original development tree for Linux kernel GTP module; now long in mainline.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

1275 lines
34 KiB

#include <linux/ceph/ceph_debug.h>
#include <linux/spinlock.h>
#include <linux/fs_struct.h>
#include <linux/namei.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>
12 years ago
#include <linux/slab.h>
#include <linux/sched.h>
#include "super.h"
#include "mds_client.h"
/*
* Directory operations: readdir, lookup, create, link, unlink,
* rename, etc.
*/
/*
* Ceph MDS operations are specified in terms of a base ino and
* relative path. Thus, the client can specify an operation on a
* specific inode (e.g., a getattr due to fstat(2)), or as a path
* relative to, say, the root directory.
*
* Normally, we limit ourselves to strict inode ops (no path component)
* or dentry operations (a single path component relative to an ino). The
* exception to this is open_root_dentry(), which will open the mount
* point by name.
*/
const struct inode_operations ceph_dir_iops;
const struct file_operations ceph_dir_fops;
const struct dentry_operations ceph_dentry_ops;
/*
* Initialize ceph dentry state.
*/
int ceph_init_dentry(struct dentry *dentry)
{
struct ceph_dentry_info *di;
if (dentry->d_fsdata)
return 0;
if (dentry->d_parent == NULL || /* nfs fh_to_dentry */
ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
d_set_d_op(dentry, &ceph_dentry_ops);
else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
else
d_set_d_op(dentry, &ceph_snap_dentry_ops);
di = kmem_cache_alloc(ceph_dentry_cachep, GFP_NOFS | __GFP_ZERO);
if (!di)
return -ENOMEM; /* oh well */
spin_lock(&dentry->d_lock);
if (dentry->d_fsdata) {
/* lost a race */
kmem_cache_free(ceph_dentry_cachep, di);
goto out_unlock;
}
di->dentry = dentry;
di->lease_session = NULL;
dentry->d_fsdata = di;
dentry->d_time = jiffies;
ceph_dentry_lru_add(dentry);
out_unlock:
spin_unlock(&dentry->d_lock);
return 0;
}
/*
* for readdir, we encode the directory frag and offset within that
* frag into f_pos.
*/
static unsigned fpos_frag(loff_t p)
{
return p >> 32;
}
static unsigned fpos_off(loff_t p)
{
return p & 0xffffffff;
}
/*
* When possible, we try to satisfy a readdir by peeking at the
* dcache. We make this work by carefully ordering dentries on
* d_u.d_child when we initially get results back from the MDS, and
* falling back to a "normal" sync readdir if any dentries in the dir
* are dropped.
*
* I_COMPLETE tells indicates we have all dentries in the dir. It is
* defined IFF we hold CEPH_CAP_FILE_SHARED (which will be revoked by
* the MDS if/when the directory is modified).
*/
static int __dcache_readdir(struct file *filp,
void *dirent, filldir_t filldir)
{
struct ceph_file_info *fi = filp->private_data;
struct dentry *parent = filp->f_dentry;
struct inode *dir = parent->d_inode;
struct list_head *p;
struct dentry *dentry, *last;
struct ceph_dentry_info *di;
int err = 0;
/* claim ref on last dentry we returned */
last = fi->dentry;
fi->dentry = NULL;
dout("__dcache_readdir %p at %llu (last %p)\n", dir, filp->f_pos,
last);
spin_lock(&parent->d_lock);
/* start at beginning? */
if (filp->f_pos == 2 || last == NULL ||
filp->f_pos < ceph_dentry(last)->offset) {
if (list_empty(&parent->d_subdirs))
goto out_unlock;
p = parent->d_subdirs.prev;
dout(" initial p %p/%p\n", p->prev, p->next);
} else {
p = last->d_u.d_child.prev;
}
more:
dentry = list_entry(p, struct dentry, d_u.d_child);
di = ceph_dentry(dentry);
while (1) {
dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next,
d_unhashed(dentry) ? "!hashed" : "hashed",
parent->d_subdirs.prev, parent->d_subdirs.next);
if (p == &parent->d_subdirs) {
fi->at_end = 1;
goto out_unlock;
}
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
if (!d_unhashed(dentry) && dentry->d_inode &&
ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
filp->f_pos <= di->offset)
break;
dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry,
dentry->d_name.len, dentry->d_name.name, di->offset,
filp->f_pos, d_unhashed(dentry) ? " unhashed" : "",
!dentry->d_inode ? " null" : "");
spin_unlock(&dentry->d_lock);
p = p->prev;
dentry = list_entry(p, struct dentry, d_u.d_child);
di = ceph_dentry(dentry);
}
dget_dlock(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&parent->d_lock);
dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, filp->f_pos,
dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
filp->f_pos = di->offset;
err = filldir(dirent, dentry->d_name.name,
dentry->d_name.len, di->offset,
ceph_translate_ino(dentry->d_sb, dentry->d_inode->i_ino),
dentry->d_inode->i_mode >> 12);
if (last) {
if (err < 0) {
/* remember our position */
fi->dentry = last;
fi->next_offset = di->offset;
} else {
dput(last);
}
}
last = dentry;
if (err < 0)
goto out;
filp->f_pos++;
/* make sure a dentry wasn't dropped while we didn't have parent lock */
if (!ceph_i_test(dir, CEPH_I_COMPLETE)) {
dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
err = -EAGAIN;
goto out;
}
spin_lock(&parent->d_lock);
p = p->prev; /* advance to next dentry */
goto more;
out_unlock:
spin_unlock(&parent->d_lock);
out:
if (last)
dput(last);
return err;
}
/*
* make note of the last dentry we read, so we can
* continue at the same lexicographical point,
* regardless of what dir changes take place on the
* server.
*/
static int note_last_dentry(struct ceph_file_info *fi, const char *name,
int len)
{
kfree(fi->last_name);
fi->last_name = kmalloc(len+1, GFP_NOFS);
if (!fi->last_name)
return -ENOMEM;
memcpy(fi->last_name, name, len);
fi->last_name[len] = 0;
dout("note_last_dentry '%s'\n", fi->last_name);
return 0;
}
static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
struct ceph_file_info *fi = filp->private_data;
struct inode *inode = filp->f_dentry->d_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
unsigned frag = fpos_frag(filp->f_pos);
int off = fpos_off(filp->f_pos);
int err;
u32 ftype;
struct ceph_mds_reply_info_parsed *rinfo;
const int max_entries = fsc->mount_options->max_readdir;
const int max_bytes = fsc->mount_options->max_readdir_bytes;
dout("readdir %p filp %p frag %u off %u\n", inode, filp, frag, off);
if (fi->at_end)
return 0;
/* always start with . and .. */
if (filp->f_pos == 0) {
/* note dir version at start of readdir so we can tell
* if any dentries get dropped */
fi->dir_release_count = ci->i_release_count;
dout("readdir off 0 -> '.'\n");
if (filldir(dirent, ".", 1, ceph_make_fpos(0, 0),
ceph_translate_ino(inode->i_sb, inode->i_ino),
inode->i_mode >> 12) < 0)
return 0;
filp->f_pos = 1;
off = 1;
}
if (filp->f_pos == 1) {
ino_t ino = filp->f_dentry->d_parent->d_inode->i_ino;
dout("readdir off 1 -> '..'\n");
if (filldir(dirent, "..", 2, ceph_make_fpos(0, 1),
ceph_translate_ino(inode->i_sb, ino),
inode->i_mode >> 12) < 0)
return 0;
filp->f_pos = 2;
off = 2;
}
/* can we use the dcache? */
spin_lock(&inode->i_lock);
if ((filp->f_pos == 2 || fi->dentry) &&
!ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
ceph_snap(inode) != CEPH_SNAPDIR &&
(ci->i_ceph_flags & CEPH_I_COMPLETE) &&
__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
spin_unlock(&inode->i_lock);
err = __dcache_readdir(filp, dirent, filldir);
if (err != -EAGAIN)
return err;
} else {
spin_unlock(&inode->i_lock);
}
if (fi->dentry) {
err = note_last_dentry(fi, fi->dentry->d_name.name,
fi->dentry->d_name.len);
if (err)
return err;
dput(fi->dentry);
fi->dentry = NULL;
}
/* proceed with a normal readdir */
more:
/* do we have the correct frag content buffered? */
if (fi->frag != frag || fi->last_readdir == NULL) {
struct ceph_mds_request *req;
int op = ceph_snap(inode) == CEPH_SNAPDIR ?
CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR;
/* discard old result, if any */
if (fi->last_readdir) {
ceph_mdsc_put_request(fi->last_readdir);
fi->last_readdir = NULL;
}
/* requery frag tree, as the frag topology may have changed */
frag = ceph_choose_frag(ceph_inode(inode), frag, NULL, NULL);
dout("readdir fetching %llx.%llx frag %x offset '%s'\n",
ceph_vinop(inode), frag, fi->last_name);
req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = igrab(inode);
req->r_dentry = dget(filp->f_dentry);
/* hints to request -> mds selection code */
req->r_direct_mode = USE_AUTH_MDS;
req->r_direct_hash = ceph_frag_value(frag);
req->r_direct_is_hash = true;
req->r_path2 = kstrdup(fi->last_name, GFP_NOFS);
req->r_readdir_offset = fi->next_offset;
req->r_args.readdir.frag = cpu_to_le32(frag);
req->r_args.readdir.max_entries = cpu_to_le32(max_entries);
req->r_args.readdir.max_bytes = cpu_to_le32(max_bytes);
req->r_num_caps = max_entries + 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (err < 0) {
ceph_mdsc_put_request(req);
return err;
}
dout("readdir got and parsed readdir result=%d"
" on frag %x, end=%d, complete=%d\n", err, frag,
(int)req->r_reply_info.dir_end,
(int)req->r_reply_info.dir_complete);
if (!req->r_did_prepopulate) {
dout("readdir !did_prepopulate");
fi->dir_release_count--; /* preclude I_COMPLETE */
}
/* note next offset and last dentry name */
fi->offset = fi->next_offset;
fi->last_readdir = req;
if (req->r_reply_info.dir_end) {
kfree(fi->last_name);
fi->last_name = NULL;
if (ceph_frag_is_rightmost(frag))
fi->next_offset = 2;
else
fi->next_offset = 0;
} else {
rinfo = &req->r_reply_info;
err = note_last_dentry(fi,
rinfo->dir_dname[rinfo->dir_nr-1],
rinfo->dir_dname_len[rinfo->dir_nr-1]);
if (err)
return err;
fi->next_offset += rinfo->dir_nr;
}
}
rinfo = &fi->last_readdir->r_reply_info;
dout("readdir frag %x num %d off %d chunkoff %d\n", frag,
rinfo->dir_nr, off, fi->offset);
while (off - fi->offset >= 0 && off - fi->offset < rinfo->dir_nr) {
u64 pos = ceph_make_fpos(frag, off);
struct ceph_mds_reply_inode *in =
rinfo->dir_in[off - fi->offset].in;
struct ceph_vino vino;
ino_t ino;
dout("readdir off %d (%d/%d) -> %lld '%.*s' %p\n",
off, off - fi->offset, rinfo->dir_nr, pos,
rinfo->dir_dname_len[off - fi->offset],
rinfo->dir_dname[off - fi->offset], in);
BUG_ON(!in);
ftype = le32_to_cpu(in->mode) >> 12;
vino.ino = le64_to_cpu(in->ino);
vino.snap = le64_to_cpu(in->snapid);
ino = ceph_vino_to_ino(vino);
if (filldir(dirent,
rinfo->dir_dname[off - fi->offset],
rinfo->dir_dname_len[off - fi->offset],
pos,
ceph_translate_ino(inode->i_sb, ino), ftype) < 0) {
dout("filldir stopping us...\n");
return 0;
}
off++;
filp->f_pos = pos + 1;
}
if (fi->last_name) {
ceph_mdsc_put_request(fi->last_readdir);
fi->last_readdir = NULL;
goto more;
}
/* more frags? */
if (!ceph_frag_is_rightmost(frag)) {
frag = ceph_frag_next(frag);
off = 0;
filp->f_pos = ceph_make_fpos(frag, off);
dout("readdir next frag is %x\n", frag);
goto more;
}
fi->at_end = 1;
/*
* if dir_release_count still matches the dir, no dentries
* were released during the whole readdir, and we should have
* the complete dir contents in our cache.
*/
spin_lock(&inode->i_lock);
if (ci->i_release_count == fi->dir_release_count) {
dout(" marking %p complete\n", inode);
/* ci->i_ceph_flags |= CEPH_I_COMPLETE; */
ci->i_max_offset = filp->f_pos;
}
spin_unlock(&inode->i_lock);
dout("readdir %p filp %p done.\n", inode, filp);
return 0;
}
static void reset_readdir(struct ceph_file_info *fi)
{
if (fi->last_readdir) {
ceph_mdsc_put_request(fi->last_readdir);
fi->last_readdir = NULL;
}
kfree(fi->last_name);
fi->last_name = NULL;
fi->next_offset = 2; /* compensate for . and .. */
if (fi->dentry) {
dput(fi->dentry);
fi->dentry = NULL;
}
fi->at_end = 0;
}
static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int origin)
{
struct ceph_file_info *fi = file->private_data;
struct inode *inode = file->f_mapping->host;
loff_t old_offset = offset;
loff_t retval;
mutex_lock(&inode->i_mutex);
switch (origin) {
case SEEK_END:
offset += inode->i_size + 2; /* FIXME */
break;
case SEEK_CUR:
offset += file->f_pos;
}
retval = -EINVAL;
if (offset >= 0 && offset <= inode->i_sb->s_maxbytes) {
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
fi->at_end = 0;
}
retval = offset;
/*
* discard buffered readdir content on seekdir(0), or
* seek to new frag, or seek prior to current chunk.
*/
if (offset == 0 ||
fpos_frag(offset) != fpos_frag(old_offset) ||
fpos_off(offset) < fi->offset) {
dout("dir_llseek dropping %p content\n", file);
reset_readdir(fi);
}
/* bump dir_release_count if we did a forward seek */
if (offset > old_offset)
fi->dir_release_count--;
}
mutex_unlock(&inode->i_mutex);
return retval;
}
/*
* Process result of a lookup/open request.
*
* Mainly, make sure we return the final req->r_dentry (if it already
* existed) in place of the original VFS-provided dentry when they
* differ.
*
* Gracefully handle the case where the MDS replies with -ENOENT and
* no trace (which it may do, at its discretion, e.g., if it doesn't
* care to issue a lease on the negative dentry).
*/
struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
struct dentry *dentry, int err)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
struct inode *parent = dentry->d_parent->d_inode;
/* .snap dir? */
if (err == -ENOENT &&
ceph_snap(parent) == CEPH_NOSNAP &&
strcmp(dentry->d_name.name,
fsc->mount_options->snapdir_name) == 0) {
struct inode *inode = ceph_get_snapdir(parent);
dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n",
dentry, dentry->d_name.len, dentry->d_name.name, inode);
BUG_ON(!d_unhashed(dentry));
d_add(dentry, inode);
err = 0;
}
if (err == -ENOENT) {
/* no trace? */
err = 0;
if (!req->r_reply_info.head->is_dentry) {
dout("ENOENT and no trace, dentry %p inode %p\n",
dentry, dentry->d_inode);
if (dentry->d_inode) {
d_drop(dentry);
err = -ENOENT;
} else {
d_add(dentry, NULL);
}
}
}
if (err)
dentry = ERR_PTR(err);
else if (dentry != req->r_dentry)
dentry = dget(req->r_dentry); /* we got spliced */
else
dentry = NULL;
return dentry;
}
static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
{
return ceph_ino(inode) == CEPH_INO_ROOT &&
strncmp(dentry->d_name.name, ".ceph", 5) == 0;
}
/*
* Look up a single dir entry. If there is a lookup intent, inform
* the MDS so that it gets our 'caps wanted' value in a single op.
*/
static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
int op;
int err;
dout("lookup %p dentry %p '%.*s'\n",
dir, dentry, dentry->d_name.len, dentry->d_name.name);
if (dentry->d_name.len > NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
err = ceph_init_dentry(dentry);
if (err < 0)
return ERR_PTR(err);
/* open (but not create!) intent? */
if (nd &&
(nd->flags & LOOKUP_OPEN) &&
(nd->flags & LOOKUP_CONTINUE) == 0 && /* only open last component */
!(nd->intent.open.flags & O_CREAT)) {
int mode = nd->intent.open.create_mode & ~current->fs->umask;
return ceph_lookup_open(dir, dentry, nd, mode, 1);
}
/* can we conclude ENOENT locally? */
if (dentry->d_inode == NULL) {
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_dentry_info *di = ceph_dentry(dentry);
spin_lock(&dir->i_lock);
dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags);
if (strncmp(dentry->d_name.name,
fsc->mount_options->snapdir_name,
dentry->d_name.len) &&
!is_root_ceph_dentry(dir, dentry) &&
(ci->i_ceph_flags & CEPH_I_COMPLETE) &&
(__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) {
spin_unlock(&dir->i_lock);
dout(" dir %p complete, -ENOENT\n", dir);
d_add(dentry, NULL);
di->lease_shared_gen = ci->i_shared_gen;
return NULL;
}
spin_unlock(&dir->i_lock);
}
op = ceph_snap(dir) == CEPH_SNAPDIR ?
CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;
req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
if (IS_ERR(req))
return ERR_CAST(req);
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
/* we only need inode linkage */
req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE);
req->r_locked_dir = dir;
err = ceph_mdsc_do_request(mdsc, NULL, req);
dentry = ceph_finish_lookup(req, dentry, err);
ceph_mdsc_put_request(req); /* will dput(dentry) */
dout("lookup result=%p\n", dentry);
return dentry;
}
/*
* If we do a create but get no trace back from the MDS, follow up with
* a lookup (the VFS expects us to link up the provided dentry).
*/
int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
{
struct dentry *result = ceph_lookup(dir, dentry, NULL);
if (result && !IS_ERR(result)) {
/*
* We created the item, then did a lookup, and found
* it was already linked to another inode we already
* had in our cache (and thus got spliced). Link our
* dentry to that inode, but don't hash it, just in
* case the VFS wants to dereference it.
*/
BUG_ON(!result->d_inode);
d_instantiate(dentry, result->d_inode);
return 0;
}
return PTR_ERR(result);
}
static int ceph_mknod(struct inode *dir, struct dentry *dentry,
int mode, dev_t rdev)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
int err;
if (ceph_snap(dir) != CEPH_NOSNAP)
return -EROFS;
dout("mknod in dir %p dentry %p mode 0%o rdev %d\n",
dir, dentry, mode, rdev);
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_MKNOD, USE_AUTH_MDS);
if (IS_ERR(req)) {
d_drop(dentry);
return PTR_ERR(req);
}
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
req->r_locked_dir = dir;
req->r_args.mknod.mode = cpu_to_le32(mode);
req->r_args.mknod.rdev = cpu_to_le32(rdev);
req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
err = ceph_mdsc_do_request(mdsc, dir, req);
if (!err && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
if (err)
d_drop(dentry);
return err;
}
static int ceph_create(struct inode *dir, struct dentry *dentry, int mode,
struct nameidata *nd)
{
dout("create in dir %p dentry %p name '%.*s'\n",
dir, dentry, dentry->d_name.len, dentry->d_name.name);
if (ceph_snap(dir) != CEPH_NOSNAP)
return -EROFS;
if (nd) {
BUG_ON((nd->flags & LOOKUP_OPEN) == 0);
dentry = ceph_lookup_open(dir, dentry, nd, mode, 0);
/* hrm, what should i do here if we get aliased? */
if (IS_ERR(dentry))
return PTR_ERR(dentry);
return 0;
}
/* fall back to mknod */
return ceph_mknod(dir, dentry, (mode & ~S_IFMT) | S_IFREG, 0);
}
static int ceph_symlink(struct inode *dir, struct dentry *dentry,
const char *dest)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
int err;
if (ceph_snap(dir) != CEPH_NOSNAP)
return -EROFS;
dout("symlink in dir %p dentry %p to '%s'\n", dir, dentry, dest);
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SYMLINK, USE_AUTH_MDS);
if (IS_ERR(req)) {
d_drop(dentry);
return PTR_ERR(req);
}
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
req->r_path2 = kstrdup(dest, GFP_NOFS);
req->r_locked_dir = dir;
req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
err = ceph_mdsc_do_request(mdsc, dir, req);
if (!err && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
if (err)
d_drop(dentry);
return err;
}
static int ceph_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
int err = -EROFS;
int op;
if (ceph_snap(dir) == CEPH_SNAPDIR) {
/* mkdir .snap/foo is a MKSNAP */
op = CEPH_MDS_OP_MKSNAP;
dout("mksnap dir %p snap '%.*s' dn %p\n", dir,
dentry->d_name.len, dentry->d_name.name, dentry);
} else if (ceph_snap(dir) == CEPH_NOSNAP) {
dout("mkdir dir %p dn %p mode 0%o\n", dir, dentry, mode);
op = CEPH_MDS_OP_MKDIR;
} else {
goto out;
}
req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
req->r_locked_dir = dir;
req->r_args.mkdir.mode = cpu_to_le32(mode);
req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
err = ceph_mdsc_do_request(mdsc, dir, req);
if (!err && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
out:
if (err < 0)
d_drop(dentry);
return err;
}
static int ceph_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
int err;