For zfcpdump we can't map the HSA storage because it is only available via
a read interface. Therefore, for the new vmcore mmap feature we have
introduce a new mechanism to create mappings on demand.
This patch introduces a new architecture function remap_oldmem_pfn_range()
that should be used to create mappings with remap_pfn_range() for oldmem
areas that can be directly mapped. For zfcpdump this is everything
besides of the HSA memory. For the areas that are not mapped by
remap_oldmem_pfn_range() a generic vmcore a new generic vmcore fault
handler mmap_vmcore_fault() is called.
This handler works as follows:
* Get already available or new page from page cache (find_or_create_page)
* Check if /proc/vmcore page is filled with data (PageUptodate)
* If yes:
Return that page
* If no:
Fill page using __vmcore_read(), set PageUptodate, and return page
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Cc: Jan Willeke <willeke@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
For s390 we want to use /proc/vmcore for our SCSI stand-alone dump
(zfcpdump). We have support where the first HSA_SIZE bytes are saved into
a hypervisor owned memory area (HSA) before the kdump kernel is booted.
When the kdump kernel starts, it is restricted to use only HSA_SIZE bytes.
The advantages of this mechanism are:
* No crashkernel memory has to be defined in the old kernel.
* Early boot problems (before kexec_load has been done) can be dumped
* Non-Linux systems can be dumped.
We modify the s390 copy_oldmem_page() function to read from the HSA memory
if memory below HSA_SIZE bytes is requested.
Since we cannot use the kexec tool to load the kernel in this scenario,
we have to build the ELF header in the 2nd (kdump/new) kernel.
So with the following patch set we would like to introduce the new
function that the ELF header for /proc/vmcore can be created in the 2nd
kernel memory.
The following steps are done during zfcpdump execution:
1. Production system crashes
2. User boots a SCSI disk that has been prepared with the zfcpdump tool
3. Hypervisor saves CPU state of boot CPU and HSA_SIZE bytes of memory into HSA
4. Boot loader loads kernel into low memory area
5. Kernel boots and uses only HSA_SIZE bytes of memory
6. Kernel saves registers of non-boot CPUs
7. Kernel does memory detection for dump memory map
8. Kernel creates ELF header for /proc/vmcore
9. /proc/vmcore uses this header for initialization
10. The zfcpdump user space reads /proc/vmcore to write dump to SCSI disk
- copy_oldmem_page() copies from HSA for memory below HSA_SIZE
- copy_oldmem_page() copies from real memory for memory above HSA_SIZE
Currently for s390 we create the ELF core header in the 2nd kernel with a
small trick. We relocate the addresses in the ELF header in a way that
for the /proc/vmcore code it seems to be in the 1st kernel (old) memory
and the read_from_oldmem() returns the correct data. This allows the
/proc/vmcore code to use the ELF header in the 2nd kernel.
This patch:
Exchange the old mechanism with the new and much cleaner function call
override feature that now offcially allows to create the ELF core header
in the 2nd kernel.
To use the new feature the following function have to be defined
by the architecture backend code to read from new memory:
* elfcorehdr_alloc: Allocate ELF header
* elfcorehdr_free: Free the memory of the ELF header
* elfcorehdr_read: Read from ELF header
* elfcorehdr_read_notes: Read from ELF notes
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Cc: Jan Willeke <willeke@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The error hanling and ret-from-loop look confusing and inconsistent.
- "retval >= 0" simply returns
- "!bprm->file" returns too but with read_unlock() because
binfmt_lock was already re-acquired
- "retval != -ENOEXEC || bprm->mm == NULL" does "break" and
relies on the same check after the main loop
Consolidate these checks into a single if/return statement.
need_retry still checks "retval == -ENOEXEC", but this and -ENOENT before
the main loop are not needed. This is only for pathological and
impossible list_empty(&formats) case.
It is not clear why do we check "bprm->mm == NULL", probably this
should be removed.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Zach Levis <zml@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A separate one-liner for better documentation.
It doesn't make sense to retry if request_module() fails to exec
/sbin/modprobe, add the additional "request_module() < 0" check.
However, this logic still doesn't look exactly right:
1. It would be better to check "request_module() != 0", the user
space modprobe process should report the correct exit code.
But I didn't dare to add the user-visible change.
2. The whole ENOEXEC logic looks suboptimal. Suppose that we try
to exec a "#!path-to-unsupported-binary" script. In this case
request_module() + "retry" will be done twice: first by the
"depth == 1" code, and then again by the "depth == 0" caller
which doesn't make sense.
3. And note that in the case above bprm->buf was already changed
by load_script()->prepare_binprm(), so this looks even more
ugly.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Zach Levis <zml@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
search_binary_handler() uses "for (try=0; try<2; try++)" to avoid "goto"
but the code looks too complicated and horrible imho. We still need to
check "try == 0" before request_module() and add the additional "break"
for !CONFIG_MODULES case.
Kill this loop and use a simple "bool need_retry" + "goto retry". The
code looks much simpler and we do not even need ifdef's, gcc can optimize
out the "if (need_retry)" block if !IS_ENABLED().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Zach Levis <zml@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
search_binary_handler() checks ->load_binary != NULL for no reason, this
method should be always defined. Turn this check into WARN_ON() and move
it into __register_binfmt().
Also, kill the function pointer. The current code looks confusing, as if
->load_binary can go away after read_unlock(&binfmt_lock). But we rely on
module_get(fmt->module), this fmt can't be changed or unregistered,
otherwise this code is buggy anyway.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Zach Levis <zml@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When search_binary_handler() succeeds it does allow_write_access() and
fput(), then it clears bprm->file to ensure the caller will not do the
same.
We can simply move this code to exec_binprm() which is called only once.
In fact we could move this to free_bprm() and remove the same code in
do_execve_common's error path.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Zach Levis <zml@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A separate one-liner with the minor fix.
PROC_EVENT_EXEC reports the "exec" event, but this message is sent at
least twice if search_binary_handler() is called by ->load_binary()
recursively, say, load_script().
Move it to exec_binprm(), this is "depth == 0" code too.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Zach Levis <zml@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Nobody except search_binary_handler() should touch ->recursion_depth, "int
depth" buys nothing but complicates the code, kill it.
Probably we should also kill "fn" and the !NULL check, ->load_binary
should be always defined. And it can not go away after read_unlock() or
this code is buggy anyway.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Zach Levis <zml@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
task_pid_nr_ns() and trace/ptrace code in the middle of the recursive
search_binary_handler() looks confusing and imho annoying. We only need
this code if "depth == 0", lets add a simple helper which calls
search_binary_handler() and does trace_sched_process_exec() +
ptrace_event().
The patch also moves the setting of task->did_exec, we need to do this
only once.
Note: we can kill either task->did_exec or PF_FORKNOEXEC.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Zach Levis <zml@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
proc_fd_permission() says "process can still access /proc/self/fd after it
has executed a setuid()", but the "task_pid() = proc_pid() check only
helps if the task is group leader, /proc/self points to
/proc/<leader-pid>.
Change this check to use task_tgid() so that the whole thread group can
access its /proc/self/fd or /proc/<tid-of-sub-thread>/fd.
Notes:
- CLONE_THREAD does not require CLONE_FILES so task->files
can differ, but I don't think this can lead to any security
problem. And this matches same_thread_group() in
__ptrace_may_access().
- /proc/self should probably point to /proc/<thread-tid>, but
it is too late to change the rules. Perhaps it makes sense
to add /proc/thread though.
Test-case:
void *tfunc(void *arg)
{
assert(opendir("/proc/self/fd"));
return NULL;
}
int main(void)
{
pthread_t t;
pthread_create(&t, NULL, tfunc, NULL);
pthread_join(t, NULL);
return 0;
}
fails if, say, this executable is not readable and suid_dumpable = 0.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mpol_to_str() may fail, and not fill the buffer (e.g. -EINVAL), so need
check about it, or buffer may not be zero based, and next seq_printf()
will cause issue.
The failure return need after mpol_cond_put() to match get_vma_policy().
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add a new %P variable to be used in core_pattern. This variable contains
the global PID (PID in the init namespace) as %p contains the PID in the
current namespace which isn't always what we want.
The main use for this is to make it easier to handle crashes that happened
within a container. With that new variables it's possible to have the
crashes dumped into the container or forwarded to the host with the right
PID (from the host's point of view).
Signed-off-by: Stéphane Graber <stgraber@ubuntu.com>
Reported-by: Hans Feldt <hans.feldt@ericsson.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Andy Whitcroft <apw@canonical.com>
Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patchset implements POSIX ACLs support in hfsplus driver.
Mac OS X beginning with version 10.4 ("Tiger") support NFSv4 ACLs, which
are part of the NFSv4 standard. HFS+ stores ACLs in the form of
specially named extended attributes (com.apple.system.Security).
But this patchset doesn't use "com.apple.system.Security" extended
attributes. It implements support of POSIX ACLs in the form of extended
attributes with names "system.posix_acl_access" and
"system.posix_acl_default". These xattrs are treated only under Linux.
POSIX ACLs doesn't mean something under Mac OS X. Thereby, this patch
set provides opportunity to use POSIX ACLs under Linux on HFS+
filesystem.
This patch:
Add CONFIG_HFSPLUS_FS_POSIX_ACL kernel configuration option, DBG_ACL_MOD
debugging flag and acl.h file with declaration of essential functions
for support POSIX ACLs in hfsplus driver.
Signed-off-by: Vyacheslav Dubeyko <slava@dubeyko.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hin-Tak Leung <htl10@users.sourceforge.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
ep_free() might iterate on a huge set of epitems and hold cpu too long.
Add two cond_resched() in order to yield cpu to other tasks. This is safe
as we only hold mutexes in this function.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Theodore Ts'o <tytso@mit.edu>
Acked-by: Eric Wong <normalperson@yhbt.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Free the bio_integrity_pool in the fail path of biovec_create_pool in
function bioset_integrity_create().
Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There is a race between mark inode dirty and writeback thread, see the
following scenario. In this case, writeback thread will not run though
there is dirty_io.
__mark_inode_dirty() bdi_writeback_workfn()
... ...
spin_lock(&inode->i_lock);
...
if (bdi_cap_writeback_dirty(bdi)) {
<<< assume wb has dirty_io, so wakeup_bdi is false.
<<< the following inode_dirty also have wakeup_bdi false.
if (!wb_has_dirty_io(&bdi->wb))
wakeup_bdi = true;
}
spin_unlock(&inode->i_lock);
<<< assume last dirty_io is removed here.
pages_written = wb_do_writeback(wb);
...
<<< work_list empty and wb has no dirty_io,
<<< delayed_work will not be queued.
if (!list_empty(&bdi->work_list) ||
(wb_has_dirty_io(wb) && dirty_writeback_interval))
queue_delayed_work(bdi_wq, &wb->dwork,
msecs_to_jiffies(dirty_writeback_interval * 10));
spin_lock(&bdi->wb.list_lock);
inode->dirtied_when = jiffies;
<<< new dirty_io is added.
list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
spin_unlock(&bdi->wb.list_lock);
<<< though there is dirty_io, but wakeup_bdi is false,
<<< so writeback thread will not be waked up and
<<< the new dirty_io will not be flushed.
if (wakeup_bdi)
bdi_wakeup_thread_delayed(bdi);
Writeback will run until there is a new flush work queued. This may cause
a lot of dirty pages stay in memory for a long time.
Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The feature prevents mistrusted filesystems (ie: FUSE mounts created by
unprivileged users) to grow a large number of dirty pages before
throttling. For such filesystems balance_dirty_pages always check bdi
counters against bdi limits. I.e. even if global "nr_dirty" is under
"freerun", it's not allowed to skip bdi checks. The only use case for now
is fuse: it sets bdi max_ratio to 1% by default and system administrators
are supposed to expect that this limit won't be exceeded.
The feature is on if a BDI is marked by BDI_CAP_STRICTLIMIT flag. A
filesystem may set the flag when it initializes its BDI.
The problematic scenario comes from the fact that nobody pays attention to
the NR_WRITEBACK_TEMP counter (i.e. number of pages under fuse
writeback). The implementation of fuse writeback releases original page
(by calling end_page_writeback) almost immediately. A fuse request queued
for real processing bears a copy of original page. Hence, if userspace
fuse daemon doesn't finalize write requests in timely manner, an
aggressive mmap writer can pollute virtually all memory by those temporary
fuse page copies. They are carefully accounted in NR_WRITEBACK_TEMP, but
nobody cares.
To make further explanations shorter, let me use "NR_WRITEBACK_TEMP
problem" as a shortcut for "a possibility of uncontrolled grow of amount
of RAM consumed by temporary pages allocated by kernel fuse to process
writeback".
The problem was very easy to reproduce. There is a trivial example
filesystem implementation in fuse userspace distribution: fusexmp_fh.c. I
added "sleep(1);" to the write methods, then recompiled and mounted it.
Then created a huge file on the mount point and run a simple program which
mmap-ed the file to a memory region, then wrote a data to the region. An
hour later I observed almost all RAM consumed by fuse writeback. Since
then some unrelated changes in kernel fuse made it more difficult to
reproduce, but it is still possible now.
Putting this theoretical happens-in-the-lab thing aside, there is another
thing that really hurts real world (FUSE) users. This is write-through
page cache policy FUSE currently uses. I.e. handling write(2), kernel
fuse populates page cache and flushes user data to the server
synchronously. This is excessively suboptimal. Pavel Emelyanov's patches
("writeback cache policy") solve the problem, but they also make resolving
NR_WRITEBACK_TEMP problem absolutely necessary. Otherwise, simply copying
a huge file to a fuse mount would result in memory starvation. Miklos,
the maintainer of FUSE, believes strictlimit feature the way to go.
And eventually putting FUSE topics aside, there is one more use-case for
strictlimit feature. Using a slow USB stick (mass storage) in a machine
with huge amount of RAM installed is a well-known pain. Let's make simple
computations. Assuming 64GB of RAM installed, existing implementation of
balance_dirty_pages will start throttling only after 9.6GB of RAM becomes
dirty (freerun == 15% of total RAM). So, the command "cp 9GB_file
/media/my-usb-storage/" may return in a few seconds, but subsequent
"umount /media/my-usb-storage/" will take more than two hours if effective
throughput of the storage is, to say, 1MB/sec.
After inclusion of strictlimit feature, it will be trivial to add a knob
(e.g. /sys/devices/virtual/bdi/x:y/strictlimit) to enable it on demand.
Manually or via udev rule. May be I'm wrong, but it seems to be quite a
natural desire to limit the amount of dirty memory for some devices we are
not fully trust (in the sense of sustainable throughput).
[akpm@linux-foundation.org: fix warning in page-writeback.c]
Signed-off-by: Maxim Patlasov <MPatlasov@parallels.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It's not used globally and could be static.
Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pavel reported that in case if vma area get unmapped and then mapped (or
expanded) in-place, the soft dirty tracker won't be able to recognize this
situation since it works on pte level and ptes are get zapped on unmap,
loosing soft dirty bit of course.
So to resolve this situation we need to track actions on vma level, there
VM_SOFTDIRTY flag comes in. When new vma area created (or old expanded)
we set this bit, and keep it here until application calls for clearing
soft dirty bit.
Thus when user space application track memory changes now it can detect if
vma area is renewed.
Reported-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Rob Landley <rob@landley.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In case when system contains no dirty pages, wakeup_flusher_threads() will
submit WB_SYNC_NONE writeback for 0 pages so wb_writeback() exits
immediately without doing anything, even though there are dirty inodes in
the system. Thus sync(1) will write all the dirty inodes from a
WB_SYNC_ALL writeback pass which is slow.
Fix the problem by using get_nr_dirty_pages() in wakeup_flusher_threads()
instead of calculating number of dirty pages manually. That function also
takes number of dirty inodes into account.
Signed-off-by: Jan Kara <jack@suse.cz>
Reported-by: Paul Taysom <taysom@chromium.org>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Call fiemap ioctl(2) with given start offset as well as an desired mapping
range should show extents if possible. However, we somehow figure out the
end offset of mapping via 'mapping_end -= cpos' before iterating the
extent records which would cause problems if the given fiemap length is
too small to a cluster size, e.g,
Cluster size 4096:
debugfs.ocfs2 1.6.3
Block Size Bits: 12 Cluster Size Bits: 12
The extended fiemap test utility From David:
https://gist.github.com/anonymous/6172331
# dd if=/dev/urandom of=/ocfs2/test_file bs=1M count=1000
# ./fiemap /ocfs2/test_file 4096 10
start: 4096, length: 10
File /ocfs2/test_file has 0 extents:
# Logical Physical Length Flags
^^^^^ <-- No extent is shown
In this case, at ocfs2_fiemap(): cpos == mapping_end == 1. Hence the
loop of searching extent records was not executed at all.
This patch remove the in question 'mapping_end -= cpos', and loops
until the cpos is larger than the mapping_end as usual.
# ./fiemap /ocfs2/test_file 4096 10
start: 4096, length: 10
File /ocfs2/test_file has 1 extents:
# Logical Physical Length Flags
0: 0000000000000000 0000000056a01000 0000000006a00000 0000
Signed-off-by: Jie Liu <jeff.liu@oracle.com>
Reported-by: David Weber <wb@munzinger.de>
Tested-by: David Weber <wb@munzinger.de>
Cc: Sunil Mushran <sunil.mushran@gmail.com>
Cc: Mark Fashen <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Variable ip in dlmfs_get_root_inode() is defined but not used. So clean
it up.
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Reviewed-by: Jie Liu <jeff.liu@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In o2hb_shutdown_slot() and o2hb_check_slot(), since event is defined as
local, it is only valid during the call stack. So the following tiny race
case may happen in a multi-volumes mounted environment:
o2hb-vol1 o2hb-vol2
1) o2hb_shutdown_slot
allocate local event1
2) queue_node_event
add event1 to global o2hb_node_events
3) o2hb_shutdown_slot
allocate local event2
4) queue_node_event
add event2 to global o2hb_node_events
5) o2hb_run_event_list
delete event1 from o2hb_node_events
6) o2hb_run_event_list
event1 empty, return
7) o2hb_shutdown_slot
event1 lifecycle ends
8) o2hb_fire_callbacks
event1 is already *invalid*
This patch lets it wait on o2hb_callback_sem when another thread is firing
callbacks. And for performance consideration, we only call
o2hb_run_event_list when there is an event queued.
Signed-off-by: Joyce <xuejiufei@huawei.com>
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since o2nm_get_node_by_num() may return NULL, we add this check in
o2net_accept_one() to avoid possible NULL pointer dereference.
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Code in o2net_handler_tree_lookup() may be corrupted by mistake. So
adjust it to promote readability.
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In ocfs2_remove_inode_range(), there is a memory leak. The variable path
has allocated memory with ocfs2_new_path_from_et(), but it is not free.
Signed-off-by: Younger Liu <younger.liu@huawei.com>
Reviewed-by: Jie Liu <jeff.liu@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In ocfs2_reflink_xattr_rec(), meta_ac and data_ac are allocated by calling
ocfs2_lock_reflink_xattr_rec_allocators().
Once an error occurs when allocating *data_ac, it frees *meta_ac which is
allocated before. Here it mistakenly sets meta_ac to NULL but *meta_ac.
Then ocfs2_reflink_xattr_rec() will try to free meta_ac again which is
already invalid.
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Reviewed-by: Jie Liu <jeff.liu@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
dlm_do_local_recovery_cleanup() should force clean refmap if the owner of
lockres is UNKNOWN. Otherwise node may hang when umounting filesystems.
Here's the situation:
Node1 Node2
dlmlock()
-> dlm_get_lock_resource()
send DLM_MASTER_REQUEST_MSG to
other nodes.
trying to master this lockres,
return MAYBE.
selected as the master of lockresA,
set mle->master to Node1,
and do assert_master,
send DLM_ASSERT_MASTER_MSG to Node2.
Node 2 has interest on lockresA
and return
DLM_ASSERT_RESPONSE_MASTERY_REF
then something happened and
Node2 crashed.
Receiving DLM_ASSERT_RESPONSE_MASTERY_REF, set Node2 into refmap, and keep
sending DLM_ASSERT_MASTER_MSG to other nodes
o2hb found node2 down, calling dlm_hb_node_down() -->
dlm_do_local_recovery_cleanup() the master of lockresA is still UNKNOWN,
no need to call dlm_free_dead_locks().
Set the master of lockresA to Node1, but Node2 stills remains in refmap.
When Node1 umount, it found that the refmap of lockresA is not empty and
attempted to migrate it to Node2, But Node2 is already down, so umount
hang, trying to migrate lockresA again and again.
Signed-off-by: joyce <xuejiufei@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Jie Liu <jeff.liu@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In ocfs2_xattr_set(), if ocfs2_start_trans failed, meta_ac and data_ac
should be free. Otherwise, It would lead to a memory leak.
Signed-off-by: Younger Liu <younger.liu@huawei.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Reviewed-by: Jie Liu <jeff.liu@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In ocfs2_xattr_value_attach_refcount(), if error occurs when calling
ocfs2_xattr_get_clusters(), it will go with unexpected behavior since
local variables p_cluster, num_clusters and ext_flags are declared without
initialization.
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Acked-by: Jie Liu <jeff.liu@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The ocfs2 path is not properly freed which leads to a memory leak at
__ocfs2_move_extents().
This patch stops the leaks of the ocfs2_path structure.
Signed-off-by: Jie Liu <jeff.liu@oracle.com>
Reviewed-by: Younger Liu <younger.liu@huawei.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In ocfs2_attach_refcount_tree() and ocfs2_duplicate_extent_list(), if
error occurs when calling ocfs2_get_clusters(), it will go with
unexpected behavior as local variables p_cluster, num_clusters and
ext_flags are declared without initialization.
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Reviewed-by: Jie Liu <jeff.liu@oracle.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In ocfs2_acl_from_xattr(), if size is less than sizeof(struct
posix_acl_entry), it returns ERR_PTR(-EINVAL) directly. Then assign (size
/ sizeof(struct posix_acl_entry)) to count which will be at least 1, that
means the following branch (count < 0) and (count == 0) will never be
true.
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Acked-by: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[dan.carpenter@oracle.com: fix up some NULL dereference bugs]
Signed-off-by: Dong Fang <yp.fangdong@gmail.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Jeff Liu <jeff.liu@oracle.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix some possible null pointer dereferences that were detected by the
static code analyser, smatch.
Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Reported-by: Guozhonghua <guozhonghua@h3c.com>
Cc: Sunil Mushran <sunil.mushran@gmail.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There is an issue in reserving and claiming space for localalloc, When
localalloc space is not enough, it would claim space from global_bitmap.
And if there is not enough free space in global_bitmap, the size of
claiming space would set to half of orignal size and retry.
The issue is as follows: osb->local_alloc_bits is set to half of orignal
size in ocfs2_recalc_la_window(), but ac->ac_bits_wanted is set to
osb->local_alloc_default_bits which is not changed. localalloc always
reserves and claims local_alloc_default_bits space and returns ENOSPC.
So, ac->ac_bits_wanted should be osb->local_alloc_bits which would be
changed.
Signed-off-by: Younger Liu <younger.liu@huawei.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Jeff Liu <jeff.liu@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
dlm_request_all_locks() should deal with the status sent from target node
if DLM_LOCK_REQUEST_MSG is sent successfully, or recovery master will fall
into endless loop, waiting for other nodes to send locks and
DLM_RECO_DATA_DONE_MSG to me.
NodeA NodeB
selected as recovery master
dlm_remaster_locks()
->dlm_request_all_locks()
send DLM_LOCK_REQUEST_MSG to nodeA
It happened that NodeA cannot alloc memory when it processes this
message. dlm_request_all_locks_handler() do not queue
dlm_request_all_locks_worker and returns -ENOMEM. It will never send
locks and DLM_RECO_DATA_DONE_MSG to NodeB.
NodeB do not deal with the status
sent from nodeA, and will fall in
endless loop waiting for the
recovery state of NodeA to be
changed.
Signed-off-by: joyce <xuejiufei@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Jeff Liu <jeff.liu@oracle.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Though ocfs2 uses inode->i_mutex to protect i_size, there are both
i_size_read/write() and direct accesses. Clean up all direct access to
eliminate confusion.
Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Jie Liu <jeff.liu@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The issue scenario is as following:
When fallocating a very large disk space for a small file,
__ocfs2_extend_allocation attempts to get a very large transaction. For
some journal sizes, there may be not enough room for this transaction,
and the fallocate will fail.
The patch below extends & restarts the transaction as necessary while
allocating space, and should work with even the smallest journal. This
patch refers ext4 resize.
Test:
# mkfs.ocfs2 -b 4K -C 32K -T datafiles /dev/sdc
...(jounral size is 32M)
# mount.ocfs2 /dev/sdc /mnt/ocfs2/
# touch /mnt/ocfs2/1.log
# fallocate -o 0 -l 400G /mnt/ocfs2/1.log
fallocate: /mnt/ocfs2/1.log: fallocate failed: Cannot allocate memory
# tail -f /var/log/messages
[ 7372.278591] JBD: fallocate wants too many credits (2051 > 2048)
[ 7372.278597] (fallocate,6438,0):__ocfs2_extend_allocation:709 ERROR: status = -12
[ 7372.278603] (fallocate,6438,0):ocfs2_allocate_unwritten_extents:1504 ERROR: status = -12
[ 7372.278607] (fallocate,6438,0):__ocfs2_change_file_space:1955 ERROR: status = -12
^C
With this patch, the test works well.
Signed-off-by: Younger Liu <younger.liu@huawei.com>
Cc: Jie Liu <jeff.liu@oracle.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull nfsd updates from Bruce Fields:
"This was a very quiet cycle! Just a few bugfixes and some cleanup"
* 'nfsd-next' of git://linux-nfs.org/~bfields/linux:
rpc: let xdr layer allocate gssproxy receieve pages
rpc: fix huge kmalloc's in gss-proxy
rpc: comment on linux_cred encoding, treat all as unsigned
rpc: clean up decoding of gssproxy linux creds
svcrpc: remove unused rq_resused
nfsd4: nfsd4_create_clid_dir prints uninitialized data
nfsd4: fix leak of inode reference on delegation failure
Revert "nfsd: nfs4_file_get_access: need to be more careful with O_RDWR"
sunrpc: prepare NFS for 2038
nfsd4: fix setlease error return
nfsd: nfs4_file_get_access: need to be more careful with O_RDWR
Pull vfs pile 3 (of many) from Al Viro:
"Waiman's conversion of d_path() and bits related to it,
kern_path_mountpoint(), several cleanups and fixes (exportfs
one is -stable fodder, IMO).
There definitely will be more... ;-/"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
split read_seqretry_or_unlock(), convert d_walk() to resulting primitives
dcache: Translating dentry into pathname without taking rename_lock
autofs4 - fix device ioctl mount lookup
introduce kern_path_mountpoint()
rename user_path_umountat() to user_path_mountpoint_at()
take unlazy_walk() into umount_lookup_last()
Kill indirect include of file.h from eventfd.h, use fdget() in cgroup.c
prune_super(): sb->s_op is never NULL
exportfs: don't assume that ->iterate() won't feed us too long entries
afs: get rid of redundant ->d_name.len checks
When I moved the RCU walk termination into unlazy_walk(), I didn't copy
quite all of it: for the successful RCU termination we properly add the
necessary reference counts to our temporary copy of the root path, but
for the failure case we need to make sure that any temporary root path
information is cleared out (since it does _not_ have the proper
reference counts from the RCU lookup).
We could clean up this mess by just always dropping the temporary root
information, but Al points out that that would mean that a single lookup
through symlinks could see multiple different root entries if it races
with another thread doing chroot. Not that I think we should really
care (we had that before too, back before we had a copy of the root path
in the nameidata).
Al says he has a cunning plan. In the meantime, this is the minimal fix
for the problem, even if it's not all that pretty.
Reported-by: Mace Moneta <moneta.mace@gmail.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Separate "check if we need to retry" from "unlock if we are done and
had seq_writelock"; that allows to use these guys in d_walk(), where
we need to recheck every time we ascend back to parent, but do *not*
want to unlock until the very end. Lift rcu_read_lock/rcu_read_unlock
out into callers.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
For 3.12-rc1 there are a number of bugfixes in addition to work to ease usage
of shared code between libxfs and the kernel, the rest of the work to enable
project and group quotas to be used simultaneously, performance optimisations
in the log and the CIL, directory entry file type support, fixes for log space
reservations, some spelling/grammar cleanups, and the addition of user
namespace support.
- introduce readahead to log recovery
- add directory entry file type support
- fix a number of spelling errors in comments
- introduce new Q_XGETQSTATV quotactl for project quotas
- add USER_NS support
- log space reservation rework
- CIL optimisations
- kernel/userspace libxfs rework
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.10 (GNU/Linux)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=V4s4
-----END PGP SIGNATURE-----
Merge tag 'xfs-for-linus-v3.12-rc1' of git://oss.sgi.com/xfs/xfs
Pull xfs updates from Ben Myers:
"For 3.12-rc1 there are a number of bugfixes in addition to work to
ease usage of shared code between libxfs and the kernel, the rest of
the work to enable project and group quotas to be used simultaneously,
performance optimisations in the log and the CIL, directory entry file
type support, fixes for log space reservations, some spelling/grammar
cleanups, and the addition of user namespace support.
- introduce readahead to log recovery
- add directory entry file type support
- fix a number of spelling errors in comments
- introduce new Q_XGETQSTATV quotactl for project quotas
- add USER_NS support
- log space reservation rework
- CIL optimisations
- kernel/userspace libxfs rework"
* tag 'xfs-for-linus-v3.12-rc1' of git://oss.sgi.com/xfs/xfs: (112 commits)
xfs: XFS_MOUNT_QUOTA_ALL needed by userspace
xfs: dtype changed xfs_dir2_sfe_put_ino to xfs_dir3_sfe_put_ino
Fix wrong flag ASSERT in xfs_attr_shortform_getvalue
xfs: finish removing IOP_* macros.
xfs: inode log reservations are too small
xfs: check correct status variable for xfs_inobt_get_rec() call
xfs: inode buffers may not be valid during recovery readahead
xfs: check LSN ordering for v5 superblocks during recovery
xfs: btree block LSN escaping to disk uninitialised
XFS: Assertion failed: first <= last && last < BBTOB(bp->b_length), file: fs/xfs/xfs_trans_buf.c, line: 568
xfs: fix bad dquot buffer size in log recovery readahead
xfs: don't account buffer cancellation during log recovery readahead
xfs: check for underflow in xfs_iformat_fork()
xfs: xfs_dir3_sfe_put_ino can be static
xfs: introduce object readahead to log recovery
xfs: Simplify xfs_ail_min() with list_first_entry_or_null()
xfs: Register hotcpu notifier after initialization
xfs: add xfs sb v4 support for dirent filetype field
xfs: Add write support for dirent filetype field
xfs: Add read-only support for dirent filetype field
...
Not using the return value can in the generic case be racy, so it's
in general good practice to check the return value instead.
This also resolved the warning caused on ARM and other architectures:
fs/direct-io.c: In function 'sb_init_dio_done_wq':
fs/direct-io.c:557:2: warning: value computed is not used [-Wunused-value]
Signed-off-by: Olof Johansson <olof@lixom.net>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: H Peter Anvin <hpa@zytor.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When running the AIM7's short workload, Linus' lockref patch eliminated
most of the spinlock contention. However, there were still some left:
8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock
|--42.21%-- d_path
| proc_pid_readlink
| SyS_readlinkat
| SyS_readlink
| system_call
| __GI___readlink
|
|--40.97%-- sys_getcwd
| system_call
| __getcwd
The big one here is the rename_lock (seqlock) contention in d_path()
and the getcwd system call. This patch will eliminate the need to take
the rename_lock while translating dentries into the full pathnames.
The need to take the rename_lock is to make sure that no rename
operation can be ongoing while the translation is in progress. However,
only one thread can take the rename_lock thus blocking all the other
threads that need it even though the translation process won't make
any change to the dentries.
This patch will replace the writer's write_seqlock/write_sequnlock
sequence of the rename_lock of the callers of the prepend_path() and
__dentry_path() functions with the reader's read_seqbegin/read_seqretry
sequence within these 2 functions. As a result, the code will have to
retry if one or more rename operations had been performed. In addition,
RCU read lock will be taken during the translation process to make sure
that no dentries will go away. To prevent live-lock from happening,
the code will switch back to take the rename_lock if read_seqretry()
fails for three times.
To further reduce spinlock contention, this patch does not take the
dentry's d_lock when copying the filename from the dentries. Instead,
it treats the name pointer and length as unreliable and just copy
the string byte-by-byte over until it hits a null byte or the end of
string as specified by the length. This should avoid stepping into
invalid memory address. The error cases are left to be handled by
the sequence number check.
The following code re-factoring are also made:
1. Move prepend('/') into prepend_name() to remove one conditional
check.
2. Move the global root check in prepend_path() back to the top of
the while loop.
With this patch, the _raw_spin_lock will now account for only 1.2%
of the total CPU cycles for the short workload. This patch also has
the effect of reducing the effect of running perf on its profile
since the perf command itself can be a heavy user of the d_path()
function depending on the complexity of the workload.
When taking the perf profile of the high-systime workload, the amount
of spinlock contention contributed by running perf without this patch
was about 16%. With this patch, the spinlock contention caused by
the running of perf will go away and we will have a more accurate
perf profile.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
