9 files changed, 117 insertions, 34 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 8fa77e233944..76da12537956 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -443,7 +443,7 @@ static struct kiocb *__aio_get_req(struct kioctx *ctx)
         req->private = NULL;
         req->ki_iovec = NULL;
         INIT_LIST_HEAD(&req->ki_run_list);
-        req->ki_eventfd = ERR_PTR(-EINVAL);
+        req->ki_eventfd = NULL;
 
         /* Check if the completion queue has enough free space to
          * accept an event from this io.
@@ -485,8 +485,6 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
 {
         assert_spin_locked(&ctx->ctx_lock);
 
-        if (!IS_ERR(req->ki_eventfd))
-                fput(req->ki_eventfd);
         if (req->ki_dtor)
                 req->ki_dtor(req);
         if (req->ki_iovec != &req->ki_inline_vec)
@@ -508,8 +506,11 @@ static void aio_fput_routine(struct work_struct *data)
                 list_del(&req->ki_list);
                 spin_unlock_irq(&fput_lock);
 
-                /* Complete the fput */
-                __fput(req->ki_filp);
+                /* Complete the fput(s) */
+                if (req->ki_filp != NULL)
+                        __fput(req->ki_filp);
+                if (req->ki_eventfd != NULL)
+                        __fput(req->ki_eventfd);
 
                 /* Link the iocb into the context's free list */
                 spin_lock_irq(&ctx->ctx_lock);
@@ -527,12 +528,14 @@ static void aio_fput_routine(struct work_struct *data)
  */
 static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 {
+        int schedule_putreq = 0;
+
         dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n",
                 req, atomic_long_read(&req->ki_filp->f_count));
 
         assert_spin_locked(&ctx->ctx_lock);
 
-        req->ki_users --;
+        req->ki_users--;
         BUG_ON(req->ki_users < 0);
         if (likely(req->ki_users))
                 return 0;
@@ -540,10 +543,23 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
         req->ki_cancel = NULL;
         req->ki_retry = NULL;
 
-        /* Must be done under the lock to serialise against cancellation.
-         * Call this aio_fput as it duplicates fput via the fput_work.
+        /*
+         * Try to optimize the aio and eventfd file* puts, by avoiding to
+         * schedule work in case it is not __fput() time. In normal cases,
+         * we would not be holding the last reference to the file*, so
+         * this function will be executed w/out any aio kthread wakeup.
          */
-        if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) {
+        if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count)))
+                schedule_putreq++;
+        else
+                req->ki_filp = NULL;
+        if (req->ki_eventfd != NULL) {
+                if (unlikely(atomic_long_dec_and_test(&req->ki_eventfd->f_count)))
+                        schedule_putreq++;
+                else
+                        req->ki_eventfd = NULL;
+        }
+        if (unlikely(schedule_putreq)) {
                 get_ioctx(ctx);
                 spin_lock(&fput_lock);
                 list_add(&req->ki_list, &fput_head);
@@ -571,7 +587,7 @@ int aio_put_req(struct kiocb *req)
 static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 {
         struct mm_struct *mm = current->mm;
-        struct kioctx *ctx = NULL;
+        struct kioctx *ctx, *ret = NULL;
         struct hlist_node *n;
 
         rcu_read_lock();
@@ -579,12 +595,13 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
         hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) {
                 if (ctx->user_id == ctx_id && !ctx->dead) {
                         get_ioctx(ctx);
+                        ret = ctx;
                         break;
                 }
         }
 
         rcu_read_unlock();
-        return ctx;
+        return ret;
 }
 
 /*
@@ -1009,7 +1026,7 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
          * eventfd. The eventfd_signal() function is safe to be called
          * from IRQ context.
          */
-        if (!IS_ERR(iocb->ki_eventfd))
+        if (iocb->ki_eventfd != NULL)
                 eventfd_signal(iocb->ki_eventfd, 1);
 
 put_rq:
@@ -1608,6 +1625,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
                 req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd);
                 if (IS_ERR(req->ki_eventfd)) {
                         ret = PTR_ERR(req->ki_eventfd);
+                        req->ki_eventfd = NULL;
                         goto out_put_req;
                 }
         }
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 82491ba8fa40..5e1d4e30e9d8 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -784,7 +784,14 @@ struct btrfs_fs_info {
         struct list_head dirty_cowonly_roots;
 
         struct btrfs_fs_devices *fs_devices;
+
+        /*
+         * the space_info list is almost entirely read only.  It only changes
+         * when we add a new raid type to the FS, and that happens
+         * very rarely.  RCU is used to protect it.
+         */
         struct list_head space_info;
+
         spinlock_t delalloc_lock;
         spinlock_t new_trans_lock;
         u64 delalloc_bytes;
@@ -1797,6 +1804,8 @@ int btrfs_cleanup_reloc_trees(struct btrfs_root *root);
 int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len);
 u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags);
 void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde);
+void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
+
 int btrfs_check_metadata_free_space(struct btrfs_root *root);
 int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode,
                                 u64 bytes);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9abf81f71c46..fefe83ad2059 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -20,6 +20,7 @@
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/sort.h>
+#include <linux/rcupdate.h>
 #include "compat.h"
 #include "hash.h"
 #include "crc32c.h"
@@ -330,13 +331,33 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
 {
         struct list_head *head = &info->space_info;
         struct btrfs_space_info *found;
-        list_for_each_entry(found, head, list) {
-                if (found->flags == flags)
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(found, head, list) {
+                if (found->flags == flags) {
+                        rcu_read_unlock();
                         return found;
+                }
         }
+        rcu_read_unlock();
         return NULL;
 }
 
+/*
+ * after adding space to the filesystem, we need to clear the full flags
+ * on all the space infos.
+ */
+void btrfs_clear_space_info_full(struct btrfs_fs_info *info)
+{
+        struct list_head *head = &info->space_info;
+        struct btrfs_space_info *found;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(found, head, list)
+                found->full = 0;
+        rcu_read_unlock();
+}
+
 static u64 div_factor(u64 num, int factor)
 {
         if (factor == 10)
@@ -1903,7 +1924,6 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
         if (!found)
                 return -ENOMEM;
 
-        list_add(&found->list, &info->space_info);
         INIT_LIST_HEAD(&found->block_groups);
         init_rwsem(&found->groups_sem);
         spin_lock_init(&found->lock);
@@ -1917,6 +1937,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
         found->full = 0;
         found->force_alloc = 0;
         *space_info = found;
+        list_add_rcu(&found->list, &info->space_info);
         return 0;
 }
 
@@ -6320,6 +6341,7 @@ out:
 int btrfs_free_block_groups(struct btrfs_fs_info *info)
 {
         struct btrfs_block_group_cache *block_group;
+        struct btrfs_space_info *space_info;
         struct rb_node *n;
 
         spin_lock(&info->block_group_cache_lock);
@@ -6341,6 +6363,23 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
                 spin_lock(&info->block_group_cache_lock);
         }
         spin_unlock(&info->block_group_cache_lock);
+
+        /* now that all the block groups are freed, go through and
+         * free all the space_info structs.  This is only called during
+         * the final stages of unmount, and so we know nobody is
+         * using them.  We call synchronize_rcu() once before we start,
+         * just to be on the safe side.
+         */
+        synchronize_rcu();
+
+        while(!list_empty(&info->space_info)) {
+                space_info = list_entry(info->space_info.next,
+                                        struct btrfs_space_info,
+                                        list);
+
+                list_del(&space_info->list);
+                kfree(space_info);
+        }
         return 0;
 }
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1316139bf9e8..dd06e18e5aac 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1374,6 +1374,12 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
                 ret = btrfs_add_device(trans, root, device);
         }
 
+        /*
+         * we've got more storage, clear any full flags on the space
+         * infos
+         */
+        btrfs_clear_space_info_full(root->fs_info);
+
         unlock_chunks(root);
         btrfs_commit_transaction(trans, root);
 
@@ -1459,6 +1465,8 @@ static int __btrfs_grow_device(struct btrfs_trans_handle *trans,
         device->fs_devices->total_rw_bytes += diff;
 
         device->total_bytes = new_size;
+        btrfs_clear_space_info_full(device->dev_root->fs_info);
+
         return btrfs_update_device(trans, device);
 }
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 9f697419ed8e..891e1c78e4f1 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -760,15 +760,9 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  * If warn is true, then emit a warning if the page is not uptodate and has
  * not been truncated.
  */
-static int __set_page_dirty(struct page *page,
+static void __set_page_dirty(struct page *page,
                 struct address_space *mapping, int warn)
 {
-        if (unlikely(!mapping))
-                return !TestSetPageDirty(page);
-
-        if (TestSetPageDirty(page))
-                return 0;
-
         spin_lock_irq(&mapping->tree_lock);
         if (page->mapping) {    /* Race with truncate? */
                 WARN_ON_ONCE(warn && !PageUptodate(page));
@@ -785,8 +779,6 @@ static int __set_page_dirty(struct page *page,
         }
         spin_unlock_irq(&mapping->tree_lock);
         __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-
-        return 1;
 }
 
 /*
@@ -816,6 +808,7 @@ static int __set_page_dirty(struct page *page,
  */
 int __set_page_dirty_buffers(struct page *page)
 {
+        int newly_dirty;
         struct address_space *mapping = page_mapping(page);
 
         if (unlikely(!mapping))
@@ -831,9 +824,12 @@ int __set_page_dirty_buffers(struct page *page)
                         bh = bh->b_this_page;
                 } while (bh != head);
         }
+        newly_dirty = !TestSetPageDirty(page);
         spin_unlock(&mapping->private_lock);
 
-        return __set_page_dirty(page, mapping, 1);
+        if (newly_dirty)
+                __set_page_dirty(page, mapping, 1);
+        return newly_dirty;
 }
 EXPORT_SYMBOL(__set_page_dirty_buffers);
 
@@ -1262,8 +1258,11 @@ void mark_buffer_dirty(struct buffer_head *bh)
                         return;
         }
 
-        if (!test_set_buffer_dirty(bh))
-                __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0);
+        if (!test_set_buffer_dirty(bh)) {
+                struct page *page = bh->b_page;
+                if (!TestSetPageDirty(page))
+                        __set_page_dirty(page, page_mapping(page), 0);
+        }
 }
 
 /*
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e2eab196875f..e0aa4fe4f596 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1122,7 +1122,8 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
         struct ext4_extent_idx *ix;
         struct ext4_extent *ex;
         ext4_fsblk_t block;
-        int depth, ee_len;
+        int depth;      /* Note, NOT eh_depth; depth from top of tree */
+        int ee_len;
 
         BUG_ON(path == NULL);
         depth = path->p_depth;
@@ -1179,7 +1180,8 @@ got_index:
                 if (bh == NULL)
                         return -EIO;
                 eh = ext_block_hdr(bh);
-                if (ext4_ext_check_header(inode, eh, depth)) {
+                /* subtract from p_depth to get proper eh_depth */
+                if (ext4_ext_check_header(inode, eh, path->p_depth - depth)) {
                         put_bh(bh);
                         return -EIO;
                 }
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 627f8c3337a3..2d2b3585ee91 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -698,6 +698,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
         struct inode *ret;
         ext4_group_t i;
         int free = 0;
+        static int once = 1;
         ext4_group_t flex_group;
 
         /* Cannot create files in a deleted directory */
@@ -719,7 +720,8 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
                 ret2 = find_group_flex(sb, dir, &group);
                 if (ret2 == -1) {
                         ret2 = find_group_other(sb, dir, &group);
-                        if (ret2 == 0 && printk_ratelimit())
+                        if (ret2 == 0 && once)
+                                once = 0;
                                 printk(KERN_NOTICE "ext4: find_group_flex "
                                        "failed, fallback succeeded dir %lu\n",
                                        dir->i_ino);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4415beeb0b62..9f61e62f435f 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1447,7 +1447,7 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac,
         struct ext4_free_extent *gex = &ac->ac_g_ex;
 
         BUG_ON(ex->fe_len <= 0);
-        BUG_ON(ex->fe_len >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+        BUG_ON(ex->fe_len > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
         BUG_ON(ex->fe_start >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
         BUG_ON(ac->ac_status != AC_STATUS_CONTINUE);
 
@@ -3292,7 +3292,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
         }
         BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
                         start > ac->ac_o_ex.fe_logical);
-        BUG_ON(size <= 0 || size >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+        BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
 
         /* now prepare goal request */
 
@@ -3589,6 +3589,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
                         struct super_block *sb, struct ext4_prealloc_space *pa)
 {
         ext4_group_t grp;
+        ext4_fsblk_t grp_blk;
 
         if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
                 return;
@@ -3603,8 +3604,12 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
         pa->pa_deleted = 1;
         spin_unlock(&pa->pa_lock);
 
-        /* -1 is to protect from crossing allocation group */
-        ext4_get_group_no_and_offset(sb, pa->pa_pstart - 1, &grp, NULL);
+        grp_blk = pa->pa_pstart;
+        /* If linear, pa_pstart may be in the next group when pa is used up */
+        if (pa->pa_linear)
+                grp_blk--;
+
+        ext4_get_group_no_and_offset(sb, grp_blk, &grp, NULL);
 
         /*
          * possible race:
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index f65953be39c0..9250067943d8 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2596,6 +2596,7 @@ static nfsd4_enc nfsd4_enc_ops[] = {
         [OP_LOOKUPP]            = (nfsd4_enc)nfsd4_encode_noop,
         [OP_NVERIFY]            = (nfsd4_enc)nfsd4_encode_noop,
         [OP_OPEN]               = (nfsd4_enc)nfsd4_encode_open,
+        [OP_OPENATTR]           = (nfsd4_enc)nfsd4_encode_noop,
         [OP_OPEN_CONFIRM]       = (nfsd4_enc)nfsd4_encode_open_confirm,
         [OP_OPEN_DOWNGRADE]     = (nfsd4_enc)nfsd4_encode_open_downgrade,
         [OP_PUTFH]              = (nfsd4_enc)nfsd4_encode_noop,