/*
* Dirty a page. Optimistically adjust accounting, on the assumption
* that we won't race with invalidate. If we do, readjust.
*/
static int ceph_set_page_dirty(struct page *page)
{
struct address_space *mapping = page->mapping;
struct inode *inode;
struct ceph_inode_info *ci;
struct ceph_snap_context *snapc;
int ret;
if (unlikely(!mapping))
return !TestSetPageDirty(page);
if (PageDirty(page)) {
dout("%p set_page_dirty %p idx %lu -- already dirty\n",
mapping->host, page, page->index);
BUG_ON(!PagePrivate(page));
return 0;
}
inode = mapping->host;
ci = ceph_inode(inode);
/* dirty the head */
spin_lock(&ci->i_ceph_lock);
BUG_ON(ci->i_wr_ref == 0); // caller should hold Fw reference
if (__ceph_have_pending_cap_snap(ci)) {
struct ceph_cap_snap *capsnap =
list_last_entry(&ci->i_cap_snaps,
struct ceph_cap_snap,
ci_item);
snapc = ceph_get_snap_context(capsnap->context);
capsnap->dirty_pages++;
} else {
static void ceph_aio_retry_work(struct work_struct *work)
{
struct ceph_aio_work *aio_work =
container_of(work, struct ceph_aio_work, work);
struct ceph_osd_request *orig_req = aio_work->req;
struct ceph_aio_request *aio_req = orig_req->r_priv;
struct inode *inode = orig_req->r_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_snap_context *snapc;
struct ceph_osd_request *req;
int ret;
spin_lock(&ci->i_ceph_lock);
if (__ceph_have_pending_cap_snap(ci)) {
struct ceph_cap_snap *capsnap =
list_last_entry(&ci->i_cap_snaps,
struct ceph_cap_snap,
ci_item);
snapc = ceph_get_snap_context(capsnap->context);
} else {
/*
* build new request AND message
*
*/
void ceph_osdc_build_request(struct ceph_osd_request *req,
u64 off, u64 *plen,
struct ceph_osd_req_op *src_ops,
struct ceph_snap_context *snapc,
struct timespec *mtime,
const char *oid,
int oid_len)
{
struct ceph_msg *msg = req->r_request;
struct ceph_osd_request_head *head;
struct ceph_osd_req_op *src_op;
struct ceph_osd_op *op;
void *p;
int num_op = get_num_ops(src_ops, NULL);
size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
int flags = req->r_flags;
u64 data_len = 0;
int i;
head = msg->front.iov_base;
op = (void *)(head + 1);
p = (void *)(op + num_op);
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);
/* fill in oid */
head->object_len = cpu_to_le32(oid_len);
memcpy(p, oid, oid_len);
p += oid_len;
src_op = src_ops;
while (src_op->op) {
osd_req_encode_op(req, op, src_op);
src_op++;
op++;
}
if (req->r_trail)
data_len += req->r_trail->length;
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);
}
}
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 + data_len);
} else if (data_len) {
req->r_request->hdr.data_off = 0;
req->r_request->hdr.data_len = cpu_to_le32(data_len);
}
req->r_request->page_alignment = req->r_page_alignment;
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;
}
/*
* 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;
}
inode = mapping->host;
ci = ceph_inode(inode);
/* dirty the head */
spin_lock(&ci->i_ceph_lock);
BUG_ON(ci->i_wr_ref == 0); // caller should hold Fw reference
if (__ceph_have_pending_cap_snap(ci)) {
struct ceph_cap_snap *capsnap =
list_last_entry(&ci->i_cap_snaps,
struct ceph_cap_snap,
ci_item);
snapc = ceph_get_snap_context(capsnap->context);
capsnap->dirty_pages++;
} else {
BUG_ON(!ci->i_head_snapc);
snapc = ceph_get_snap_context(ci->i_head_snapc);
++ci->i_wrbuffer_ref_head;
}
if (ci->i_wrbuffer_ref == 0)
ihold(inode);
++ci->i_wrbuffer_ref;
dout("%p set_page_dirty %p idx %lu head %d/%d -> %d/%d "
"snapc %p seq %lld (%d snaps)\n",
mapping->host, page, page->index,
ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
snapc, snapc->seq, snapc->num_snaps);
spin_unlock(&ci->i_ceph_lock);
/*
* Reference snap context in page->private. Also set
