_private.h

Three mostly trivial conflicts.

The net/bridge/br_private.h conflict was a function signature (argument
addition) change overlapping with the extern removals from Joe Perches.

In drivers/net/netconsole.c we had one change adjusting a printk message
whilst another changed "printk(KERN_INFO" into "pr_info(".

Lastly, the emulex change was a new inline function addition overlapping
with Joe Perches's extern removals.

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

7 files changed, 110 insertions, 96 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 610e3df2768..cca80d96e50 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1278,64 +1278,90 @@ out:
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+	struct anon_vma *anon_vma = NULL;
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
+	int page_nid = -1, this_nid = numa_node_id();
 	int target_nid;
-	int current_nid = -1;
-	bool migrated;
+	bool page_locked;
+	bool migrated = false;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
 	page = pmd_page(pmd);
-	get_page(page);
-	current_nid = page_to_nid(page);
+	page_nid = page_to_nid(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
+	/*
+	 * Acquire the page lock to serialise THP migrations but avoid dropping
+	 * page_table_lock if at all possible
+	 */
+	page_locked = trylock_page(page);
 	target_nid = mpol_misplaced(page, vma, haddr);
 	if (target_nid == -1) {
-		put_page(page);
-		goto clear_pmdnuma;
+		/* If the page was locked, there are no parallel migrations */
+		if (page_locked)
+			goto clear_pmdnuma;
+
+		/*
+		 * Otherwise wait for potential migrations and retry. We do
+		 * relock and check_same as the page may no longer be mapped.
+		 * As the fault is being retried, do not account for it.
+		 */
+		spin_unlock(&mm->page_table_lock);
+		wait_on_page_locked(page);
+		page_nid = -1;
+		goto out;
 	}
 
-	/* Acquire the page lock to serialise THP migrations */
+	/* Page is misplaced, serialise migrations and parallel THP splits */
+	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-	lock_page(page);
+	if (!page_locked)
+		lock_page(page);
+	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PTE did not while locked */
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp))) {
 		unlock_page(page);
 		put_page(page);
+		page_nid = -1;
 		goto out_unlock;
 	}
-	spin_unlock(&mm->page_table_lock);
 
-	/* Migrate the THP to the requested node */
+	/*
+	 * Migrate the THP to the requested node, returns with page unlocked
+	 * and pmd_numa cleared.
+	 */
+	spin_unlock(&mm->page_table_lock);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
 				pmdp, pmd, addr, page, target_nid);
-	if (!migrated)
-		goto check_same;
-
-	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
-	return 0;
+	if (migrated)
+		page_nid = target_nid;
 
-check_same:
-	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(pmd, *pmdp)))
-		goto out_unlock;
+	goto out;
 clear_pmdnuma:
+	BUG_ON(!PageLocked(page));
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
+	unlock_page(page);
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
-	if (current_nid != -1)
-		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
+
+out:
+	if (anon_vma)
+		page_unlock_anon_vma_read(anon_vma);
+
+	if (page_nid != -1)
+		task_numa_fault(page_nid, HPAGE_PMD_NR, migrated);
+
 	return 0;
 }
 
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 72467914b85..72f9decb010 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -81,8 +81,9 @@ restart:
 		 * decrement nr_to_walk first so that we don't livelock if we
 		 * get stuck on large numbesr of LRU_RETRY items
 		 */
-		if (--(*nr_to_walk) == 0)
+		if (!*nr_to_walk)
 			break;
+		--*nr_to_walk;
 
 		ret = isolate(item, &nlru->lock, cb_arg);
 		switch (ret) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9c9c685e4dd..665dcd7abff 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -54,6 +54,7 @@
 #include <linux/page_cgroup.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
+#include <linux/lockdep.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -2046,6 +2047,12 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 	return total;
 }
 
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map memcg_oom_lock_dep_map = {
+	.name = "memcg_oom_lock",
+};
+#endif
+
 static DEFINE_SPINLOCK(memcg_oom_lock);
 
 /*
@@ -2083,7 +2090,8 @@ static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
 			}
 			iter->oom_lock = false;
 		}
-	}
+	} else
+		mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_);
 
 	spin_unlock(&memcg_oom_lock);
 
@@ -2095,6 +2103,7 @@ static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
 	struct mem_cgroup *iter;
 
 	spin_lock(&memcg_oom_lock);
+	mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_);
 	for_each_mem_cgroup_tree(iter, memcg)
 		iter->oom_lock = false;
 	spin_unlock(&memcg_oom_lock);
@@ -2765,10 +2774,10 @@ done:
 	*ptr = memcg;
 	return 0;
 nomem:
-	*ptr = NULL;
-	if (gfp_mask & __GFP_NOFAIL)
-		return 0;
-	return -ENOMEM;
+	if (!(gfp_mask & __GFP_NOFAIL)) {
+		*ptr = NULL;
+		return -ENOMEM;
+	}
 bypass:
 	*ptr = root_mem_cgroup;
 	return -EINTR;
@@ -3773,8 +3782,7 @@ void mem_cgroup_move_account_page_stat(struct mem_cgroup *from,
 {
 	/* Update stat data for mem_cgroup */
 	preempt_disable();
-	WARN_ON_ONCE(from->stat->count[idx] < nr_pages);
-	__this_cpu_add(from->stat->count[idx], -nr_pages);
+	__this_cpu_sub(from->stat->count[idx], nr_pages);
 	__this_cpu_add(to->stat->count[idx], nr_pages);
 	preempt_enable();
 }
@@ -4950,31 +4958,18 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 	} while (usage > 0);
 }
 
-/*
- * This mainly exists for tests during the setting of set of use_hierarchy.
- * Since this is the very setting we are changing, the current hierarchy value
- * is meaningless
- */
-static inline bool __memcg_has_children(struct mem_cgroup *memcg)
-{
-	struct cgroup_subsys_state *pos;
-
-	/* bounce at first found */
-	css_for_each_child(pos, &memcg->css)
-		return true;
-	return false;
-}
-
-/*
- * Must be called with memcg_create_mutex held, unless the cgroup is guaranteed
- * to be already dead (as in mem_cgroup_force_empty, for instance).  This is
- * from mem_cgroup_count_children(), in the sense that we don't really care how
- * many children we have; we only need to know if we have any.  It also counts
- * any memcg without hierarchy as infertile.
- */
 static inline bool memcg_has_children(struct mem_cgroup *memcg)
 {
-	return memcg->use_hierarchy && __memcg_has_children(memcg);
+	lockdep_assert_held(&memcg_create_mutex);
+	/*
+	 * The lock does not prevent addition or deletion to the list
+	 * of children, but it prevents a new child from being
+	 * initialized based on this parent in css_online(), so it's
+	 * enough to decide whether hierarchically inherited
+	 * attributes can still be changed or not.
+	 */
+	return memcg->use_hierarchy &&
+		!list_empty(&memcg->css.cgroup->children);
 }
 
 /*
@@ -5054,7 +5049,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
 	 */
 	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
 				(val == 1 || val == 0)) {
-		if (!__memcg_has_children(memcg))
+		if (list_empty(&memcg->css.cgroup->children))
 			memcg->use_hierarchy = val;
 		else
 			retval = -EBUSY;
diff --git a/mm/memory.c b/mm/memory.c
index 1311f26497e..d176154c243 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3521,12 +3521,12 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
-				unsigned long addr, int current_nid)
+				unsigned long addr, int page_nid)
 {
 	get_page(page);
 
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == numa_node_id())
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
 	return mpol_misplaced(page, vma, addr);
@@ -3537,7 +3537,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
-	int current_nid = -1;
+	int page_nid = -1;
 	int target_nid;
 	bool migrated = false;
 
@@ -3567,15 +3567,10 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return 0;
 	}
 
-	current_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+	page_nid = page_to_nid(page);
+	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 	pte_unmap_unlock(ptep, ptl);
 	if (target_nid == -1) {
-		/*
-		 * Account for the fault against the current node if it not
-		 * being replaced regardless of where the page is located.
-		 */
-		current_nid = numa_node_id();
 		put_page(page);
 		goto out;
 	}
@@ -3583,11 +3578,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Migrate to the requested node */
 	migrated = migrate_misplaced_page(page, target_nid);
 	if (migrated)
-		current_nid = target_nid;
+		page_nid = target_nid;
 
 out:
-	if (current_nid != -1)
-		task_numa_fault(current_nid, 1, migrated);
+	if (page_nid != -1)
+		task_numa_fault(page_nid, 1, migrated);
 	return 0;
 }
 
@@ -3602,7 +3597,6 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
-	int local_nid = numa_node_id();
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3625,9 +3619,10 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
 		pte_t pteval = *pte;
 		struct page *page;
-		int curr_nid = local_nid;
+		int page_nid = -1;
 		int target_nid;
-		bool migrated;
+		bool migrated = false;
+
 		if (!pte_present(pteval))
 			continue;
 		if (!pte_numa(pteval))
@@ -3649,25 +3644,19 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(page_mapcount(page) != 1))
 			continue;
 
-		/*
-		 * Note that the NUMA fault is later accounted to either
-		 * the node that is currently running or where the page is
-		 * migrated to.
-		 */
-		curr_nid = local_nid;
-		target_nid = numa_migrate_prep(page, vma, addr,
-					       page_to_nid(page));
-		if (target_nid == -1) {
+		page_nid = page_to_nid(page);
+		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
+		pte_unmap_unlock(pte, ptl);
+		if (target_nid != -1) {
+			migrated = migrate_misplaced_page(page, target_nid);
+			if (migrated)
+				page_nid = target_nid;
+		} else {
 			put_page(page);
-			continue;
 		}
 
-		/* Migrate to the requested node */
-		pte_unmap_unlock(pte, ptl);
-		migrated = migrate_misplaced_page(page, target_nid);
-		if (migrated)
-			curr_nid = target_nid;
-		task_numa_fault(curr_nid, 1, migrated);
+		if (page_nid != -1)
+			task_numa_fault(page_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index 7a7325ee1d0..c04692774e8 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1715,12 +1715,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		unlock_page(new_page);
 		put_page(new_page);		/* Free it */
 
-		unlock_page(page);
+		/* Retake the callers reference and putback on LRU */
+		get_page(page);
 		putback_lru_page(page);
-
-		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-		isolated = 0;
-		goto out;
+		mod_zone_page_state(page_zone(page),
+			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
+		goto out_fail;
 	}
 
 	/*
@@ -1737,9 +1737,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 	entry = pmd_mkhuge(entry);
 
-	page_add_new_anon_rmap(new_page, vma, haddr);
-
+	pmdp_clear_flush(vma, haddr, pmd);
 	set_pmd_at(mm, haddr, pmd, entry);
+	page_add_new_anon_rmap(new_page, vma, haddr);
 	update_mmu_cache_pmd(vma, address, &entry);
 	page_remove_rmap(page);
 	/*
@@ -1758,7 +1758,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
 	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
 
-out:
 	mod_zone_page_state(page_zone(page),
 			NR_ISOLATED_ANON + page_lru,
 			-HPAGE_PMD_NR);
@@ -1767,6 +1766,10 @@ out:
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
+	entry = pmd_mknonnuma(entry);
+	set_pmd_at(mm, haddr, pmd, entry);
+	update_mmu_cache_pmd(vma, address, &entry);
+
 	unlock_page(page);
 	put_page(page);
 	return 0;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a3af058f68e..412ba2b7326 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -148,7 +148,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 				split_huge_page_pmd(vma, addr, pmd);
 			else if (change_huge_pmd(vma, pmd, addr, newprot,
 						 prot_numa)) {
-				pages += HPAGE_PMD_NR;
+				pages++;
 				continue;
 			}
 			/* fall through */
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 5da2cbcfdbb..2beeabf502c 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -242,7 +242,7 @@ int walk_page_range(unsigned long addr, unsigned long end,
 		if (err)
 			break;
 		pgd++;
-	} while (addr = next, addr != end);
+	} while (addr = next, addr < end);
 
 	return err;
 }