mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-22 00:40:03 +00:00
![David Howells](/assets/img/avatar_default.png)
Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2216 lines
60 KiB
C
2216 lines
60 KiB
C
#include <linux/ceph/ceph_debug.h>
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/string.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/xattr.h>
|
|
#include <linux/posix_acl.h>
|
|
#include <linux/random.h>
|
|
#include <linux/sort.h>
|
|
|
|
#include "super.h"
|
|
#include "mds_client.h"
|
|
#include "cache.h"
|
|
#include <linux/ceph/decode.h>
|
|
|
|
/*
|
|
* Ceph inode operations
|
|
*
|
|
* Implement basic inode helpers (get, alloc) and inode ops (getattr,
|
|
* setattr, etc.), xattr helpers, and helpers for assimilating
|
|
* metadata returned by the MDS into our cache.
|
|
*
|
|
* Also define helpers for doing asynchronous writeback, invalidation,
|
|
* and truncation for the benefit of those who can't afford to block
|
|
* (typically because they are in the message handler path).
|
|
*/
|
|
|
|
static const struct inode_operations ceph_symlink_iops;
|
|
|
|
static void ceph_invalidate_work(struct work_struct *work);
|
|
static void ceph_writeback_work(struct work_struct *work);
|
|
static void ceph_vmtruncate_work(struct work_struct *work);
|
|
|
|
/*
|
|
* find or create an inode, given the ceph ino number
|
|
*/
|
|
static int ceph_set_ino_cb(struct inode *inode, void *data)
|
|
{
|
|
ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
|
|
inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
|
|
return 0;
|
|
}
|
|
|
|
struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
|
|
{
|
|
struct inode *inode;
|
|
ino_t t = ceph_vino_to_ino(vino);
|
|
|
|
inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino);
|
|
if (inode == NULL)
|
|
return ERR_PTR(-ENOMEM);
|
|
if (inode->i_state & I_NEW) {
|
|
dout("get_inode created new inode %p %llx.%llx ino %llx\n",
|
|
inode, ceph_vinop(inode), (u64)inode->i_ino);
|
|
unlock_new_inode(inode);
|
|
}
|
|
|
|
dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino,
|
|
vino.snap, inode);
|
|
return inode;
|
|
}
|
|
|
|
/*
|
|
* get/constuct snapdir inode for a given directory
|
|
*/
|
|
struct inode *ceph_get_snapdir(struct inode *parent)
|
|
{
|
|
struct ceph_vino vino = {
|
|
.ino = ceph_ino(parent),
|
|
.snap = CEPH_SNAPDIR,
|
|
};
|
|
struct inode *inode = ceph_get_inode(parent->i_sb, vino);
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
BUG_ON(!S_ISDIR(parent->i_mode));
|
|
if (IS_ERR(inode))
|
|
return inode;
|
|
inode->i_mode = parent->i_mode;
|
|
inode->i_uid = parent->i_uid;
|
|
inode->i_gid = parent->i_gid;
|
|
inode->i_op = &ceph_snapdir_iops;
|
|
inode->i_fop = &ceph_snapdir_fops;
|
|
ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
|
|
ci->i_rbytes = 0;
|
|
return inode;
|
|
}
|
|
|
|
const struct inode_operations ceph_file_iops = {
|
|
.permission = ceph_permission,
|
|
.setattr = ceph_setattr,
|
|
.getattr = ceph_getattr,
|
|
.listxattr = ceph_listxattr,
|
|
.get_acl = ceph_get_acl,
|
|
.set_acl = ceph_set_acl,
|
|
};
|
|
|
|
|
|
/*
|
|
* We use a 'frag tree' to keep track of the MDS's directory fragments
|
|
* for a given inode (usually there is just a single fragment). We
|
|
* need to know when a child frag is delegated to a new MDS, or when
|
|
* it is flagged as replicated, so we can direct our requests
|
|
* accordingly.
|
|
*/
|
|
|
|
/*
|
|
* find/create a frag in the tree
|
|
*/
|
|
static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci,
|
|
u32 f)
|
|
{
|
|
struct rb_node **p;
|
|
struct rb_node *parent = NULL;
|
|
struct ceph_inode_frag *frag;
|
|
int c;
|
|
|
|
p = &ci->i_fragtree.rb_node;
|
|
while (*p) {
|
|
parent = *p;
|
|
frag = rb_entry(parent, struct ceph_inode_frag, node);
|
|
c = ceph_frag_compare(f, frag->frag);
|
|
if (c < 0)
|
|
p = &(*p)->rb_left;
|
|
else if (c > 0)
|
|
p = &(*p)->rb_right;
|
|
else
|
|
return frag;
|
|
}
|
|
|
|
frag = kmalloc(sizeof(*frag), GFP_NOFS);
|
|
if (!frag) {
|
|
pr_err("__get_or_create_frag ENOMEM on %p %llx.%llx "
|
|
"frag %x\n", &ci->vfs_inode,
|
|
ceph_vinop(&ci->vfs_inode), f);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
frag->frag = f;
|
|
frag->split_by = 0;
|
|
frag->mds = -1;
|
|
frag->ndist = 0;
|
|
|
|
rb_link_node(&frag->node, parent, p);
|
|
rb_insert_color(&frag->node, &ci->i_fragtree);
|
|
|
|
dout("get_or_create_frag added %llx.%llx frag %x\n",
|
|
ceph_vinop(&ci->vfs_inode), f);
|
|
return frag;
|
|
}
|
|
|
|
/*
|
|
* find a specific frag @f
|
|
*/
|
|
struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f)
|
|
{
|
|
struct rb_node *n = ci->i_fragtree.rb_node;
|
|
|
|
while (n) {
|
|
struct ceph_inode_frag *frag =
|
|
rb_entry(n, struct ceph_inode_frag, node);
|
|
int c = ceph_frag_compare(f, frag->frag);
|
|
if (c < 0)
|
|
n = n->rb_left;
|
|
else if (c > 0)
|
|
n = n->rb_right;
|
|
else
|
|
return frag;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* Choose frag containing the given value @v. If @pfrag is
|
|
* specified, copy the frag delegation info to the caller if
|
|
* it is present.
|
|
*/
|
|
static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
|
|
struct ceph_inode_frag *pfrag, int *found)
|
|
{
|
|
u32 t = ceph_frag_make(0, 0);
|
|
struct ceph_inode_frag *frag;
|
|
unsigned nway, i;
|
|
u32 n;
|
|
|
|
if (found)
|
|
*found = 0;
|
|
|
|
while (1) {
|
|
WARN_ON(!ceph_frag_contains_value(t, v));
|
|
frag = __ceph_find_frag(ci, t);
|
|
if (!frag)
|
|
break; /* t is a leaf */
|
|
if (frag->split_by == 0) {
|
|
if (pfrag)
|
|
memcpy(pfrag, frag, sizeof(*pfrag));
|
|
if (found)
|
|
*found = 1;
|
|
break;
|
|
}
|
|
|
|
/* choose child */
|
|
nway = 1 << frag->split_by;
|
|
dout("choose_frag(%x) %x splits by %d (%d ways)\n", v, t,
|
|
frag->split_by, nway);
|
|
for (i = 0; i < nway; i++) {
|
|
n = ceph_frag_make_child(t, frag->split_by, i);
|
|
if (ceph_frag_contains_value(n, v)) {
|
|
t = n;
|
|
break;
|
|
}
|
|
}
|
|
BUG_ON(i == nway);
|
|
}
|
|
dout("choose_frag(%x) = %x\n", v, t);
|
|
|
|
return t;
|
|
}
|
|
|
|
u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
|
|
struct ceph_inode_frag *pfrag, int *found)
|
|
{
|
|
u32 ret;
|
|
mutex_lock(&ci->i_fragtree_mutex);
|
|
ret = __ceph_choose_frag(ci, v, pfrag, found);
|
|
mutex_unlock(&ci->i_fragtree_mutex);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Process dirfrag (delegation) info from the mds. Include leaf
|
|
* fragment in tree ONLY if ndist > 0. Otherwise, only
|
|
* branches/splits are included in i_fragtree)
|
|
*/
|
|
static int ceph_fill_dirfrag(struct inode *inode,
|
|
struct ceph_mds_reply_dirfrag *dirinfo)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
struct ceph_inode_frag *frag;
|
|
u32 id = le32_to_cpu(dirinfo->frag);
|
|
int mds = le32_to_cpu(dirinfo->auth);
|
|
int ndist = le32_to_cpu(dirinfo->ndist);
|
|
int diri_auth = -1;
|
|
int i;
|
|
int err = 0;
|
|
|
|
spin_lock(&ci->i_ceph_lock);
|
|
if (ci->i_auth_cap)
|
|
diri_auth = ci->i_auth_cap->mds;
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
|
|
if (mds == -1) /* CDIR_AUTH_PARENT */
|
|
mds = diri_auth;
|
|
|
|
mutex_lock(&ci->i_fragtree_mutex);
|
|
if (ndist == 0 && mds == diri_auth) {
|
|
/* no delegation info needed. */
|
|
frag = __ceph_find_frag(ci, id);
|
|
if (!frag)
|
|
goto out;
|
|
if (frag->split_by == 0) {
|
|
/* tree leaf, remove */
|
|
dout("fill_dirfrag removed %llx.%llx frag %x"
|
|
" (no ref)\n", ceph_vinop(inode), id);
|
|
rb_erase(&frag->node, &ci->i_fragtree);
|
|
kfree(frag);
|
|
} else {
|
|
/* tree branch, keep and clear */
|
|
dout("fill_dirfrag cleared %llx.%llx frag %x"
|
|
" referral\n", ceph_vinop(inode), id);
|
|
frag->mds = -1;
|
|
frag->ndist = 0;
|
|
}
|
|
goto out;
|
|
}
|
|
|
|
|
|
/* find/add this frag to store mds delegation info */
|
|
frag = __get_or_create_frag(ci, id);
|
|
if (IS_ERR(frag)) {
|
|
/* this is not the end of the world; we can continue
|
|
with bad/inaccurate delegation info */
|
|
pr_err("fill_dirfrag ENOMEM on mds ref %llx.%llx fg %x\n",
|
|
ceph_vinop(inode), le32_to_cpu(dirinfo->frag));
|
|
err = -ENOMEM;
|
|
goto out;
|
|
}
|
|
|
|
frag->mds = mds;
|
|
frag->ndist = min_t(u32, ndist, CEPH_MAX_DIRFRAG_REP);
|
|
for (i = 0; i < frag->ndist; i++)
|
|
frag->dist[i] = le32_to_cpu(dirinfo->dist[i]);
|
|
dout("fill_dirfrag %llx.%llx frag %x ndist=%d\n",
|
|
ceph_vinop(inode), frag->frag, frag->ndist);
|
|
|
|
out:
|
|
mutex_unlock(&ci->i_fragtree_mutex);
|
|
return err;
|
|
}
|
|
|
|
static int frag_tree_split_cmp(const void *l, const void *r)
|
|
{
|
|
struct ceph_frag_tree_split *ls = (struct ceph_frag_tree_split*)l;
|
|
struct ceph_frag_tree_split *rs = (struct ceph_frag_tree_split*)r;
|
|
return ceph_frag_compare(le32_to_cpu(ls->frag),
|
|
le32_to_cpu(rs->frag));
|
|
}
|
|
|
|
static bool is_frag_child(u32 f, struct ceph_inode_frag *frag)
|
|
{
|
|
if (!frag)
|
|
return f == ceph_frag_make(0, 0);
|
|
if (ceph_frag_bits(f) != ceph_frag_bits(frag->frag) + frag->split_by)
|
|
return false;
|
|
return ceph_frag_contains_value(frag->frag, ceph_frag_value(f));
|
|
}
|
|
|
|
static int ceph_fill_fragtree(struct inode *inode,
|
|
struct ceph_frag_tree_head *fragtree,
|
|
struct ceph_mds_reply_dirfrag *dirinfo)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
struct ceph_inode_frag *frag, *prev_frag = NULL;
|
|
struct rb_node *rb_node;
|
|
unsigned i, split_by, nsplits;
|
|
u32 id;
|
|
bool update = false;
|
|
|
|
mutex_lock(&ci->i_fragtree_mutex);
|
|
nsplits = le32_to_cpu(fragtree->nsplits);
|
|
if (nsplits != ci->i_fragtree_nsplits) {
|
|
update = true;
|
|
} else if (nsplits) {
|
|
i = prandom_u32() % nsplits;
|
|
id = le32_to_cpu(fragtree->splits[i].frag);
|
|
if (!__ceph_find_frag(ci, id))
|
|
update = true;
|
|
} else if (!RB_EMPTY_ROOT(&ci->i_fragtree)) {
|
|
rb_node = rb_first(&ci->i_fragtree);
|
|
frag = rb_entry(rb_node, struct ceph_inode_frag, node);
|
|
if (frag->frag != ceph_frag_make(0, 0) || rb_next(rb_node))
|
|
update = true;
|
|
}
|
|
if (!update && dirinfo) {
|
|
id = le32_to_cpu(dirinfo->frag);
|
|
if (id != __ceph_choose_frag(ci, id, NULL, NULL))
|
|
update = true;
|
|
}
|
|
if (!update)
|
|
goto out_unlock;
|
|
|
|
if (nsplits > 1) {
|
|
sort(fragtree->splits, nsplits, sizeof(fragtree->splits[0]),
|
|
frag_tree_split_cmp, NULL);
|
|
}
|
|
|
|
dout("fill_fragtree %llx.%llx\n", ceph_vinop(inode));
|
|
rb_node = rb_first(&ci->i_fragtree);
|
|
for (i = 0; i < nsplits; i++) {
|
|
id = le32_to_cpu(fragtree->splits[i].frag);
|
|
split_by = le32_to_cpu(fragtree->splits[i].by);
|
|
if (split_by == 0 || ceph_frag_bits(id) + split_by > 24) {
|
|
pr_err("fill_fragtree %llx.%llx invalid split %d/%u, "
|
|
"frag %x split by %d\n", ceph_vinop(inode),
|
|
i, nsplits, id, split_by);
|
|
continue;
|
|
}
|
|
frag = NULL;
|
|
while (rb_node) {
|
|
frag = rb_entry(rb_node, struct ceph_inode_frag, node);
|
|
if (ceph_frag_compare(frag->frag, id) >= 0) {
|
|
if (frag->frag != id)
|
|
frag = NULL;
|
|
else
|
|
rb_node = rb_next(rb_node);
|
|
break;
|
|
}
|
|
rb_node = rb_next(rb_node);
|
|
/* delete stale split/leaf node */
|
|
if (frag->split_by > 0 ||
|
|
!is_frag_child(frag->frag, prev_frag)) {
|
|
rb_erase(&frag->node, &ci->i_fragtree);
|
|
if (frag->split_by > 0)
|
|
ci->i_fragtree_nsplits--;
|
|
kfree(frag);
|
|
}
|
|
frag = NULL;
|
|
}
|
|
if (!frag) {
|
|
frag = __get_or_create_frag(ci, id);
|
|
if (IS_ERR(frag))
|
|
continue;
|
|
}
|
|
if (frag->split_by == 0)
|
|
ci->i_fragtree_nsplits++;
|
|
frag->split_by = split_by;
|
|
dout(" frag %x split by %d\n", frag->frag, frag->split_by);
|
|
prev_frag = frag;
|
|
}
|
|
while (rb_node) {
|
|
frag = rb_entry(rb_node, struct ceph_inode_frag, node);
|
|
rb_node = rb_next(rb_node);
|
|
/* delete stale split/leaf node */
|
|
if (frag->split_by > 0 ||
|
|
!is_frag_child(frag->frag, prev_frag)) {
|
|
rb_erase(&frag->node, &ci->i_fragtree);
|
|
if (frag->split_by > 0)
|
|
ci->i_fragtree_nsplits--;
|
|
kfree(frag);
|
|
}
|
|
}
|
|
out_unlock:
|
|
mutex_unlock(&ci->i_fragtree_mutex);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* initialize a newly allocated inode.
|
|
*/
|
|
struct inode *ceph_alloc_inode(struct super_block *sb)
|
|
{
|
|
struct ceph_inode_info *ci;
|
|
int i;
|
|
|
|
ci = kmem_cache_alloc(ceph_inode_cachep, GFP_NOFS);
|
|
if (!ci)
|
|
return NULL;
|
|
|
|
dout("alloc_inode %p\n", &ci->vfs_inode);
|
|
|
|
spin_lock_init(&ci->i_ceph_lock);
|
|
|
|
ci->i_version = 0;
|
|
ci->i_inline_version = 0;
|
|
ci->i_time_warp_seq = 0;
|
|
ci->i_ceph_flags = 0;
|
|
atomic64_set(&ci->i_ordered_count, 1);
|
|
atomic64_set(&ci->i_release_count, 1);
|
|
atomic64_set(&ci->i_complete_seq[0], 0);
|
|
atomic64_set(&ci->i_complete_seq[1], 0);
|
|
ci->i_symlink = NULL;
|
|
|
|
memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
|
|
RCU_INIT_POINTER(ci->i_layout.pool_ns, NULL);
|
|
|
|
ci->i_fragtree = RB_ROOT;
|
|
mutex_init(&ci->i_fragtree_mutex);
|
|
|
|
ci->i_xattrs.blob = NULL;
|
|
ci->i_xattrs.prealloc_blob = NULL;
|
|
ci->i_xattrs.dirty = false;
|
|
ci->i_xattrs.index = RB_ROOT;
|
|
ci->i_xattrs.count = 0;
|
|
ci->i_xattrs.names_size = 0;
|
|
ci->i_xattrs.vals_size = 0;
|
|
ci->i_xattrs.version = 0;
|
|
ci->i_xattrs.index_version = 0;
|
|
|
|
ci->i_caps = RB_ROOT;
|
|
ci->i_auth_cap = NULL;
|
|
ci->i_dirty_caps = 0;
|
|
ci->i_flushing_caps = 0;
|
|
INIT_LIST_HEAD(&ci->i_dirty_item);
|
|
INIT_LIST_HEAD(&ci->i_flushing_item);
|
|
ci->i_prealloc_cap_flush = NULL;
|
|
INIT_LIST_HEAD(&ci->i_cap_flush_list);
|
|
init_waitqueue_head(&ci->i_cap_wq);
|
|
ci->i_hold_caps_min = 0;
|
|
ci->i_hold_caps_max = 0;
|
|
INIT_LIST_HEAD(&ci->i_cap_delay_list);
|
|
INIT_LIST_HEAD(&ci->i_cap_snaps);
|
|
ci->i_head_snapc = NULL;
|
|
ci->i_snap_caps = 0;
|
|
|
|
for (i = 0; i < CEPH_FILE_MODE_BITS; i++)
|
|
ci->i_nr_by_mode[i] = 0;
|
|
|
|
mutex_init(&ci->i_truncate_mutex);
|
|
ci->i_truncate_seq = 0;
|
|
ci->i_truncate_size = 0;
|
|
ci->i_truncate_pending = 0;
|
|
|
|
ci->i_max_size = 0;
|
|
ci->i_reported_size = 0;
|
|
ci->i_wanted_max_size = 0;
|
|
ci->i_requested_max_size = 0;
|
|
|
|
ci->i_pin_ref = 0;
|
|
ci->i_rd_ref = 0;
|
|
ci->i_rdcache_ref = 0;
|
|
ci->i_wr_ref = 0;
|
|
ci->i_wb_ref = 0;
|
|
ci->i_wrbuffer_ref = 0;
|
|
ci->i_wrbuffer_ref_head = 0;
|
|
ci->i_shared_gen = 0;
|
|
ci->i_rdcache_gen = 0;
|
|
ci->i_rdcache_revoking = 0;
|
|
|
|
INIT_LIST_HEAD(&ci->i_unsafe_dirops);
|
|
INIT_LIST_HEAD(&ci->i_unsafe_iops);
|
|
spin_lock_init(&ci->i_unsafe_lock);
|
|
|
|
ci->i_snap_realm = NULL;
|
|
INIT_LIST_HEAD(&ci->i_snap_realm_item);
|
|
INIT_LIST_HEAD(&ci->i_snap_flush_item);
|
|
|
|
INIT_WORK(&ci->i_wb_work, ceph_writeback_work);
|
|
INIT_WORK(&ci->i_pg_inv_work, ceph_invalidate_work);
|
|
|
|
INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work);
|
|
|
|
ceph_fscache_inode_init(ci);
|
|
|
|
return &ci->vfs_inode;
|
|
}
|
|
|
|
static void ceph_i_callback(struct rcu_head *head)
|
|
{
|
|
struct inode *inode = container_of(head, struct inode, i_rcu);
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
kmem_cache_free(ceph_inode_cachep, ci);
|
|
}
|
|
|
|
void ceph_destroy_inode(struct inode *inode)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
struct ceph_inode_frag *frag;
|
|
struct rb_node *n;
|
|
|
|
dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
|
|
|
|
ceph_fscache_unregister_inode_cookie(ci);
|
|
|
|
ceph_queue_caps_release(inode);
|
|
|
|
/*
|
|
* we may still have a snap_realm reference if there are stray
|
|
* caps in i_snap_caps.
|
|
*/
|
|
if (ci->i_snap_realm) {
|
|
struct ceph_mds_client *mdsc =
|
|
ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
|
|
struct ceph_snap_realm *realm = ci->i_snap_realm;
|
|
|
|
dout(" dropping residual ref to snap realm %p\n", realm);
|
|
spin_lock(&realm->inodes_with_caps_lock);
|
|
list_del_init(&ci->i_snap_realm_item);
|
|
spin_unlock(&realm->inodes_with_caps_lock);
|
|
ceph_put_snap_realm(mdsc, realm);
|
|
}
|
|
|
|
kfree(ci->i_symlink);
|
|
while ((n = rb_first(&ci->i_fragtree)) != NULL) {
|
|
frag = rb_entry(n, struct ceph_inode_frag, node);
|
|
rb_erase(n, &ci->i_fragtree);
|
|
kfree(frag);
|
|
}
|
|
ci->i_fragtree_nsplits = 0;
|
|
|
|
__ceph_destroy_xattrs(ci);
|
|
if (ci->i_xattrs.blob)
|
|
ceph_buffer_put(ci->i_xattrs.blob);
|
|
if (ci->i_xattrs.prealloc_blob)
|
|
ceph_buffer_put(ci->i_xattrs.prealloc_blob);
|
|
|
|
ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns));
|
|
|
|
call_rcu(&inode->i_rcu, ceph_i_callback);
|
|
}
|
|
|
|
int ceph_drop_inode(struct inode *inode)
|
|
{
|
|
/*
|
|
* Positve dentry and corresponding inode are always accompanied
|
|
* in MDS reply. So no need to keep inode in the cache after
|
|
* dropping all its aliases.
|
|
*/
|
|
return 1;
|
|
}
|
|
|
|
static inline blkcnt_t calc_inode_blocks(u64 size)
|
|
{
|
|
return (size + (1<<9) - 1) >> 9;
|
|
}
|
|
|
|
/*
|
|
* Helpers to fill in size, ctime, mtime, and atime. We have to be
|
|
* careful because either the client or MDS may have more up to date
|
|
* info, depending on which capabilities are held, and whether
|
|
* time_warp_seq or truncate_seq have increased. (Ordinarily, mtime
|
|
* and size are monotonically increasing, except when utimes() or
|
|
* truncate() increments the corresponding _seq values.)
|
|
*/
|
|
int ceph_fill_file_size(struct inode *inode, int issued,
|
|
u32 truncate_seq, u64 truncate_size, u64 size)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
int queue_trunc = 0;
|
|
|
|
if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 ||
|
|
(truncate_seq == ci->i_truncate_seq && size > inode->i_size)) {
|
|
dout("size %lld -> %llu\n", inode->i_size, size);
|
|
if (size > 0 && S_ISDIR(inode->i_mode)) {
|
|
pr_err("fill_file_size non-zero size for directory\n");
|
|
size = 0;
|
|
}
|
|
i_size_write(inode, size);
|
|
inode->i_blocks = calc_inode_blocks(size);
|
|
ci->i_reported_size = size;
|
|
if (truncate_seq != ci->i_truncate_seq) {
|
|
dout("truncate_seq %u -> %u\n",
|
|
ci->i_truncate_seq, truncate_seq);
|
|
ci->i_truncate_seq = truncate_seq;
|
|
|
|
/* the MDS should have revoked these caps */
|
|
WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL |
|
|
CEPH_CAP_FILE_RD |
|
|
CEPH_CAP_FILE_WR |
|
|
CEPH_CAP_FILE_LAZYIO));
|
|
/*
|
|
* If we hold relevant caps, or in the case where we're
|
|
* not the only client referencing this file and we
|
|
* don't hold those caps, then we need to check whether
|
|
* the file is either opened or mmaped
|
|
*/
|
|
if ((issued & (CEPH_CAP_FILE_CACHE|
|
|
CEPH_CAP_FILE_BUFFER)) ||
|
|
mapping_mapped(inode->i_mapping) ||
|
|
__ceph_caps_file_wanted(ci)) {
|
|
ci->i_truncate_pending++;
|
|
queue_trunc = 1;
|
|
}
|
|
}
|
|
}
|
|
if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) >= 0 &&
|
|
ci->i_truncate_size != truncate_size) {
|
|
dout("truncate_size %lld -> %llu\n", ci->i_truncate_size,
|
|
truncate_size);
|
|
ci->i_truncate_size = truncate_size;
|
|
}
|
|
|
|
if (queue_trunc)
|
|
ceph_fscache_invalidate(inode);
|
|
|
|
return queue_trunc;
|
|
}
|
|
|
|
void ceph_fill_file_time(struct inode *inode, int issued,
|
|
u64 time_warp_seq, struct timespec *ctime,
|
|
struct timespec *mtime, struct timespec *atime)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
int warn = 0;
|
|
|
|
if (issued & (CEPH_CAP_FILE_EXCL|
|
|
CEPH_CAP_FILE_WR|
|
|
CEPH_CAP_FILE_BUFFER|
|
|
CEPH_CAP_AUTH_EXCL|
|
|
CEPH_CAP_XATTR_EXCL)) {
|
|
if (timespec_compare(ctime, &inode->i_ctime) > 0) {
|
|
dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",
|
|
inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
|
|
ctime->tv_sec, ctime->tv_nsec);
|
|
inode->i_ctime = *ctime;
|
|
}
|
|
if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
|
|
/* the MDS did a utimes() */
|
|
dout("mtime %ld.%09ld -> %ld.%09ld "
|
|
"tw %d -> %d\n",
|
|
inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
|
|
mtime->tv_sec, mtime->tv_nsec,
|
|
ci->i_time_warp_seq, (int)time_warp_seq);
|
|
|
|
inode->i_mtime = *mtime;
|
|
inode->i_atime = *atime;
|
|
ci->i_time_warp_seq = time_warp_seq;
|
|
} else if (time_warp_seq == ci->i_time_warp_seq) {
|
|
/* nobody did utimes(); take the max */
|
|
if (timespec_compare(mtime, &inode->i_mtime) > 0) {
|
|
dout("mtime %ld.%09ld -> %ld.%09ld inc\n",
|
|
inode->i_mtime.tv_sec,
|
|
inode->i_mtime.tv_nsec,
|
|
mtime->tv_sec, mtime->tv_nsec);
|
|
inode->i_mtime = *mtime;
|
|
}
|
|
if (timespec_compare(atime, &inode->i_atime) > 0) {
|
|
dout("atime %ld.%09ld -> %ld.%09ld inc\n",
|
|
inode->i_atime.tv_sec,
|
|
inode->i_atime.tv_nsec,
|
|
atime->tv_sec, atime->tv_nsec);
|
|
inode->i_atime = *atime;
|
|
}
|
|
} else if (issued & CEPH_CAP_FILE_EXCL) {
|
|
/* we did a utimes(); ignore mds values */
|
|
} else {
|
|
warn = 1;
|
|
}
|
|
} else {
|
|
/* we have no write|excl caps; whatever the MDS says is true */
|
|
if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) {
|
|
inode->i_ctime = *ctime;
|
|
inode->i_mtime = *mtime;
|
|
inode->i_atime = *atime;
|
|
ci->i_time_warp_seq = time_warp_seq;
|
|
} else {
|
|
warn = 1;
|
|
}
|
|
}
|
|
if (warn) /* time_warp_seq shouldn't go backwards */
|
|
dout("%p mds time_warp_seq %llu < %u\n",
|
|
inode, time_warp_seq, ci->i_time_warp_seq);
|
|
}
|
|
|
|
/*
|
|
* Populate an inode based on info from mds. May be called on new or
|
|
* existing inodes.
|
|
*/
|
|
static int fill_inode(struct inode *inode, struct page *locked_page,
|
|
struct ceph_mds_reply_info_in *iinfo,
|
|
struct ceph_mds_reply_dirfrag *dirinfo,
|
|
struct ceph_mds_session *session,
|
|
unsigned long ttl_from, int cap_fmode,
|
|
struct ceph_cap_reservation *caps_reservation)
|
|
{
|
|
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
|
|
struct ceph_mds_reply_inode *info = iinfo->in;
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
int issued = 0, implemented, new_issued;
|
|
struct timespec mtime, atime, ctime;
|
|
struct ceph_buffer *xattr_blob = NULL;
|
|
struct ceph_string *pool_ns = NULL;
|
|
struct ceph_cap *new_cap = NULL;
|
|
int err = 0;
|
|
bool wake = false;
|
|
bool queue_trunc = false;
|
|
bool new_version = false;
|
|
bool fill_inline = false;
|
|
|
|
dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
|
|
inode, ceph_vinop(inode), le64_to_cpu(info->version),
|
|
ci->i_version);
|
|
|
|
/* prealloc new cap struct */
|
|
if (info->cap.caps && ceph_snap(inode) == CEPH_NOSNAP)
|
|
new_cap = ceph_get_cap(mdsc, caps_reservation);
|
|
|
|
/*
|
|
* prealloc xattr data, if it looks like we'll need it. only
|
|
* if len > 4 (meaning there are actually xattrs; the first 4
|
|
* bytes are the xattr count).
|
|
*/
|
|
if (iinfo->xattr_len > 4) {
|
|
xattr_blob = ceph_buffer_new(iinfo->xattr_len, GFP_NOFS);
|
|
if (!xattr_blob)
|
|
pr_err("fill_inode ENOMEM xattr blob %d bytes\n",
|
|
iinfo->xattr_len);
|
|
}
|
|
|
|
if (iinfo->pool_ns_len > 0)
|
|
pool_ns = ceph_find_or_create_string(iinfo->pool_ns_data,
|
|
iinfo->pool_ns_len);
|
|
|
|
spin_lock(&ci->i_ceph_lock);
|
|
|
|
/*
|
|
* provided version will be odd if inode value is projected,
|
|
* even if stable. skip the update if we have newer stable
|
|
* info (ours>=theirs, e.g. due to racing mds replies), unless
|
|
* we are getting projected (unstable) info (in which case the
|
|
* version is odd, and we want ours>theirs).
|
|
* us them
|
|
* 2 2 skip
|
|
* 3 2 skip
|
|
* 3 3 update
|
|
*/
|
|
if (ci->i_version == 0 ||
|
|
((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
|
|
le64_to_cpu(info->version) > (ci->i_version & ~1)))
|
|
new_version = true;
|
|
|
|
issued = __ceph_caps_issued(ci, &implemented);
|
|
issued |= implemented | __ceph_caps_dirty(ci);
|
|
new_issued = ~issued & le32_to_cpu(info->cap.caps);
|
|
|
|
/* update inode */
|
|
ci->i_version = le64_to_cpu(info->version);
|
|
inode->i_version++;
|
|
inode->i_rdev = le32_to_cpu(info->rdev);
|
|
inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
|
|
|
|
if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
|
|
(issued & CEPH_CAP_AUTH_EXCL) == 0) {
|
|
inode->i_mode = le32_to_cpu(info->mode);
|
|
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
|
|
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
|
|
dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
|
|
from_kuid(&init_user_ns, inode->i_uid),
|
|
from_kgid(&init_user_ns, inode->i_gid));
|
|
}
|
|
|
|
if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) &&
|
|
(issued & CEPH_CAP_LINK_EXCL) == 0)
|
|
set_nlink(inode, le32_to_cpu(info->nlink));
|
|
|
|
if (new_version || (new_issued & CEPH_CAP_ANY_RD)) {
|
|
/* be careful with mtime, atime, size */
|
|
ceph_decode_timespec(&atime, &info->atime);
|
|
ceph_decode_timespec(&mtime, &info->mtime);
|
|
ceph_decode_timespec(&ctime, &info->ctime);
|
|
ceph_fill_file_time(inode, issued,
|
|
le32_to_cpu(info->time_warp_seq),
|
|
&ctime, &mtime, &atime);
|
|
}
|
|
|
|
if (new_version ||
|
|
(new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
|
|
s64 old_pool = ci->i_layout.pool_id;
|
|
struct ceph_string *old_ns;
|
|
|
|
ceph_file_layout_from_legacy(&ci->i_layout, &info->layout);
|
|
old_ns = rcu_dereference_protected(ci->i_layout.pool_ns,
|
|
lockdep_is_held(&ci->i_ceph_lock));
|
|
rcu_assign_pointer(ci->i_layout.pool_ns, pool_ns);
|
|
|
|
if (ci->i_layout.pool_id != old_pool || pool_ns != old_ns)
|
|
ci->i_ceph_flags &= ~CEPH_I_POOL_PERM;
|
|
|
|
pool_ns = old_ns;
|
|
|
|
queue_trunc = ceph_fill_file_size(inode, issued,
|
|
le32_to_cpu(info->truncate_seq),
|
|
le64_to_cpu(info->truncate_size),
|
|
le64_to_cpu(info->size));
|
|
/* only update max_size on auth cap */
|
|
if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
|
|
ci->i_max_size != le64_to_cpu(info->max_size)) {
|
|
dout("max_size %lld -> %llu\n", ci->i_max_size,
|
|
le64_to_cpu(info->max_size));
|
|
ci->i_max_size = le64_to_cpu(info->max_size);
|
|
}
|
|
}
|
|
|
|
/* xattrs */
|
|
/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
|
|
if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) &&
|
|
le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
|
|
if (ci->i_xattrs.blob)
|
|
ceph_buffer_put(ci->i_xattrs.blob);
|
|
ci->i_xattrs.blob = xattr_blob;
|
|
if (xattr_blob)
|
|
memcpy(ci->i_xattrs.blob->vec.iov_base,
|
|
iinfo->xattr_data, iinfo->xattr_len);
|
|
ci->i_xattrs.version = le64_to_cpu(info->xattr_version);
|
|
ceph_forget_all_cached_acls(inode);
|
|
xattr_blob = NULL;
|
|
}
|
|
|
|
inode->i_mapping->a_ops = &ceph_aops;
|
|
|
|
switch (inode->i_mode & S_IFMT) {
|
|
case S_IFIFO:
|
|
case S_IFBLK:
|
|
case S_IFCHR:
|
|
case S_IFSOCK:
|
|
init_special_inode(inode, inode->i_mode, inode->i_rdev);
|
|
inode->i_op = &ceph_file_iops;
|
|
break;
|
|
case S_IFREG:
|
|
inode->i_op = &ceph_file_iops;
|
|
inode->i_fop = &ceph_file_fops;
|
|
break;
|
|
case S_IFLNK:
|
|
inode->i_op = &ceph_symlink_iops;
|
|
if (!ci->i_symlink) {
|
|
u32 symlen = iinfo->symlink_len;
|
|
char *sym;
|
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
|
|
if (symlen != i_size_read(inode)) {
|
|
pr_err("fill_inode %llx.%llx BAD symlink "
|
|
"size %lld\n", ceph_vinop(inode),
|
|
i_size_read(inode));
|
|
i_size_write(inode, symlen);
|
|
inode->i_blocks = calc_inode_blocks(symlen);
|
|
}
|
|
|
|
err = -ENOMEM;
|
|
sym = kstrndup(iinfo->symlink, symlen, GFP_NOFS);
|
|
if (!sym)
|
|
goto out;
|
|
|
|
spin_lock(&ci->i_ceph_lock);
|
|
if (!ci->i_symlink)
|
|
ci->i_symlink = sym;
|
|
else
|
|
kfree(sym); /* lost a race */
|
|
}
|
|
inode->i_link = ci->i_symlink;
|
|
break;
|
|
case S_IFDIR:
|
|
inode->i_op = &ceph_dir_iops;
|
|
inode->i_fop = &ceph_dir_fops;
|
|
|
|
ci->i_dir_layout = iinfo->dir_layout;
|
|
|
|
ci->i_files = le64_to_cpu(info->files);
|
|
ci->i_subdirs = le64_to_cpu(info->subdirs);
|
|
ci->i_rbytes = le64_to_cpu(info->rbytes);
|
|
ci->i_rfiles = le64_to_cpu(info->rfiles);
|
|
ci->i_rsubdirs = le64_to_cpu(info->rsubdirs);
|
|
ceph_decode_timespec(&ci->i_rctime, &info->rctime);
|
|
break;
|
|
default:
|
|
pr_err("fill_inode %llx.%llx BAD mode 0%o\n",
|
|
ceph_vinop(inode), inode->i_mode);
|
|
}
|
|
|
|
/* were we issued a capability? */
|
|
if (info->cap.caps) {
|
|
if (ceph_snap(inode) == CEPH_NOSNAP) {
|
|
unsigned caps = le32_to_cpu(info->cap.caps);
|
|
ceph_add_cap(inode, session,
|
|
le64_to_cpu(info->cap.cap_id),
|
|
cap_fmode, caps,
|
|
le32_to_cpu(info->cap.wanted),
|
|
le32_to_cpu(info->cap.seq),
|
|
le32_to_cpu(info->cap.mseq),
|
|
le64_to_cpu(info->cap.realm),
|
|
info->cap.flags, &new_cap);
|
|
|
|
/* set dir completion flag? */
|
|
if (S_ISDIR(inode->i_mode) &&
|
|
ci->i_files == 0 && ci->i_subdirs == 0 &&
|
|
(caps & CEPH_CAP_FILE_SHARED) &&
|
|
(issued & CEPH_CAP_FILE_EXCL) == 0 &&
|
|
!__ceph_dir_is_complete(ci)) {
|
|
dout(" marking %p complete (empty)\n", inode);
|
|
i_size_write(inode, 0);
|
|
__ceph_dir_set_complete(ci,
|
|
atomic64_read(&ci->i_release_count),
|
|
atomic64_read(&ci->i_ordered_count));
|
|
}
|
|
|
|
wake = true;
|
|
} else {
|
|
dout(" %p got snap_caps %s\n", inode,
|
|
ceph_cap_string(le32_to_cpu(info->cap.caps)));
|
|
ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
|
|
if (cap_fmode >= 0)
|
|
__ceph_get_fmode(ci, cap_fmode);
|
|
}
|
|
} else if (cap_fmode >= 0) {
|
|
pr_warn("mds issued no caps on %llx.%llx\n",
|
|
ceph_vinop(inode));
|
|
__ceph_get_fmode(ci, cap_fmode);
|
|
}
|
|
|
|
if (iinfo->inline_version > 0 &&
|
|
iinfo->inline_version >= ci->i_inline_version) {
|
|
int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
|
|
ci->i_inline_version = iinfo->inline_version;
|
|
if (ci->i_inline_version != CEPH_INLINE_NONE &&
|
|
(locked_page ||
|
|
(le32_to_cpu(info->cap.caps) & cache_caps)))
|
|
fill_inline = true;
|
|
}
|
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
|
|
if (fill_inline)
|
|
ceph_fill_inline_data(inode, locked_page,
|
|
iinfo->inline_data, iinfo->inline_len);
|
|
|
|
if (wake)
|
|
wake_up_all(&ci->i_cap_wq);
|
|
|
|
/* queue truncate if we saw i_size decrease */
|
|
if (queue_trunc)
|
|
ceph_queue_vmtruncate(inode);
|
|
|
|
/* populate frag tree */
|
|
if (S_ISDIR(inode->i_mode))
|
|
ceph_fill_fragtree(inode, &info->fragtree, dirinfo);
|
|
|
|
/* update delegation info? */
|
|
if (dirinfo)
|
|
ceph_fill_dirfrag(inode, dirinfo);
|
|
|
|
err = 0;
|
|
out:
|
|
if (new_cap)
|
|
ceph_put_cap(mdsc, new_cap);
|
|
if (xattr_blob)
|
|
ceph_buffer_put(xattr_blob);
|
|
ceph_put_string(pool_ns);
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* caller should hold session s_mutex.
|
|
*/
|
|
static void update_dentry_lease(struct dentry *dentry,
|
|
struct ceph_mds_reply_lease *lease,
|
|
struct ceph_mds_session *session,
|
|
unsigned long from_time,
|
|
struct ceph_vino *tgt_vino,
|
|
struct ceph_vino *dir_vino)
|
|
{
|
|
struct ceph_dentry_info *di = ceph_dentry(dentry);
|
|
long unsigned duration = le32_to_cpu(lease->duration_ms);
|
|
long unsigned ttl = from_time + (duration * HZ) / 1000;
|
|
long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000;
|
|
struct inode *dir;
|
|
|
|
/*
|
|
* Make sure dentry's inode matches tgt_vino. NULL tgt_vino means that
|
|
* we expect a negative dentry.
|
|
*/
|
|
if (!tgt_vino && d_really_is_positive(dentry))
|
|
return;
|
|
|
|
if (tgt_vino && (d_really_is_negative(dentry) ||
|
|
!ceph_ino_compare(d_inode(dentry), tgt_vino)))
|
|
return;
|
|
|
|
spin_lock(&dentry->d_lock);
|
|
dout("update_dentry_lease %p duration %lu ms ttl %lu\n",
|
|
dentry, duration, ttl);
|
|
|
|
dir = d_inode(dentry->d_parent);
|
|
|
|
/* make sure parent matches dir_vino */
|
|
if (!ceph_ino_compare(dir, dir_vino))
|
|
goto out_unlock;
|
|
|
|
/* only track leases on regular dentries */
|
|
if (ceph_snap(dir) != CEPH_NOSNAP)
|
|
goto out_unlock;
|
|
|
|
di->lease_shared_gen = ceph_inode(dir)->i_shared_gen;
|
|
|
|
if (duration == 0)
|
|
goto out_unlock;
|
|
|
|
if (di->lease_gen == session->s_cap_gen &&
|
|
time_before(ttl, di->time))
|
|
goto out_unlock; /* we already have a newer lease. */
|
|
|
|
if (di->lease_session && di->lease_session != session)
|
|
goto out_unlock;
|
|
|
|
ceph_dentry_lru_touch(dentry);
|
|
|
|
if (!di->lease_session)
|
|
di->lease_session = ceph_get_mds_session(session);
|
|
di->lease_gen = session->s_cap_gen;
|
|
di->lease_seq = le32_to_cpu(lease->seq);
|
|
di->lease_renew_after = half_ttl;
|
|
di->lease_renew_from = 0;
|
|
di->time = ttl;
|
|
out_unlock:
|
|
spin_unlock(&dentry->d_lock);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* splice a dentry to an inode.
|
|
* caller must hold directory i_mutex for this to be safe.
|
|
*/
|
|
static struct dentry *splice_dentry(struct dentry *dn, struct inode *in)
|
|
{
|
|
struct dentry *realdn;
|
|
|
|
BUG_ON(d_inode(dn));
|
|
|
|
/* dn must be unhashed */
|
|
if (!d_unhashed(dn))
|
|
d_drop(dn);
|
|
realdn = d_splice_alias(in, dn);
|
|
if (IS_ERR(realdn)) {
|
|
pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
|
|
PTR_ERR(realdn), dn, in, ceph_vinop(in));
|
|
dn = realdn; /* note realdn contains the error */
|
|
goto out;
|
|
} else if (realdn) {
|
|
dout("dn %p (%d) spliced with %p (%d) "
|
|
"inode %p ino %llx.%llx\n",
|
|
dn, d_count(dn),
|
|
realdn, d_count(realdn),
|
|
d_inode(realdn), ceph_vinop(d_inode(realdn)));
|
|
dput(dn);
|
|
dn = realdn;
|
|
} else {
|
|
BUG_ON(!ceph_dentry(dn));
|
|
dout("dn %p attached to %p ino %llx.%llx\n",
|
|
dn, d_inode(dn), ceph_vinop(d_inode(dn)));
|
|
}
|
|
out:
|
|
return dn;
|
|
}
|
|
|
|
/*
|
|
* Incorporate results into the local cache. This is either just
|
|
* one inode, or a directory, dentry, and possibly linked-to inode (e.g.,
|
|
* after a lookup).
|
|
*
|
|
* A reply may contain
|
|
* a directory inode along with a dentry.
|
|
* and/or a target inode
|
|
*
|
|
* Called with snap_rwsem (read).
|
|
*/
|
|
int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
|
|
{
|
|
struct ceph_mds_session *session = req->r_session;
|
|
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
|
|
struct inode *in = NULL;
|
|
struct ceph_vino tvino, dvino;
|
|
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
|
|
int err = 0;
|
|
|
|
dout("fill_trace %p is_dentry %d is_target %d\n", req,
|
|
rinfo->head->is_dentry, rinfo->head->is_target);
|
|
|
|
if (!rinfo->head->is_target && !rinfo->head->is_dentry) {
|
|
dout("fill_trace reply is empty!\n");
|
|
if (rinfo->head->result == 0 && req->r_parent)
|
|
ceph_invalidate_dir_request(req);
|
|
return 0;
|
|
}
|
|
|
|
if (rinfo->head->is_dentry) {
|
|
struct inode *dir = req->r_parent;
|
|
|
|
if (dir) {
|
|
err = fill_inode(dir, NULL,
|
|
&rinfo->diri, rinfo->dirfrag,
|
|
session, req->r_request_started, -1,
|
|
&req->r_caps_reservation);
|
|
if (err < 0)
|
|
goto done;
|
|
} else {
|
|
WARN_ON_ONCE(1);
|
|
}
|
|
|
|
if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME) {
|
|
struct qstr dname;
|
|
struct dentry *dn, *parent;
|
|
|
|
BUG_ON(!rinfo->head->is_target);
|
|
BUG_ON(req->r_dentry);
|
|
|
|
parent = d_find_any_alias(dir);
|
|
BUG_ON(!parent);
|
|
|
|
dname.name = rinfo->dname;
|
|
dname.len = rinfo->dname_len;
|
|
dname.hash = full_name_hash(parent, dname.name, dname.len);
|
|
tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
|
|
tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
|
|
retry_lookup:
|
|
dn = d_lookup(parent, &dname);
|
|
dout("d_lookup on parent=%p name=%.*s got %p\n",
|
|
parent, dname.len, dname.name, dn);
|
|
|
|
if (!dn) {
|
|
dn = d_alloc(parent, &dname);
|
|
dout("d_alloc %p '%.*s' = %p\n", parent,
|
|
dname.len, dname.name, dn);
|
|
if (dn == NULL) {
|
|
dput(parent);
|
|
err = -ENOMEM;
|
|
goto done;
|
|
}
|
|
err = 0;
|
|
} else if (d_really_is_positive(dn) &&
|
|
(ceph_ino(d_inode(dn)) != tvino.ino ||
|
|
ceph_snap(d_inode(dn)) != tvino.snap)) {
|
|
dout(" dn %p points to wrong inode %p\n",
|
|
dn, d_inode(dn));
|
|
d_delete(dn);
|
|
dput(dn);
|
|
goto retry_lookup;
|
|
}
|
|
|
|
req->r_dentry = dn;
|
|
dput(parent);
|
|
}
|
|
}
|
|
|
|
if (rinfo->head->is_target) {
|
|
tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
|
|
tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
|
|
|
|
in = ceph_get_inode(sb, tvino);
|
|
if (IS_ERR(in)) {
|
|
err = PTR_ERR(in);
|
|
goto done;
|
|
}
|
|
req->r_target_inode = in;
|
|
|
|
err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
|
|
session, req->r_request_started,
|
|
(!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
|
|
rinfo->head->result == 0) ? req->r_fmode : -1,
|
|
&req->r_caps_reservation);
|
|
if (err < 0) {
|
|
pr_err("fill_inode badness %p %llx.%llx\n",
|
|
in, ceph_vinop(in));
|
|
goto done;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* ignore null lease/binding on snapdir ENOENT, or else we
|
|
* will have trouble splicing in the virtual snapdir later
|
|
*/
|
|
if (rinfo->head->is_dentry &&
|
|
!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
|
|
test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
|
|
(rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
|
|
fsc->mount_options->snapdir_name,
|
|
req->r_dentry->d_name.len))) {
|
|
/*
|
|
* lookup link rename : null -> possibly existing inode
|
|
* mknod symlink mkdir : null -> new inode
|
|
* unlink : linked -> null
|
|
*/
|
|
struct inode *dir = req->r_parent;
|
|
struct dentry *dn = req->r_dentry;
|
|
bool have_dir_cap, have_lease;
|
|
|
|
BUG_ON(!dn);
|
|
BUG_ON(!dir);
|
|
BUG_ON(d_inode(dn->d_parent) != dir);
|
|
|
|
dvino.ino = le64_to_cpu(rinfo->diri.in->ino);
|
|
dvino.snap = le64_to_cpu(rinfo->diri.in->snapid);
|
|
|
|
BUG_ON(ceph_ino(dir) != dvino.ino);
|
|
BUG_ON(ceph_snap(dir) != dvino.snap);
|
|
|
|
/* do we have a lease on the whole dir? */
|
|
have_dir_cap =
|
|
(le32_to_cpu(rinfo->diri.in->cap.caps) &
|
|
CEPH_CAP_FILE_SHARED);
|
|
|
|
/* do we have a dn lease? */
|
|
have_lease = have_dir_cap ||
|
|
le32_to_cpu(rinfo->dlease->duration_ms);
|
|
if (!have_lease)
|
|
dout("fill_trace no dentry lease or dir cap\n");
|
|
|
|
/* rename? */
|
|
if (req->r_old_dentry && req->r_op == CEPH_MDS_OP_RENAME) {
|
|
struct inode *olddir = req->r_old_dentry_dir;
|
|
BUG_ON(!olddir);
|
|
|
|
dout(" src %p '%pd' dst %p '%pd'\n",
|
|
req->r_old_dentry,
|
|
req->r_old_dentry,
|
|
dn, dn);
|
|
dout("fill_trace doing d_move %p -> %p\n",
|
|
req->r_old_dentry, dn);
|
|
|
|
/* d_move screws up sibling dentries' offsets */
|
|
ceph_dir_clear_ordered(dir);
|
|
ceph_dir_clear_ordered(olddir);
|
|
|
|
d_move(req->r_old_dentry, dn);
|
|
dout(" src %p '%pd' dst %p '%pd'\n",
|
|
req->r_old_dentry,
|
|
req->r_old_dentry,
|
|
dn, dn);
|
|
|
|
/* ensure target dentry is invalidated, despite
|
|
rehashing bug in vfs_rename_dir */
|
|
ceph_invalidate_dentry_lease(dn);
|
|
|
|
dout("dn %p gets new offset %lld\n", req->r_old_dentry,
|
|
ceph_dentry(req->r_old_dentry)->offset);
|
|
|
|
dn = req->r_old_dentry; /* use old_dentry */
|
|
}
|
|
|
|
/* null dentry? */
|
|
if (!rinfo->head->is_target) {
|
|
dout("fill_trace null dentry\n");
|
|
if (d_really_is_positive(dn)) {
|
|
ceph_dir_clear_ordered(dir);
|
|
dout("d_delete %p\n", dn);
|
|
d_delete(dn);
|
|
} else if (have_lease) {
|
|
if (d_unhashed(dn))
|
|
d_add(dn, NULL);
|
|
update_dentry_lease(dn, rinfo->dlease,
|
|
session,
|
|
req->r_request_started,
|
|
NULL, &dvino);
|
|
}
|
|
goto done;
|
|
}
|
|
|
|
/* attach proper inode */
|
|
if (d_really_is_negative(dn)) {
|
|
ceph_dir_clear_ordered(dir);
|
|
ihold(in);
|
|
dn = splice_dentry(dn, in);
|
|
if (IS_ERR(dn)) {
|
|
err = PTR_ERR(dn);
|
|
goto done;
|
|
}
|
|
req->r_dentry = dn; /* may have spliced */
|
|
} else if (d_really_is_positive(dn) && d_inode(dn) != in) {
|
|
dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
|
|
dn, d_inode(dn), ceph_vinop(d_inode(dn)),
|
|
ceph_vinop(in));
|
|
d_invalidate(dn);
|
|
have_lease = false;
|
|
}
|
|
|
|
if (have_lease) {
|
|
tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
|
|
tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
|
|
update_dentry_lease(dn, rinfo->dlease, session,
|
|
req->r_request_started,
|
|
&tvino, &dvino);
|
|
}
|
|
dout(" final dn %p\n", dn);
|
|
} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
|
|
req->r_op == CEPH_MDS_OP_MKSNAP) &&
|
|
!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
|
|
struct dentry *dn = req->r_dentry;
|
|
struct inode *dir = req->r_parent;
|
|
|
|
/* fill out a snapdir LOOKUPSNAP dentry */
|
|
BUG_ON(!dn);
|
|
BUG_ON(!dir);
|
|
BUG_ON(ceph_snap(dir) != CEPH_SNAPDIR);
|
|
dout(" linking snapped dir %p to dn %p\n", in, dn);
|
|
ceph_dir_clear_ordered(dir);
|
|
ihold(in);
|
|
dn = splice_dentry(dn, in);
|
|
if (IS_ERR(dn)) {
|
|
err = PTR_ERR(dn);
|
|
goto done;
|
|
}
|
|
req->r_dentry = dn; /* may have spliced */
|
|
} else if (rinfo->head->is_dentry) {
|
|
struct ceph_vino *ptvino = NULL;
|
|
|
|
if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) ||
|
|
le32_to_cpu(rinfo->dlease->duration_ms)) {
|
|
dvino.ino = le64_to_cpu(rinfo->diri.in->ino);
|
|
dvino.snap = le64_to_cpu(rinfo->diri.in->snapid);
|
|
|
|
if (rinfo->head->is_target) {
|
|
tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
|
|
tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
|
|
ptvino = &tvino;
|
|
}
|
|
|
|
update_dentry_lease(req->r_dentry, rinfo->dlease,
|
|
session, req->r_request_started, ptvino,
|
|
&dvino);
|
|
} else {
|
|
dout("%s: no dentry lease or dir cap\n", __func__);
|
|
}
|
|
}
|
|
done:
|
|
dout("fill_trace done err=%d\n", err);
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* Prepopulate our cache with readdir results, leases, etc.
|
|
*/
|
|
static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
|
|
struct ceph_mds_session *session)
|
|
{
|
|
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
|
|
int i, err = 0;
|
|
|
|
for (i = 0; i < rinfo->dir_nr; i++) {
|
|
struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
|
|
struct ceph_vino vino;
|
|
struct inode *in;
|
|
int rc;
|
|
|
|
vino.ino = le64_to_cpu(rde->inode.in->ino);
|
|
vino.snap = le64_to_cpu(rde->inode.in->snapid);
|
|
|
|
in = ceph_get_inode(req->r_dentry->d_sb, vino);
|
|
if (IS_ERR(in)) {
|
|
err = PTR_ERR(in);
|
|
dout("new_inode badness got %d\n", err);
|
|
continue;
|
|
}
|
|
rc = fill_inode(in, NULL, &rde->inode, NULL, session,
|
|
req->r_request_started, -1,
|
|
&req->r_caps_reservation);
|
|
if (rc < 0) {
|
|
pr_err("fill_inode badness on %p got %d\n", in, rc);
|
|
err = rc;
|
|
}
|
|
iput(in);
|
|
}
|
|
|
|
return err;
|
|
}
|
|
|
|
void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl)
|
|
{
|
|
if (ctl->page) {
|
|
kunmap(ctl->page);
|
|
put_page(ctl->page);
|
|
ctl->page = NULL;
|
|
}
|
|
}
|
|
|
|
static int fill_readdir_cache(struct inode *dir, struct dentry *dn,
|
|
struct ceph_readdir_cache_control *ctl,
|
|
struct ceph_mds_request *req)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(dir);
|
|
unsigned nsize = PAGE_SIZE / sizeof(struct dentry*);
|
|
unsigned idx = ctl->index % nsize;
|
|
pgoff_t pgoff = ctl->index / nsize;
|
|
|
|
if (!ctl->page || pgoff != page_index(ctl->page)) {
|
|
ceph_readdir_cache_release(ctl);
|
|
if (idx == 0)
|
|
ctl->page = grab_cache_page(&dir->i_data, pgoff);
|
|
else
|
|
ctl->page = find_lock_page(&dir->i_data, pgoff);
|
|
if (!ctl->page) {
|
|
ctl->index = -1;
|
|
return idx == 0 ? -ENOMEM : 0;
|
|
}
|
|
/* reading/filling the cache are serialized by
|
|
* i_mutex, no need to use page lock */
|
|
unlock_page(ctl->page);
|
|
ctl->dentries = kmap(ctl->page);
|
|
if (idx == 0)
|
|
memset(ctl->dentries, 0, PAGE_SIZE);
|
|
}
|
|
|
|
if (req->r_dir_release_cnt == atomic64_read(&ci->i_release_count) &&
|
|
req->r_dir_ordered_cnt == atomic64_read(&ci->i_ordered_count)) {
|
|
dout("readdir cache dn %p idx %d\n", dn, ctl->index);
|
|
ctl->dentries[idx] = dn;
|
|
ctl->index++;
|
|
} else {
|
|
dout("disable readdir cache\n");
|
|
ctl->index = -1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
int ceph_readdir_prepopulate(struct ceph_mds_request *req,
|
|
struct ceph_mds_session *session)
|
|
{
|
|
struct dentry *parent = req->r_dentry;
|
|
struct ceph_inode_info *ci = ceph_inode(d_inode(parent));
|
|
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
|
|
struct qstr dname;
|
|
struct dentry *dn;
|
|
struct inode *in;
|
|
int err = 0, skipped = 0, ret, i;
|
|
struct inode *snapdir = NULL;
|
|
struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
|
|
u32 frag = le32_to_cpu(rhead->args.readdir.frag);
|
|
u32 last_hash = 0;
|
|
u32 fpos_offset;
|
|
struct ceph_readdir_cache_control cache_ctl = {};
|
|
|
|
if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags))
|
|
return readdir_prepopulate_inodes_only(req, session);
|
|
|
|
if (rinfo->hash_order && req->r_path2) {
|
|
last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
|
|
req->r_path2, strlen(req->r_path2));
|
|
last_hash = ceph_frag_value(last_hash);
|
|
}
|
|
|
|
if (rinfo->dir_dir &&
|
|
le32_to_cpu(rinfo->dir_dir->frag) != frag) {
|
|
dout("readdir_prepopulate got new frag %x -> %x\n",
|
|
frag, le32_to_cpu(rinfo->dir_dir->frag));
|
|
frag = le32_to_cpu(rinfo->dir_dir->frag);
|
|
if (!rinfo->hash_order)
|
|
req->r_readdir_offset = 2;
|
|
}
|
|
|
|
if (le32_to_cpu(rinfo->head->op) == CEPH_MDS_OP_LSSNAP) {
|
|
snapdir = ceph_get_snapdir(d_inode(parent));
|
|
parent = d_find_alias(snapdir);
|
|
dout("readdir_prepopulate %d items under SNAPDIR dn %p\n",
|
|
rinfo->dir_nr, parent);
|
|
} else {
|
|
dout("readdir_prepopulate %d items under dn %p\n",
|
|
rinfo->dir_nr, parent);
|
|
if (rinfo->dir_dir)
|
|
ceph_fill_dirfrag(d_inode(parent), rinfo->dir_dir);
|
|
}
|
|
|
|
if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2 &&
|
|
!(rinfo->hash_order && req->r_path2)) {
|
|
/* note dir version at start of readdir so we can tell
|
|
* if any dentries get dropped */
|
|
req->r_dir_release_cnt = atomic64_read(&ci->i_release_count);
|
|
req->r_dir_ordered_cnt = atomic64_read(&ci->i_ordered_count);
|
|
req->r_readdir_cache_idx = 0;
|
|
}
|
|
|
|
cache_ctl.index = req->r_readdir_cache_idx;
|
|
fpos_offset = req->r_readdir_offset;
|
|
|
|
/* FIXME: release caps/leases if error occurs */
|
|
for (i = 0; i < rinfo->dir_nr; i++) {
|
|
struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
|
|
struct ceph_vino tvino, dvino;
|
|
|
|
dname.name = rde->name;
|
|
dname.len = rde->name_len;
|
|
dname.hash = full_name_hash(parent, dname.name, dname.len);
|
|
|
|
tvino.ino = le64_to_cpu(rde->inode.in->ino);
|
|
tvino.snap = le64_to_cpu(rde->inode.in->snapid);
|
|
|
|
if (rinfo->hash_order) {
|
|
u32 hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
|
|
rde->name, rde->name_len);
|
|
hash = ceph_frag_value(hash);
|
|
if (hash != last_hash)
|
|
fpos_offset = 2;
|
|
last_hash = hash;
|
|
rde->offset = ceph_make_fpos(hash, fpos_offset++, true);
|
|
} else {
|
|
rde->offset = ceph_make_fpos(frag, fpos_offset++, false);
|
|
}
|
|
|
|
retry_lookup:
|
|
dn = d_lookup(parent, &dname);
|
|
dout("d_lookup on parent=%p name=%.*s got %p\n",
|
|
parent, dname.len, dname.name, dn);
|
|
|
|
if (!dn) {
|
|
dn = d_alloc(parent, &dname);
|
|
dout("d_alloc %p '%.*s' = %p\n", parent,
|
|
dname.len, dname.name, dn);
|
|
if (dn == NULL) {
|
|
dout("d_alloc badness\n");
|
|
err = -ENOMEM;
|
|
goto out;
|
|
}
|
|
} else if (d_really_is_positive(dn) &&
|
|
(ceph_ino(d_inode(dn)) != tvino.ino ||
|
|
ceph_snap(d_inode(dn)) != tvino.snap)) {
|
|
dout(" dn %p points to wrong inode %p\n",
|
|
dn, d_inode(dn));
|
|
d_delete(dn);
|
|
dput(dn);
|
|
goto retry_lookup;
|
|
}
|
|
|
|
/* inode */
|
|
if (d_really_is_positive(dn)) {
|
|
in = d_inode(dn);
|
|
} else {
|
|
in = ceph_get_inode(parent->d_sb, tvino);
|
|
if (IS_ERR(in)) {
|
|
dout("new_inode badness\n");
|
|
d_drop(dn);
|
|
dput(dn);
|
|
err = PTR_ERR(in);
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
ret = fill_inode(in, NULL, &rde->inode, NULL, session,
|
|
req->r_request_started, -1,
|
|
&req->r_caps_reservation);
|
|
if (ret < 0) {
|
|
pr_err("fill_inode badness on %p\n", in);
|
|
if (d_really_is_negative(dn))
|
|
iput(in);
|
|
d_drop(dn);
|
|
err = ret;
|
|
goto next_item;
|
|
}
|
|
|
|
if (d_really_is_negative(dn)) {
|
|
struct dentry *realdn;
|
|
|
|
if (ceph_security_xattr_deadlock(in)) {
|
|
dout(" skip splicing dn %p to inode %p"
|
|
" (security xattr deadlock)\n", dn, in);
|
|
iput(in);
|
|
skipped++;
|
|
goto next_item;
|
|
}
|
|
|
|
realdn = splice_dentry(dn, in);
|
|
if (IS_ERR(realdn)) {
|
|
err = PTR_ERR(realdn);
|
|
d_drop(dn);
|
|
dn = NULL;
|
|
goto next_item;
|
|
}
|
|
dn = realdn;
|
|
}
|
|
|
|
ceph_dentry(dn)->offset = rde->offset;
|
|
|
|
dvino = ceph_vino(d_inode(parent));
|
|
update_dentry_lease(dn, rde->lease, req->r_session,
|
|
req->r_request_started, &tvino, &dvino);
|
|
|
|
if (err == 0 && skipped == 0 && cache_ctl.index >= 0) {
|
|
ret = fill_readdir_cache(d_inode(parent), dn,
|
|
&cache_ctl, req);
|
|
if (ret < 0)
|
|
err = ret;
|
|
}
|
|
next_item:
|
|
if (dn)
|
|
dput(dn);
|
|
}
|
|
out:
|
|
if (err == 0 && skipped == 0) {
|
|
set_bit(CEPH_MDS_R_DID_PREPOPULATE, &req->r_req_flags);
|
|
req->r_readdir_cache_idx = cache_ctl.index;
|
|
}
|
|
ceph_readdir_cache_release(&cache_ctl);
|
|
if (snapdir) {
|
|
iput(snapdir);
|
|
dput(parent);
|
|
}
|
|
dout("readdir_prepopulate done\n");
|
|
return err;
|
|
}
|
|
|
|
int ceph_inode_set_size(struct inode *inode, loff_t size)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
int ret = 0;
|
|
|
|
spin_lock(&ci->i_ceph_lock);
|
|
dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size);
|
|
i_size_write(inode, size);
|
|
inode->i_blocks = calc_inode_blocks(size);
|
|
|
|
/* tell the MDS if we are approaching max_size */
|
|
if ((size << 1) >= ci->i_max_size &&
|
|
(ci->i_reported_size << 1) < ci->i_max_size)
|
|
ret = 1;
|
|
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Write back inode data in a worker thread. (This can't be done
|
|
* in the message handler context.)
|
|
*/
|
|
void ceph_queue_writeback(struct inode *inode)
|
|
{
|
|
ihold(inode);
|
|
if (queue_work(ceph_inode_to_client(inode)->wb_wq,
|
|
&ceph_inode(inode)->i_wb_work)) {
|
|
dout("ceph_queue_writeback %p\n", inode);
|
|
} else {
|
|
dout("ceph_queue_writeback %p failed\n", inode);
|
|
iput(inode);
|
|
}
|
|
}
|
|
|
|
static void ceph_writeback_work(struct work_struct *work)
|
|
{
|
|
struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
|
|
i_wb_work);
|
|
struct inode *inode = &ci->vfs_inode;
|
|
|
|
dout("writeback %p\n", inode);
|
|
filemap_fdatawrite(&inode->i_data);
|
|
iput(inode);
|
|
}
|
|
|
|
/*
|
|
* queue an async invalidation
|
|
*/
|
|
void ceph_queue_invalidate(struct inode *inode)
|
|
{
|
|
ihold(inode);
|
|
if (queue_work(ceph_inode_to_client(inode)->pg_inv_wq,
|
|
&ceph_inode(inode)->i_pg_inv_work)) {
|
|
dout("ceph_queue_invalidate %p\n", inode);
|
|
} else {
|
|
dout("ceph_queue_invalidate %p failed\n", inode);
|
|
iput(inode);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Invalidate inode pages in a worker thread. (This can't be done
|
|
* in the message handler context.)
|
|
*/
|
|
static void ceph_invalidate_work(struct work_struct *work)
|
|
{
|
|
struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
|
|
i_pg_inv_work);
|
|
struct inode *inode = &ci->vfs_inode;
|
|
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
|
|
u32 orig_gen;
|
|
int check = 0;
|
|
|
|
mutex_lock(&ci->i_truncate_mutex);
|
|
|
|
if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
|
|
pr_warn_ratelimited("invalidate_pages %p %lld forced umount\n",
|
|
inode, ceph_ino(inode));
|
|
mapping_set_error(inode->i_mapping, -EIO);
|
|
truncate_pagecache(inode, 0);
|
|
mutex_unlock(&ci->i_truncate_mutex);
|
|
goto out;
|
|
}
|
|
|
|
spin_lock(&ci->i_ceph_lock);
|
|
dout("invalidate_pages %p gen %d revoking %d\n", inode,
|
|
ci->i_rdcache_gen, ci->i_rdcache_revoking);
|
|
if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
|
|
if (__ceph_caps_revoking_other(ci, NULL, CEPH_CAP_FILE_CACHE))
|
|
check = 1;
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
mutex_unlock(&ci->i_truncate_mutex);
|
|
goto out;
|
|
}
|
|
orig_gen = ci->i_rdcache_gen;
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
|
|
if (invalidate_inode_pages2(inode->i_mapping) < 0) {
|
|
pr_err("invalidate_pages %p fails\n", inode);
|
|
}
|
|
|
|
spin_lock(&ci->i_ceph_lock);
|
|
if (orig_gen == ci->i_rdcache_gen &&
|
|
orig_gen == ci->i_rdcache_revoking) {
|
|
dout("invalidate_pages %p gen %d successful\n", inode,
|
|
ci->i_rdcache_gen);
|
|
ci->i_rdcache_revoking--;
|
|
check = 1;
|
|
} else {
|
|
dout("invalidate_pages %p gen %d raced, now %d revoking %d\n",
|
|
inode, orig_gen, ci->i_rdcache_gen,
|
|
ci->i_rdcache_revoking);
|
|
if (__ceph_caps_revoking_other(ci, NULL, CEPH_CAP_FILE_CACHE))
|
|
check = 1;
|
|
}
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
mutex_unlock(&ci->i_truncate_mutex);
|
|
out:
|
|
if (check)
|
|
ceph_check_caps(ci, 0, NULL);
|
|
iput(inode);
|
|
}
|
|
|
|
|
|
/*
|
|
* called by trunc_wq;
|
|
*
|
|
* We also truncate in a separate thread as well.
|
|
*/
|
|
static void ceph_vmtruncate_work(struct work_struct *work)
|
|
{
|
|
struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
|
|
i_vmtruncate_work);
|
|
struct inode *inode = &ci->vfs_inode;
|
|
|
|
dout("vmtruncate_work %p\n", inode);
|
|
__ceph_do_pending_vmtruncate(inode);
|
|
iput(inode);
|
|
}
|
|
|
|
/*
|
|
* Queue an async vmtruncate. If we fail to queue work, we will handle
|
|
* the truncation the next time we call __ceph_do_pending_vmtruncate.
|
|
*/
|
|
void ceph_queue_vmtruncate(struct inode *inode)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
|
|
ihold(inode);
|
|
|
|
if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq,
|
|
&ci->i_vmtruncate_work)) {
|
|
dout("ceph_queue_vmtruncate %p\n", inode);
|
|
} else {
|
|
dout("ceph_queue_vmtruncate %p failed, pending=%d\n",
|
|
inode, ci->i_truncate_pending);
|
|
iput(inode);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Make sure any pending truncation is applied before doing anything
|
|
* that may depend on it.
|
|
*/
|
|
void __ceph_do_pending_vmtruncate(struct inode *inode)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
u64 to;
|
|
int wrbuffer_refs, finish = 0;
|
|
|
|
mutex_lock(&ci->i_truncate_mutex);
|
|
retry:
|
|
spin_lock(&ci->i_ceph_lock);
|
|
if (ci->i_truncate_pending == 0) {
|
|
dout("__do_pending_vmtruncate %p none pending\n", inode);
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
mutex_unlock(&ci->i_truncate_mutex);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* make sure any dirty snapped pages are flushed before we
|
|
* possibly truncate them.. so write AND block!
|
|
*/
|
|
if (ci->i_wrbuffer_ref_head < ci->i_wrbuffer_ref) {
|
|
dout("__do_pending_vmtruncate %p flushing snaps first\n",
|
|
inode);
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
filemap_write_and_wait_range(&inode->i_data, 0,
|
|
inode->i_sb->s_maxbytes);
|
|
goto retry;
|
|
}
|
|
|
|
/* there should be no reader or writer */
|
|
WARN_ON_ONCE(ci->i_rd_ref || ci->i_wr_ref);
|
|
|
|
to = ci->i_truncate_size;
|
|
wrbuffer_refs = ci->i_wrbuffer_ref;
|
|
dout("__do_pending_vmtruncate %p (%d) to %lld\n", inode,
|
|
ci->i_truncate_pending, to);
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
|
|
truncate_pagecache(inode, to);
|
|
|
|
spin_lock(&ci->i_ceph_lock);
|
|
if (to == ci->i_truncate_size) {
|
|
ci->i_truncate_pending = 0;
|
|
finish = 1;
|
|
}
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
if (!finish)
|
|
goto retry;
|
|
|
|
mutex_unlock(&ci->i_truncate_mutex);
|
|
|
|
if (wrbuffer_refs == 0)
|
|
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
|
|
|
|
wake_up_all(&ci->i_cap_wq);
|
|
}
|
|
|
|
/*
|
|
* symlinks
|
|
*/
|
|
static const struct inode_operations ceph_symlink_iops = {
|
|
.get_link = simple_get_link,
|
|
.setattr = ceph_setattr,
|
|
.getattr = ceph_getattr,
|
|
.listxattr = ceph_listxattr,
|
|
};
|
|
|
|
int __ceph_setattr(struct inode *inode, struct iattr *attr)
|
|
{
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
const unsigned int ia_valid = attr->ia_valid;
|
|
struct ceph_mds_request *req;
|
|
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
|
|
struct ceph_cap_flush *prealloc_cf;
|
|
int issued;
|
|
int release = 0, dirtied = 0;
|
|
int mask = 0;
|
|
int err = 0;
|
|
int inode_dirty_flags = 0;
|
|
bool lock_snap_rwsem = false;
|
|
|
|
prealloc_cf = ceph_alloc_cap_flush();
|
|
if (!prealloc_cf)
|
|
return -ENOMEM;
|
|
|
|
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETATTR,
|
|
USE_AUTH_MDS);
|
|
if (IS_ERR(req)) {
|
|
ceph_free_cap_flush(prealloc_cf);
|
|
return PTR_ERR(req);
|
|
}
|
|
|
|
spin_lock(&ci->i_ceph_lock);
|
|
issued = __ceph_caps_issued(ci, NULL);
|
|
|
|
if (!ci->i_head_snapc &&
|
|
(issued & (CEPH_CAP_ANY_EXCL | CEPH_CAP_FILE_WR))) {
|
|
lock_snap_rwsem = true;
|
|
if (!down_read_trylock(&mdsc->snap_rwsem)) {
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
down_read(&mdsc->snap_rwsem);
|
|
spin_lock(&ci->i_ceph_lock);
|
|
issued = __ceph_caps_issued(ci, NULL);
|
|
}
|
|
}
|
|
|
|
dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
|
|
|
|
if (ia_valid & ATTR_UID) {
|
|
dout("setattr %p uid %d -> %d\n", inode,
|
|
from_kuid(&init_user_ns, inode->i_uid),
|
|
from_kuid(&init_user_ns, attr->ia_uid));
|
|
if (issued & CEPH_CAP_AUTH_EXCL) {
|
|
inode->i_uid = attr->ia_uid;
|
|
dirtied |= CEPH_CAP_AUTH_EXCL;
|
|
} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
|
|
!uid_eq(attr->ia_uid, inode->i_uid)) {
|
|
req->r_args.setattr.uid = cpu_to_le32(
|
|
from_kuid(&init_user_ns, attr->ia_uid));
|
|
mask |= CEPH_SETATTR_UID;
|
|
release |= CEPH_CAP_AUTH_SHARED;
|
|
}
|
|
}
|
|
if (ia_valid & ATTR_GID) {
|
|
dout("setattr %p gid %d -> %d\n", inode,
|
|
from_kgid(&init_user_ns, inode->i_gid),
|
|
from_kgid(&init_user_ns, attr->ia_gid));
|
|
if (issued & CEPH_CAP_AUTH_EXCL) {
|
|
inode->i_gid = attr->ia_gid;
|
|
dirtied |= CEPH_CAP_AUTH_EXCL;
|
|
} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
|
|
!gid_eq(attr->ia_gid, inode->i_gid)) {
|
|
req->r_args.setattr.gid = cpu_to_le32(
|
|
from_kgid(&init_user_ns, attr->ia_gid));
|
|
mask |= CEPH_SETATTR_GID;
|
|
release |= CEPH_CAP_AUTH_SHARED;
|
|
}
|
|
}
|
|
if (ia_valid & ATTR_MODE) {
|
|
dout("setattr %p mode 0%o -> 0%o\n", inode, inode->i_mode,
|
|
attr->ia_mode);
|
|
if (issued & CEPH_CAP_AUTH_EXCL) {
|
|
inode->i_mode = attr->ia_mode;
|
|
dirtied |= CEPH_CAP_AUTH_EXCL;
|
|
} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
|
|
attr->ia_mode != inode->i_mode) {
|
|
inode->i_mode = attr->ia_mode;
|
|
req->r_args.setattr.mode = cpu_to_le32(attr->ia_mode);
|
|
mask |= CEPH_SETATTR_MODE;
|
|
release |= CEPH_CAP_AUTH_SHARED;
|
|
}
|
|
}
|
|
|
|
if (ia_valid & ATTR_ATIME) {
|
|
dout("setattr %p atime %ld.%ld -> %ld.%ld\n", inode,
|
|
inode->i_atime.tv_sec, inode->i_atime.tv_nsec,
|
|
attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec);
|
|
if (issued & CEPH_CAP_FILE_EXCL) {
|
|
ci->i_time_warp_seq++;
|
|
inode->i_atime = attr->ia_atime;
|
|
dirtied |= CEPH_CAP_FILE_EXCL;
|
|
} else if ((issued & CEPH_CAP_FILE_WR) &&
|
|
timespec_compare(&inode->i_atime,
|
|
&attr->ia_atime) < 0) {
|
|
inode->i_atime = attr->ia_atime;
|
|
dirtied |= CEPH_CAP_FILE_WR;
|
|
} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
|
|
!timespec_equal(&inode->i_atime, &attr->ia_atime)) {
|
|
ceph_encode_timespec(&req->r_args.setattr.atime,
|
|
&attr->ia_atime);
|
|
mask |= CEPH_SETATTR_ATIME;
|
|
release |= CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_RD |
|
|
CEPH_CAP_FILE_WR;
|
|
}
|
|
}
|
|
if (ia_valid & ATTR_MTIME) {
|
|
dout("setattr %p mtime %ld.%ld -> %ld.%ld\n", inode,
|
|
inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
|
|
attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec);
|
|
if (issued & CEPH_CAP_FILE_EXCL) {
|
|
ci->i_time_warp_seq++;
|
|
inode->i_mtime = attr->ia_mtime;
|
|
dirtied |= CEPH_CAP_FILE_EXCL;
|
|
} else if ((issued & CEPH_CAP_FILE_WR) &&
|
|
timespec_compare(&inode->i_mtime,
|
|
&attr->ia_mtime) < 0) {
|
|
inode->i_mtime = attr->ia_mtime;
|
|
dirtied |= CEPH_CAP_FILE_WR;
|
|
} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
|
|
!timespec_equal(&inode->i_mtime, &attr->ia_mtime)) {
|
|
ceph_encode_timespec(&req->r_args.setattr.mtime,
|
|
&attr->ia_mtime);
|
|
mask |= CEPH_SETATTR_MTIME;
|
|
release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD |
|
|
CEPH_CAP_FILE_WR;
|
|
}
|
|
}
|
|
if (ia_valid & ATTR_SIZE) {
|
|
dout("setattr %p size %lld -> %lld\n", inode,
|
|
inode->i_size, attr->ia_size);
|
|
if ((issued & CEPH_CAP_FILE_EXCL) &&
|
|
attr->ia_size > inode->i_size) {
|
|
i_size_write(inode, attr->ia_size);
|
|
inode->i_blocks = calc_inode_blocks(attr->ia_size);
|
|
inode->i_ctime = attr->ia_ctime;
|
|
ci->i_reported_size = attr->ia_size;
|
|
dirtied |= CEPH_CAP_FILE_EXCL;
|
|
} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
|
|
attr->ia_size != inode->i_size) {
|
|
req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
|
|
req->r_args.setattr.old_size =
|
|
cpu_to_le64(inode->i_size);
|
|
mask |= CEPH_SETATTR_SIZE;
|
|
release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD |
|
|
CEPH_CAP_FILE_WR;
|
|
}
|
|
}
|
|
|
|
/* these do nothing */
|
|
if (ia_valid & ATTR_CTIME) {
|
|
bool only = (ia_valid & (ATTR_SIZE|ATTR_MTIME|ATTR_ATIME|
|
|
ATTR_MODE|ATTR_UID|ATTR_GID)) == 0;
|
|
dout("setattr %p ctime %ld.%ld -> %ld.%ld (%s)\n", inode,
|
|
inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
|
|
attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec,
|
|
only ? "ctime only" : "ignored");
|
|
inode->i_ctime = attr->ia_ctime;
|
|
if (only) {
|
|
/*
|
|
* if kernel wants to dirty ctime but nothing else,
|
|
* we need to choose a cap to dirty under, or do
|
|
* a almost-no-op setattr
|
|
*/
|
|
if (issued & CEPH_CAP_AUTH_EXCL)
|
|
dirtied |= CEPH_CAP_AUTH_EXCL;
|
|
else if (issued & CEPH_CAP_FILE_EXCL)
|
|
dirtied |= CEPH_CAP_FILE_EXCL;
|
|
else if (issued & CEPH_CAP_XATTR_EXCL)
|
|
dirtied |= CEPH_CAP_XATTR_EXCL;
|
|
else
|
|
mask |= CEPH_SETATTR_CTIME;
|
|
}
|
|
}
|
|
if (ia_valid & ATTR_FILE)
|
|
dout("setattr %p ATTR_FILE ... hrm!\n", inode);
|
|
|
|
if (dirtied) {
|
|
inode_dirty_flags = __ceph_mark_dirty_caps(ci, dirtied,
|
|
&prealloc_cf);
|
|
inode->i_ctime = current_time(inode);
|
|
}
|
|
|
|
release &= issued;
|
|
spin_unlock(&ci->i_ceph_lock);
|
|
if (lock_snap_rwsem)
|
|
up_read(&mdsc->snap_rwsem);
|
|
|
|
if (inode_dirty_flags)
|
|
__mark_inode_dirty(inode, inode_dirty_flags);
|
|
|
|
if (ia_valid & ATTR_MODE) {
|
|
err = posix_acl_chmod(inode, attr->ia_mode);
|
|
if (err)
|
|
goto out_put;
|
|
}
|
|
|
|
if (mask) {
|
|
req->r_inode = inode;
|
|
ihold(inode);
|
|
req->r_inode_drop = release;
|
|
req->r_args.setattr.mask = cpu_to_le32(mask);
|
|
req->r_num_caps = 1;
|
|
err = ceph_mdsc_do_request(mdsc, NULL, req);
|
|
}
|
|
dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
|
|
ceph_cap_string(dirtied), mask);
|
|
|
|
ceph_mdsc_put_request(req);
|
|
if (mask & CEPH_SETATTR_SIZE)
|
|
__ceph_do_pending_vmtruncate(inode);
|
|
ceph_free_cap_flush(prealloc_cf);
|
|
return err;
|
|
out_put:
|
|
ceph_mdsc_put_request(req);
|
|
ceph_free_cap_flush(prealloc_cf);
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* setattr
|
|
*/
|
|
int ceph_setattr(struct dentry *dentry, struct iattr *attr)
|
|
{
|
|
struct inode *inode = d_inode(dentry);
|
|
int err;
|
|
|
|
if (ceph_snap(inode) != CEPH_NOSNAP)
|
|
return -EROFS;
|
|
|
|
err = setattr_prepare(dentry, attr);
|
|
if (err != 0)
|
|
return err;
|
|
|
|
return __ceph_setattr(inode, attr);
|
|
}
|
|
|
|
/*
|
|
* Verify that we have a lease on the given mask. If not,
|
|
* do a getattr against an mds.
|
|
*/
|
|
int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
|
|
int mask, bool force)
|
|
{
|
|
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
|
|
struct ceph_mds_client *mdsc = fsc->mdsc;
|
|
struct ceph_mds_request *req;
|
|
int err;
|
|
|
|
if (ceph_snap(inode) == CEPH_SNAPDIR) {
|
|
dout("do_getattr inode %p SNAPDIR\n", inode);
|
|
return 0;
|
|
}
|
|
|
|
dout("do_getattr inode %p mask %s mode 0%o\n",
|
|
inode, ceph_cap_string(mask), inode->i_mode);
|
|
if (!force && ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
|
|
return 0;
|
|
|
|
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS);
|
|
if (IS_ERR(req))
|
|
return PTR_ERR(req);
|
|
req->r_inode = inode;
|
|
ihold(inode);
|
|
req->r_num_caps = 1;
|
|
req->r_args.getattr.mask = cpu_to_le32(mask);
|
|
req->r_locked_page = locked_page;
|
|
err = ceph_mdsc_do_request(mdsc, NULL, req);
|
|
if (locked_page && err == 0) {
|
|
u64 inline_version = req->r_reply_info.targeti.inline_version;
|
|
if (inline_version == 0) {
|
|
/* the reply is supposed to contain inline data */
|
|
err = -EINVAL;
|
|
} else if (inline_version == CEPH_INLINE_NONE) {
|
|
err = -ENODATA;
|
|
} else {
|
|
err = req->r_reply_info.targeti.inline_len;
|
|
}
|
|
}
|
|
ceph_mdsc_put_request(req);
|
|
dout("do_getattr result=%d\n", err);
|
|
return err;
|
|
}
|
|
|
|
|
|
/*
|
|
* Check inode permissions. We verify we have a valid value for
|
|
* the AUTH cap, then call the generic handler.
|
|
*/
|
|
int ceph_permission(struct inode *inode, int mask)
|
|
{
|
|
int err;
|
|
|
|
if (mask & MAY_NOT_BLOCK)
|
|
return -ECHILD;
|
|
|
|
err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, false);
|
|
|
|
if (!err)
|
|
err = generic_permission(inode, mask);
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* Get all attributes. Hopefully somedata we'll have a statlite()
|
|
* and can limit the fields we require to be accurate.
|
|
*/
|
|
int ceph_getattr(const struct path *path, struct kstat *stat,
|
|
u32 request_mask, unsigned int flags)
|
|
{
|
|
struct inode *inode = d_inode(path->dentry);
|
|
struct ceph_inode_info *ci = ceph_inode(inode);
|
|
int err;
|
|
|
|
err = ceph_do_getattr(inode, CEPH_STAT_CAP_INODE_ALL, false);
|
|
if (!err) {
|
|
generic_fillattr(inode, stat);
|
|
stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino);
|
|
if (ceph_snap(inode) != CEPH_NOSNAP)
|
|
stat->dev = ceph_snap(inode);
|
|
else
|
|
stat->dev = 0;
|
|
if (S_ISDIR(inode->i_mode)) {
|
|
if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb),
|
|
RBYTES))
|
|
stat->size = ci->i_rbytes;
|
|
else
|
|
stat->size = ci->i_files + ci->i_subdirs;
|
|
stat->blocks = 0;
|
|
stat->blksize = 65536;
|
|
}
|
|
}
|
|
return err;
|
|
}
|