void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
struct ceph_file_layout *layout,
u64 snapid,
u64 off, u64 *plen, u64 *bno,
struct ceph_osd_request *req,
struct ceph_osd_req_op *op)
{
struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
u64 orig_len = *plen;
u64 objoff, objlen; /* extent in object */
reqhead->snapid = cpu_to_le64(snapid);
/* object extent? */
ceph_calc_file_object_mapping(layout, off, plen, bno,
&objoff, &objlen);
if (*plen < orig_len)
dout(" skipping last %llu, final file extent %llu~%llu\n",
orig_len - *plen, off, *plen);
if (op_has_extent(op->op)) {
op->extent.offset = objoff;
op->extent.length = objlen;
}
req->r_num_pages = calc_pages_for(off, *plen);
req->r_page_alignment = off & ~PAGE_MASK;
if (op->op == CEPH_OSD_OP_WRITE)
op->payload_len = *plen;
dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
*bno, objoff, objlen, req->r_num_pages);
}
/*
* calculate the mapping of a file extent onto an object, and fill out the
* request accordingly. shorten extent as necessary if it crosses an
* object boundary.
*
* fill osd op in request message.
*/
static void calc_layout(struct ceph_osd_client *osdc,
struct ceph_vino vino, struct ceph_file_layout *layout,
u64 off, u64 *plen,
struct ceph_osd_request *req)
{
struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
struct ceph_osd_op *op = (void *)(reqhead + 1);
u64 orig_len = *plen;
u64 objoff, objlen; /* extent in object */
u64 bno;
reqhead->snapid = cpu_to_le64(vino.snap);
/* object extent? */
ceph_calc_file_object_mapping(layout, off, plen, &bno,
&objoff, &objlen);
if (*plen < orig_len)
dout(" skipping last %llu, final file extent %llu~%llu\n",
orig_len - *plen, off, *plen);
sprintf(req->r_oid, "%llx.%08llx", vino.ino, bno);
req->r_oid_len = strlen(req->r_oid);
op->extent.offset = cpu_to_le64(objoff);
op->extent.length = cpu_to_le64(objlen);
req->r_num_pages = calc_pages_for(off, *plen);
dout("calc_layout %s (%d) %llu~%llu (%d pages)\n",
req->r_oid, req->r_oid_len, objoff, objlen, req->r_num_pages);
}
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;
}
struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
struct ceph_file_layout *layout,
struct ceph_vino vino,
u64 off, u64 *plen,
int opcode, int flags,
struct ceph_snap_context *snapc,
int do_sync,
u32 truncate_seq,
u64 truncate_size,
struct timespec *mtime,
bool use_mempool, int num_reply,
int page_align)
{
struct ceph_osd_req_op ops[3];
struct ceph_osd_request *req;
int r;
ops[0].op = opcode;
ops[0].extent.truncate_seq = truncate_seq;
ops[0].extent.truncate_size = truncate_size;
ops[0].payload_len = 0;
if (do_sync) {
ops[1].op = CEPH_OSD_OP_STARTSYNC;
ops[1].payload_len = 0;
ops[2].op = 0;
} else
ops[1].op = 0;
req = ceph_osdc_alloc_request(osdc, flags,
snapc, ops,
use_mempool,
GFP_NOFS, NULL, NULL);
if (!req)
return NULL;
r = calc_layout(osdc, vino, layout, off, plen, req, ops);
if (r < 0)
return ERR_PTR(r);
req->r_file_layout = *layout;
req->r_num_pages = calc_pages_for(page_align, *plen);
req->r_page_alignment = page_align;
ceph_osdc_build_request(req, off, plen, ops,
snapc,
mtime,
req->r_oid, req->r_oid_len);
return req;
}
/*
* build new request AND message, calculate layout, and adjust file
* extent as needed.
*
* if the file was recently truncated, we include information about its
* old and new size so that the object can be updated appropriately. (we
* avoid synchronously deleting truncated objects because it's slow.)
*
* if @do_sync, include a 'startsync' command so that the osd will flush
* data quickly.
*/
struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
struct ceph_file_layout *layout,
struct ceph_vino vino,
u64 off, u64 *plen,
int opcode, int flags,
struct ceph_snap_context *snapc,
int do_sync,
u32 truncate_seq,
u64 truncate_size,
struct timespec *mtime,
bool use_mempool, int num_reply,
int page_align)
{
struct ceph_osd_req_op ops[3];
struct ceph_osd_request *req;
ops[0].op = opcode;
ops[0].extent.truncate_seq = truncate_seq;
ops[0].extent.truncate_size = truncate_size;
ops[0].payload_len = 0;
if (do_sync) {
ops[1].op = CEPH_OSD_OP_STARTSYNC;
ops[1].payload_len = 0;
ops[2].op = 0;
} else
ops[1].op = 0;
req = ceph_osdc_alloc_request(osdc, flags,
snapc, ops,
use_mempool,
GFP_NOFS, NULL, NULL);
if (!req)
return NULL;
/* calculate max write size */
calc_layout(osdc, vino, layout, off, plen, req, ops);
req->r_file_layout = *layout; /* keep a copy */
/* in case it differs from natural (file) alignment that
calc_layout filled in for us */
req->r_num_pages = calc_pages_for(page_align, *plen);
req->r_page_alignment = page_align;
ceph_osdc_build_request(req, off, plen, ops,
snapc,
mtime,
req->r_oid, req->r_oid_len);
return req;
}
/*
* Completely synchronous read and write methods. Direct from __user
* buffer to osd, or directly to user pages (if O_DIRECT).
*
* If the read spans object boundary, just do multiple reads.
*/
static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
int *checkeof)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct page **pages;
u64 off = iocb->ki_pos;
int num_pages;
ssize_t ret;
size_t len = iov_iter_count(to);
dout("sync_read on file %p %llu~%u %s\n", file, off,
(unsigned)len,
(file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
if (!len)
return 0;
/*
* flush any page cache pages in this range. this
* will make concurrent normal and sync io slow,
* but it will at least behave sensibly when they are
* in sequence.
*/
ret = filemap_write_and_wait_range(inode->i_mapping, off,
off + len);
if (ret < 0)
return ret;
if (unlikely(to->type & ITER_PIPE)) {
size_t page_off;
ret = iov_iter_get_pages_alloc(to, &pages, len,
&page_off);
if (ret <= 0)
return -ENOMEM;
num_pages = DIV_ROUND_UP(ret + page_off, PAGE_SIZE);
ret = striped_read(inode, off, ret, pages, num_pages,
page_off, checkeof);
if (ret > 0) {
iov_iter_advance(to, ret);
off += ret;
} else {
iov_iter_advance(to, 0);
}
ceph_put_page_vector(pages, num_pages, false);
} else {
num_pages = calc_pages_for(off, len);
pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
if (IS_ERR(pages))
return PTR_ERR(pages);
ret = striped_read(inode, off, len, pages, num_pages,
(off & ~PAGE_MASK), checkeof);
if (ret > 0) {
int l, k = 0;
size_t left = ret;
while (left) {
size_t page_off = off & ~PAGE_MASK;
size_t copy = min_t(size_t, left,
PAGE_SIZE - page_off);
l = copy_page_to_iter(pages[k++], page_off,
copy, to);
off += l;
left -= l;
if (l < copy)
break;
}
}
ceph_release_page_vector(pages, num_pages);
}
if (off > iocb->ki_pos) {
ret = off - iocb->ki_pos;
iocb->ki_pos = off;
}
dout("sync_read result %zd\n", ret);
return ret;
}
