6 files changed, 81 insertions, 23 deletions

diff --git a/fs/file.c b/fs/file.c
index 771578b33fb6..db25c2bdfe46 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -34,7 +34,7 @@ static void *alloc_fdmem(size_t size)
          * vmalloc() if the allocation size will be considered "large" by the VM.
          */
         if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-                void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
+                void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY);
                 if (data != NULL)
                         return data;
         }
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index be38b573495a..4a48fe4b84b6 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1846,6 +1846,11 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
                                                         GFP_KERNEL)) {
                 SetPageUptodate(page);
                 unlock_page(page);
+                /*
+                 * add_to_page_cache_lru() grabs an extra page refcount.
+                 * Drop it here to avoid leaking this page later.
+                 */
+                page_cache_release(page);
         } else
                 __free_page(page);
 
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index aada5801567a..e2edff38be52 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7158,7 +7158,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
         if (end > i_size_read(inode))
                 end = i_size_read(inode);
 
-        BUG_ON(start >= end);
+        BUG_ON(start > end);
 
         if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) ||
             !(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) ||
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index d77d71ead8d1..8450262bcf2a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -185,6 +185,9 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
                               file->f_path.dentry->d_name.name,
                               (unsigned long long)datasync);
 
+        if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
+                return -EROFS;
+
         err = filemap_write_and_wait_range(inode->i_mapping, start, end);
         if (err)
                 return err;
@@ -474,11 +477,6 @@ static int ocfs2_truncate_file(struct inode *inode,
                 goto bail;
         }
 
-        /* lets handle the simple truncate cases before doing any more
-         * cluster locking. */
-        if (new_i_size == le64_to_cpu(fe->i_size))
-                goto bail;
-
         down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
         ocfs2_resv_discard(&osb->osb_la_resmap,
@@ -718,7 +716,8 @@ leave:
  * While a write will already be ordering the data, a truncate will not.
  * Thus, we need to explicitly order the zeroed pages.
  */
-static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode)
+static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode,
+                                                struct buffer_head *di_bh)
 {
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
         handle_t *handle = NULL;
@@ -735,7 +734,14 @@ static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode)
         }
 
         ret = ocfs2_jbd2_file_inode(handle, inode);
-        if (ret < 0)
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+                                      OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret)
                 mlog_errno(ret);
 
 out:
@@ -751,7 +757,7 @@ out:
  * to be too fragile to do exactly what we need without us having to
  * worry about recursive locking in ->write_begin() and ->write_end(). */
 static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
-                                 u64 abs_to)
+                                 u64 abs_to, struct buffer_head *di_bh)
 {
         struct address_space *mapping = inode->i_mapping;
         struct page *page;
@@ -759,6 +765,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
         handle_t *handle = NULL;
         int ret = 0;
         unsigned zero_from, zero_to, block_start, block_end;
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 
         BUG_ON(abs_from >= abs_to);
         BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
@@ -801,7 +808,8 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
                 }
 
                 if (!handle) {
-                        handle = ocfs2_zero_start_ordered_transaction(inode);
+                        handle = ocfs2_zero_start_ordered_transaction(inode,
+                                                                      di_bh);
                         if (IS_ERR(handle)) {
                                 ret = PTR_ERR(handle);
                                 handle = NULL;
@@ -818,8 +826,22 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
                         ret = 0;
         }
 
-        if (handle)
+        if (handle) {
+                /*
+                 * fs-writeback will release the dirty pages without page lock
+                 * whose offset are over inode size, the release happens at
+                 * block_write_full_page_endio().
+                 */
+                i_size_write(inode, abs_to);
+                inode->i_blocks = ocfs2_inode_sector_count(inode);
+                di->i_size = cpu_to_le64((u64)i_size_read(inode));
+                inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+                di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+                di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+                di->i_mtime_nsec = di->i_ctime_nsec;
+                ocfs2_journal_dirty(handle, di_bh);
                 ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+        }
 
 out_unlock:
         unlock_page(page);
@@ -915,7 +937,7 @@ out:
  * has made sure that the entire range needs zeroing.
  */
 static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
-                                   u64 range_end)
+                                   u64 range_end, struct buffer_head *di_bh)
 {
         int rc = 0;
         u64 next_pos;
@@ -931,7 +953,7 @@ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
                 next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
                 if (next_pos > range_end)
                         next_pos = range_end;
-                rc = ocfs2_write_zero_page(inode, zero_pos, next_pos);
+                rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh);
                 if (rc < 0) {
                         mlog_errno(rc);
                         break;
@@ -977,7 +999,7 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
                         range_end = zero_to_size;
 
                 ret = ocfs2_zero_extend_range(inode, range_start,
-                                              range_end);
+                                              range_end, di_bh);
                 if (ret) {
                         mlog_errno(ret);
                         break;
@@ -1145,14 +1167,14 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
                 goto bail_unlock_rw;
         }
 
-        if (size_change && attr->ia_size != i_size_read(inode)) {
+        if (size_change) {
                 status = inode_newsize_ok(inode, attr->ia_size);
                 if (status)
                         goto bail_unlock;
 
                 inode_dio_wait(inode);
 
-                if (i_size_read(inode) > attr->ia_size) {
+                if (i_size_read(inode) >= attr->ia_size) {
                         if (ocfs2_should_order_data(inode)) {
                                 status = ocfs2_begin_ordered_truncate(inode,
                                                                       attr->ia_size);
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index f4d609be9400..3683643f3f0e 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -664,6 +664,7 @@ static int ocfs2_link(struct dentry *old_dentry,
         struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
         struct ocfs2_dir_lookup_result lookup = { NULL, };
         sigset_t oldset;
+        u64 old_de_ino;
 
         trace_ocfs2_link((unsigned long long)OCFS2_I(inode)->ip_blkno,
                          old_dentry->d_name.len, old_dentry->d_name.name,
@@ -686,6 +687,22 @@ static int ocfs2_link(struct dentry *old_dentry,
                 goto out;
         }
 
+        err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name,
+                        old_dentry->d_name.len, &old_de_ino);
+        if (err) {
+                err = -ENOENT;
+                goto out;
+        }
+
+        /*
+         * Check whether another node removed the source inode while we
+         * were in the vfs.
+         */
+        if (old_de_ino != OCFS2_I(inode)->ip_blkno) {
+                err = -ENOENT;
+                goto out;
+        }
+
         err = ocfs2_check_dir_for_entry(dir, dentry->d_name.name,
                                         dentry->d_name.len);
         if (err)
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 2ca7ba047f04..88d4585b30f1 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -468,17 +468,24 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
                         return rc;
                 }
                 nhdr_ptr = notes_section;
-                while (real_sz < max_sz) {
-                        if (nhdr_ptr->n_namesz == 0)
-                                break;
+                while (nhdr_ptr->n_namesz != 0) {
                         sz = sizeof(Elf64_Nhdr) +
                                 ((nhdr_ptr->n_namesz + 3) & ~3) +
                                 ((nhdr_ptr->n_descsz + 3) & ~3);
+                        if ((real_sz + sz) > max_sz) {
+                                pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+                                        nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+                                break;
+                        }
                         real_sz += sz;
                         nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz);
                 }
                 kfree(notes_section);
                 phdr_ptr->p_memsz = real_sz;
+                if (real_sz == 0) {
+                        pr_warn("Warning: Zero PT_NOTE entries found\n");
+                        return -EINVAL;
+                }
         }
 
         return 0;
@@ -648,17 +655,24 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
                         return rc;
                 }
                 nhdr_ptr = notes_section;
-                while (real_sz < max_sz) {
-                        if (nhdr_ptr->n_namesz == 0)
-                                break;
+                while (nhdr_ptr->n_namesz != 0) {
                         sz = sizeof(Elf32_Nhdr) +
                                 ((nhdr_ptr->n_namesz + 3) & ~3) +
                                 ((nhdr_ptr->n_descsz + 3) & ~3);
+                        if ((real_sz + sz) > max_sz) {
+                                pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+                                        nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+                                break;
+                        }
                         real_sz += sz;
                         nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz);
                 }
                 kfree(notes_section);
                 phdr_ptr->p_memsz = real_sz;
+                if (real_sz == 0) {
+                        pr_warn("Warning: Zero PT_NOTE entries found\n");
+                        return -EINVAL;
+                }
         }
 
         return 0;