linux-sg2042/fs/reiserfs/dir.c

320 lines
9.1 KiB
C
Raw Normal View History

/*
* Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
*/
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/reiserfs_fs.h>
#include <linux/stat.h>
#include <linux/buffer_head.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 <asm/uaccess.h>
extern const struct reiserfs_key MIN_KEY;
static int reiserfs_readdir(struct file *, void *, filldir_t);
static int reiserfs_dir_fsync(struct file *filp, loff_t start, loff_t end,
int datasync);
const struct file_operations reiserfs_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
.readdir = reiserfs_readdir,
.fsync = reiserfs_dir_fsync,
.unlocked_ioctl = reiserfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = reiserfs_compat_ioctl,
#endif
};
static int reiserfs_dir_fsync(struct file *filp, loff_t start, loff_t end,
int datasync)
{
struct inode *inode = filp->f_mapping->host;
int err;
err = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (err)
return err;
mutex_lock(&inode->i_mutex);
reiserfs_write_lock(inode->i_sb);
err = reiserfs_commit_for_inode(inode);
reiserfs_write_unlock(inode->i_sb);
mutex_unlock(&inode->i_mutex);
if (err < 0)
return err;
return 0;
}
#define store_ih(where,what) copy_item_head (where, what)
static inline bool is_privroot_deh(struct dentry *dir,
struct reiserfs_de_head *deh)
{
struct dentry *privroot = REISERFS_SB(dir->d_sb)->priv_root;
return (dir == dir->d_parent && privroot->d_inode &&
deh->deh_objectid == INODE_PKEY(privroot->d_inode)->k_objectid);
}
int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
filldir_t filldir, loff_t *pos)
{
struct inode *inode = dentry->d_inode;
struct cpu_key pos_key; /* key of current position in the directory (key of directory entry) */
INITIALIZE_PATH(path_to_entry);
struct buffer_head *bh;
int item_num, entry_num;
const struct reiserfs_key *rkey;
struct item_head *ih, tmp_ih;
int search_res;
char *local_buf;
loff_t next_pos;
char small_buf[32]; /* avoid kmalloc if we can */
struct reiserfs_dir_entry de;
int ret = 0;
reiserfs_write_lock(inode->i_sb);
reiserfs_check_lock_depth(inode->i_sb, "readdir");
/* form key for search the next directory entry using f_pos field of
file structure */
make_cpu_key(&pos_key, inode, *pos ?: DOT_OFFSET, TYPE_DIRENTRY, 3);
next_pos = cpu_key_k_offset(&pos_key);
path_to_entry.reada = PATH_READA;
while (1) {
research:
/* search the directory item, containing entry with specified key */
search_res =
search_by_entry_key(inode->i_sb, &pos_key, &path_to_entry,
&de);
if (search_res == IO_ERROR) {
// FIXME: we could just skip part of directory which could
// not be read
ret = -EIO;
goto out;
}
entry_num = de.de_entry_num;
bh = de.de_bh;
item_num = de.de_item_num;
ih = de.de_ih;
store_ih(&tmp_ih, ih);
/* we must have found item, that is item of this directory, */
RFALSE(COMP_SHORT_KEYS(&(ih->ih_key), &pos_key),
"vs-9000: found item %h does not match to dir we readdir %K",
ih, &pos_key);
RFALSE(item_num > B_NR_ITEMS(bh) - 1,
"vs-9005 item_num == %d, item amount == %d",
item_num, B_NR_ITEMS(bh));
/* and entry must be not more than number of entries in the item */
RFALSE(I_ENTRY_COUNT(ih) < entry_num,
"vs-9010: entry number is too big %d (%d)",
entry_num, I_ENTRY_COUNT(ih));
if (search_res == POSITION_FOUND
|| entry_num < I_ENTRY_COUNT(ih)) {
/* go through all entries in the directory item beginning from the entry, that has been found */
struct reiserfs_de_head *deh =
B_I_DEH(bh, ih) + entry_num;
for (; entry_num < I_ENTRY_COUNT(ih);
entry_num++, deh++) {
int d_reclen;
char *d_name;
off_t d_off;
ino_t d_ino;
if (!de_visible(deh))
/* it is hidden entry */
continue;
d_reclen = entry_length(bh, ih, entry_num);
d_name = B_I_DEH_ENTRY_FILE_NAME(bh, ih, deh);
if (d_reclen <= 0 ||
d_name + d_reclen > bh->b_data + bh->b_size) {
/* There is corrupted data in entry,
* We'd better stop here */
pathrelse(&path_to_entry);
ret = -EIO;
goto out;
}
if (!d_name[d_reclen - 1])
d_reclen = strlen(d_name);
if (d_reclen >
REISERFS_MAX_NAME(inode->i_sb->
s_blocksize)) {
/* too big to send back to VFS */
continue;
}
/* Ignore the .reiserfs_priv entry */
if (is_privroot_deh(dentry, deh))
continue;
d_off = deh_offset(deh);
*pos = d_off;
d_ino = deh_objectid(deh);
if (d_reclen <= 32) {
local_buf = small_buf;
} else {
local_buf = kmalloc(d_reclen,
GFP_NOFS);
if (!local_buf) {
pathrelse(&path_to_entry);
ret = -ENOMEM;
goto out;
}
if (item_moved(&tmp_ih, &path_to_entry)) {
kfree(local_buf);
goto research;
}
}
// Note, that we copy name to user space via temporary
// buffer (local_buf) because filldir will block if
// user space buffer is swapped out. At that time
// entry can move to somewhere else
memcpy(local_buf, d_name, d_reclen);
reiserfs: kill-the-BKL This patch is an attempt to remove the Bkl based locking scheme from reiserfs and is intended. It is a bit inspired from an old attempt by Peter Zijlstra: http://lkml.indiana.edu/hypermail/linux/kernel/0704.2/2174.html The bkl is heavily used in this filesystem to prevent from concurrent write accesses on the filesystem. Reiserfs makes a deep use of the specific properties of the Bkl: - It can be acqquired recursively by a same task - It is released on the schedule() calls and reacquired when schedule() returns The two properties above are a roadmap for the reiserfs write locking so it's very hard to simply replace it with a common mutex. - We need a recursive-able locking unless we want to restructure several blocks of the code. - We need to identify the sites where the bkl was implictly relaxed (schedule, wait, sync, etc...) so that we can in turn release and reacquire our new lock explicitly. Such implicit releases of the lock are often required to let other resources producer/consumer do their job or we can suffer unexpected starvations or deadlocks. So the new lock that replaces the bkl here is a per superblock mutex with a specific property: it can be acquired recursively by a same task, like the bkl. For such purpose, we integrate a lock owner and a lock depth field on the superblock information structure. The first axis on this patch is to turn reiserfs_write_(un)lock() function into a wrapper to manage this mutex. Also some explicit calls to lock_kernel() have been converted to reiserfs_write_lock() helpers. The second axis is to find the important blocking sites (schedule...(), wait_on_buffer(), sync_dirty_buffer(), etc...) and then apply an explicit release of the write lock on these locations before blocking. Then we can safely wait for those who can give us resources or those who need some. Typically this is a fight between the current writer, the reiserfs workqueue (aka the async commiter) and the pdflush threads. The third axis is a consequence of the second. The write lock is usually on top of a lock dependency chain which can include the journal lock, the flush lock or the commit lock. So it's dangerous to release and trying to reacquire the write lock while we still hold other locks. This is fine with the bkl: T1 T2 lock_kernel() mutex_lock(A) unlock_kernel() // do something lock_kernel() mutex_lock(A) -> already locked by T1 schedule() (and then unlock_kernel()) lock_kernel() mutex_unlock(A) .... This is not fine with a mutex: T1 T2 mutex_lock(write) mutex_lock(A) mutex_unlock(write) // do something mutex_lock(write) mutex_lock(A) -> already locked by T1 schedule() mutex_lock(write) -> already locked by T2 deadlock The solution in this patch is to provide a helper which releases the write lock and sleep a bit if we can't lock a mutex that depend on it. It's another simulation of the bkl behaviour. The last axis is to locate the fs callbacks that are called with the bkl held, according to Documentation/filesystem/Locking. Those are: - reiserfs_remount - reiserfs_fill_super - reiserfs_put_super Reiserfs didn't need to explicitly lock because of the context of these callbacks. But now we must take care of that with the new locking. After this patch, reiserfs suffers from a slight performance regression (for now). On UP, a high volume write with dd reports an average of 27 MB/s instead of 30 MB/s without the patch applied. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Jeff Mahoney <jeffm@suse.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Bron Gondwana <brong@fastmail.fm> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> LKML-Reference: <1239070789-13354-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-07 10:19:49 +08:00
/*
* Since filldir might sleep, we can release
* the write lock here for other waiters
*/
reiserfs_write_unlock(inode->i_sb);
if (filldir
(dirent, local_buf, d_reclen, d_off, d_ino,
DT_UNKNOWN) < 0) {
reiserfs: kill-the-BKL This patch is an attempt to remove the Bkl based locking scheme from reiserfs and is intended. It is a bit inspired from an old attempt by Peter Zijlstra: http://lkml.indiana.edu/hypermail/linux/kernel/0704.2/2174.html The bkl is heavily used in this filesystem to prevent from concurrent write accesses on the filesystem. Reiserfs makes a deep use of the specific properties of the Bkl: - It can be acqquired recursively by a same task - It is released on the schedule() calls and reacquired when schedule() returns The two properties above are a roadmap for the reiserfs write locking so it's very hard to simply replace it with a common mutex. - We need a recursive-able locking unless we want to restructure several blocks of the code. - We need to identify the sites where the bkl was implictly relaxed (schedule, wait, sync, etc...) so that we can in turn release and reacquire our new lock explicitly. Such implicit releases of the lock are often required to let other resources producer/consumer do their job or we can suffer unexpected starvations or deadlocks. So the new lock that replaces the bkl here is a per superblock mutex with a specific property: it can be acquired recursively by a same task, like the bkl. For such purpose, we integrate a lock owner and a lock depth field on the superblock information structure. The first axis on this patch is to turn reiserfs_write_(un)lock() function into a wrapper to manage this mutex. Also some explicit calls to lock_kernel() have been converted to reiserfs_write_lock() helpers. The second axis is to find the important blocking sites (schedule...(), wait_on_buffer(), sync_dirty_buffer(), etc...) and then apply an explicit release of the write lock on these locations before blocking. Then we can safely wait for those who can give us resources or those who need some. Typically this is a fight between the current writer, the reiserfs workqueue (aka the async commiter) and the pdflush threads. The third axis is a consequence of the second. The write lock is usually on top of a lock dependency chain which can include the journal lock, the flush lock or the commit lock. So it's dangerous to release and trying to reacquire the write lock while we still hold other locks. This is fine with the bkl: T1 T2 lock_kernel() mutex_lock(A) unlock_kernel() // do something lock_kernel() mutex_lock(A) -> already locked by T1 schedule() (and then unlock_kernel()) lock_kernel() mutex_unlock(A) .... This is not fine with a mutex: T1 T2 mutex_lock(write) mutex_lock(A) mutex_unlock(write) // do something mutex_lock(write) mutex_lock(A) -> already locked by T1 schedule() mutex_lock(write) -> already locked by T2 deadlock The solution in this patch is to provide a helper which releases the write lock and sleep a bit if we can't lock a mutex that depend on it. It's another simulation of the bkl behaviour. The last axis is to locate the fs callbacks that are called with the bkl held, according to Documentation/filesystem/Locking. Those are: - reiserfs_remount - reiserfs_fill_super - reiserfs_put_super Reiserfs didn't need to explicitly lock because of the context of these callbacks. But now we must take care of that with the new locking. After this patch, reiserfs suffers from a slight performance regression (for now). On UP, a high volume write with dd reports an average of 27 MB/s instead of 30 MB/s without the patch applied. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Jeff Mahoney <jeffm@suse.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Bron Gondwana <brong@fastmail.fm> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> LKML-Reference: <1239070789-13354-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-07 10:19:49 +08:00
reiserfs_write_lock(inode->i_sb);
if (local_buf != small_buf) {
kfree(local_buf);
}
goto end;
}
reiserfs: kill-the-BKL This patch is an attempt to remove the Bkl based locking scheme from reiserfs and is intended. It is a bit inspired from an old attempt by Peter Zijlstra: http://lkml.indiana.edu/hypermail/linux/kernel/0704.2/2174.html The bkl is heavily used in this filesystem to prevent from concurrent write accesses on the filesystem. Reiserfs makes a deep use of the specific properties of the Bkl: - It can be acqquired recursively by a same task - It is released on the schedule() calls and reacquired when schedule() returns The two properties above are a roadmap for the reiserfs write locking so it's very hard to simply replace it with a common mutex. - We need a recursive-able locking unless we want to restructure several blocks of the code. - We need to identify the sites where the bkl was implictly relaxed (schedule, wait, sync, etc...) so that we can in turn release and reacquire our new lock explicitly. Such implicit releases of the lock are often required to let other resources producer/consumer do their job or we can suffer unexpected starvations or deadlocks. So the new lock that replaces the bkl here is a per superblock mutex with a specific property: it can be acquired recursively by a same task, like the bkl. For such purpose, we integrate a lock owner and a lock depth field on the superblock information structure. The first axis on this patch is to turn reiserfs_write_(un)lock() function into a wrapper to manage this mutex. Also some explicit calls to lock_kernel() have been converted to reiserfs_write_lock() helpers. The second axis is to find the important blocking sites (schedule...(), wait_on_buffer(), sync_dirty_buffer(), etc...) and then apply an explicit release of the write lock on these locations before blocking. Then we can safely wait for those who can give us resources or those who need some. Typically this is a fight between the current writer, the reiserfs workqueue (aka the async commiter) and the pdflush threads. The third axis is a consequence of the second. The write lock is usually on top of a lock dependency chain which can include the journal lock, the flush lock or the commit lock. So it's dangerous to release and trying to reacquire the write lock while we still hold other locks. This is fine with the bkl: T1 T2 lock_kernel() mutex_lock(A) unlock_kernel() // do something lock_kernel() mutex_lock(A) -> already locked by T1 schedule() (and then unlock_kernel()) lock_kernel() mutex_unlock(A) .... This is not fine with a mutex: T1 T2 mutex_lock(write) mutex_lock(A) mutex_unlock(write) // do something mutex_lock(write) mutex_lock(A) -> already locked by T1 schedule() mutex_lock(write) -> already locked by T2 deadlock The solution in this patch is to provide a helper which releases the write lock and sleep a bit if we can't lock a mutex that depend on it. It's another simulation of the bkl behaviour. The last axis is to locate the fs callbacks that are called with the bkl held, according to Documentation/filesystem/Locking. Those are: - reiserfs_remount - reiserfs_fill_super - reiserfs_put_super Reiserfs didn't need to explicitly lock because of the context of these callbacks. But now we must take care of that with the new locking. After this patch, reiserfs suffers from a slight performance regression (for now). On UP, a high volume write with dd reports an average of 27 MB/s instead of 30 MB/s without the patch applied. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Jeff Mahoney <jeffm@suse.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Bron Gondwana <brong@fastmail.fm> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> LKML-Reference: <1239070789-13354-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-07 10:19:49 +08:00
reiserfs_write_lock(inode->i_sb);
if (local_buf != small_buf) {
kfree(local_buf);
}
// next entry should be looked for with such offset
next_pos = deh_offset(deh) + 1;
if (item_moved(&tmp_ih, &path_to_entry)) {
goto research;
}
} /* for */
}
if (item_num != B_NR_ITEMS(bh) - 1)
// end of directory has been reached
goto end;
/* item we went through is last item of node. Using right
delimiting key check is it directory end */
rkey = get_rkey(&path_to_entry, inode->i_sb);
if (!comp_le_keys(rkey, &MIN_KEY)) {
/* set pos_key to key, that is the smallest and greater
that key of the last entry in the item */
set_cpu_key_k_offset(&pos_key, next_pos);
continue;
}
if (COMP_SHORT_KEYS(rkey, &pos_key)) {
// end of directory has been reached
goto end;
}
/* directory continues in the right neighboring block */
set_cpu_key_k_offset(&pos_key,
le_key_k_offset(KEY_FORMAT_3_5, rkey));
} /* while */
end:
*pos = next_pos;
pathrelse(&path_to_entry);
reiserfs_check_path(&path_to_entry);
out:
reiserfs_write_unlock(inode->i_sb);
return ret;
}
static int reiserfs_readdir(struct file *file, void *dirent, filldir_t filldir)
{
struct dentry *dentry = file->f_path.dentry;
return reiserfs_readdir_dentry(dentry, dirent, filldir, &file->f_pos);
}
/* compose directory item containing "." and ".." entries (entries are
not aligned to 4 byte boundary) */
/* the last four params are LE */
void make_empty_dir_item_v1(char *body, __le32 dirid, __le32 objid,
__le32 par_dirid, __le32 par_objid)
{
struct reiserfs_de_head *deh;
memset(body, 0, EMPTY_DIR_SIZE_V1);
deh = (struct reiserfs_de_head *)body;
/* direntry header of "." */
put_deh_offset(&(deh[0]), DOT_OFFSET);
/* these two are from make_le_item_head, and are are LE */
deh[0].deh_dir_id = dirid;
deh[0].deh_objectid = objid;
deh[0].deh_state = 0; /* Endian safe if 0 */
put_deh_location(&(deh[0]), EMPTY_DIR_SIZE_V1 - strlen("."));
mark_de_visible(&(deh[0]));
/* direntry header of ".." */
put_deh_offset(&(deh[1]), DOT_DOT_OFFSET);
/* key of ".." for the root directory */
/* these two are from the inode, and are are LE */
deh[1].deh_dir_id = par_dirid;
deh[1].deh_objectid = par_objid;
deh[1].deh_state = 0; /* Endian safe if 0 */
put_deh_location(&(deh[1]), deh_location(&(deh[0])) - strlen(".."));
mark_de_visible(&(deh[1]));
/* copy ".." and "." */
memcpy(body + deh_location(&(deh[0])), ".", 1);
memcpy(body + deh_location(&(deh[1])), "..", 2);
}
/* compose directory item containing "." and ".." entries */
void make_empty_dir_item(char *body, __le32 dirid, __le32 objid,
__le32 par_dirid, __le32 par_objid)
{
struct reiserfs_de_head *deh;
memset(body, 0, EMPTY_DIR_SIZE);
deh = (struct reiserfs_de_head *)body;
/* direntry header of "." */
put_deh_offset(&(deh[0]), DOT_OFFSET);
/* these two are from make_le_item_head, and are are LE */
deh[0].deh_dir_id = dirid;
deh[0].deh_objectid = objid;
deh[0].deh_state = 0; /* Endian safe if 0 */
put_deh_location(&(deh[0]), EMPTY_DIR_SIZE - ROUND_UP(strlen(".")));
mark_de_visible(&(deh[0]));
/* direntry header of ".." */
put_deh_offset(&(deh[1]), DOT_DOT_OFFSET);
/* key of ".." for the root directory */
/* these two are from the inode, and are are LE */
deh[1].deh_dir_id = par_dirid;
deh[1].deh_objectid = par_objid;
deh[1].deh_state = 0; /* Endian safe if 0 */
put_deh_location(&(deh[1]),
deh_location(&(deh[0])) - ROUND_UP(strlen("..")));
mark_de_visible(&(deh[1]));
/* copy ".." and "." */
memcpy(body + deh_location(&(deh[0])), ".", 1);
memcpy(body + deh_location(&(deh[1])), "..", 2);
}