----------------------------
-What: Support for VMware's guest paravirtuliazation technique [VMI] will be
- dropped.
-When: 2.6.37 or earlier.
-Why: With the recent innovations in CPU hardware acceleration technologies
- from Intel and AMD, VMware ran a few experiments to compare these
- techniques to guest paravirtualization technique on VMware's platform.
- These hardware assisted virtualization techniques have outperformed the
- performance benefits provided by VMI in most of the workloads. VMware
- expects that these hardware features will be ubiquitous in a couple of
- years, as a result, VMware has started a phased retirement of this
- feature from the hypervisor. We will be removing this feature from the
- Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
- technical reasons (read opportunity to remove major chunk of pvops)
- arise.
-
- Please note that VMI has always been an optimization and non-VMI kernels
- still work fine on VMware's platform.
- Latest versions of VMware's product which support VMI are,
- Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
- releases for these products will continue supporting VMI.
-
- For more details about VMI retirement take a look at this,
- http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
-
-Who: Alok N Kataria <akataria@vmware.com>
-
-----------------------------
-
What: Support for lcd_switch and display_get in asus-laptop driver
When: March 2010
Why: These two features use non-standard interfaces. There are the
----------------------------
-What: old ieee1394 subsystem (CONFIG_IEEE1394)
-When: 2.6.37
-Files: drivers/ieee1394/ except init_ohci1394_dma.c
-Why: superseded by drivers/firewire/ (CONFIG_FIREWIRE) which offers more
- features, better performance, and better security, all with smaller
- and more modern code base
-Who: Stefan Richter <stefanr@s5r6.in-berlin.de>
-
-----------------------------
-
What: The acpi_sleep=s4_nonvs command line option
When: 2.6.37
Files: arch/x86/kernel/acpi/sleep.c
----------------------------
-
+What: iwlwifi disable_hw_scan module parameters
+When: 2.6.40
+Why: Hareware scan is the prefer method for iwlwifi devices for
+ scanning operation. Remove software scan support for all the
+ iwlwifi devices.
+
+Who: Wey-Yi Guy <wey-yi.w.guy@intel.com>
+
+----------------------------
++
+ What: access to nfsd auth cache through sys_nfsservctl or '.' files
+ in the 'nfsd' filesystem.
+ When: 2.6.40
+ Why: This is a legacy interface which have been replaced by a more
+ dynamic cache. Continuing to maintain this interface is an
+ unnecessary burden.
+ Who: NeilBrown <neilb@suse.de>
+
+ ----------------------------
{
compat_ssize_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
- struct iovec *iov;
+ struct iovec *iov = iovstack;
ssize_t ret;
io_fn_t fn;
iov_fn_t fnv;
}
#endif /* HAVE_SET_RESTORE_SIGMASK */
- #if defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)
+ #if (defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)) && !defined(CONFIG_NFSD_DEPRECATED)
/* Stuff for NFS server syscalls... */
struct compat_nfsctl_svc {
u16 svc32_port;
#include "iostat.h"
#include "internal.h"
#include "fscache.h"
+#include "pnfs.h"
#define NFSDBG_FACILITY NFSDBG_CLIENT
cred = rpc_lookup_machine_cred();
if (!IS_ERR(cred))
clp->cl_machine_cred = cred;
-
+#if defined(CONFIG_NFS_V4_1)
+ INIT_LIST_HEAD(&clp->cl_layouts);
+#endif
nfs_fscache_get_client_cookie(clp);
return clp;
nfs_free_client(clp);
}
}
+EXPORT_SYMBOL_GPL(nfs_put_client);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
/*
{
struct rpc_clnt *clnt = NULL;
struct rpc_create_args args = {
+ .net = &init_net,
.protocol = clp->cl_proto,
.address = (struct sockaddr *)&clp->cl_addr,
.addrsize = clp->cl_addrlen,
*/
static void nfs_destroy_server(struct nfs_server *server)
{
- if (!(server->flags & NFS_MOUNT_NONLM))
+ if (!(server->flags & NFS_MOUNT_LOCAL_FLOCK) ||
+ !(server->flags & NFS_MOUNT_LOCAL_FCNTL))
nlmclnt_done(server->nlm_host);
}
if (nlm_init.nfs_version > 3)
return 0;
- if (server->flags & NFS_MOUNT_NONLM)
+ if ((server->flags & NFS_MOUNT_LOCAL_FLOCK) &&
+ (server->flags & NFS_MOUNT_LOCAL_FCNTL))
return 0;
switch (clp->cl_proto) {
if (server->wsize > NFS_MAX_FILE_IO_SIZE)
server->wsize = NFS_MAX_FILE_IO_SIZE;
server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ set_pnfs_layoutdriver(server, fsinfo->layouttype);
+
server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
server->dtsize = nfs_block_size(fsinfo->dtpref, NULL);
- if (server->dtsize > PAGE_CACHE_SIZE)
- server->dtsize = PAGE_CACHE_SIZE;
+ if (server->dtsize > PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES)
+ server->dtsize = PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES;
if (server->dtsize > server->rsize)
server->dtsize = server->rsize;
server->maxfilesize = fsinfo->maxfilesize;
+ server->time_delta = fsinfo->time_delta;
+
/* We're airborne Set socket buffersize */
rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
}
}
fsinfo.fattr = fattr;
+ fsinfo.layouttype = 0;
error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo);
if (error < 0)
goto out_error;
{
dprintk("--> nfs_free_server()\n");
+ unset_pnfs_layoutdriver(server);
spin_lock(&nfs_client_lock);
list_del(&server->client_link);
list_del(&server->master_link);
/* Initialise the client representation from the mount data */
server->flags = data->flags;
- server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|
- NFS_CAP_POSIX_LOCK;
+ server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
+ if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+ server->caps |= NFS_CAP_READDIRPLUS;
server->options = data->options;
/* Get a client record */
.rpc_resp = &result,
};
struct rpc_create_args args = {
+ .net = &init_net,
.protocol = info->protocol,
.address = info->sap,
.addrsize = info->salen,
.to_retries = 2,
};
struct rpc_create_args args = {
+ .net = &init_net,
.protocol = IPPROTO_UDP,
.address = info->sap,
.addrsize = info->salen,
for (i = 0; i < entries; i++) {
flavors[i] = ntohl(*p++);
- dprintk("NFS:\tflavor %u: %d\n", i, flavors[i]);
+ dprintk("NFS: auth flavor[%u]: %d\n", i, flavors[i]);
}
*count = i;
tristate "NFS server support"
depends on INET
depends on FILE_LOCKING
+ depends on BKL # fix as soon as lockd is done
select LOCKD
select SUNRPC
select EXPORTFS
If unsure, say N.
+ config NFSD_DEPRECATED
+ bool "Include support for deprecated syscall interface to NFSD"
+ depends on NFSD
+ default y
+ help
+ The syscall interface to nfsd was obsoleted in 2.6.0 by a new
+ filesystem based interface. The old interface is due for removal
+ in 2.6.40. If you wish to remove the interface before then
+ say N.
+
+ In unsure, say Y.
+
config NFSD_V2_ACL
bool
depends on NFSD
*/
#include <linux/file.h>
-#include <linux/smp_lock.h>
+#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/namei.h>
#include <linux/swap.h>
{
struct nfs4_delegation *dp;
struct nfs4_file *fp = stp->st_file;
- struct nfs4_cb_conn *cb = &stp->st_stateowner->so_client->cl_cb_conn;
dprintk("NFSD alloc_init_deleg\n");
/*
nfs4_file_get_access(fp, O_RDONLY);
dp->dl_flock = NULL;
dp->dl_type = type;
- dp->dl_ident = cb->cb_ident;
dp->dl_stateid.si_boot = boot_time;
dp->dl_stateid.si_stateownerid = current_delegid++;
dp->dl_stateid.si_fileid = 0;
*/
#define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44)
+ 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]);
+ }
+
/*
- * 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)
+ * We don't actually need to cache the rpc and session headers, so we
+ * can allocate a little less for each slot:
+ */
+ static inline int slot_bytes(struct nfsd4_channel_attrs *ca)
+ {
+ return ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+ }
+
+ static int nfsd4_sanitize_slot_size(u32 size)
+ {
+ size -= NFSD_MIN_HDR_SEQ_SZ; /* We don't cache the rpc header */
+ size = min_t(u32, size, NFSD_SLOT_CACHE_SIZE);
+
+ return size;
+ }
+
+ /*
+ * XXX: If we run out of reserved DRC memory we could (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_drc_size(struct nfsd4_channel_attrs *fchan)
+ static int nfsd4_get_drc_mem(int slotsize, u32 num)
{
- int mem, size = fchan->maxresp_cached;
+ int avail;
- if (fchan->maxreqs < 1)
- return nfserr_inval;
+ num = min_t(u32, num, NFSD_MAX_SLOTS_PER_SESSION);
- 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;
+ spin_lock(&nfsd_drc_lock);
+ avail = min_t(int, NFSD_MAX_MEM_PER_SESSION,
+ nfsd_drc_max_mem - nfsd_drc_mem_used);
+ num = min_t(int, num, avail / slotsize);
+ nfsd_drc_mem_used += num * slotsize;
+ spin_unlock(&nfsd_drc_lock);
- /* 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;
- }
+ return num;
+ }
+ static void nfsd4_put_drc_mem(int slotsize, int num)
+ {
spin_lock(&nfsd_drc_lock);
- /* 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;
+ nfsd_drc_mem_used -= slotsize * num;
spin_unlock(&nfsd_drc_lock);
+ }
- if (fchan->maxreqs == 0)
- return nfserr_jukebox;
+ static struct nfsd4_session *alloc_session(int slotsize, int numslots)
+ {
+ struct nfsd4_session *new;
+ int mem, i;
- fchan->maxresp_cached = size + NFSD_MIN_HDR_SEQ_SZ;
- return 0;
+ BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *)
+ + sizeof(struct nfsd4_session) > PAGE_SIZE);
+ mem = numslots * sizeof(struct nfsd4_slot *);
+
+ new = kzalloc(sizeof(*new) + mem, GFP_KERNEL);
+ if (!new)
+ return NULL;
+ /* allocate each struct nfsd4_slot and data cache in one piece */
+ for (i = 0; i < numslots; i++) {
+ mem = sizeof(struct nfsd4_slot) + slotsize;
+ new->se_slots[i] = kzalloc(mem, GFP_KERNEL);
+ if (!new->se_slots[i])
+ goto out_free;
+ }
+ return new;
+ out_free:
+ while (i--)
+ kfree(new->se_slots[i]);
+ kfree(new);
+ return NULL;
}
- /*
- * fchan holds the client values on input, and the server values on output
- * sv_max_mesg is the maximum payload plus one page for overhead.
- */
- static int init_forechannel_attrs(struct svc_rqst *rqstp,
- struct nfsd4_channel_attrs *session_fchan,
- struct nfsd4_channel_attrs *fchan)
+ static void init_forechannel_attrs(struct nfsd4_channel_attrs *new, struct nfsd4_channel_attrs *req, int numslots, int slotsize)
{
- int status = 0;
- __u32 maxcount = nfsd_serv->sv_max_mesg;
+ u32 maxrpc = nfsd_serv->sv_max_mesg;
- /* headerpadsz set to zero in encode routine */
+ new->maxreqs = numslots;
+ new->maxresp_cached = slotsize + NFSD_MIN_HDR_SEQ_SZ;
+ new->maxreq_sz = min_t(u32, req->maxreq_sz, maxrpc);
+ new->maxresp_sz = min_t(u32, req->maxresp_sz, maxrpc);
+ new->maxops = min_t(u32, req->maxops, NFSD_MAX_OPS_PER_COMPOUND);
+ }
- /* Use the client's max request and max response size if possible */
- if (fchan->maxreq_sz > maxcount)
- fchan->maxreq_sz = maxcount;
- session_fchan->maxreq_sz = fchan->maxreq_sz;
+ static void free_conn(struct nfsd4_conn *c)
+ {
+ svc_xprt_put(c->cn_xprt);
+ kfree(c);
+ }
- if (fchan->maxresp_sz > maxcount)
- fchan->maxresp_sz = maxcount;
- session_fchan->maxresp_sz = fchan->maxresp_sz;
+ static void nfsd4_conn_lost(struct svc_xpt_user *u)
+ {
+ struct nfsd4_conn *c = container_of(u, struct nfsd4_conn, cn_xpt_user);
+ struct nfs4_client *clp = c->cn_session->se_client;
- /* Use the client's maxops if possible */
- if (fchan->maxops > NFSD_MAX_OPS_PER_COMPOUND)
- fchan->maxops = NFSD_MAX_OPS_PER_COMPOUND;
- session_fchan->maxops = fchan->maxops;
+ spin_lock(&clp->cl_lock);
+ if (!list_empty(&c->cn_persession)) {
+ list_del(&c->cn_persession);
+ free_conn(c);
+ }
+ spin_unlock(&clp->cl_lock);
+ }
- /* FIXME: Error means no more DRC pages so the server should
- * recover pages from existing sessions. For now fail session
- * creation.
- */
- status = set_forechannel_drc_size(fchan);
+ static struct nfsd4_conn *alloc_conn(struct svc_rqst *rqstp, u32 flags)
+ {
+ struct nfsd4_conn *conn;
- session_fchan->maxresp_cached = fchan->maxresp_cached;
- session_fchan->maxreqs = fchan->maxreqs;
+ conn = kmalloc(sizeof(struct nfsd4_conn), GFP_KERNEL);
+ if (!conn)
+ return NULL;
+ svc_xprt_get(rqstp->rq_xprt);
+ conn->cn_xprt = rqstp->rq_xprt;
+ conn->cn_flags = flags;
+ INIT_LIST_HEAD(&conn->cn_xpt_user.list);
+ return conn;
+ }
- dprintk("%s status %d\n", __func__, status);
- return status;
+ static void __nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses)
+ {
+ conn->cn_session = ses;
+ list_add(&conn->cn_persession, &ses->se_conns);
}
- static void
- free_session_slots(struct nfsd4_session *ses)
+ static void nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses)
{
- int i;
+ struct nfs4_client *clp = ses->se_client;
- for (i = 0; i < ses->se_fchannel.maxreqs; i++)
- kfree(ses->se_slots[i]);
+ spin_lock(&clp->cl_lock);
+ __nfsd4_hash_conn(conn, ses);
+ spin_unlock(&clp->cl_lock);
}
- /*
- * We don't actually need to cache the rpc and session headers, so we
- * can allocate a little less for each slot:
- */
- static inline int slot_bytes(struct nfsd4_channel_attrs *ca)
+ static void nfsd4_register_conn(struct nfsd4_conn *conn)
{
- return ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+ conn->cn_xpt_user.callback = nfsd4_conn_lost;
+ register_xpt_user(conn->cn_xprt, &conn->cn_xpt_user);
}
- static int
- alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
- struct nfsd4_create_session *cses)
+ static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses)
{
- struct nfsd4_session *new, tmp;
- struct nfsd4_slot *sp;
- int idx, slotsize, cachesize, i;
- int status;
+ struct nfsd4_conn *conn;
+ u32 flags = NFS4_CDFC4_FORE;
- memset(&tmp, 0, sizeof(tmp));
+ if (ses->se_flags & SESSION4_BACK_CHAN)
+ flags |= NFS4_CDFC4_BACK;
+ conn = alloc_conn(rqstp, flags);
+ if (!conn)
+ return nfserr_jukebox;
+ nfsd4_hash_conn(conn, ses);
+ nfsd4_register_conn(conn);
+ return nfs_ok;
+ }
- /* FIXME: For now, we just accept the client back channel attributes. */
- tmp.se_bchannel = cses->back_channel;
- status = init_forechannel_attrs(rqstp, &tmp.se_fchannel,
- &cses->fore_channel);
- if (status)
- goto out;
+ static void nfsd4_del_conns(struct nfsd4_session *s)
+ {
+ struct nfs4_client *clp = s->se_client;
+ struct nfsd4_conn *c;
- BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot)
- + sizeof(struct nfsd4_session) > PAGE_SIZE);
+ spin_lock(&clp->cl_lock);
+ while (!list_empty(&s->se_conns)) {
+ c = list_first_entry(&s->se_conns, struct nfsd4_conn, cn_persession);
+ list_del_init(&c->cn_persession);
+ spin_unlock(&clp->cl_lock);
- status = nfserr_jukebox;
- /* 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;
+ unregister_xpt_user(c->cn_xprt, &c->cn_xpt_user);
+ free_conn(c);
- memcpy(new, &tmp, sizeof(*new));
+ spin_lock(&clp->cl_lock);
+ }
+ spin_unlock(&clp->cl_lock);
+ }
- /* allocate each struct nfsd4_slot and data cache in one piece */
- cachesize = slot_bytes(&new->se_fchannel);
- 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;
+ void free_session(struct kref *kref)
+ {
+ struct nfsd4_session *ses;
+ int mem;
+
+ ses = container_of(kref, struct nfsd4_session, se_ref);
+ nfsd4_del_conns(ses);
+ spin_lock(&nfsd_drc_lock);
+ mem = ses->se_fchannel.maxreqs * slot_bytes(&ses->se_fchannel);
+ nfsd_drc_mem_used -= mem;
+ spin_unlock(&nfsd_drc_lock);
+ free_session_slots(ses);
+ kfree(ses);
+ }
+
+ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, struct nfsd4_create_session *cses)
+ {
+ struct nfsd4_session *new;
+ struct nfsd4_channel_attrs *fchan = &cses->fore_channel;
+ int numslots, slotsize;
+ int status;
+ int idx;
+
+ /*
+ * Note decreasing slot size below client's request may
+ * make it difficult for client to function correctly, whereas
+ * decreasing the number of slots will (just?) affect
+ * performance. When short on memory we therefore prefer to
+ * decrease number of slots instead of their size.
+ */
+ slotsize = nfsd4_sanitize_slot_size(fchan->maxresp_cached);
+ numslots = nfsd4_get_drc_mem(slotsize, fchan->maxreqs);
+
+ new = alloc_session(slotsize, numslots);
+ if (!new) {
+ nfsd4_put_drc_mem(slotsize, fchan->maxreqs);
+ return NULL;
}
+ init_forechannel_attrs(&new->se_fchannel, fchan, numslots, slotsize);
new->se_client = clp;
gen_sessionid(new);
- idx = hash_sessionid(&new->se_sessionid);
- memcpy(clp->cl_sessionid.data, new->se_sessionid.data,
- NFS4_MAX_SESSIONID_LEN);
+ INIT_LIST_HEAD(&new->se_conns);
+
+ new->se_cb_seq_nr = 1;
new->se_flags = cses->flags;
+ new->se_cb_prog = cses->callback_prog;
kref_init(&new->se_ref);
+ idx = hash_sessionid(&new->se_sessionid);
spin_lock(&client_lock);
list_add(&new->se_hash, &sessionid_hashtbl[idx]);
list_add(&new->se_perclnt, &clp->cl_sessions);
spin_unlock(&client_lock);
- status = nfs_ok;
- out:
- return status;
- out_free:
- free_session_slots(new);
- kfree(new);
- goto out;
+ status = nfsd4_new_conn(rqstp, new);
+ /* whoops: benny points out, status is ignored! (err, or bogus) */
+ if (status) {
+ free_session(&new->se_ref);
+ return NULL;
+ }
+ if (!clp->cl_cb_session && (cses->flags & SESSION4_BACK_CHAN)) {
+ struct sockaddr *sa = svc_addr(rqstp);
+
+ clp->cl_cb_session = new;
+ clp->cl_cb_conn.cb_xprt = rqstp->rq_xprt;
+ svc_xprt_get(rqstp->rq_xprt);
+ rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa);
+ clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa);
+ nfsd4_probe_callback(clp);
+ }
+ return new;
}
/* caller must hold client_lock */
list_del(&ses->se_perclnt);
}
- void
- free_session(struct kref *kref)
- {
- struct nfsd4_session *ses;
- int mem;
-
- ses = container_of(kref, struct nfsd4_session, se_ref);
- spin_lock(&nfsd_drc_lock);
- mem = ses->se_fchannel.maxreqs * slot_bytes(&ses->se_fchannel);
- nfsd_drc_mem_used -= mem;
- spin_unlock(&nfsd_drc_lock);
- free_session_slots(ses);
- kfree(ses);
- }
-
/* must be called under the client_lock */
static inline void
renew_client_locked(struct nfs4_client *clp)
static inline void
free_client(struct nfs4_client *clp)
{
+ while (!list_empty(&clp->cl_sessions)) {
+ struct nfsd4_session *ses;
+ ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
+ se_perclnt);
+ list_del(&ses->se_perclnt);
+ nfsd4_put_session(ses);
+ }
if (clp->cl_cred.cr_group_info)
put_group_info(clp->cl_cred.cr_group_info);
kfree(clp->cl_principal);
static inline void
unhash_client_locked(struct nfs4_client *clp)
{
+ struct nfsd4_session *ses;
+
mark_client_expired(clp);
list_del(&clp->cl_lru);
- while (!list_empty(&clp->cl_sessions)) {
- struct nfsd4_session *ses;
- ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
- se_perclnt);
- unhash_session(ses);
- nfsd4_put_session(ses);
- }
+ list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
+ list_del_init(&ses->se_hash);
}
static void
sop = list_entry(clp->cl_openowners.next, struct nfs4_stateowner, so_perclient);
release_openowner(sop);
}
- nfsd4_set_callback_client(clp, NULL);
+ nfsd4_shutdown_callback(clp);
if (clp->cl_cb_conn.cb_xprt)
svc_xprt_put(clp->cl_cb_conn.cb_xprt);
list_del(&clp->cl_idhash);
if (clp == NULL)
return NULL;
+ INIT_LIST_HEAD(&clp->cl_sessions);
+
princ = svc_gss_principal(rqstp);
if (princ) {
clp->cl_principal = kstrdup(princ, GFP_KERNEL);
INIT_LIST_HEAD(&clp->cl_strhash);
INIT_LIST_HEAD(&clp->cl_openowners);
INIT_LIST_HEAD(&clp->cl_delegations);
- INIT_LIST_HEAD(&clp->cl_sessions);
INIT_LIST_HEAD(&clp->cl_lru);
+ spin_lock_init(&clp->cl_lock);
+ INIT_WORK(&clp->cl_cb_null.cb_work, nfsd4_do_callback_rpc);
clp->cl_time = get_seconds();
clear_bit(0, &clp->cl_cb_slot_busy);
rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
clp->cl_flavor = rqstp->rq_flavor;
copy_cred(&clp->cl_cred, &rqstp->rq_cred);
gen_confirm(clp);
-
+ clp->cl_cb_session = NULL;
return clp;
}
static void
gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid)
{
- struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
+ struct nfs4_cb_conn *conn = &clp->cl_cb_conn;
unsigned short expected_family;
/* Currently, we only support tcp and tcp6 for the callback channel */
else
goto out_err;
- cb->cb_addrlen = rpc_uaddr2sockaddr(se->se_callback_addr_val,
+ conn->cb_addrlen = rpc_uaddr2sockaddr(se->se_callback_addr_val,
se->se_callback_addr_len,
- (struct sockaddr *) &cb->cb_addr,
- sizeof(cb->cb_addr));
+ (struct sockaddr *)&conn->cb_addr,
+ sizeof(conn->cb_addr));
- if (!cb->cb_addrlen || cb->cb_addr.ss_family != expected_family)
+ if (!conn->cb_addrlen || conn->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;
+ if (conn->cb_addr.ss_family == AF_INET6)
+ ((struct sockaddr_in6 *)&conn->cb_addr)->sin6_scope_id = scopeid;
- cb->cb_minorversion = 0;
- cb->cb_prog = se->se_callback_prog;
- cb->cb_ident = se->se_callback_ident;
+ conn->cb_prog = se->se_callback_prog;
+ conn->cb_ident = se->se_callback_ident;
return;
out_err:
- cb->cb_addr.ss_family = AF_UNSPEC;
- cb->cb_addrlen = 0;
+ conn->cb_addr.ss_family = AF_UNSPEC;
+ conn->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);
{
struct sockaddr *sa = svc_addr(rqstp);
struct nfs4_client *conf, *unconf;
+ struct nfsd4_session *new;
struct nfsd4_clid_slot *cs_slot = NULL;
+ bool confirm_me = false;
int status = 0;
nfs4_lock_state();
cs_slot->sl_seqid, cr_ses->seqid);
goto out;
}
- cs_slot->sl_seqid++;
} else if (unconf) {
if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) ||
!rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) {
if (status) {
/* an unconfirmed replay returns misordered */
status = nfserr_seq_misordered;
- goto out_cache;
+ goto out;
}
- cs_slot->sl_seqid++; /* from 0 to 1 */
- move_to_confirmed(unconf);
-
- if (cr_ses->flags & SESSION4_BACK_CHAN) {
- unconf->cl_cb_conn.cb_xprt = rqstp->rq_xprt;
- svc_xprt_get(rqstp->rq_xprt);
- rpc_copy_addr(
- (struct sockaddr *)&unconf->cl_cb_conn.cb_addr,
- sa);
- unconf->cl_cb_conn.cb_addrlen = svc_addr_len(sa);
- unconf->cl_cb_conn.cb_minorversion =
- cstate->minorversion;
- unconf->cl_cb_conn.cb_prog = cr_ses->callback_prog;
- unconf->cl_cb_seq_nr = 1;
- nfsd4_probe_callback(unconf, &unconf->cl_cb_conn);
- }
+ confirm_me = true;
conf = unconf;
} else {
status = nfserr_stale_clientid;
goto out;
}
+ /*
+ * XXX: we should probably set this at creation time, and check
+ * for consistent minorversion use throughout:
+ */
+ conf->cl_minorversion = 1;
/*
* We do not support RDMA or persistent sessions
*/
cr_ses->flags &= ~SESSION4_PERSIST;
cr_ses->flags &= ~SESSION4_RDMA;
- status = alloc_init_session(rqstp, conf, cr_ses);
- if (status)
+ status = nfserr_jukebox;
+ new = alloc_init_session(rqstp, conf, cr_ses);
+ if (!new)
goto out;
-
- memcpy(cr_ses->sessionid.data, conf->cl_sessionid.data,
+ status = nfs_ok;
+ memcpy(cr_ses->sessionid.data, new->se_sessionid.data,
NFS4_MAX_SESSIONID_LEN);
+ cs_slot->sl_seqid++;
cr_ses->seqid = cs_slot->sl_seqid;
- out_cache:
/* cache solo and embedded create sessions under the state lock */
nfsd4_cache_create_session(cr_ses, cs_slot, status);
+ if (confirm_me)
+ move_to_confirmed(conf);
out:
nfs4_unlock_state();
dprintk("%s returns %d\n", __func__, ntohl(status));
nfs4_lock_state();
/* wait for callbacks */
- nfsd4_set_callback_client(ses->se_client, NULL);
+ nfsd4_shutdown_callback(ses->se_client);
nfs4_unlock_state();
+
+ nfsd4_del_conns(ses);
+
nfsd4_put_session(ses);
status = nfs_ok;
out:
return status;
}
+ static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_session *s)
+ {
+ struct nfsd4_conn *c;
+
+ list_for_each_entry(c, &s->se_conns, cn_persession) {
+ if (c->cn_xprt == xpt) {
+ return c;
+ }
+ }
+ return NULL;
+ }
+
+ static void nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_session *ses)
+ {
+ struct nfs4_client *clp = ses->se_client;
+ struct nfsd4_conn *c;
+
+ spin_lock(&clp->cl_lock);
+ c = __nfsd4_find_conn(new->cn_xprt, ses);
+ if (c) {
+ spin_unlock(&clp->cl_lock);
+ free_conn(new);
+ return;
+ }
+ __nfsd4_hash_conn(new, ses);
+ spin_unlock(&clp->cl_lock);
+ nfsd4_register_conn(new);
+ return;
+ }
+
__be32
nfsd4_sequence(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
struct nfsd4_compoundres *resp = rqstp->rq_resp;
struct nfsd4_session *session;
struct nfsd4_slot *slot;
+ struct nfsd4_conn *conn;
int status;
if (resp->opcnt != 1)
return nfserr_sequence_pos;
+ /*
+ * Will be either used or freed by nfsd4_sequence_check_conn
+ * below.
+ */
+ conn = alloc_conn(rqstp, NFS4_CDFC4_FORE);
+ if (!conn)
+ return nfserr_jukebox;
+
spin_lock(&client_lock);
status = nfserr_badsession;
session = find_in_sessionid_hashtbl(&seq->sessionid);
if (status)
goto out;
+ nfsd4_sequence_check_conn(conn, session);
+ conn = NULL;
+
/* Success! bump slot seqid */
slot->sl_inuse = true;
slot->sl_seqid = seq->seqid;
nfsd4_get_session(cstate->session);
atomic_inc(&session->se_client->cl_refcount);
}
+ kfree(conn);
spin_unlock(&client_lock);
dprintk("%s: return %d\n", __func__, ntohl(status));
return status;
goto out;
gen_clid(new);
}
+ /*
+ * XXX: we should probably set this at creation time, and check
+ * for consistent minorversion use throughout:
+ */
+ new->cl_minorversion = 0;
gen_callback(new, setclid, rpc_get_scope_id(sa));
add_to_unconfirmed(new, strhashval);
setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot;
status = nfserr_clid_inuse;
else {
atomic_set(&conf->cl_cb_set, 0);
- nfsd4_probe_callback(conf, &unconf->cl_cb_conn);
+ nfsd4_change_callback(conf, &unconf->cl_cb_conn);
+ nfsd4_probe_callback(conf);
expire_client(unconf);
status = nfs_ok;
}
move_to_confirmed(unconf);
conf = unconf;
- nfsd4_probe_callback(conf, &conf->cl_cb_conn);
+ nfsd4_probe_callback(conf);
status = nfs_ok;
}
} else if ((!conf || (conf && !same_verf(&conf->cl_confirm, &confirm)))
if (STALE_STATEID(stateid))
goto out;
- status = nfserr_bad_stateid;
+ /*
+ * We assume that any stateid that has the current boot time,
+ * but that we can't find, is expired:
+ */
+ status = nfserr_expired;
if (is_delegation_stateid(stateid)) {
dp = find_delegation_stateid(ino, stateid);
if (!dp)
stp = find_stateid(stateid, flags);
if (!stp)
goto out;
+ status = nfserr_bad_stateid;
if (nfs4_check_fh(current_fh, stp))
goto out;
if (!stp->st_stateowner->so_confirmed)
* a replayed close:
*/
sop = search_close_lru(stateid->si_stateownerid, flags);
+ /* It's not stale; let's assume it's expired: */
if (sop == NULL)
- return nfserr_bad_stateid;
+ return nfserr_expired;
*sopp = sop;
goto check_replay;
}
status = nfserr_bad_stateid;
if (!is_delegation_stateid(stateid))
goto out;
+ status = nfserr_expired;
dp = find_delegation_stateid(inode, stateid);
if (!dp)
goto out;
struct inode *inode = filp->fi_inode;
int status = 0;
- lock_kernel();
+ lock_flocks();
for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) {
if ((*flpp)->fl_owner == (fl_owner_t)lowner) {
status = 1;
}
}
out:
- unlock_kernel();
+ unlock_flocks();
return status;
}
*/
enum {
NFSD_Root = 1,
+ #ifdef CONFIG_NFSD_DEPRECATED
NFSD_Svc,
NFSD_Add,
NFSD_Del,
NFSD_Unexport,
NFSD_Getfd,
NFSD_Getfs,
+ #endif
NFSD_List,
NFSD_Export_features,
NFSD_Fh,
/*
* write() for these nodes.
*/
+ #ifdef CONFIG_NFSD_DEPRECATED
static ssize_t write_svc(struct file *file, char *buf, size_t size);
static ssize_t write_add(struct file *file, char *buf, size_t size);
static ssize_t write_del(struct file *file, char *buf, size_t size);
static ssize_t write_unexport(struct file *file, char *buf, size_t size);
static ssize_t write_getfd(struct file *file, char *buf, size_t size);
static ssize_t write_getfs(struct file *file, char *buf, size_t size);
+ #endif
static ssize_t write_filehandle(struct file *file, char *buf, size_t size);
static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size);
static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size);
#endif
static ssize_t (*write_op[])(struct file *, char *, size_t) = {
+ #ifdef CONFIG_NFSD_DEPRECATED
[NFSD_Svc] = write_svc,
[NFSD_Add] = write_add,
[NFSD_Del] = write_del,
[NFSD_Unexport] = write_unexport,
[NFSD_Getfd] = write_getfd,
[NFSD_Getfs] = write_getfs,
+ #endif
[NFSD_Fh] = write_filehandle,
[NFSD_FO_UnlockIP] = write_unlock_ip,
[NFSD_FO_UnlockFS] = write_unlock_fs,
static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos)
{
+ static int warned;
+ if (file->f_dentry->d_name.name[0] == '.' && !warned) {
+ printk(KERN_INFO
+ "Warning: \"%s\" uses deprecated NFSD interface: %s."
+ " This will be removed in 2.6.40\n",
+ current->comm, file->f_dentry->d_name.name);
+ warned = 1;
+ }
if (! file->private_data) {
/* An attempt to read a transaction file without writing
* causes a 0-byte write so that the file can return
.write = nfsctl_transaction_write,
.read = nfsctl_transaction_read,
.release = simple_transaction_release,
+ .llseek = default_llseek,
};
static int exports_open(struct inode *inode, struct file *file)
* payload - write methods
*/
+ #ifdef CONFIG_NFSD_DEPRECATED
/**
* write_svc - Start kernel's NFSD server
*
ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6);
- clp = auth_unix_lookup(&in6);
+ clp = auth_unix_lookup(&init_net, &in6);
if (!clp)
err = -EPERM;
else {
ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6);
- clp = auth_unix_lookup(&in6);
+ clp = auth_unix_lookup(&init_net, &in6);
if (!clp)
err = -EPERM;
else {
out:
return err;
}
+ #endif /* CONFIG_NFSD_DEPRECATED */
/**
* write_unlock_ip - Release all locks used by a client
if (err != 0)
return err;
- err = svc_create_xprt(nfsd_serv, transport,
+ err = svc_create_xprt(nfsd_serv, transport, &init_net,
PF_INET, port, SVC_SOCK_ANONYMOUS);
if (err < 0)
goto out_err;
- err = svc_create_xprt(nfsd_serv, transport,
+ err = svc_create_xprt(nfsd_serv, transport, &init_net,
PF_INET6, port, SVC_SOCK_ANONYMOUS);
if (err < 0 && err != -EAFNOSUPPORT)
goto out_close;
static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
{
static struct tree_descr nfsd_files[] = {
+ #ifdef CONFIG_NFSD_DEPRECATED
[NFSD_Svc] = {".svc", &transaction_ops, S_IWUSR},
[NFSD_Add] = {".add", &transaction_ops, S_IWUSR},
[NFSD_Del] = {".del", &transaction_ops, S_IWUSR},
[NFSD_Unexport] = {".unexport", &transaction_ops, S_IWUSR},
[NFSD_Getfd] = {".getfd", &transaction_ops, S_IWUSR|S_IRUSR},
[NFSD_Getfs] = {".getfs", &transaction_ops, S_IWUSR|S_IRUSR},
+ #endif
[NFSD_List] = {"exports", &exports_operations, S_IRUGO},
[NFSD_Export_features] = {"export_features",
&export_features_operations, S_IRUGO},
#define NFS4_BITMAP_SIZE 2
#define NFS4_VERIFIER_SIZE 8
-#define NFS4_STATEID_SIZE 16
+#define NFS4_STATEID_SEQID_SIZE 4
+#define NFS4_STATEID_OTHER_SIZE 12
+#define NFS4_STATEID_SIZE (NFS4_STATEID_SEQID_SIZE + NFS4_STATEID_OTHER_SIZE)
#define NFS4_FHSIZE 128
#define NFS4_MAXPATHLEN PATH_MAX
#define NFS4_MAXNAMLEN NAME_MAX
#define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL 0x10000
#define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED 0x20000
+ #define NFS4_CDFC4_FORE 0x1
+ #define NFS4_CDFC4_BACK 0x2
+
#define NFS4_SET_TO_SERVER_TIME 0
#define NFS4_SET_TO_CLIENT_TIME 1
};
typedef struct { char data[NFS4_VERIFIER_SIZE]; } nfs4_verifier;
-typedef struct { char data[NFS4_STATEID_SIZE]; } nfs4_stateid;
+
+struct nfs41_stateid {
+ __be32 seqid;
+ char other[NFS4_STATEID_OTHER_SIZE];
+} __attribute__ ((packed));
+
+typedef union {
+ char data[NFS4_STATEID_SIZE];
+ struct nfs41_stateid stateid;
+} nfs4_stateid;
enum nfs_opnum4 {
OP_ACCESS = 3,
#define FATTR4_WORD1_TIME_MODIFY (1UL << 21)
#define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22)
#define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23)
+#define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30)
+#define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1)
#define NFSPROC4_NULL 0
#define NFSPROC4_COMPOUND 1
NFSPROC4_CLNT_SEQUENCE,
NFSPROC4_CLNT_GET_LEASE_TIME,
NFSPROC4_CLNT_RECLAIM_COMPLETE,
+ NFSPROC4_CLNT_LAYOUTGET,
+ NFSPROC4_CLNT_GETDEVICEINFO,
};
/* nfs41 types */
SP4_SSV = 2
};
+enum pnfs_layouttype {
+ LAYOUT_NFSV4_1_FILES = 1,
+ LAYOUT_OSD2_OBJECTS = 2,
+ LAYOUT_BLOCK_VOLUME = 3,
+};
+
+/* used for both layout return and recall */
+enum pnfs_layoutreturn_type {
+ RETURN_FILE = 1,
+ RETURN_FSID = 2,
+ RETURN_ALL = 3
+};
+
+enum pnfs_iomode {
+ IOMODE_READ = 1,
+ IOMODE_RW = 2,
+ IOMODE_ANY = 3,
+};
+
+enum pnfs_notify_deviceid_type4 {
+ NOTIFY_DEVICEID4_CHANGE = 1 << 1,
+ NOTIFY_DEVICEID4_DELETE = 1 << 2,
+};
+
+#define NFL4_UFLG_MASK 0x0000003F
+#define NFL4_UFLG_DENSE 0x00000001
+#define NFL4_UFLG_COMMIT_THRU_MDS 0x00000002
+#define NFL4_UFLG_STRIPE_UNIT_SIZE_MASK 0xFFFFFFC0
+
+/* Encoded in the loh_body field of type layouthint4 */
+enum filelayout_hint_care4 {
+ NFLH4_CARE_DENSE = NFL4_UFLG_DENSE,
+ NFLH4_CARE_COMMIT_THRU_MDS = NFL4_UFLG_COMMIT_THRU_MDS,
+ NFLH4_CARE_STRIPE_UNIT_SIZE = 0x00000040,
+ NFLH4_CARE_STRIPE_COUNT = 0x00000080
+};
+
+#define NFS4_DEVICEID4_SIZE 16
+
+struct nfs4_deviceid {
+ char data[NFS4_DEVICEID4_SIZE];
+};
+
#endif
#endif
#ifdef __KERNEL__
struct rpc_create_args {
+ struct net *net;
int protocol;
struct sockaddr *address;
size_t addrsize;
int rpcb_v4_register(const u32 program, const u32 version,
const struct sockaddr *address,
const char *netid);
-int rpcb_getport_sync(struct sockaddr_in *, u32, u32, int);
void rpcb_getport_async(struct rpc_task *);
void rpc_call_start(struct rpc_task *);
* specified. Zero is returned for a success.
*/
-int move_addr_to_user(struct sockaddr *kaddr, int klen, void __user *uaddr,
- int __user *ulen)
+static int move_addr_to_user(struct sockaddr *kaddr, int klen,
+ void __user *uaddr, int __user *ulen)
{
int err;
int len;
const struct file_operations bad_sock_fops = {
.owner = THIS_MODULE,
.open = sock_no_open,
+ .llseek = noop_llseek,
};
/**
}
EXPORT_SYMBOL(sock_release);
-int sock_tx_timestamp(struct msghdr *msg, struct sock *sk,
- union skb_shared_tx *shtx)
+int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags)
{
- shtx->flags = 0;
+ *tx_flags = 0;
if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE))
- shtx->hardware = 1;
+ *tx_flags |= SKBTX_HW_TSTAMP;
if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE))
- shtx->software = 1;
+ *tx_flags |= SKBTX_SW_TSTAMP;
return 0;
}
EXPORT_SYMBOL(sock_tx_timestamp);
}
EXPORT_SYMBOL_GPL(__sock_recv_timestamp);
-inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
+static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb)
{
if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount)
put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL,
}
EXPORT_SYMBOL(sock_wake_async);
- static int __sock_create(struct net *net, int family, int type, int protocol,
+ int __sock_create(struct net *net, int family, int type, int protocol,
struct socket **res, int kern)
{
int err;
rcu_read_unlock();
goto out_sock_release;
}
+ EXPORT_SYMBOL(__sock_create);
int sock_create(int family, int type, int protocol, struct socket **res)
{
* Afterwards, it will be a kernel pointer. Thus the compiler-assisted
* checking falls down on this.
*/
- if (copy_from_user(ctl_buf, (void __user *)msg_sys.msg_control,
+ if (copy_from_user(ctl_buf,
+ (void __user __force *)msg_sys.msg_control,
ctl_len))
goto out_freectl;
msg_sys.msg_control = ctl_buf;
char *optval, int *optlen)
{
mm_segment_t oldfs = get_fs();
+ char __user *uoptval;
+ int __user *uoptlen;
int err;
+ uoptval = (char __user __force *) optval;
+ uoptlen = (int __user __force *) optlen;
+
set_fs(KERNEL_DS);
if (level == SOL_SOCKET)
- err = sock_getsockopt(sock, level, optname, optval, optlen);
+ err = sock_getsockopt(sock, level, optname, uoptval, uoptlen);
else
- err = sock->ops->getsockopt(sock, level, optname, optval,
- optlen);
+ err = sock->ops->getsockopt(sock, level, optname, uoptval,
+ uoptlen);
set_fs(oldfs);
return err;
}
char *optval, unsigned int optlen)
{
mm_segment_t oldfs = get_fs();
+ char __user *uoptval;
int err;
+ uoptval = (char __user __force *) optval;
+
set_fs(KERNEL_DS);
if (level == SOL_SOCKET)
- err = sock_setsockopt(sock, level, optname, optval, optlen);
+ err = sock_setsockopt(sock, level, optname, uoptval, optlen);
else
- err = sock->ops->setsockopt(sock, level, optname, optval,
+ err = sock->ops->setsockopt(sock, level, optname, uoptval,
optlen);
set_fs(oldfs);
return err;
int
rpcauth_refreshcred(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_rqstp->rq_cred;
+ struct rpc_cred *cred;
int err;
cred = task->tk_rqstp->rq_cred;
return err;
}
- void __exit rpcauth_remove_module(void)
+ void rpcauth_remove_module(void)
{
rpc_destroy_authunix();
rpc_destroy_generic_auth();
#include <linux/workqueue.h>
#include <linux/mutex.h>
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
#include <asm/ioctls.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
+ #include "netns.h"
#define RPCDBG_FACILITY RPCDBG_CACHE
- static int cache_defer_req(struct cache_req *req, struct cache_head *item);
+ static void cache_defer_req(struct cache_req *req, struct cache_head *item);
static void cache_revisit_request(struct cache_head *item);
static void cache_init(struct cache_head *h)
{
- time_t now = get_seconds();
+ time_t now = seconds_since_boot();
h->next = NULL;
h->flags = 0;
kref_init(&h->ref);
static inline int cache_is_expired(struct cache_detail *detail, struct cache_head *h)
{
- return (h->expiry_time < get_seconds()) ||
+ return (h->expiry_time < seconds_since_boot()) ||
(detail->flush_time > h->last_refresh);
}
static void cache_fresh_locked(struct cache_head *head, time_t expiry)
{
head->expiry_time = expiry;
- head->last_refresh = get_seconds();
+ head->last_refresh = seconds_since_boot();
set_bit(CACHE_VALID, &head->flags);
}
/* now see if we want to start an upcall */
refresh_age = (h->expiry_time - h->last_refresh);
- age = get_seconds() - h->last_refresh;
+ age = seconds_since_boot() - h->last_refresh;
if (rqstp == NULL) {
if (rv == -EAGAIN)
cache_revisit_request(h);
if (rv == -EAGAIN) {
set_bit(CACHE_NEGATIVE, &h->flags);
- cache_fresh_locked(h, get_seconds()+CACHE_NEW_EXPIRY);
+ cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY);
cache_fresh_unlocked(h, detail);
rv = -ENOENT;
}
}
if (rv == -EAGAIN) {
- if (cache_defer_req(rqstp, h) < 0) {
+ cache_defer_req(rqstp, h);
+ if (!test_bit(CACHE_PENDING, &h->flags)) {
/* Request is not deferred */
rv = cache_is_valid(detail, h);
if (rv == -EAGAIN)
return -1;
}
current_detail = list_entry(next, struct cache_detail, others);
- if (current_detail->nextcheck > get_seconds())
+ if (current_detail->nextcheck > seconds_since_boot())
current_index = current_detail->hash_size;
else {
current_index = 0;
- current_detail->nextcheck = get_seconds()+30*60;
+ current_detail->nextcheck = seconds_since_boot()+30*60;
}
}
void cache_purge(struct cache_detail *detail)
{
detail->flush_time = LONG_MAX;
- detail->nextcheck = get_seconds();
+ detail->nextcheck = seconds_since_boot();
cache_flush();
detail->flush_time = 1;
}
static DEFINE_SPINLOCK(cache_defer_lock);
static LIST_HEAD(cache_defer_list);
- static struct list_head cache_defer_hash[DFR_HASHSIZE];
+ static struct hlist_head cache_defer_hash[DFR_HASHSIZE];
static int cache_defer_cnt;
- static int cache_defer_req(struct cache_req *req, struct cache_head *item)
+ static void __unhash_deferred_req(struct cache_deferred_req *dreq)
+ {
+ hlist_del_init(&dreq->hash);
+ if (!list_empty(&dreq->recent)) {
+ list_del_init(&dreq->recent);
+ cache_defer_cnt--;
+ }
+ }
+
+ static void __hash_deferred_req(struct cache_deferred_req *dreq, struct cache_head *item)
{
- struct cache_deferred_req *dreq, *discard;
int hash = DFR_HASH(item);
- if (cache_defer_cnt >= DFR_MAX) {
- /* too much in the cache, randomly drop this one,
- * or continue and drop the oldest below
- */
- if (net_random()&1)
- return -ENOMEM;
- }
- dreq = req->defer(req);
- if (dreq == NULL)
- return -ENOMEM;
+ INIT_LIST_HEAD(&dreq->recent);
+ hlist_add_head(&dreq->hash, &cache_defer_hash[hash]);
+ }
+
+ static void setup_deferral(struct cache_deferred_req *dreq,
+ struct cache_head *item,
+ int count_me)
+ {
dreq->item = item;
spin_lock(&cache_defer_lock);
- list_add(&dreq->recent, &cache_defer_list);
-
- if (cache_defer_hash[hash].next == NULL)
- INIT_LIST_HEAD(&cache_defer_hash[hash]);
- list_add(&dreq->hash, &cache_defer_hash[hash]);
+ __hash_deferred_req(dreq, item);
- /* it is in, now maybe clean up */
- discard = NULL;
- if (++cache_defer_cnt > DFR_MAX) {
- discard = list_entry(cache_defer_list.prev,
- struct cache_deferred_req, recent);
- list_del_init(&discard->recent);
- list_del_init(&discard->hash);
- cache_defer_cnt--;
+ if (count_me) {
+ cache_defer_cnt++;
+ list_add(&dreq->recent, &cache_defer_list);
}
+
spin_unlock(&cache_defer_lock);
+ }
+
+ struct thread_deferred_req {
+ struct cache_deferred_req handle;
+ struct completion completion;
+ };
+
+ static void cache_restart_thread(struct cache_deferred_req *dreq, int too_many)
+ {
+ struct thread_deferred_req *dr =
+ container_of(dreq, struct thread_deferred_req, handle);
+ complete(&dr->completion);
+ }
+
+ static void cache_wait_req(struct cache_req *req, struct cache_head *item)
+ {
+ struct thread_deferred_req sleeper;
+ struct cache_deferred_req *dreq = &sleeper.handle;
+
+ sleeper.completion = COMPLETION_INITIALIZER_ONSTACK(sleeper.completion);
+ dreq->revisit = cache_restart_thread;
+
+ setup_deferral(dreq, item, 0);
+
+ if (!test_bit(CACHE_PENDING, &item->flags) ||
+ wait_for_completion_interruptible_timeout(
+ &sleeper.completion, req->thread_wait) <= 0) {
+ /* The completion wasn't completed, so we need
+ * to clean up
+ */
+ spin_lock(&cache_defer_lock);
+ if (!hlist_unhashed(&sleeper.handle.hash)) {
+ __unhash_deferred_req(&sleeper.handle);
+ spin_unlock(&cache_defer_lock);
+ } else {
+ /* cache_revisit_request already removed
+ * this from the hash table, but hasn't
+ * called ->revisit yet. It will very soon
+ * and we need to wait for it.
+ */
+ spin_unlock(&cache_defer_lock);
+ wait_for_completion(&sleeper.completion);
+ }
+ }
+ }
+
+ static void cache_limit_defers(void)
+ {
+ /* Make sure we haven't exceed the limit of allowed deferred
+ * requests.
+ */
+ struct cache_deferred_req *discard = NULL;
+
+ if (cache_defer_cnt <= DFR_MAX)
+ return;
+
+ spin_lock(&cache_defer_lock);
+
+ /* Consider removing either the first or the last */
+ if (cache_defer_cnt > DFR_MAX) {
+ if (net_random() & 1)
+ discard = list_entry(cache_defer_list.next,
+ struct cache_deferred_req, recent);
+ else
+ discard = list_entry(cache_defer_list.prev,
+ struct cache_deferred_req, recent);
+ __unhash_deferred_req(discard);
+ }
+ spin_unlock(&cache_defer_lock);
if (discard)
- /* there was one too many */
discard->revisit(discard, 1);
+ }
- if (!test_bit(CACHE_PENDING, &item->flags)) {
- /* must have just been validated... */
- cache_revisit_request(item);
- return -EAGAIN;
+ static void cache_defer_req(struct cache_req *req, struct cache_head *item)
+ {
+ struct cache_deferred_req *dreq;
+
+ if (req->thread_wait) {
+ cache_wait_req(req, item);
+ if (!test_bit(CACHE_PENDING, &item->flags))
+ return;
}
- return 0;
+ dreq = req->defer(req);
+ if (dreq == NULL)
+ return;
+ setup_deferral(dreq, item, 1);
+ if (!test_bit(CACHE_PENDING, &item->flags))
+ /* Bit could have been cleared before we managed to
+ * set up the deferral, so need to revisit just in case
+ */
+ cache_revisit_request(item);
+
+ cache_limit_defers();
}
static void cache_revisit_request(struct cache_head *item)
{
struct cache_deferred_req *dreq;
struct list_head pending;
-
- struct list_head *lp;
+ struct hlist_node *lp, *tmp;
int hash = DFR_HASH(item);
INIT_LIST_HEAD(&pending);
spin_lock(&cache_defer_lock);
- lp = cache_defer_hash[hash].next;
- if (lp) {
- while (lp != &cache_defer_hash[hash]) {
- dreq = list_entry(lp, struct cache_deferred_req, hash);
- lp = lp->next;
- if (dreq->item == item) {
- list_del_init(&dreq->hash);
- list_move(&dreq->recent, &pending);
- cache_defer_cnt--;
- }
+ hlist_for_each_entry_safe(dreq, lp, tmp, &cache_defer_hash[hash], hash)
+ if (dreq->item == item) {
+ __unhash_deferred_req(dreq);
+ list_add(&dreq->recent, &pending);
}
- }
+
spin_unlock(&cache_defer_lock);
while (!list_empty(&pending)) {
list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) {
if (dreq->owner == owner) {
- list_del_init(&dreq->hash);
- list_move(&dreq->recent, &pending);
- cache_defer_cnt--;
+ __unhash_deferred_req(dreq);
+ list_add(&dreq->recent, &pending);
}
}
spin_unlock(&cache_defer_lock);
filp->private_data = NULL;
kfree(rp);
- cd->last_close = get_seconds();
+ cd->last_close = seconds_since_boot();
atomic_dec(&cd->readers);
}
module_put(cd->owner);
}
}
+ static bool cache_listeners_exist(struct cache_detail *detail)
+ {
+ if (atomic_read(&detail->readers))
+ return true;
+ if (detail->last_close == 0)
+ /* This cache was never opened */
+ return false;
+ if (detail->last_close < seconds_since_boot() - 30)
+ /*
+ * We allow for the possibility that someone might
+ * restart a userspace daemon without restarting the
+ * server; but after 30 seconds, we give up.
+ */
+ return false;
+ return true;
+ }
+
/*
* register an upcall request to user-space and queue it up for read() by the
* upcall daemon.
char *bp;
int len;
- if (atomic_read(&detail->readers) == 0 &&
- detail->last_close < get_seconds() - 30) {
- warn_no_listener(detail);
- return -EINVAL;
+ if (!cache_listeners_exist(detail)) {
+ warn_no_listener(detail);
+ return -EINVAL;
}
buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (bp[0] == '\\' && bp[1] == 'x') {
/* HEX STRING */
bp += 2;
- while (isxdigit(bp[0]) && isxdigit(bp[1]) && len < bufsize) {
- int byte = isdigit(*bp) ? *bp-'0' : toupper(*bp)-'A'+10;
- bp++;
- byte <<= 4;
- byte |= isdigit(*bp) ? *bp-'0' : toupper(*bp)-'A'+10;
- *dest++ = byte;
- bp++;
+ while (len < bufsize) {
+ int h, l;
+
+ h = hex_to_bin(bp[0]);
+ if (h < 0)
+ break;
+
+ l = hex_to_bin(bp[1]);
+ if (l < 0)
+ break;
+
+ *dest++ = (h << 4) | l;
+ bp += 2;
len++;
}
} else {
ifdebug(CACHE)
seq_printf(m, "# expiry=%ld refcnt=%d flags=%lx\n",
- cp->expiry_time, atomic_read(&cp->ref.refcount), cp->flags);
+ convert_to_wallclock(cp->expiry_time),
+ atomic_read(&cp->ref.refcount), cp->flags);
cache_get(cp);
if (cache_check(cd, cp, NULL))
/* cache_check does a cache_put on failure */
unsigned long p = *ppos;
size_t len;
- sprintf(tbuf, "%lu\n", cd->flush_time);
+ sprintf(tbuf, "%lu\n", convert_to_wallclock(cd->flush_time));
len = strlen(tbuf);
if (p >= len)
return 0;
struct cache_detail *cd)
{
char tbuf[20];
- char *ep;
- long flushtime;
+ char *bp, *ep;
+
if (*ppos || count > sizeof(tbuf)-1)
return -EINVAL;
if (copy_from_user(tbuf, buf, count))
return -EFAULT;
tbuf[count] = 0;
- flushtime = simple_strtoul(tbuf, &ep, 0);
+ simple_strtoul(tbuf, &ep, 0);
if (*ep && *ep != '\n')
return -EINVAL;
- cd->flush_time = flushtime;
- cd->nextcheck = get_seconds();
+ bp = tbuf;
+ cd->flush_time = get_expiry(&bp);
+ cd->nextcheck = seconds_since_boot();
cache_flush();
*ppos += count;
static long cache_ioctl_procfs(struct file *filp,
unsigned int cmd, unsigned long arg)
{
- long ret;
struct inode *inode = filp->f_path.dentry->d_inode;
struct cache_detail *cd = PDE(inode)->data;
- lock_kernel();
- ret = cache_ioctl(inode, filp, cmd, arg, cd);
- unlock_kernel();
-
- return ret;
+ return cache_ioctl(inode, filp, cmd, arg, cd);
}
static int cache_open_procfs(struct inode *inode, struct file *filp)
.read = read_flush_procfs,
.write = write_flush_procfs,
.release = release_flush_procfs,
+ .llseek = no_llseek,
};
- static void remove_cache_proc_entries(struct cache_detail *cd)
+ static void remove_cache_proc_entries(struct cache_detail *cd, struct net *net)
{
+ struct sunrpc_net *sn;
+
if (cd->u.procfs.proc_ent == NULL)
return;
if (cd->u.procfs.flush_ent)
if (cd->u.procfs.content_ent)
remove_proc_entry("content", cd->u.procfs.proc_ent);
cd->u.procfs.proc_ent = NULL;
- remove_proc_entry(cd->name, proc_net_rpc);
+ sn = net_generic(net, sunrpc_net_id);
+ remove_proc_entry(cd->name, sn->proc_net_rpc);
}
#ifdef CONFIG_PROC_FS
- static int create_cache_proc_entries(struct cache_detail *cd)
+ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
{
struct proc_dir_entry *p;
+ struct sunrpc_net *sn;
- cd->u.procfs.proc_ent = proc_mkdir(cd->name, proc_net_rpc);
+ sn = net_generic(net, sunrpc_net_id);
+ cd->u.procfs.proc_ent = proc_mkdir(cd->name, sn->proc_net_rpc);
if (cd->u.procfs.proc_ent == NULL)
goto out_nomem;
cd->u.procfs.channel_ent = NULL;
}
return 0;
out_nomem:
- remove_cache_proc_entries(cd);
+ remove_cache_proc_entries(cd, net);
return -ENOMEM;
}
#else /* CONFIG_PROC_FS */
- static int create_cache_proc_entries(struct cache_detail *cd)
+ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
{
return 0;
}
INIT_DELAYED_WORK_DEFERRABLE(&cache_cleaner, do_cache_clean);
}
- int cache_register(struct cache_detail *cd)
+ int cache_register_net(struct cache_detail *cd, struct net *net)
{
int ret;
sunrpc_init_cache_detail(cd);
- ret = create_cache_proc_entries(cd);
+ ret = create_cache_proc_entries(cd, net);
if (ret)
sunrpc_destroy_cache_detail(cd);
return ret;
}
+
+ int cache_register(struct cache_detail *cd)
+ {
+ return cache_register_net(cd, &init_net);
+ }
EXPORT_SYMBOL_GPL(cache_register);
- void cache_unregister(struct cache_detail *cd)
+ void cache_unregister_net(struct cache_detail *cd, struct net *net)
{
- remove_cache_proc_entries(cd);
+ remove_cache_proc_entries(cd, net);
sunrpc_destroy_cache_detail(cd);
}
+
+ void cache_unregister(struct cache_detail *cd)
+ {
+ cache_unregister_net(cd, &init_net);
+ }
EXPORT_SYMBOL_GPL(cache_unregister);
static ssize_t cache_read_pipefs(struct file *filp, char __user *buf,
{
struct inode *inode = filp->f_dentry->d_inode;
struct cache_detail *cd = RPC_I(inode)->private;
- long ret;
- lock_kernel();
- ret = cache_ioctl(inode, filp, cmd, arg, cd);
- unlock_kernel();
-
- return ret;
+ return cache_ioctl(inode, filp, cmd, arg, cd);
}
static int cache_open_pipefs(struct inode *inode, struct file *filp)
.read = read_flush_pipefs,
.write = write_flush_pipefs,
.release = release_flush_pipefs,
+ .llseek = no_llseek,
};
int sunrpc_cache_register_pipefs(struct dentry *parent,
struct rpc_xprt *xprt;
struct rpc_clnt *clnt;
struct xprt_create xprtargs = {
+ .net = args->net,
.ident = args->protocol,
.srcaddr = args->saddress,
.dstaddr = args->address,
rpcauth_invalcred(task);
/* Ensure we obtain a new XID! */
xprt_release(task);
- task->tk_action = call_refresh;
+ task->tk_action = call_reserve;
goto out_retry;
case RPC_AUTH_BADCRED:
case RPC_AUTH_BADVERF:
static int rpcb_create_local(void)
{
struct rpc_create_args args = {
+ .net = &init_net,
.protocol = XPRT_TRANSPORT_TCP,
.address = (struct sockaddr *)&rpcb_inaddr_loopback,
.addrsize = sizeof(rpcb_inaddr_loopback),
*/
clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4);
if (IS_ERR(clnt4)) {
- dprintk("RPC: failed to create local rpcbind v4 "
- "cleint (errno %ld).\n", PTR_ERR(clnt4));
+ dprintk("RPC: failed to bind second program to "
+ "rpcbind v4 client (errno %ld).\n",
+ PTR_ERR(clnt4));
clnt4 = NULL;
}
size_t salen, int proto, u32 version)
{
struct rpc_create_args args = {
+ .net = &init_net,
.protocol = proto,
.address = srvaddr,
.addrsize = salen,
((struct sockaddr_in6 *)srvaddr)->sin6_port = htons(RPCBIND_PORT);
break;
default:
- return NULL;
+ return ERR_PTR(-EAFNOSUPPORT);
}
return rpc_create(&args);
return -EAFNOSUPPORT;
}
-/**
- * rpcb_getport_sync - obtain the port for an RPC service on a given host
- * @sin: address of remote peer
- * @prog: RPC program number to bind
- * @vers: RPC version number to bind
- * @prot: transport protocol to use to make this request
- *
- * Return value is the requested advertised port number,
- * or a negative errno value.
- *
- * Called from outside the RPC client in a synchronous task context.
- * Uses default timeout parameters specified by underlying transport.
- *
- * XXX: Needs to support IPv6
- */
-int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot)
-{
- struct rpcbind_args map = {
- .r_prog = prog,
- .r_vers = vers,
- .r_prot = prot,
- .r_port = 0,
- };
- struct rpc_message msg = {
- .rpc_proc = &rpcb_procedures2[RPCBPROC_GETPORT],
- .rpc_argp = &map,
- .rpc_resp = &map,
- };
- struct rpc_clnt *rpcb_clnt;
- int status;
-
- dprintk("RPC: %s(%pI4, %u, %u, %d)\n",
- __func__, &sin->sin_addr.s_addr, prog, vers, prot);
-
- rpcb_clnt = rpcb_create(NULL, (struct sockaddr *)sin,
- sizeof(*sin), prot, RPCBVERS_2);
- if (IS_ERR(rpcb_clnt))
- return PTR_ERR(rpcb_clnt);
-
- status = rpc_call_sync(rpcb_clnt, &msg, 0);
- rpc_shutdown_client(rpcb_clnt);
-
- if (status >= 0) {
- if (map.r_port != 0)
- return map.r_port;
- status = -EACCES;
- }
- return status;
-}
-EXPORT_SYMBOL_GPL(rpcb_getport_sync);
-
static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, struct rpc_procinfo *proc)
{
struct rpc_message msg = {
xs_close(xprt);
xs_free_peer_addresses(xprt);
- kfree(xprt->slot);
- kfree(xprt);
+ xprt_free(xprt);
module_put(THIS_MODULE);
}
u32 _xid;
__be32 *xp;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
dprintk("RPC: xs_udp_data_ready...\n");
if (!(xprt = xprt_from_sock(sk)))
goto out;
dropit:
skb_free_datagram(sk, skb);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
dprintk("RPC: xs_tcp_data_ready...\n");
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
if (xprt->shutdown)
read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
} while (read > 0);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
/*
{
struct rpc_xprt *xprt;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: xs_tcp_state_change client %p...\n", xprt);
switch (sk->sk_state) {
case TCP_ESTABLISHED:
- spin_lock_bh(&xprt->transport_lock);
+ spin_lock(&xprt->transport_lock);
if (!xprt_test_and_set_connected(xprt)) {
struct sock_xprt *transport = container_of(xprt,
struct sock_xprt, xprt);
xprt_wake_pending_tasks(xprt, -EAGAIN);
}
- spin_unlock_bh(&xprt->transport_lock);
+ spin_unlock(&xprt->transport_lock);
break;
case TCP_FIN_WAIT1:
/* The client initiated a shutdown of the socket */
xs_sock_mark_closed(xprt);
}
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
/**
{
struct rpc_xprt *xprt;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: %s client %p...\n"
__func__, xprt, sk->sk_err);
xprt_wake_pending_tasks(xprt, -EAGAIN);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static void xs_write_space(struct sock *sk)
*/
static void xs_udp_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
/* from net/core/sock.c:sock_def_write_space */
if (sock_writeable(sk))
xs_write_space(sk);
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
/**
*/
static void xs_tcp_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
/* from net/core/stream.c:sk_stream_write_space */
if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
xs_write_space(sk);
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)
xs_update_peer_port(xprt);
}
- static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket *sock)
+ static unsigned short xs_get_srcport(struct sock_xprt *transport)
{
unsigned short port = transport->srcport;
return port;
}
- static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket *sock, unsigned short port)
+ static unsigned short xs_next_srcport(struct sock_xprt *transport, unsigned short port)
{
if (transport->srcport != 0)
transport->srcport = 0;
return xprt_max_resvport;
return --port;
}
-
- static int xs_bind4(struct sock_xprt *transport, struct socket *sock)
+ static int xs_bind(struct sock_xprt *transport, struct socket *sock)
{
- struct sockaddr_in myaddr = {
- .sin_family = AF_INET,
- };
- struct sockaddr_in *sa;
+ struct sockaddr_storage myaddr;
int err, nloop = 0;
- unsigned short port = xs_get_srcport(transport, sock);
+ unsigned short port = xs_get_srcport(transport);
unsigned short last;
- sa = (struct sockaddr_in *)&transport->srcaddr;
- myaddr.sin_addr = sa->sin_addr;
+ memcpy(&myaddr, &transport->srcaddr, transport->xprt.addrlen);
do {
- myaddr.sin_port = htons(port);
- err = kernel_bind(sock, (struct sockaddr *) &myaddr,
- sizeof(myaddr));
+ rpc_set_port((struct sockaddr *)&myaddr, port);
+ err = kernel_bind(sock, (struct sockaddr *)&myaddr,
+ transport->xprt.addrlen);
if (port == 0)
break;
if (err == 0) {
break;
}
last = port;
- port = xs_next_srcport(transport, sock, port);
+ port = xs_next_srcport(transport, port);
if (port > last)
nloop++;
} while (err == -EADDRINUSE && nloop != 2);
- dprintk("RPC: %s %pI4:%u: %s (%d)\n",
- __func__, &myaddr.sin_addr,
- port, err ? "failed" : "ok", err);
- return err;
- }
-
- static int xs_bind6(struct sock_xprt *transport, struct socket *sock)
- {
- struct sockaddr_in6 myaddr = {
- .sin6_family = AF_INET6,
- };
- struct sockaddr_in6 *sa;
- int err, nloop = 0;
- unsigned short port = xs_get_srcport(transport, sock);
- unsigned short last;
- sa = (struct sockaddr_in6 *)&transport->srcaddr;
- myaddr.sin6_addr = sa->sin6_addr;
- do {
- myaddr.sin6_port = htons(port);
- err = kernel_bind(sock, (struct sockaddr *) &myaddr,
- sizeof(myaddr));
- if (port == 0)
- break;
- if (err == 0) {
- transport->srcport = port;
- break;
- }
- last = port;
- port = xs_next_srcport(transport, sock, port);
- if (port > last)
- nloop++;
- } while (err == -EADDRINUSE && nloop != 2);
- dprintk("RPC: xs_bind6 %pI6:%u: %s (%d)\n",
- &myaddr.sin6_addr, port, err ? "failed" : "ok", err);
+ if (myaddr.ss_family == AF_INET)
+ dprintk("RPC: %s %pI4:%u: %s (%d)\n", __func__,
+ &((struct sockaddr_in *)&myaddr)->sin_addr,
+ port, err ? "failed" : "ok", err);
+ else
+ dprintk("RPC: %s %pI6:%u: %s (%d)\n", __func__,
+ &((struct sockaddr_in6 *)&myaddr)->sin6_addr,
+ port, err ? "failed" : "ok", err);
return err;
}
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key xs_key[2];
static struct lock_class_key xs_slock_key[2];
sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC",
&xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]);
}
+
+ static inline void xs_reclassify_socket(int family, struct socket *sock)
+ {
+ switch (family) {
+ case AF_INET:
+ xs_reclassify_socket4(sock);
+ break;
+ case AF_INET6:
+ xs_reclassify_socket6(sock);
+ break;
+ }
+ }
#else
static inline void xs_reclassify_socket4(struct socket *sock)
{
static inline void xs_reclassify_socket6(struct socket *sock)
{
}
+
+ static inline void xs_reclassify_socket(int family, struct socket *sock)
+ {
+ }
#endif
+ static struct socket *xs_create_sock(struct rpc_xprt *xprt,
+ struct sock_xprt *transport, int family, int type, int protocol)
+ {
+ struct socket *sock;
+ int err;
+
+ err = __sock_create(xprt->xprt_net, family, type, protocol, &sock, 1);
+ if (err < 0) {
+ dprintk("RPC: can't create %d transport socket (%d).\n",
+ protocol, -err);
+ goto out;
+ }
+ xs_reclassify_socket(family, sock);
+
+ if (xs_bind(transport, sock)) {
+ sock_release(sock);
+ goto out;
+ }
+
+ return sock;
+ out:
+ return ERR_PTR(err);
+ }
+
static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
xs_udp_do_set_buffer_size(xprt);
}
- /**
- * xs_udp_connect_worker4 - set up a UDP socket
- * @work: RPC transport to connect
- *
- * Invoked by a work queue tasklet.
- */
- static void xs_udp_connect_worker4(struct work_struct *work)
+ static void xs_udp_setup_socket(struct work_struct *work)
{
struct sock_xprt *transport =
container_of(work, struct sock_xprt, connect_worker.work);
struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock = transport->sock;
- int err, status = -EIO;
+ int status = -EIO;
if (xprt->shutdown)
goto out;
/* Start by resetting any existing state */
xs_reset_transport(transport);
-
- err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
- if (err < 0) {
- dprintk("RPC: can't create UDP transport socket (%d).\n", -err);
+ sock = xs_create_sock(xprt, transport,
+ xs_addr(xprt)->sa_family, SOCK_DGRAM, IPPROTO_UDP);
+ if (IS_ERR(sock))
goto out;
- }
- xs_reclassify_socket4(sock);
-
- if (xs_bind4(transport, sock)) {
- sock_release(sock);
- goto out;
- }
-
- dprintk("RPC: worker connecting xprt %p via %s to "
- "%s (port %s)\n", xprt,
- xprt->address_strings[RPC_DISPLAY_PROTO],
- xprt->address_strings[RPC_DISPLAY_ADDR],
- xprt->address_strings[RPC_DISPLAY_PORT]);
-
- xs_udp_finish_connecting(xprt, sock);
- status = 0;
- out:
- xprt_clear_connecting(xprt);
- xprt_wake_pending_tasks(xprt, status);
- }
-
- /**
- * xs_udp_connect_worker6 - set up a UDP socket
- * @work: RPC transport to connect
- *
- * Invoked by a work queue tasklet.
- */
- static void xs_udp_connect_worker6(struct work_struct *work)
- {
- struct sock_xprt *transport =
- container_of(work, struct sock_xprt, connect_worker.work);
- struct rpc_xprt *xprt = &transport->xprt;
- struct socket *sock = transport->sock;
- int err, status = -EIO;
-
- if (xprt->shutdown)
- goto out;
-
- /* Start by resetting any existing state */
- xs_reset_transport(transport);
-
- err = sock_create_kern(PF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock);
- if (err < 0) {
- dprintk("RPC: can't create UDP transport socket (%d).\n", -err);
- goto out;
- }
- xs_reclassify_socket6(sock);
-
- if (xs_bind6(transport, sock) < 0) {
- sock_release(sock);
- goto out;
- }
dprintk("RPC: worker connecting xprt %p via %s to "
"%s (port %s)\n", xprt,
* We need to preserve the port number so the reply cache on the server can
* find our cached RPC replies when we get around to reconnecting.
*/
- static void xs_abort_connection(struct rpc_xprt *xprt, struct sock_xprt *transport)
+ static void xs_abort_connection(struct sock_xprt *transport)
{
int result;
struct sockaddr any;
- dprintk("RPC: disconnecting xprt %p to reuse port\n", xprt);
+ dprintk("RPC: disconnecting xprt %p to reuse port\n", transport);
/*
* Disconnect the transport socket by doing a connect operation
any.sa_family = AF_UNSPEC;
result = kernel_connect(transport->sock, &any, sizeof(any), 0);
if (!result)
- xs_sock_mark_closed(xprt);
+ xs_sock_mark_closed(&transport->xprt);
else
dprintk("RPC: AF_UNSPEC connect return code %d\n",
result);
}
- static void xs_tcp_reuse_connection(struct rpc_xprt *xprt, struct sock_xprt *transport)
+ static void xs_tcp_reuse_connection(struct sock_xprt *transport)
{
unsigned int state = transport->inet->sk_state;
"sk_shutdown set to %d\n",
__func__, transport->inet->sk_shutdown);
}
- xs_abort_connection(xprt, transport);
+ xs_abort_connection(transport);
}
static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
*
* Invoked by a work queue tasklet.
*/
- static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
- struct sock_xprt *transport,
- struct socket *(*create_sock)(struct rpc_xprt *,
- struct sock_xprt *))
+ static void xs_tcp_setup_socket(struct work_struct *work)
{
+ struct sock_xprt *transport =
+ container_of(work, struct sock_xprt, connect_worker.work);
struct socket *sock = transport->sock;
+ struct rpc_xprt *xprt = &transport->xprt;
int status = -EIO;
if (xprt->shutdown)
if (!sock) {
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
- sock = create_sock(xprt, transport);
+ sock = xs_create_sock(xprt, transport,
+ xs_addr(xprt)->sa_family, SOCK_STREAM, IPPROTO_TCP);
if (IS_ERR(sock)) {
status = PTR_ERR(sock);
goto out;
abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
&xprt->state);
/* "close" the socket, preserving the local port */
- xs_tcp_reuse_connection(xprt, transport);
+ xs_tcp_reuse_connection(transport);
if (abort_and_exit)
goto out_eagain;
xprt_wake_pending_tasks(xprt, status);
}
- static struct socket *xs_create_tcp_sock4(struct rpc_xprt *xprt,
- struct sock_xprt *transport)
- {
- struct socket *sock;
- int err;
-
- /* start from scratch */
- err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
- if (err < 0) {
- dprintk("RPC: can't create TCP transport socket (%d).\n",
- -err);
- goto out_err;
- }
- xs_reclassify_socket4(sock);
-
- if (xs_bind4(transport, sock) < 0) {
- sock_release(sock);
- goto out_err;
- }
- return sock;
- out_err:
- return ERR_PTR(-EIO);
- }
-
- /**
- * xs_tcp_connect_worker4 - connect a TCP socket to a remote endpoint
- * @work: RPC transport to connect
- *
- * Invoked by a work queue tasklet.
- */
- static void xs_tcp_connect_worker4(struct work_struct *work)
- {
- struct sock_xprt *transport =
- container_of(work, struct sock_xprt, connect_worker.work);
- struct rpc_xprt *xprt = &transport->xprt;
-
- xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock4);
- }
-
- static struct socket *xs_create_tcp_sock6(struct rpc_xprt *xprt,
- struct sock_xprt *transport)
- {
- struct socket *sock;
- int err;
-
- /* start from scratch */
- err = sock_create_kern(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &sock);
- if (err < 0) {
- dprintk("RPC: can't create TCP transport socket (%d).\n",
- -err);
- goto out_err;
- }
- xs_reclassify_socket6(sock);
-
- if (xs_bind6(transport, sock) < 0) {
- sock_release(sock);
- goto out_err;
- }
- return sock;
- out_err:
- return ERR_PTR(-EIO);
- }
-
- /**
- * xs_tcp_connect_worker6 - connect a TCP socket to a remote endpoint
- * @work: RPC transport to connect
- *
- * Invoked by a work queue tasklet.
- */
- static void xs_tcp_connect_worker6(struct work_struct *work)
- {
- struct sock_xprt *transport =
- container_of(work, struct sock_xprt, connect_worker.work);
- struct rpc_xprt *xprt = &transport->xprt;
-
- xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock6);
- }
-
/**
* xs_connect - connect a socket to a remote endpoint
* @task: address of RPC task that manages state of connect request
.print_stats = xs_tcp_print_stats,
};
+ static int xs_init_anyaddr(const int family, struct sockaddr *sap)
+ {
+ static const struct sockaddr_in sin = {
+ .sin_family = AF_INET,
+ .sin_addr.s_addr = htonl(INADDR_ANY),
+ };
+ static const struct sockaddr_in6 sin6 = {
+ .sin6_family = AF_INET6,
+ .sin6_addr = IN6ADDR_ANY_INIT,
+ };
+
+ switch (family) {
+ case AF_INET:
+ memcpy(sap, &sin, sizeof(sin));
+ break;
+ case AF_INET6:
+ memcpy(sap, &sin6, sizeof(sin6));
+ break;
+ default:
+ dprintk("RPC: %s: Bad address family\n", __func__);
+ return -EAFNOSUPPORT;
+ }
+ return 0;
+ }
+
static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
unsigned int slot_table_size)
{
return ERR_PTR(-EBADF);
}
- new = kzalloc(sizeof(*new), GFP_KERNEL);
- if (new == NULL) {
+ xprt = xprt_alloc(args->net, sizeof(*new), slot_table_size);
+ if (xprt == NULL) {
dprintk("RPC: xs_setup_xprt: couldn't allocate "
"rpc_xprt\n");
return ERR_PTR(-ENOMEM);
}
- xprt = &new->xprt;
-
- xprt->max_reqs = slot_table_size;
- xprt->slot = kcalloc(xprt->max_reqs, sizeof(struct rpc_rqst), GFP_KERNEL);
- if (xprt->slot == NULL) {
- kfree(xprt);
- dprintk("RPC: xs_setup_xprt: couldn't allocate slot "
- "table\n");
- return ERR_PTR(-ENOMEM);
- }
+ new = container_of(xprt, struct sock_xprt, xprt);
memcpy(&xprt->addr, args->dstaddr, args->addrlen);
xprt->addrlen = args->addrlen;
if (args->srcaddr)
memcpy(&new->srcaddr, args->srcaddr, args->addrlen);
+ else {
+ int err;
+ err = xs_init_anyaddr(args->dstaddr->sa_family,
+ (struct sockaddr *)&new->srcaddr);
+ if (err != 0)
+ return ERR_PTR(err);
+ }
return xprt;
}
xprt_set_bound(xprt);
INIT_DELAYED_WORK(&transport->connect_worker,
- xs_udp_connect_worker4);
+ xs_udp_setup_socket);
xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP);
break;
case AF_INET6:
xprt_set_bound(xprt);
INIT_DELAYED_WORK(&transport->connect_worker,
- xs_udp_connect_worker6);
+ xs_udp_setup_socket);
xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6);
break;
default:
return xprt;
ret = ERR_PTR(-EINVAL);
out_err:
- kfree(xprt->slot);
- kfree(xprt);
+ xprt_free(xprt);
return ret;
}
xprt_set_bound(xprt);
INIT_DELAYED_WORK(&transport->connect_worker,
- xs_tcp_connect_worker4);
+ xs_tcp_setup_socket);
xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP);
break;
case AF_INET6:
xprt_set_bound(xprt);
INIT_DELAYED_WORK(&transport->connect_worker,
- xs_tcp_connect_worker6);
+ xs_tcp_setup_socket);
xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6);
break;
default:
return xprt;
ret = ERR_PTR(-EINVAL);
out_err:
- kfree(xprt->slot);
- kfree(xprt);
+ xprt_free(xprt);
return ret;
}
goto out_err;
}
- if (xprt_bound(xprt))
- dprintk("RPC: set up xprt to %s (port %s) via %s\n",
- xprt->address_strings[RPC_DISPLAY_ADDR],
- xprt->address_strings[RPC_DISPLAY_PORT],
- xprt->address_strings[RPC_DISPLAY_PROTO]);
- else
- dprintk("RPC: set up xprt to %s (autobind) via %s\n",
- xprt->address_strings[RPC_DISPLAY_ADDR],
- xprt->address_strings[RPC_DISPLAY_PROTO]);
+ dprintk("RPC: set up xprt to %s (port %s) via %s\n",
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PORT],
+ xprt->address_strings[RPC_DISPLAY_PROTO]);
/*
* Since we don't want connections for the backchannel, we set
return xprt;
ret = ERR_PTR(-EINVAL);
out_err:
- kfree(xprt->slot);
- kfree(xprt);
+ xprt_free(xprt);
return ret;
}
projects / cascardo / linux.git / commitdiff