}
/*
- * Give the client the number of slots it requests bound by
- * NFSD_MAX_SLOTS_PER_SESSION and by nfsd_drc_max_mem.
+ * The protocol defines ca_maxresponssize_cached to include the size of
+ * the rpc header, but all we need to cache is the data starting after
+ * the end of the initial SEQUENCE operation--the rest we regenerate
+ * each time. Therefore we can advertise a ca_maxresponssize_cached
+ * value that is the number of bytes in our cache plus a few additional
+ * bytes. In order to stay on the safe side, and not promise more than
+ * we can cache, those additional bytes must be the minimum possible: 24
+ * bytes of rpc header (xid through accept state, with AUTH_NULL
+ * verifier), 12 for the compound header (with zero-length tag), and 44
+ * for the SEQUENCE op response:
+ */
+#define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44)
+
+/*
+ * Give the client the number of ca_maxresponsesize_cached slots it
+ * requests, of size bounded by NFSD_SLOT_CACHE_SIZE,
+ * NFSD_MAX_MEM_PER_SESSION, and nfsd_drc_max_mem. Do not allow more
+ * than NFSD_MAX_SLOTS_PER_SESSION.
*
- * If we run out of reserved DRC memory we should (up to a point) re-negotiate
- * active sessions and reduce their slot usage to make rooom for new
- * connections. For now we just fail the create session.
+ * If we run out of reserved DRC memory we should (up to a point)
+ * re-negotiate active sessions and reduce their slot usage to make
+ * rooom for new connections. For now we just fail the create session.
*/
-static int set_forechannel_maxreqs(struct nfsd4_channel_attrs *fchan)
+static int set_forechannel_drc_size(struct nfsd4_channel_attrs *fchan)
{
- int mem;
+ int mem, size = fchan->maxresp_cached;
if (fchan->maxreqs < 1)
return nfserr_inval;
- else if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
- fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
- mem = fchan->maxreqs * NFSD_SLOT_CACHE_SIZE;
+ if (size < NFSD_MIN_HDR_SEQ_SZ)
+ size = NFSD_MIN_HDR_SEQ_SZ;
+ size -= NFSD_MIN_HDR_SEQ_SZ;
+ if (size > NFSD_SLOT_CACHE_SIZE)
+ size = NFSD_SLOT_CACHE_SIZE;
+
+ /* bound the maxreqs by NFSD_MAX_MEM_PER_SESSION */
+ mem = fchan->maxreqs * size;
+ if (mem > NFSD_MAX_MEM_PER_SESSION) {
+ fchan->maxreqs = NFSD_MAX_MEM_PER_SESSION / size;
+ if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
+ fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
+ mem = fchan->maxreqs * size;
+ }
spin_lock(&nfsd_drc_lock);
- if (mem + nfsd_drc_mem_used > nfsd_drc_max_mem)
- mem = ((nfsd_drc_max_mem - nfsd_drc_mem_used) /
- NFSD_SLOT_CACHE_SIZE) * NFSD_SLOT_CACHE_SIZE;
+ /* bound the total session drc memory ussage */
+ if (mem + nfsd_drc_mem_used > nfsd_drc_max_mem) {
+ fchan->maxreqs = (nfsd_drc_max_mem - nfsd_drc_mem_used) / size;
+ mem = fchan->maxreqs * size;
+ }
nfsd_drc_mem_used += mem;
spin_unlock(&nfsd_drc_lock);
- fchan->maxreqs = mem / NFSD_SLOT_CACHE_SIZE;
if (fchan->maxreqs == 0)
- return nfserr_resource;
+ return nfserr_serverfault;
+
+ fchan->maxresp_cached = size + NFSD_MIN_HDR_SEQ_SZ;
return 0;
}
fchan->maxresp_sz = maxcount;
session_fchan->maxresp_sz = fchan->maxresp_sz;
- session_fchan->maxresp_cached = NFSD_SLOT_CACHE_SIZE;
- fchan->maxresp_cached = session_fchan->maxresp_cached;
-
/* Use the client's maxops if possible */
if (fchan->maxops > NFSD_MAX_OPS_PER_COMPOUND)
fchan->maxops = NFSD_MAX_OPS_PER_COMPOUND;
* recover pages from existing sessions. For now fail session
* creation.
*/
- status = set_forechannel_maxreqs(fchan);
+ status = set_forechannel_drc_size(fchan);
+ session_fchan->maxresp_cached = fchan->maxresp_cached;
session_fchan->maxreqs = fchan->maxreqs;
+
+ dprintk("%s status %d\n", __func__, status);
return status;
}
+static void
+free_session_slots(struct nfsd4_session *ses)
+{
+ int i;
+
+ for (i = 0; i < ses->se_fchannel.maxreqs; i++)
+ kfree(ses->se_slots[i]);
+}
+
static int
alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
struct nfsd4_create_session *cses)
{
struct nfsd4_session *new, tmp;
- int idx, status = nfserr_resource, slotsize;
+ struct nfsd4_slot *sp;
+ int idx, slotsize, cachesize, i;
+ int status;
memset(&tmp, 0, sizeof(tmp));
if (status)
goto out;
- /* allocate struct nfsd4_session and slot table in one piece */
- slotsize = tmp.se_fchannel.maxreqs * sizeof(struct nfsd4_slot);
+ BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot)
+ + sizeof(struct nfsd4_session) > PAGE_SIZE);
+
+ status = nfserr_serverfault;
+ /* allocate struct nfsd4_session and slot table pointers in one piece */
+ slotsize = tmp.se_fchannel.maxreqs * sizeof(struct nfsd4_slot *);
new = kzalloc(sizeof(*new) + slotsize, GFP_KERNEL);
if (!new)
goto out;
memcpy(new, &tmp, sizeof(*new));
+ /* allocate each struct nfsd4_slot and data cache in one piece */
+ cachesize = new->se_fchannel.maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+ for (i = 0; i < new->se_fchannel.maxreqs; i++) {
+ sp = kzalloc(sizeof(*sp) + cachesize, GFP_KERNEL);
+ if (!sp)
+ goto out_free;
+ new->se_slots[i] = sp;
+ }
+
new->se_client = clp;
gen_sessionid(new);
idx = hash_sessionid(&new->se_sessionid);
status = nfs_ok;
out:
return status;
+out_free:
+ free_session_slots(new);
+ kfree(new);
+ goto out;
}
/* caller must hold sessionid_lock */
nfsd4_put_session(ses);
}
-static void nfsd4_release_respages(struct page **respages, short resused);
-
void
free_session(struct kref *kref)
{
struct nfsd4_session *ses;
- int i;
ses = container_of(kref, struct nfsd4_session, se_ref);
- for (i = 0; i < ses->se_fchannel.maxreqs; i++) {
- struct nfsd4_cache_entry *e = &ses->se_slots[i].sl_cache_entry;
- nfsd4_release_respages(e->ce_respages, e->ce_resused);
- }
spin_lock(&nfsd_drc_lock);
nfsd_drc_mem_used -= ses->se_fchannel.maxreqs * NFSD_SLOT_CACHE_SIZE;
spin_unlock(&nfsd_drc_lock);
+ free_session_slots(ses);
kfree(ses);
}
return NULL;
}
-/* a helper function for parse_callback */
-static int
-parse_octet(unsigned int *lenp, char **addrp)
-{
- unsigned int len = *lenp;
- char *p = *addrp;
- int n = -1;
- char c;
-
- for (;;) {
- if (!len)
- break;
- len--;
- c = *p++;
- if (c == '.')
- break;
- if ((c < '0') || (c > '9')) {
- n = -1;
- break;
- }
- if (n < 0)
- n = 0;
- n = (n * 10) + (c - '0');
- if (n > 255) {
- n = -1;
- break;
- }
- }
- *lenp = len;
- *addrp = p;
- return n;
-}
-
-/* parse and set the setclientid ipv4 callback address */
-static int
-parse_ipv4(unsigned int addr_len, char *addr_val, unsigned int *cbaddrp, unsigned short *cbportp)
-{
- int temp = 0;
- u32 cbaddr = 0;
- u16 cbport = 0;
- u32 addrlen = addr_len;
- char *addr = addr_val;
- int i, shift;
-
- /* ipaddress */
- shift = 24;
- for(i = 4; i > 0 ; i--) {
- if ((temp = parse_octet(&addrlen, &addr)) < 0) {
- return 0;
- }
- cbaddr |= (temp << shift);
- if (shift > 0)
- shift -= 8;
- }
- *cbaddrp = cbaddr;
-
- /* port */
- shift = 8;
- for(i = 2; i > 0 ; i--) {
- if ((temp = parse_octet(&addrlen, &addr)) < 0) {
- return 0;
- }
- cbport |= (temp << shift);
- if (shift > 0)
- shift -= 8;
- }
- *cbportp = cbport;
- return 1;
-}
-
static void
-gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se)
+gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid)
{
struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
-
- /* Currently, we only support tcp for the callback channel */
- if ((se->se_callback_netid_len != 3) || memcmp((char *)se->se_callback_netid_val, "tcp", 3))
+ unsigned short expected_family;
+
+ /* Currently, we only support tcp and tcp6 for the callback channel */
+ if (se->se_callback_netid_len == 3 &&
+ !memcmp(se->se_callback_netid_val, "tcp", 3))
+ expected_family = AF_INET;
+ else if (se->se_callback_netid_len == 4 &&
+ !memcmp(se->se_callback_netid_val, "tcp6", 4))
+ expected_family = AF_INET6;
+ else
goto out_err;
- if ( !(parse_ipv4(se->se_callback_addr_len, se->se_callback_addr_val,
- &cb->cb_addr, &cb->cb_port)))
+ cb->cb_addrlen = rpc_uaddr2sockaddr(se->se_callback_addr_val,
+ se->se_callback_addr_len,
+ (struct sockaddr *) &cb->cb_addr,
+ sizeof(cb->cb_addr));
+
+ if (!cb->cb_addrlen || cb->cb_addr.ss_family != expected_family)
goto out_err;
+
+ if (cb->cb_addr.ss_family == AF_INET6)
+ ((struct sockaddr_in6 *) &cb->cb_addr)->sin6_scope_id = scopeid;
+
cb->cb_minorversion = 0;
cb->cb_prog = se->se_callback_prog;
cb->cb_ident = se->se_callback_ident;
return;
out_err:
+ cb->cb_addr.ss_family = AF_UNSPEC;
+ cb->cb_addrlen = 0;
dprintk(KERN_INFO "NFSD: this client (clientid %08x/%08x) "
"will not receive delegations\n",
clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id);
return;
}
-void
-nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp)
-{
- struct nfsd4_compoundres *resp = rqstp->rq_resp;
-
- resp->cstate.statp = statp;
-}
-
/*
- * Dereference the result pages.
- */
-static void
-nfsd4_release_respages(struct page **respages, short resused)
-{
- int i;
-
- dprintk("--> %s\n", __func__);
- for (i = 0; i < resused; i++) {
- if (!respages[i])
- continue;
- put_page(respages[i]);
- respages[i] = NULL;
- }
-}
-
-static void
-nfsd4_copy_pages(struct page **topages, struct page **frompages, short count)
-{
- int i;
-
- for (i = 0; i < count; i++) {
- topages[i] = frompages[i];
- if (!topages[i])
- continue;
- get_page(topages[i]);
- }
-}
-
-/*
- * Cache the reply pages up to NFSD_PAGES_PER_SLOT + 1, clearing the previous
- * pages. We add a page to NFSD_PAGES_PER_SLOT for the case where the total
- * length of the XDR response is less than se_fmaxresp_cached
- * (NFSD_PAGES_PER_SLOT * PAGE_SIZE) but the xdr_buf pages is used for a
- * of the reply (e.g. readdir).
- *
- * Store the base and length of the rq_req.head[0] page
- * of the NFSv4.1 data, just past the rpc header.
+ * Cache a reply. nfsd4_check_drc_limit() has bounded the cache size.
*/
void
nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
{
- struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry;
- struct svc_rqst *rqstp = resp->rqstp;
- struct nfsd4_compoundargs *args = rqstp->rq_argp;
- struct nfsd4_op *op = &args->ops[resp->opcnt];
- struct kvec *resv = &rqstp->rq_res.head[0];
-
- dprintk("--> %s entry %p\n", __func__, entry);
-
- /* Don't cache a failed OP_SEQUENCE. */
- if (resp->opcnt == 1 && op->opnum == OP_SEQUENCE && resp->cstate.status)
- return;
+ struct nfsd4_slot *slot = resp->cstate.slot;
+ unsigned int base;
- nfsd4_release_respages(entry->ce_respages, entry->ce_resused);
- entry->ce_opcnt = resp->opcnt;
- entry->ce_status = resp->cstate.status;
+ dprintk("--> %s slot %p\n", __func__, slot);
- /*
- * Don't need a page to cache just the sequence operation - the slot
- * does this for us!
- */
+ slot->sl_opcnt = resp->opcnt;
+ slot->sl_status = resp->cstate.status;
if (nfsd4_not_cached(resp)) {
- entry->ce_resused = 0;
- entry->ce_rpchdrlen = 0;
- dprintk("%s Just cache SEQUENCE. ce_cachethis %d\n", __func__,
- resp->cstate.slot->sl_cache_entry.ce_cachethis);
+ slot->sl_datalen = 0;
return;
}
- entry->ce_resused = rqstp->rq_resused;
- if (entry->ce_resused > NFSD_PAGES_PER_SLOT + 1)
- entry->ce_resused = NFSD_PAGES_PER_SLOT + 1;
- nfsd4_copy_pages(entry->ce_respages, rqstp->rq_respages,
- entry->ce_resused);
- entry->ce_datav.iov_base = resp->cstate.statp;
- entry->ce_datav.iov_len = resv->iov_len - ((char *)resp->cstate.statp -
- (char *)page_address(rqstp->rq_respages[0]));
- /* Current request rpc header length*/
- entry->ce_rpchdrlen = (char *)resp->cstate.statp -
- (char *)page_address(rqstp->rq_respages[0]);
-}
-
-/*
- * We keep the rpc header, but take the nfs reply from the replycache.
- */
-static int
-nfsd41_copy_replay_data(struct nfsd4_compoundres *resp,
- struct nfsd4_cache_entry *entry)
-{
- struct svc_rqst *rqstp = resp->rqstp;
- struct kvec *resv = &resp->rqstp->rq_res.head[0];
- int len;
-
- /* Current request rpc header length*/
- len = (char *)resp->cstate.statp -
- (char *)page_address(rqstp->rq_respages[0]);
- if (entry->ce_datav.iov_len + len > PAGE_SIZE) {
- dprintk("%s v41 cached reply too large (%Zd).\n", __func__,
- entry->ce_datav.iov_len);
- return 0;
- }
- /* copy the cached reply nfsd data past the current rpc header */
- memcpy((char *)resv->iov_base + len, entry->ce_datav.iov_base,
- entry->ce_datav.iov_len);
- resv->iov_len = len + entry->ce_datav.iov_len;
- return 1;
+ slot->sl_datalen = (char *)resp->p - (char *)resp->cstate.datap;
+ base = (char *)resp->cstate.datap -
+ (char *)resp->xbuf->head[0].iov_base;
+ if (read_bytes_from_xdr_buf(resp->xbuf, base, slot->sl_data,
+ slot->sl_datalen))
+ WARN("%s: sessions DRC could not cache compound\n", __func__);
+ return;
}
/*
struct nfsd4_slot *slot = resp->cstate.slot;
dprintk("--> %s resp->opcnt %d cachethis %u \n", __func__,
- resp->opcnt, resp->cstate.slot->sl_cache_entry.ce_cachethis);
+ resp->opcnt, resp->cstate.slot->sl_cachethis);
/* Encode the replayed sequence operation */
op = &args->ops[resp->opcnt - 1];
nfsd4_encode_operation(resp, op);
/* Return nfserr_retry_uncached_rep in next operation. */
- if (args->opcnt > 1 && slot->sl_cache_entry.ce_cachethis == 0) {
+ if (args->opcnt > 1 && slot->sl_cachethis == 0) {
op = &args->ops[resp->opcnt++];
op->status = nfserr_retry_uncached_rep;
nfsd4_encode_operation(resp, op);
}
/*
- * Keep the first page of the replay. Copy the NFSv4.1 data from the first
- * cached page. Replace any futher replay pages from the cache.
+ * The sequence operation is not cached because we can use the slot and
+ * session values.
*/
__be32
nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
struct nfsd4_sequence *seq)
{
- struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry;
+ struct nfsd4_slot *slot = resp->cstate.slot;
__be32 status;
- dprintk("--> %s entry %p\n", __func__, entry);
-
- /*
- * If this is just the sequence operation, we did not keep
- * a page in the cache entry because we can just use the
- * slot info stored in struct nfsd4_sequence that was checked
- * against the slot in nfsd4_sequence().
- *
- * This occurs when seq->cachethis is FALSE, or when the client
- * session inactivity timer fires and a solo sequence operation
- * is sent (lease renewal).
- */
- seq->maxslots = resp->cstate.session->se_fchannel.maxreqs;
+ dprintk("--> %s slot %p\n", __func__, slot);
/* Either returns 0 or nfserr_retry_uncached */
status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp);
if (status == nfserr_retry_uncached_rep)
return status;
- if (!nfsd41_copy_replay_data(resp, entry)) {
- /*
- * Not enough room to use the replay rpc header, send the
- * cached header. Release all the allocated result pages.
- */
- svc_free_res_pages(resp->rqstp);
- nfsd4_copy_pages(resp->rqstp->rq_respages, entry->ce_respages,
- entry->ce_resused);
- } else {
- /* Release all but the first allocated result page */
-
- resp->rqstp->rq_resused--;
- svc_free_res_pages(resp->rqstp);
-
- nfsd4_copy_pages(&resp->rqstp->rq_respages[1],
- &entry->ce_respages[1],
- entry->ce_resused - 1);
- }
+ /* The sequence operation has been encoded, cstate->datap set. */
+ memcpy(resp->cstate.datap, slot->sl_data, slot->sl_datalen);
- resp->rqstp->rq_resused = entry->ce_resused;
- resp->opcnt = entry->ce_opcnt;
- resp->cstate.iovlen = entry->ce_datav.iov_len + entry->ce_rpchdrlen;
- status = entry->ce_status;
+ resp->opcnt = slot->sl_opcnt;
+ resp->p = resp->cstate.datap + XDR_QUADLEN(slot->sl_datalen);
+ status = slot->sl_status;
return status;
}
/* Normal case */
new = create_client(exid->clname, dname);
if (new == NULL) {
- status = nfserr_resource;
+ status = nfserr_serverfault;
goto out;
}
if (seq->slotid >= session->se_fchannel.maxreqs)
goto out;
- slot = &session->se_slots[seq->slotid];
+ slot = session->se_slots[seq->slotid];
dprintk("%s: slotid %d\n", __func__, seq->slotid);
+ /* We do not negotiate the number of slots yet, so set the
+ * maxslots to the session maxreqs which is used to encode
+ * sr_highest_slotid and the sr_target_slot id to maxslots */
+ seq->maxslots = session->se_fchannel.maxreqs;
+
status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_inuse);
if (status == nfserr_replay_cache) {
cstate->slot = slot;
cstate->session = session;
/* Return the cached reply status and set cstate->status
- * for nfsd4_svc_encode_compoundres processing */
+ * for nfsd4_proc_compound processing */
status = nfsd4_replay_cache_entry(resp, seq);
cstate->status = nfserr_replay_cache;
- goto replay_cache;
+ goto out;
}
if (status)
goto out;
/* Success! bump slot seqid */
slot->sl_inuse = true;
slot->sl_seqid = seq->seqid;
- slot->sl_cache_entry.ce_cachethis = seq->cachethis;
- /* Always set the cache entry cachethis for solo sequence */
- if (nfsd4_is_solo_sequence(resp))
- slot->sl_cache_entry.ce_cachethis = 1;
+ slot->sl_cachethis = seq->cachethis;
cstate->slot = slot;
cstate->session = session;
-replay_cache:
- /* Renew the clientid on success and on replay.
- * Hold a session reference until done processing the compound:
+ /* Hold a session reference until done processing the compound:
* nfsd4_put_session called only if the cstate slot is set.
*/
- renew_client(session->se_client);
nfsd4_get_session(session);
out:
spin_unlock(&sessionid_lock);
+ /* Renew the clientid on success and on replay */
+ if (cstate->session) {
+ nfs4_lock_state();
+ renew_client(session->se_client);
+ nfs4_unlock_state();
+ }
dprintk("%s: return %d\n", __func__, ntohl(status));
return status;
}
}
copy_cred(&new->cl_cred, &rqstp->rq_cred);
gen_confirm(new);
- gen_callback(new, setclid);
+ gen_callback(new, setclid, rpc_get_scope_id(sa));
add_to_unconfirmed(new, strhashval);
setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot;
setclid->se_clientid.cl_id = new->cl_clientid.cl_id;
/* initialization to perform when the nfsd service is started: */
-static void
+static int
__nfs4_state_start(void)
{
unsigned long grace_time;
printk(KERN_INFO "NFSD: starting %ld-second grace period\n",
grace_time/HZ);
laundry_wq = create_singlethread_workqueue("nfsd4");
+ if (laundry_wq == NULL)
+ return -ENOMEM;
queue_delayed_work(laundry_wq, &laundromat_work, grace_time);
set_max_delegations();
+ return 0;
}
-void
+int
nfs4_state_start(void)
{
+ int ret;
+
if (nfs4_init)
- return;
+ return 0;
nfsd4_load_reboot_recovery_data();
- __nfs4_state_start();
+ ret = __nfs4_state_start();
+ if (ret)
+ return ret;
nfs4_init = 1;
- return;
+ return 0;
}
time_t
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff