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_alloc_request(struct ceph_osd_client *osdc,
int flags,
struct ceph_snap_context *snapc,
struct ceph_osd_req_op *ops,
bool use_mempool,
gfp_t gfp_flags,
struct page **pages,
struct bio *bio)
{
struct ceph_osd_request *req;
struct ceph_msg *msg;
int needs_trail;
int num_op = get_num_ops(ops, &needs_trail);
size_t msg_size = sizeof(struct ceph_osd_request_head);
msg_size += num_op*sizeof(struct ceph_osd_op);
if (use_mempool) {
req = mempool_alloc(osdc->req_mempool, gfp_flags);
memset(req, 0, sizeof(*req));
} else {
req = kzalloc(sizeof(*req), gfp_flags);
}
if (req == NULL)
return NULL;
req->r_osdc = osdc;
req->r_mempool = use_mempool;
kref_init(&req->r_kref);
init_completion(&req->r_completion);
init_completion(&req->r_safe_completion);
rb_init_node(&req->r_node);
INIT_LIST_HEAD(&req->r_unsafe_item);
INIT_LIST_HEAD(&req->r_linger_item);
INIT_LIST_HEAD(&req->r_linger_osd);
INIT_LIST_HEAD(&req->r_req_lru_item);
INIT_LIST_HEAD(&req->r_osd_item);
req->r_flags = flags;
WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
/* create reply message */
if (use_mempool)
msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
else
msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY,
OSD_OPREPLY_FRONT_LEN, gfp_flags, true);
if (!msg) {
ceph_osdc_put_request(req);
return NULL;
}
req->r_reply = msg;
/* allocate space for the trailing data */
if (needs_trail) {
req->r_trail = kmalloc(sizeof(struct ceph_pagelist), gfp_flags);
if (!req->r_trail) {
ceph_osdc_put_request(req);
return NULL;
}
ceph_pagelist_init(req->r_trail);
}
/* create request message; allow space for oid */
msg_size += MAX_OBJ_NAME_SIZE;
if (snapc)
msg_size += sizeof(u64) * snapc->num_snaps;
if (use_mempool)
msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
else
msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags, true);
if (!msg) {
ceph_osdc_put_request(req);
return NULL;
}
memset(msg->front.iov_base, 0, msg->front.iov_len);
req->r_request = msg;
req->r_pages = pages;
#ifdef CONFIG_BLOCK
if (bio) {
req->r_bio = bio;
bio_get(req->r_bio);
}
#endif
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)
{
struct ceph_osd_request *req;
struct ceph_msg *msg;
struct ceph_osd_request_head *head;
struct ceph_osd_op *op;
void *p;
int num_op = 1 + do_sync;
size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
int i;
if (use_mempool) {
req = mempool_alloc(osdc->req_mempool, GFP_NOFS);
memset(req, 0, sizeof(*req));
} else {
req = kzalloc(sizeof(*req), GFP_NOFS);
}
if (req == NULL)
return NULL;
req->r_osdc = osdc;
req->r_mempool = use_mempool;
kref_init(&req->r_kref);
init_completion(&req->r_completion);
init_completion(&req->r_safe_completion);
INIT_LIST_HEAD(&req->r_unsafe_item);
req->r_flags = flags;
WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
/* create reply message */
if (use_mempool)
msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
else
msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY,
OSD_OPREPLY_FRONT_LEN, GFP_NOFS);
if (!msg) {
ceph_osdc_put_request(req);
return NULL;
}
req->r_reply = msg;
/* create request message; allow space for oid */
msg_size += 40;
if (snapc)
msg_size += sizeof(u64) * snapc->num_snaps;
if (use_mempool)
msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
else
msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, GFP_NOFS);
if (!msg) {
ceph_osdc_put_request(req);
return NULL;
}
msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP);
memset(msg->front.iov_base, 0, msg->front.iov_len);
head = msg->front.iov_base;
op = (void *)(head + 1);
p = (void *)(op + num_op);
req->r_request = msg;
req->r_snapc = ceph_get_snap_context(snapc);
head->client_inc = cpu_to_le32(1); /* always, for now. */
head->flags = cpu_to_le32(flags);
if (flags & CEPH_OSD_FLAG_WRITE)
ceph_encode_timespec(&head->mtime, mtime);
head->num_ops = cpu_to_le16(num_op);
op->op = cpu_to_le16(opcode);
/* calculate max write size */
calc_layout(osdc, vino, layout, off, plen, req);
req->r_file_layout = *layout; /* keep a copy */
if (flags & CEPH_OSD_FLAG_WRITE) {
req->r_request->hdr.data_off = cpu_to_le16(off);
req->r_request->hdr.data_len = cpu_to_le32(*plen);
op->payload_len = cpu_to_le32(*plen);
}
op->extent.truncate_size = cpu_to_le64(truncate_size);
op->extent.truncate_seq = cpu_to_le32(truncate_seq);
/* fill in oid */
head->object_len = cpu_to_le32(req->r_oid_len);
memcpy(p, req->r_oid, req->r_oid_len);
p += req->r_oid_len;
if (do_sync) {
op++;
op->op = cpu_to_le16(CEPH_OSD_OP_STARTSYNC);
}
if (snapc) {
head->snap_seq = cpu_to_le64(snapc->seq);
head->num_snaps = cpu_to_le32(snapc->num_snaps);
for (i = 0; i < snapc->num_snaps; i++) {
put_unaligned_le64(snapc->snaps[i], p);
p += sizeof(u64);
}
}
BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
msg_size = p - msg->front.iov_base;
msg->front.iov_len = msg_size;
msg->hdr.front_len = cpu_to_le32(msg_size);
return req;
}
