fsnotify_replace_event need to lock both the old and the new event.  This
causes lockdep to get all pissed off since it dosn't know this is safe.
It's safe in this case since the new event is impossible to be reached from
other places in the kernel.
Signed-off-by: Eric Paris <eparis@redhat.com>

fanotify would like to clone events already on its notification list, make
changes to the new event, and then replace the old event on the list with
the new event.  This patch implements the replace functionality of that
process.
Signed-off-by: Eric Paris <eparis@redhat.com>

fsnotify_clone_event will take an event, clone it, and return the cloned
event to the caller.  Since events may be in use by multiple fsnotify
groups simultaneously certain event entries (such as the mask) cannot be
changed after the event was created.  Since fanotify would like to merge
events happening on the same file it needs a new clean event to work with
so it can change any fields it wishes.
Signed-off-by: Eric Paris <eparis@redhat.com>

inotify only wishes to merge a new event with the last event on the
notification fifo.  fanotify is willing to merge any events including by
means of bitwise OR masks of multiple events together.  This patch moves
the inotify event merging logic out of the generic fsnotify notification.c
and into the inotify code.  This allows each use of fsnotify to provide
their own merge functionality.
Signed-off-by: Eric Paris <eparis@redhat.com>

fanotify needs a path in order to open an fd to the object which changed.
Currently notifications to inode's parents are done using only the inode.
For some parental notification we have the entire file, send that so
fanotify can use it.
Signed-off-by: Eric Paris <eparis@redhat.com>

fanotify, the upcoming notification system actually needs a struct path so it can
do opens in the context of listeners, and it needs a file so it can get f_flags
from the original process.  Close was the only operation that already was passing
a struct file to the notification hook.  This patch passes a file for access,
modify, and open as well as they are easily available to these hooks.
Signed-off-by: Eric Paris <eparis@redhat.com>

fanotify is going to need to look at file->private_data to know if an event
should be sent or not.  This passes the data (which might be a file,
dentry, inode, or none) to the should_send function calls so fanotify can
get that information when available
Signed-off-by: Eric Paris <eparis@redhat.com>

fanotify is only interested in event types which contain enough information
to open the original file in the context of the fanotify listener.  Since
fanotify may not want to send events if that data isn't present we pass
the data type to the should_send_event function call so fanotify can express
its lack of interest.
Signed-off-by: Eric Paris <eparis@redhat.com>

fsnotify event initialization is done entry by entry with almost everything
set to either 0 or NULL.  Use kmem_cache_zalloc and only initialize things
that need non-zero initialization.  Also means we don't have to change
initialization entries based on the config options.
Signed-off-by: Eric Paris <eparis@redhat.com>

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

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>

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>

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>

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>

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>

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>

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>

There are no longer any users of the inotify kernel interface.  Mark it for
removal as fsnotify is more generic and is easier to use.  There are no
known out of tree users of the inotify kernel interface.
Signed-off-by: Eric Paris <eparis@redhat.com>

Simply switch audit_trees from using inotify to using fsnotify for it's
inode pinning and disappearing act information.
Signed-off-by: Eric Paris <eparis@redhat.com>

This patch allows a task to add a second fsnotify mark to an inode for the
same group.  This mark will be added to the end of the inode's list and
this will never be found by the stand fsnotify_find_mark() function.   This
is useful if a user wants to add a new mark before removing the old one.
Signed-off-by: Eric Paris <eparis@redhat.com>

Simple copy fsnotify information from one mark to another in preparation
for the second mark to replace the first.
Signed-off-by: Eric Paris <eparis@redhat.com>

deleting audit watch rules is not currently done under audit_filter_mutex.
It was done this way because we could not hold the mutex during inotify
manipulation.  Since we are using fsnotify we don't need to do the extra
get/put pair nor do we need the private list on which to store the parents
while they are about to be freed.
Signed-off-by: Eric Paris <eparis@redhat.com>

fsnotify can handle mutexes to be held across all fsnotify operations since
it deals strickly in spinlocks.  This can simplify and reduce some of the
audit_filter_mutex taking and dropping.
Signed-off-by: Eric Paris <eparis@redhat.com>

Audit currently uses inotify to pin inodes in core and to detect when
watched inodes are deleted or unmounted.  This patch uses fsnotify instead
of inotify.
Signed-off-by: Eric Paris <eparis@redhat.com>

No real changes, just cleanup to the audit_watch split patch which we done
with minimal code changes for easy review.  Now fix interfaces to make
things work better.
Signed-off-by: Eric Paris <eparis@redhat.com>

This patch moves all of the idr editing operations into their own idr
functions.  It makes it easier to prove locking correctness and to to
understand the code flow.
Signed-off-by: Eric Paris <eparis@redhat.com>

fsnotify_add_mark is supposed to add a mark to the g_list and i_list and to
set the group and inode for the mark.  fsnotify_destroy_mark_by_entry uses
the fact that ->group != NULL to know if this group should be destroyed or
if it's already been done.

But fsnotify_add_mark sets the group and inode before it actually adds the
mark to the i_list and g_list.  This can result in a race in inotify, it
requires 3 threads.

sys_inotify_add_watch("file")	sys_inotify_add_watch("file")	sys_inotify_rm_watch([a])
inotify_update_watch()
inotify_new_watch()
inotify_add_to_idr()
   ^--- returns wd = [a]
				inotfiy_update_watch()
				inotify_new_watch()
				inotify_add_to_idr()
				fsnotify_add_mark()
				   ^--- returns wd = [b]
				returns to userspace;
								inotify_idr_find([a])
								   ^--- gives us the pointer from task 1
fsnotify_add_mark()
   ^--- this is going to set the mark->group and mark->inode fields, but will
return -EEXIST because of the race with [b].
								fsnotify_destroy_mark()
								   ^--- since ->group != NULL we call back
									into inotify_freeing_mark() which calls
								inotify_remove_from_idr([a])

since fsnotify_add_mark() failed we call:
inotify_remove_from_idr([a])     <------WHOOPS it's not in the idr, this could
					have been any entry added later!

The fix is to make sure we don't set mark->group until we are sure the mark is
on the inode and fsnotify_add_mark will return success.
Signed-off-by: Eric Paris <eparis@redhat.com>

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (102 commits)
  crypto: sha-s390 - Fix warnings in import function
  crypto: vmac - New hash algorithm for intel_txt support
  crypto: api - Do not displace newly registered algorithms
  crypto: ansi_cprng - Fix module initialization
  crypto: xcbc - Fix alignment calculation of xcbc_tfm_ctx
  crypto: fips - Depend on ansi_cprng
  crypto: blkcipher - Do not use eseqiv on stream ciphers
  crypto: ctr - Use chainiv on raw counter mode
  Revert crypto: fips - Select CPRNG
  crypto: rng - Fix typo
  crypto: talitos - add support for 36 bit addressing
  crypto: talitos - align locks on cache lines
  crypto: talitos - simplify hmac data size calculation
  crypto: mv_cesa - Add support for Orion5X crypto engine
  crypto: cryptd - Add support to access underlaying shash
  crypto: gcm - Use GHASH digest algorithm
  crypto: ghash - Add GHASH digest algorithm for GCM
  crypto: authenc - Convert to ahash
  crypto: api - Fix aligned ctx helper
  crypto: hmac - Prehash ipad/opad
  ...

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6: (377 commits)
  ASoC: au1x: PSC-AC97 bugfixes
  ALSA: dummy - Increase MAX_PCM_SUBSTREAMS to 128
  ALSA: dummy - Add debug proc file
  ALSA: Add const prefix to proc helper functions
  ALSA: Re-export snd_pcm_format_name() function
  ALSA: hda - Use auto model for HP laptops with ALC268 codec
  ALSA: cs46xx - Fix minimum period size
  ASoC: Fix WM835x Out4 capture enumeration
  ALSA: Remove unneeded ifdef from sound/core.h
  ALSA: Remove struct snd_monitor_file from public sound/core.h
  ASoC: Remove unuused hw_read_t
  sound: oxygen: work around MCE when changing volume
  ALSA: dummy - Fake buffer allocations
  ALSA: hda/realtek: Added support for CLEVO M540R subsystem, 6 channel + digital
  ASoC: fix pxa2xx-ac97.c breakage
  ALSA: dummy - Fix the timer calculation in systimer mode
  ALSA: dummy - Add more description
  ALSA: dummy - Better jiffies handling
  ALSA: dummy - Support high-res timer mode
  ALSA: Release v1.0.21
  ...

* 'writeback' of git://git.kernel.dk/linux-2.6-block:
  writeback: check for registered bdi in flusher add and inode dirty
  writeback: add name to backing_dev_info
  writeback: add some debug inode list counters to bdi stats
  writeback: get rid of pdflush completely
  writeback: switch to per-bdi threads for flushing data
  writeback: move dirty inodes from super_block to backing_dev_info
  writeback: get rid of generic_sync_sb_inodes() export

* 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6: (54 commits)
  [S390] tape: Use pr_xxx instead of dev_xxx in shared driver code
  [S390] Wire up page fault events for software perf counters.
  [S390] Remove smp_cpu_not_running.
  [S390] Get rid of cpuid.h header file.
  [S390] Limit cpu detection to 256 physical cpus.
  [S390] tape: Fix device online messages
  [S390] Enable guest page hinting by default.
  [S390] use generic scatterlist.h
  [S390] s390dbf: Add description for usage of "%s" in sprintf events
  [S390] Initialize __LC_THREAD_INFO early.
  [S390] fix recursive locking on page_table_lock
  [S390] kvm: use console_initcall() to initialize s390 virtio console
  [S390] tape: reversed order of labels
  [S390] hypfs: Use "%u" instead of "%d" for unsigned ints in snprintf
  [S390] kernel: Print an error message if kernel NSS cannot be defined
  [S390] zcrypt: Free ap_device if dev_set_name fails.
  [S390] zcrypt: Use spin_lock_bh in suspend callback
  [S390] xpram: Remove checksum validation for suspend/resume
  [S390] vmur: Invalid allocation sequence for vmur class
  [S390] hypfs: remove useless variable qname
  ...

* 'kmemleak' of git://linux-arm.org/linux-2.6:
  kmemleak: Improve the "Early log buffer exceeded" error message
  kmemleak: fix sparse warning for static declarations
  kmemleak: fix sparse warning over overshadowed flags
  kmemleak: move common painting code together
  kmemleak: add clear command support
  kmemleak: use bool for true/false questions
  kmemleak: Do no create the clean-up thread during kmemleak_disable()
  kmemleak: Scan all thread stacks
  kmemleak: Don't scan uninitialized memory when kmemcheck is enabled
  kmemleak: Ignore the aperture memory hole on x86_64
  kmemleak: Printing of the objects hex dump
  kmemleak: Do not report alloc_bootmem blocks as leaks
  kmemleak: Save the stack trace for early allocations
  kmemleak: Mark the early log buffer as __initdata
  kmemleak: Dump object information on request
  kmemleak: Allow rescheduling during an object scanning

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (48 commits)
  RDMA/iwcm: Reject the connection when the cm_id is destroyed
  RDMA/cxgb3: Clean up properly on FW mismatch failures
  RDMA/cxgb3: Don't ignore insert_handle() failures
  MAINTAINERS: InfiniBand/RDMA mailing list transition to vger
  IB/mad: Allow tuning of QP0 and QP1 sizes
  IB/mad: Fix possible lock-lock-timer deadlock
  RDMA/nes: Map MTU to IB_MTU_* and correctly report link state
  RDMA/nes: Rework the disconn routine for terminate and flushing
  RDMA/nes: Use the flush code to fill in cqe error
  RDMA/nes: Make poll_cq return correct number of wqes during flush
  RDMA/nes: Use flush mechanism to set status for wqe in error
  RDMA/nes: Implement Terminate Packet
  RDMA/nes: Add CQ error handling
  RDMA/nes: Clean out CQ completions when QP is destroyed
  RDMA/nes: Change memory allocation for cqp request to GFP_ATOMIC
  RDMA/nes: Allocate work item for disconnect event handling
  RDMA/nes: Update refcnt during disconnect
  IB/mthca: Don't allow userspace open while recovering from catastrophic error
  IB/mthca: Distinguish multiple devices in /proc/interrupts
  IB/mthca: Annotate CQ locking
  ...

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6: (57 commits)
  binfmt_elf: fix PT_INTERP bss handling
  TPM: Fixup boot probe timeout for tpm_tis driver
  sysfs: Add labeling support for sysfs
  LSM/SELinux: inode_{get,set,notify}secctx hooks to access LSM security context information.
  VFS: Factor out part of vfs_setxattr so it can be called from the SELinux hook for inode_setsecctx.
  KEYS: Add missing linux/tracehook.h #inclusions
  KEYS: Fix default security_session_to_parent()
  Security/SELinux: includecheck fix kernel/sysctl.c
  KEYS: security_cred_alloc_blank() should return int under all circumstances
  IMA: open new file for read
  KEYS: Add a keyctl to install a process's session keyring on its parent [try #6]
  KEYS: Extend TIF_NOTIFY_RESUME to (almost) all architectures [try #6]
  KEYS: Do some whitespace cleanups [try #6]
  KEYS: Make /proc/keys use keyid not numread as file position [try #6]
  KEYS: Add garbage collection for dead, revoked and expired keys. [try #6]
  KEYS: Flag dead keys to induce EKEYREVOKED [try #6]
  KEYS: Allow keyctl_revoke() on keys that have SETATTR but not WRITE perm [try #6]
  KEYS: Deal with dead-type keys appropriately [try #6]
  CRED: Add some configurable debugging [try #6]
  selinux: Support for the new TUN LSM hooks
  ...

Based on a suggestion from Jaswinder, clarify what the user would need
to do to avoid this error message from kmemleak.
Reported-by: Jaswinder Singh Rajput <jaswinder@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

For messages from the tape core that is shared between the 3590 and 34xx
tape disciplines, we want to have the "tape" prefix instead of "tape_3590"
or "tape_34xx". In order to fix this, we now use the pr_xxx printk macros.
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

smp_cpu_not_running() and cpu_stopped() are doing the same.
Remove one and also get rid of the last hard_smp_processor_id() leftover.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

Merge cpuid.h header file into cpu.h.
While at it convert from typedef to struct declaration and also
convert cio code to use proper lowcore structure instead of casts.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

Saves us more than 65k pointless IPIs.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>