linux.git/fs/ecryptfs, branch v2.6.33

ecryptfs: use after free

2010-01-20T04:36:06+00:00

The "full_alg_name" variable is used on a couple error paths, so we
shouldn't free it until the end.

Signed-off-by: Dan Carpenter 
Cc: stable@kernel.org
Signed-off-by: Tyler Hicks

ecryptfs: Eliminate useless code

2010-01-20T04:36:05+00:00

The variable lower_dentry is initialized twice to the same (side effect-free)
expression.  Drop one initialization.

A simplified version of the semantic match that finds this problem is:
(http://coccinelle.lip6.fr/)

// 
@forall@
idexpression *x;
identifier f!=ERR_PTR;
@@

x = f(...)
... when != x
(
x = f(...,<+...x...+>,...)
|
* x = f(...)
)
// 

Signed-off-by: Julia Lawall 
Signed-off-by: Tyler Hicks

ecryptfs: fix interpose/interpolate typos in comments

2010-01-20T04:36:03+00:00

Signed-off-by: Erez Zadok 
Acked-by: Dustin Kirkland 
Signed-off-by: Tyler Hicks

ecryptfs: pass matching flags to interpose as defined and used there

2010-01-20T04:36:02+00:00

ecryptfs_interpose checks if one of the flags passed is
ECRYPTFS_INTERPOSE_FLAG_D_ADD, defined as 0x00000001 in ecryptfs_kernel.h.
But the only user of ecryptfs_interpose to pass a non-zero flag to it, has
hard-coded the value as "1". This could spell trouble if any of these values
changes in the future.

Signed-off-by: Erez Zadok 
Cc: Dustin Kirkland 
Cc: Al Viro 
Signed-off-by: Tyler Hicks

ecryptfs: remove unnecessary d_drop calls in ecryptfs_link

2010-01-20T04:36:00+00:00

Unnecessary because it would unhash perfectly valid dentries, causing them
to have to be re-looked up the next time they're needed, which presumably is
right after.

Signed-off-by: Aseem Rastogi 
Signed-off-by: Shrikar archak 
Signed-off-by: Erez Zadok 
Cc: Saumitra Bhanage 
Cc: Al Viro 
Signed-off-by: Tyler Hicks

ecryptfs: don't ignore return value from lock_rename

2010-01-20T04:35:59+00:00

Signed-off-by: Erez Zadok 
Cc: Dustin Kirkland 
Cc: Andrew Morton 
Cc: Al Viro 
Signed-off-by: Tyler Hicks

ecryptfs: initialize private persistent file before dereferencing pointer

2010-01-20T04:32:54+00:00

Ecryptfs_open dereferences a pointer to the private lower file (the one
stored in the ecryptfs inode), without checking if the pointer is NULL.
Right afterward, it initializes that pointer if it is NULL.  Swap order of
statements to first initialize.  Bug discovered by Duckjin Kang.

Signed-off-by: Duckjin Kang 
Signed-off-by: Erez Zadok 
Cc: Dustin Kirkland 
Cc: Al Viro 
Cc: 
Signed-off-by: Tyler Hicks

eCryptfs: Remove mmap from directory operations

2010-01-20T04:32:11+00:00

Adrian reported that mkfontscale didn't work inside of eCryptfs mounts.
Strace revealed the following:

open("./", O_RDONLY|O_NONBLOCK|O_LARGEFILE|O_DIRECTORY|O_CLOEXEC) = 3
fcntl64(3, F_GETFD) = 0x1 (flags FD_CLOEXEC)
open("./fonts.scale", O_WRONLY|O_CREAT|O_TRUNC, 0666) = 4
getdents(3, /* 80 entries */, 32768) = 2304
open("./.", O_RDONLY) = 5
fcntl64(5, F_SETFD, FD_CLOEXEC) = 0
fstat64(5, {st_mode=S_IFDIR|0755, st_size=16384, ...}) = 0
mmap2(NULL, 16384, PROT_READ, MAP_PRIVATE, 5, 0) = 0xb7fcf000
close(5) = 0
--- SIGBUS (Bus error) @ 0 (0) ---
+++ killed by SIGBUS +++

The mmap2() on a directory was successful, resulting in a SIGBUS
signal later.  This patch removes mmap() from the list of possible
ecryptfs_dir_fops so that mmap() isn't possible on eCryptfs directory
files.

https://bugs.launchpad.net/ecryptfs/+bug/400443

Reported-by: Adrian C. 
Signed-off-by: Tyler Hicks

eCryptfs: Add getattr function

2010-01-20T04:32:09+00:00

The i_blocks field of an eCryptfs inode cannot be trusted, but
generic_fillattr() uses it to instantiate the blocks field of a stat()
syscall when a filesystem doesn't implement its own getattr().  Users
have noticed that the output of du is incorrect on newly created files.

This patch creates ecryptfs_getattr() which calls into the lower
filesystem's getattr() so that eCryptfs can use its kstat.blocks value
after calling generic_fillattr().  It is important to note that the
block count includes the eCryptfs metadata stored in the beginning of
the lower file plus any padding used to fill an extent before
encryption.

https://bugs.launchpad.net/ecryptfs/+bug/390833

Reported-by: Dominic Sacré 
Signed-off-by: Tyler Hicks

eCryptfs: Use notify_change for truncating lower inodes

2010-01-20T04:32:07+00:00

When truncating inodes in the lower filesystem, eCryptfs directly
invoked vmtruncate(). As Christoph Hellwig pointed out, vmtruncate() is
a filesystem helper function, but filesystems may need to do more than
just a call to vmtruncate().

This patch moves the lower inode truncation out of ecryptfs_truncate()
and renames the function to truncate_upper().  truncate_upper() updates
an iattr for the lower inode to indicate if the lower inode needs to be
truncated upon return.  ecryptfs_setattr() then calls notify_change(),
using the updated iattr for the lower inode, to complete the truncation.

For eCryptfs functions needing to truncate, ecryptfs_truncate() is
reintroduced as a simple way to truncate the upper inode to a specified
size and then truncate the lower inode accordingly.

https://bugs.launchpad.net/bugs/451368

Reported-by: Christoph Hellwig 
Acked-by: Dustin Kirkland 
Cc: ecryptfs-devel@lists.launchpad.net
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Tyler Hicks