The problem that this patch aims to fix is vfsmount refcounting scalability.
We need to take a reference on the vfsmount for every successful path lookup,
which often go to the same mount point.
The fundamental difficulty is that a "simple" reference count can never be made
scalable, because any time a reference is dropped, we must check whether that
was the last reference. To do that requires communication with all other CPUs
that may have taken a reference count.
We can make refcounts more scalable in a couple of ways, involving keeping
distributed counters, and checking for the global-zero condition less
frequently.
- check the global sum once every interval (this will delay zero detection
for some interval, so it's probably a showstopper for vfsmounts).
- keep a local count and only taking the global sum when local reaches 0 (this
is difficult for vfsmounts, because we can't hold preempt off for the life of
a reference, so a counter would need to be per-thread or tied strongly to a
particular CPU which requires more locking).
- keep a local difference of increments and decrements, which allows us to sum
the total difference and hence find the refcount when summing all CPUs. Then,
keep a single integer "long" refcount for slow and long lasting references,
and only take the global sum of local counters when the long refcount is 0.
This last scheme is what I implemented here. Attached mounts and process root
and working directory references are "long" references, and everything else is
a short reference.
This allows scalable vfsmount references during path walking over mounted
subtrees and unattached (lazy umounted) mounts with processes still running
in them.
This results in one fewer atomic op in the fastpath: mntget is now just a
per-CPU inc, rather than an atomic inc; and mntput just requires a spinlock
and non-atomic decrement in the common case. However code is otherwise bigger
and heavier, so single threaded performance is basically a wash.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Regardless of how much we possibly try to scale dcache, there is likely
always going to be some fundamental contention when adding or removing children
under the same parent. Pseudo filesystems do not seem need to have connected
dentries because by definition they are disconnected.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Reduce some branches and memory accesses in dcache lookup by adding dentry
flags to indicate common d_ops are set, rather than having to check them.
This saves a pointer memory access (dentry->d_op) in common path lookup
situations, and saves another pointer load and branch in cases where we
have d_op but not the particular operation.
Patched with:
git grep -E '[.>]([[:space:]])*d_op([[:space:]])*=' | xargs sed -e 's/\([^\t ]*\)->d_op = \(.*\);/d_set_d_op(\1, \2);/' -e 's/\([^\t ]*\)\.d_op = \(.*\);/d_set_d_op(\&\1, \2);/' -i
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Pseudo filesystems that don't put inode on RCU list or reachable by
rcu-walk dentries do not need to RCU free their inodes.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
This avoids some include-file hell, and the function isn't really
important enough to be inlined anyway.
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
And in particular, use it in 'pipe_fcntl()'.
The other pipe functions do not need to use the 'careful' version, since
they are only ever called for things that are already known to be pipes.
The normal read/write/ioctl functions are called through the file
operations structures, so if a file isn't a pipe, they'd never get
called. But pipe_fcntl() is special, and called directly from the
generic fcntl code, and needs to use the same careful function that the
splice code is using.
Cc: Jens Axboe <jaxboe@fusionio.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Jones <davej@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Instead of always assigning an increasing inode number in new_inode
move the call to assign it into those callers that actually need it.
For now callers that need it is estimated conservatively, that is
the call is added to all filesystems that do not assign an i_ino
by themselves. For a few more filesystems we can avoid assigning
any inode number given that they aren't user visible, and for others
it could be done lazily when an inode number is actually needed,
but that's left for later patches.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
The arguments were transposed, we want to assign the error code to
'ret', which is being returned.
Signed-off-by: Nicolas Kaiser <nikai@nikai.net>
Cc: stable@kernel.org
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
As it stands this check compares the number of pages to the page size.
This makes no sense and makes the fcntl fail in almost any sane case.
Fix it by checking if nr_pages is not zero (it can become zero only if
arg is too big and round_pipe_size() overflows).
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
pipe_set_size() needs to copy pipe bufs from the old circular buffer
to the new.
The current code gets this wrong in multiple ways, resulting in oops.
Test program is available here:
http://www.kernel.org/pub/linux/kernel/people/mszeredi/piperesize/
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This changes the interface to be based on bytes instead. The API
matches that of F_SETPIPE_SZ in that it rounds up the passed in
size so that the resulting page array is a power-of-2 in size.
The proc file is renamed to /proc/sys/fs/pipe-max-size to
reflect this change.
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Change it to CAP_SYS_RESOURCE, as that more accurately models what
we want to control.
Suggested-by: Michael Kerrisk <mtk.manpages@googlemail.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
We don't need to pages to guarantee the POSIX requirement
that upto a page size write must be atomic to an empty
pipe.
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
mm: export generic_pipe_buf_*() to modules
fuse: support splice() reading from fuse device
fuse: allow splice to move pages
mm: export remove_from_page_cache() to modules
mm: export lru_cache_add_*() to modules
fuse: support splice() writing to fuse device
fuse: get page reference for readpages
fuse: use get_user_pages_fast()
fuse: remove unneeded variable
Add a mutex_unlock missing on the error path. At other exists from the
function that return an error flag, the mutex is unlocked, so do the same
here.
The semantic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression E1;
@@
* mutex_lock(E1,...);
<+... when != E1
if (...) {
... when != E1
* return ...;
}
...+>
* mutex_unlock(E1,...);
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Instead of requiring an exact number of pages as the argument and
return value, change the API to deal with number of bytes instead.
This also relaxes the requirement that the passed in size must
result in a power-of-2 page array size. Round up to the nearest
power-of-2 automatically and return the resulting size of the pipe
on success.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
If the passed in size is larger than what has been set as the
system wide limit and the user is not root, we want to return
permission denied (not invalid value).
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
We need at least two to guarantee proper POSIX behaviour, so
never allow a smaller limit than that.
Also expose a /proc/sys/fs/pipe-max-pages sysctl file that allows
root to define a sane upper limit. Make it default to 16 times the
default size, which is 16 pages.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This patch adds F_GETPIPE_SZ and F_SETPIPE_SZ fcntl() actions for
growing and shrinking the size of a pipe and adjusts pipe.c and splice.c
(and relay and network splice) usage to work with these larger (or smaller)
pipes.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Filesystems outside the regular namespace do not have to clear DCACHE_UNHASHED
in order to have a working /proc/$pid/fd/XXX. Nothing in proc prevents the
fd link from being used if its dentry is not in the hash.
Also, it does not get put into the dcache hash if DCACHE_UNHASHED is clear;
that depends on the filesystem calling d_add or d_rehash.
So delete the misleading comments and needless code.
Acked-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
This patch fixes a null pointer exception in pipe_rdwr_open() which
generates the stack trace:
> Unable to handle kernel NULL pointer dereference at 0000000000000028 RIP:
> [<ffffffff802899a5>] pipe_rdwr_open+0x35/0x70
> [<ffffffff8028125c>] __dentry_open+0x13c/0x230
> [<ffffffff8028143d>] do_filp_open+0x2d/0x40
> [<ffffffff802814aa>] do_sys_open+0x5a/0x100
> [<ffffffff8021faf3>] sysenter_do_call+0x1b/0x67
The failure mode is triggered by an attempt to open an anonymous
pipe via /proc/pid/fd/* as exemplified by this script:
=============================================================
while : ; do
{ echo y ; sleep 1 ; } | { while read ; do echo z$REPLY; done ; } &
PID=$!
OUT=$(ps -efl | grep 'sleep 1' | grep -v grep |
{ read PID REST ; echo $PID; } )
OUT="${OUT%% *}"
DELAY=$((RANDOM * 1000 / 32768))
usleep $((DELAY * 1000 + RANDOM % 1000 ))
echo n > /proc/$OUT/fd/1 # Trigger defect
done
=============================================================
Note that the failure window is quite small and I could only
reliably reproduce the defect by inserting a small delay
in pipe_rdwr_open(). For example:
static int
pipe_rdwr_open(struct inode *inode, struct file *filp)
{
msleep(100);
mutex_lock(&inode->i_mutex);
Although the defect was observed in pipe_rdwr_open(), I think it
makes sense to replicate the change through all the pipe_*_open()
functions.
The core of the change is to verify that inode->i_pipe has not
been released before attempting to manipulate it. If inode->i_pipe
is no longer present, return ENOENT to indicate so.
The comment about potentially using atomic_t for i_pipe->readers
and i_pipe->writers has also been removed because it is no longer
relevant in this context. The inode->i_mutex lock must be used so
that inode->i_pipe can be dealt with correctly.
Signed-off-by: Earl Chew <earl_chew@agilent.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The presumed use of the pipe_double_lock() routine is to lock 2 locks in
a deadlock free way by ordering the locks by their address. However it
fails to keep the specified lock classes in order and explicitly
annotates a deadlock.
Rectify this.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Miklos Szeredi <mszeredi@suse.cz>
LKML-Reference: <1248163763.15751.11098.camel@twins>
If f_op->splice_read() is not implemented, fall back to a plain read.
Use vfs_readv() to read into previously allocated pages.
This will allow splice and functions using splice, such as the loop
device, to work on all filesystems. This includes "direct_io" files
in fuse which bypass the page cache.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
There are lots of sequences like this, especially in splice code:
if (pipe->inode)
mutex_lock(&pipe->inode->i_mutex);
/* do something */
if (pipe->inode)
mutex_unlock(&pipe->inode->i_mutex);
so introduce helpers which do the conditional locking and unlocking.
Also replace the inode_double_lock() call with a pipe_double_lock()
helper to avoid spreading the use of this functionality beyond the
pipe code.
This patch is just a cleanup, and should cause no behavioral changes.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
The last user of do_pipe is in arch/alpha/, after replacing it with
do_pipe_flags, the do_pipe can be totally dropped.
Signed-off-by: Cheng Renquan <crquan@gmail.com>
Acked-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Most fasync implementations do something like:
return fasync_helper(...);
But fasync_helper() will return a positive value at times - a feature used
in at least one place. Thus, a number of other drivers do:
err = fasync_helper(...);
if (err < 0)
return err;
return 0;
In the interests of consistency and more concise code, it makes sense to
map positive return values onto zero where ->fasync() is called.
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
If the second fasync_helper() fails, pipe_rdwr_fasync() returns the error
but leaves the file on ->fasync_readers.
This was always wrong, but since 233e70f422
"saner FASYNC handling on file close" we have the new problem. Because in
this case setfl() doesn't set FASYNC bit, __fput() will not do
->fasync(0), and we leak fasync_struct with ->fa_file pointing to the
freed file.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove __attribute__((weak)) from common code sys_pipe implemantation.
IA64, ALPHA, SUPERH (32bit) and SPARC (32bit) have own implemantations
with the same name. Just rename them.
For sys_pipe2 there is no architecture specific implementation.
Cc: Richard Henderson <rth@twiddle.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Wrap access to task credentials so that they can be separated more easily from
the task_struct during the introduction of COW creds.
Change most current->(|e|s|fs)[ug]id to current_(|e|s|fs)[ug]id().
Change some task->e?[ug]id to task_e?[ug]id(). In some places it makes more
sense to use RCU directly rather than a convenient wrapper; these will be
addressed by later patches.
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: James Morris <jmorris@namei.org>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: James Morris <jmorris@namei.org>
As it is, all instances of ->release() for files that have ->fasync()
need to remember to evict file from fasync lists; forgetting that
creates a hole and we actually have a bunch that *does* forget.
So let's keep our lives simple - let __fput() check FASYNC in
file->f_flags and call ->fasync() there if it's been set. And lose that
crap in ->release() instances - leaving it there is still valid, but we
don't have to bother anymore.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch adds O_NONBLOCK support to pipe2. It is minimally more involved
than the patches for eventfd et.al but still trivial. The interfaces of the
create_write_pipe and create_read_pipe helper functions were changed and the
one other caller as well.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/syscall.h>
#ifndef __NR_pipe2
# ifdef __x86_64__
# define __NR_pipe2 293
# elif defined __i386__
# define __NR_pipe2 331
# else
# error "need __NR_pipe2"
# endif
#endif
int
main (void)
{
int fds[2];
if (syscall (__NR_pipe2, fds, 0) == -1)
{
puts ("pipe2(0) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
int fl = fcntl (fds[i], F_GETFL);
if (fl == -1)
{
puts ("fcntl failed");
return 1;
}
if (fl & O_NONBLOCK)
{
printf ("pipe2(0) set non-blocking mode for fds[%d]\n", i);
return 1;
}
close (fds[i]);
}
if (syscall (__NR_pipe2, fds, O_NONBLOCK) == -1)
{
puts ("pipe2(O_NONBLOCK) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
int fl = fcntl (fds[i], F_GETFL);
if (fl == -1)
{
puts ("fcntl failed");
return 1;
}
if ((fl & O_NONBLOCK) == 0)
{
printf ("pipe2(O_NONBLOCK) does not set non-blocking mode for fds[%d]\n", i);
return 1;
}
close (fds[i]);
}
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch introduces the new syscall pipe2 which is like pipe but it also
takes an additional parameter which takes a flag value. This patch implements
the handling of O_CLOEXEC for the flag. I did not add support for the new
syscall for the architectures which have a special sys_pipe implementation. I
think the maintainers of those archs have the chance to go with the unified
implementation but that's up to them.
The implementation introduces do_pipe_flags. I did that instead of changing
all callers of do_pipe because some of the callers are written in assembler.
I would probably screw up changing the assembly code. To avoid breaking code
do_pipe is now a small wrapper around do_pipe_flags. Once all callers are
changed over to do_pipe_flags the old do_pipe function can be removed.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/syscall.h>
#ifndef __NR_pipe2
# ifdef __x86_64__
# define __NR_pipe2 293
# elif defined __i386__
# define __NR_pipe2 331
# else
# error "need __NR_pipe2"
# endif
#endif
int
main (void)
{
int fd[2];
if (syscall (__NR_pipe2, fd, 0) != 0)
{
puts ("pipe2(0) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
int coe = fcntl (fd[i], F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
printf ("pipe2(0) set close-on-exit for fd[%d]\n", i);
return 1;
}
}
close (fd[0]);
close (fd[1]);
if (syscall (__NR_pipe2, fd, O_CLOEXEC) != 0)
{
puts ("pipe2(O_CLOEXEC) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
int coe = fcntl (fd[i], F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
printf ("pipe2(O_CLOEXEC) does not set close-on-exit for fd[%d]\n", i);
return 1;
}
}
close (fd[0]);
close (fd[1]);
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Here are some more places where path_{get,put}() can be used instead of
dput()/mntput() pair.
Signed-off-by: Jan Blunck <jblunck@suse.de>
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: Al Viro <viro@zeniv.linux.org.uk>
Remember to close the files if copy_to_user() failed.
Spotted by dm.n9107@gmail.com.
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Cc: DM <dm.n9107@gmail.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This replaces the duplicated arch-specific versions of "sys_pipe()" with
one unified implementation. This removes almost 250 lines of duplicated
code.
It's marked __weak, so that *if* an architecture wants to override the
default implementation it can do so by simply having its own replacement
version, since many architectures use alternate calling conventions for
the 'pipe()' system call for legacy reasons (ie traditional UNIX
implementations often return the two file descriptors in registers)
I still haven't changed the cris version even though Linus says the BKL
isn't needed. The arch maintainer can easily do it if there are really
no obstacles.
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Some new uses of get_empty_filp() have crept in; switched
to alloc_file() to make sure that pieces of initialization
won't be missing.
We really need to kill get_empty_filp().
[AV] fixed dentry leak on failure exit in anon_inode_getfd()
Cc: Erez Zadok <ezk@cs.sunysb.edu>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: "J Bruce Fields" <bfields@fieldses.org>
Acked-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
make sync wakeups affine for cache-cold tasks: if a cache-cold task
is woken up by a sync wakeup then use the opportunity to migrate it
straight away. (the two tasks are 'related' because they communicate)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix some typos in pipe.c and splice.c.
Add pipes API to kernel-api.tmpl.
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
As per Andrew Mortons request, here's a set of documentation for
the generic pipe_buf_operations hooks, the pipe, and pipe_buffer
structures.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
The name 'pin' was badly chosen, it doesn't pin a pipe buffer
in the most commonly used sense in the kernel. So change the
name to 'confirm', after debating this issue with Hugh
Dickins a bit.
A good return from ->confirm() means that the buffer is really
there, and that the contents are good.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
1) Introduces a new method in 'struct dentry_operations'. This method
called d_dname() might be called from d_path() to build a pathname for
special filesystems. It is called without locks.
Future patches (if we succeed in having one common dentry for all
pipes/sockets) may need to change prototype of this method, but we now
use : char *d_dname(struct dentry *dentry, char *buffer, int buflen);
2) Adds a dynamic_dname() helper function that eases d_dname() implementations
3) Defines d_dname method for sockets : No more sprintf() at socket
creation. This is delayed up to the moment someone does an access to
/proc/pid/fd/...
4) Defines d_dname method for pipes : No more sprintf() at pipe
creation. This is delayed up to the moment someone does an access to
/proc/pid/fd/...
A benchmark consisting of 1.000.000 calls to pipe()/close()/close() gives a
*nice* speedup on my Pentium(M) 1.6 Ghz :
3.090 s instead of 3.450 s
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Christoph Hellwig <hch@infradead.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Provide an audit record of the descriptor pair returned by pipe() and
socketpair(). Rewritten from the original posted to linux-audit by
John D. Ramsdell <ramsdell@mitre.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
- pipe/splice should use const pipe_buf_operations and file_operations
- struct pipe_inode_info has an unused field "start" : get rid of it.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch changes struct file to use struct path instead of having
independent pointers to struct dentry and struct vfsmount, and converts all
users of f_{dentry,vfsmnt} in fs/ to use f_path.{dentry,mnt}.
Additionally, it adds two #define's to make the transition easier for users of
the f_dentry and f_vfsmnt.
Signed-off-by: Josef "Jeff" Sipek <jsipek@cs.sunysb.edu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
We currently insert pipe dentries into the global dentry hashtable. This
is suboptimal because there is currently no way these entries can be used
for a lookup(). (/proc/xxx/fd/xxx uses a different mechanism). Inserting
them in dentry hashtable slows dcache lookups.
To let __dpath() still work correctly (ie not adding a " (deleted)") after
dentry name, we do :
- Right after d_alloc(), pretend they are hashed by clearing the
DCACHE_UNHASHED bit.
- Call d_instantiate() instead of d_add() : dentry is not inserted in
hash table.
__dpath() & friends work as intended during dentry lifetime.
- At dismantle time, once dput() must clear the dentry, setting again
DCACHE_UNHASHED bit inside the custom d_delete() function provided by
pipe code, so that dput() can just kill_it.
This patch, combined with (avoid RCU for never hashed dentries) reduced
time of { pipe(p); close(p[0]); close(p[1]);} on my UP machine (1.6GHz
Pentium-M) from 3.23 us to 2.86 us (But this patch does not depend on other
patches, only bench results)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Split the big and hard to read do_pipe function into smaller pieces.
This creates new create_write_pipe/free_write_pipe/create_read_pipe
functions. These functions are made global so that they can be used by
other parts of the kernel.
The resulting code is more generic and easier to read and has cleaner error
handling and less gotos.
[akpm@osdl.org: cleanup]
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch removes readv() and writev() methods and replaces them with
aio_read()/aio_write() methods.
Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This eliminates the i_blksize field from struct inode. Filesystems that want
to provide a per-inode st_blksize can do so by providing their own getattr
routine instead of using the generic_fillattr() function.
Note that some filesystems were providing pretty much random (and incorrect)
values for i_blksize.
[bunk@stusta.de: cleanup]
[akpm@osdl.org: generic_fillattr() fix]
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.
The filesystem is then required to manually set the superblock and root dentry
pointers. For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).
The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.
This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing. In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.
The patch also makes the following changes:
(*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
pointer argument and return an integer, so most filesystems have to change
very little.
(*) If one of the convenience function is not used, then get_sb() should
normally call simple_set_mnt() to instantiate the vfsmount. This will
always return 0, and so can be tail-called from get_sb().
(*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
dcache upon superblock destruction rather than shrink_dcache_anon().
This is required because the superblock may now have multiple trees that
aren't actually bound to s_root, but that still need to be cleaned up. The
currently called functions assume that the whole tree is rooted at s_root,
and that anonymous dentries are not the roots of trees which results in
dentries being left unculled.
However, with the way NFS superblock sharing are currently set to be
implemented, these assumptions are violated: the root of the filesystem is
simply a dummy dentry and inode (the real inode for '/' may well be
inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
with child trees.
[*] Anonymous until discovered from another tree.
(*) The documentation has been adjusted, including the additional bit of
changing ext2_* into foo_* in the documentation.
[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The pipe ->map() method uses kmap() to virtually map the pages, which
is both slow and has known scalability issues on SMP. This patch enables
atomic copying of pipe pages, by pre-faulting data and using kmap_atomic()
instead.
lmbench bw_pipe and lat_pipe measurements agree this is a Good Thing. Here
are results from that on a UP machine with highmem (1.5GiB of RAM), running
first a UP kernel, SMP kernel, and SMP kernel patched.
Vanilla-UP:
Pipe bandwidth: 1622.28 MB/sec
Pipe bandwidth: 1610.59 MB/sec
Pipe bandwidth: 1608.30 MB/sec
Pipe latency: 7.3275 microseconds
Pipe latency: 7.2995 microseconds
Pipe latency: 7.3097 microseconds
Vanilla-SMP:
Pipe bandwidth: 1382.19 MB/sec
Pipe bandwidth: 1317.27 MB/sec
Pipe bandwidth: 1355.61 MB/sec
Pipe latency: 9.6402 microseconds
Pipe latency: 9.6696 microseconds
Pipe latency: 9.6153 microseconds
Patched-SMP:
Pipe bandwidth: 1578.70 MB/sec
Pipe bandwidth: 1579.95 MB/sec
Pipe bandwidth: 1578.63 MB/sec
Pipe latency: 9.1654 microseconds
Pipe latency: 9.2266 microseconds
Pipe latency: 9.1527 microseconds
Signed-off-by: Jens Axboe <axboe@suse.de>
The ->map() function is really expensive on highmem machines right now,
since it has to use the slower kmap() instead of kmap_atomic(). Splice
rarely needs to access the virtual address of a page, so it's a waste
of time doing it.
Introduce ->pin() to take over the responsibility of making sure the
page data is valid. ->map() is then reduced to just kmap(). That way we
can also share a most of the pipe buffer ops between pipe.c and splice.c
Signed-off-by: Jens Axboe <axboe@suse.de>
Found by Oleg Nesterov <oleg@tv-sign.ru>, fixed by me.
- Only allow full pages to go to the page cache.
- Check page != buf->page instead of using PIPE_BUF_FLAG_STOLEN.
- Remember to clear 'stolen' if add_to_page_cache() fails.
And as a cleanup on that:
- Make the bottom fall-through logic a little less convoluted. Also make
the steal path hold an extra reference to the page, so we don't have
to differentiate between stolen and non-stolen at the end.
Signed-off-by: Jens Axboe <axboe@suse.de>
- Check that page has suitable count for stealing in the regular pipes.
- pipe_to_file() assumes that the page is locked on succesful steal, so
do that in the pipe steal hook
- Missing unlock_page() in add_to_page_cache() failure.
Signed-off-by: Jens Axboe <axboe@suse.de>
Basically an in-kernel implementation of tee, which uses splice and the
pipe buffers as an intelligent way to pass data around by reference.
Where the user space tee consumes the input and produces a stdout and
file output, this syscall merely duplicates the data inside a pipe to
another pipe. No data is copied, the output just grabs a reference to the
input pipe data.
Signed-off-by: Jens Axboe <axboe@suse.de>
It's more efficient for sendfile() emulation. Basically we cache an
internal private pipe and just use that as the intermediate area for
pages. Direct splicing is not available from sys_splice(), it is only
meant to be used for sendfile() emulation.
Additional patch from Ingo Molnar to avoid the PIPE_BUFFERS loop at
exit for the normal fast path.
Signed-off-by: Jens Axboe <axboe@suse.de>
separate out the 'internal pipe object' abstraction, and make it
usable to splice. This cleans up and fixes several aspects of the
internal splice APIs and the pipe code:
- pipes: the allocation and freeing of pipe_inode_info is now more symmetric
and more streamlined with existing kernel practices.
- splice: small micro-optimization: less pointer dereferencing in splice
methods
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Update XFS for the ->splice_read/->splice_write changes.
Signed-off-by: Jens Axboe <axboe@suse.de>
Originally from Nick Piggin, just adapted to the newer branch.
You can't check PageLRU without holding zone->lru_lock. The page
release code can get away with it only because the page refcount is 0 at
that point. Also, you can't reliably remove pages from the LRU unless
the refcount is 0. Ever.
Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Jens Axboe <axboe@suse.de>
By cleaning up the writeback logic (killing write_one_page() and the manual
set_page_dirty()), we can get rid of ->stolen inside the pipe_buffer and
just keep it local in pipe_to_file().
This also adds dirty page balancing logic and O_SYNC handling.
Signed-off-by: Jens Axboe <axboe@suse.de>
This enables the caller to migrate pages from one address space page
cache to another. In buzz word marketing, you can do zero-copy file
copies!
Signed-off-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This adds support for the sys_splice system call. Using a pipe as a
transport, it can connect to files or sockets (latter as output only).
From the splice.c comments:
"splice": joining two ropes together by interweaving their strands.
This is the "extended pipe" functionality, where a pipe is used as
an arbitrary in-memory buffer. Think of a pipe as a small kernel
buffer that you can use to transfer data from one end to the other.
The traditional unix read/write is extended with a "splice()" operation
that transfers data buffers to or from a pipe buffer.
Named by Larry McVoy, original implementation from Linus, extended by
Jens to support splicing to files and fixing the initial implementation
bugs.
Signed-off-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This is a conversion to make the various file_operations structs in fs/
const. Basically a regexp job, with a few manual fixups
The goal is both to increase correctness (harder to accidentally write to
shared datastructures) and reducing the false sharing of cachelines with
things that get dirty in .data (while .rodata is nicely read only and thus
cache clean)
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
I discovered on oprofile hunting on a SMP platform that dentry lookups were
slowed down because d_hash_mask, d_hash_shift and dentry_hashtable were in
a cache line that contained inodes_stat. So each time inodes_stats is
changed by a cpu, other cpus have to refill their cache line.
This patch moves some variables to the __read_mostly section, in order to
avoid false sharing. RCU dentry lookups can go full speed.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Remove the "inline" keyword from a bunch of big functions in the kernel with
the goal of shrinking it by 30kb to 40kb
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Jeff Garzik <jgarzik@pobox.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
To allow various options to work per-mount instead of per-sb we need a
struct vfsmount when updating ctime and mtime. This preparation patch
replaces the inode_update_time routine with a file_update_atime routine so
we can easily get at the vfsmount. (and the file makes more sense in this
context anyway). Also get rid of the unused second argument - we always
want to update the ctime when calling this routine.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Anton Altaparmakov <aia21@cantab.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch converts the inode semaphore to a mutex. I have tested it on
XFS and compiled as much as one can consider on an ia64. Anyway your
luck with it might be different.
Modified-by: Ingo Molnar <mingo@elte.hu>
(finished the conversion)
Signed-off-by: Jes Sorensen <jes@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch implements a task state bit (TASK_NONINTERACTIVE), which can be
used by blocking points to mark the task's wait as "non-interactive". This
does not mean the task will be considered a CPU-hog - the wait will simply
not have an effect on the waiting task's priority - positive or negative
alike. Right now only pipe_wait() will make use of it, because it's a
common source of not-so-interactive waits (kernel compilation jobs, etc.).
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Remove a redundant fifo_poll() abstraction from fs/pipe.c and adds a big
fat comment stating we set POLLERR for FIFOs too on Linux unlike most
Unices.
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Nick Piggin