02 Mar, 2007
40 commits
-
Describes how/when the information exported to `/proc/stat' is calculated,
and possible problems with this approach.Signed-off-by: Vassili Karpov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The SMT scheduler incorrectly skips kernel threads even if they are
runnable (but they are preempted by a higher-prio user-space task which got
SMT-delayed by an even higher-priority task running on a sibling CPU).Fix this for now by only doing the SMT-nice optimization if the
to-be-delayed task is the only runnable task. (This should cover most of
the real-life cases anyway.)This bug has been in the SMT scheduler since 2.6.17 or so, but has only
been noticed now by the active check in the dynticks code.Signed-off-by: Ingo Molnar
Cc: Michal Piotrowski
Cc: Nick Piggin
Cc: Thomas Gleixner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
ps3: Introduce CONFIG_PS3_ADVANCED, as suggested by Roman Zippel, and use
it to control questions about PS3 subsystems that may not be obvious for
the casual user.This gets rid of the following warning on non-powerpc platforms: |
drivers/video/Kconfig:1604:warning: 'select' used by config symbol 'FB_PS3'
refer to undefined symbol 'PS3_PS3AV'Signed-off-by: Geert Uytterhoeven
Acked-by: Geoff Levand
Cc: Paul Mackerras
Cc: Roman Zippel
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
There are race issues around ext[34] xattr block release code.
ext[34]_xattr_release_block() checks the reference count of xattr block
(h_refcount) and frees that xattr block if it is the last one reference it.
Unlike ext2, the check of this counter is unprotected by any lock.
ext[34]_xattr_release_block() will free the mb_cache entry before freeing
that xattr block. There is a small window between the check for the re
h_refcount ==1 and the call to mb_cache_entry_free(). During this small
window another inode might find this xattr block from the mbcache and reuse
it, racing a refcount updates. The xattr block will later be freed by the
first inode without notice other inode is still use it. Later if that
block is reallocated as a datablock for other file, then more serious
problem might happen.We need put a lock around places checking the refount as well to avoid
racing issue. Another place need this kind of protection is in
ext3_xattr_block_set(), where it will modify the xattr block content in-
the-fly if the refcount is 1 (means it's the only inode reference it).This will also fix another issue: the xattr block may not get freed at all
if no lock is to protect the refcount check at the release time. It is
possible that the last two inodes could release the shared xattr block at
the same time. But both of them think they are not the last one so only
decreased the h_refcount without freeing xattr block at all.We need to call lock_buffer() after ext3_journal_get_write_access() to
avoid deadlock (because the later will call lock_buffer()/unlock_buffer
() as well).Signed-off-by: Mingming Cao
Cc: Andreas Gruenbacher
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix the fact that pte_mkread set _PAGE_RW instead of _PAGE_USER (the logic is
copied from i386 in most place, so it is really as bad as you're thinking).Thus currently page tables are more permissive than they should.
Such a change may trigger other latent bugs, so be careful with this.
Signed-off-by: Paolo 'Blaisorblade' Giarrusso
Signed-off-by: Jeff Dike
Cc: Paolo 'Blaisorblade' Giarrusso
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This fixes a problem seen by a number of people running UML on newer host
kernels. init would hang with an infinite segfault loop.It turns out that the host kernel was providing a AT_SYSINFO_EHDR of
0xffffe000, which faked UML into believing that the host VDSO page could be
reused. However, AT_SYSINFO pointed into the middle of the address space, and
was unmapped as a result. Because UML was providing AT_SYSINFO_EHDR and
AT_SYSINFO to its own processes, these would branch to nowhere when trying to
use the VDSO.The fix is to also check the location of AT_SYSINFO when deciding whether to
use the host's VDSO.Signed-off-by: Jeff Dike
Cc: Paolo 'Blaisorblade' Giarrusso
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add the RAW device driver options to the UML Kconfig.char file so that you may
use them in UML.Signed-off-by: Allan Graves
Signed-off-by: Jeff Dike
Cc: Paolo 'Blaisorblade' Giarrusso
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
linux/irq.h uses EINVAL but does not #include linux/errno.h. This results in
the compiler spitting out errors on some files.Signed-off-by: David Howells
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
throttle_vm_writeout() is designed to wait for the dirty levels to subside.
But if the caller holds IO or FS locks, we might be holding up that writeout.So change it to take a single nap to give other devices a chance to clean some
memory, then return.Cc: Nick Piggin
Cc: OGAWA Hirofumi
Cc: Kumar Gala
Cc: Pete Zaitcev
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Since the bay driver depends on the dock driver for proper notification,
make this driver depend on the dock driver.Signed-off-by: Kristen Carlson Accardi
Acked-by: Len Brown
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The code is seemingly trying to make sure that rb_next() brings us to
successive increasing vma entries.But the two variables, prev and pend, used to perform these checks, are
never advanced.Signed-off-by: David S. Miller
Cc: Andrea Arcangeli
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
In the 2.6.20 hang patch, I accidentally threw out an error message.
This puts it back.Signed-off-by: Jeff Dike
Cc: Paolo 'Blaisorblade' Giarrusso
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add some locking to host_ldt_entries to prevent racing when reading LDT
information from the host.The locking is somewhat more careful than my previous attempt. Now, only
the check of host_ldt_entries is locked. The lock is dropped immediately
afterwards, and if the LDT needs initializing, that (and the memory
allocations needed) proceed outside the lock.Also fixed some style violations.
Signed-off-by: Jeff Dike
Cc: Paolo 'Blaisorblade' Giarrusso
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
a) Remove #define acrobatics that have become unnecessary by the move of
asyncdata.o into the common part.b) Correct the rule for building the common part into the kernel when
some or all hardware specific parts are built as modules.Signed-off-by: Tilman Schmidt
Cc: Adrian Bunk
Cc: Karsten Keil
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Dmitriy Monakhov wrote:
> if path_lookup() return non zero code we don't have to worry about
> 'nd' parameter, but ecryptfs_read_super does path_release(&nd) after
> path_lookup has failed, and dentry counter becomes negativeDo not do a path_release after a path_lookup error.
Signed-off-by: Michael Halcrow
Cc: Dmitriy Monakhov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Remove unnecessary flush_dcache_page() call. Thanks to Dmitriy
Monakhov for pointing this out.Signed-off-by: Michael Halcrow
Cc: Dmitriy Monakhov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
O_LARGEFILE should be set here when opening the lower file.
Signed-off-by: Michael Halcrow
Cc: Dmitriy Monakhov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix an oops on the rtc_device_unregister() path by waiting until the last
moment before nulling the rtc->ops vector. Fix some potential oopses by
having the rtc_class_open()/rtc_class_close() interface increase the RTC's
reference count while an RTC handle is available outside the RTC framework.Signed-off-by: David Brownell
Cc: Alessandro Zummo
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
adaplas@pol.net is still alive, but is choking on the traffic.
Signed-off-by: Antonino Daplas
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add -mm testing to SubmitChecklist.
Signed-off-by: Randy Dunlap
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
lockdep_init() is marked __init but used in several places
outside __init code. This causes following warnings:
$ scripts/mod/modpost kernel/lockdep.o
WARNING: kernel/built-in.o - Section mismatch: reference to .init.text:lockdep_init from .text.lockdep_init_map after 'lockdep_init_map' (at offset 0x105)
WARNING: kernel/built-in.o - Section mismatch: reference to .init.text:lockdep_init from .text.lockdep_reset_lock after 'lockdep_reset_lock' (at offset 0x35)
WARNING: kernel/built-in.o - Section mismatch: reference to .init.text:lockdep_init from .text.__lock_acquire after '__lock_acquire' (at offset 0xb2)The warnings are less obviously due to heavy inlining by gcc - this is not
altered.Fix the section mismatch warnings by removing the __init marking, which
seems obviously wrong.Signed-off-by: Sam Ravnborg
Acked-by: Ingo Molnar
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Rename PG_checked to PG_owner_priv_1 to reflect its availablilty as a
private flag for use by the owner/allocator of the page. In the case of
pagecache pages (which might be considered to be owned by the mm),
filesystems may use the flag.Signed-off-by: Jeremy Fitzhardinge
Signed-off-by: Nick Piggin
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
/home/bunk/linux/kernel-2.6/linux-2.6.20-mm2/kernel/sysctl.c:1411: error: conflicting types for 'register_sysctl_table'
/home/bunk/linux/kernel-2.6/linux-2.6.20-mm2/include/linux/sysctl.h:1042: error: previous declaration of 'register_sysctl_table' was here
make[2]: *** [kernel/sysctl.o] Error 1Caused by commit 0b4d414714f0d2f922d39424b0c5c82ad900a381.
Signed-off-by: Adrian Bunk
Cc: "Eric W. Biederman"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Problem description at:
http://bugzilla.kernel.org/show_bug.cgi?id=8048Commit b18ec80396834497933d77b81ec0918519f4e2a7
[PATCH] sched: improve migration accuracy
optimized the scheduler time calculations, but broke posix-cpu-timers.The problem is that the p->last_ran value is not updated after a context
switch. So a subsequent call to current_sched_time() calculates with a
stale p->last_ran value, i.e. accounts the full time, which the task was
scheduled away.Signed-off-by: Thomas Gleixner
Acked-by: Ingo Molnar
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
eCryptfs lower file handling code has several issues:
- Retval from prepare_write()/commit_write() wasn't checked to equality
to AOP_TRUNCATED_PAGE.
- In some places page wasn't unmapped and unlocked after error.Signed-off-by: Michael Halcrow
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix kernel-doc warnings in 2.6.20-git15 (lib/, mm/, kernel/, include/).
Signed-off-by: Randy Dunlap
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Allow space(s) between "__attribute__" and "((blah))" so that
kernel-doc does not complain like:Warning(/tester/linsrc/linux-2.6.20-git15//kernel/timer.c:939): No description found for parameter 'read_persistent_clock(void'
Signed-off-by: Randy Dunlap
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Signed-off-by: Daniel Walker
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add some missing lazy MMU hooks for NOMMU mode.
Signed-off-by: David Howells
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
FRV does not require a ZONE_DMA, so all DMA'able pages that aren't highmem
should be in ZONE_NORMAL.Signed-off-by: David Howells
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
i.e. one or more drives can be added and the array will re-stripe
while on-line.Most of the interesting work was already done for raid5. This just extends it
to raid6.mdadm newer than 2.6 is needed for complete safety, however any version of
mdadm which support raid5 reshape will do a good enough job in almost all
cases (an 'echo repair > /sys/block/mdX/md/sync_action' is recommended after a
reshape that was aborted and had to be restarted with an such a version of
mdadm).Signed-off-by: Neil Brown
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
An error always aborts any resync/recovery/reshape on the understanding that
it will immediately be restarted if that still makes sense. However a reshape
currently doesn't get restarted. With this patch it does.To avoid restarting when it is not possible to do work, we call into the
personality to check that a reshape is ok, and strengthen raid5_check_reshape
to fail if there are too many failed devices.We also break some code out into a separate function: remove_and_add_spares as
the indent level for that code was getting crazy.Signed-off-by: Neil Brown
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The mddev and queue might be used for another array which does not set these,
so they need to be cleared.Signed-off-by: NeilBrown
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
md tries to warn the user if they e.g. create a raid1 using two partitions of
the same device, as this does not provide true redundancy.However it also warns if a raid0 is created like this, and there is nothing
wrong with that.At the place where the warning is currently printer, we don't necessarily know
what level the array will be, so move the warning from the point where the
device is added to the point where the array is started.Signed-off-by: Neil Brown
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
- Use kernel_fpu_begin() and kernel_fpu_end()
- Use boot_cpu_has() for feature testing even in userspaceSigned-off-by: H. Peter Anvin
Signed-off-by: Neil Brown
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
There are two errors that can lead to recovery problems with raid10
when used in 'far' more (not the default).Due to a '>' instead of '>=' the wrong block is located which would result in
garbage being written to some random location, quite possible outside the
range of the device, causing the newly reconstructed device to fail.The device size calculation had some rounding errors (it didn't round when it
should) and so recovery would go a few blocks too far which would again cause
a write to a random block address and probably a device error.The code for working with device sizes was fairly confused and spread out, so
this has been tided up a bit.Signed-off-by: Neil Brown
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
If register_blkdev() or alloc-disk fail in mm_init() after
pci_register_driver() succeeds, then mm_pci_driver is not unregistered
properly:Cc: Philip Guo
Signed-off-by: Neil Brown
Cc: Jens Axboe
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Signed-off-by: Adrian Bunk
Cc: Ben Dooks
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
shmem_{nopage,mmap} are no longer used in ipc/shm.c
Signed-off-by: Adrian Bunk
Cc: "Eric W. Biederman"
Cc: Hugh Dickins
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
shm_nopage() can become static.
Signed-off-by: Adrian Bunk
Acked-by: Eric W. Biederman
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
