45 files changed, 223 insertions, 191 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 06e8ff12b97c..4230252fd689 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -11,7 +11,6 @@
 #include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/major.h>
-#include <linux/smp_lock.h>
 #include <linux/device_cgroup.h>
 #include <linux/highmem.h>
 #include <linux/blkdev.h>
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e9c874abc9e1..561438b6a50c 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -204,7 +204,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
        err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
                                  page->index << PAGE_CACHE_SHIFT, &len,
                                  ci->i_truncate_seq, ci->i_truncate_size,
-                                  &page, 1);
+                                  &page, 1, 0);
        if (err == -ENOENT)
                err = 0;
        if (err < 0) {
@@ -287,7 +287,7 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
        rc = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
                                 offset, &len,
                                 ci->i_truncate_seq, ci->i_truncate_size,
-                                 pages, nr_pages);
+                                 pages, nr_pages, 0);
        if (rc == -ENOENT)
                rc = 0;
        if (rc < 0)
@@ -774,7 +774,7 @@ get_more_pages:
                                            snapc, do_sync,
                                            ci->i_truncate_seq,
                                            ci->i_truncate_size,
-                                            &inode->i_mtime, true, 1);
+                                            &inode->i_mtime, true, 1, 0);
                                max_pages = req->r_num_pages;
                                alloc_page_vec(fsc, req);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 98ab13e2b71d..60d27bc9eb83 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1430,8 +1430,8 @@ static int try_nonblocking_invalidate(struct inode *inode)
            invalidating_gen == ci->i_rdcache_gen) {
                /* success. */
                dout("try_nonblocking_invalidate %p success\n", inode);
-                ci->i_rdcache_gen = 0;
+                /* save any racing async invalidate some trouble */
-                ci->i_rdcache_revoking = 0;
+                ci->i_rdcache_revoking = ci->i_rdcache_gen - 1;
                return 0;
        }
        dout("try_nonblocking_invalidate %p failed\n", inode);
@@ -2273,8 +2273,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 {
        struct ceph_inode_info *ci = ceph_inode(inode);
        int mds = session->s_mds;
-        unsigned seq = le32_to_cpu(grant->seq);
+        int seq = le32_to_cpu(grant->seq);
-        unsigned issue_seq = le32_to_cpu(grant->issue_seq);
        int newcaps = le32_to_cpu(grant->caps);
        int issued, implemented, used, wanted, dirty;
        u64 size = le64_to_cpu(grant->size);
@@ -2286,8 +2285,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
        int revoked_rdcache = 0;
        int queue_invalidate = 0;
-        dout("handle_cap_grant inode %p cap %p mds%d seq %u/%u %s\n",
+        dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
-             inode, cap, mds, seq, issue_seq, ceph_cap_string(newcaps));
+             inode, cap, mds, seq, ceph_cap_string(newcaps));
        dout(" size %llu max_size %llu, i_size %llu\n", size, max_size,
                inode->i_size);
@@ -2383,7 +2382,6 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
        }
        cap->seq = seq;
-        cap->issue_seq = issue_seq;
        /* file layout may have changed */
        ci->i_layout = grant->layout;
@@ -2691,6 +2689,11 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
                     NULL /* no caps context */);
        try_flush_caps(inode, session, NULL);
        up_read(&mdsc->snap_rwsem);
+        /* make sure we re-request max_size, if necessary */
+        spin_lock(&inode->i_lock);
+        ci->i_requested_max_size = 0;
+        spin_unlock(&inode->i_lock);
 }
 /*
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index e0a2dc6fcafc..7d447af84ec4 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -336,7 +336,10 @@ more:
                if (req->r_reply_info.dir_end) {
                        kfree(fi->last_name);
                        fi->last_name = NULL;
-                        fi->next_offset = 2;
+                        if (ceph_frag_is_rightmost(frag))
+                                fi->next_offset = 2;
+                        else
+                                fi->next_offset = 0;
                } else {
                        rinfo = &req->r_reply_info;
                        err = note_last_dentry(fi,
@@ -355,18 +358,22 @@ more:
                u64 pos = ceph_make_fpos(frag, off);
                struct ceph_mds_reply_inode *in =
                        rinfo->dir_in[off - fi->offset].in;
+                struct ceph_vino vino;
+                ino_t ino;
                dout("readdir off %d (%d/%d) -> %lld '%.*s' %p\n",
                     off, off - fi->offset, rinfo->dir_nr, pos,
                     rinfo->dir_dname_len[off - fi->offset],
                     rinfo->dir_dname[off - fi->offset], in);
                BUG_ON(!in);
                ftype = le32_to_cpu(in->mode) >> 12;
+                vino.ino = le64_to_cpu(in->ino);
+                vino.snap = le64_to_cpu(in->snapid);
+                ino = ceph_vino_to_ino(vino);
                if (filldir(dirent,
                            rinfo->dir_dname[off - fi->offset],
                            rinfo->dir_dname_len[off - fi->offset],
-                            pos,
+                            pos, ino, ftype) < 0) {
-                            le64_to_cpu(in->ino),
-                            ftype) < 0) {
                        dout("filldir stopping us...\n");
                        return 0;
                }
@@ -414,6 +421,7 @@ static void reset_readdir(struct ceph_file_info *fi)
                fi->last_readdir = NULL;
        }
        kfree(fi->last_name);
+        fi->last_name = NULL;
        fi->next_offset = 2;  /* compensate for . and .. */
        if (fi->dentry) {
                dput(fi->dentry);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index e77c28cf3690..8d79b8912e31 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -154,11 +154,13 @@ int ceph_open(struct inode *inode, struct file *file)
        }
        /*
-         * No need to block if we have any caps.  Update wanted set
+         * No need to block if we have caps on the auth MDS (for
+         * write) or any MDS (for read).  Update wanted set
         * asynchronously.
         */
        spin_lock(&inode->i_lock);
-        if (__ceph_is_any_real_caps(ci)) {
+        if (__ceph_is_any_real_caps(ci) &&
+            (((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
                int mds_wanted = __ceph_caps_mds_wanted(ci);
                int issued = __ceph_caps_issued(ci, NULL);
@@ -280,11 +282,12 @@ int ceph_release(struct inode *inode, struct file *file)
 static int striped_read(struct inode *inode,
                        u64 off, u64 len,
                        struct page **pages, int num_pages,
-                        int *checkeof)
+                        int *checkeof, bool align_to_pages)
 {
        struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
        struct ceph_inode_info *ci = ceph_inode(inode);
        u64 pos, this_len;
+        int io_align, page_align;
        int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */
        int left, pages_left;
        int read;
@@ -300,14 +303,19 @@ static int striped_read(struct inode *inode,
        page_pos = pages;
        pages_left = num_pages;
        read = 0;
+        io_align = off & ~PAGE_MASK;
 more:
+        if (align_to_pages)
+                page_align = (pos - io_align) & ~PAGE_MASK;
+        else
+                page_align = pos & ~PAGE_MASK;
        this_len = left;
        ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
                                  &ci->i_layout, pos, &this_len,
                                  ci->i_truncate_seq,
                                  ci->i_truncate_size,
-                                  page_pos, pages_left);
+                                  page_pos, pages_left, page_align);
        hit_stripe = this_len < left;
        was_short = ret >= 0 && ret < this_len;
        if (ret == -ENOENT)
@@ -374,26 +382,25 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
        dout("sync_read on file %p %llu~%u %s\n", file, off, len,
             (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
-        if (file->f_flags & O_DIRECT) {
+        if (file->f_flags & O_DIRECT)
-                pages = ceph_get_direct_page_vector(data, num_pages, off, len);
+                pages = ceph_get_direct_page_vector(data, num_pages);
+        else
-                /*
-                 * flush any page cache pages in this range.  this
-                 * will make concurrent normal and O_DIRECT io slow,
-                 * but it will at least behave sensibly when they are
-                 * in sequence.
-                 */
-        } else {
                pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
-        }
        if (IS_ERR(pages))
                return PTR_ERR(pages);
+        /*
+         * flush any page cache pages in this range.  this
+         * will make concurrent normal and sync io slow,
+         * but it will at least behave sensibly when they are
+         * in sequence.
+         */
        ret = filemap_write_and_wait(inode->i_mapping);
        if (ret < 0)
                goto done;
-        ret = striped_read(inode, off, len, pages, num_pages, checkeof);
+        ret = striped_read(inode, off, len, pages, num_pages, checkeof,
+                           file->f_flags & O_DIRECT);
        if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
                ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
@@ -448,6 +455,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
        int flags;
        int do_sync = 0;
        int check_caps = 0;
+        int page_align, io_align;
        int ret;
        struct timespec mtime = CURRENT_TIME;
@@ -462,6 +470,8 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
        else
                pos = *offset;
+        io_align = pos & ~PAGE_MASK;
        ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left);
        if (ret < 0)
                return ret;
@@ -486,20 +496,26 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
         */
 more:
        len = left;
+        if (file->f_flags & O_DIRECT)
+                /* write from beginning of first page, regardless of
+                   io alignment */
+                page_align = (pos - io_align) & ~PAGE_MASK;
+        else
+                page_align = pos & ~PAGE_MASK;
        req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
                                    ceph_vino(inode), pos, &len,
                                    CEPH_OSD_OP_WRITE, flags,
                                    ci->i_snap_realm->cached_context,
                                    do_sync,
                                    ci->i_truncate_seq, ci->i_truncate_size,
-                                    &mtime, false, 2);
+                                    &mtime, false, 2, page_align);
        if (!req)
                return -ENOMEM;
        num_pages = calc_pages_for(pos, len);
        if (file->f_flags & O_DIRECT) {
-                pages = ceph_get_direct_page_vector(data, num_pages, pos, len);
+                pages = ceph_get_direct_page_vector(data, num_pages);
                if (IS_ERR(pages)) {
                        ret = PTR_ERR(pages);
                        goto out;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 1d6a45b5a04c..bf1286588f26 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2,7 +2,6 @@
 #include <linux/module.h>
 #include <linux/fs.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/uaccess.h>
@@ -471,7 +470,9 @@ void ceph_fill_file_time(struct inode *inode, int issued,
        if (issued & (CEPH_CAP_FILE_EXCL|
                      CEPH_CAP_FILE_WR|
-                      CEPH_CAP_FILE_BUFFER)) {
+                      CEPH_CAP_FILE_BUFFER|
+                      CEPH_CAP_AUTH_EXCL|
+                      CEPH_CAP_XATTR_EXCL)) {
                if (timespec_compare(ctime, &inode->i_ctime) > 0) {
                        dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",
                             inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
@@ -511,7 +512,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
                        warn = 1;
                }
        } else {
-                /* we have no write caps; whatever the MDS says is true */
+                /* we have no write|excl caps; whatever the MDS says is true */
                if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) {
                        inode->i_ctime = *ctime;
                        inode->i_mtime = *mtime;
@@ -567,12 +568,17 @@ static int fill_inode(struct inode *inode,
        /*
         * provided version will be odd if inode value is projected,
-         * even if stable.  skip the update if we have a newer info
+         * even if stable.  skip the update if we have newer stable
-         * (e.g., due to inode info racing form multiple MDSs), or if
+         * info (ours>=theirs, e.g. due to racing mds replies), unless
-         * we are getting projected (unstable) inode info.
+         * we are getting projected (unstable) info (in which case the
+         * version is odd, and we want ours>theirs).
+         *   us   them
+         *   2    2     skip
+         *   3    2     skip
+         *   3    3     update
         */
        if (le64_to_cpu(info->version) > 0 &&
-            (ci->i_version & ~1) > le64_to_cpu(info->version))
+            (ci->i_version & ~1) >= le64_to_cpu(info->version))
                goto no_change;
        issued = __ceph_caps_issued(ci, &implemented);
@@ -606,7 +612,14 @@ static int fill_inode(struct inode *inode,
                            le32_to_cpu(info->time_warp_seq),
                            &ctime, &mtime, &atime);
-        ci->i_max_size = le64_to_cpu(info->max_size);
+        /* only update max_size on auth cap */
+        if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+            ci->i_max_size != le64_to_cpu(info->max_size)) {
+                dout("max_size %lld -> %llu\n", ci->i_max_size,
+                     le64_to_cpu(info->max_size));
+                ci->i_max_size = le64_to_cpu(info->max_size);
+        }
        ci->i_layout = info->layout;
        inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
@@ -1055,7 +1068,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                ininfo = rinfo->targeti.in;
                vino.ino = le64_to_cpu(ininfo->ino);
                vino.snap = le64_to_cpu(ininfo->snapid);
-                if (!dn->d_inode) {
+                in = dn->d_inode;
+                if (!in) {
                        in = ceph_get_inode(sb, vino);
                        if (IS_ERR(in)) {
                                pr_err("fill_trace bad get_inode "
@@ -1386,11 +1400,8 @@ static void ceph_invalidate_work(struct work_struct *work)
        spin_lock(&inode->i_lock);
        dout("invalidate_pages %p gen %d revoking %d\n", inode,
             ci->i_rdcache_gen, ci->i_rdcache_revoking);
-        if (ci->i_rdcache_gen == 0 ||
+        if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
-            ci->i_rdcache_revoking != ci->i_rdcache_gen) {
-                BUG_ON(ci->i_rdcache_revoking > ci->i_rdcache_gen);
                /* nevermind! */
-                ci->i_rdcache_revoking = 0;
                spin_unlock(&inode->i_lock);
                goto out;
        }
@@ -1400,15 +1411,16 @@ static void ceph_invalidate_work(struct work_struct *work)
        ceph_invalidate_nondirty_pages(inode->i_mapping);
        spin_lock(&inode->i_lock);
-        if (orig_gen == ci->i_rdcache_gen) {
+        if (orig_gen == ci->i_rdcache_gen &&
+            orig_gen == ci->i_rdcache_revoking) {
                dout("invalidate_pages %p gen %d successful\n", inode,
                     ci->i_rdcache_gen);
-                ci->i_rdcache_gen = 0;
+                ci->i_rdcache_revoking--;
-                ci->i_rdcache_revoking = 0;
                check = 1;
        } else {
-                dout("invalidate_pages %p gen %d raced, gen now %d\n",
+                dout("invalidate_pages %p gen %d raced, now %d revoking %d\n",
-                     inode, orig_gen, ci->i_rdcache_gen);
+                     inode, orig_gen, ci->i_rdcache_gen,
+                     ci->i_rdcache_revoking);
        }
        spin_unlock(&inode->i_lock);
@@ -1739,7 +1751,7 @@ int ceph_do_getattr(struct inode *inode, int mask)
                return 0;
        }
-        dout("do_getattr inode %p mask %s\n", inode, ceph_cap_string(mask));
+        dout("do_getattr inode %p mask %s mode 0%o\n", inode, ceph_cap_string(mask), inode->i_mode);
        if (ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
                return 0;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 3142b15940c2..098b18508479 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -6,7 +6,6 @@
 #include <linux/sched.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include "super.h"
 #include "mds_client.h"
@@ -529,6 +528,9 @@ static void __register_request(struct ceph_mds_client *mdsc,
        ceph_mdsc_get_request(req);
        __insert_request(mdsc, req);
+        req->r_uid = current_fsuid();
+        req->r_gid = current_fsgid();
        if (dir) {
                struct ceph_inode_info *ci = ceph_inode(dir);
@@ -1588,8 +1590,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
        head->mdsmap_epoch = cpu_to_le32(mdsc->mdsmap->m_epoch);
        head->op = cpu_to_le32(req->r_op);
-        head->caller_uid = cpu_to_le32(current_fsuid());
+        head->caller_uid = cpu_to_le32(req->r_uid);
-        head->caller_gid = cpu_to_le32(current_fsgid());
+        head->caller_gid = cpu_to_le32(req->r_gid);
        head->args = req->r_args;
        ceph_encode_filepath(&p, end, ino1, path1);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index d66d63c72355..9341fd4f1432 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -170,6 +170,8 @@ struct ceph_mds_request {
        union ceph_mds_request_args r_args;
        int r_fmode;        /* file mode, if expecting cap */
+        uid_t r_uid;
+        gid_t r_gid;
        /* for choosing which mds to send this request to */
        int r_direct_mode;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1886294e12f7..7f01728a4657 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -293,9 +293,7 @@ struct ceph_inode_info {
        int i_rd_ref, i_rdcache_ref, i_wr_ref;
        int i_wrbuffer_ref, i_wrbuffer_ref_head;
        u32 i_shared_gen;       /* increment each time we get FILE_SHARED */
-        u32 i_rdcache_gen;      /* we increment this each time we get
+        u32 i_rdcache_gen;      /* incremented each time we get FILE_CACHE. */
-                                   FILE_CACHE.  If it's non-zero, we
-                                   _may_ have cached pages. */
        u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */
        struct list_head i_unsafe_writes; /* uncommitted sync writes */
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 410ed188faa1..a60579b007b0 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -19,7 +19,6 @@
 #include <linux/compiler.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/ioctl.h>
 #include <linux/if.h>
 #include <linux/if_bridge.h>
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index 253732382d37..2720178b7718 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -28,7 +28,6 @@
 #include <linux/key.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/file.h>
 #include <linux/crypto.h>
 #include "ecryptfs_kernel.h"
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 2fedaf8b5012..acf8695fa8f0 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -27,7 +27,6 @@
 #include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/parser.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/exportfs.h>
 #include <linux/vfs.h>
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bf5ae883b1bd..eb3bc2fe647e 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -331,6 +331,30 @@ mext_out:
                return err;
        }
+        case FITRIM:
+        {
+                struct super_block *sb = inode->i_sb;
+                struct fstrim_range range;
+                int ret = 0;
+                if (!capable(CAP_SYS_ADMIN))
+                        return -EPERM;
+                if (copy_from_user(&range, (struct fstrim_range *)arg,
+                    sizeof(range)))
+                        return -EFAULT;
+                ret = ext4_trim_fs(sb, &range);
+                if (ret < 0)
+                        return ret;
+                if (copy_to_user((struct fstrim_range *)arg, &range,
+                    sizeof(range)))
+                        return -EFAULT;
+                return 0;
+        }
        default:
                return -ENOTTY;
        }
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 7f5451cd1d38..beacce11ac50 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -237,8 +237,6 @@ static void ext4_end_bio(struct bio *bio, int error)
                        } while (bh != head);
                }
-                put_io_page(io_end->pages[i]);
                /*
                 * If this is a partial write which happened to make
                 * all buffers uptodate then we can optimize away a
@@ -248,6 +246,8 @@ static void ext4_end_bio(struct bio *bio, int error)
                 */
                if (!partial_write)
                        SetPageUptodate(page);
+                put_io_page(io_end->pages[i]);
        }
        io_end->num_io_pages = 0;
        inode = io_end->inode;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 61182fe6254e..e32195d6aac3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1197,7 +1197,6 @@ static const struct super_operations ext4_sops = {
        .quota_write    = ext4_quota_write,
 #endif
        .bdev_try_to_free_page = bdev_try_to_free_page,
-        .trim_fs        = ext4_trim_fs
 };
 static const struct super_operations ext4_nojournal_sops = {
@@ -2799,9 +2798,6 @@ static void ext4_clear_request_list(void)
        struct ext4_li_request *elr;
        mutex_lock(&ext4_li_info->li_list_mtx);
-        if (list_empty(&ext4_li_info->li_request_list))
-                return;
        list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
                elr = list_entry(pos, struct ext4_li_request,
                                 lr_request);
@@ -3268,13 +3264,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
         * Test whether we have more sectors than will fit in sector_t,
         * and whether the max offset is addressable by the page cache.
         */
-        ret = generic_check_addressable(sb->s_blocksize_bits,
+        err = generic_check_addressable(sb->s_blocksize_bits,
                                        ext4_blocks_count(es));
-        if (ret) {
+        if (err) {
                ext4_msg(sb, KERN_ERR, "filesystem"
                         " too large to mount safely on this system");
                if (sizeof(sector_t) < 8)
                        ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
+                ret = err;
                goto failed_mount;
        }
diff --git a/fs/ioctl.c b/fs/ioctl.c
index e92fdbb3bc3a..d6cc16476620 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -6,7 +6,6 @@
 #include <linux/syscalls.h>
 #include <linux/mm.h>
-#include <linux/smp_lock.h>
 #include <linux/capability.h>
 #include <linux/file.h>
 #include <linux/fs.h>
@@ -530,41 +529,6 @@ static int ioctl_fsthaw(struct file *filp)
        return thaw_super(sb);
 }
-static int ioctl_fstrim(struct file *filp, void __user *argp)
-{
-        struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
-        struct fstrim_range range;
-        int ret = 0;
-        if (!capable(CAP_SYS_ADMIN))
-                return -EPERM;
-        /* If filesystem doesn't support trim feature, return. */
-        if (sb->s_op->trim_fs == NULL)
-                return -EOPNOTSUPP;
-        /* If a blockdevice-backed filesystem isn't specified, return EINVAL. */
-        if (sb->s_bdev == NULL)
-                return -EINVAL;
-        if (argp == NULL) {
-                range.start = 0;
-                range.len = ULLONG_MAX;
-                range.minlen = 0;
-        } else if (copy_from_user(&range, argp, sizeof(range)))
-                return -EFAULT;
-        ret = sb->s_op->trim_fs(sb, &range);
-        if (ret < 0)
-                return ret;
-        if ((argp != NULL) &&
-            (copy_to_user(argp, &range, sizeof(range))))
-                return -EFAULT;
-        return 0;
-}
 /*
 * When you add any new common ioctls to the switches above and below
 * please update compat_sys_ioctl() too.
@@ -615,10 +579,6 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
                error = ioctl_fsthaw(filp);
                break;
-        case FITRIM:
-                error = ioctl_fstrim(filp, argp);
-                break;
        case FS_IOC_FIEMAP:
                return ioctl_fiemap(filp, arg);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index c590d155c095..f837ba953529 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -899,6 +899,14 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
        /* journal descriptor can store up to n blocks -bzzz */
        journal->j_blocksize = blocksize;
+        journal->j_dev = bdev;
+        journal->j_fs_dev = fs_dev;
+        journal->j_blk_offset = start;
+        journal->j_maxlen = len;
+        bdevname(journal->j_dev, journal->j_devname);
+        p = journal->j_devname;
+        while ((p = strchr(p, '/')))
+                *p = '!';
        jbd2_stats_proc_init(journal);
        n = journal->j_blocksize / sizeof(journal_block_tag_t);
        journal->j_wbufsize = n;
@@ -908,14 +916,6 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
                        __func__);
                goto out_err;
        }
-        journal->j_dev = bdev;
-        journal->j_fs_dev = fs_dev;
-        journal->j_blk_offset = start;
-        journal->j_maxlen = len;
-        bdevname(journal->j_dev, journal->j_devname);
-        p = journal->j_devname;
-        while ((p = strchr(p, '/')))
-                *p = '!';
        bh = __getblk(journal->j_dev, start, journal->j_blocksize);
        if (!bh) {
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index d5bb86866e6c..25509eb28fd7 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -14,7 +14,6 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/lockd.h>
-#include <linux/smp_lock.h>
 #include <linux/kthread.h>
 #define NLMDBG_FACILITY         NLMDBG_CLIENT
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 47ea1e1925b8..332c54cf75e0 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -7,7 +7,6 @@
 */
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/errno.h>
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 25e21e4023b2..ed0c59fe23ce 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -124,7 +124,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
                        continue;
                if (host->h_server != ni->server)
                        continue;
-                if (ni->server &&
+                if (ni->server && ni->src_len != 0 &&
                    !rpc_cmp_addr(nlm_srcaddr(host), ni->src_sap))
                        continue;
@@ -167,6 +167,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
        host->h_addrlen = ni->salen;
        rpc_set_port(nlm_addr(host), 0);
        memcpy(nlm_srcaddr(host), ni->src_sap, ni->src_len);
+        host->h_srcaddrlen = ni->src_len;
        host->h_version    = ni->version;
        host->h_proto      = ni->protocol;
        host->h_rpcclnt    = NULL;
@@ -238,9 +239,6 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
                                     const char *hostname,
                                     int noresvport)
 {
-        const struct sockaddr source = {
-                .sa_family      = AF_UNSPEC,
-        };
        struct nlm_lookup_host_info ni = {
                .server         = 0,
                .sap            = sap,
@@ -249,8 +247,6 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
                .version        = version,
                .hostname       = hostname,
                .hostname_len   = strlen(hostname),
-                .src_sap        = &source,
-                .src_len        = sizeof(source),
                .noresvport     = noresvport,
        };
@@ -357,7 +353,6 @@ nlm_bind_host(struct nlm_host *host)
                        .protocol       = host->h_proto,
                        .address        = nlm_addr(host),
                        .addrsize       = host->h_addrlen,
-                        .saddress       = nlm_srcaddr(host),
                        .timeout        = &timeparms,
                        .servername     = host->h_name,
                        .program        = &nlm_program,
@@ -376,6 +371,8 @@ nlm_bind_host(struct nlm_host *host)
                        args.flags |= RPC_CLNT_CREATE_HARDRTRY;
                if (host->h_noresvport)
                        args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
+                if (host->h_srcaddrlen)
+                        args.saddress = nlm_srcaddr(host);
                clnt = rpc_create(&args);
                if (!IS_ERR(clnt))
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index a336e832475d..38d261192453 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -9,7 +9,6 @@
 #include <linux/types.h>
 #include <linux/time.h>
-#include <linux/smp_lock.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index c462d346acbd..ef5659b211e9 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -25,7 +25,6 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/nlm.h>
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index c3069f38d602..0caea5310ac3 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -9,7 +9,6 @@
 #include <linux/types.h>
 #include <linux/time.h>
-#include <linux/smp_lock.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
diff --git a/fs/locks.c b/fs/locks.c
index 0e62dd35d088..8729347bcd1a 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -122,7 +122,6 @@
 #include <linux/module.h>
 #include <linux/security.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/syscalls.h>
 #include <linux/time.h>
 #include <linux/rcupdate.h>
diff --git a/fs/namespace.c b/fs/namespace.c
index 8a415c9c5e55..3dbfc072ec70 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -13,7 +13,6 @@
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/percpu.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/acct.h>
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index aac8832e919e..f22b12e7d337 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -19,7 +19,6 @@
 #include <linux/mm.h>
 #include <asm/uaccess.h>
 #include <asm/byteorder.h>
-#include <linux/smp_lock.h>
 #include <linux/ncp_fs.h>
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index 6c754f70c529..cb50aaf981df 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -17,7 +17,6 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/ncp_fs.h>
 #include "ncplib_kernel.h"
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index d290545aa0c4..8fb93b604e73 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -26,7 +26,6 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/vfs.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index c2a1f9a155c3..d40a547e3377 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -17,7 +17,6 @@
 #include <linux/mount.h>
 #include <linux/slab.h>
 #include <linux/highuid.h>
-#include <linux/smp_lock.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index aeec017fe814..93a8b3bd69e3 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -9,7 +9,6 @@
 #include <linux/completion.h>
 #include <linux/ip.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfs_fs.h>
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 232a7eead33a..1fd62fc49be3 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/nfs4.h>
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 07ac3847e562..662df2a5fad5 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -34,6 +34,7 @@
 #include <linux/mount.h>
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
+#include <linux/kmemleak.h>
 #include "delegation.h"
 #include "iostat.h"
@@ -194,9 +195,13 @@ typedef struct {
 static
 struct nfs_cache_array *nfs_readdir_get_array(struct page *page)
 {
+        void *ptr;
        if (page == NULL)
                return ERR_PTR(-EIO);
-        return (struct nfs_cache_array *)kmap(page);
+        ptr = kmap(page);
+        if (ptr == NULL)
+                return ERR_PTR(-ENOMEM);
+        return ptr;
 }
 static
@@ -213,6 +218,9 @@ int nfs_readdir_clear_array(struct page *page, gfp_t mask)
 {
        struct nfs_cache_array *array = nfs_readdir_get_array(page);
        int i;
+        if (IS_ERR(array))
+                return PTR_ERR(array);
        for (i = 0; i < array->size; i++)
                kfree(array->array[i].string.name);
        nfs_readdir_release_array(page);
@@ -231,6 +239,11 @@ int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int le
        string->name = kmemdup(name, len, GFP_KERNEL);
        if (string->name == NULL)
                return -ENOMEM;
+        /*
+         * Avoid a kmemleak false positive. The pointer to the name is stored
+         * in a page cache page which kmemleak does not scan.
+         */
+        kmemleak_not_leak(string->name);
        string->hash = full_name_hash(name, len);
        return 0;
 }
@@ -244,7 +257,7 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
        if (IS_ERR(array))
                return PTR_ERR(array);
-        ret = -EIO;
+        ret = -ENOSPC;
        if (array->size >= MAX_READDIR_ARRAY)
                goto out;
@@ -255,9 +268,9 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
        if (ret)
                goto out;
        array->last_cookie = entry->cookie;
+        array->size++;
        if (entry->eof == 1)
                array->eof_index = array->size;
-        array->size++;
 out:
        nfs_readdir_release_array(page);
        return ret;
@@ -272,7 +285,7 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
        if (diff < 0)
                goto out_eof;
        if (diff >= array->size) {
-                if (array->eof_index > 0)
+                if (array->eof_index >= 0)
                        goto out_eof;
                desc->current_index += array->size;
                return -EAGAIN;
@@ -281,8 +294,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
        index = (unsigned int)diff;
        *desc->dir_cookie = array->array[index].cookie;
        desc->cache_entry_index = index;
-        if (index == array->eof_index)
-                desc->eof = 1;
        return 0;
 out_eof:
        desc->eof = 1;
@@ -296,17 +307,17 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
        int status = -EAGAIN;
        for (i = 0; i < array->size; i++) {
-                if (i == array->eof_index) {
-                        desc->eof = 1;
-                        status = -EBADCOOKIE;
-                }
                if (array->array[i].cookie == *desc->dir_cookie) {
                        desc->cache_entry_index = i;
                        status = 0;
-                        break;
+                        goto out;
                }
        }
+        if (i == array->eof_index) {
+                desc->eof = 1;
+                status = -EBADCOOKIE;
+        }
+out:
        return status;
 }
@@ -449,7 +460,7 @@ out:
 /* Perform conversion from xdr to cache array */
 static
-void nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry,
+int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry,
                                void *xdr_page, struct page *page, unsigned int buflen)
 {
        struct xdr_stream stream;
@@ -471,21 +482,29 @@ void nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *e
        do {
                status = xdr_decode(desc, entry, &stream);
-                if (status != 0)
+                if (status != 0) {
+                        if (status == -EAGAIN)
+                                status = 0;
                        break;
+                }
-                if (nfs_readdir_add_to_array(entry, page) == -1)
-                        break;
                if (desc->plus == 1)
                        nfs_prime_dcache(desc->file->f_path.dentry, entry);
+                status = nfs_readdir_add_to_array(entry, page);
+                if (status != 0)
+                        break;
        } while (!entry->eof);
        if (status == -EBADCOOKIE && entry->eof) {
                array = nfs_readdir_get_array(page);
-                array->eof_index = array->size - 1;
+                if (!IS_ERR(array)) {
-                status = 0;
+                        array->eof_index = array->size;
-                nfs_readdir_release_array(page);
+                        status = 0;
+                        nfs_readdir_release_array(page);
+                }
        }
+        return status;
 }
 static
@@ -537,7 +556,7 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
        struct nfs_entry entry;
        struct file     *file = desc->file;
        struct nfs_cache_array *array;
-        int status = 0;
+        int status = -ENOMEM;
        unsigned int array_size = ARRAY_SIZE(pages);
        entry.prev_cookie = 0;
@@ -549,6 +568,10 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
                goto out;
        array = nfs_readdir_get_array(page);
+        if (IS_ERR(array)) {
+                status = PTR_ERR(array);
+                goto out;
+        }
        memset(array, 0, sizeof(struct nfs_cache_array));
        array->eof_index = -1;
@@ -556,12 +579,19 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
        if (!pages_ptr)
                goto out_release_array;
        do {
+                unsigned int pglen;
                status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode);
                if (status < 0)
                        break;
-                nfs_readdir_page_filler(desc, &entry, pages_ptr, page, array_size * PAGE_SIZE);
+                pglen = status;
-        } while (array->eof_index < 0 && array->size < MAX_READDIR_ARRAY);
+                status = nfs_readdir_page_filler(desc, &entry, pages_ptr, page, pglen);
+                if (status < 0) {
+                        if (status == -ENOSPC)
+                                status = 0;
+                        break;
+                }
+        } while (array->eof_index < 0);
        nfs_readdir_free_large_page(pages_ptr, pages, array_size);
 out_release_array:
@@ -582,8 +612,10 @@ static
 int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
 {
        struct inode    *inode = desc->file->f_path.dentry->d_inode;
+        int ret;
-        if (nfs_readdir_xdr_to_array(desc, page, inode) < 0)
+        ret = nfs_readdir_xdr_to_array(desc, page, inode);
+        if (ret < 0)
                goto error;
        SetPageUptodate(page);
@@ -595,7 +627,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
        return 0;
 error:
        unlock_page(page);
-        return -EIO;
+        return ret;
 }
 static
@@ -608,12 +640,8 @@ void cache_page_release(nfs_readdir_descriptor_t *desc)
 static
 struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
 {
-        struct page *page;
+        return read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping,
-        page = read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping,
                        desc->page_index, (filler_t *)nfs_readdir_filler, desc);
-        if (IS_ERR(page))
-                desc->eof = 1;
-        return page;
 }
 /*
@@ -639,8 +667,10 @@ int find_cache_page(nfs_readdir_descriptor_t *desc)
 static inline
 int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
 {
-        int res = -EAGAIN;
+        int res;
+        if (desc->page_index == 0)
+                desc->current_index = 0;
        while (1) {
                res = find_cache_page(desc);
                if (res != -EAGAIN)
@@ -670,6 +700,8 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
        struct dentry *dentry = NULL;
        array = nfs_readdir_get_array(desc->page);
+        if (IS_ERR(array))
+                return PTR_ERR(array);
        for (i = desc->cache_entry_index; i < array->size; i++) {
                d_type = DT_UNKNOWN;
@@ -685,11 +717,9 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
                        *desc->dir_cookie = array->array[i+1].cookie;
                else
                        *desc->dir_cookie = array->last_cookie;
-                if (i == array->eof_index) {
-                        desc->eof = 1;
-                        break;
-                }
        }
+        if (i == array->eof_index)
+                desc->eof = 1;
        nfs_readdir_release_array(desc->page);
        cache_page_release(desc);
@@ -1345,12 +1375,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
                                res = NULL;
                                goto out;
                        /* This turned out not to be a regular file */
-                        case -EISDIR:
                        case -ENOTDIR:
                                goto no_open;
                        case -ELOOP:
                                if (!(nd->intent.open.flags & O_NOFOLLOW))
                                        goto no_open;
+                        /* case -EISDIR: */
                        /* case -EINVAL: */
                        default:
                                res = ERR_CAST(inode);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index e6bf45710cc7..2563f765c9b4 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -423,7 +423,7 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy)
        struct page **page;
        size_t hdrlen;
        unsigned int pglen, recvd;
-        int status, nr = 0;
+        int status;
        if ((status = ntohl(*p++)))
                return nfs_stat_to_errno(status);
@@ -443,7 +443,7 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy)
        if (pglen > recvd)
                pglen = recvd;
        page = rcvbuf->pages;
-        return nr;
+        return pglen;
 }
 static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index d9a5e832c257..748dc91a4a14 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -555,7 +555,7 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res
        struct page **page;
        size_t hdrlen;
        u32 recvd, pglen;
-        int status, nr = 0;
+        int status;
        status = ntohl(*p++);
        /* Decode post_op_attrs */
@@ -586,7 +586,7 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res
                pglen = recvd;
        page = rcvbuf->pages;
-        return nr;
+        return pglen;
 }
 __be32 *
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0f24cdf2cb13..6a653ffd8e4e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2852,8 +2852,10 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
        nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args);
        res.pgbase = args.pgbase;
        status = nfs4_call_sync(NFS_SERVER(dir), &msg, &args, &res, 0);
-        if (status == 0)
+        if (status >= 0) {
                memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE);
+                status += args.pgbase;
+        }
        nfs_invalidate_atime(dir);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index f313c4cce7e4..b7a204ff6fe1 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4518,7 +4518,7 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n
        xdr_read_pages(xdr, pglen);
-        return 0;
+        return pglen;
 }
 static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 0a42e8f4adcb..3c045044fca2 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -39,7 +39,6 @@
 #include <linux/nfs_mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/lockd/bind.h>
-#include <linux/smp_lock.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/mnt_namespace.h>
@@ -67,6 +66,12 @@
 #define NFSDBG_FACILITY         NFSDBG_VFS
+#ifdef CONFIG_NFS_V3
+#define NFS_DEFAULT_VERSION 3
+#else
+#define NFS_DEFAULT_VERSION 2
+#endif
 enum {
        /* Mount options that take no arguments */
        Opt_soft, Opt_hard,
@@ -2277,7 +2282,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
        };
        int error = -ENOMEM;
-        data = nfs_alloc_parsed_mount_data(3);
+        data = nfs_alloc_parsed_mount_data(NFS_DEFAULT_VERSION);
        mntfh = nfs_alloc_fhandle();
        if (data == NULL || mntfh == NULL)
                goto out_free_fh;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ad2bfa68d534..116cab970e0f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2262,7 +2262,7 @@ nfs4_file_downgrade(struct nfs4_file *fp, unsigned int share_access)
 * Spawn a thread to perform a recall on the delegation represented
 * by the lease (file_lock)
 *
- * Called from break_lease() with lock_kernel() held.
+ * Called from break_lease() with lock_flocks() held.
 * Note: we assume break_lease will only call this *once* for any given
 * lease.
 */
@@ -2286,7 +2286,7 @@ void nfsd_break_deleg_cb(struct file_lock *fl)
        list_add_tail(&dp->dl_recall_lru, &del_recall_lru);
        spin_unlock(&recall_lock);
-        /* only place dl_time is set. protected by lock_kernel*/
+        /* only place dl_time is set. protected by lock_flocks*/
        dp->dl_time = get_seconds();
        /*
@@ -2303,7 +2303,7 @@ void nfsd_break_deleg_cb(struct file_lock *fl)
 /*
 * The file_lock is being reapd.
 *
- * Called by locks_free_lock() with lock_kernel() held.
+ * Called by locks_free_lock() with lock_flocks() held.
 */
 static
 void nfsd_release_deleg_cb(struct file_lock *fl)
@@ -2318,7 +2318,7 @@ void nfsd_release_deleg_cb(struct file_lock *fl)
 }
 /*
- * Called from setlease() with lock_kernel() held
+ * Called from setlease() with lock_flocks() held
 */
 static
 int nfsd_same_client_deleg_cb(struct file_lock *onlist, struct file_lock *try)
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index f02c0ef31578..cfeab7ce3697 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -41,7 +41,6 @@
 #include <linux/mount.h>
 #include <linux/seq_file.h>
 #include <linux/quotaops.h>
-#include <linux/smp_lock.h>
 #define MLOG_MASK_PREFIX ML_SUPER
 #include <cluster/masklog.h>
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 9c2b5f484879..3ddb6068177c 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -16,7 +16,6 @@
 #include <linux/limits.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/sysctl.h>
 #include <linux/slab.h>
diff --git a/fs/read_write.c b/fs/read_write.c
index 431a0ed610c8..5d431bacbea9 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -9,7 +9,6 @@
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/uio.h>
-#include <linux/smp_lock.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
 #include <linux/module.h>
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 41656d40dc5c..0bae036831e2 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -8,7 +8,6 @@
 #include <linux/reiserfs_acl.h>
 #include <linux/reiserfs_xattr.h>
 #include <linux/exportfs.h>
-#include <linux/smp_lock.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index adf22b485cea..bd9763e76bae 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -9,7 +9,6 @@
 #include <linux/time.h>
 #include <asm/uaccess.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/compat.h>
 /*
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 076c8b194682..d31bce1a9f90 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -43,7 +43,6 @@
 #include <linux/fcntl.h>
 #include <linux/stat.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/workqueue.h>
 #include <linux/writeback.h>
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 3bf7a6457f4d..b243117b8752 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -28,7 +28,6 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/crc32.h>
-#include <linux/smp_lock.h>
 struct file_system_type reiserfs_fs_type;