11 files changed, 73 insertions, 80 deletions

diff --git a/fs/aio.c b/fs/aio.c
index dbe699e9828c..ea2e19820381 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1562,6 +1562,7 @@ int fastcall io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
                 fput(file);
                 return -EAGAIN;
         }
+        req->ki_filp = file;
         if (iocb->aio_flags & IOCB_FLAG_RESFD) {
                 /*
                  * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
@@ -1576,7 +1577,6 @@ int fastcall io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
                 }
         }
 
-        req->ki_filp = file;
         ret = put_user(req->ki_key, &user_iocb->aio_key);
         if (unlikely(ret)) {
                 dprintk("EFAULT: aio_key\n");
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 861141b4f6d6..fcb3405bb14e 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -742,6 +742,7 @@ static int load_flat_file(struct linux_binprm * bprm,
          * __start to address 4 so that is okay).
          */
         if (rev > OLD_FLAT_VERSION) {
+                unsigned long persistent = 0;
                 for (i=0; i < relocs; i++) {
                         unsigned long addr, relval;
 
@@ -749,6 +750,8 @@ static int load_flat_file(struct linux_binprm * bprm,
                            relocated (of course, the address has to be
                            relocated first).  */
                         relval = ntohl(reloc[i]);
+                        if (flat_set_persistent (relval, &persistent))
+                                continue;
                         addr = flat_get_relocate_addr(relval);
                         rp = (unsigned long *) calc_reloc(addr, libinfo, id, 1);
                         if (rp == (unsigned long *)RELOC_FAILED) {
@@ -757,7 +760,8 @@ static int load_flat_file(struct linux_binprm * bprm,
                         }
 
                         /* Get the pointer's value.  */
-                        addr = flat_get_addr_from_rp(rp, relval, flags);
+                        addr = flat_get_addr_from_rp(rp, relval, flags,
+                                                        &persistent);
                         if (addr != 0) {
                                 /*
                                  * Do the relocation.  PIC relocs in the data section are
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index d098c7af0d22..d120ec39bcb0 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -485,8 +485,10 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
                         return nlm_granted;
                 /* Create host handle for callback */
                 host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len);
-                if (host == NULL)
+                if (host == NULL) {
+                        kfree(conf);
                         return nlm_lck_denied_nolocks;
+                }
                 block = nlmsvc_create_block(rqstp, host, file, lock, cookie);
                 if (block == NULL) {
                         kfree(conf);
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index a49f9feff776..a204484072f3 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -588,16 +588,6 @@ static int nfs_init_server(struct nfs_server *server, const struct nfs_mount_dat
         server->namelen  = data->namlen;
         /* Create a client RPC handle for the NFSv3 ACL management interface */
         nfs_init_server_aclclient(server);
-        if (clp->cl_nfsversion == 3) {
-                if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
-                        server->namelen = NFS3_MAXNAMLEN;
-                if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
-                        server->caps |= NFS_CAP_READDIRPLUS;
-        } else {
-                if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
-                        server->namelen = NFS2_MAXNAMLEN;
-        }
-
         dprintk("<-- nfs_init_server() = 0 [new %p]\n", clp);
         return 0;
 
@@ -794,6 +784,16 @@ struct nfs_server *nfs_create_server(const struct nfs_mount_data *data,
         error = nfs_probe_fsinfo(server, mntfh, &fattr);
         if (error < 0)
                 goto error;
+        if (server->nfs_client->rpc_ops->version == 3) {
+                if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
+                        server->namelen = NFS3_MAXNAMLEN;
+                if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+                        server->caps |= NFS_CAP_READDIRPLUS;
+        } else {
+                if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
+                        server->namelen = NFS2_MAXNAMLEN;
+        }
+
         if (!(fattr.valid & NFS_ATTR_FATTR)) {
                 error = server->nfs_client->rpc_ops->getattr(server, mntfh, &fattr);
                 if (error < 0) {
@@ -984,6 +984,9 @@ struct nfs_server *nfs4_create_server(const struct nfs4_mount_data *data,
         if (error < 0)
                 goto error;
 
+        if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
+                server->namelen = NFS4_MAXNAMLEN;
+
         BUG_ON(!server->nfs_client);
         BUG_ON(!server->nfs_client->rpc_ops);
         BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
@@ -1056,6 +1059,9 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
         if (error < 0)
                 goto error;
 
+        if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
+                server->namelen = NFS4_MAXNAMLEN;
+
         dprintk("Referral FSID: %llx:%llx\n",
                 (unsigned long long) server->fsid.major,
                 (unsigned long long) server->fsid.minor);
@@ -1115,6 +1121,9 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
         if (error < 0)
                 goto out_free_server;
 
+        if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
+                server->namelen = NFS4_MAXNAMLEN;
+
         dprintk("Cloned FSID: %llx:%llx\n",
                 (unsigned long long) server->fsid.major,
                 (unsigned long long) server->fsid.minor);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index ea97408e423e..e4a04d16b8b0 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1162,6 +1162,8 @@ static struct dentry *nfs_readdir_lookup(nfs_readdir_descriptor_t *desc)
         }
         if (!desc->plus || !(entry->fattr->valid & NFS_ATTR_FATTR))
                 return NULL;
+        if (name.len > NFS_SERVER(dir)->namelen)
+                return NULL;
         /* Note: caller is already holding the dir->i_mutex! */
         dentry = d_alloc(parent, &name);
         if (dentry == NULL)
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index d1cbf0a0fbb2..522e5ad4d8ad 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -175,6 +175,9 @@ next_component:
                 path++;
         name.len = path - (const char *) name.name;
 
+        if (name.len > NFS4_MAXNAMLEN)
+                return -ENAMETOOLONG;
+
 eat_dot_dir:
         while (*path == '/')
                 path++;
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index de984d272576..d272847d5a07 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -514,8 +514,10 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
         ac->ac_bh = osb->local_alloc_bh;
         status = 0;
 bail:
-        if (status < 0 && local_alloc_inode)
+        if (status < 0 && local_alloc_inode) {
+                mutex_unlock(&local_alloc_inode->i_mutex);
                 iput(local_alloc_inode);
+        }
 
         mlog_exit(status);
         return status;
diff --git a/fs/splice.c b/fs/splice.c
index c010a72ca2d2..e95a36228863 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1224,6 +1224,33 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 }
 
 /*
+ * Do a copy-from-user while holding the mmap_semaphore for reading, in a
+ * manner safe from deadlocking with simultaneous mmap() (grabbing mmap_sem
+ * for writing) and page faulting on the user memory pointed to by src.
+ * This assumes that we will very rarely hit the partial != 0 path, or this
+ * will not be a win.
+ */
+static int copy_from_user_mmap_sem(void *dst, const void __user *src, size_t n)
+{
+        int partial;
+
+        pagefault_disable();
+        partial = __copy_from_user_inatomic(dst, src, n);
+        pagefault_enable();
+
+        /*
+         * Didn't copy everything, drop the mmap_sem and do a faulting copy
+         */
+        if (unlikely(partial)) {
+                up_read(&current->mm->mmap_sem);
+                partial = copy_from_user(dst, src, n);
+                down_read(&current->mm->mmap_sem);
+        }
+
+        return partial;
+}
+
+/*
  * Map an iov into an array of pages and offset/length tupples. With the
  * partial_page structure, we can map several non-contiguous ranges into
  * our ones pages[] map instead of splitting that operation into pieces.
@@ -1236,31 +1263,26 @@ static int get_iovec_page_array(const struct iovec __user *iov,
 {
         int buffers = 0, error = 0;
 
-        /*
-         * It's ok to take the mmap_sem for reading, even
-         * across a "get_user()".
-         */
         down_read(&current->mm->mmap_sem);
 
         while (nr_vecs) {
                 unsigned long off, npages;
+                struct iovec entry;
                 void __user *base;
                 size_t len;
                 int i;
 
-                /*
-                 * Get user address base and length for this iovec.
-                 */
-                error = get_user(base, &iov->iov_base);
-                if (unlikely(error))
-                        break;
-                error = get_user(len, &iov->iov_len);
-                if (unlikely(error))
+                error = -EFAULT;
+                if (copy_from_user_mmap_sem(&entry, iov, sizeof(entry)))
                         break;
 
+                base = entry.iov_base;
+                len = entry.iov_len;
+
                 /*
                  * Sanity check this iovec. 0 read succeeds.
                  */
+                error = 0;
                 if (unlikely(!len))
                         break;
                 error = -EFAULT;
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index fa25b7dcc6c3..d7e136143066 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -52,11 +52,6 @@ typedef struct xfs_buf_log_format_t {
 #define XFS_BLI_UDQUOT_BUF      0x4
 #define XFS_BLI_PDQUOT_BUF      0x8
 #define XFS_BLI_GDQUOT_BUF      0x10
-/*
- * This flag indicates that the buffer contains newly allocated
- * inodes.
- */
-#define XFS_BLI_INODE_NEW_BUF   0x20
 
 #define XFS_BLI_CHUNK           128
 #define XFS_BLI_SHIFT           7
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 7174991f4bef..8ae6e8e5f3db 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1874,7 +1874,6 @@ xlog_recover_do_inode_buffer(
 /*ARGSUSED*/
 STATIC void
 xlog_recover_do_reg_buffer(
-        xfs_mount_t             *mp,
         xlog_recover_item_t     *item,
         xfs_buf_t               *bp,
         xfs_buf_log_format_t    *buf_f)
@@ -1885,50 +1884,6 @@ xlog_recover_do_reg_buffer(
         unsigned int            *data_map = NULL;
         unsigned int            map_size = 0;
         int                     error;
-        int                     stale_buf = 1;
-
-        /*
-         * Scan through the on-disk inode buffer and attempt to
-         * determine if it has been written to since it was logged.
-         *
-         * - If any of the magic numbers are incorrect then the buffer is stale
-         * - If any of the modes are non-zero then the buffer is not stale
-         * - If all of the modes are zero and at least one of the generation
-         *   counts is non-zero then the buffer is stale
-         *
-         * If the end result is a stale buffer then the log buffer is replayed
-         * otherwise it is skipped.
-         *
-         * This heuristic is not perfect.  It can be improved by scanning the
-         * entire inode chunk for evidence that any of the inode clusters have
-         * been updated.  To fix this problem completely we will need a major
-         * architectural change to the logging system.
-         */
-        if (buf_f->blf_flags & XFS_BLI_INODE_NEW_BUF) {
-                xfs_dinode_t    *dip;
-                int             inodes_per_buf;
-                int             mode_count = 0;
-                int             gen_count = 0;
-
-                stale_buf = 0;
-                inodes_per_buf = XFS_BUF_COUNT(bp) >> mp->m_sb.sb_inodelog;
-                for (i = 0; i < inodes_per_buf; i++) {
-                        dip = (xfs_dinode_t *)xfs_buf_offset(bp,
-                                i * mp->m_sb.sb_inodesize);
-                        if (be16_to_cpu(dip->di_core.di_magic) !=
-                                        XFS_DINODE_MAGIC) {
-                                stale_buf = 1;
-                                break;
-                        }
-                        if (dip->di_core.di_mode)
-                                mode_count++;
-                        if (dip->di_core.di_gen)
-                                gen_count++;
-                }
-
-                if (!mode_count && gen_count)
-                        stale_buf = 1;
-        }
 
         switch (buf_f->blf_type) {
         case XFS_LI_BUF:
@@ -1962,7 +1917,7 @@ xlog_recover_do_reg_buffer(
                                                -1, 0, XFS_QMOPT_DOWARN,
                                                "dquot_buf_recover");
                 }
-                if (!error && stale_buf)
+                if (!error)
                         memcpy(xfs_buf_offset(bp,
                                 (uint)bit << XFS_BLI_SHIFT),    /* dest */
                                 item->ri_buf[i].i_addr,         /* source */
@@ -2134,7 +2089,7 @@ xlog_recover_do_dquot_buffer(
         if (log->l_quotaoffs_flag & type)
                 return;
 
-        xlog_recover_do_reg_buffer(mp, item, bp, buf_f);
+        xlog_recover_do_reg_buffer(item, bp, buf_f);
 }
 
 /*
@@ -2235,7 +2190,7 @@ xlog_recover_do_buffer_trans(
                   (XFS_BLI_UDQUOT_BUF|XFS_BLI_PDQUOT_BUF|XFS_BLI_GDQUOT_BUF)) {
                 xlog_recover_do_dquot_buffer(mp, log, item, bp, buf_f);
         } else {
-                xlog_recover_do_reg_buffer(mp, item, bp, buf_f);
+                xlog_recover_do_reg_buffer(item, bp, buf_f);
         }
         if (error)
                 return XFS_ERROR(error);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 95fff6872a2f..60b6b898022b 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -966,7 +966,6 @@ xfs_trans_inode_alloc_buf(
         ASSERT(atomic_read(&bip->bli_refcount) > 0);
 
         bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF;
-        bip->bli_format.blf_flags |= XFS_BLI_INODE_NEW_BUF;
 }