x86 PAT: fix performance drop for glx, use UC minus for ioremap(), ioremap_nocache() and pci_mmap_page_range()
Use UC_MINUS for ioremap(), ioremap_nocache() instead of strong UC.
Once all the X drivers move to ioremap_wc(), we can go back to strong
UC semantics for ioremap() and ioremap_nocache().
To avoid attribute aliasing issues, pci_mmap_page_range() will also
use UC_MINUS for default non write-combining mapping request.
Next steps:
a) change all the video drivers using ioremap() or ioremap_nocache()
and adding WC MTTR using mttr_add() to ioremap_wc()
b) for strict usage, we can go back to strong uc semantics
for ioremap() and ioremap_nocache() after some grace period for
completing step-a.
c) user level X server needs to use the appropriate method for setting
up WC mapping (like using resourceX_wc sysfs file instead of
adding MTRR for WC and using /dev/mem or resourceX under /sys)
Sam Ravnborg [Tue, 29 Apr 2008 10:48:15 +0000 (12:48 +0200)]
x86: use defconfigs from x86/configs/*
Daniel Drake <dsd@gentoo.org> reported:
In 2.6.23, if you unpacked a kernel source tarball and then
ran "make menuconfig" you'd be presented with this message:
# using defaults found in arch/i386/defconfig
and the default options would be set.
The same thing in 2.6.24 does not give you any "using defaults" message, and
the default config options within menuconfig are rather blank (e.g. no PCI
support). You can work around this by explicitly running "make defconfig"
before menuconfig, but it would be nice to have the behaviour the way it was
for 2.6.23 (and the way it still is for other archs).
Fixed by adding a x86 specific defconfig list to Kconfig.
Fixes: http://bugzilla.kernel.org/show_bug.cgi?id=10470 Tested-by: dsd@gentoo.org Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Alan Cox [Tue, 29 Apr 2008 13:20:23 +0000 (14:20 +0100)]
toshiba: use ioremap_cached
The switch of ioremap to default to uncached doesn't break this driver
but it does needlessly slow it down as BIOS space is cachable and this
driver is quite happy scanning cached ROM space.
Signed-off-by: Alan Cox <alan@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
revert: "x86: ioremap(), extend check to all RAM pages"
Vegard Nossum reported a large (150 seconds) boot delay during bootup,
and bisected it to "x86: ioremap(), extend check to all RAM pages"
(commit bdd3cee2e4b). Revert this commit for now.
The kernel prints the compat vdso address regardless of whether compat
vdso mode is enabled or not, which is confusing. Given that this
isn't very interesting information anyway, just remove the printk.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Gerhard Mack <gmack@innerfire.net> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The .asciz directive takes any number of strings, but each one is zero-
terminated, and string pasting is not done as in C. That results in only the
first line being output.
Replace .asciz with multiple .ascii directives and terminate with .asciz.
Dmitri Vorobiev [Sun, 27 Apr 2008 23:15:58 +0000 (03:15 +0400)]
x86: iommu_sac_force can become static
The iommu_sac_force variable is needlessly defined global,
and this patch makes it static. Additionally, this variable
needs not be explicitly initialized.
Signed-off-by: Dmitri Vorobiev <dmitri.vorobiev@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
James Bottomley reported that the following commit:
| commit 6371b495991debfd1417b17c2bc4f7d7bae05739
| Author: Ingo Molnar <mingo@elte.hu>
| Date: Wed Jan 30 13:33:40 2008 +0100
|
| x86: change ioremap() to default to uncached
broke Voyager.
James says:
" it broke a class of voyager machines: those which
rely on the quad interrupt controller (QIC). The precis of why they
broke is because the QIC does IPIs (or CPIs in its terminology) via
cache line interference: you interrupt a processor by moving a
designated memory area to write exclusive in the cache (by simply
writing to the line) and the CPU acks the interrupt by moving it back to
read shared (by reading from it). That area, is, of course, mapped by
ioremap, so reversing the ioremap semantics and adding the uncached bit
completely breaks the QIC. "
Sorry about that!
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6
* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6: (179 commits)
ACPI: Fix acpi_processor_idle and idle= boot parameters interaction
acpi: fix section mismatch warning in pnpacpi
intel_menlo: fix build warning
ACPI: Cleanup: Remove unneeded, multiple local dummy variables
ACPI: video - fix permissions on some proc entries
ACPI: video - properly handle errors when registering proc elements
ACPI: video - do not store invalid entries in attached_array list
ACPI: re-name acpi_pm_ops to acpi_suspend_ops
ACER_WMI/ASUS_LAPTOP: fix build bug
thinkpad_acpi: fix possible NULL pointer dereference if kstrdup failed
ACPI: check a return value correctly in acpi_power_get_context()
#if 0 acpi/bay.c:eject_removable_drive()
eeepc-laptop: add hwmon fan control
eeepc-laptop: add backlight
eeepc-laptop: add base driver
ACPI: thinkpad-acpi: bump up version to 0.20
ACPI: thinkpad-acpi: fix selects in Kconfig
ACPI: thinkpad-acpi: use a private workqueue
ACPI: thinkpad-acpi: fluff really minor fix
ACPI: thinkpad-acpi: use uppercase for "LED" on user documentation
...
Fixed conflicts in drivers/acpi/video.c and drivers/misc/intel_menlow.c
manually.
ACPI: Fix acpi_processor_idle and idle= boot parameters interaction
acpi_processor_idle and "idle=" boot parameter interaction is broken.
The problem is that, at boot time acpi driver is checking for "idle=" boot
option and not registering the acpi idle handler. But, when there is a CST
changed callback (typically when switching AC <-> battery or suspend-resume)
there are no checks for boot_option_idle_override and acpi idle handler tries
to get installed with nasty side effects.
With CPU_IDLE configured this issue causes results in a nasty oops on CST
change callback and without CPU_IDLE there is no oops, but boot option
of "idle=" gets ignored and acpi idle handler gets installed.
Change the behavior to not do anything in acpi idle handler when there is a
"idle=" boot option.
Note that the problem is only there when "idle=" boot option is used.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
Sam Ravnborg [Tue, 29 Apr 2008 20:52:01 +0000 (22:52 +0200)]
acpi: fix section mismatch warning in pnpacpi
Fix following section mismatch warning:
WARNING: vmlinux.o(.text+0x153d69): Section mismatch in reference from the function is_exclusive_device() to the variable .init.data:excluded_id_list
is_exclusive_device is only used from __init context so document
this with the __init annotation and get rid of the warning.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Len Brown <len.brown@intel.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (53 commits)
tcp: Overflow bug in Vegas
[IPv4] UFO: prevent generation of chained skb destined to UFO device
iwlwifi: move the selects to the tristate drivers
ipv4: annotate a few functions __init in ipconfig.c
atm: ambassador: vcc_sf semaphore to mutex
MAINTAINERS: The socketcan-core list is subscribers-only.
netfilter: nf_conntrack: padding breaks conntrack hash on ARM
ipv4: Update MTU to all related cache entries in ip_rt_frag_needed()
sch_sfq: use del_timer_sync() in sfq_destroy()
net: Add compat support for getsockopt (MCAST_MSFILTER)
net: Several cleanups for the setsockopt compat support.
ipvs: fix oops in backup for fwmark conn templates
bridge: kernel panic when unloading bridge module
bridge: fix error handling in br_add_if()
netfilter: {nfnetlink,ip,ip6}_queue: fix skb_over_panic when enlarging packets
netfilter: x_tables: fix net namespace leak when reading /proc/net/xxx_tables_names
netfilter: xt_TCPOPTSTRIP: signed tcphoff for ipv6_skip_exthdr() retval
tcp: Limit cwnd growth when deferring for GSO
tcp: Allow send-limited cwnd to grow up to max_burst when gso disabled
[netdrvr] gianfar: Determine TBIPA value dynamically
...
I realize some of the maintainers email clients and/or scripts cannot
handle UTF-8 encoded names properly, as a result your ChangeLogs
displays me as two different person :).
Following patch adds correctly encoded name of mine into .mailmap, to
prevent appearing it not to be so or badly displayed.
x86.git randconfig testing found a build failure on latest -git:
drivers/built-in.o: In function `set_type':
tuner-core.c:(.text+0x2a9a26): undefined reference to `tea5761_attach'
tuner-core.c:(.text+0x2a9d05): undefined reference to `tda9887_attach'
tuner-core.c:(.text+0x2a9d51): undefined reference to `xc2028_attach'
tuner-core.c:(.text+0x2a9e22): undefined reference to `tda829x_attach'
tuner-core.c:(.text+0x2a9e3f): undefined reference to `microtune_attach'
drivers/built-in.o: In function `tuner_probe':
tuner-core.c:(.text+0x2aa18a): undefined reference to `tda829x_probe'
tuner-core.c:(.text+0x2aa302): undefined reference to `tea5761_autodetection'
the problem is caused by the drivers/media/common/tuners/ subdirectory
not being part of the kbuild hierarchy anymore, due to commit 7c91f0624 ("V4L/DVB(7767): Move tuners to common/tuners").
this seems similar to the problem also reported by Mike Galbraith.
memory hotplug: allocate usemap on the section with pgdat
Usemaps are allocated on the section which has pgdat by this.
Because usemap size is very small, many other sections usemaps are allocated
on only one page. If a section has usemap, it can't be removed until removing
other sections. This dependency is not desirable for memory removing.
Pgdat has similar feature. When a section has pgdat area, it must be the last
section for removing on the node. So, if section A has pgdat and section B
has usemap for section A, Both sections can't be removed due to dependency
each other.
To solve this issue, this patch collects usemap on same section with pgdat.
If other sections doesn't have any dependency, this section will be able to be
removed finally.
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
broke davem's sparc64 bootup. Revert it while we work out what went wrong.
Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
What was happening is that migrate_page_copy wants to transfer the PG_dirty
bit from old page to new page, so what it would do is set_page_dirty(newpage).
However set_page_dirty() is used to set the entire page dirty, wheras in
this case, only part of the page was dirty, and it also was not uptodate.
Marking the whole page dirty with set_page_dirty would lead to corruption or
unresolvable conditions -- a dirty && !uptodate page and dirty && !uptodate
buffers.
Possibly we could just ClearPageDirty(oldpage); SetPageDirty(newpage);
however in the interests of keeping the change minimal...
Signed-off-by: Nick Piggin <npiggin@suse.de> Tested-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Robert P. J. Day [Wed, 30 Apr 2008 07:55:14 +0000 (00:55 -0700)]
Drop the exporting of empty <linux/byteorder/generic.h>
Fix up the contents of <linux/byteorder/> so that it doesn't export a
content-free generic.h to user space. This involves:
* Removing the __KERNEL__ tests from generic.h and dropping it from
Kbuild.
* Wrapping the inclusions of generic.h in both big_endian.h and
little_endian.h in __KERNEL__ tests.
* Shifting big_endian.h and little_endian.h from header-y to
unifdef-y in Kbuild.
Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Robert P. J. Day [Wed, 30 Apr 2008 07:55:13 +0000 (00:55 -0700)]
remove __KERNEL__ tests of unexported headers under asm-generic/
Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Robert P. J. Day [Wed, 30 Apr 2008 07:55:12 +0000 (00:55 -0700)]
Remove "#ifdef __KERNEL__" checks from unexported headers
Remove the "#ifdef __KERNEL__" tests from unexported header files in
linux/include whose entire contents are wrapped in that preprocessor
test.
Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
brd: modify ramdisk device to be able to manage partitions
This patch adds partition management for Block RAM Device (BRD).
This patch is done to keep in sync BRD and loop device drivers.
This patch adds a parameter to the module, max_part, to specify
the maximum number of partitions per RAM device.
Example:
# modprobe brd max_part=63
# ls -l /dev/ram*
brw-rw---- 1 root disk 1, 0 2008-04-03 13:39 /dev/ram0
brw-rw---- 1 root disk 1, 64 2008-04-03 13:39 /dev/ram1
brw-rw---- 1 root disk 1, 640 2008-04-03 13:39 /dev/ram10
brw-rw---- 1 root disk 1, 704 2008-04-03 13:39 /dev/ram11
brw-rw---- 1 root disk 1, 768 2008-04-03 13:39 /dev/ram12
brw-rw---- 1 root disk 1, 832 2008-04-03 13:39 /dev/ram13
brw-rw---- 1 root disk 1, 896 2008-04-03 13:39 /dev/ram14
brw-rw---- 1 root disk 1, 960 2008-04-03 13:39 /dev/ram15
brw-rw---- 1 root disk 1, 128 2008-04-03 13:39 /dev/ram2
brw-rw---- 1 root disk 1, 192 2008-04-03 13:39 /dev/ram3
brw-rw---- 1 root disk 1, 256 2008-04-03 13:39 /dev/ram4
brw-rw---- 1 root disk 1, 320 2008-04-03 13:39 /dev/ram5
brw-rw---- 1 root disk 1, 384 2008-04-03 13:39 /dev/ram6
brw-rw---- 1 root disk 1, 448 2008-04-03 13:39 /dev/ram7
brw-rw---- 1 root disk 1, 512 2008-04-03 13:39 /dev/ram8
brw-rw---- 1 root disk 1, 576 2008-04-03 13:39 /dev/ram9
# fdisk /dev/ram0
Device contains neither a valid DOS partition table, nor Sun, SGI or OSF disklabel
Building a new DOS disklabel. Changes will remain in memory only,
until you decide to write them. After that, of course, the previous
content won't be recoverable.
Warning: invalid flag 0x0000 of partition table 4 will be corrected by w(rite)
Command (m for help): o
Building a new DOS disklabel. Changes will remain in memory only,
until you decide to write them. After that, of course, the previous
content won't be recoverable.
Warning: invalid flag 0x0000 of partition table 4 will be corrected by w(rite)
Command (m for help): n
Command action
e extended
p primary partition (1-4)
p
Partition number (1-4): 1
First cylinder (1-2, default 1): 1
Last cylinder or +size or +sizeM or +sizeK (1-2, default 2): 2
Command (m for help): w
The partition table has been altered!
Calling ioctl() to re-read partition table.
Syncing disks.
# ls -l /dev/ram0*
brw-rw---- 1 root disk 1, 0 2008-04-03 13:40 /dev/ram0
brw-rw---- 1 root disk 1, 1 2008-04-03 13:40 /dev/ram0p1
# mkfs /dev/ram0p1
mke2fs 1.40-WIP (14-Nov-2006)
Filesystem label=
OS type: Linux
Block size=1024 (log=0)
Fragment size=1024 (log=0)
4016 inodes, 16032 blocks
801 blocks (5.00%) reserved for the super user
First data block=1
Maximum filesystem blocks=16515072
2 block groups
8192 blocks per group, 8192 fragments per group
2008 inodes per group
Superblock backups stored on blocks:
8193
This filesystem will be automatically checked every 26 mounts or
180 days, whichever comes first. Use tune2fs -c or -i to override.
# mount /dev/ram0p1 /mnt
df /mnt
Filesystem 1K-blocks Used Available Use% Mounted on
/dev/ram0p1 15521 138 14582 1% /mnt
# ls -l /mnt
total 12
drwx------ 2 root root 12288 2008-04-03 13:41 lost+found
# umount /mnt
# rmmod brd
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net> Acked-by: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Thomas Gleixner [Wed, 30 Apr 2008 07:55:04 +0000 (00:55 -0700)]
add hrtimer specific debugobjects code
hrtimers have now dynamic users in the network code. Put them under
debugobjects surveillance as well.
Add calls to the generic object debugging infrastructure and provide fixup
functions which allow to keep the system alive when recoverable problems have
been detected by the object debugging core code.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Greg KH <greg@kroah.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Thomas Gleixner [Wed, 30 Apr 2008 07:55:03 +0000 (00:55 -0700)]
debugobjects: add timer specific object debugging code
Add calls to the generic object debugging infrastructure and provide fixup
functions which allow to keep the system alive when recoverable problems have
been detected by the object debugging core code.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Greg KH <greg@kroah.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Thomas Gleixner [Wed, 30 Apr 2008 07:55:01 +0000 (00:55 -0700)]
infrastructure to debug (dynamic) objects
We can see an ever repeating problem pattern with objects of any kind in the
kernel:
1) freeing of active objects
2) reinitialization of active objects
Both problems can be hard to debug because the crash happens at a point where
we have no chance to decode the root cause anymore. One problem spot are
kernel timers, where the detection of the problem often happens in interrupt
context and usually causes the machine to panic.
While working on a timer related bug report I had to hack specialized code
into the timer subsystem to get a reasonable hint for the root cause. This
debug hack was fine for temporary use, but far from a mergeable solution due
to the intrusiveness into the timer code.
The code further lacked the ability to detect and report the root cause
instantly and keep the system operational.
Keeping the system operational is important to get hold of the debug
information without special debugging aids like serial consoles and special
knowledge of the bug reporter.
The problems described above are not restricted to timers, but timers tend to
expose it usually in a full system crash. Other objects are less explosive,
but the symptoms caused by such mistakes can be even harder to debug.
Instead of creating specialized debugging code for the timer subsystem a
generic infrastructure is created which allows developers to verify their code
and provides an easy to enable debug facility for users in case of trouble.
The debugobjects core code keeps track of operations on static and dynamic
objects by inserting them into a hashed list and sanity checking them on
object operations and provides additional checks whenever kernel memory is
freed.
The tracked object operations are:
- initializing an object
- adding an object to a subsystem list
- deleting an object from a subsystem list
Each operation is sanity checked before the operation is executed and the
subsystem specific code can provide a fixup function which allows to prevent
the damage of the operation. When the sanity check triggers a warning message
and a stack trace is printed.
The list of operations can be extended if the need arises. For now it's
limited to the requirements of the first user (timers).
The core code enqueues the objects into hash buckets. The hash index is
generated from the address of the object to simplify the lookup for the check
on kfree/vfree. Each bucket has it's own spinlock to avoid contention on a
global lock.
The debug code can be compiled in without being active. The runtime overhead
is minimal and could be optimized by asm alternatives. A kernel command line
option enables the debugging code.
Thanks to Ingo Molnar for review, suggestions and cleanup patches.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@elte.hu> Cc: Greg KH <greg@kroah.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Thomas Gleixner [Wed, 30 Apr 2008 07:54:59 +0000 (00:54 -0700)]
slab: add a flag to prevent debug_free checks on a kmem_cache
This is a preperatory patch for the debugobjects infrastructure. The flag
prevents debug_free checks on kmem_caches. This is necessary to avoid
resursive calls into a debug mechanism which uses a kmem_cache itself.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Andrew Morton [Wed, 30 Apr 2008 07:54:54 +0000 (00:54 -0700)]
alloc_uid: cleanup
Use kmem_cache_zalloc(), remove large amounts of initialisation code and
ifdeffery.
Note: this assumes that memset(*atomic_t, 0) correctly initialises the
atomic_t. This is true for all present archtiectures and if it becomes false
for a future architecture then we'll need to make large changes all over the
place anyway.
Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Samuel Thibault [Wed, 30 Apr 2008 07:54:51 +0000 (00:54 -0700)]
Basic braille screen reader support
This adds a minimalistic braille screen reader support. This is meant to
be used by blind people e.g. on boot failures or when / cannot be mounted
etc and thus the userland screen readers can not work.
[akpm@linux-foundation.org: fix exports] Signed-off-by: Samuel Thibault <samuel.thibault@ens-lyon.org> Cc: Jiri Kosina <jikos@jikos.cz> Cc: Dmitry Torokhov <dtor@mail.ru> Acked-by: Alan Cox <alan@redhat.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use the proper helper to open a blockdevice by name for filesystem use,
this makes sure it's properly claimed (also added for open-by-number) and
gets rid of the struct file abuse.
Tested by mounting a reiserfs filesystem with external journal.
Signed-off-by: Christoph Hellwig <hch@lst.de> Cc: Chris Mason <chris.mason@oracle.com> Cc: Jeff Mahoney <jeffm@suse.com> Acked-by: Edward Shishkin <edward.shishkin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Nick Piggin [Wed, 30 Apr 2008 07:54:42 +0000 (00:54 -0700)]
fuse: implement perform_write
Introduce fuse_perform_write. With fusexmp (a passthrough filesystem), large
(1MB) writes into a backing tmpfs filesystem are sped up by almost 4 times
(256MB/s vs 71MB/s).
[mszeredi@suse.cz]:
- split into smaller functions
- testing
- duplicate generic_file_aio_write(), so that there's no need to add a
new ->perform_write() a_op. Comment from hch.
Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Quoting Linus (3 years ago, FUSE inclusion discussions):
"User-space filesystems are hard to get right. I'd claim that they
are almost impossible, unless you limit them somehow (shared
writable mappings are the nastiest part - if you don't have those,
you can reasonably limit your problems by limiting the number of
dirty pages you accept through normal "write()" calls)."
Instead of attempting the impossible, I've just waited for the dirty page
accounting infrastructure to materialize (thanks to Peter Zijlstra and
others). This nicely solved the biggest problem: limiting the number of pages
used for write caching.
Some small details remained, however, which this largish patch attempts to
address. It provides a page writeback implementation for fuse, which is
completely safe against VM related deadlocks. Performance may not be very
good for certain usage patterns, but generally it should be acceptable.
It has been tested extensively with fsx-linux and bash-shared-mapping.
fuse_writepage() allocates a new temporary page with GFP_NOFS|__GFP_HIGHMEM.
It copies the contents of the original page, and queues a WRITE request to the
userspace filesystem using this temp page.
The writeback is finished instantly from the MM's point of view: the page is
removed from the radix trees, and the PageDirty and PageWriteback flags are
cleared.
For the duration of the actual write, the NR_WRITEBACK_TEMP counter is
incremented. The per-bdi writeback count is not decremented until the actual
write completes.
On dirtying the page, fuse waits for a previous write to finish before
proceeding. This makes sure, there can only be one temporary page used at a
time for one cached page.
This approach is wasteful in both memory and CPU bandwidth, so why is this
complication needed?
The basic problem is that there can be no guarantee about the time in which
the userspace filesystem will complete a write. It may be buggy or even
malicious, and fail to complete WRITE requests. We don't want unrelated parts
of the system to grind to a halt in such cases.
Also a filesystem may need additional resources (particularly memory) to
complete a WRITE request. There's a great danger of a deadlock if that
allocation may wait for the writepage to finish.
Currently there are several cases where the kernel can block on page
writeback:
- allocation order is larger than PAGE_ALLOC_COSTLY_ORDER
- page migration
- throttle_vm_writeout (through NR_WRITEBACK)
- sync(2)
Of course in some cases (fsync, msync) we explicitly want to allow blocking.
So for these cases new code has to be added to fuse, since the VM is not
tracking writeback pages for us any more.
As an extra safetly measure, the maximum dirty ratio allocated to a single
fuse filesystem is set to 1% by default. This way one (or several) buggy or
malicious fuse filesystems cannot slow down the rest of the system by hogging
dirty memory.
With appropriate privileges, this limit can be raised through
'/sys/class/bdi/<bdi>/max_ratio'.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fuse will use temporary buffers to write back dirty data from memory mappings
(normal writes are done synchronously). This is needed, because there cannot
be any guarantee about the time in which a write will complete.
By using temporary buffers, from the MM's point if view the page is written
back immediately. If the writeout was due to memory pressure, this
effectively migrates data from a full zone to a less full zone.
This patch adds a new counter (NR_WRITEBACK_TEMP) for the number of pages used
as temporary buffers.
[Lee.Schermerhorn@hp.com: add vmstat_text for NR_WRITEBACK_TEMP] Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm: bdi: add separate writeback accounting capability
Add a new BDI capability flag: BDI_CAP_NO_ACCT_WB. If this flag is
set, then don't update the per-bdi writeback stats from
test_set_page_writeback() and test_clear_page_writeback().
Misc cleanups:
- convert bdi_cap_writeback_dirty() and friends to static inline functions
- create a flag that includes all three dirty/writeback related flags,
since almst all users will want to have them toghether
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Peter Zijlstra [Wed, 30 Apr 2008 07:54:35 +0000 (00:54 -0700)]
mm: bdi: allow setting a minimum for the bdi dirty limit
Under normal circumstances each device is given a part of the total write-back
cache that relates to its current avg writeout speed in relation to the other
devices.
min_ratio - allows one to assign a minimum portion of the write-back cache to
a particular device. This is useful in situations where you might want to
provide a minimum QoS. (One request for this feature came from flash based
storage people who wanted to avoid writing out at all costs - they of course
needed some pdflush hacks as well)
max_ratio - allows one to assign a maximum portion of the dirty limit to a
particular device. This is useful in situations where you want to avoid one
device taking all or most of the write-back cache. Eg. an NFS mount that is
prone to get stuck, or a FUSE mount which you don't trust to play fair.
Add "min_ratio" to /sys/class/bdi. This indicates the minimum percentage of
the global dirty threshold allocated to this bdi.
[mszeredi@suse.cz]
- fix parsing in min_ratio_store()
- document new sysfs attribute
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Register FUSE's backing_dev_info under sysfs with the name "fuse-MAJOR:MINOR"
Make the fuse control filesystem use s_dev instead of a fuse specific ID.
This makes it easier to match directories under /sys/fs/fuse/connections/ with
directories under /sys/class/bdi, and with actual mounts.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Peter Zijlstra [Wed, 30 Apr 2008 07:54:32 +0000 (00:54 -0700)]
mm: bdi: export BDI attributes in sysfs
Provide a place in sysfs (/sys/class/bdi) for the backing_dev_info object.
This allows us to see and set the various BDI specific variables.
In particular this properly exposes the read-ahead window for all relevant
users and /sys/block/<block>/queue/read_ahead_kb should be deprecated.
With patient help from Kay Sievers and Greg KH
[mszeredi@suse.cz]
- split off NFS and FUSE changes into separate patches
- document new sysfs attributes under Documentation/ABI
- do bdi_class_init as a core_initcall, otherwise the "default" BDI
won't be initialized
- remove bdi_init_fmt macro, it's not used very much
Pavel Emelyanov [Wed, 30 Apr 2008 07:54:31 +0000 (00:54 -0700)]
pidns: make pid->level and pid_ns->level unsigned
These values represent the nesting level of a namespace and pids living in it,
and it's always non-negative.
Turning this from int to unsigned int saves some space in pid.c (11 bytes on
x86 and 64 on ia64) by letting the compiler optimize the pid_nr_ns a bit.
E.g. on ia64 this removes the sign extension calls, which compiler adds to
optimize access to pid->nubers[ns->level].
Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1. sys_getpgid() needs rcu_read_lock() to derive the pgrp _nr, even if
the task is current, otherwise we can race with another thread which
does sys_setpgid().
2. Use rcu_read_lock() instead of tasklist_lock when pid != 0, make sure
that we don't use the NULL pid if the task exits right after successful
find_task_by_vpid().
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
pids: sys_getsid: fix unsafe *pid usage, fix possible 0 instead of -ESRCH
1. sys_getsid() needs rcu_read_lock() to derive the session _nr, even if
the task is current, otherwise we can race with another thread which
does sys_setsid().
2. The task can exit between find_task_by_vpid() and task_session_vnr(),
in that unlikely case sys_getsid() returns 0 instead of -ESRCH.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Without tasklist_lock held task_session()/task_pgrp() can return NULL if the
caller races with setprgp()/setsid() which does detach_pid() + attach_pid().
This can happen even if task == current.
Intoduce the new helper, change_pid(), which should be used instead. This way
the caller always sees the special pid != NULL, either old or new.
Also change the prototype of attach_pid(), it always returns 0 and nobody
check the returned value.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
pids: de_thread: don't clear session/pgrp pids for the old leader
Based on Eric W. Biederman's idea.
Unless task == current, without tasklist_lock held task_session()/task_pgrp()
can return NULL if the caller races with de_thread() which switches the group
leader.
Change transfer_pid() to not clear old->pids[type].pid for the old leader.
This means that its .pid can point to "nowhere", but this is already true for
sub-threads, and the old leader is not group_leader() any longer. IOW, with
or without this change we can't trust task's special pids unless it is the
group leader.
Pavel Emelyanov [Wed, 30 Apr 2008 07:54:23 +0000 (00:54 -0700)]
Use find_task_by_vpid in taskstats
The pid to lookup a task by is passed inside taskstats code via genetlink
message.
Since netlink packets are now processed in the context of the sending task,
this is correct to lookup the task with find_task_by_vpid() here.
Besides, I fix the call to fill_pid() from taskstats_exit(), since the
tsk->pid is not required in fill_pid() in this case, and the pid field on
task_struct is going to be deprecated as well.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Jay Lan <jlan@engr.sgi.com> Cc: Jonathan Lim <jlim@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Factor out the code used to allocate/free a pts index into new interfaces,
devpts_new_index() and devpts_kill_index(). This localizes the external data
structures used in managing the pts indices.
[akpm@linux-foundation.org: undo accidental mutex2sem conversion] Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Signed-off-by: Serge Hallyn <serue@us.ibm.com> Signed-off-by: Matt Helsley <matthltc@us.ibm.com> Acked-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
projects / linux-2.6 / log