Commits · ef288c4613dafbd1d4bd7049eda3f9f65eee62d1 · linux / linux-davinci

11 Sep, 2009 40 commits

fsnotify: kzalloc fsnotify groups · ef288c46

Eric Paris authored Aug 13, 2009

Use kzalloc for fsnotify_groups so that none of the fields can leak any
information accidentally.
Signed-off-by: Eric Paris <eparis@redhat.com>

ef288c46

inotify: use container_of instead of casting · 679b0575

Eric Paris authored Aug 13, 2009

inotify_free_mark casts directly from an fsnotify_mark_entry to an
inotify_inode_mark_entry.  This works, but should use container_of instead
for future proofing.
Signed-off-by: Eric Paris <eparis@redhat.com>

679b0575

fsnotify: use fsnotify_create_event to allocate the q_overflow event · cd799603

Eric Paris authored Aug 13, 2009

Currently fsnotify defines a static fsnotify event which is sent when a
group overflows its allotted queue length. This patch just allocates that
event from the event cache rather than defining it statically. There is no
known reason that the current implementation is wrong, but this makes sure the
event is initialized and created like any other.
Signed-off-by: Eric Paris <eparis@redhat.com>

cd799603

Audit: rearrange audit_context to save 16 bytes per struct · e5b98075

Eric Paris authored Aug 13, 2009

pahole pointed out that on x86_64 struct audit_context can be rearrainged
to save 16 bytes per struct.  Since we have an audit_context per task this
can acually be a pretty significant gain.
Signed-off-by: Eric Paris <eparis@redhat.com>

e5b98075

Audit: reorganize struct audit_watch to save 8 bytes · abca45ed

Eric Paris authored Aug 13, 2009

pahole showed that struct audit_watch had two holes:

struct audit_watch {
        atomic_t                   count;                /*     0     4 */

        /* XXX 4 bytes hole, try to pack */

        char *                     path;                 /*     8     8 */
        dev_t                      dev;                  /*    16     4 */

        /* XXX 4 bytes hole, try to pack */

        long unsigned int          ino;                  /*    24     8 */
        struct audit_parent *      parent;               /*    32     8 */
        struct list_head           wlist;                /*    40    16 */
        struct list_head           rules;                /*    56    16 */
        /* --- cacheline 1 boundary (64 bytes) was 8 bytes ago --- */

        /* size: 72, cachelines: 2, members: 7 */
        /* sum members: 64, holes: 2, sum holes: 8 */
        /* last cacheline: 8 bytes */
};      /* definitions: 1 */

by moving dev after count we save 8 bytes,  actually improving cacheline
usage.  There are typically very few of these in the kernel so it won't be
a large savings, but it's a good thing no matter what.
Signed-off-by: Eric Paris <eparis@redhat.com>

abca45ed

Audit: audit watch init should not be before fsnotify init · f7d7c698

Eric Paris authored Jul 01, 2009

Audit watch init and fsnotify init both use subsys_initcall() but since the
audit watch code is linked in before the fsnotify code the audit watch code
would be using the fsnotify srcu struct before it was initialized.  This
patch fixes that problem by moving audit watch init to device_initcall() so
it happens after fsnotify is ready.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Eric Paris <eparis@redhat.com>
Tested-by : Sachin Sant <sachinp@in.ibm.com>

f7d7c698

Audit: split audit watch Kconfig · 36ad2da5

Eric Paris authored Jun 30, 2009

Audit watch should depend on CONFIG_AUDIT_SYSCALL and should select
FSNOTIFY.  This splits the spagetti like mixing of audit_watch and
audit_filter code so they can be configured seperately.
Signed-off-by: Eric Paris <eparis@redhat.com>

36ad2da5

Audit: audit watches depend on fsnotify · 64d9ec23

Eric Paris authored Jun 30, 2009

CONFIG_AUDIT builds audit_watches which depend on fsnotify.  Make
CONFIG_AUDIT select fsnotify.
Reported-by: Alexander Beregalov <a.beregalov@gmail.com>
Signed-off-by: Eric Paris <eparis@redhat.com>