Kevin VanMaren [Fri, 3 Feb 2006 20:51:32 +0000 (21:51 +0100)]
[PATCH] x86_64: When allocation of merged SG lists fails in the IOMMU don't merge
[ AK: I redid Kevin's fix to be simpler, but the idea and original
analysis of the problem is from Kevin]
This avoid allocation failures on some SATA systems like Nvidia CK8
when the IOMMU gets fragmented. Modern SATA devices have quite large queues
(128 entries) and the FS with ext2/3 is good enough now that it often
passes whole 128 page sg lists down to the driver. These require
512K of continuous free space in the IOMMU aperture to map when merged.
When the IOMMU is fragmented this could lead to spurious IO errors
due to failing mappings.
Short term fix is to just try to map the SG list again unmerged
page by page - this way fragmentation doesn't matter anymore.
The code for that was already there, but it just wasn't enabled for the
merge case.
According to Kevin at least the Nvidia device doesn't seem to benefit
from merging much anyways, so the only slowdown is from trying
to do an unnecessary merge attempt.
Kevin plans to implement better fragmentation avoidance in the future,
but that wouldn't be 2.6.16 material.
TBD: should add some statistic counters to count how often that really
happens.
Andi Kleen [Fri, 3 Feb 2006 20:51:29 +0000 (21:51 +0100)]
[PATCH] x86_64: Fix zero mcfg entry workaround on x86-64
I broke this earlier when moving the patch from i386 to x86-64.
Need to return the virtual address here, not the physical address.
This fixes some boot time crashes on x86-64.
Andi Kleen [Fri, 3 Feb 2006 20:51:26 +0000 (21:51 +0100)]
[PATCH] x86_64: Do more checking in the SRAT header code
- Check if the processor/memory affinity entries are long enough
according to the ACPI 3.0 spec.
- Ignore memory affinity entries that define a zero length region.
Ashok Raj [Fri, 3 Feb 2006 20:51:23 +0000 (21:51 +0100)]
[PATCH] x86_64: data/functions wrongly marked as __init with cpu hotplug.
attached patch is 2 more cases i found via running the reference_init.pl
script. These were easy to spot just knowing the file names. There is
one another about init/main.c that i cant exactly zero in. (partly
because i dont know how to interpret the data thats spewed out of the tool).
Chen, Kenneth W [Fri, 3 Feb 2006 20:51:14 +0000 (21:51 +0100)]
[PATCH] x86_64: Fix memory policy build without CONFIG_HUGETLBFS
> mm/mempolicy.c: In function `huge_zonelist':
> mm/mempolicy.c:1045: error: `HPAGE_SHIFT' undeclared (first use in this function)
> mm/mempolicy.c:1045: error: (Each undeclared identifier is reported only once
> mm/mempolicy.c:1045: error: for each function it appears in.)
> make[1]: *** [mm/mempolicy.o] Error 1
Need to wrap huge_zonelist function with CONFIG_HUGETLBFS.
[PATCH] x86_64: Fix the node cpumask of a cpu going down
Currently, x86_64 and ia64 arches do not clear the corresponding bits
in the node's cpumask when a cpu goes down or cpu bring up is cancelled.
This is buggy since there are pieces of common code where the cpumask is
checked in the cpu down code path to decide on things (like in the slab
down path). PPC does the right thing, but x86_64 and ia64 don't (This
was the reason Sonny hit upon a slab bug during cpu offline on ppc and
could not reproduce on other arches). This patch fixes it for x86_64.
I won't attempt ia64 as I cannot test it.
Andi Kleen [Fri, 3 Feb 2006 20:51:02 +0000 (21:51 +0100)]
[PATCH] x86_64: Undo the earlier changes to remove unrolled copy/memset functions
They cause quite bad performance regressions on Netburst
This is temporary until we can get new optimized functions
for these CPUs.
This undoes changes that were done in 2.6.15 and in 2.6.16-rc1,
essentially bringing the code back to 2.6.14 level. Only change
is I renamed the X86_FEATURE_K8_C flag to X86_FEATURE_REP_GOOD
and fixed the check for the flag and also fixed some comments.
Shaohua Li [Fri, 3 Feb 2006 20:50:56 +0000 (21:50 +0100)]
[PATCH] x86_64: [PATCH] timer resume
At resume time, TSC's value or something similar might be changed a lot
against suspend time. This could make system gets a very big lost ticks.
See http://bugzilla.kernel.org/show_bug.cgi?id=5825
Andi Kleen [Fri, 3 Feb 2006 20:50:50 +0000 (21:50 +0100)]
[PATCH] x86_64: Allow to run main time keeping from the local APIC interrupt
Another piece from the no-idle-tick patch.
This can be enabled with the "apicmaintimer" option.
This is mainly useful when the PIT/HPET interrupt is unreliable.
Note there are some systems that are known to stop the APIC
timer in C3. For those it will never work, but this case
should be automatically detected.
It also only works with PM timer right now. When HPET is used
the way the main timer handler computes the delay doesn't work.
It should be a bit more efficient because there is one less
regular interrupt to process on the boot processor.
Stephen Smalley [Fri, 3 Feb 2006 13:21:12 +0000 (08:21 -0500)]
[PATCH] SELinux: fix size-128 slab leak
Remove private inode tests from security_inode_alloc and security_inode_free,
as we otherwise end up leaking inode security structures for private inodes.
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Mark Fasheh [Wed, 18 Jan 2006 18:31:47 +0000 (10:31 -0800)]
[PATCH] ocfs2: don't wait on recovery when locking journal
The mount path had incorrectly asked the locking code to wait for recovery
completion, which deadlocks things because recovery waits for mount to
complete first.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
this changes if() BUG(); constructs to BUG_ON() which is
cleaner, contains unlikely() and can better optimized away.
Signed-off-by: Eric Sesterhenn <snakebyte@gmx.de> Signed-off-by: Joel Becker <joel.becker@oracle.com> Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Joel Becker [Wed, 25 Jan 2006 21:31:07 +0000 (13:31 -0800)]
configfs: Add permission and ownership to configfs objects.
configfs always made item and attribute ownership root.root and
permissions based on a umask of 022. Add ->setattr() to allow
chown(2)/chmod(2), and persist the changes for the lifetime of the
items and attributes.
Signed-off-by: Joel Becker <joel.becker@oracle.com> Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Arjan van de Ven [Sat, 14 Jan 2006 05:54:23 +0000 (21:54 -0800)]
[PATCH] ocfs2: Semaphore to mutex conversion.
Semaphore to mutex conversion.
The conversion was generated via scripts, and the result was validated
automatically via a script as well.
Signed-off-by: Arjan van de Ven <arjan@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Kurt Hackel [Thu, 12 Jan 2006 22:24:55 +0000 (14:24 -0800)]
[PATCH] ocfs2/dlm: fixes
* fix a hang which can occur during shutdown migration
* do not allow nodes to join during recovery
* when restarting lock mastery, do not ignore nodes which come up
* more than one node could become recovery master, fix this
* sleep to allow some time for heartbeat state to catch up to network
* extra debug info for bad recovery state problems
* make DLM_RECO_NODE_DATA_DONE a valid state for non-master recovery nodes
* prune all locks from dead nodes on $RECOVERY lock resources
* do NOT automatically add new nodes to mle nodemaps until they have properly
joined the domain
* make sure dlm_pick_recovery_master only exits when all nodes have synced
* properly handle dlmunlock errors in dlm_pick_recovery_master
* do not propagate network errors in dlm_send_begin_reco_message
* dead nodes were not being put in the recovery map sometimes, fix this
* dlmunlock was failing to clear the unlock actions on DLM_DENIED
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com> Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
I just purchased a HighPoint Rocket 1520 SATA controller. There seems to
be no libata driver (yet), but there is an ide driver, hpt366. When the
driver gets loaded, it causes a kernel NULL pointer dereference in
pci_bus_clock_list. It seems to be because the driver is waiting for clock
stabilization in init_hpt37x() which never comes. The driver just
continues on with the pci drvdata set to NULL, instead of a valid clock
entry. The following patch prevents the NULL dereference from happening,
but instead exit with an error.
Acked-by: Bartlomiej Zolnierkiewicz <B.Zolnierkiewicz@elka.pw.edu.pl> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Richard Purdie [Fri, 3 Feb 2006 11:04:55 +0000 (03:04 -0800)]
[PATCH] stop CompactFlash devices being marked as removable
This patch stops CompactFlash devices being marked as removable. They are
not removable (as defined by Linux) as the media and device are
inseparable. When a card is removed, the whole device is removed from the
system and never sits in a media-less state.
This stops some nasty udev device creation/destruction loops.
Further, once this change is made, there is no need for ide to can be
removed from ide_drive_t.
Signed-off-by: Richard Purdie <rpurdie@rpsys.net> Acked-by: Bartlomiej Zolnierkiewicz <B.Zolnierkiewicz@elka.pw.edu.pl> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Andreas Mohr [Fri, 3 Feb 2006 11:04:54 +0000 (03:04 -0800)]
[PATCH] ide Kconfig fixes
CONFIG_BLK_DEV_IDECS docu mentions everything and the kitchen sink, yet
fails to list the most important/widespread (IMHO) device: Compact Flash
PCMCIA adapters.
This incomplete description recently caused me to deselect the ide_cs
module, causing great pain soon thereafter when I realized why I had
actually enabled it some years ago.
Updates:
- make sure to mention Compact Flash adapters
- fix some random typos in ide Kconfig
Signed-off-by: Andreas Mohr <andi@lisas.de> Acked-by: Bartlomiej Zolnierkiewicz <B.Zolnierkiewicz@elka.pw.edu.pl> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Jayachandran C [Fri, 3 Feb 2006 11:04:51 +0000 (03:04 -0800)]
[PATCH] IPMI: fix issues reported by Coverity in ipmi_msghandler.c
While looking to the report by Coverity in ipmi, I came across the
following issue:
The IPMI message handler relies on two defines which are the same -one in
include/linux/ipmi.h
#define IPMI_NUM_CHANNELS 0x10
and one in drivers/char/ipmi/ipmi_msghandler.
#define IPMI_MAX_CHANNELS 16
These are used interchangeably in ipmi_msghandler.c, but since the array
addr->channels[] is of size IPMI_MAX_CHANNELS, I have made a patch that
uses IPMI_MAX_CHANNELS for all the checks for the array index.
NOTE: You could probably remove the line that defines IPMI_NUM_CHANNELS
from ipmi.h, or move IPMI_MAX_CHANNELS to ipmi.h
Signed-off-by: Jayachandran C. <c.jayachandran@gmail.com> Cc: Corey Minyard <minyard@acm.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Jayachandran C [Fri, 3 Feb 2006 11:04:50 +0000 (03:04 -0800)]
[PATCH] UDF: Fix issues reported by Coverity in namei.c
This patch fixes an issue in fs/udf/namei.c reported by Coverity:
Error reported(1776)
CID: 1776
Checker: UNUSED_VALUE (help)
File: fs/udf/namei.c
Function: udf_lookup
Description: Pointer returned from "udf_find_entry" is never used
Patch description:
remove unused variable fi.
Signed-off-by: Jayachandran C. <c.jayachandran@gmail.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Karsten Keil [Fri, 3 Feb 2006 11:04:48 +0000 (03:04 -0800)]
[PATCH] i4l: warning fixes
drivers/isdn/hisax/hscx_irq.c: In function `hscx_interrupt':
drivers/isdn/hisax/hscx_irq.c:201: warning: comparison is always 1 due to width of bit-field
It's due to
(PACKET_NOACK != bcs->tx_skb->pkt_type)
pkt_type is only three bit wide.
I think this should fix it for the moment, pkt_type 7 is not used yet and
this is only used internal in hisax.
Andrew Morton [Fri, 3 Feb 2006 11:04:47 +0000 (03:04 -0800)]
[PATCH] ip2main.c warning fixes
With Eric's "i386: Add a temporary to make put_user more type safe" patch we
get a pile of warnings out of ip2m1in.c:
drivers/char/ip2main.c: In function `ip2_ipl_ioctl':
drivers/char/ip2main.c:2910: warning: assignment makes integer from pointer without a cast
drivers/char/ip2main.c:2911: warning: assignment makes integer from pointer without a cast
drivers/char/ip2main.c:2912: warning: assignment makes integer from pointer without a cast
etc.
This ioctl is copying the kernel virtual address of a large number of
functions out to userspace. Heaven knows why.
Rather than fixing the warnings, I think we'll just nuke that code.
The patch also fixes a couple of `defined but not used' warnings.
Cc: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
By including version.h edac_mc was rebuilding on every incremental build.
Which defeats the point of incremental builds.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Paul Fulghum [Fri, 3 Feb 2006 11:04:41 +0000 (03:04 -0800)]
[PATCH] new tty buffering locking fix
Change locking in the new tty buffering facility from using tty->read_lock,
which is currently ignored by drivers and thus ineffective. New locking
uses a new tty buffering specific lock enforced centrally in the tty
buffering code.
Two drivers (esp and cyclades) are updated to use the tty buffering
functions instead of accessing tty buffering internals directly. This is
required for the new locking to work.
Minor checks for NULL buffers added to
tty_prepare_flip_string/tty_prepare_flip_string_flags
Signed-off-by: Paul Fulghum <paulkf@microgate.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Fix to broken comment to synchronize_rcu() noted by Keith Owens. Also add
sentence noting that synchronize_sched() and synchronize_rcu() are not
necessarily identical.
Signed-off-by: Paul E. McKenney <paulmck@us.ibm.com> Cc: Keith Owens <kaos@sgi.com> Cc: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Herbert Poetzl [Fri, 3 Feb 2006 11:04:37 +0000 (03:04 -0800)]
[PATCH] quota: fix error code for ext2_new_inode()
The quota check in ext2_new_inode() returns ENOSPC where it should return
EDQUOT instead.
Signed-off-by: Herbert Pötzl <herbert@13thfloor.at> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Zhang, Yanmin [Fri, 3 Feb 2006 11:04:36 +0000 (03:04 -0800)]
[PATCH] Export cpu topology in sysfs
The patch implements cpu topology exportation by sysfs.
Items (attributes) are similar to /proc/cpuinfo.
1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
represent the physical package id of cpu X;
2) /sys/devices/system/cpu/cpuX/topology/core_id:
represent the cpu core id to cpu X;
3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
represent the thread siblings to cpu X in the same core;
4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
represent the thread siblings to cpu X in the same physical package;
To implement it in an architecture-neutral way, a new source file,
driver/base/topology.c, is to export the 5 attributes.
If one architecture wants to support this feature, it just needs to
implement 4 defines, typically in file include/asm-XXX/topology.h.
The 4 defines are:
#define topology_physical_package_id(cpu)
#define topology_core_id(cpu)
#define topology_thread_siblings(cpu)
#define topology_core_siblings(cpu)
The type of **_id is int.
The type of siblings is cpumask_t.
To be consistent on all architectures, the 4 attributes should have
deafult values if their values are unavailable. Below is the rule.
1) physical_package_id: If cpu has no physical package id, -1 is the
default value.
2) core_id: If cpu doesn't support multi-core, its core id is 0.
3) thread_siblings: Just include itself, if the cpu doesn't support
HT/multi-thread.
4) core_siblings: Just include itself, if the cpu doesn't support
multi-core and HT/Multi-thread.
So be careful when declaring the 4 defines in include/asm-XXX/topology.h.
If an attribute isn't defined on an architecture, it won't be exported.
Peter Williams [Fri, 3 Feb 2006 11:04:33 +0000 (03:04 -0800)]
[PATCH] lib: Fix bug in int_sqrt() for 64 bit longs
The implementation of int_sqrt() assumes that longs have 32 bits. On
systems that have 64 bit longs this will result in gross errors when the
argument to the function is greater than 2^32 - 1 on such systems. I doubt
whether any such use is currently made of int_sqrt() but the attached patch
fixes the problem anyway.
Signed-off-by: Peter Williams <pwil3058@bigpond.com.au> Cc: Dave Jones <davej@codemonkey.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Herbert Poetzl [Fri, 3 Feb 2006 11:04:32 +0000 (03:04 -0800)]
[PATCH] quota: remove unused sync_dquots_dev()
The already removed sync_dquots_dev(dev,type) is still defined in the
no-quota case.
Signed-off-by: Herbert Pötzl <herbert@13thfloor.at> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
dean gaudet [Fri, 3 Feb 2006 11:04:30 +0000 (03:04 -0800)]
[PATCH] fcntl F_SETFL and read-only IS_APPEND files
There is code in setfl() which attempts to preserve the O_APPEND flag on
IS_APPEND files... however IS_APPEND files could also be opened O_RDONLY
and in that case setfl() should not require O_APPEND...
coreutils 5.93 tail -f attempts to set O_NONBLOCK even on regular files...
unfortunately if you try this on an append-only log file the result is
this:
I offer up the patch below as one way of fixing the problem... i've tested
it fixes the problem with tail -f but haven't really tested beyond that.
(I also reported the coreutils bug upstream... it shouldn't fail imho...
<https://savannah.gnu.org/bugs/index.php?func=detailitem&item_id=15473>)
Signed-off-by: dean gaudet <dean@arctic.org> Cc: Al Viro <viro@ftp.linux.org.uk> Acked-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Markus Lidel [Fri, 3 Feb 2006 11:04:29 +0000 (03:04 -0800)]
[PATCH] I2O: fix and workaround for Motorola/Freescale controller
- This controller violates the I2O spec for the I/O registers. The patch
contains a workaround which moves the registers to the proper location.
(originally author: Matthew Starzewski)
- If a message frame is beyond the mapped address range a error is
returned.
Signed-off-by: Markus Lidel <Markus.Lidel@shadowconnect.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Jeff Moyer [Fri, 3 Feb 2006 11:04:27 +0000 (03:04 -0800)]
[PATCH] fix O_DIRECT read of last block in a sparse file
Currently, if you open a file O_DIRECT, truncate it to a size that is not a
multiple of the disk block size, and then try to read the last block in the
file, the read will return 0. The problem is in do_direct_IO, here:
/* Handle holes */
if (!buffer_mapped(map_bh)) {
char *kaddr;
...
if (dio->block_in_file >=
i_size_read(dio->inode)>>blkbits) {
/* We hit eof */
page_cache_release(page);
goto out;
}
We shift off any remaining bytes in the final block of the I/O, resulting
in a 0-sized read. I've attached a patch that fixes this. I'm not happy
about how ugly the math is getting, so suggestions are more than welcome.
I've tested this with a simple program that performs the steps outlined for
reproducing the problem above. Without the patch, we get a 0-sized result
from read. With the patch, we get the correct return value from the short
read.
Signed-off-by: Jeff Moyer <jmoyer@redhat.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Suparna Bhattacharya <suparna@in.ibm.com> Cc: Mingming Cao <cmm@us.ibm.com> Cc: Joel Becker <Joel.Becker@oracle.com> Cc: "Chen, Kenneth W" <kenneth.w.chen@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Randy Dunlap [Fri, 3 Feb 2006 11:04:23 +0000 (03:04 -0800)]
[PATCH] cpuset: fix sparse warning
kernel/cpuset.c:644:38: warning: non-ANSI function declaration of function 'cpuset_update_task_memory_state'
Signed-off-by: Randy Dunlap <rdunlap@xenotime.net> Acked-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
[PATCH] v9fs: fix corner cases when flushing request
When v9fs_mux_rpc sends a 9P message, it may be put in the queue of unsent
request. If the user process receives a signal, v9fs_mux_rpc sets the
request error to ERREQFLUSH and assigns NULL to request's send message. If
the message was still in the unsent queue, v9fs_write_work would produce an
oops while processing it.
The patch makes sure that requests that are being flushed are moved to the
pending requests queue safely.
If a request is being flushed, don't remove it from the list of pending
requests even if it receives a reply before the flush is acknoledged. The
request will be removed during from the Rflush handler (v9fs_mux_flush_cb).
Signed-off-by: Latchesar Ionkov <lucho@ionkov.net> Cc: Eric Van Hensbergen <ericvh@ericvh.myip.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Two symlink fixes, v9fs_readlink didn't copy the last character of the
symlink name, v9fs_vfs_follow_link incorrectly called strlen of newly
allocated buffer instead of PATH_MAX.
There is a code path that passed size to ext2_xattr_set
(ext3_xattr_set_handle) before initializing it. The callees don't use the
value in that case, but gcc cannot tell. Always initialize size to get rid
of the warnings.
Signed-off-by: Andreas Gruenbacher <agruen@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Dave Jones [Fri, 3 Feb 2006 11:04:11 +0000 (03:04 -0800)]
[PATCH] EDAC config cleanup
The AMD76x chipsets aren't used in 64-bit, so don't offer the driver to the
user.
Signed-off-by: Dave Jones <davej@redhat.com> Acked-by: Alan Cox <alan@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Fix the problem in kernel 2.6.15.1 (and early versions) that OProfile on
x86_64 does not correctly collect the stack traces for kernel functions.
The original code in valid_kernel_stack() in arch/i386/oprofile/backtrace.c
assumes that the frame pointer (headaddr) should be greater than stack
(i.e., regs).
This assumption is wrong for x86_64 because NMIs in x86_64 use a seperate
stack different from the kernel stack. Therefore, the variable stack now
points to some location on the NMI stack, which turns out to be at a higher
address than the frame pointer (headaddr) on the kernel stack. The correct
comparison here should be between headaddr and regs->rsp for x86_64.
Signed-off-by: Tong Li <tong.n.li@intel.com> Cc: John Levon <levon@movementarian.org> Cc: Philippe Elie <phil.el@wanadoo.fr> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
projects / linux-2.6 / log