->readdir passes lofft_t offsets (used as nfs cookies) to
nfs3svc_encode_entry{,_plus}, but when they pass it on to encode_entry it
becomes an 'off_t', which isn't good.

So filesystems that returned 64bit offsets would lose.
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

unlock_buffer(), like unlock_page(), must not clear the lock without
ensuring that the critical section is closed.

Mingming later sent the same patch, saying:

We are running SDET benchmark and saw double free issue for ext3 extended
attributes block, which complains the same xattr block already being freed (in
ext3_xattr_release_block()).  The problem could also been triggered by
multiple threads loop untar/rm a kernel tree.

The race is caused by missing a memory barrier at unlock_buffer() before the
lock bit being cleared, resulting in possible concurrent h_refcounter update.
That causes a reference counter leak, then later leads to the double free that
we have seen.

Inside unlock_buffer(), there is a memory barrier is placed *after* the lock
bit is being cleared, however, there is no memory barrier *before* the bit is
cleared.  On some arch the h_refcount update instruction and the clear bit
instruction could be reordered, thus leave the critical section re-entered.

The race is like this: For example, if the h_refcount is initialized as 1,

cpu 0:                                   cpu1
--------------------------------------   -----------------------------------
lock_buffer() /* test_and_set_bit */
clear_buffer_locked(bh);
                                        lock_buffer() /* test_and_set_bit */
h_refcount = h_refcount+1; /* = 2*/     h_refcount = h_refcount + 1; /*= 2 */
                                        clear_buffer_locked(bh);
....                                    ......

We lost a h_refcount here.  We need a memory barrier before the buffer head
lock bit being cleared to force the order of the two writes.  Please apply.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

It didn't handle that case at all, and now dump_stack()
can be implemented directly as show_stack(current, NULL)
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

The snap_rcv code reads 5 bytes so we should make sure that
we have 5 bytes in the head before proceeding.

Based on diagnosis and fix by Evgeniy Polyakov, reported by
Alan J. Wylie.

Patch also kills the skb->sk assignment before kfree_skb
since it's redundant.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

-Fixes ABBA deadlock noted by Patrick McHardy <kaber@trash.net>:

> There is at least one ABBA deadlock, est_timer() does:
> read_lock(&est_lock)
> spin_lock(e->stats_lock) (which is dev->queue_lock)
>
> and qdisc_destroy calls htb_destroy under dev->queue_lock, which
> calls htb_destroy_class, then gen_kill_estimator and this
> write_locks est_lock.

To fix the ABBA deadlock the rate estimators are now kept on an rcu list.

-The est_lock changes the use from protecting the list to protecting
the update to the 'bstat' pointer in order to avoid NULL dereferencing.

-The 'interval' member of the gen_estimator structure removed as it is
not needed.
Signed-off-by: Ranko Zivojnovic <ranko@spidernet.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Currently when icmp_errors_use_inbound_ifaddr is set and an ICMP error is
sent after the packet passed through ip_output(), an address from the
outgoing interface is chosen as ICMP source address since skb->dev doesn't
point to the incoming interface anymore.

Fix this by doing an interface lookup on rt->dst.iif and using that device.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Normally a serial Bluetooth device is opened, TIOSETD'ed to N_HCI line
discipline, HCIUARTSETPROTO'ed and finally closed. In case the device
fails to HCIUARTSETPROTO, closing it produces a NULL pointer dereference.
Signed-off-by: Ohad Ben-Cohen <ohad@bencohen.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

A trivial fix to (what looks like) an unintentional fall-through in the
HCI line discipline.
Signed-off-by: Ohad Ben-Cohen <ohad@bencohen.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Add "optical" to sysfs "media" attribute as already in /proc
Signed-off-by: Danny Kukawka <dkukawka@suse.de>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Sergey Vlasov reported that his "FUJITSU MCC3064AP, ATAPI OPTICAL drive"
pops up as UNKNOWN in /proc/ide/*/media .

Closes kernel Bugzilla #4145.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

On the SCSI layer ioctl path there is no implicit permissions check for
ioctls (and indeed other drivers implement unprivileged ioctls). aacraid
however allows all sorts of very admin only things to be done so should
check.
Signed-off-by: Alan Cox <alan@redhat.com>
Acked-by: Mark Salyzyn <mark_salyzyn@adaptec.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

This patch makes CIFS honour a process' umask like other filesystems.
Of course the server is still free to munge the permissions if it wants
to; but the client will send the "right" permissions to begin with.

A few caveats:

1) It only applies to filesystems that have CAP_UNIX (aka support unix
extensions)
2) It applies the correct mode to the follow up CIFSSMBUnixSetPerms()
after remote creation

When mode to CIFS/NTFS ACL mapping is complete we can do the
same thing for that case for servers which do not
support the Unix Extensions.
Signed-off-by: Matt Keenen <matt@opcode-solutions.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Reported by Chris Evans <scarybeasts@gmail.com>:

> The summary is that an evil 80211 frame can crash out a victim's
> machine. It only applies to drivers using the 80211 wireless code, and
> only then to certain drivers (and even then depends on a card's
> firmware not dropping a dubious packet). I must confess I'm not
> keeping track of Linux wireless support, and the different protocol
> stacks etc.
>
> Details are as follows:
>
> ieee80211_rx() does not explicitly check that "skb->len >= hdrlen".
> There are other skb->len checks, but not enough to prevent a subtle
> off-by-two error if the frame has the IEEE80211_STYPE_QOS_DATA flag
> set.
>
> This leads to integer underflow and crash here:
>
> if (frag != 0)
>    flen -= hdrlen;
>
> (flen is subsequently used as a memcpy length parameter).

How about this?
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

The pwc driver is defficient in locking, which can trigger an oops
when disconnecting.

Adrian Bunk:
Backported to 2.6.16.
Signed-off-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

The pwc driver has a disconnect method that waits for user space to
close the device. This opens up an opportunity for a DoS attack,
blocking the USB subsystem and making khubd's task busy wait in
kernel space. This patch shifts freeing resources to close if an opened
device is disconnected.

Adrian Bunk:
Backported to 2.6.16.
Signed-off-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Looks like the MAP_FIXED case is using the wrong address hint.  I'd
expect the comment "don't mess with it" means pass the request
straight on through, not change the address requested to -ENOMEM.
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

On 32-bit machines, mount -t hugetlbfs -o size=4G gave a 0GB filesystem,
size=5G gave a 1GB filesystem etc: there's no point in masking size with
HPAGE_MASK just before shifting its lower bits away, and since HPAGE_MASK is a
UL, that removed all the higher bits of the unsigned long long size.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

The lats commit causes the wrong return value.
is_hugepage_only_range() is a boolean, so we should return
-EINVAL rather than 1.

Also - we can use "mm" instead of looking up "current->mm" again.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Unlike mmap(), the codepath for brk() creates a vma without first checking
that it doesn't touch a region exclusively reserved for hugepages.  On
powerpc, this can allow it to create a normal page vma in a hugepage
region, causing oopses and other badness.

Add a test to prevent this.  With this patch, brk() will simply fail if it
attempts to move the break into a hugepage reserved region.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

fix is_hugepage_only_range() definition to be "overlaps"
instead of "within architectural restricted hugetlb address
range".  Simplify the ia64 specific code that used to use
is_hugepage_only_range() to just check which region the
address is in.
Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

When expanding the stack, we don't currently check if the VMA will cross
into an area of the address space that is reserved for hugetlb pages.
Subsequent faults on the expanded portion of such a VMA will confuse the
low-level MMU code, resulting in an OOPS.  Check for this.
Signed-off-by: Adam Litke <agl@us.ibm.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

If it's EXPORT_SYMBOL'ed it can't be __devinit.

Reported by Mikael Pettersson.
Signed-off-by: Adrian Bunk <bunk@kernel.org>

hugetlb_vmtruncate_list was misconverted to prio_tree: its prio_tree is in
units of PAGE_SIZE (PAGE_CACHE_SIZE) like any other, not HPAGE_SIZE (whereas
its radix_tree is kept in units of HPAGE_SIZE, otherwise slots would be
absurdly sparse).

At first I thought the error benign, just calling __unmap_hugepage_range on
more vmas than necessary; but on 32-bit machines, when the prio_tree is
searched correctly, it happens to ensure the v_offset calculation won't
overflow.  As it stood, when truncating at or beyond 4GB, it was liable to
discard pages COWed from lower offsets; or even to clear pmd entries of
preceding vmas, triggering exit_mmap's BUG_ON(nr_ptes).
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

In kernel bugzilla #6248 (http://bugzilla.kernel.org/show_bug.cgi?id=6248),
Adrian Bunk <bunk@stusta.de> notes that CONFIG_HUGETLBFS is missing Kconfig
help text.
Signed-off-by: Arthur Othieno <apgo@patchbomb.org>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Fix typos, spelling, etc., in Doc/vm/hugetlbpage.txt.
Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

DEBUG_PAGEALLOC is not compatible with hugetlb page support.  That debug
option turns off PSE.  Once it is turned off in CR4, the cpu will ignore
pse bit in the pmd and causing infinite page-not- present faults.

So disable DEBUG_PAGEALLOC if the user selected hugetlbfs.
Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Function lazy_mmu_prot_update is also used on huge pages when it is called
by set_huge_ptep_writable, but it isn't aware of huge pages.
Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com>
Acked-by: Ken Chen <kenneth.w.chen@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Clear parent death signal on SID transitions to prevent unauthorized
signaling between SIDs.
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Acked-by: Eric Paris <eparis@parisplace.org>
Signed-off-by: James Morris <jmorris@localhost.localdomain>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

I need this patch to get a UML kernel to compile.  This is with the
kernel headers in FC6 which are automatically generated from the kernel
tree.  Some headers are missing but those files don't need them.  At
least it appears so since the resuling kernel works fine.

Tested on x86-64.
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

cherry picked from commit c545d6ad

Update get_dvb_firmware script for the new location of the
tda10046 firmware.

The old location doesn't work anymore.
Signed-off-by: Andreas Arens <ari@goron.de>
Signed-off-by: Michael Krufky <mkrufky@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

cherry picked from commit 302170a4

get_dvb_firmware: update script for new location of sp8870 firmware

This url is no longer valid:
http://www.technotrend.de/new/217g/tt_Premium_217g.zip

Replace with:
http://www.softwarepatch.pl/9999ccd06a4813cb827dbb0005071c71/tt_Premium_217g.zip

Thanks-to: Tobias Stoeber <tobi@to-st.de>
Signed-off-by: Michael Krufky <mkrufky@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

We went and named them __NR_sys_foo instead of __NR_foo.

It may be too late to change this, but we can at least add the proper names
now.
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

Signed-off-by: Jan Altenberg <tb10alj@tglx.de>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

When only GSO skb was partially ACKed, no hints are reset,
therefore fastpath_cnt_hint must be tweaked too or else it can
corrupt fackets_out. The corruption to occur, one must have
non-trivial ACK/SACK sequence, so this bug is not very often
that harmful. There's a fackets_out state reset in TCP because
fackets_out is known to be inaccurate and that fixes the issue
eventually anyway.

In case there was also at least one skb that got fully ACKed,
the fastpath_skb_hint is set to NULL which causes a recount for
fastpath_cnt_hint (the old value won't be accessed anymore),
thus it can safely be decremented without additional checking.

Reported by Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>