Merge tag 'v3.10.46' into linux-linaro-lsk

This is the 3.10.46 stable release

3 files changed, 59 insertions, 20 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f8548abd6ee..603f1fa1b7a3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -208,9 +208,9 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
 #endif
 	si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;
 
-	if ((flags & MF_ACTION_REQUIRED) && t == current) {
+	if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
 		si.si_code = BUS_MCEERR_AR;
-		ret = force_sig_info(SIGBUS, &si, t);
+		ret = force_sig_info(SIGBUS, &si, current);
 	} else {
 		/*
 		 * Don't use force here, it's convenient if the signal
@@ -382,10 +382,12 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
 	}
 }
 
-static int task_early_kill(struct task_struct *tsk)
+static int task_early_kill(struct task_struct *tsk, int force_early)
 {
 	if (!tsk->mm)
 		return 0;
+	if (force_early)
+		return 1;
 	if (tsk->flags & PF_MCE_PROCESS)
 		return !!(tsk->flags & PF_MCE_EARLY);
 	return sysctl_memory_failure_early_kill;
@@ -395,7 +397,7 @@ static int task_early_kill(struct task_struct *tsk)
  * Collect processes when the error hit an anonymous page.
  */
 static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -411,7 +413,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
 
-		if (!task_early_kill(tsk))
+		if (!task_early_kill(tsk, force_early))
 			continue;
 		anon_vma_interval_tree_foreach(vmac, &av->rb_root,
 					       pgoff, pgoff) {
@@ -430,7 +432,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
  * Collect processes when the error hit a file mapped page.
  */
 static void collect_procs_file(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -441,7 +443,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
-		if (!task_early_kill(tsk))
+		if (!task_early_kill(tsk, force_early))
 			continue;
 
 		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
@@ -467,7 +469,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
  * First preallocate one tokill structure outside the spin locks,
  * so that we can kill at least one process reasonably reliable.
  */
-static void collect_procs(struct page *page, struct list_head *tokill)
+static void collect_procs(struct page *page, struct list_head *tokill,
+				int force_early)
 {
 	struct to_kill *tk;
 
@@ -478,9 +481,9 @@ static void collect_procs(struct page *page, struct list_head *tokill)
 	if (!tk)
 		return;
 	if (PageAnon(page))
-		collect_procs_anon(page, tokill, &tk);
+		collect_procs_anon(page, tokill, &tk, force_early);
 	else
-		collect_procs_file(page, tokill, &tk);
+		collect_procs_file(page, tokill, &tk, force_early);
 	kfree(tk);
 }
 
@@ -965,7 +968,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * there's nothing that can be done.
 	 */
 	if (kill)
-		collect_procs(ppage, &tokill);
+		collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED);
 
 	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
diff --git a/mm/rmap.c b/mm/rmap.c
index b730a4409be6..705bfc8e6fcd 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -103,6 +103,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma)
 	 * LOCK should suffice since the actual taking of the lock must
 	 * happen _before_ what follows.
 	 */
+	might_sleep();
 	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
 		anon_vma_lock_write(anon_vma);
 		anon_vma_unlock_write(anon_vma);
@@ -426,8 +427,9 @@ struct anon_vma *page_get_anon_vma(struct page *page)
 	 * above cannot corrupt).
 	 */
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
+		return NULL;
 	}
 out:
 	rcu_read_unlock();
@@ -477,9 +479,9 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page)
 	}
 
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
-		goto out;
+		return NULL;
 	}
 
 	/* we pinned the anon_vma, its safe to sleep */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 43ddef3cf44f..4e89500391dc 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2286,10 +2286,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
+		if (!populated_zone(zone))
+			continue;
+
 		pfmemalloc_reserve += min_wmark_pages(zone);
 		free_pages += zone_page_state(zone, NR_FREE_PAGES);
 	}
 
+	/* If there are no reserves (unexpected config) then do not throttle */
+	if (!pfmemalloc_reserve)
+		return true;
+
 	wmark_ok = free_pages > pfmemalloc_reserve / 2;
 
 	/* kswapd must be awake if processes are being throttled */
@@ -2314,9 +2321,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 					nodemask_t *nodemask)
 {
+	struct zoneref *z;
 	struct zone *zone;
-	int high_zoneidx = gfp_zone(gfp_mask);
-	pg_data_t *pgdat;
+	pg_data_t *pgdat = NULL;
 
 	/*
 	 * Kernel threads should not be throttled as they may be indirectly
@@ -2335,10 +2342,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	if (fatal_signal_pending(current))
 		goto out;
 
-	/* Check if the pfmemalloc reserves are ok */
-	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
-	pgdat = zone->zone_pgdat;
-	if (pfmemalloc_watermark_ok(pgdat))
+	/*
+	 * Check if the pfmemalloc reserves are ok by finding the first node
+	 * with a usable ZONE_NORMAL or lower zone. The expectation is that
+	 * GFP_KERNEL will be required for allocating network buffers when
+	 * swapping over the network so ZONE_HIGHMEM is unusable.
+	 *
+	 * Throttling is based on the first usable node and throttled processes
+	 * wait on a queue until kswapd makes progress and wakes them. There
+	 * is an affinity then between processes waking up and where reclaim
+	 * progress has been made assuming the process wakes on the same node.
+	 * More importantly, processes running on remote nodes will not compete
+	 * for remote pfmemalloc reserves and processes on different nodes
+	 * should make reasonable progress.
+	 */
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_mask, nodemask) {
+		if (zone_idx(zone) > ZONE_NORMAL)
+			continue;
+
+		/* Throttle based on the first usable node */
+		pgdat = zone->zone_pgdat;
+		if (pfmemalloc_watermark_ok(pgdat))
+			goto out;
+		break;
+	}
+
+	/* If no zone was usable by the allocation flags then do not throttle */
+	if (!pgdat)
 		goto out;
 
 	/* Account for the throttling */
@@ -3059,7 +3090,10 @@ static int kswapd(void *p)
 		}
 	}
 
+	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
 	current->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+
 	return 0;
 }