2010-04-07 05:14:15 +07:00
|
|
|
#include <linux/ceph/ceph_debug.h>
|
2009-10-07 01:31:13 +07:00
|
|
|
|
|
|
|
#include <linux/exportfs.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 15:04:11 +07:00
|
|
|
#include <linux/slab.h>
|
2009-10-07 01:31:13 +07:00
|
|
|
#include <asm/unaligned.h>
|
|
|
|
|
|
|
|
#include "super.h"
|
2010-04-07 05:14:15 +07:00
|
|
|
#include "mds_client.h"
|
2009-10-07 01:31:13 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Basic fh
|
|
|
|
*/
|
|
|
|
struct ceph_nfs_fh {
|
|
|
|
u64 ino;
|
|
|
|
} __attribute__ ((packed));
|
|
|
|
|
|
|
|
/*
|
2014-03-01 17:05:41 +07:00
|
|
|
* Larger fh that includes parent ino.
|
2009-10-07 01:31:13 +07:00
|
|
|
*/
|
|
|
|
struct ceph_nfs_confh {
|
|
|
|
u64 ino, parent_ino;
|
|
|
|
} __attribute__ ((packed));
|
|
|
|
|
2012-04-06 02:07:36 +07:00
|
|
|
static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
|
|
|
|
struct inode *parent_inode)
|
2009-10-07 01:31:13 +07:00
|
|
|
{
|
2010-10-05 17:33:41 +07:00
|
|
|
int type;
|
2009-10-07 01:31:13 +07:00
|
|
|
struct ceph_nfs_fh *fh = (void *)rawfh;
|
|
|
|
struct ceph_nfs_confh *cfh = (void *)rawfh;
|
2010-10-05 17:33:41 +07:00
|
|
|
int connected_handle_length = sizeof(*cfh)/4;
|
|
|
|
int handle_length = sizeof(*fh)/4;
|
2009-10-07 01:31:13 +07:00
|
|
|
|
|
|
|
/* don't re-export snaps */
|
|
|
|
if (ceph_snap(inode) != CEPH_NOSNAP)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2014-03-01 17:05:41 +07:00
|
|
|
if (parent_inode && (*max_len < connected_handle_length)) {
|
|
|
|
*max_len = connected_handle_length;
|
|
|
|
return FILEID_INVALID;
|
|
|
|
} else if (*max_len < handle_length) {
|
|
|
|
*max_len = handle_length;
|
|
|
|
return FILEID_INVALID;
|
|
|
|
}
|
2012-12-19 05:21:23 +07:00
|
|
|
|
2014-03-01 17:05:41 +07:00
|
|
|
if (parent_inode) {
|
|
|
|
dout("encode_fh %llx with parent %llx\n",
|
|
|
|
ceph_ino(inode), ceph_ino(parent_inode));
|
2012-04-06 02:07:36 +07:00
|
|
|
cfh->ino = ceph_ino(inode);
|
2014-03-01 17:05:41 +07:00
|
|
|
cfh->parent_ino = ceph_ino(parent_inode);
|
2010-10-05 17:33:41 +07:00
|
|
|
*max_len = connected_handle_length;
|
2014-03-01 17:05:41 +07:00
|
|
|
type = FILEID_INO32_GEN_PARENT;
|
2009-10-07 01:31:13 +07:00
|
|
|
} else {
|
2014-03-01 17:05:41 +07:00
|
|
|
dout("encode_fh %llx\n", ceph_ino(inode));
|
|
|
|
fh->ino = ceph_ino(inode);
|
2010-10-05 17:33:42 +07:00
|
|
|
*max_len = handle_length;
|
2014-03-01 17:05:41 +07:00
|
|
|
type = FILEID_INO32_GEN;
|
2009-10-07 01:31:13 +07:00
|
|
|
}
|
|
|
|
return type;
|
|
|
|
}
|
|
|
|
|
2014-03-01 17:05:41 +07:00
|
|
|
static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
|
2009-10-07 01:31:13 +07:00
|
|
|
{
|
2011-04-06 23:31:40 +07:00
|
|
|
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
|
2009-10-07 01:31:13 +07:00
|
|
|
struct inode *inode;
|
|
|
|
struct ceph_vino vino;
|
|
|
|
int err;
|
|
|
|
|
2014-03-01 17:05:41 +07:00
|
|
|
vino.ino = ino;
|
2009-10-07 01:31:13 +07:00
|
|
|
vino.snap = CEPH_NOSNAP;
|
|
|
|
inode = ceph_find_inode(sb, vino);
|
2011-04-06 23:31:40 +07:00
|
|
|
if (!inode) {
|
|
|
|
struct ceph_mds_request *req;
|
2016-03-07 09:34:50 +07:00
|
|
|
int mask;
|
2011-04-06 23:31:40 +07:00
|
|
|
|
|
|
|
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
|
|
|
|
USE_ANY_MDS);
|
|
|
|
if (IS_ERR(req))
|
|
|
|
return ERR_CAST(req);
|
|
|
|
|
2016-03-07 09:34:50 +07:00
|
|
|
mask = CEPH_STAT_CAP_INODE;
|
|
|
|
if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
|
|
|
|
mask |= CEPH_CAP_XATTR_SHARED;
|
|
|
|
req->r_args.getattr.mask = cpu_to_le32(mask);
|
|
|
|
|
2011-04-06 23:31:40 +07:00
|
|
|
req->r_ino1 = vino;
|
|
|
|
req->r_num_caps = 1;
|
|
|
|
err = ceph_mdsc_do_request(mdsc, NULL, req);
|
2011-04-06 23:35:00 +07:00
|
|
|
inode = req->r_target_inode;
|
|
|
|
if (inode)
|
2011-05-27 23:24:26 +07:00
|
|
|
ihold(inode);
|
2011-04-06 23:31:40 +07:00
|
|
|
ceph_mdsc_put_request(req);
|
|
|
|
if (!inode)
|
|
|
|
return ERR_PTR(-ESTALE);
|
2017-05-17 18:21:07 +07:00
|
|
|
if (inode->i_nlink == 0) {
|
|
|
|
iput(inode);
|
|
|
|
return ERR_PTR(-ESTALE);
|
|
|
|
}
|
2011-04-06 23:31:40 +07:00
|
|
|
}
|
2009-10-07 01:31:13 +07:00
|
|
|
|
2016-10-29 09:05:13 +07:00
|
|
|
return d_obtain_alias(inode);
|
2009-10-07 01:31:13 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2014-03-01 17:05:41 +07:00
|
|
|
* convert regular fh to dentry
|
2009-10-07 01:31:13 +07:00
|
|
|
*/
|
2014-03-01 17:05:41 +07:00
|
|
|
static struct dentry *ceph_fh_to_dentry(struct super_block *sb,
|
|
|
|
struct fid *fid,
|
|
|
|
int fh_len, int fh_type)
|
2009-10-07 01:31:13 +07:00
|
|
|
{
|
2014-03-01 17:05:41 +07:00
|
|
|
struct ceph_nfs_fh *fh = (void *)fid->raw;
|
2009-10-07 01:31:13 +07:00
|
|
|
|
2014-03-01 17:05:41 +07:00
|
|
|
if (fh_type != FILEID_INO32_GEN &&
|
|
|
|
fh_type != FILEID_INO32_GEN_PARENT)
|
|
|
|
return NULL;
|
|
|
|
if (fh_len < sizeof(*fh) / 4)
|
|
|
|
return NULL;
|
2009-10-07 01:31:13 +07:00
|
|
|
|
2014-03-01 17:05:41 +07:00
|
|
|
dout("fh_to_dentry %llx\n", fh->ino);
|
|
|
|
return __fh_to_dentry(sb, fh->ino);
|
2009-10-07 01:31:13 +07:00
|
|
|
}
|
|
|
|
|
2014-03-01 21:11:45 +07:00
|
|
|
static struct dentry *__get_parent(struct super_block *sb,
|
|
|
|
struct dentry *child, u64 ino)
|
|
|
|
{
|
|
|
|
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
|
|
|
|
struct ceph_mds_request *req;
|
|
|
|
struct inode *inode;
|
2016-03-07 09:34:50 +07:00
|
|
|
int mask;
|
2014-03-01 21:11:45 +07:00
|
|
|
int err;
|
|
|
|
|
|
|
|
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPPARENT,
|
|
|
|
USE_ANY_MDS);
|
|
|
|
if (IS_ERR(req))
|
|
|
|
return ERR_CAST(req);
|
|
|
|
|
|
|
|
if (child) {
|
2015-03-18 05:25:59 +07:00
|
|
|
req->r_inode = d_inode(child);
|
|
|
|
ihold(d_inode(child));
|
2014-03-01 21:11:45 +07:00
|
|
|
} else {
|
|
|
|
req->r_ino1 = (struct ceph_vino) {
|
|
|
|
.ino = ino,
|
|
|
|
.snap = CEPH_NOSNAP,
|
|
|
|
};
|
|
|
|
}
|
2016-03-07 09:34:50 +07:00
|
|
|
|
|
|
|
mask = CEPH_STAT_CAP_INODE;
|
|
|
|
if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
|
|
|
|
mask |= CEPH_CAP_XATTR_SHARED;
|
|
|
|
req->r_args.getattr.mask = cpu_to_le32(mask);
|
|
|
|
|
2014-03-01 21:11:45 +07:00
|
|
|
req->r_num_caps = 1;
|
|
|
|
err = ceph_mdsc_do_request(mdsc, NULL, req);
|
|
|
|
inode = req->r_target_inode;
|
|
|
|
if (inode)
|
|
|
|
ihold(inode);
|
|
|
|
ceph_mdsc_put_request(req);
|
|
|
|
if (!inode)
|
|
|
|
return ERR_PTR(-ENOENT);
|
|
|
|
|
2016-10-29 09:05:13 +07:00
|
|
|
return d_obtain_alias(inode);
|
2014-03-01 21:11:45 +07:00
|
|
|
}
|
|
|
|
|
2014-04-09 13:11:31 +07:00
|
|
|
static struct dentry *ceph_get_parent(struct dentry *child)
|
2014-03-01 21:11:45 +07:00
|
|
|
{
|
|
|
|
/* don't re-export snaps */
|
2015-03-18 05:25:59 +07:00
|
|
|
if (ceph_snap(d_inode(child)) != CEPH_NOSNAP)
|
2014-03-01 21:11:45 +07:00
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
|
|
|
dout("get_parent %p ino %llx.%llx\n",
|
2015-03-18 05:25:59 +07:00
|
|
|
child, ceph_vinop(d_inode(child)));
|
2014-03-01 21:11:45 +07:00
|
|
|
return __get_parent(child->d_sb, child, 0);
|
|
|
|
}
|
|
|
|
|
2009-10-07 01:31:13 +07:00
|
|
|
/*
|
2014-03-01 22:09:05 +07:00
|
|
|
* convert regular fh to parent
|
2009-10-07 01:31:13 +07:00
|
|
|
*/
|
|
|
|
static struct dentry *ceph_fh_to_parent(struct super_block *sb,
|
2014-03-01 22:09:05 +07:00
|
|
|
struct fid *fid,
|
2009-10-07 01:31:13 +07:00
|
|
|
int fh_len, int fh_type)
|
|
|
|
{
|
|
|
|
struct ceph_nfs_confh *cfh = (void *)fid->raw;
|
|
|
|
struct dentry *dentry;
|
|
|
|
|
2014-03-01 22:09:05 +07:00
|
|
|
if (fh_type != FILEID_INO32_GEN_PARENT)
|
|
|
|
return NULL;
|
tmpfs,ceph,gfs2,isofs,reiserfs,xfs: fix fh_len checking
Fuzzing with trinity oopsed on the 1st instruction of shmem_fh_to_dentry(),
u64 inum = fid->raw[2];
which is unhelpfully reported as at the end of shmem_alloc_inode():
BUG: unable to handle kernel paging request at ffff880061cd3000
IP: [<ffffffff812190d0>] shmem_alloc_inode+0x40/0x40
Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
Call Trace:
[<ffffffff81488649>] ? exportfs_decode_fh+0x79/0x2d0
[<ffffffff812d77c3>] do_handle_open+0x163/0x2c0
[<ffffffff812d792c>] sys_open_by_handle_at+0xc/0x10
[<ffffffff83a5f3f8>] tracesys+0xe1/0xe6
Right, tmpfs is being stupid to access fid->raw[2] before validating that
fh_len includes it: the buffer kmalloc'ed by do_sys_name_to_handle() may
fall at the end of a page, and the next page not be present.
But some other filesystems (ceph, gfs2, isofs, reiserfs, xfs) are being
careless about fh_len too, in fh_to_dentry() and/or fh_to_parent(), and
could oops in the same way: add the missing fh_len checks to those.
Reported-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Sage Weil <sage@inktank.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-10-08 10:32:51 +07:00
|
|
|
if (fh_len < sizeof(*cfh) / 4)
|
2014-03-01 22:09:05 +07:00
|
|
|
return NULL;
|
2009-10-07 01:31:13 +07:00
|
|
|
|
2014-03-01 22:09:05 +07:00
|
|
|
dout("fh_to_parent %llx\n", cfh->parent_ino);
|
|
|
|
dentry = __get_parent(sb, NULL, cfh->ino);
|
2016-06-25 10:49:03 +07:00
|
|
|
if (unlikely(dentry == ERR_PTR(-ENOENT)))
|
2014-03-01 22:09:05 +07:00
|
|
|
dentry = __fh_to_dentry(sb, cfh->parent_ino);
|
2009-10-07 01:31:13 +07:00
|
|
|
return dentry;
|
|
|
|
}
|
|
|
|
|
2014-03-06 15:40:32 +07:00
|
|
|
static int ceph_get_name(struct dentry *parent, char *name,
|
|
|
|
struct dentry *child)
|
|
|
|
{
|
|
|
|
struct ceph_mds_client *mdsc;
|
|
|
|
struct ceph_mds_request *req;
|
|
|
|
int err;
|
|
|
|
|
2015-03-18 05:25:59 +07:00
|
|
|
mdsc = ceph_inode_to_client(d_inode(child))->mdsc;
|
2014-03-06 15:40:32 +07:00
|
|
|
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
|
|
|
|
USE_ANY_MDS);
|
|
|
|
if (IS_ERR(req))
|
|
|
|
return PTR_ERR(req);
|
|
|
|
|
2016-01-23 03:40:57 +07:00
|
|
|
inode_lock(d_inode(parent));
|
2014-03-06 15:40:32 +07:00
|
|
|
|
2015-03-18 05:25:59 +07:00
|
|
|
req->r_inode = d_inode(child);
|
|
|
|
ihold(d_inode(child));
|
|
|
|
req->r_ino2 = ceph_vino(d_inode(parent));
|
2017-01-31 22:28:26 +07:00
|
|
|
req->r_parent = d_inode(parent);
|
|
|
|
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
|
2014-03-06 15:40:32 +07:00
|
|
|
req->r_num_caps = 2;
|
|
|
|
err = ceph_mdsc_do_request(mdsc, NULL, req);
|
|
|
|
|
2016-01-23 03:40:57 +07:00
|
|
|
inode_unlock(d_inode(parent));
|
2014-03-06 15:40:32 +07:00
|
|
|
|
|
|
|
if (!err) {
|
|
|
|
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
|
|
|
|
memcpy(name, rinfo->dname, rinfo->dname_len);
|
|
|
|
name[rinfo->dname_len] = 0;
|
|
|
|
dout("get_name %p ino %llx.%llx name %s\n",
|
2015-03-18 05:25:59 +07:00
|
|
|
child, ceph_vinop(d_inode(child)), name);
|
2014-03-06 15:40:32 +07:00
|
|
|
} else {
|
|
|
|
dout("get_name %p ino %llx.%llx err %d\n",
|
2015-03-18 05:25:59 +07:00
|
|
|
child, ceph_vinop(d_inode(child)), err);
|
2014-03-06 15:40:32 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
ceph_mdsc_put_request(req);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2009-10-07 01:31:13 +07:00
|
|
|
const struct export_operations ceph_export_ops = {
|
|
|
|
.encode_fh = ceph_encode_fh,
|
|
|
|
.fh_to_dentry = ceph_fh_to_dentry,
|
|
|
|
.fh_to_parent = ceph_fh_to_parent,
|
2014-03-01 21:11:45 +07:00
|
|
|
.get_parent = ceph_get_parent,
|
2014-03-06 15:40:32 +07:00
|
|
|
.get_name = ceph_get_name,
|
2009-10-07 01:31:13 +07:00
|
|
|
};
|