Merge tag 'v3.1-rc6' into staging/for_v3.2

* tag 'v3.1-rc6': (1902 commits)
  Linux 3.1-rc6
  ioctl: register LTTng ioctl
  fuse: fix memory leak
  fuse: fix flock breakage
  Btrfs: add dummy extent if dst offset excceeds file end in
  Btrfs: calc file extent num_bytes correctly in file clone
  btrfs: xattr: fix attribute removal
  Btrfs: fix wrong nbytes information of the inode
  Btrfs: fix the file extent gap when doing direct IO
  Btrfs: fix unclosed transaction handle in btrfs_cont_expand
  Btrfs: fix misuse of trans block rsv
  Btrfs: reset to appropriate block rsv after orphan operations
  Btrfs: skip locking if searching the commit root in csum lookup
  btrfs: fix warning in iput for bad-inode
  Btrfs: fix an oops when deleting snapshots
  [media] vp7045: fix buffer setup
  [media] nuvoton-cir: simplify raw IR sample handling
  [media] [Resend] viacam: Don't explode if pci_find_bus() returns NULL
  [media] v4l2: Fix documentation of the codec device controls
  [media] gspca - sonixj: Fix the darkness of sensor om6802 in 320x240
  ...

1 files changed, 26 insertions, 78 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5f84d2351ddb..ebd1e86bef1c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -35,7 +35,6 @@
 #include <linux/limits.h>
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
-#include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
@@ -1842,29 +1841,23 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
  */
 static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
 {
-	int lock_count = -1;
 	struct mem_cgroup *iter, *failed = NULL;
 	bool cond = true;
 
 	for_each_mem_cgroup_tree_cond(iter, mem, cond) {
-		bool locked = iter->oom_lock;
-
-		iter->oom_lock = true;
-		if (lock_count == -1)
-			lock_count = iter->oom_lock;
-		else if (lock_count != locked) {
+		if (iter->oom_lock) {
 			/*
 			 * this subtree of our hierarchy is already locked
 			 * so we cannot give a lock.
 			 */
-			lock_count = 0;
 			failed = iter;
 			cond = false;
-		}
+		} else
+			iter->oom_lock = true;
 	}
 
 	if (!failed)
-		goto done;
+		return true;
 
 	/*
 	 * OK, we failed to lock the whole subtree so we have to clean up
@@ -1878,8 +1871,7 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
 		}
 		iter->oom_lock = false;
 	}
-done:
-	return lock_count;
+	return false;
 }
 
 /*
@@ -2092,6 +2084,7 @@ struct memcg_stock_pcp {
 #define FLUSHING_CACHED_CHARGE	(0)
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
+static DEFINE_MUTEX(percpu_charge_mutex);
 
 /*
  * Try to consume stocked charge on this cpu. If success, one page is consumed
@@ -2169,13 +2162,7 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
 
 	/* Notify other cpus that system-wide "drain" is running */
 	get_online_cpus();
-	/*
-	 * Get a hint for avoiding draining charges on the current cpu,
-	 * which must be exhausted by our charging.  It is not required that
-	 * this be a precise check, so we use raw_smp_processor_id() instead of
-	 * getcpu()/putcpu().
-	 */
-	curcpu = raw_smp_processor_id();
+	curcpu = get_cpu();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
 		struct mem_cgroup *mem;
@@ -2192,14 +2179,14 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
 				schedule_work_on(cpu, &stock->work);
 		}
 	}
+	put_cpu();
 
 	if (!sync)
 		goto out;
 
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
-		if (mem_cgroup_same_or_subtree(root_mem, stock->cached) &&
-				test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
+		if (test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
 			flush_work(&stock->work);
 	}
 out:
@@ -2214,14 +2201,22 @@ out:
  */
 static void drain_all_stock_async(struct mem_cgroup *root_mem)
 {
+	/*
+	 * If someone calls draining, avoid adding more kworker runs.
+	 */
+	if (!mutex_trylock(&percpu_charge_mutex))
+		return;
 	drain_all_stock(root_mem, false);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /* This is a synchronous drain interface. */
 static void drain_all_stock_sync(struct mem_cgroup *root_mem)
 {
 	/* called when force_empty is called */
+	mutex_lock(&percpu_charge_mutex);
 	drain_all_stock(root_mem, true);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /*
@@ -2873,30 +2868,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 		return 0;
 	if (PageCompound(page))
 		return 0;
-	/*
-	 * Corner case handling. This is called from add_to_page_cache()
-	 * in usual. But some FS (shmem) precharges this page before calling it
-	 * and call add_to_page_cache() with GFP_NOWAIT.
-	 *
-	 * For GFP_NOWAIT case, the page may be pre-charged before calling
-	 * add_to_page_cache(). (See shmem.c) check it here and avoid to call
-	 * charge twice. (It works but has to pay a bit larger cost.)
-	 * And when the page is SwapCache, it should take swap information
-	 * into account. This is under lock_page() now.
-	 */
-	if (!(gfp_mask & __GFP_WAIT)) {
-		struct page_cgroup *pc;
-
-		pc = lookup_page_cgroup(page);
-		if (!pc)
-			return 0;
-		lock_page_cgroup(pc);
-		if (PageCgroupUsed(pc)) {
-			unlock_page_cgroup(pc);
-			return 0;
-		}
-		unlock_page_cgroup(pc);
-	}
 
 	if (unlikely(!mm))
 		mm = &init_mm;
@@ -3486,31 +3457,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
 	cgroup_release_and_wakeup_rmdir(&mem->css);
 }
 
-/*
- * A call to try to shrink memory usage on charge failure at shmem's swapin.
- * Calling hierarchical_reclaim is not enough because we should update
- * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM.
- * Moreover considering hierarchy, we should reclaim from the mem_over_limit,
- * not from the memcg which this page would be charged to.
- * try_charge_swapin does all of these works properly.
- */
-int mem_cgroup_shmem_charge_fallback(struct page *page,
-			    struct mm_struct *mm,
-			    gfp_t gfp_mask)
-{
-	struct mem_cgroup *mem;
-	int ret;
-
-	if (mem_cgroup_disabled())
-		return 0;
-
-	ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
-	if (!ret)
-		mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */
-
-	return ret;
-}
-
 #ifdef CONFIG_DEBUG_VM
 static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
 {
@@ -5330,15 +5276,17 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 		pgoff = pte_to_pgoff(ptent);
 
 	/* page is moved even if it's not RSS of this task(page-faulted). */
-	if (!mapping_cap_swap_backed(mapping)) { /* normal file */
-		page = find_get_page(mapping, pgoff);
-	} else { /* shmem/tmpfs file. we should take account of swap too. */
-		swp_entry_t ent;
-		mem_cgroup_get_shmem_target(inode, pgoff, &page, &ent);
+	page = find_get_page(mapping, pgoff);
+
+#ifdef CONFIG_SWAP
+	/* shmem/tmpfs may report page out on swap: account for that too. */
+	if (radix_tree_exceptional_entry(page)) {
+		swp_entry_t swap = radix_to_swp_entry(page);
 		if (do_swap_account)
-			entry->val = ent.val;
+			*entry = swap;
+		page = find_get_page(&swapper_space, swap.val);
 	}
-
+#endif
 	return page;
 }