While the comment says:
* To prevent rpciod from hanging, this allocator never sleeps,
* returning NULL if the request cannot be serviced immediately.
The function does not actually check for NULL pointers being returned.
Signed-off-by: Peter Zijlstra <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
Change the atomic_t in struct nfs_server to atomic_long_t in anticipation
of machines that can handle 8+TB of (4K) pages under writeback.
However I suspect other things in NFS will start going *bang* by then.
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Trond Myklebust <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
invalidate_bdev() is superfluous when truncate_inode_pages() is also
called. do call invalidate_bh_lrus() though, to avoid stale pointers.
Signed-off-by: Peter Zijlstra <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Remove duplicate work in kill_bdev().
It currently invalidates and then truncates the bdev's mapping.
invalidate_mapping_pages() will opportunistically remove pages from the
mapping. And truncate_inode_pages() will forcefully remove all pages.
The only thing truncate doesn't do is flush the bh lrus. So do that
explicitly. This avoids (very unlikely) but possible invalid lookup
results if the same bdev is quickly re-issued.
It also will prevent extreme kernel latencies which are observed when
blockdevs which have a large amount of pagecache are unmounted, by avoiding
invalidate_mapping_pages() on that path. invalidate_mapping_pages() has no
cond_resched (it can be called under spinlock), whereas truncate_inode_pages()
has one.
[[email protected]: restore nrpages==0 optimisation]
Signed-off-by: Peter Zijlstra <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Remove the destroy_dirty_buffers argument from invalidate_bdev(), it hasn't
been used in 6 years (so akpm says).
find * -name \*.[ch] | xargs grep -l invalidate_bdev |
while read file; do
quilt add $file;
sed -ie 's/invalidate_bdev(\([^,]*\),[^)]*)/invalidate_bdev(\1)/g' $file;
done
Signed-off-by: Peter Zijlstra <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The current NFS client congestion logic is severly broken, it marks the
backing device congested during each nfs_writepages() call but doesn't
mirror this in nfs_writepage() which makes for deadlocks. Also it
implements its own waitqueue.
Replace this by a more regular congestion implementation that puts a cap on
the number of active writeback pages and uses the bdi congestion waitqueue.
Also always use an interruptible wait since it makes sense to be able to
SIGKILL the process even for mounts without 'intr'.
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Trond Myklebust <[email protected]>
Cc: Christoph Lameter <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
ecryptfs uses a lock_parent() function, which I hope really locks the parents
and is not abused
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Michael Halcrow <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Fix up the work on stack and exit scope trouble by placing the work_struct
in the uml_net_private data.
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Jeff Dike <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Fix the locking of signal->tty.
Use ->sighand->siglock to protect ->signal->tty; this lock is already used
by most other members of ->signal/->sighand. And unless we are 'current'
or the tasklist_lock is held we need ->siglock to access ->signal anyway.
(NOTE: sys_unshare() is broken wrt ->sighand locking rules)
Note that tty_mutex is held over tty destruction, so while holding
tty_mutex any tty pointer remains valid. Otherwise the lifetime of ttys
are governed by their open file handles. This leaves some holes for tty
access from signal->tty (or any other non file related tty access).
It solves the tty SLAB scribbles we were seeing.
(NOTE: the change from group_send_sig_info to __group_send_sig_info needs to
be examined by someone familiar with the security framework, I think
it is safe given the SEND_SIG_PRIV from other __group_send_sig_info
invocations)
[[email protected]: 3270 fix]
[[email protected]: various post-viro fixes]
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Alan Cox <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Prarit Bhargava <[email protected]>
Cc: Chris Wright <[email protected]>
Cc: Roland McGrath <[email protected]>
Cc: Stephen Smalley <[email protected]>
Cc: James Morris <[email protected]>
Cc: "David S. Miller" <[email protected]>
Cc: Jeff Dike <[email protected]>
Cc: Martin Schwidefsky <[email protected]>
Cc: Jan Kara <[email protected]>
Signed-off-by: Martin Schwidefsky <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Workqueue functions should not leak locks, assert so, printing the
last function ran.
Use macros in lockdep.h to avoid include dependency pains.
[[email protected]: build fix]
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Ingo Molnar <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Add debug_show_held_locks(current) to __might_sleep() and schedule(); this
makes finding the offending lock leak easier.
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Ingo Molnar <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
rmmod/3080 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
(proc_subdir_lock){--..}, at: [<c04a33b0>] remove_proc_entry+0x40/0x191
and this task is already holding:
(ide_lock){++..}, at: [<c05651a2>] ide_unregister_subdriver+0x39/0xc8
which would create a new lock dependency:
(ide_lock){++..} -> (proc_subdir_lock){--..}
but this new dependency connects a hard-irq-safe lock:
(ide_lock){++..}
... which became hard-irq-safe at:
[<c043c458>] lock_acquire+0x4b/0x6b
[<c06129d7>] _spin_lock_irqsave+0x22/0x32
[<c0567870>] ide_intr+0x17/0x1a9
[<c044eb31>] handle_IRQ_event+0x20/0x4d
[<c044ebf2>] __do_IRQ+0x94/0xef
[<c0406771>] do_IRQ+0x9e/0xbd
to a hard-irq-unsafe lock:
(proc_subdir_lock){--..}
... which became hard-irq-unsafe at:
... [<c043c458>] lock_acquire+0x4b/0x6b
[<c06126ab>] _spin_lock+0x19/0x28
[<c04a32f2>] xlate_proc_name+0x1b/0x99
[<c04a3547>] proc_create+0x46/0xdf
[<c04a3642>] create_proc_entry+0x62/0xa5
[<c07c1972>] proc_misc_init+0x1c/0x1d2
[<c07c1844>] proc_root_init+0x4c/0xe9
[<c07ad703>] start_kernel+0x294/0x3b3
Move ide_remove_proc_entries() out from under ide_lock; there is nothing
that indicates that this is needed.
In specific, the call to ide_add_proc_entries() is unprotected, and there
is nothing else in the file using the respective ->proc fields. Also the
lock order around destroy_proc_ide_interface() suggests this.
Alan sayeth:
proc_ide_write_settings walks the setting list under ide_setting_sem, read
ditto. remove_proc_entry is doing proc side housekeeping.
Looks fine to me, although that old code is such a mess anything could be
going on.
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Alan Cox <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Stick NFS sockets in their own class to avoid some lockdep warnings. NFS
sockets are never exposed to user-space, and will hence not trigger certain
code paths that would otherwise pose deadlock scenarios.
[[email protected]: cleanups]
Signed-off-by: Peter Zijlstra <[email protected]>
Signed-off-by: Steven Dickson <[email protected]>
Acked-by: Ingo Molnar <[email protected]>
Cc: Trond Myklebust <[email protected]>
Acked-by: Neil Brown <[email protected]>
Cc: "David S. Miller" <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
[ Fixed patch corruption by quilt, pointed out by Peter Zijlstra ]
Signed-off-by: Linus Torvalds <[email protected]>
Make kmap_atomic/kunmap_atomic denote a pagefault disabled scope. All non
trivial implementations already do this anyway.
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Nick Piggin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Introduce pagefault_{disable,enable}() and use these where previously we did
manual preempt increments/decrements to make the pagefault handler do the
atomic thing.
Currently they still rely on the increased preempt count, but do not rely on
the disabled preemption, this might go away in the future.
(NOTE: the extra barrier() in pagefault_disable might fix some holes on
machines which have too many registers for their own good)
[[email protected]: s390 fix]
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Nick Piggin <[email protected]>
Cc: Martin Schwidefsky <[email protected]>
Signed-off-by: Heiko Carstens <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
In light of the recent pagefault and filemap_copy_from_user work I've gone
through all the arch pagefault handlers to make sure the inc_preempt_count()
'feature' works as expected.
Several sections of code (including the new filemap_copy_from_user) rely on
the fact that faults do not take locks under increased preempt count.
arch/x86_64 - good
arch/powerpc - good
arch/cris - fixed
arch/i386 - good
arch/parisc - fixed
arch/sh - good
arch/sparc - good
arch/s390 - good
arch/m68k - fixed
arch/ppc - good
arch/alpha - fixed
arch/mips - good
arch/sparc64 - good
arch/ia64 - good
arch/arm - fixed
arch/um - good
arch/avr32 - good
arch/h8300 - NA
arch/m32r - good
arch/v850 - good
arch/frv - fixed
arch/m68knommu - NA
arch/arm26 - fixed
arch/sh64 - fixed
arch/xtensa - good
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Nick Piggin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
I noticed an insane high density of repeated characters fixable by a
simple regular expression:
% s/{.fn = \([^,]*\),[[:space:]]\+\(\\\n[[:space:]]\+\)\?.name = "\1"}/TYPE_SCTP_FUNC(\1)/g
(NOTE: the .name for .fn = sctp_sf_do_9_2_start_shutdown didn't match)
Signed-off-by: Peter Zijlstra <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Make the delayacct lock irqsave; this avoids the possible deadlock where
an interrupt is taken while holding the delayacct lock which needs to
take the delayacct lock.
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Oleg Nesterov <[email protected]>
Cc: Balbir Singh <[email protected]>
Cc: Shailabh Nagar <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
BUG: warning at kernel/rtmutex-debug.c:125/rt_mutex_debug_task_free() (Not tainted)
[<c04051e3>] show_trace_log_lvl+0x58/0x16a
[<c04057f0>] show_trace+0xd/0x10
[<c0405900>] dump_stack+0x19/0x1b
[<c043f03d>] rt_mutex_debug_task_free+0x35/0x6a
[<c04224c0>] free_task+0x15/0x24
[<c042378c>] copy_process+0x12bd/0x1324
[<c0423835>] do_fork+0x42/0x113
[<c04021dd>] sys_fork+0x19/0x1b
[<c0403fb7>] syscall_call+0x7/0xb
In copy_process(), dup_task_struct() also duplicates the ->pi_lock,
->pi_waiters and ->pi_blocked_on members. rt_mutex_debug_task_free()
called from free_task() validates these members. However free_task() can
be invoked before these members are reset for the new task.
Move the initialization code before the first bail that can hit free_task().
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Ingo Molnar <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This annotation makes it possible to assign a subclass on lock init. This
annotation is meant to reduce the _nested() annotations by assigning a
default subclass.
One could do without this annotation and rely on lockdep_set_class()
exclusively, but that would require a manual stack of struct lock_class_key
objects.
Signed-off-by: Peter Zijlstra <[email protected]>
Signed-off-by: Dmitry Torokhov <[email protected]>
BUG: warning at kernel/lockdep.c:1816/trace_hardirqs_on() (Not tainted)
Call Trace:
show_trace
dump_stack
trace_hardirqs_on
:forcedeth:nv_nic_irq_other
handle_IRQ_event
__do_IRQ
do_IRQ
ret_from_intr
DWARF2 barf
default_idle
cpu_idle
rest_init
start_kernel
_sinittext
These 3 functions nv_nic_irq_tx(), nv_nic_irq_rx() and nv_nic_irq_other()
are reachable from IRQ context and process context. Make use of the
irq-save/restore spinlock variant.
(Compile tested only, since I do not have the hardware)
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Jeff Garzik <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arjan van de Ven <[email protected]>
Cc: Dave Jones <[email protected]>
Cc: Andrew Morton <[email protected]>
Signed-off-by: Jeff Garzik <[email protected]>
Currently we can silently drop data if the write to swap failed. It
usually doesn't result in data-corruption because on page-in the process
will receive SIGBUS (assuming write-failure implies read-failure).
This assumption might or might not be valid.
This patch will avoid the page being discarded after a failed write. But
will print a warning the sysadmin _should_ take to heart, if a lot of swap
space becomes un-writeable, OOM is not far off.
Tested by making the write fail 'randomly' once every 50 writes or so.
[[email protected]: printk warning fix]
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
With the tracking of dirty pages properly done now, msync doesn't need to scan
the PTEs anymore to determine the dirty status.
From: Hugh Dickins <[email protected]>
In looking to do that, I made some other tidyups: can remove several
#includes, and sys_msync loop termination not quite right.
Most of those points are criticisms of the existing sys_msync, not of your
patch. In particular, the loop termination errors were introduced in 2.6.17:
I did notice this shortly before it came out, but decided I was more likely to
get it wrong myself, and make matters worse if I tried to rush a last-minute
fix in. And it's not terribly likely to go wrong, nor disastrous if it does
go wrong (may miss reporting an unmapped area; may also fsync file of a
following vma).
Signed-off-by: Peter Zijlstra <[email protected]>
Signed-off-by: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Wrt. the recent modifications in do_wp_page() Hugh Dickins pointed out:
"I now realize it's right to the first order (normal case) and to the
second order (ptrace poke), but not to the third order (ptrace poke
anon page here to be COWed - perhaps can't occur without intervening
mprotects)."
This patch restores the old COW behaviour for anonymous pages.
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Smallish cleanup to install_page(), could save a memory read (haven't checked
the asm output) and sure looks nicer.
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
mprotect() resets the page protections, which could result in extra write
faults for those pages whose dirty state we track using write faults and are
dirty already.
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Now that we can detect writers of shared mappings, throttle them. Avoids OOM
by surprise.
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Tracking of dirty pages in shared writeable mmap()s.
The idea is simple: write protect clean shared writeable pages, catch the
write-fault, make writeable and set dirty. On page write-back clean all the
PTE dirty bits and write protect them once again.
The implementation is a tad harder, mainly because the default
backing_dev_info capabilities were too loosely maintained. Hence it is not
enough to test the backing_dev_info for cap_account_dirty.
The current heuristic is as follows, a VMA is eligible when:
- its shared writeable
(vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)
- it is not a 'special' mapping
(vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0
- the backing_dev_info is cap_account_dirty
mapping_cap_account_dirty(vma->vm_file->f_mapping)
- f_op->mmap() didn't change the default page protection
Page from remap_pfn_range() are explicitly excluded because their COW
semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and
because they don't have a backing store anyway.
mprotect() is taught about the new behaviour as well. However it overrides
the last condition.
Cleaning the pages on write-back is done with page_mkclean() a new rmap call.
It can be called on any page, but is currently only implemented for mapped
pages, if the page is found the be of a VMA that accounts dirty pages it will
also wrprotect the PTE.
Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from
under ->private_lock. This seems to be safe, since ->private_lock is used to
serialize access to the buffers, not the page itself. This is needed because
clear_page_dirty() will call into page_mkclean() and would thereby violate
locking order.
[[email protected]: Provide a page_mkclean() implementation for NOMMU]
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Hugh Dickins <[email protected]>
Signed-off-by: David Howells <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
On Wed, 2006-08-09 at 07:57 +0200, Rolf Eike Beer wrote:
> =============================================
> [ INFO: possible recursive locking detected ]
> ---------------------------------------------
> parted/7929 is trying to acquire lock:
> (&bdev->bd_mutex){--..}, at: [<c105eb8d>] __blkdev_put+0x1e/0x13c
>
> but task is already holding lock:
> (&bdev->bd_mutex){--..}, at: [<c105eec6>] do_open+0x72/0x3a8
>
> other info that might help us debug this:
> 1 lock held by parted/7929:
> #0: (&bdev->bd_mutex){--..}, at: [<c105eec6>] do_open+0x72/0x3a8
> stack backtrace:
> [<c1003aad>] show_trace_log_lvl+0x58/0x15b
> [<c100495f>] show_trace+0xd/0x10
> [<c1004979>] dump_stack+0x17/0x1a
> [<c102dee5>] __lock_acquire+0x753/0x99c
> [<c102e3b0>] lock_acquire+0x4a/0x6a
> [<c1204501>] mutex_lock_nested+0xc8/0x20c
> [<c105eb8d>] __blkdev_put+0x1e/0x13c
> [<c105ecc4>] blkdev_put+0xa/0xc
> [<c105f18a>] do_open+0x336/0x3a8
> [<c105f21b>] blkdev_open+0x1f/0x4c
> [<c1057b40>] __dentry_open+0xc7/0x1aa
> [<c1057c91>] nameidata_to_filp+0x1c/0x2e
> [<c1057cd1>] do_filp_open+0x2e/0x35
> [<c1057dd7>] do_sys_open+0x38/0x68
> [<c1057e33>] sys_open+0x16/0x18
> [<c1002845>] sysenter_past_esp+0x56/0x8d
OK, I'm having a look here; its all new to me so bear with me.
blkdev_open() calls
do_open(bdev, ...,BD_MUTEX_NORMAL) and takes
mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_NORMAL)
then something fails, and we're thrown to:
out_first: where
if (bdev != bdev->bd_contains)
blkdev_put(bdev->bd_contains) which is
__blkdev_put(bdev->bd_contains, BD_MUTEX_NORMAL) which does
mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_NORMAL) <--- lockdep trigger
When going to out_first, dbev->bd_contains is either bdev or whole, and
since we take the branch it must be whole. So it seems to me the
following patch would be the right one:
[[email protected]: compile fix]
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Arjan van de Ven <[email protected]>
Acked-by: NeilBrown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The comment states: 'Setting a tag on a not-present item is a BUG.' Hence
if 'index' is larger than the maxindex; the item _cannot_ be presen; it
should also be a BUG.
Also, this allows the following statement (assume a fresh tree):
radix_tree_tag_set(root, 16, 1);
to fail silently, but when preceded by:
radix_tree_insert(root, 32, item);
it would BUG, because the height has been extended by the insert.
In neither case was 16 present.
Signed-off-by: Peter Zijlstra <[email protected]>
Acked-by: Nick Piggin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Peter Zijlstra