OpenCloudOS-Kernel/fs/nilfs2/ioctl.c

1339 lines
35 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0+
/*
* NILFS ioctl operations.
*
* Copyright (C) 2007, 2008 Nippon Telegraph and Telephone Corporation.
*
* Written by Koji Sato.
*/
#include <linux/fs.h>
#include <linux/wait.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/capability.h> /* capable() */
#include <linux/uaccess.h> /* copy_from_user(), copy_to_user() */
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
#include <linux/vmalloc.h>
#include <linux/compat.h> /* compat_ptr() */
#include <linux/mount.h> /* mnt_want_write_file(), mnt_drop_write_file() */
#include <linux/buffer_head.h>
#include <linux/fileattr.h>
#include "nilfs.h"
#include "segment.h"
#include "bmap.h"
#include "cpfile.h"
#include "sufile.h"
#include "dat.h"
/**
* nilfs_ioctl_wrap_copy - wrapping function of get/set metadata info
* @nilfs: nilfs object
* @argv: vector of arguments from userspace
* @dir: set of direction flags
* @dofunc: concrete function of get/set metadata info
*
* Description: nilfs_ioctl_wrap_copy() gets/sets metadata info by means of
* calling dofunc() function on the basis of @argv argument.
*
* Return Value: On success, 0 is returned and requested metadata info
* is copied into userspace. On error, one of the following
* negative error codes is returned.
*
* %-EINVAL - Invalid arguments from userspace.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-EFAULT - Failure during execution of requested operation.
*/
static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
struct nilfs_argv *argv, int dir,
ssize_t (*dofunc)(struct the_nilfs *,
__u64 *, int,
void *, size_t, size_t))
{
void *buf;
void __user *base = (void __user *)(unsigned long)argv->v_base;
nilfs2: fix problems of memory allocation in ioctl This is another patch for fixing the following problems of a memory copy function in nilfs2 ioctl: (1) It tries to allocate 128KB size of memory even for small objects. (2) Though the function repeatedly tries large memory allocations while reducing the size, GFP_NOWAIT flag is not specified. This increases the possibility of system memory shortage. (3) During the retries of (2), verbose warnings are printed because _GFP_NOWARN flag is not used for the kmalloc calls. The first patch was still doing large allocations by kmalloc which are repeatedly tried while reducing the size. Andi Kleen told me that using copy_from_user for large memory is not good from the viewpoint of preempt latency: On Fri, 12 Dec 2008 21:24:11 +0100, Andi Kleen <andi@firstfloor.org> wrote: > > In the current interface, each data item is copied twice: one is to > > the allocated memory from user space (via copy_from_user), and another > > For such large copies it is better to use multiple smaller (e.g. 4K) > copy user, that gives better real time preempt latencies. Each cfu has a > cond_resched(), but only one, not multiple times in the inner loop. He also advised me that: On Sun, 14 Dec 2008 16:13:27 +0100, Andi Kleen <andi@firstfloor.org> wrote: > Better would be if you could go to PAGE_SIZE. order 0 allocations > are typically the fastest / least likely to stall. > > Also in this case it's a good idea to use __get_free_pages() > directly, kmalloc tends to be become less efficient at larger > sizes. For the function in question, the size of buffer memory can be reduced since the buffer is repeatedly used for a number of small objects. On the other hand, it may incur large preempt latencies for larger buffer because a copy_from_user (and a copy_to_user) was applied only once each cycle. With that, this revision uses the order 0 allocations with __get_free_pages() to fix the original problems. Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-07 10:01:43 +08:00
size_t maxmembs, total, n;
ssize_t nr;
int ret, i;
__u64 pos, ppos;
if (argv->v_nmembs == 0)
return 0;
nilfs2: fix problems of memory allocation in ioctl This is another patch for fixing the following problems of a memory copy function in nilfs2 ioctl: (1) It tries to allocate 128KB size of memory even for small objects. (2) Though the function repeatedly tries large memory allocations while reducing the size, GFP_NOWAIT flag is not specified. This increases the possibility of system memory shortage. (3) During the retries of (2), verbose warnings are printed because _GFP_NOWARN flag is not used for the kmalloc calls. The first patch was still doing large allocations by kmalloc which are repeatedly tried while reducing the size. Andi Kleen told me that using copy_from_user for large memory is not good from the viewpoint of preempt latency: On Fri, 12 Dec 2008 21:24:11 +0100, Andi Kleen <andi@firstfloor.org> wrote: > > In the current interface, each data item is copied twice: one is to > > the allocated memory from user space (via copy_from_user), and another > > For such large copies it is better to use multiple smaller (e.g. 4K) > copy user, that gives better real time preempt latencies. Each cfu has a > cond_resched(), but only one, not multiple times in the inner loop. He also advised me that: On Sun, 14 Dec 2008 16:13:27 +0100, Andi Kleen <andi@firstfloor.org> wrote: > Better would be if you could go to PAGE_SIZE. order 0 allocations > are typically the fastest / least likely to stall. > > Also in this case it's a good idea to use __get_free_pages() > directly, kmalloc tends to be become less efficient at larger > sizes. For the function in question, the size of buffer memory can be reduced since the buffer is repeatedly used for a number of small objects. On the other hand, it may incur large preempt latencies for larger buffer because a copy_from_user (and a copy_to_user) was applied only once each cycle. With that, this revision uses the order 0 allocations with __get_free_pages() to fix the original problems. Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-07 10:01:43 +08:00
if (argv->v_size > PAGE_SIZE)
return -EINVAL;
/*
* Reject pairs of a start item position (argv->v_index) and a
* total count (argv->v_nmembs) which leads position 'pos' to
* overflow by the increment at the end of the loop.
*/
if (argv->v_index > ~(__u64)0 - argv->v_nmembs)
return -EINVAL;
nilfs2: fix problems of memory allocation in ioctl This is another patch for fixing the following problems of a memory copy function in nilfs2 ioctl: (1) It tries to allocate 128KB size of memory even for small objects. (2) Though the function repeatedly tries large memory allocations while reducing the size, GFP_NOWAIT flag is not specified. This increases the possibility of system memory shortage. (3) During the retries of (2), verbose warnings are printed because _GFP_NOWARN flag is not used for the kmalloc calls. The first patch was still doing large allocations by kmalloc which are repeatedly tried while reducing the size. Andi Kleen told me that using copy_from_user for large memory is not good from the viewpoint of preempt latency: On Fri, 12 Dec 2008 21:24:11 +0100, Andi Kleen <andi@firstfloor.org> wrote: > > In the current interface, each data item is copied twice: one is to > > the allocated memory from user space (via copy_from_user), and another > > For such large copies it is better to use multiple smaller (e.g. 4K) > copy user, that gives better real time preempt latencies. Each cfu has a > cond_resched(), but only one, not multiple times in the inner loop. He also advised me that: On Sun, 14 Dec 2008 16:13:27 +0100, Andi Kleen <andi@firstfloor.org> wrote: > Better would be if you could go to PAGE_SIZE. order 0 allocations > are typically the fastest / least likely to stall. > > Also in this case it's a good idea to use __get_free_pages() > directly, kmalloc tends to be become less efficient at larger > sizes. For the function in question, the size of buffer memory can be reduced since the buffer is repeatedly used for a number of small objects. On the other hand, it may incur large preempt latencies for larger buffer because a copy_from_user (and a copy_to_user) was applied only once each cycle. With that, this revision uses the order 0 allocations with __get_free_pages() to fix the original problems. Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-07 10:01:43 +08:00
buf = (void *)__get_free_pages(GFP_NOFS, 0);
if (unlikely(!buf))
return -ENOMEM;
nilfs2: fix problems of memory allocation in ioctl This is another patch for fixing the following problems of a memory copy function in nilfs2 ioctl: (1) It tries to allocate 128KB size of memory even for small objects. (2) Though the function repeatedly tries large memory allocations while reducing the size, GFP_NOWAIT flag is not specified. This increases the possibility of system memory shortage. (3) During the retries of (2), verbose warnings are printed because _GFP_NOWARN flag is not used for the kmalloc calls. The first patch was still doing large allocations by kmalloc which are repeatedly tried while reducing the size. Andi Kleen told me that using copy_from_user for large memory is not good from the viewpoint of preempt latency: On Fri, 12 Dec 2008 21:24:11 +0100, Andi Kleen <andi@firstfloor.org> wrote: > > In the current interface, each data item is copied twice: one is to > > the allocated memory from user space (via copy_from_user), and another > > For such large copies it is better to use multiple smaller (e.g. 4K) > copy user, that gives better real time preempt latencies. Each cfu has a > cond_resched(), but only one, not multiple times in the inner loop. He also advised me that: On Sun, 14 Dec 2008 16:13:27 +0100, Andi Kleen <andi@firstfloor.org> wrote: > Better would be if you could go to PAGE_SIZE. order 0 allocations > are typically the fastest / least likely to stall. > > Also in this case it's a good idea to use __get_free_pages() > directly, kmalloc tends to be become less efficient at larger > sizes. For the function in question, the size of buffer memory can be reduced since the buffer is repeatedly used for a number of small objects. On the other hand, it may incur large preempt latencies for larger buffer because a copy_from_user (and a copy_to_user) was applied only once each cycle. With that, this revision uses the order 0 allocations with __get_free_pages() to fix the original problems. Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-07 10:01:43 +08:00
maxmembs = PAGE_SIZE / argv->v_size;
ret = 0;
total = 0;
pos = argv->v_index;
for (i = 0; i < argv->v_nmembs; i += n) {
n = (argv->v_nmembs - i < maxmembs) ?
argv->v_nmembs - i : maxmembs;
if ((dir & _IOC_WRITE) &&
copy_from_user(buf, base + argv->v_size * i,
argv->v_size * n)) {
ret = -EFAULT;
break;
}
ppos = pos;
nr = dofunc(nilfs, &pos, argv->v_flags, buf, argv->v_size,
n);
if (nr < 0) {
ret = nr;
break;
}
if ((dir & _IOC_READ) &&
copy_to_user(base + argv->v_size * i, buf,
argv->v_size * nr)) {
ret = -EFAULT;
break;
}
total += nr;
if ((size_t)nr < n)
break;
if (pos == ppos)
pos += n;
}
argv->v_nmembs = total;
nilfs2: fix problems of memory allocation in ioctl This is another patch for fixing the following problems of a memory copy function in nilfs2 ioctl: (1) It tries to allocate 128KB size of memory even for small objects. (2) Though the function repeatedly tries large memory allocations while reducing the size, GFP_NOWAIT flag is not specified. This increases the possibility of system memory shortage. (3) During the retries of (2), verbose warnings are printed because _GFP_NOWARN flag is not used for the kmalloc calls. The first patch was still doing large allocations by kmalloc which are repeatedly tried while reducing the size. Andi Kleen told me that using copy_from_user for large memory is not good from the viewpoint of preempt latency: On Fri, 12 Dec 2008 21:24:11 +0100, Andi Kleen <andi@firstfloor.org> wrote: > > In the current interface, each data item is copied twice: one is to > > the allocated memory from user space (via copy_from_user), and another > > For such large copies it is better to use multiple smaller (e.g. 4K) > copy user, that gives better real time preempt latencies. Each cfu has a > cond_resched(), but only one, not multiple times in the inner loop. He also advised me that: On Sun, 14 Dec 2008 16:13:27 +0100, Andi Kleen <andi@firstfloor.org> wrote: > Better would be if you could go to PAGE_SIZE. order 0 allocations > are typically the fastest / least likely to stall. > > Also in this case it's a good idea to use __get_free_pages() > directly, kmalloc tends to be become less efficient at larger > sizes. For the function in question, the size of buffer memory can be reduced since the buffer is repeatedly used for a number of small objects. On the other hand, it may incur large preempt latencies for larger buffer because a copy_from_user (and a copy_to_user) was applied only once each cycle. With that, this revision uses the order 0 allocations with __get_free_pages() to fix the original problems. Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-07 10:01:43 +08:00
free_pages((unsigned long)buf, 0);
return ret;
}
/**
* nilfs_fileattr_get - ioctl to support lsattr
*/
int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
struct inode *inode = d_inode(dentry);
fileattr_fill_flags(fa, NILFS_I(inode)->i_flags & FS_FL_USER_VISIBLE);
return 0;
}
/**
* nilfs_fileattr_set - ioctl to support chattr
*/
int nilfs_fileattr_set(struct user_namespace *mnt_userns,
struct dentry *dentry, struct fileattr *fa)
{
struct inode *inode = d_inode(dentry);
struct nilfs_transaction_info ti;
unsigned int flags, oldflags;
int ret;
if (fileattr_has_fsx(fa))
return -EOPNOTSUPP;
flags = nilfs_mask_flags(inode->i_mode, fa->flags);
ret = nilfs_transaction_begin(inode->i_sb, &ti, 0);
if (ret)
return ret;
oldflags = NILFS_I(inode)->i_flags & ~FS_FL_USER_MODIFIABLE;
NILFS_I(inode)->i_flags = oldflags | (flags & FS_FL_USER_MODIFIABLE);
nilfs_set_inode_flags(inode);
inode->i_ctime = current_time(inode);
if (IS_SYNC(inode))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
nilfs_mark_inode_dirty(inode);
return nilfs_transaction_commit(inode->i_sb);
}
/**
* nilfs_ioctl_getversion - get info about a file's version (generation number)
*/
static int nilfs_ioctl_getversion(struct inode *inode, void __user *argp)
{
return put_user(inode->i_generation, (int __user *)argp);
}
/**
* nilfs_ioctl_change_cpmode - change checkpoint mode (checkpoint/snapshot)
* @inode: inode object
* @filp: file object
* @cmd: ioctl's request code
* @argp: pointer on argument from userspace
*
* Description: nilfs_ioctl_change_cpmode() function changes mode of
* given checkpoint between checkpoint and snapshot state. This ioctl
* is used in chcp and mkcp utilities.
*
* Return Value: On success, 0 is returned and mode of a checkpoint is
* changed. On error, one of the following negative error codes
* is returned.
*
* %-EPERM - Operation not permitted.
*
* %-EFAULT - Failure during checkpoint mode changing.
*/
static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
struct nilfs_transaction_info ti;
struct nilfs_cpmode cpmode;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
ret = -EFAULT;
if (copy_from_user(&cpmode, argp, sizeof(cpmode)))
goto out;
nilfs2: fix deadlock issue between chcp and thaw ioctls An fs-thaw ioctl causes deadlock with a chcp or mkcp -s command: chcp D ffff88013870f3d0 0 1325 1324 0x00000004 ... Call Trace: nilfs_transaction_begin+0x11c/0x1a0 [nilfs2] wake_up_bit+0x20/0x20 copy_from_user+0x18/0x30 [nilfs2] nilfs_ioctl_change_cpmode+0x7d/0xcf [nilfs2] nilfs_ioctl+0x252/0x61a [nilfs2] do_page_fault+0x311/0x34c get_unmapped_area+0x132/0x14e do_vfs_ioctl+0x44b/0x490 __set_task_blocked+0x5a/0x61 vm_mmap_pgoff+0x76/0x87 __set_current_blocked+0x30/0x4a sys_ioctl+0x4b/0x6f system_call_fastpath+0x16/0x1b thaw D ffff88013870d890 0 1352 1351 0x00000004 ... Call Trace: rwsem_down_failed_common+0xdb/0x10f call_rwsem_down_write_failed+0x13/0x20 down_write+0x25/0x27 thaw_super+0x13/0x9e do_vfs_ioctl+0x1f5/0x490 vm_mmap_pgoff+0x76/0x87 sys_ioctl+0x4b/0x6f filp_close+0x64/0x6c system_call_fastpath+0x16/0x1b where the thaw ioctl deadlocked at thaw_super() when called while chcp was waiting at nilfs_transaction_begin() called from nilfs_ioctl_change_cpmode(). This deadlock is 100% reproducible. This is because nilfs_ioctl_change_cpmode() first locks sb->s_umount in read mode and then waits for unfreezing in nilfs_transaction_begin(), whereas thaw_super() locks sb->s_umount in write mode. The locking of sb->s_umount here was intended to make snapshot mounts and the downgrade of snapshots to checkpoints exclusive. This fixes the deadlock issue by replacing the sb->s_umount usage in nilfs_ioctl_change_cpmode() with a dedicated mutex which protects snapshot mounts. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Cc: Fernando Luis Vazquez Cao <fernando@oss.ntt.co.jp> Tested-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 05:42:07 +08:00
mutex_lock(&nilfs->ns_snapshot_mount_mutex);
nilfs_transaction_begin(inode->i_sb, &ti, 0);
ret = nilfs_cpfile_change_cpmode(
nilfs->ns_cpfile, cpmode.cm_cno, cpmode.cm_mode);
if (unlikely(ret < 0))
nilfs_transaction_abort(inode->i_sb);
else
nilfs_transaction_commit(inode->i_sb); /* never fails */
nilfs2: fix deadlock issue between chcp and thaw ioctls An fs-thaw ioctl causes deadlock with a chcp or mkcp -s command: chcp D ffff88013870f3d0 0 1325 1324 0x00000004 ... Call Trace: nilfs_transaction_begin+0x11c/0x1a0 [nilfs2] wake_up_bit+0x20/0x20 copy_from_user+0x18/0x30 [nilfs2] nilfs_ioctl_change_cpmode+0x7d/0xcf [nilfs2] nilfs_ioctl+0x252/0x61a [nilfs2] do_page_fault+0x311/0x34c get_unmapped_area+0x132/0x14e do_vfs_ioctl+0x44b/0x490 __set_task_blocked+0x5a/0x61 vm_mmap_pgoff+0x76/0x87 __set_current_blocked+0x30/0x4a sys_ioctl+0x4b/0x6f system_call_fastpath+0x16/0x1b thaw D ffff88013870d890 0 1352 1351 0x00000004 ... Call Trace: rwsem_down_failed_common+0xdb/0x10f call_rwsem_down_write_failed+0x13/0x20 down_write+0x25/0x27 thaw_super+0x13/0x9e do_vfs_ioctl+0x1f5/0x490 vm_mmap_pgoff+0x76/0x87 sys_ioctl+0x4b/0x6f filp_close+0x64/0x6c system_call_fastpath+0x16/0x1b where the thaw ioctl deadlocked at thaw_super() when called while chcp was waiting at nilfs_transaction_begin() called from nilfs_ioctl_change_cpmode(). This deadlock is 100% reproducible. This is because nilfs_ioctl_change_cpmode() first locks sb->s_umount in read mode and then waits for unfreezing in nilfs_transaction_begin(), whereas thaw_super() locks sb->s_umount in write mode. The locking of sb->s_umount here was intended to make snapshot mounts and the downgrade of snapshots to checkpoints exclusive. This fixes the deadlock issue by replacing the sb->s_umount usage in nilfs_ioctl_change_cpmode() with a dedicated mutex which protects snapshot mounts. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Cc: Fernando Luis Vazquez Cao <fernando@oss.ntt.co.jp> Tested-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 05:42:07 +08:00
mutex_unlock(&nilfs->ns_snapshot_mount_mutex);
out:
mnt_drop_write_file(filp);
return ret;
}
/**
* nilfs_ioctl_delete_checkpoint - remove checkpoint
* @inode: inode object
* @filp: file object
* @cmd: ioctl's request code
* @argp: pointer on argument from userspace
*
* Description: nilfs_ioctl_delete_checkpoint() function removes
* checkpoint from NILFS2 file system. This ioctl is used in rmcp
* utility.
*
* Return Value: On success, 0 is returned and a checkpoint is
* removed. On error, one of the following negative error codes
* is returned.
*
* %-EPERM - Operation not permitted.
*
* %-EFAULT - Failure during checkpoint removing.
*/
static int
nilfs_ioctl_delete_checkpoint(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
struct nilfs_transaction_info ti;
__u64 cno;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
ret = -EFAULT;
if (copy_from_user(&cno, argp, sizeof(cno)))
goto out;
nilfs_transaction_begin(inode->i_sb, &ti, 0);
ret = nilfs_cpfile_delete_checkpoint(nilfs->ns_cpfile, cno);
if (unlikely(ret < 0))
nilfs_transaction_abort(inode->i_sb);
else
nilfs_transaction_commit(inode->i_sb); /* never fails */
out:
mnt_drop_write_file(filp);
return ret;
}
/**
* nilfs_ioctl_do_get_cpinfo - callback method getting info about checkpoints
* @nilfs: nilfs object
* @posp: pointer on array of checkpoint's numbers
* @flags: checkpoint mode (checkpoint or snapshot)
* @buf: buffer for storing checkponts' info
* @size: size in bytes of one checkpoint info item in array
* @nmembs: number of checkpoints in array (numbers and infos)
*
* Description: nilfs_ioctl_do_get_cpinfo() function returns info about
* requested checkpoints. The NILFS_IOCTL_GET_CPINFO ioctl is used in
* lscp utility and by nilfs_cleanerd daemon.
*
* Return value: count of nilfs_cpinfo structures in output buffer.
*/
static ssize_t
nilfs_ioctl_do_get_cpinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
void *buf, size_t size, size_t nmembs)
{
int ret;
down_read(&nilfs->ns_segctor_sem);
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
ret = nilfs_cpfile_get_cpinfo(nilfs->ns_cpfile, posp, flags, buf,
size, nmembs);
up_read(&nilfs->ns_segctor_sem);
return ret;
}
/**
* nilfs_ioctl_get_cpstat - get checkpoints statistics
* @inode: inode object
* @filp: file object
* @cmd: ioctl's request code
* @argp: pointer on argument from userspace
*
* Description: nilfs_ioctl_get_cpstat() returns information about checkpoints.
* The NILFS_IOCTL_GET_CPSTAT ioctl is used by lscp, rmcp utilities
* and by nilfs_cleanerd daemon.
*
* Return Value: On success, 0 is returned, and checkpoints information is
* copied into userspace pointer @argp. On error, one of the following
* negative error codes is returned.
*
* %-EIO - I/O error.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-EFAULT - Failure during getting checkpoints statistics.
*/
static int nilfs_ioctl_get_cpstat(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
struct nilfs_cpstat cpstat;
int ret;
down_read(&nilfs->ns_segctor_sem);
ret = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat);
up_read(&nilfs->ns_segctor_sem);
if (ret < 0)
return ret;
if (copy_to_user(argp, &cpstat, sizeof(cpstat)))
ret = -EFAULT;
return ret;
}
/**
* nilfs_ioctl_do_get_suinfo - callback method getting segment usage info
* @nilfs: nilfs object
* @posp: pointer on array of segment numbers
* @flags: *not used*
* @buf: buffer for storing suinfo array
* @size: size in bytes of one suinfo item in array
* @nmembs: count of segment numbers and suinfos in array
*
* Description: nilfs_ioctl_do_get_suinfo() function returns segment usage
* info about requested segments. The NILFS_IOCTL_GET_SUINFO ioctl is used
* in lssu, nilfs_resize utilities and by nilfs_cleanerd daemon.
*
* Return value: count of nilfs_suinfo structures in output buffer.
*/
static ssize_t
nilfs_ioctl_do_get_suinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
void *buf, size_t size, size_t nmembs)
{
int ret;
down_read(&nilfs->ns_segctor_sem);
ret = nilfs_sufile_get_suinfo(nilfs->ns_sufile, *posp, buf, size,
nmembs);
up_read(&nilfs->ns_segctor_sem);
return ret;
}
/**
* nilfs_ioctl_get_sustat - get segment usage statistics
* @inode: inode object
* @filp: file object
* @cmd: ioctl's request code
* @argp: pointer on argument from userspace
*
* Description: nilfs_ioctl_get_sustat() returns segment usage statistics.
* The NILFS_IOCTL_GET_SUSTAT ioctl is used in lssu, nilfs_resize utilities
* and by nilfs_cleanerd daemon.
*
* Return Value: On success, 0 is returned, and segment usage information is
* copied into userspace pointer @argp. On error, one of the following
* negative error codes is returned.
*
* %-EIO - I/O error.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-EFAULT - Failure during getting segment usage statistics.
*/
static int nilfs_ioctl_get_sustat(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
struct nilfs_sustat sustat;
int ret;
down_read(&nilfs->ns_segctor_sem);
ret = nilfs_sufile_get_stat(nilfs->ns_sufile, &sustat);
up_read(&nilfs->ns_segctor_sem);
if (ret < 0)
return ret;
if (copy_to_user(argp, &sustat, sizeof(sustat)))
ret = -EFAULT;
return ret;
}
/**
* nilfs_ioctl_do_get_vinfo - callback method getting virtual blocks info
* @nilfs: nilfs object
* @posp: *not used*
* @flags: *not used*
* @buf: buffer for storing array of nilfs_vinfo structures
* @size: size in bytes of one vinfo item in array
* @nmembs: count of vinfos in array
*
* Description: nilfs_ioctl_do_get_vinfo() function returns information
* on virtual block addresses. The NILFS_IOCTL_GET_VINFO ioctl is used
* by nilfs_cleanerd daemon.
*
* Return value: count of nilfs_vinfo structures in output buffer.
*/
static ssize_t
nilfs_ioctl_do_get_vinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
void *buf, size_t size, size_t nmembs)
{
int ret;
down_read(&nilfs->ns_segctor_sem);
ret = nilfs_dat_get_vinfo(nilfs->ns_dat, buf, size, nmembs);
up_read(&nilfs->ns_segctor_sem);
return ret;
}
/**
* nilfs_ioctl_do_get_bdescs - callback method getting disk block descriptors
* @nilfs: nilfs object
* @posp: *not used*
* @flags: *not used*
* @buf: buffer for storing array of nilfs_bdesc structures
* @size: size in bytes of one bdesc item in array
* @nmembs: count of bdescs in array
*
* Description: nilfs_ioctl_do_get_bdescs() function returns information
* about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl
* is used by nilfs_cleanerd daemon.
*
* Return value: count of nilfs_bdescs structures in output buffer.
*/
static ssize_t
nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags,
void *buf, size_t size, size_t nmembs)
{
struct nilfs_bmap *bmap = NILFS_I(nilfs->ns_dat)->i_bmap;
struct nilfs_bdesc *bdescs = buf;
int ret, i;
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
down_read(&nilfs->ns_segctor_sem);
for (i = 0; i < nmembs; i++) {
ret = nilfs_bmap_lookup_at_level(bmap,
bdescs[i].bd_offset,
bdescs[i].bd_level + 1,
&bdescs[i].bd_blocknr);
if (ret < 0) {
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
if (ret != -ENOENT) {
up_read(&nilfs->ns_segctor_sem);
return ret;
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
}
bdescs[i].bd_blocknr = 0;
}
}
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
up_read(&nilfs->ns_segctor_sem);
return nmembs;
}
/**
* nilfs_ioctl_get_bdescs - get disk block descriptors
* @inode: inode object
* @filp: file object
* @cmd: ioctl's request code
* @argp: pointer on argument from userspace
*
* Description: nilfs_ioctl_do_get_bdescs() function returns information
* about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl
* is used by nilfs_cleanerd daemon.
*
* Return Value: On success, 0 is returned, and disk block descriptors are
* copied into userspace pointer @argp. On error, one of the following
* negative error codes is returned.
*
* %-EINVAL - Invalid arguments from userspace.
*
* %-EIO - I/O error.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-EFAULT - Failure during getting disk block descriptors.
*/
static int nilfs_ioctl_get_bdescs(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
struct nilfs_argv argv;
int ret;
if (copy_from_user(&argv, argp, sizeof(argv)))
return -EFAULT;
if (argv.v_size != sizeof(struct nilfs_bdesc))
return -EINVAL;
ret = nilfs_ioctl_wrap_copy(nilfs, &argv, _IOC_DIR(cmd),
nilfs_ioctl_do_get_bdescs);
if (ret < 0)
return ret;
if (copy_to_user(argp, &argv, sizeof(argv)))
ret = -EFAULT;
return ret;
}
/**
* nilfs_ioctl_move_inode_block - prepare data/node block for moving by GC
* @inode: inode object
* @vdesc: descriptor of virtual block number
* @buffers: list of moving buffers
*
* Description: nilfs_ioctl_move_inode_block() function registers data/node
* buffer in the GC pagecache and submit read request.
*
* Return Value: On success, 0 is returned. On error, one of the following
* negative error codes is returned.
*
* %-EIO - I/O error.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-ENOENT - Requested block doesn't exist.
*
* %-EEXIST - Blocks conflict is detected.
*/
static int nilfs_ioctl_move_inode_block(struct inode *inode,
struct nilfs_vdesc *vdesc,
struct list_head *buffers)
{
struct buffer_head *bh;
int ret;
if (vdesc->vd_flags == 0)
ret = nilfs_gccache_submit_read_data(
inode, vdesc->vd_offset, vdesc->vd_blocknr,
vdesc->vd_vblocknr, &bh);
else
ret = nilfs_gccache_submit_read_node(
inode, vdesc->vd_blocknr, vdesc->vd_vblocknr, &bh);
if (unlikely(ret < 0)) {
if (ret == -ENOENT)
nilfs_crit(inode->i_sb,
"%s: invalid virtual block address (%s): ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu",
__func__, vdesc->vd_flags ? "node" : "data",
(unsigned long long)vdesc->vd_ino,
(unsigned long long)vdesc->vd_cno,
(unsigned long long)vdesc->vd_offset,
(unsigned long long)vdesc->vd_blocknr,
(unsigned long long)vdesc->vd_vblocknr);
return ret;
}
if (unlikely(!list_empty(&bh->b_assoc_buffers))) {
nilfs_crit(inode->i_sb,
"%s: conflicting %s buffer: ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu",
__func__, vdesc->vd_flags ? "node" : "data",
(unsigned long long)vdesc->vd_ino,
(unsigned long long)vdesc->vd_cno,
(unsigned long long)vdesc->vd_offset,
(unsigned long long)vdesc->vd_blocknr,
(unsigned long long)vdesc->vd_vblocknr);
brelse(bh);
return -EEXIST;
}
list_add_tail(&bh->b_assoc_buffers, buffers);
return 0;
}
/**
* nilfs_ioctl_move_blocks - move valid inode's blocks during garbage collection
* @sb: superblock object
* @argv: vector of arguments from userspace
* @buf: array of nilfs_vdesc structures
*
* Description: nilfs_ioctl_move_blocks() function reads valid data/node
* blocks that garbage collector specified with the array of nilfs_vdesc
* structures and stores them into page caches of GC inodes.
*
* Return Value: Number of processed nilfs_vdesc structures or
* error code, otherwise.
*/
static int nilfs_ioctl_move_blocks(struct super_block *sb,
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
struct nilfs_argv *argv, void *buf)
{
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
size_t nmembs = argv->v_nmembs;
struct the_nilfs *nilfs = sb->s_fs_info;
struct inode *inode;
struct nilfs_vdesc *vdesc;
struct buffer_head *bh, *n;
LIST_HEAD(buffers);
ino_t ino;
__u64 cno;
int i, ret;
for (i = 0, vdesc = buf; i < nmembs; ) {
ino = vdesc->vd_ino;
cno = vdesc->vd_cno;
inode = nilfs_iget_for_gc(sb, ino, cno);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
goto failed;
}
if (list_empty(&NILFS_I(inode)->i_dirty)) {
/*
* Add the inode to GC inode list. Garbage Collection
* is serialized and no two processes manipulate the
* list simultaneously.
*/
igrab(inode);
list_add(&NILFS_I(inode)->i_dirty,
&nilfs->ns_gc_inodes);
}
do {
ret = nilfs_ioctl_move_inode_block(inode, vdesc,
&buffers);
if (unlikely(ret < 0)) {
iput(inode);
goto failed;
}
vdesc++;
} while (++i < nmembs &&
vdesc->vd_ino == ino && vdesc->vd_cno == cno);
iput(inode); /* The inode still remains in GC inode list */
}
list_for_each_entry_safe(bh, n, &buffers, b_assoc_buffers) {
ret = nilfs_gccache_wait_and_mark_dirty(bh);
if (unlikely(ret < 0)) {
WARN_ON(ret == -EEXIST);
goto failed;
}
list_del_init(&bh->b_assoc_buffers);
brelse(bh);
}
return nmembs;
failed:
list_for_each_entry_safe(bh, n, &buffers, b_assoc_buffers) {
list_del_init(&bh->b_assoc_buffers);
brelse(bh);
}
return ret;
}
/**
* nilfs_ioctl_delete_checkpoints - delete checkpoints
* @nilfs: nilfs object
* @argv: vector of arguments from userspace
* @buf: array of periods of checkpoints numbers
*
* Description: nilfs_ioctl_delete_checkpoints() function deletes checkpoints
* in the period from p_start to p_end, excluding p_end itself. The checkpoints
* which have been already deleted are ignored.
*
* Return Value: Number of processed nilfs_period structures or
* error code, otherwise.
*
* %-EIO - I/O error.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-EINVAL - invalid checkpoints.
*/
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
static int nilfs_ioctl_delete_checkpoints(struct the_nilfs *nilfs,
struct nilfs_argv *argv, void *buf)
{
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
size_t nmembs = argv->v_nmembs;
struct inode *cpfile = nilfs->ns_cpfile;
struct nilfs_period *periods = buf;
int ret, i;
for (i = 0; i < nmembs; i++) {
ret = nilfs_cpfile_delete_checkpoints(
cpfile, periods[i].p_start, periods[i].p_end);
if (ret < 0)
return ret;
}
return nmembs;
}
/**
* nilfs_ioctl_free_vblocknrs - free virtual block numbers
* @nilfs: nilfs object
* @argv: vector of arguments from userspace
* @buf: array of virtual block numbers
*
* Description: nilfs_ioctl_free_vblocknrs() function frees
* the virtual block numbers specified by @buf and @argv->v_nmembs.
*
* Return Value: Number of processed virtual block numbers or
* error code, otherwise.
*
* %-EIO - I/O error.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-ENOENT - The virtual block number have not been allocated.
*/
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
static int nilfs_ioctl_free_vblocknrs(struct the_nilfs *nilfs,
struct nilfs_argv *argv, void *buf)
{
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
size_t nmembs = argv->v_nmembs;
int ret;
ret = nilfs_dat_freev(nilfs->ns_dat, buf, nmembs);
return (ret < 0) ? ret : nmembs;
}
/**
* nilfs_ioctl_mark_blocks_dirty - mark blocks dirty
* @nilfs: nilfs object
* @argv: vector of arguments from userspace
* @buf: array of block descriptors
*
* Description: nilfs_ioctl_mark_blocks_dirty() function marks
* metadata file or data blocks as dirty.
*
* Return Value: Number of processed block descriptors or
* error code, otherwise.
*
* %-ENOMEM - Insufficient memory available.
*
* %-EIO - I/O error
*
* %-ENOENT - the specified block does not exist (hole block)
*/
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs,
struct nilfs_argv *argv, void *buf)
{
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
size_t nmembs = argv->v_nmembs;
struct nilfs_bmap *bmap = NILFS_I(nilfs->ns_dat)->i_bmap;
struct nilfs_bdesc *bdescs = buf;
struct buffer_head *bh;
int ret, i;
for (i = 0; i < nmembs; i++) {
/* XXX: use macro or inline func to check liveness */
ret = nilfs_bmap_lookup_at_level(bmap,
bdescs[i].bd_offset,
bdescs[i].bd_level + 1,
&bdescs[i].bd_blocknr);
if (ret < 0) {
if (ret != -ENOENT)
return ret;
bdescs[i].bd_blocknr = 0;
}
if (bdescs[i].bd_blocknr != bdescs[i].bd_oblocknr)
/* skip dead block */
continue;
if (bdescs[i].bd_level == 0) {
ret = nilfs_mdt_get_block(nilfs->ns_dat,
bdescs[i].bd_offset,
false, NULL, &bh);
if (unlikely(ret)) {
WARN_ON(ret == -ENOENT);
return ret;
}
mark_buffer_dirty(bh);
nilfs_mdt_mark_dirty(nilfs->ns_dat);
put_bh(bh);
} else {
ret = nilfs_bmap_mark(bmap, bdescs[i].bd_offset,
bdescs[i].bd_level);
if (ret < 0) {
WARN_ON(ret == -ENOENT);
return ret;
}
}
}
return nmembs;
}
int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *nilfs,
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
struct nilfs_argv *argv, void **kbufs)
{
const char *msg;
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
int ret;
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
ret = nilfs_ioctl_delete_checkpoints(nilfs, &argv[1], kbufs[1]);
if (ret < 0) {
/*
* can safely abort because checkpoints can be removed
* independently.
*/
msg = "cannot delete checkpoints";
goto failed;
}
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
ret = nilfs_ioctl_free_vblocknrs(nilfs, &argv[2], kbufs[2]);
if (ret < 0) {
/*
* can safely abort because DAT file is updated atomically
* using a copy-on-write technique.
*/
msg = "cannot delete virtual blocks from DAT file";
goto failed;
}
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
ret = nilfs_ioctl_mark_blocks_dirty(nilfs, &argv[3], kbufs[3]);
if (ret < 0) {
/*
* can safely abort because the operation is nondestructive.
*/
msg = "cannot mark copying blocks dirty";
goto failed;
}
return 0;
failed:
nilfs_err(nilfs->ns_sb, "error %d preparing GC: %s", ret, msg);
return ret;
}
/**
* nilfs_ioctl_clean_segments - clean segments
* @inode: inode object
* @filp: file object
* @cmd: ioctl's request code
* @argp: pointer on argument from userspace
*
* Description: nilfs_ioctl_clean_segments() function makes garbage
* collection operation in the environment of requested parameters
* from userspace. The NILFS_IOCTL_CLEAN_SEGMENTS ioctl is used by
* nilfs_cleanerd daemon.
*
* Return Value: On success, 0 is returned or error code, otherwise.
*/
static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
struct nilfs_argv argv[5];
static const size_t argsz[5] = {
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
sizeof(struct nilfs_vdesc),
sizeof(struct nilfs_period),
sizeof(__u64),
sizeof(struct nilfs_bdesc),
sizeof(__u64),
};
void __user *base;
void *kbufs[5];
struct the_nilfs *nilfs;
size_t len, nsegs;
int n, ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
ret = mnt_want_write_file(filp);
if (ret)
return ret;
ret = -EFAULT;
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
if (copy_from_user(argv, argp, sizeof(argv)))
goto out;
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
ret = -EINVAL;
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
nsegs = argv[4].v_nmembs;
if (argv[4].v_size != argsz[4])
goto out;
if (nsegs > UINT_MAX / sizeof(__u64))
goto out;
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
/*
* argv[4] points to segment numbers this ioctl cleans. We
* use kmalloc() for its buffer because memory used for the
* segment numbers is enough small.
*/
kbufs[4] = memdup_user((void __user *)(unsigned long)argv[4].v_base,
nsegs * sizeof(__u64));
if (IS_ERR(kbufs[4])) {
ret = PTR_ERR(kbufs[4]);
goto out;
}
nilfs = inode->i_sb->s_fs_info;
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
for (n = 0; n < 4; n++) {
ret = -EINVAL;
if (argv[n].v_size != argsz[n])
goto out_free;
if (argv[n].v_nmembs > nsegs * nilfs->ns_blocks_per_segment)
goto out_free;
if (argv[n].v_nmembs >= UINT_MAX / argv[n].v_size)
goto out_free;
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
len = argv[n].v_size * argv[n].v_nmembs;
base = (void __user *)(unsigned long)argv[n].v_base;
if (len == 0) {
kbufs[n] = NULL;
continue;
}
kbufs[n] = vmalloc(len);
if (!kbufs[n]) {
ret = -ENOMEM;
goto out_free;
}
if (copy_from_user(kbufs[n], base, len)) {
ret = -EFAULT;
vfree(kbufs[n]);
goto out_free;
}
}
nilfs2: shorten freeze period due to GC in write operation v3 This is a re-revised patch to shorten freeze period. This version include a fix of the bug Konishi-san mentioned last time. When GC is runnning, GC moves live block to difference segments. Copying live blocks into memory is done in a transaction, however it is not necessarily to be in the transaction. This patch will get the nilfs_ioctl_move_blocks() out from transaction lock and put it before the transaction. I ran sysbench fileio test against nilfs partition. I copied some DVD/CD images and created snapshot to create live blocks before starting the benchmark. Followings are summary of rc8 and rc8 w/ the patch of per-request statistics, which is min/max and avg. I ran each test three times and bellow is average of those numers. According to this benchmark result, average time is slightly degrated. However, worstcase (max) result is significantly improved. This can address a few seconds write freeze. - random write per-request performance of rc8 min 0.843ms max 680.406ms avg 3.050ms - random write per-request performance of rc8 w/ this patch min 0.843ms -> 100.00% max 380.490ms -> 55.90% avg 3.233ms -> 106.00% - sequential write per-request performance of rc8 min 0.736ms max 774.343ms avg 2.883ms - sequential write per-request performance of rc8 w/ this patch min 0.720ms -> 97.80% max 644.280ms-> 83.20% avg 3.130ms -> 108.50% -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- protection_period 150 selection_policy timestamp # timestamp in ascend order nsegments_per_clean 2 cleaning_interval 2 retry_interval 60 use_mmap log_priority info -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- Signed-off-by: Jiro SEKIBA <jir@unicus.jp> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-09-03 21:24:17 +08:00
/*
* nilfs_ioctl_move_blocks() will call nilfs_iget_for_gc(),
nilfs2: shorten freeze period due to GC in write operation v3 This is a re-revised patch to shorten freeze period. This version include a fix of the bug Konishi-san mentioned last time. When GC is runnning, GC moves live block to difference segments. Copying live blocks into memory is done in a transaction, however it is not necessarily to be in the transaction. This patch will get the nilfs_ioctl_move_blocks() out from transaction lock and put it before the transaction. I ran sysbench fileio test against nilfs partition. I copied some DVD/CD images and created snapshot to create live blocks before starting the benchmark. Followings are summary of rc8 and rc8 w/ the patch of per-request statistics, which is min/max and avg. I ran each test three times and bellow is average of those numers. According to this benchmark result, average time is slightly degrated. However, worstcase (max) result is significantly improved. This can address a few seconds write freeze. - random write per-request performance of rc8 min 0.843ms max 680.406ms avg 3.050ms - random write per-request performance of rc8 w/ this patch min 0.843ms -> 100.00% max 380.490ms -> 55.90% avg 3.233ms -> 106.00% - sequential write per-request performance of rc8 min 0.736ms max 774.343ms avg 2.883ms - sequential write per-request performance of rc8 w/ this patch min 0.720ms -> 97.80% max 644.280ms-> 83.20% avg 3.130ms -> 108.50% -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- protection_period 150 selection_policy timestamp # timestamp in ascend order nsegments_per_clean 2 cleaning_interval 2 retry_interval 60 use_mmap log_priority info -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- Signed-off-by: Jiro SEKIBA <jir@unicus.jp> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-09-03 21:24:17 +08:00
* which will operates an inode list without blocking.
* To protect the list from concurrent operations,
* nilfs_ioctl_move_blocks should be atomic operation.
*/
if (test_and_set_bit(THE_NILFS_GC_RUNNING, &nilfs->ns_flags)) {
ret = -EBUSY;
goto out_free;
}
ret = nilfs_ioctl_move_blocks(inode->i_sb, &argv[0], kbufs[0]);
if (ret < 0) {
nilfs_err(inode->i_sb,
"error %d preparing GC: cannot read source blocks",
ret);
} else {
nilfs2: fix fix very long mount time issue There exists a situation when GC can work in background alone without any other filesystem activity during significant time. The nilfs_clean_segments() method calls nilfs_segctor_construct() that updates superblocks in the case of NILFS_SC_SUPER_ROOT and THE_NILFS_DISCONTINUED flags are set. But when GC is working alone the nilfs_clean_segments() is called with unset THE_NILFS_DISCONTINUED flag. As a result, the update of superblocks doesn't occurred all this time and in the case of SPOR superblocks keep very old values of last super root placement. SYMPTOMS: Trying to mount a NILFS2 volume after SPOR in such environment ends with very long mounting time (it can achieve about several hours in some cases). REPRODUCING PATH: 1. It needs to use external USB HDD, disable automount and doesn't make any additional filesystem activity on the NILFS2 volume. 2. Generate temporary file with size about 100 - 500 GB (for example, dd if=/dev/zero of=<file_name> bs=1073741824 count=200). The size of file defines duration of GC working. 3. Then it needs to delete file. 4. Start GC manually by means of command "nilfs-clean -p 0". When you start GC by means of such way then, at the end, superblocks is updated by once. So, for simulation of SPOR, it needs to wait sometime (15 - 40 minutes) and simply switch off USB HDD manually. 5. Switch on USB HDD again and try to mount NILFS2 volume. As a result, NILFS2 volume will mount during very long time. REPRODUCIBILITY: 100% FIX: This patch adds checking that superblocks need to update and set THE_NILFS_DISCONTINUED flag before nilfs_clean_segments() call. Reported-by: Sergey Alexandrov <splavgm@gmail.com> Signed-off-by: Vyacheslav Dubeyko <slava@dubeyko.com> Tested-by: Vyacheslav Dubeyko <slava@dubeyko.com> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Tested-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-05 06:28:41 +08:00
if (nilfs_sb_need_update(nilfs))
set_nilfs_discontinued(nilfs);
nilfs2: shorten freeze period due to GC in write operation v3 This is a re-revised patch to shorten freeze period. This version include a fix of the bug Konishi-san mentioned last time. When GC is runnning, GC moves live block to difference segments. Copying live blocks into memory is done in a transaction, however it is not necessarily to be in the transaction. This patch will get the nilfs_ioctl_move_blocks() out from transaction lock and put it before the transaction. I ran sysbench fileio test against nilfs partition. I copied some DVD/CD images and created snapshot to create live blocks before starting the benchmark. Followings are summary of rc8 and rc8 w/ the patch of per-request statistics, which is min/max and avg. I ran each test three times and bellow is average of those numers. According to this benchmark result, average time is slightly degrated. However, worstcase (max) result is significantly improved. This can address a few seconds write freeze. - random write per-request performance of rc8 min 0.843ms max 680.406ms avg 3.050ms - random write per-request performance of rc8 w/ this patch min 0.843ms -> 100.00% max 380.490ms -> 55.90% avg 3.233ms -> 106.00% - sequential write per-request performance of rc8 min 0.736ms max 774.343ms avg 2.883ms - sequential write per-request performance of rc8 w/ this patch min 0.720ms -> 97.80% max 644.280ms-> 83.20% avg 3.130ms -> 108.50% -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- protection_period 150 selection_policy timestamp # timestamp in ascend order nsegments_per_clean 2 cleaning_interval 2 retry_interval 60 use_mmap log_priority info -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- Signed-off-by: Jiro SEKIBA <jir@unicus.jp> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-09-03 21:24:17 +08:00
ret = nilfs_clean_segments(inode->i_sb, argv, kbufs);
nilfs2: fix fix very long mount time issue There exists a situation when GC can work in background alone without any other filesystem activity during significant time. The nilfs_clean_segments() method calls nilfs_segctor_construct() that updates superblocks in the case of NILFS_SC_SUPER_ROOT and THE_NILFS_DISCONTINUED flags are set. But when GC is working alone the nilfs_clean_segments() is called with unset THE_NILFS_DISCONTINUED flag. As a result, the update of superblocks doesn't occurred all this time and in the case of SPOR superblocks keep very old values of last super root placement. SYMPTOMS: Trying to mount a NILFS2 volume after SPOR in such environment ends with very long mounting time (it can achieve about several hours in some cases). REPRODUCING PATH: 1. It needs to use external USB HDD, disable automount and doesn't make any additional filesystem activity on the NILFS2 volume. 2. Generate temporary file with size about 100 - 500 GB (for example, dd if=/dev/zero of=<file_name> bs=1073741824 count=200). The size of file defines duration of GC working. 3. Then it needs to delete file. 4. Start GC manually by means of command "nilfs-clean -p 0". When you start GC by means of such way then, at the end, superblocks is updated by once. So, for simulation of SPOR, it needs to wait sometime (15 - 40 minutes) and simply switch off USB HDD manually. 5. Switch on USB HDD again and try to mount NILFS2 volume. As a result, NILFS2 volume will mount during very long time. REPRODUCIBILITY: 100% FIX: This patch adds checking that superblocks need to update and set THE_NILFS_DISCONTINUED flag before nilfs_clean_segments() call. Reported-by: Sergey Alexandrov <splavgm@gmail.com> Signed-off-by: Vyacheslav Dubeyko <slava@dubeyko.com> Tested-by: Vyacheslav Dubeyko <slava@dubeyko.com> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Tested-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-05 06:28:41 +08:00
}
nilfs2: shorten freeze period due to GC in write operation v3 This is a re-revised patch to shorten freeze period. This version include a fix of the bug Konishi-san mentioned last time. When GC is runnning, GC moves live block to difference segments. Copying live blocks into memory is done in a transaction, however it is not necessarily to be in the transaction. This patch will get the nilfs_ioctl_move_blocks() out from transaction lock and put it before the transaction. I ran sysbench fileio test against nilfs partition. I copied some DVD/CD images and created snapshot to create live blocks before starting the benchmark. Followings are summary of rc8 and rc8 w/ the patch of per-request statistics, which is min/max and avg. I ran each test three times and bellow is average of those numers. According to this benchmark result, average time is slightly degrated. However, worstcase (max) result is significantly improved. This can address a few seconds write freeze. - random write per-request performance of rc8 min 0.843ms max 680.406ms avg 3.050ms - random write per-request performance of rc8 w/ this patch min 0.843ms -> 100.00% max 380.490ms -> 55.90% avg 3.233ms -> 106.00% - sequential write per-request performance of rc8 min 0.736ms max 774.343ms avg 2.883ms - sequential write per-request performance of rc8 w/ this patch min 0.720ms -> 97.80% max 644.280ms-> 83.20% avg 3.130ms -> 108.50% -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- protection_period 150 selection_policy timestamp # timestamp in ascend order nsegments_per_clean 2 cleaning_interval 2 retry_interval 60 use_mmap log_priority info -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- Signed-off-by: Jiro SEKIBA <jir@unicus.jp> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-09-03 21:24:17 +08:00
nilfs_remove_all_gcinodes(nilfs);
nilfs2: shorten freeze period due to GC in write operation v3 This is a re-revised patch to shorten freeze period. This version include a fix of the bug Konishi-san mentioned last time. When GC is runnning, GC moves live block to difference segments. Copying live blocks into memory is done in a transaction, however it is not necessarily to be in the transaction. This patch will get the nilfs_ioctl_move_blocks() out from transaction lock and put it before the transaction. I ran sysbench fileio test against nilfs partition. I copied some DVD/CD images and created snapshot to create live blocks before starting the benchmark. Followings are summary of rc8 and rc8 w/ the patch of per-request statistics, which is min/max and avg. I ran each test three times and bellow is average of those numers. According to this benchmark result, average time is slightly degrated. However, worstcase (max) result is significantly improved. This can address a few seconds write freeze. - random write per-request performance of rc8 min 0.843ms max 680.406ms avg 3.050ms - random write per-request performance of rc8 w/ this patch min 0.843ms -> 100.00% max 380.490ms -> 55.90% avg 3.233ms -> 106.00% - sequential write per-request performance of rc8 min 0.736ms max 774.343ms avg 2.883ms - sequential write per-request performance of rc8 w/ this patch min 0.720ms -> 97.80% max 644.280ms-> 83.20% avg 3.130ms -> 108.50% -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- protection_period 150 selection_policy timestamp # timestamp in ascend order nsegments_per_clean 2 cleaning_interval 2 retry_interval 60 use_mmap log_priority info -----8<-----8<-----nilfs_cleanerd.conf-----8<-----8<----- Signed-off-by: Jiro SEKIBA <jir@unicus.jp> Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-09-03 21:24:17 +08:00
clear_nilfs_gc_running(nilfs);
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
out_free:
while (--n >= 0)
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
vfree(kbufs[n]);
kfree(kbufs[4]);
out:
mnt_drop_write_file(filp);
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
return ret;
}
/**
* nilfs_ioctl_sync - make a checkpoint
* @inode: inode object
* @filp: file object
* @cmd: ioctl's request code
* @argp: pointer on argument from userspace
*
* Description: nilfs_ioctl_sync() function constructs a logical segment
* for checkpointing. This function guarantees that all modified data
* and metadata are written out to the device when it successfully
* returned.
*
* Return Value: On success, 0 is retured. On errors, one of the following
* negative error code is returned.
*
* %-EROFS - Read only filesystem.
*
* %-EIO - I/O error
*
* %-ENOSPC - No space left on device (only in a panic state).
*
* %-ERESTARTSYS - Interrupted.
*
* %-ENOMEM - Insufficient memory available.
*
* %-EFAULT - Failure during execution of requested operation.
*/
static int nilfs_ioctl_sync(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
__u64 cno;
int ret;
struct the_nilfs *nilfs;
ret = nilfs_construct_segment(inode->i_sb);
if (ret < 0)
return ret;
nilfs = inode->i_sb->s_fs_info;
ret = nilfs_flush_device(nilfs);
if (ret < 0)
return ret;
if (argp != NULL) {
down_read(&nilfs->ns_segctor_sem);
cno = nilfs->ns_cno - 1;
up_read(&nilfs->ns_segctor_sem);
if (copy_to_user(argp, &cno, sizeof(cno)))
return -EFAULT;
}
return 0;
}
/**
* nilfs_ioctl_resize - resize NILFS2 volume
* @inode: inode object
* @filp: file object
* @argp: pointer on argument from userspace
*
* Return Value: On success, 0 is returned or error code, otherwise.
*/
static int nilfs_ioctl_resize(struct inode *inode, struct file *filp,
void __user *argp)
{
__u64 newsize;
int ret = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto out;
ret = mnt_want_write_file(filp);
if (ret)
goto out;
ret = -EFAULT;
if (copy_from_user(&newsize, argp, sizeof(newsize)))
goto out_drop_write;
ret = nilfs_resize_fs(inode->i_sb, newsize);
out_drop_write:
mnt_drop_write_file(filp);
out:
return ret;
}
/**
* nilfs_ioctl_trim_fs() - trim ioctl handle function
* @inode: inode object
* @argp: pointer on argument from userspace
*
* Description: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It
* checks the arguments from userspace and calls nilfs_sufile_trim_fs, which
* performs the actual trim operation.
*
* Return Value: On success, 0 is returned or negative error code, otherwise.
*/
static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
struct request_queue *q = bdev_get_queue(nilfs->ns_bdev);
struct fstrim_range range;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if (copy_from_user(&range, argp, sizeof(range)))
return -EFAULT;
range.minlen = max_t(u64, range.minlen, q->limits.discard_granularity);
down_read(&nilfs->ns_segctor_sem);
ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range);
up_read(&nilfs->ns_segctor_sem);
if (ret < 0)
return ret;
if (copy_to_user(argp, &range, sizeof(range)))
return -EFAULT;
return 0;
}
/**
* nilfs_ioctl_set_alloc_range - limit range of segments to be allocated
* @inode: inode object
* @argp: pointer on argument from userspace
*
* Description: nilfs_ioctl_set_alloc_range() function defines lower limit
* of segments in bytes and upper limit of segments in bytes.
* The NILFS_IOCTL_SET_ALLOC_RANGE is used by nilfs_resize utility.
*
* Return Value: On success, 0 is returned or error code, otherwise.
*/
static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
__u64 range[2];
__u64 minseg, maxseg;
unsigned long segbytes;
int ret = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto out;
ret = -EFAULT;
if (copy_from_user(range, argp, sizeof(__u64[2])))
goto out;
ret = -ERANGE;
if (range[1] > bdev_nr_bytes(inode->i_sb->s_bdev))
goto out;
segbytes = nilfs->ns_blocks_per_segment * nilfs->ns_blocksize;
minseg = range[0] + segbytes - 1;
do_div(minseg, segbytes);
maxseg = NILFS_SB2_OFFSET_BYTES(range[1]);
do_div(maxseg, segbytes);
maxseg--;
ret = nilfs_sufile_set_alloc_range(nilfs->ns_sufile, minseg, maxseg);
out:
return ret;
}
/**
* nilfs_ioctl_get_info - wrapping function of get metadata info
* @inode: inode object
* @filp: file object
* @cmd: ioctl's request code
* @argp: pointer on argument from userspace
* @membsz: size of an item in bytes
* @dofunc: concrete function of getting metadata info
*
* Description: nilfs_ioctl_get_info() gets metadata info by means of
* calling dofunc() function.
*
* Return Value: On success, 0 is returned and requested metadata info
* is copied into userspace. On error, one of the following
* negative error codes is returned.
*
* %-EINVAL - Invalid arguments from userspace.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-EFAULT - Failure during execution of requested operation.
*/
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp,
size_t membsz,
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
ssize_t (*dofunc)(struct the_nilfs *,
__u64 *, int,
void *, size_t, size_t))
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
struct nilfs_argv argv;
int ret;
if (copy_from_user(&argv, argp, sizeof(argv)))
return -EFAULT;
if (argv.v_size < membsz)
return -EINVAL;
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
ret = nilfs_ioctl_wrap_copy(nilfs, &argv, _IOC_DIR(cmd), dofunc);
if (ret < 0)
return ret;
if (copy_to_user(argp, &argv, sizeof(argv)))
ret = -EFAULT;
return ret;
}
/**
* nilfs_ioctl_set_suinfo - set segment usage info
* @inode: inode object
* @filp: file object
* @cmd: ioctl's request code
* @argp: pointer on argument from userspace
*
* Description: Expects an array of nilfs_suinfo_update structures
* encapsulated in nilfs_argv and updates the segment usage info
* according to the flags in nilfs_suinfo_update.
*
* Return Value: On success, 0 is returned. On error, one of the
* following negative error codes is returned.
*
* %-EPERM - Not enough permissions
*
* %-EFAULT - Error copying input data
*
* %-EIO - I/O error.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-EINVAL - Invalid values in input (segment number, flags or nblocks)
*/
static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
struct nilfs_transaction_info ti;
struct nilfs_argv argv;
size_t len;
void __user *base;
void *kbuf;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
ret = -EFAULT;
if (copy_from_user(&argv, argp, sizeof(argv)))
goto out;
ret = -EINVAL;
if (argv.v_size < sizeof(struct nilfs_suinfo_update))
goto out;
if (argv.v_nmembs > nilfs->ns_nsegments)
goto out;
if (argv.v_nmembs >= UINT_MAX / argv.v_size)
goto out;
len = argv.v_size * argv.v_nmembs;
if (!len) {
ret = 0;
goto out;
}
base = (void __user *)(unsigned long)argv.v_base;
kbuf = vmalloc(len);
if (!kbuf) {
ret = -ENOMEM;
goto out;
}
if (copy_from_user(kbuf, base, len)) {
ret = -EFAULT;
goto out_free;
}
nilfs_transaction_begin(inode->i_sb, &ti, 0);
ret = nilfs_sufile_set_suinfo(nilfs->ns_sufile, kbuf, argv.v_size,
argv.v_nmembs);
if (unlikely(ret < 0))
nilfs_transaction_abort(inode->i_sb);
else
nilfs_transaction_commit(inode->i_sb); /* never fails */
out_free:
vfree(kbuf);
out:
mnt_drop_write_file(filp);
return ret;
}
long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
void __user *argp = (void __user *)arg;
switch (cmd) {
case FS_IOC_GETVERSION:
return nilfs_ioctl_getversion(inode, argp);
case NILFS_IOCTL_CHANGE_CPMODE:
return nilfs_ioctl_change_cpmode(inode, filp, cmd, argp);
case NILFS_IOCTL_DELETE_CHECKPOINT:
return nilfs_ioctl_delete_checkpoint(inode, filp, cmd, argp);
case NILFS_IOCTL_GET_CPINFO:
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
return nilfs_ioctl_get_info(inode, filp, cmd, argp,
sizeof(struct nilfs_cpinfo),
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
nilfs_ioctl_do_get_cpinfo);
case NILFS_IOCTL_GET_CPSTAT:
return nilfs_ioctl_get_cpstat(inode, filp, cmd, argp);
case NILFS_IOCTL_GET_SUINFO:
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
return nilfs_ioctl_get_info(inode, filp, cmd, argp,
sizeof(struct nilfs_suinfo),
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
nilfs_ioctl_do_get_suinfo);
case NILFS_IOCTL_SET_SUINFO:
return nilfs_ioctl_set_suinfo(inode, filp, cmd, argp);
case NILFS_IOCTL_GET_SUSTAT:
return nilfs_ioctl_get_sustat(inode, filp, cmd, argp);
case NILFS_IOCTL_GET_VINFO:
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
return nilfs_ioctl_get_info(inode, filp, cmd, argp,
sizeof(struct nilfs_vinfo),
nilfs2: fix possible circular locking for get information ioctls This is one of two patches which are to correct possible circular locking between mm->mmap_sem and nilfs->ns_segctor_sem. The problem was detected by lockdep check as follows: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00002-g3552613 #6 ------------------------------------------------------- mmap/5418 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c730>] copy_to_user+0x2c/0xfc [<d0d11b4f>] nilfs_ioctl_wrap_copy+0x103/0x160 [nilfs2] [<d0d11fa9>] nilfs_ioctl+0x30a/0x3b0 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by mmap/5418: #0: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a stack backtrace: Pid: 5418, comm: mmap Not tainted 2.6.30-rc3-nilfs-00002-g3552613 #6 Call Trace: [<c0432145>] ? printk+0xf/0x12 [<c0145c48>] print_circular_bug_tail+0xaa/0xb5 [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<d0d10149>] ? nilfs_sufile_get_stat+0x1e/0x105 [nilfs2] [<c013b59a>] ? up_read+0x16/0x2c [<d0d10225>] ? nilfs_sufile_get_stat+0xfa/0x105 [nilfs2] [<c01474a9>] lock_acquire+0xba/0xdd [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e852>] ? nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0d0e852>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043700a>] ? do_page_fault+0x1d8/0x30a [<c013b54f>] ? down_read_trylock+0x39/0x43 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0436e32>] ? do_page_fault+0x0/0x30a [<c0435462>] error_code+0x72/0x78 [<c0436e32>] ? do_page_fault+0x0/0x30a This makes the lock granularity of nilfs->ns_segctor_sem finer than that of the mmap semaphore for ioctl commands except nilfs_clean_segments(). The successive patch ("nilfs2: fix lock order reversal in nilfs_clean_segments ioctl") is required to fully resolve the problem. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-04-30 01:21:00 +08:00
nilfs_ioctl_do_get_vinfo);
case NILFS_IOCTL_GET_BDESCS:
return nilfs_ioctl_get_bdescs(inode, filp, cmd, argp);
case NILFS_IOCTL_CLEAN_SEGMENTS:
return nilfs_ioctl_clean_segments(inode, filp, cmd, argp);
case NILFS_IOCTL_SYNC:
return nilfs_ioctl_sync(inode, filp, cmd, argp);
case NILFS_IOCTL_RESIZE:
return nilfs_ioctl_resize(inode, filp, argp);
case NILFS_IOCTL_SET_ALLOC_RANGE:
return nilfs_ioctl_set_alloc_range(inode, argp);
case FITRIM:
return nilfs_ioctl_trim_fs(inode, argp);
default:
return -ENOTTY;
}
}
#ifdef CONFIG_COMPAT
long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
case FS_IOC32_GETVERSION:
cmd = FS_IOC_GETVERSION;
break;
case NILFS_IOCTL_CHANGE_CPMODE:
case NILFS_IOCTL_DELETE_CHECKPOINT:
case NILFS_IOCTL_GET_CPINFO:
case NILFS_IOCTL_GET_CPSTAT:
case NILFS_IOCTL_GET_SUINFO:
case NILFS_IOCTL_SET_SUINFO:
case NILFS_IOCTL_GET_SUSTAT:
case NILFS_IOCTL_GET_VINFO:
case NILFS_IOCTL_GET_BDESCS:
case NILFS_IOCTL_CLEAN_SEGMENTS:
case NILFS_IOCTL_SYNC:
case NILFS_IOCTL_RESIZE:
case NILFS_IOCTL_SET_ALLOC_RANGE:
case FITRIM:
break;
default:
return -ENOIOCTLCMD;
}
return nilfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
}
#endif