Merge branch '2.6.25.y' into testing

11 files changed, 109 insertions, 60 deletions

diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c
index bcda2c6b6a04..5dbba896a7df 100644
--- a/fs/cifs/asn1.c
+++ b/fs/cifs/asn1.c
@@ -186,6 +186,11 @@ asn1_length_decode(struct asn1_ctx *ctx, unsigned int *def, unsigned int *len)
 			}
 		}
 	}
+
+	/* don't trust len bigger than ctx buffer */
+	if (*len > ctx->end - ctx->pointer)
+		return 0;
+
 	return 1;
 }
 
@@ -203,6 +208,10 @@ asn1_header_decode(struct asn1_ctx *ctx,
 	if (!asn1_length_decode(ctx, &def, &len))
 		return 0;
 
+	/* primitive shall be definite, indefinite shall be constructed */
+	if (*con == ASN1_PRI && !def)
+		return 0;
+
 	if (def)
 		*eoc = ctx->pointer + len;
 	else
@@ -389,6 +398,11 @@ asn1_oid_decode(struct asn1_ctx *ctx,
 	unsigned long *optr;
 
 	size = eoc - ctx->pointer + 1;
+
+	/* first subid actually encodes first two subids */
+	if (size < 2 || size > ULONG_MAX/sizeof(unsigned long))
+		return 0;
+
 	*oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC);
 	if (*oid == NULL)
 		return 0;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index bc673c8c1e6b..e1031b9e2c55 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -161,12 +161,14 @@ static void cifs_unix_info_to_inode(struct inode *inode,
 	spin_unlock(&inode->i_lock);
 }
 
-static const unsigned char *cifs_get_search_path(struct cifsTconInfo *pTcon,
-					const char *search_path)
+static const unsigned char *cifs_get_search_path(struct cifs_sb_info *cifs_sb,
+						const char *search_path)
 {
 	int tree_len;
 	int path_len;
+	int i;
 	char *tmp_path;
+	struct cifsTconInfo *pTcon = cifs_sb->tcon;
 
 	if (!(pTcon->Flags & SMB_SHARE_IS_IN_DFS))
 		return search_path;
@@ -180,6 +182,11 @@ static const unsigned char *cifs_get_search_path(struct cifsTconInfo *pTcon,
 		return search_path;
 
 	strncpy(tmp_path, pTcon->treeName, tree_len);
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
+		for (i = 0; i < tree_len; i++) {
+			if (tmp_path[i] == '\\')
+				tmp_path[i] = '/';
+		}
 	strncpy(tmp_path+tree_len, search_path, path_len);
 	tmp_path[tree_len+path_len] = 0;
 	return tmp_path;
@@ -199,7 +206,7 @@ int cifs_get_inode_info_unix(struct inode **pinode,
 	pTcon = cifs_sb->tcon;
 	cFYI(1, ("Getting info on %s", search_path));
 
-	full_path = cifs_get_search_path(pTcon, search_path);
+	full_path = cifs_get_search_path(cifs_sb, search_path);
 
 try_again_CIFSSMBUnixQPathInfo:
 	/* could have done a find first instead but this returns more info */
@@ -402,7 +409,7 @@ int cifs_get_inode_info(struct inode **pinode,
 			return -ENOMEM;
 		pfindData = (FILE_ALL_INFO *)buf;
 
-		full_path = cifs_get_search_path(pTcon, search_path);
+		full_path = cifs_get_search_path(cifs_sb, search_path);
 
 try_again_CIFSSMBQPathInfo:
 		/* could do find first instead but this returns more info */
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 5007f788da01..7c607af8ba22 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -626,8 +626,6 @@ int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm,
 int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key,
 				      struct ecryptfs_auth_tok **auth_tok,
 				      char *sig);
-int ecryptfs_write_zeros(struct file *file, pgoff_t index, int start,
-			 int num_zeros);
 int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data,
 			 loff_t offset, size_t size);
 int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode,
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 0c4928623bbc..7cafdbc32484 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -157,20 +157,6 @@ int ecryptfs_write(struct file *ecryptfs_file, char *data, loff_t offset,
 			       ecryptfs_page_idx, rc);
 			goto out;
 		}
-		if (start_offset_in_page) {
-			/* Read in the page from the lower
-			 * into the eCryptfs inode page cache,
-			 * decrypting */
-			rc = ecryptfs_decrypt_page(ecryptfs_page);
-			if (rc) {
-				printk(KERN_ERR "%s: Error decrypting "
-				       "page; rc = [%d]\n",
-				       __FUNCTION__, rc);
-				ClearPageUptodate(ecryptfs_page);
-				page_cache_release(ecryptfs_page);
-				goto out;
-			}
-		}
 		ecryptfs_page_virt = kmap_atomic(ecryptfs_page, KM_USER0);
 
 		/*
@@ -349,14 +335,6 @@ int ecryptfs_read(char *data, loff_t offset, size_t size,
 			       ecryptfs_page_idx, rc);
 			goto out;
 		}
-		rc = ecryptfs_decrypt_page(ecryptfs_page);
-		if (rc) {
-			printk(KERN_ERR "%s: Error decrypting "
-			       "page; rc = [%d]\n", __FUNCTION__, rc);
-			ClearPageUptodate(ecryptfs_page);
-			page_cache_release(ecryptfs_page);
-			goto out;
-		}
 		ecryptfs_page_virt = kmap_atomic(ecryptfs_page, KM_USER0);
 		memcpy((data + data_offset),
 		       ((char *)ecryptfs_page_virt + start_offset_in_page),
diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c
index 42856541e9a5..84119afe17a6 100644
--- a/fs/ext3/xattr.c
+++ b/fs/ext3/xattr.c
@@ -1000,6 +1000,11 @@ ext3_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 			i.value = NULL;
 			error = ext3_xattr_block_set(handle, inode, &i, &bs);
 		} else if (error == -ENOSPC) {
+			if (EXT3_I(inode)->i_file_acl && !bs.s.base) {
+				error = ext3_xattr_block_find(inode, &i, &bs);
+				if (error)
+					goto cleanup;
+			}
 			error = ext3_xattr_block_set(handle, inode, &i, &bs);
 			if (error)
 				goto cleanup;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index e9054c1c7d93..70d856badabf 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1011,6 +1011,11 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 			i.value = NULL;
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
 		} else if (error == -ENOSPC) {
+			if (EXT4_I(inode)->i_file_acl && !bs.s.base) {
+				error = ext4_xattr_block_find(inode, &i, &bs);
+				if (error)
+					goto cleanup;
+			}
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
 			if (error)
 				goto cleanup;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 07d6c4853fe8..6b1c67a76233 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -287,7 +287,7 @@ static void render_cap_t(struct seq_file *m, const char *header,
 	seq_printf(m, "%s", header);
 	CAP_FOR_EACH_U32(__capi) {
 		seq_printf(m, "%08x",
-			   a->cap[(_LINUX_CAPABILITY_U32S-1) - __capi]);
+			   a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
 	}
 	seq_printf(m, "\n");
 }
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 81d7d145292a..d6f21bd0cee6 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -126,6 +126,25 @@ struct pid_entry {
 		NULL, &proc_single_file_operations,	\
 		{ .proc_show = &proc_##OTYPE } )
 
+/*
+ * Count the number of hardlinks for the pid_entry table, excluding the .
+ * and .. links.
+ */
+static unsigned int pid_entry_count_dirs(const struct pid_entry *entries,
+	unsigned int n)
+{
+	unsigned int i;
+	unsigned int count;
+
+	count = 0;
+	for (i = 0; i < n; ++i) {
+		if (S_ISDIR(entries[i].mode))
+			++count;
+	}
+
+	return count;
+}
+
 int maps_protect;
 EXPORT_SYMBOL(maps_protect);
 
@@ -2483,10 +2502,9 @@ static struct dentry *proc_pid_instantiate(struct inode *dir,
 	inode->i_op = &proc_tgid_base_inode_operations;
 	inode->i_fop = &proc_tgid_base_operations;
 	inode->i_flags|=S_IMMUTABLE;
-	inode->i_nlink = 5;
-#ifdef CONFIG_SECURITY
-	inode->i_nlink += 1;
-#endif
+
+	inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff,
+		ARRAY_SIZE(tgid_base_stuff));
 
 	dentry->d_op = &pid_dentry_operations;
 
@@ -2713,10 +2731,9 @@ static struct dentry *proc_task_instantiate(struct inode *dir,
 	inode->i_op = &proc_tid_base_inode_operations;
 	inode->i_fop = &proc_tid_base_operations;
 	inode->i_flags|=S_IMMUTABLE;
-	inode->i_nlink = 4;
-#ifdef CONFIG_SECURITY
-	inode->i_nlink += 1;
-#endif
+
+	inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff,
+		ARRAY_SIZE(tid_base_stuff));
 
 	dentry->d_op = &pid_dentry_operations;
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 9dfb5ff24209..dca9b465690d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -524,7 +524,7 @@ const struct file_operations proc_clear_refs_operations = {
 };
 
 struct pagemapread {
-	char __user *out, *end;
+	u64 __user *out, *end;
 };
 
 #define PM_ENTRY_BYTES      sizeof(u64)
@@ -547,21 +547,11 @@ struct pagemapread {
 static int add_to_pagemap(unsigned long addr, u64 pfn,
 			  struct pagemapread *pm)
 {
-	/*
-	 * Make sure there's room in the buffer for an
-	 * entire entry.  Otherwise, only copy part of
-	 * the pfn.
-	 */
-	if (pm->out + PM_ENTRY_BYTES >= pm->end) {
-		if (copy_to_user(pm->out, &pfn, pm->end - pm->out))
-			return -EFAULT;
-		pm->out = pm->end;
-		return PM_END_OF_BUFFER;
-	}
-
 	if (put_user(pfn, pm->out))
 		return -EFAULT;
-	pm->out += PM_ENTRY_BYTES;
+	pm->out++;
+	if (pm->out >= pm->end)
+		return PM_END_OF_BUFFER;
 	return 0;
 }
 
@@ -662,7 +652,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 
 	ret = -EINVAL;
 	/* file position must be aligned */
-	if (*ppos % PM_ENTRY_BYTES)
+	if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
 		goto out_task;
 
 	ret = 0;
@@ -692,8 +682,8 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		goto out_pages;
 	}
 
-	pm.out = buf;
-	pm.end = buf + count;
+	pm.out = (u64 *)buf;
+	pm.end = (u64 *)(buf + count);
 
 	if (!ptrace_may_attach(task)) {
 		ret = -EIO;
@@ -718,9 +708,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		if (ret == PM_END_OF_BUFFER)
 			ret = 0;
 		/* don't need mmap_sem for these, but this looks cleaner */
-		*ppos += pm.out - buf;
+		*ppos += (char *)pm.out - buf;
 		if (!ret)
-			ret = pm.out - buf;
+			ret = (char *)pm.out - buf;
 	}
 
 out_pages:
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index e347bfd47c91..9831c9051163 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -387,6 +387,8 @@ _xfs_buf_lookup_pages(
 		if (unlikely(page == NULL)) {
 			if (flags & XBF_READ_AHEAD) {
 				bp->b_page_count = i;
+				for (i = 0; i < bp->b_page_count; i++)
+					unlock_page(bp->b_pages[i]);
 				return -ENOMEM;
 			}
 
@@ -416,17 +418,24 @@ _xfs_buf_lookup_pages(
 		ASSERT(!PagePrivate(page));
 		if (!PageUptodate(page)) {
 			page_count--;
-			if (blocksize < PAGE_CACHE_SIZE && !PagePrivate(page)) {
+			if (blocksize >= PAGE_CACHE_SIZE) {
+				if (flags & XBF_READ)
+					bp->b_flags |= _XBF_PAGE_LOCKED;
+			} else if (!PagePrivate(page)) {
 				if (test_page_region(page, offset, nbytes))
 					page_count++;
 			}
 		}
 
-		unlock_page(page);
 		bp->b_pages[i] = page;
 		offset = 0;
 	}
 
+	if (!(bp->b_flags & _XBF_PAGE_LOCKED)) {
+		for (i = 0; i < bp->b_page_count; i++)
+			unlock_page(bp->b_pages[i]);
+	}
+
 	if (page_count == bp->b_page_count)
 		bp->b_flags |= XBF_DONE;
 
@@ -746,6 +755,7 @@ xfs_buf_associate_memory(
 	bp->b_count_desired = len;
 	bp->b_buffer_length = buflen;
 	bp->b_flags |= XBF_MAPPED;
+	bp->b_flags &= ~_XBF_PAGE_LOCKED;
 
 	return 0;
 }
@@ -1093,8 +1103,10 @@ _xfs_buf_ioend(
 	xfs_buf_t		*bp,
 	int			schedule)
 {
-	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
+		bp->b_flags &= ~_XBF_PAGE_LOCKED;
 		xfs_buf_ioend(bp, schedule);
+	}
 }
 
 STATIC void
@@ -1125,6 +1137,9 @@ xfs_buf_bio_end_io(
 
 		if (--bvec >= bio->bi_io_vec)
 			prefetchw(&bvec->bv_page->flags);
+
+		if (bp->b_flags & _XBF_PAGE_LOCKED)
+			unlock_page(page);
 	} while (bvec >= bio->bi_io_vec);
 
 	_xfs_buf_ioend(bp, 1);
@@ -1163,7 +1178,8 @@ _xfs_buf_ioapply(
 	 * filesystem block size is not smaller than the page size.
 	 */
 	if ((bp->b_buffer_length < PAGE_CACHE_SIZE) &&
-	    (bp->b_flags & XBF_READ) &&
+	    ((bp->b_flags & (XBF_READ|_XBF_PAGE_LOCKED)) ==
+	      (XBF_READ|_XBF_PAGE_LOCKED)) &&
 	    (blocksize >= PAGE_CACHE_SIZE)) {
 		bio = bio_alloc(GFP_NOIO, 1);
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index a3d207de48b8..441f7c38b0e4 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -66,6 +66,25 @@ typedef enum {
 	_XBF_PAGES = (1 << 18),	    /* backed by refcounted pages	   */
 	_XBF_RUN_QUEUES = (1 << 19),/* run block device task queue	   */
 	_XBF_DELWRI_Q = (1 << 21),   /* buffer on delwri queue		   */
+
+	/*
+	 * Special flag for supporting metadata blocks smaller than a FSB.
+	 *
+	 * In this case we can have multiple xfs_buf_t on a single page and
+	 * need to lock out concurrent xfs_buf_t readers as they only
+	 * serialise access to the buffer.
+	 *
+	 * If the FSB size >= PAGE_CACHE_SIZE case, we have no serialisation
+	 * between reads of the page. Hence we can have one thread read the
+	 * page and modify it, but then race with another thread that thinks
+	 * the page is not up-to-date and hence reads it again.
+	 *
+	 * The result is that the first modifcation to the page is lost.
+	 * This sort of AGF/AGI reading race can happen when unlinking inodes
+	 * that require truncation and results in the AGI unlinked list
+	 * modifications being lost.
+	 */
+	_XBF_PAGE_LOCKED = (1 << 22),
 } xfs_buf_flags_t;
 
 typedef enum {