static void ceph_aio_complete_req(struct ceph_osd_request *req)
{
int rc = req->r_result;
struct inode *inode = req->r_inode;
struct ceph_aio_request *aio_req = req->r_priv;
struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
int num_pages = calc_pages_for((u64)osd_data->alignment,
osd_data->length);
dout("ceph_aio_complete_req %p rc %d bytes %llu\n",
inode, rc, osd_data->length);
if (rc == -EOLDSNAPC) {
struct ceph_aio_work *aio_work;
BUG_ON(!aio_req->write);
aio_work = kmalloc(sizeof(*aio_work), GFP_NOFS);
if (aio_work) {
INIT_WORK(&aio_work->work, ceph_aio_retry_work);
aio_work->req = req;
queue_work(ceph_inode_to_client(inode)->wb_wq,
&aio_work->work);
return;
}
rc = -ENOMEM;
} else if (!aio_req->write) {
if (rc == -ENOENT)
rc = 0;
if (rc >= 0 && osd_data->length > rc) {
int zoff = osd_data->alignment + rc;
int zlen = osd_data->length - rc;
/*
* If read is satisfied by single OSD request,
* it can pass EOF. Otherwise read is within
* i_size.
*/
if (aio_req->num_reqs == 1) {
loff_t i_size = i_size_read(inode);
loff_t endoff = aio_req->iocb->ki_pos + rc;
if (endoff < i_size)
zlen = min_t(size_t, zlen,
i_size - endoff);
aio_req->total_len = rc + zlen;
}
if (zlen > 0)
ceph_zero_page_vector_range(zoff, zlen,
osd_data->pages);
}
}
ceph_put_page_vector(osd_data->pages, num_pages, !aio_req->write);
ceph_osdc_put_request(req);
if (rc < 0)
cmpxchg(&aio_req->error, 0, rc);
ceph_aio_complete(inode, aio_req);
return;
}
static int striped_read(struct inode *inode,
u64 off, u64 len,
struct page **pages, int num_pages,
int *checkeof, bool o_direct,
unsigned long buf_align)
{
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_inode_info *ci = ceph_inode(inode);
u64 pos, this_len;
int io_align, page_align;
int left, pages_left;
int read;
struct page **page_pos;
int ret;
bool hit_stripe, was_short;
pos = off;
left = len;
page_pos = pages;
pages_left = num_pages;
read = 0;
io_align = off & ~PAGE_MASK;
more:
if (o_direct)
page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
else
page_align = pos & ~PAGE_MASK;
this_len = left;
ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
&ci->i_layout, pos, &this_len,
ci->i_truncate_seq,
ci->i_truncate_size,
page_pos, pages_left, page_align);
if (ret == -ENOENT)
ret = 0;
hit_stripe = this_len < left;
was_short = ret >= 0 && ret < this_len;
dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
if (ret > 0) {
int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
if (read < pos - off) {
dout(" zero gap %llu to %llu\n", off + read, pos);
ceph_zero_page_vector_range(page_align + read,
pos - off - read, pages);
}
pos += ret;
read = pos - off;
left -= ret;
page_pos += didpages;
pages_left -= didpages;
if (left && hit_stripe)
goto more;
}
void ceph_adjust_quota_realms_count(struct inode *inode, bool inc)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
if (inc)
atomic64_inc(&mdsc->quotarealms_count);
else
atomic64_dec(&mdsc->quotarealms_count);
}
/*
* Read a range of bytes striped over one or more objects. Iterate over
* objects we stripe over. (That's not atomic, but good enough for now.)
*
* If we get a short result from the OSD, check against i_size; we need to
* only return a short read to the caller if we hit EOF.
*/
static int striped_read(struct inode *inode,
u64 off, u64 len,
struct page **pages, int num_pages,
int *checkeof)
{
struct ceph_client *client = ceph_inode_to_client(inode);
struct ceph_inode_info *ci = ceph_inode(inode);
u64 pos, this_len;
int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */
int left, pages_left;
int read;
struct page **page_pos;
int ret;
bool hit_stripe, was_short;
/*
* we may need to do multiple reads. not atomic, unfortunately.
*/
pos = off;
left = len;
page_pos = pages;
pages_left = num_pages;
read = 0;
more:
this_len = left;
ret = ceph_osdc_readpages(&client->osdc, ceph_vino(inode),
&ci->i_layout, pos, &this_len,
ci->i_truncate_seq,
ci->i_truncate_size,
page_pos, pages_left);
hit_stripe = this_len < left;
was_short = ret >= 0 && ret < this_len;
if (ret == -ENOENT)
ret = 0;
dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
if (ret > 0) {
int didpages =
((pos & ~PAGE_CACHE_MASK) + ret) >> PAGE_CACHE_SHIFT;
if (read < pos - off) {
dout(" zero gap %llu to %llu\n", off + read, pos);
zero_page_vector_range(page_off + read,
pos - off - read, pages);
}
pos += ret;
read = pos - off;
left -= ret;
page_pos += didpages;
pages_left -= didpages;
/* hit stripe? */
if (left && hit_stripe)
goto more;
}
static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct ceph_fs_client *fsc = ceph_inode_to_client(dentry->d_inode);
struct ceph_monmap *monmap = fsc->client->monc.monmap;
struct ceph_statfs st;
u64 fsid;
int err;
dout("statfs\n");
err = ceph_monc_do_statfs(&fsc->client->monc, &st);
if (err < 0)
return err;
/* fill in kstatfs */
buf->f_type = CEPH_SUPER_MAGIC; /* ?? */
/*
* express utilization in terms of large blocks to avoid
* overflow on 32-bit machines.
*
* NOTE: for the time being, we make bsize == frsize to humor
* not-yet-ancient versions of glibc that are broken.
* Someday, we will probably want to report a real block
* size... whatever that may mean for a network file system!
*/
buf->f_bsize = 1 << CEPH_BLOCK_SHIFT;
buf->f_frsize = 1 << CEPH_BLOCK_SHIFT;
buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10);
buf->f_bfree = (le64_to_cpu(st.kb) - le64_to_cpu(st.kb_used)) >>
(CEPH_BLOCK_SHIFT-10);
buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);
buf->f_files = le64_to_cpu(st.num_objects);
buf->f_ffree = -1;
buf->f_namelen = NAME_MAX;
/* leave fsid little-endian, regardless of host endianness */
fsid = *(u64 *)(&monmap->fsid) ^ *((u64 *)&monmap->fsid + 1);
buf->f_fsid.val[0] = fsid & 0xffffffff;
buf->f_fsid.val[1] = fsid >> 32;
return 0;
}
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;
mdsc = ceph_inode_to_client(d_inode(child))->mdsc;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
USE_ANY_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
inode_lock(d_inode(parent));
req->r_inode = d_inode(child);
ihold(d_inode(child));
req->r_ino2 = ceph_vino(d_inode(parent));
req->r_parent = d_inode(parent);
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
req->r_num_caps = 2;
err = ceph_mdsc_do_request(mdsc, NULL, req);
inode_unlock(d_inode(parent));
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",
child, ceph_vinop(d_inode(child)), name);
} else {
dout("get_name %p ino %llx.%llx err %d\n",
child, ceph_vinop(d_inode(child)), err);
}
ceph_mdsc_put_request(req);
return err;
}
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;
mdsc = ceph_inode_to_client(child->d_inode)->mdsc;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
USE_ANY_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
mutex_lock(&parent->d_inode->i_mutex);
req->r_inode = child->d_inode;
ihold(child->d_inode);
req->r_ino2 = ceph_vino(parent->d_inode);
req->r_locked_dir = parent->d_inode;
req->r_num_caps = 2;
err = ceph_mdsc_do_request(mdsc, NULL, req);
mutex_unlock(&parent->d_inode->i_mutex);
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",
child, ceph_vinop(child->d_inode), name);
} else {
dout("get_name %p ino %llx.%llx err %d\n",
child, ceph_vinop(child->d_inode), err);
}
ceph_mdsc_put_request(req);
return err;
}
static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct ceph_client *client = ceph_inode_to_client(dentry->d_inode);
struct ceph_monmap *monmap = client->monc.monmap;
struct ceph_statfs st;
u64 fsid;
int err;
dout("statfs\n");
err = ceph_monc_do_statfs(&client->monc, &st);
if (err < 0)
return err;
/* fill in kstatfs */
buf->f_type = CEPH_SUPER_MAGIC; /* ?? */
/*
* express utilization in terms of large blocks to avoid
* overflow on 32-bit machines.
*/
buf->f_bsize = 1 << CEPH_BLOCK_SHIFT;
buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10);
buf->f_bfree = (le64_to_cpu(st.kb) - le64_to_cpu(st.kb_used)) >>
(CEPH_BLOCK_SHIFT-10);
buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);
buf->f_files = le64_to_cpu(st.num_objects);
buf->f_ffree = -1;
buf->f_namelen = NAME_MAX;
buf->f_frsize = PAGE_CACHE_SIZE;
/* leave fsid little-endian, regardless of host endianness */
fsid = *(u64 *)(&monmap->fsid) ^ *((u64 *)&monmap->fsid + 1);
buf->f_fsid.val[0] = fsid & 0xffffffff;
buf->f_fsid.val[1] = fsid >> 32;
return 0;
}
/*
* Read a range of bytes striped over one or more objects. Iterate over
* objects we stripe over. (That's not atomic, but good enough for now.)
*
* If we get a short result from the OSD, check against i_size; we need to
* only return a short read to the caller if we hit EOF.
*/
static int striped_read(struct inode *inode,
u64 off, u64 len,
struct page **pages, int num_pages,
int *checkeof, bool o_direct,
unsigned long buf_align)
{
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_inode_info *ci = ceph_inode(inode);
u64 pos, this_len, left;
int io_align, page_align;
int pages_left;
int read;
struct page **page_pos;
int ret;
bool hit_stripe, was_short;
/*
* we may need to do multiple reads. not atomic, unfortunately.
*/
pos = off;
left = len;
page_pos = pages;
pages_left = num_pages;
read = 0;
io_align = off & ~PAGE_MASK;
more:
if (o_direct)
page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
else
page_align = pos & ~PAGE_MASK;
this_len = left;
ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
&ci->i_layout, pos, &this_len,
ci->i_truncate_seq,
ci->i_truncate_size,
page_pos, pages_left, page_align);
if (ret == -ENOENT)
ret = 0;
hit_stripe = this_len < left;
was_short = ret >= 0 && ret < this_len;
dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, left, read,
ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
if (ret >= 0) {
int didpages;
if (was_short && (pos + ret < inode->i_size)) {
u64 tmp = min(this_len - ret,
inode->i_size - pos - ret);
dout(" zero gap %llu to %llu\n",
pos + ret, pos + ret + tmp);
ceph_zero_page_vector_range(page_align + read + ret,
tmp, pages);
ret += tmp;
}
didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
pos += ret;
read = pos - off;
left -= ret;
page_pos += didpages;
pages_left -= didpages;
/* hit stripe and need continue*/
if (left && hit_stripe && pos < inode->i_size)
goto more;
}
static inline bool ceph_has_realms_with_quotas(struct inode *inode)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
return atomic64_read(&mdsc->quotarealms_count) > 0;
}
if (has_quota || !next)
return realm;
ceph_get_snap_realm(mdsc, next);
ceph_put_snap_realm(mdsc, realm);
realm = next;
}
if (realm)
ceph_put_snap_realm(mdsc, realm);
return NULL;
}
bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(old)->mdsc;
struct ceph_snap_realm *old_realm, *new_realm;
bool is_same;
down_read(&mdsc->snap_rwsem);
old_realm = get_quota_realm(mdsc, old);
new_realm = get_quota_realm(mdsc, new);
is_same = (old_realm == new_realm);
up_read(&mdsc->snap_rwsem);
if (old_realm)
ceph_put_snap_realm(mdsc, old_realm);
if (new_realm)
ceph_put_snap_realm(mdsc, new_realm);
return is_same;
/*
* Read a range of bytes striped over one or more objects. Iterate over
* objects we stripe over. (That's not atomic, but good enough for now.)
*
* If we get a short result from the OSD, check against i_size; we need to
* only return a short read to the caller if we hit EOF.
*/
static int striped_read(struct inode *inode,
u64 off, u64 len,
struct page **pages, int num_pages,
int *checkeof, bool o_direct,
unsigned long buf_align)
{
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_inode_info *ci = ceph_inode(inode);
u64 pos, this_len, left;
int io_align, page_align;
int pages_left;
int read;
struct page **page_pos;
int ret;
bool hit_stripe, was_short;
/*
* we may need to do multiple reads. not atomic, unfortunately.
*/
pos = off;
left = len;
page_pos = pages;
pages_left = num_pages;
read = 0;
io_align = off & ~PAGE_MASK;
if (pos + left > inode->i_size) {
*checkeof = 1;
left = inode->i_size - pos;
}
more:
if (o_direct)
page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
else
page_align = pos & ~PAGE_MASK;
this_len = left;
ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
&ci->i_layout, pos, &this_len,
ci->i_truncate_seq,
ci->i_truncate_size,
page_pos, pages_left, page_align);
if (ret == -ENOENT)
ret = 0;
hit_stripe = ret >= 0 && this_len < left;
was_short = ret >= 0 && ret < this_len;
dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, left, read,
ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
if (was_short) {
/* zero trailing bytes */
dout("zero trailing %llu bytes\n", this_len - ret);
ceph_zero_page_vector_range(page_align + ret, this_len - ret,
page_pos);
}
if (ret >= 0) {
int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
pos += this_len;
read += this_len;
left -= this_len;
page_pos += didpages;
pages_left -= didpages;
}
/*
* Read a range of bytes striped over one or more objects. Iterate over
* objects we stripe over. (That's not atomic, but good enough for now.)
*
* If we get a short result from the OSD, check against i_size; we need to
* only return a short read to the caller if we hit EOF.
*/
static int striped_read(struct inode *inode,
u64 pos, u64 len,
struct page **pages, int num_pages,
int page_align, int *checkeof)
{
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_inode_info *ci = ceph_inode(inode);
u64 this_len;
loff_t i_size;
int page_idx;
int ret, read = 0;
bool hit_stripe, was_short;
/*
* we may need to do multiple reads. not atomic, unfortunately.
*/
more:
this_len = len;
page_idx = (page_align + read) >> PAGE_SHIFT;
ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
&ci->i_layout, pos, &this_len,
ci->i_truncate_seq, ci->i_truncate_size,
pages + page_idx, num_pages - page_idx,
((page_align + read) & ~PAGE_MASK));
if (ret == -ENOENT)
ret = 0;
hit_stripe = this_len < len;
was_short = ret >= 0 && ret < this_len;
dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, len, read,
ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
i_size = i_size_read(inode);
if (ret >= 0) {
if (was_short && (pos + ret < i_size)) {
int zlen = min(this_len - ret, i_size - pos - ret);
int zoff = page_align + read + ret;
dout(" zero gap %llu to %llu\n",
pos + ret, pos + ret + zlen);
ceph_zero_page_vector_range(zoff, zlen, pages);
ret += zlen;
}
read += ret;
pos += ret;
len -= ret;
/* hit stripe and need continue*/
if (len && hit_stripe && pos < i_size)
goto more;
}
if (read > 0) {
ret = read;
/* did we bounce off eof? */
if (pos + len > i_size)
*checkeof = CHECK_EOF;
}
dout("striped_read returns %d\n", ret);
return ret;
}
