OpenCloudOS-Kernel/fs/autofs4/root.c

896 lines
23 KiB
C
Raw Normal View History

/* -*- c -*- --------------------------------------------------------------- *
*
* linux/fs/autofs/root.c
*
* Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
* Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
* Copyright 2001-2006 Ian Kent <raven@themaw.net>
*
* This file is part of the Linux kernel and is made available under
* the terms of the GNU General Public License, version 2, or at your
* option, any later version, incorporated herein by reference.
*
* ------------------------------------------------------------------------- */
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/stat.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/param.h>
#include <linux/time.h>
#include <linux/compat.h>
#include <linux/mutex.h>
#include "autofs_i.h"
static int autofs4_dir_symlink(struct inode *,struct dentry *,const char *);
static int autofs4_dir_unlink(struct inode *,struct dentry *);
static int autofs4_dir_rmdir(struct inode *,struct dentry *);
static int autofs4_dir_mkdir(struct inode *,struct dentry *,int);
static long autofs4_root_ioctl(struct file *,unsigned int,unsigned long);
#ifdef CONFIG_COMPAT
static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
#endif
static int autofs4_dir_open(struct inode *inode, struct file *file);
static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
static struct vfsmount *autofs4_d_automount(struct path *);
static int autofs4_d_manage(struct dentry *, bool);
static void autofs4_dentry_release(struct dentry *);
const struct file_operations autofs4_root_operations = {
.open = dcache_dir_open,
.release = dcache_dir_close,
.read = generic_read_dir,
.readdir = dcache_readdir,
.llseek = dcache_dir_lseek,
.unlocked_ioctl = autofs4_root_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = autofs4_root_compat_ioctl,
#endif
};
const struct file_operations autofs4_dir_operations = {
.open = autofs4_dir_open,
.release = dcache_dir_close,
.read = generic_read_dir,
.readdir = dcache_readdir,
.llseek = dcache_dir_lseek,
};
const struct inode_operations autofs4_dir_inode_operations = {
.lookup = autofs4_lookup,
.unlink = autofs4_dir_unlink,
.symlink = autofs4_dir_symlink,
.mkdir = autofs4_dir_mkdir,
.rmdir = autofs4_dir_rmdir,
};
const struct dentry_operations autofs4_dentry_operations = {
.d_automount = autofs4_d_automount,
.d_manage = autofs4_d_manage,
.d_release = autofs4_dentry_release,
};
static void autofs4_add_active(struct dentry *dentry)
{
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
if (ino) {
spin_lock(&sbi->lookup_lock);
if (!ino->active_count) {
if (list_empty(&ino->active))
list_add(&ino->active, &sbi->active_list);
}
ino->active_count++;
spin_unlock(&sbi->lookup_lock);
}
return;
}
static void autofs4_del_active(struct dentry *dentry)
{
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
if (ino) {
spin_lock(&sbi->lookup_lock);
ino->active_count--;
if (!ino->active_count) {
if (!list_empty(&ino->active))
list_del_init(&ino->active);
}
spin_unlock(&sbi->lookup_lock);
}
return;
}
static int autofs4_dir_open(struct inode *inode, struct file *file)
{
struct dentry *dentry = file->f_path.dentry;
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
DPRINTK("file=%p dentry=%p %.*s",
file, dentry, dentry->d_name.len, dentry->d_name.name);
if (autofs4_oz_mode(sbi))
goto out;
/*
* An empty directory in an autofs file system is always a
* mount point. The daemon must have failed to mount this
* during lookup so it doesn't exist. This can happen, for
* example, if user space returns an incorrect status for a
* mount request. Otherwise we're doing a readdir on the
* autofs file system so just let the libfs routines handle
* it.
*/
spin_lock(&sbi->lookup_lock);
spin_lock(&dentry->d_lock);
if (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
spin_unlock(&dentry->d_lock);
spin_unlock(&sbi->lookup_lock);
return -ENOENT;
}
spin_unlock(&dentry->d_lock);
spin_unlock(&sbi->lookup_lock);
out:
return dcache_dir_open(inode, file);
}
static void autofs4_dentry_release(struct dentry *de)
{
struct autofs_info *ino = autofs4_dentry_ino(de);
struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb);
DPRINTK("releasing %p", de);
if (!ino)
return;
if (sbi) {
spin_lock(&sbi->lookup_lock);
if (!list_empty(&ino->active))
list_del(&ino->active);
if (!list_empty(&ino->expiring))
list_del(&ino->expiring);
spin_unlock(&sbi->lookup_lock);
}
autofs4_free_ino(ino);
}
static struct dentry *autofs4_lookup_active(struct dentry *dentry)
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
{
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct dentry *parent = dentry->d_parent;
struct qstr *name = &dentry->d_name;
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
unsigned int len = name->len;
unsigned int hash = name->hash;
const unsigned char *str = name->name;
struct list_head *p, *head;
spin_lock(&sbi->lookup_lock);
head = &sbi->active_list;
list_for_each(p, head) {
struct autofs_info *ino;
struct dentry *active;
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
struct qstr *qstr;
ino = list_entry(p, struct autofs_info, active);
active = ino->dentry;
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
spin_lock(&active->d_lock);
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
/* Already gone? */
if (active->d_count == 0)
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
goto next;
qstr = &active->d_name;
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
if (active->d_name.hash != hash)
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
goto next;
if (active->d_parent != parent)
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
goto next;
if (qstr->len != len)
goto next;
if (memcmp(qstr->name, str, len))
goto next;
if (d_unhashed(active)) {
dget_dlock(active);
spin_unlock(&active->d_lock);
spin_unlock(&sbi->lookup_lock);
return active;
}
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
next:
spin_unlock(&active->d_lock);
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
}
spin_unlock(&sbi->lookup_lock);
return NULL;
}
static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
{
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct dentry *parent = dentry->d_parent;
struct qstr *name = &dentry->d_name;
unsigned int len = name->len;
unsigned int hash = name->hash;
const unsigned char *str = name->name;
struct list_head *p, *head;
spin_lock(&sbi->lookup_lock);
head = &sbi->expiring_list;
list_for_each(p, head) {
struct autofs_info *ino;
struct dentry *expiring;
struct qstr *qstr;
ino = list_entry(p, struct autofs_info, expiring);
expiring = ino->dentry;
spin_lock(&expiring->d_lock);
/* Bad luck, we've already been dentry_iput */
if (!expiring->d_inode)
goto next;
qstr = &expiring->d_name;
if (expiring->d_name.hash != hash)
goto next;
if (expiring->d_parent != parent)
goto next;
if (qstr->len != len)
goto next;
if (memcmp(qstr->name, str, len))
goto next;
if (d_unhashed(expiring)) {
dget_dlock(expiring);
spin_unlock(&expiring->d_lock);
spin_unlock(&sbi->lookup_lock);
return expiring;
}
next:
spin_unlock(&expiring->d_lock);
}
spin_unlock(&sbi->lookup_lock);
return NULL;
}
static int autofs4_mount_wait(struct dentry *dentry)
{
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
int status = 0;
if (ino->flags & AUTOFS_INF_PENDING) {
DPRINTK("waiting for mount name=%.*s",
dentry->d_name.len, dentry->d_name.name);
status = autofs4_wait(sbi, dentry, NFY_MOUNT);
DPRINTK("mount wait done status=%d", status);
}
ino->last_used = jiffies;
return status;
}
static int do_expire_wait(struct dentry *dentry)
{
struct dentry *expiring;
expiring = autofs4_lookup_expiring(dentry);
if (!expiring)
return autofs4_expire_wait(dentry);
else {
/*
* If we are racing with expire the request might not
* be quite complete, but the directory has been removed
* so it must have been successful, just wait for it.
*/
autofs4_expire_wait(expiring);
autofs4_del_expiring(expiring);
dput(expiring);
}
return 0;
}
static struct dentry *autofs4_mountpoint_changed(struct path *path)
{
struct dentry *dentry = path->dentry;
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
/*
* If this is an indirect mount the dentry could have gone away
* as a result of an expire and a new one created.
*/
if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
struct dentry *parent = dentry->d_parent;
struct autofs_info *ino;
struct dentry *new = d_lookup(parent, &dentry->d_name);
if (!new)
return NULL;
ino = autofs4_dentry_ino(new);
ino->last_used = jiffies;
dput(path->dentry);
path->dentry = new;
}
return path->dentry;
}
static struct vfsmount *autofs4_d_automount(struct path *path)
{
struct dentry *dentry = path->dentry;
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
int status;
DPRINTK("dentry=%p %.*s",
dentry, dentry->d_name.len, dentry->d_name.name);
/* The daemon never triggers a mount. */
if (autofs4_oz_mode(sbi))
return NULL;
/*
* If an expire request is pending everyone must wait.
* If the expire fails we're still mounted so continue
* the follow and return. A return of -EAGAIN (which only
* happens with indirect mounts) means the expire completed
* and the directory was removed, so just go ahead and try
* the mount.
*/
status = do_expire_wait(dentry);
if (status && status != -EAGAIN)
return NULL;
/* Callback to the daemon to perform the mount or wait */
spin_lock(&sbi->fs_lock);
if (ino->flags & AUTOFS_INF_PENDING) {
spin_unlock(&sbi->fs_lock);
status = autofs4_mount_wait(dentry);
if (status)
return ERR_PTR(status);
spin_lock(&sbi->fs_lock);
goto done;
}
/*
* If the dentry is a symlink it's equivalent to a directory
* having d_mountpoint() true, so there's no need to call back
* to the daemon.
*/
if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode))
goto done;
if (!d_mountpoint(dentry)) {
/*
* It's possible that user space hasn't removed directories
* after umounting a rootless multi-mount, although it
* should. For v5 have_submounts() is sufficient to handle
* this because the leaves of the directory tree under the
* mount never trigger mounts themselves (they have an autofs
* trigger mount mounted on them). But v4 pseudo direct mounts
* do need the leaves to to trigger mounts. In this case we
* have no choice but to use the list_empty() check and
* require user space behave.
*/
if (sbi->version > 4) {
if (have_submounts(dentry))
goto done;
} else {
spin_lock(&dentry->d_lock);
if (!list_empty(&dentry->d_subdirs)) {
spin_unlock(&dentry->d_lock);
goto done;
}
spin_unlock(&dentry->d_lock);
}
ino->flags |= AUTOFS_INF_PENDING;
spin_unlock(&sbi->fs_lock);
status = autofs4_mount_wait(dentry);
if (status)
return ERR_PTR(status);
spin_lock(&sbi->fs_lock);
ino->flags &= ~AUTOFS_INF_PENDING;
}
done:
if (!(ino->flags & AUTOFS_INF_EXPIRING)) {
/*
* Any needed mounting has been completed and the path
* updated so clear DCACHE_NEED_AUTOMOUNT so we don't
* call ->d_automount() on rootless multi-mounts since
* it can lead to an incorrect ELOOP error return.
*
* Only clear DMANAGED_AUTOMOUNT for rootless multi-mounts and
* symlinks as in all other cases the dentry will be covered by
* an actual mount so ->d_automount() won't be called during
* the follow.
*/
spin_lock(&dentry->d_lock);
if ((!d_mountpoint(dentry) &&
!list_empty(&dentry->d_subdirs)) ||
(dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)))
__managed_dentry_clear_automount(dentry);
spin_unlock(&dentry->d_lock);
}
spin_unlock(&sbi->fs_lock);
/* Mount succeeded, check if we ended up with a new dentry */
dentry = autofs4_mountpoint_changed(path);
if (!dentry)
return ERR_PTR(-ENOENT);
return NULL;
}
int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
{
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
DPRINTK("dentry=%p %.*s",
dentry, dentry->d_name.len, dentry->d_name.name);
/* The daemon never waits. */
if (autofs4_oz_mode(sbi)) {
if (rcu_walk)
return 0;
if (!d_mountpoint(dentry))
return -EISDIR;
return 0;
}
/* We need to sleep, so we need pathwalk to be in ref-mode */
if (rcu_walk)
return -ECHILD;
/* Wait for pending expires */
do_expire_wait(dentry);
/*
* This dentry may be under construction so wait on mount
* completion.
*/
return autofs4_mount_wait(dentry);
}
/* Lookups in the root directory */
static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
{
struct autofs_sb_info *sbi;
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
struct autofs_info *ino;
struct dentry *active;
DPRINTK("name = %.*s", dentry->d_name.len, dentry->d_name.name);
/* File name too long to exist */
if (dentry->d_name.len > NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
sbi = autofs4_sbi(dir->i_sb);
DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d",
current->pid, task_pgrp_nr(current), sbi->catatonic,
autofs4_oz_mode(sbi));
active = autofs4_lookup_active(dentry);
if (active) {
return active;
} else {
/*
* A dentry that is not within the root can never trigger a
* mount operation, unless the directory already exists, so we
* can return fail immediately. The daemon however does need
* to create directories within the file system.
*/
if (!autofs4_oz_mode(sbi) && !IS_ROOT(dentry->d_parent))
return ERR_PTR(-ENOENT);
/* Mark entries in the root as mount triggers */
if (autofs_type_indirect(sbi->type) && IS_ROOT(dentry->d_parent))
__managed_dentry_set_managed(dentry);
ino = autofs4_new_ino(sbi);
if (!ino)
return ERR_PTR(-ENOMEM);
dentry->d_fsdata = ino;
ino->dentry = dentry;
autofs4_add_active(dentry);
d_instantiate(dentry, NULL);
}
return NULL;
}
static int autofs4_dir_symlink(struct inode *dir,
struct dentry *dentry,
const char *symname)
{
struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
struct autofs_info *p_ino;
struct inode *inode;
size_t size = strlen(symname);
char *cp;
DPRINTK("%s <- %.*s", symname,
dentry->d_name.len, dentry->d_name.name);
if (!autofs4_oz_mode(sbi))
return -EACCES;
BUG_ON(!ino);
autofs4_clean_ino(ino);
autofs4_del_active(dentry);
cp = kmalloc(size + 1, GFP_KERNEL);
if (!cp)
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
return -ENOMEM;
strcpy(cp, symname);
inode = autofs4_get_inode(dir->i_sb, S_IFLNK | 0555);
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
if (!inode) {
kfree(cp);
if (!dentry->d_fsdata)
kfree(ino);
return -ENOMEM;
}
inode->i_private = cp;
inode->i_size = size;
d_add(dentry, inode);
dget(dentry);
atomic_inc(&ino->count);
p_ino = autofs4_dentry_ino(dentry->d_parent);
if (p_ino && dentry->d_parent != dentry)
atomic_inc(&p_ino->count);
dir->i_mtime = CURRENT_TIME;
return 0;
}
/*
* NOTE!
*
* Normal filesystems would do a "d_delete()" to tell the VFS dcache
* that the file no longer exists. However, doing that means that the
* VFS layer can turn the dentry into a negative dentry. We don't want
* this, because the unlink is probably the result of an expire.
* We simply d_drop it and add it to a expiring list in the super block,
* which allows the dentry lookup to check for an incomplete expire.
*
* If a process is blocked on the dentry waiting for the expire to finish,
* it will invalidate the dentry and try to mount with a new one.
*
* Also see autofs4_dir_rmdir()..
*/
static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
{
struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
struct autofs_info *p_ino;
/* This allows root to remove symlinks */
if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
return -EACCES;
if (atomic_dec_and_test(&ino->count)) {
p_ino = autofs4_dentry_ino(dentry->d_parent);
if (p_ino && dentry->d_parent != dentry)
atomic_dec(&p_ino->count);
}
dput(ino->dentry);
dentry->d_inode->i_size = 0;
clear_nlink(dentry->d_inode);
dir->i_mtime = CURRENT_TIME;
spin_lock(&sbi->lookup_lock);
__autofs4_add_expiring(dentry);
spin_lock(&dentry->d_lock);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&sbi->lookup_lock);
return 0;
}
/*
* Version 4 of autofs provides a pseudo direct mount implementation
* that relies on directories at the leaves of a directory tree under
* an indirect mount to trigger mounts. To allow for this we need to
* set the DMANAGED_AUTOMOUNT and DMANAGED_TRANSIT flags on the leaves
* of the directory tree. There is no need to clear the automount flag
* following a mount or restore it after an expire because these mounts
* are always covered. However, it is necessary to ensure that these
* flags are clear on non-empty directories to avoid unnecessary calls
* during path walks.
*/
static void autofs_set_leaf_automount_flags(struct dentry *dentry)
{
struct dentry *parent;
/* root and dentrys in the root are already handled */
if (IS_ROOT(dentry->d_parent))
return;
managed_dentry_set_managed(dentry);
parent = dentry->d_parent;
/* only consider parents below dentrys in the root */
if (IS_ROOT(parent->d_parent))
return;
managed_dentry_clear_managed(parent);
return;
}
static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
{
struct list_head *d_child;
struct dentry *parent;
/* flags for dentrys in the root are handled elsewhere */
if (IS_ROOT(dentry->d_parent))
return;
managed_dentry_clear_managed(dentry);
parent = dentry->d_parent;
/* only consider parents below dentrys in the root */
if (IS_ROOT(parent->d_parent))
return;
d_child = &dentry->d_u.d_child;
/* Set parent managed if it's becoming empty */
if (d_child->next == &parent->d_subdirs &&
d_child->prev == &parent->d_subdirs)
managed_dentry_set_managed(parent);
return;
}
static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
{
struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
struct autofs_info *p_ino;
DPRINTK("dentry %p, removing %.*s",
dentry, dentry->d_name.len, dentry->d_name.name);
if (!autofs4_oz_mode(sbi))
return -EACCES;
spin_lock(&sbi->lookup_lock);
spin_lock(&dentry->d_lock);
if (!list_empty(&dentry->d_subdirs)) {
spin_unlock(&dentry->d_lock);
spin_unlock(&sbi->lookup_lock);
return -ENOTEMPTY;
}
__autofs4_add_expiring(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&sbi->lookup_lock);
if (sbi->version < 5)
autofs_clear_leaf_automount_flags(dentry);
if (atomic_dec_and_test(&ino->count)) {
p_ino = autofs4_dentry_ino(dentry->d_parent);
if (p_ino && dentry->d_parent != dentry)
atomic_dec(&p_ino->count);
}
dput(ino->dentry);
dentry->d_inode->i_size = 0;
clear_nlink(dentry->d_inode);
if (dir->i_nlink)
drop_nlink(dir);
return 0;
}
static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
struct autofs_info *p_ino;
struct inode *inode;
if (!autofs4_oz_mode(sbi))
return -EACCES;
DPRINTK("dentry %p, creating %.*s",
dentry, dentry->d_name.len, dentry->d_name.name);
BUG_ON(!ino);
autofs4_clean_ino(ino);
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
autofs4_del_active(dentry);
inode = autofs4_get_inode(dir->i_sb, S_IFDIR | 0555);
if (!inode)
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
return -ENOMEM;
d_add(dentry, inode);
if (sbi->version < 5)
autofs_set_leaf_automount_flags(dentry);
dget(dentry);
atomic_inc(&ino->count);
p_ino = autofs4_dentry_ino(dentry->d_parent);
if (p_ino && dentry->d_parent != dentry)
atomic_inc(&p_ino->count);
inc_nlink(dir);
dir->i_mtime = CURRENT_TIME;
return 0;
}
/* Get/set timeout ioctl() operation */
#ifdef CONFIG_COMPAT
static inline int autofs4_compat_get_set_timeout(struct autofs_sb_info *sbi,
compat_ulong_t __user *p)
{
int rv;
unsigned long ntimeout;
if ((rv = get_user(ntimeout, p)) ||
(rv = put_user(sbi->exp_timeout/HZ, p)))
return rv;
if (ntimeout > UINT_MAX/HZ)
sbi->exp_timeout = 0;
else
sbi->exp_timeout = ntimeout * HZ;
return 0;
}
#endif
static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi,
unsigned long __user *p)
{
int rv;
unsigned long ntimeout;
if ((rv = get_user(ntimeout, p)) ||
(rv = put_user(sbi->exp_timeout/HZ, p)))
return rv;
if (ntimeout > ULONG_MAX/HZ)
sbi->exp_timeout = 0;
else
sbi->exp_timeout = ntimeout * HZ;
return 0;
}
/* Return protocol version */
static inline int autofs4_get_protover(struct autofs_sb_info *sbi, int __user *p)
{
return put_user(sbi->version, p);
}
/* Return protocol sub version */
static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi, int __user *p)
{
return put_user(sbi->sub_version, p);
}
/*
* Tells the daemon whether it can umount the autofs mount.
*/
static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
{
int status = 0;
if (may_umount(mnt))
status = 1;
DPRINTK("returning %d", status);
status = put_user(status, p);
return status;
}
/* Identify autofs4_dentries - this is so we can tell if there's
an extra dentry refcount or not. We only hold a refcount on the
dentry if its non-negative (ie, d_inode != NULL)
*/
int is_autofs4_dentry(struct dentry *dentry)
{
return dentry && dentry->d_inode &&
dentry->d_op == &autofs4_dentry_operations &&
dentry->d_fsdata != NULL;
}
/*
* ioctl()'s on the root directory is the chief method for the daemon to
* generate kernel reactions
*/
static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp,
unsigned int cmd, unsigned long arg)
{
struct autofs_sb_info *sbi = autofs4_sbi(inode->i_sb);
void __user *p = (void __user *)arg;
DPRINTK("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u",
cmd,arg,sbi,task_pgrp_nr(current));
if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
_IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT)
return -ENOTTY;
if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
return -EPERM;
switch(cmd) {
case AUTOFS_IOC_READY: /* Wait queue: go ahead and retry */
return autofs4_wait_release(sbi,(autofs_wqt_t)arg,0);
case AUTOFS_IOC_FAIL: /* Wait queue: fail with ENOENT */
return autofs4_wait_release(sbi,(autofs_wqt_t)arg,-ENOENT);
case AUTOFS_IOC_CATATONIC: /* Enter catatonic mode (daemon shutdown) */
autofs4_catatonic_mode(sbi);
return 0;
case AUTOFS_IOC_PROTOVER: /* Get protocol version */
return autofs4_get_protover(sbi, p);
case AUTOFS_IOC_PROTOSUBVER: /* Get protocol sub version */
return autofs4_get_protosubver(sbi, p);
case AUTOFS_IOC_SETTIMEOUT:
return autofs4_get_set_timeout(sbi, p);
#ifdef CONFIG_COMPAT
case AUTOFS_IOC_SETTIMEOUT32:
return autofs4_compat_get_set_timeout(sbi, p);
#endif
case AUTOFS_IOC_ASKUMOUNT:
return autofs4_ask_umount(filp->f_path.mnt, p);
/* return a single thing to expire */
case AUTOFS_IOC_EXPIRE:
return autofs4_expire_run(inode->i_sb,filp->f_path.mnt,sbi, p);
/* same as above, but can send multiple expires through pipe */
case AUTOFS_IOC_EXPIRE_MULTI:
return autofs4_expire_multi(inode->i_sb,filp->f_path.mnt,sbi, p);
default:
return -ENOSYS;
}
}
static long autofs4_root_ioctl(struct file *filp,
unsigned int cmd, unsigned long arg)
{
struct inode *inode = filp->f_dentry->d_inode;
return autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
}
#ifdef CONFIG_COMPAT
static long autofs4_root_compat_ioctl(struct file *filp,
unsigned int cmd, unsigned long arg)
{
struct inode *inode = filp->f_path.dentry->d_inode;
int ret;
if (cmd == AUTOFS_IOC_READY || cmd == AUTOFS_IOC_FAIL)
ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
else
ret = autofs4_root_ioctl_unlocked(inode, filp, cmd,
(unsigned long)compat_ptr(arg));
return ret;
}
#endif