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

Conflicts:
	drivers/net/wireless/ath/ath9k/Kconfig
	drivers/net/xen-netback/netback.c
	net/batman-adv/bat_iv_ogm.c
	net/wireless/nl80211.c

The ath9k Kconfig conflict was a change of a Kconfig option name right
next to the deletion of another option.

The xen-netback conflict was overlapping changes involving the
handling of the notify list in xen_netbk_rx_action().

Batman conflict resolution provided by Antonio Quartulli, basically
keep everything in both conflict hunks.

The nl80211 conflict is a little more involved.  In 'net' we added a
dynamic memory allocation to nl80211_dump_wiphy() to fix a race that
Linus reported.  Meanwhile in 'net-next' the handlers were converted
to use pre and post doit handlers which use a flag to determine
whether to hold the RTNL mutex around the operation.

However, the dump handlers to not use this logic.  Instead they have
to explicitly do the locking.  There were apparent bugs in the
conversion of nl80211_dump_wiphy() in that we were not dropping the
RTNL mutex in all the return paths, and it seems we very much should
be doing so.  So I fixed that whilst handling the overlapping changes.

To simplify the initial returns, I take the RTNL mutex after we try
to allocate 'tb'.

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

7 files changed, 47 insertions, 20 deletions

diff --git a/mm/frontswap.c b/mm/frontswap.c
index 538367ef1372..1b24bdcb3197 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -319,7 +319,7 @@ void __frontswap_invalidate_area(unsigned type)
 			return;
 		frontswap_ops->invalidate_area(type);
 		atomic_set(&sis->frontswap_pages, 0);
-		memset(sis->frontswap_map, 0, sis->max / sizeof(long));
+		bitmap_zero(sis->frontswap_map, sis->max);
 	}
 	clear_bit(type, need_init);
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f8feeeca6686..e2bfbf73a551 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2839,7 +2839,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait(mm, (pmd_t *)ptep, address);
+			migration_entry_wait_huge(mm, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 010d6c14129a..194721839cf5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1199,7 +1199,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 
 			mz = mem_cgroup_zoneinfo(root, nid, zid);
 			iter = &mz->reclaim_iter[reclaim->priority];
-			last_visited = iter->last_visited;
 			if (prev && reclaim->generation != iter->generation) {
 				iter->last_visited = NULL;
 				goto out_unlock;
@@ -1218,13 +1217,12 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 			 * is alive.
 			 */
 			dead_count = atomic_read(&root->dead_count);
-			smp_rmb();
-			last_visited = iter->last_visited;
-			if (last_visited) {
-				if ((dead_count != iter->last_dead_count) ||
-					!css_tryget(&last_visited->css)) {
+			if (dead_count == iter->last_dead_count) {
+				smp_rmb();
+				last_visited = iter->last_visited;
+				if (last_visited &&
+				    !css_tryget(&last_visited->css))
 					last_visited = NULL;
-				}
 			}
 		}
 
@@ -3141,8 +3139,6 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
 			return -ENOMEM;
 		}
 
-		INIT_WORK(&s->memcg_params->destroy,
-				kmem_cache_destroy_work_func);
 		s->memcg_params->is_root_cache = true;
 
 		/*
diff --git a/mm/migrate.c b/mm/migrate.c
index b1f57501de9c..6f0c24438bba 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -200,15 +200,14 @@ static void remove_migration_ptes(struct page *old, struct page *new)
  * get to the page and wait until migration is finished.
  * When we return from this function the fault will be retried.
  */
-void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
-				unsigned long address)
+static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+				spinlock_t *ptl)
 {
-	pte_t *ptep, pte;
-	spinlock_t *ptl;
+	pte_t pte;
 	swp_entry_t entry;
 	struct page *page;
 
-	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+	spin_lock(ptl);
 	pte = *ptep;
 	if (!is_swap_pte(pte))
 		goto out;
@@ -236,6 +235,20 @@ out:
 	pte_unmap_unlock(ptep, ptl);
 }
 
+void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
+				unsigned long address)
+{
+	spinlock_t *ptl = pte_lockptr(mm, pmd);
+	pte_t *ptep = pte_offset_map(pmd, address);
+	__migration_entry_wait(mm, ptep, ptl);
+}
+
+void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+{
+	spinlock_t *ptl = &(mm)->page_table_lock;
+	__migration_entry_wait(mm, pte, ptl);
+}
+
 #ifdef CONFIG_BLOCK
 /* Returns true if all buffers are successfully locked */
 static bool buffer_migrate_lock_buffers(struct buffer_head *head,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 378a15bcd649..c3edb624fccf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1628,6 +1628,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	long min = mark;
 	long lowmem_reserve = z->lowmem_reserve[classzone_idx];
 	int o;
+	long free_cma = 0;
 
 	free_pages -= (1 << order) - 1;
 	if (alloc_flags & ALLOC_HIGH)
@@ -1637,9 +1638,10 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 #ifdef CONFIG_CMA
 	/* If allocation can't use CMA areas don't use free CMA pages */
 	if (!(alloc_flags & ALLOC_CMA))
-		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+		free_cma = zone_page_state(z, NR_FREE_CMA_PAGES);
 #endif
-	if (free_pages <= min + lowmem_reserve)
+
+	if (free_pages - free_cma <= min + lowmem_reserve)
 		return false;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
diff --git a/mm/swap_state.c b/mm/swap_state.c
index b3d40dcf3624..f24ab0dff554 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -336,8 +336,24 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * Swap entry may have been freed since our caller observed it.
 		 */
 		err = swapcache_prepare(entry);
-		if (err == -EEXIST) {	/* seems racy */
+		if (err == -EEXIST) {
 			radix_tree_preload_end();
+			/*
+			 * We might race against get_swap_page() and stumble
+			 * across a SWAP_HAS_CACHE swap_map entry whose page
+			 * has not been brought into the swapcache yet, while
+			 * the other end is scheduled away waiting on discard
+			 * I/O completion at scan_swap_map().
+			 *
+			 * In order to avoid turning this transitory state
+			 * into a permanent loop around this -EEXIST case
+			 * if !CONFIG_PREEMPT and the I/O completion happens
+			 * to be waiting on the CPU waitqueue where we are now
+			 * busy looping, we just conditionally invoke the
+			 * scheduler here, if there are some more important
+			 * tasks to run.
+			 */
+			cond_resched();
 			continue;
 		}
 		if (err) {		/* swp entry is obsolete ? */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6c340d908b27..746af55b8455 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2116,7 +2116,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	}
 	/* frontswap enabled? set up bit-per-page map for frontswap */
 	if (frontswap_enabled)
-		frontswap_map = vzalloc(maxpages / sizeof(long));
+		frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long));
 
 	if (p->bdev) {
 		if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {