Commit 3e59ddff authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2:
  ocfs2: Remove overzealous BUG_ON()
  ocfs2: Don't print on unknown remote blocking call
  ocfs2: Remove EXPERIMENTAL dependency
  ocfs2: implement directory read-ahead
  ocfs2: properly update i_mtime on buffered write
  ocfs2: Fix directory link count checks in ocfs2_link()
  ocfs2: move nlink check in ocfs2_mknod()
  ocfs2: Fix heartbeat sector calculation
  [PATCH] fs/ocfs2/ioctl.c should #include "ioctl.h"
  ocfs2: add ext2 attributes
  configfs: Prevent duplicate subsystem names.
parents 6bbd9b6d eb35746c
......@@ -325,8 +325,8 @@ config FS_POSIX_ACL
source "fs/xfs/Kconfig"
config OCFS2_FS
tristate "OCFS2 file system support (EXPERIMENTAL)"
depends on NET && SYSFS && EXPERIMENTAL
tristate "OCFS2 file system support"
depends on NET && SYSFS
select CONFIGFS_FS
select JBD
select CRC32
......
......@@ -86,6 +86,32 @@ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent * pare
return sd;
}
/*
*
* Return -EEXIST if there is already a configfs element with the same
* name for the same parent.
*
* called with parent inode's i_mutex held
*/
int configfs_dirent_exists(struct configfs_dirent *parent_sd,
const unsigned char *new)
{
struct configfs_dirent * sd;
list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
if (sd->s_element) {
const unsigned char *existing = configfs_get_name(sd);
if (strcmp(existing, new))
continue;
else
return -EEXIST;
}
}
return 0;
}
int configfs_make_dirent(struct configfs_dirent * parent_sd,
struct dentry * dentry, void * element,
umode_t mode, int type)
......@@ -136,8 +162,10 @@ static int create_dir(struct config_item * k, struct dentry * p,
int error;
umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
error = configfs_make_dirent(p->d_fsdata, d, k, mode,
CONFIGFS_DIR);
error = configfs_dirent_exists(p->d_fsdata, d->d_name.name);
if (!error)
error = configfs_make_dirent(p->d_fsdata, d, k, mode,
CONFIGFS_DIR);
if (!error) {
error = configfs_create(d, mode, init_dir);
if (!error) {
......
......@@ -16,6 +16,7 @@ ocfs2-objs := \
file.o \
heartbeat.o \
inode.o \
ioctl.o \
journal.o \
localalloc.o \
mmap.o \
......
......@@ -1717,17 +1717,29 @@ static int ocfs2_do_truncate(struct ocfs2_super *osb,
ocfs2_remove_from_cache(inode, eb_bh);
BUG_ON(eb->h_suballoc_slot);
BUG_ON(el->l_recs[0].e_clusters);
BUG_ON(el->l_recs[0].e_cpos);
BUG_ON(el->l_recs[0].e_blkno);
status = ocfs2_free_extent_block(handle,
tc->tc_ext_alloc_inode,
tc->tc_ext_alloc_bh,
eb);
if (status < 0) {
mlog_errno(status);
goto bail;
if (eb->h_suballoc_slot == 0) {
/*
* This code only understands how to
* lock the suballocator in slot 0,
* which is fine because allocation is
* only ever done out of that
* suballocator too. A future version
* might change that however, so avoid
* a free if we don't know how to
* handle it. This way an fs incompat
* bit will not be necessary.
*/
status = ocfs2_free_extent_block(handle,
tc->tc_ext_alloc_inode,
tc->tc_ext_alloc_bh,
eb);
if (status < 0) {
mlog_errno(status);
goto bail;
}
}
}
brelse(eb_bh);
......
......@@ -391,31 +391,28 @@ out:
static int ocfs2_commit_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
int ret, extending = 0, locklevel = 0;
loff_t new_i_size;
int ret;
struct buffer_head *di_bh = NULL;
struct inode *inode = page->mapping->host;
struct ocfs2_journal_handle *handle = NULL;
struct ocfs2_dinode *di;
mlog_entry("(0x%p, 0x%p, %u, %u)\n", file, page, from, to);
/* NOTE: ocfs2_file_aio_write has ensured that it's safe for
* us to sample inode->i_size here without the metadata lock:
* us to continue here without rechecking the I/O against
* changed inode values.
*
* 1) We're currently holding the inode alloc lock, so no
* nodes can change it underneath us.
*
* 2) We've had to take the metadata lock at least once
* already to check for extending writes, hence insuring
* that our current copy is also up to date.
* already to check for extending writes, suid removal, etc.
* The meta data update code then ensures that we don't get a
* stale inode allocation image (i_size, i_clusters, etc).
*/
new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
if (new_i_size > i_size_read(inode)) {
extending = 1;
locklevel = 1;
}
ret = ocfs2_meta_lock_with_page(inode, NULL, &di_bh, locklevel, page);
ret = ocfs2_meta_lock_with_page(inode, NULL, &di_bh, 1, page);
if (ret != 0) {
mlog_errno(ret);
goto out;
......@@ -427,23 +424,20 @@ static int ocfs2_commit_write(struct file *file, struct page *page,
goto out_unlock_meta;
}
if (extending) {
handle = ocfs2_start_walk_page_trans(inode, page, from, to);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
handle = NULL;
goto out_unlock_data;
}
handle = ocfs2_start_walk_page_trans(inode, page, from, to);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out_unlock_data;
}
/* Mark our buffer early. We'd rather catch this error up here
* as opposed to after a successful commit_write which would
* require us to set back inode->i_size. */
ret = ocfs2_journal_access(handle, inode, di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret < 0) {
mlog_errno(ret);
goto out_commit;
}
/* Mark our buffer early. We'd rather catch this error up here
* as opposed to after a successful commit_write which would
* require us to set back inode->i_size. */
ret = ocfs2_journal_access(handle, inode, di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret < 0) {
mlog_errno(ret);
goto out_commit;
}
/* might update i_size */
......@@ -453,37 +447,28 @@ static int ocfs2_commit_write(struct file *file, struct page *page,
goto out_commit;
}
if (extending) {
loff_t size = (u64) i_size_read(inode);
struct ocfs2_dinode *di =
(struct ocfs2_dinode *)di_bh->b_data;
di = (struct ocfs2_dinode *)di_bh->b_data;
/* ocfs2_mark_inode_dirty is too heavy to use here. */
inode->i_blocks = ocfs2_align_bytes_to_sectors(size);
inode->i_ctime = inode->i_mtime = CURRENT_TIME;
/* ocfs2_mark_inode_dirty() is too heavy to use here. */
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
di->i_size = cpu_to_le64(size);
di->i_ctime = di->i_mtime =
cpu_to_le64(inode->i_mtime.tv_sec);
di->i_ctime_nsec = di->i_mtime_nsec =
cpu_to_le32(inode->i_mtime.tv_nsec);
inode->i_blocks = ocfs2_align_bytes_to_sectors((u64)(i_size_read(inode)));
di->i_size = cpu_to_le64((u64)i_size_read(inode));
ret = ocfs2_journal_dirty(handle, di_bh);
if (ret < 0) {
mlog_errno(ret);
goto out_commit;
}
ret = ocfs2_journal_dirty(handle, di_bh);
if (ret < 0) {
mlog_errno(ret);
goto out_commit;
}
BUG_ON(extending && (i_size_read(inode) != new_i_size));
out_commit:
if (handle)
ocfs2_commit_trans(handle);
ocfs2_commit_trans(handle);
out_unlock_data:
ocfs2_data_unlock(inode, 1);
out_unlock_meta:
ocfs2_meta_unlock(inode, locklevel);
ocfs2_meta_unlock(inode, 1);
out:
if (di_bh)
brelse(di_bh);
......
......@@ -100,6 +100,9 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
mlog_entry("(block=(%llu), nr=(%d), flags=%d, inode=%p)\n",
(unsigned long long)block, nr, flags, inode);
BUG_ON((flags & OCFS2_BH_READAHEAD) &&
(!inode || !(flags & OCFS2_BH_CACHED)));
if (osb == NULL || osb->sb == NULL || bhs == NULL) {
status = -EINVAL;
mlog_errno(status);
......@@ -140,6 +143,30 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
bh = bhs[i];
ignore_cache = 0;
/* There are three read-ahead cases here which we need to
* be concerned with. All three assume a buffer has
* previously been submitted with OCFS2_BH_READAHEAD
* and it hasn't yet completed I/O.
*
* 1) The current request is sync to disk. This rarely
* happens these days, and never when performance
* matters - the code can just wait on the buffer
* lock and re-submit.
*
* 2) The current request is cached, but not
* readahead. ocfs2_buffer_uptodate() will return
* false anyway, so we'll wind up waiting on the
* buffer lock to do I/O. We re-check the request
* with after getting the lock to avoid a re-submit.
*
* 3) The current request is readahead (and so must
* also be a caching one). We short circuit if the
* buffer is locked (under I/O) and if it's in the
* uptodate cache. The re-check from #2 catches the
* case that the previous read-ahead completes just
* before our is-it-in-flight check.
*/
if (flags & OCFS2_BH_CACHED &&
!ocfs2_buffer_uptodate(inode, bh)) {
mlog(ML_UPTODATE,
......@@ -169,6 +196,14 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
continue;
}
/* A read-ahead request was made - if the
* buffer is already under read-ahead from a
* previously submitted request than we are
* done here. */
if ((flags & OCFS2_BH_READAHEAD)
&& ocfs2_buffer_read_ahead(inode, bh))
continue;
lock_buffer(bh);
if (buffer_jbd(bh)) {
#ifdef CATCH_BH_JBD_RACES
......@@ -181,13 +216,22 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
continue;
#endif
}
/* Re-check ocfs2_buffer_uptodate() as a
* previously read-ahead buffer may have
* completed I/O while we were waiting for the
* buffer lock. */
if ((flags & OCFS2_BH_CACHED)
&& !(flags & OCFS2_BH_READAHEAD)
&& ocfs2_buffer_uptodate(inode, bh)) {
unlock_buffer(bh);
continue;
}
clear_buffer_uptodate(bh);
get_bh(bh); /* for end_buffer_read_sync() */
bh->b_end_io = end_buffer_read_sync;
if (flags & OCFS2_BH_READAHEAD)
submit_bh(READA, bh);
else
submit_bh(READ, bh);
submit_bh(READ, bh);
continue;
}
}
......@@ -197,34 +241,39 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
for (i = (nr - 1); i >= 0; i--) {
bh = bhs[i];
/* We know this can't have changed as we hold the
* inode sem. Avoid doing any work on the bh if the
* journal has it. */
if (!buffer_jbd(bh))
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
/* Status won't be cleared from here on out,
* so we can safely record this and loop back
* to cleanup the other buffers. Don't need to
* remove the clustered uptodate information
* for this bh as it's not marked locally
* uptodate. */
status = -EIO;
brelse(bh);
bhs[i] = NULL;
continue;
if (!(flags & OCFS2_BH_READAHEAD)) {
/* We know this can't have changed as we hold the
* inode sem. Avoid doing any work on the bh if the
* journal has it. */
if (!buffer_jbd(bh))
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
/* Status won't be cleared from here on out,
* so we can safely record this and loop back
* to cleanup the other buffers. Don't need to
* remove the clustered uptodate information
* for this bh as it's not marked locally
* uptodate. */
status = -EIO;
brelse(bh);
bhs[i] = NULL;
continue;
}
}
/* Always set the buffer in the cache, even if it was
* a forced read, or read-ahead which hasn't yet
* completed. */
if (inode)
ocfs2_set_buffer_uptodate(inode, bh);
}
if (inode)
mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
mlog(ML_BH_IO, "block=(%llu), nr=(%d), cached=%s\n",
mlog(ML_BH_IO, "block=(%llu), nr=(%d), cached=%s, flags=0x%x\n",
(unsigned long long)block, nr,
(!(flags & OCFS2_BH_CACHED) || ignore_cache) ? "no" : "yes");
(!(flags & OCFS2_BH_CACHED) || ignore_cache) ? "no" : "yes", flags);
bail:
......
......@@ -49,7 +49,7 @@ int ocfs2_read_blocks(struct ocfs2_super *osb,
#define OCFS2_BH_CACHED 1
#define OCFS2_BH_READAHEAD 8 /* use this to pass READA down to submit_bh */
#define OCFS2_BH_READAHEAD 8
static inline int ocfs2_read_block(struct ocfs2_super * osb, u64 off,
struct buffer_head **bh, int flags,
......
......@@ -320,8 +320,12 @@ static int compute_max_sectors(struct block_device *bdev)
max_pages = q->max_hw_segments;
max_pages--; /* Handle I/Os that straddle a page */
max_sectors = max_pages << (PAGE_SHIFT - 9);
if (max_pages) {
max_sectors = max_pages << (PAGE_SHIFT - 9);
} else {
/* If BIO contains 1 or less than 1 page. */
max_sectors = q->max_sectors;
}
/* Why is fls() 1-based???? */
pow_two_sectors = 1 << (fls(max_sectors) - 1);
......
......@@ -74,14 +74,14 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
int error = 0;
unsigned long offset, blk;
int i, num, stored;
unsigned long offset, blk, last_ra_blk = 0;
int i, stored;
struct buffer_head * bh, * tmp;
struct ocfs2_dir_entry * de;
int err;
struct inode *inode = filp->f_dentry->d_inode;
struct super_block * sb = inode->i_sb;
int have_disk_lock = 0;
unsigned int ra_sectors = 16;
mlog_entry("dirino=%llu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
......@@ -95,9 +95,8 @@ int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
mlog_errno(error);
/* we haven't got any yet, so propagate the error. */
stored = error;
goto bail;
goto bail_nolock;
}
have_disk_lock = 1;
offset = filp->f_pos & (sb->s_blocksize - 1);
......@@ -113,16 +112,21 @@ int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
continue;
}
/*
* Do the readahead (8k)
*/
if (!offset) {
for (i = 16 >> (sb->s_blocksize_bits - 9), num = 0;
/* The idea here is to begin with 8k read-ahead and to stay
* 4k ahead of our current position.
*
* TODO: Use the pagecache for this. We just need to
* make sure it's cluster-safe... */
if (!last_ra_blk
|| (((last_ra_blk - blk) << 9) <= (ra_sectors / 2))) {
for (i = ra_sectors >> (sb->s_blocksize_bits - 9);
i > 0; i--) {
tmp = ocfs2_bread(inode, ++blk, &err, 1);
if (tmp)
brelse(tmp);
}
last_ra_blk = blk;
ra_sectors = 8;
}
revalidate:
......@@ -194,9 +198,9 @@ revalidate:
stored = 0;
bail:
if (have_disk_lock)
ocfs2_meta_unlock(inode, 0);
ocfs2_meta_unlock(inode, 0);
bail_nolock:
mlog_exit(stored);
return stored;
......
......@@ -367,12 +367,10 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data)
goto do_ast;
}
mlog(ML_ERROR, "got %sast for unknown lock! cookie=%u:%llu, "
"name=%.*s, namelen=%u\n",
past->type == DLM_AST ? "" : "b",
dlm_get_lock_cookie_node(cookie),
dlm_get_lock_cookie_seq(cookie),
locklen, name, locklen);
mlog(0, "got %sast for unknown lock! cookie=%u:%llu, "
"name=%.*s, namelen=%u\n", past->type == DLM_AST ? "" : "b",
dlm_get_lock_cookie_node(cookie), dlm_get_lock_cookie_seq(cookie),
locklen, name, locklen);
ret = DLM_NORMAL;
unlock_out:
......
......@@ -1330,6 +1330,7 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
cpu_to_be64(ocfs2_pack_timespec(&inode->i_ctime));
lvb->lvb_imtime_packed =
cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime));
lvb->lvb_iattr = cpu_to_be32(oi->ip_attr);
mlog_meta_lvb(0, lockres);
......@@ -1360,6 +1361,9 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
oi->ip_clusters = be32_to_cpu(lvb->lvb_iclusters);
i_size_write(inode, be64_to_cpu(lvb->lvb_isize));
oi->ip_attr = be32_to_cpu(lvb->lvb_iattr);
ocfs2_set_inode_flags(inode);
/* fast-symlinks are a special case */
if (S_ISLNK(inode->i_mode) && !oi->ip_clusters)
inode->i_blocks = 0;
......@@ -2899,8 +2903,9 @@ void ocfs2_dump_meta_lvb_info(u64 level,
be32_to_cpu(lvb->lvb_iuid), be32_to_cpu(lvb->lvb_igid),
be16_to_cpu(lvb->lvb_imode));
mlog(level, "nlink %u, atime_packed 0x%llx, ctime_packed 0x%llx, "
"mtime_packed 0x%llx\n", be16_to_cpu(lvb->lvb_inlink),
"mtime_packed 0x%llx iattr 0x%x\n", be16_to_cpu(lvb->lvb_inlink),
(long long)be64_to_cpu(lvb->lvb_iatime_packed),
(long long)be64_to_cpu(lvb->lvb_ictime_packed),
(long long)be64_to_cpu(lvb->lvb_imtime_packed));
(long long)be64_to_cpu(lvb->lvb_imtime_packed),
be32_to_cpu(lvb->lvb_iattr));
}
......@@ -27,7 +27,7 @@
#ifndef DLMGLUE_H
#define DLMGLUE_H
#define OCFS2_LVB_VERSION 2
#define OCFS2_LVB_VERSION 3
struct ocfs2_meta_lvb {
__be32 lvb_version;
......@@ -40,7 +40,8 @@ struct ocfs2_meta_lvb {
__be64 lvb_isize;
__be16 lvb_imode;
__be16 lvb_inlink;
__be32 lvb_reserved[3];
__be32 lvb_iattr;
__be32 lvb_reserved[2];
};
/* ocfs2_meta_lock_full() and ocfs2_data_lock_full() 'arg_flags' flags */
......
......@@ -44,6 +44,7 @@
#include "file.h"
#include "sysfile.h"
#include "inode.h"
#include "ioctl.h"
#include "journal.h"
#include "mmap.h"
#include "suballoc.h"
......@@ -1227,10 +1228,12 @@ const struct file_operations ocfs2_fops = {
.open = ocfs2_file_open,
.aio_read = ocfs2_file_aio_read,
.aio_write = ocfs2_file_aio_write,
.ioctl = ocfs2_ioctl,
};
const struct file_operations ocfs2_dops = {
.read = generic_read_dir,
.readdir = ocfs2_readdir,
.fsync = ocfs2_sync_file,
.ioctl = ocfs2_ioctl,
};
......@@ -71,6 +71,26 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
struct inode *inode,
struct buffer_head *fe_bh);
void ocfs2_set_inode_flags(struct inode *inode)
{
unsigned int flags = OCFS2_I(inode)->ip_attr;
inode->i_flags &= ~(S_IMMUTABLE |
S_SYNC | S_APPEND | S_NOATIME | S_DIRSYNC);
if (flags & OCFS2_IMMUTABLE_FL)
inode->i_flags |= S_IMMUTABLE;
if (flags & OCFS2_SYNC_FL)
inode->i_flags |= S_SYNC;
if (flags & OCFS2_APPEND_FL)
inode->i_flags |= S_APPEND;
if (flags & OCFS2_NOATIME_FL)
inode->i_flags |= S_NOATIME;
if (flags & OCFS2_DIRSYNC_FL)
inode->i_flags |= S_DIRSYNC;
}
struct inode *ocfs2_ilookup_for_vote(struct ocfs2_super *osb,
u64 blkno,
int delete_vote)
......@@ -260,7 +280,6 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
inode->i_blocks =
ocfs2_align_bytes_to_sectors(le64_to_cpu(fe->i_size));
inode->i_mapping->a_ops = &ocfs2_aops;
inode->i_flags |= S_NOATIME;
inode->i_atime.tv_sec = le64_to_cpu(fe->i_atime);
inode->i_atime.tv_nsec = le32_to_cpu(fe->i_atime_nsec);
inode->i_mtime.tv_sec = le64_to_cpu(fe->i_mtime);
......@@ -276,6 +295,7 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
OCFS2_I(inode)->ip_orphaned_slot = OCFS2_INVALID_SLOT;
OCFS2_I(inode)->ip_attr = le32_to_cpu(fe->i_attr);
if (create_ino)
inode->i_ino = ino_from_blkno(inode->i_sb,
......@@ -330,6 +350,9 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
ocfs2_inode_lock_res_init(&OCFS2_I(inode)->ip_data_lockres,
OCFS2_LOCK_TYPE_DATA, inode);
ocfs2_set_inode_flags(inode);
inode->i_flags |= S_NOATIME;
status = 0;
bail:
mlog_exit(status);
......@@ -1027,12 +1050,8 @@ struct buffer_head *ocfs2_bread(struct inode *inode,
u64 p_blkno;
int readflags = OCFS2_BH_CACHED;
#if 0
/* only turn this on if we know we can deal with read_block
* returning nothing */
if (reada)
readflags |= OCFS2_BH_READAHEAD;
#endif
if (((u64)block << inode->i_sb->s_blocksize_bits) >=
i_size_read(inode)) {
......@@ -1131,6 +1150,7 @@ int ocfs2_mark_inode_dirty(struct ocfs2_journal_handle *handle,
spin_lock(&OCFS2_I(inode)->ip_lock);
fe->i_clusters = cpu_to_le32(OCFS2_I(inode)->ip_clusters);