summaryrefslogtreecommitdiff
path: root/fs/nfsd
diff options
context:
space:
mode:
authorDmitry Torokhov <dmitry.torokhov@gmail.com>2013-05-01 08:47:44 -0700
committerDmitry Torokhov <dmitry.torokhov@gmail.com>2013-05-01 08:47:44 -0700
commitbf61c8840efe60fd8f91446860b63338fb424158 (patch)
tree7a71832407a4f0d6346db773343f4c3ae2257b19 /fs/nfsd
parent5846115b30f3a881e542c8bfde59a699c1c13740 (diff)
parent0c6a61657da78098472fd0eb71cc01f2387fa1bb (diff)
Merge branch 'next' into for-linus
Prepare first set of updates for 3.10 merge window.
Diffstat (limited to 'fs/nfsd')
-rw-r--r--fs/nfsd/Kconfig4
-rw-r--r--fs/nfsd/acl.h2
-rw-r--r--fs/nfsd/auth.c12
-rw-r--r--fs/nfsd/auth.h6
-rw-r--r--fs/nfsd/cache.h17
-rw-r--r--fs/nfsd/export.c38
-rw-r--r--fs/nfsd/fault_inject.c113
-rw-r--r--fs/nfsd/fault_inject.h28
-rw-r--r--fs/nfsd/idmap.h8
-rw-r--r--fs/nfsd/netns.h66
-rw-r--r--fs/nfsd/nfs2acl.c25
-rw-r--r--fs/nfsd/nfs3acl.c2
-rw-r--r--fs/nfsd/nfs3proc.c11
-rw-r--r--fs/nfsd/nfs3xdr.c71
-rw-r--r--fs/nfsd/nfs4acl.c63
-rw-r--r--fs/nfsd/nfs4callback.c69
-rw-r--r--fs/nfsd/nfs4idmap.c54
-rw-r--r--fs/nfsd/nfs4proc.c81
-rw-r--r--fs/nfsd/nfs4recover.c571
-rw-r--r--fs/nfsd/nfs4state.c1134
-rw-r--r--fs/nfsd/nfs4xdr.c395
-rw-r--r--fs/nfsd/nfscache.c353
-rw-r--r--fs/nfsd/nfsctl.c168
-rw-r--r--fs/nfsd/nfsd.h42
-rw-r--r--fs/nfsd/nfsfh.c4
-rw-r--r--fs/nfsd/nfsproc.c12
-rw-r--r--fs/nfsd/nfssvc.c211
-rw-r--r--fs/nfsd/nfsxdr.c32
-rw-r--r--fs/nfsd/state.h64
-rw-r--r--fs/nfsd/vfs.c66
-rw-r--r--fs/nfsd/vfs.h8
-rw-r--r--fs/nfsd/xdr.h2
-rw-r--r--fs/nfsd/xdr3.h2
-rw-r--r--fs/nfsd/xdr4.h17
34 files changed, 2435 insertions, 1316 deletions
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 8df1ea4a6ff9..430b6872806f 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -65,8 +65,8 @@ config NFSD_V3_ACL
If unsure, say N.
config NFSD_V4
- bool "NFS server support for NFS version 4 (EXPERIMENTAL)"
- depends on NFSD && PROC_FS && EXPERIMENTAL
+ bool "NFS server support for NFS version 4"
+ depends on NFSD && PROC_FS
select NFSD_V3
select FS_POSIX_ACL
select SUNRPC_GSS
diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h
index 34e5c40af5ef..8b186a4955cc 100644
--- a/fs/nfsd/acl.h
+++ b/fs/nfsd/acl.h
@@ -44,8 +44,6 @@
struct nfs4_acl *nfs4_acl_new(int);
int nfs4_acl_get_whotype(char *, u32);
int nfs4_acl_write_who(int who, char *p);
-int nfs4_acl_permission(struct nfs4_acl *acl, uid_t owner, gid_t group,
- uid_t who, u32 mask);
#define NFS4_ACL_TYPE_DEFAULT 0x01
#define NFS4_ACL_DIR 0x02
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 34a10d78b839..06cddd572264 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -47,9 +47,9 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
if (!gi)
goto oom;
} else if (flags & NFSEXP_ROOTSQUASH) {
- if (!new->fsuid)
+ if (uid_eq(new->fsuid, GLOBAL_ROOT_UID))
new->fsuid = exp->ex_anon_uid;
- if (!new->fsgid)
+ if (gid_eq(new->fsgid, GLOBAL_ROOT_GID))
new->fsgid = exp->ex_anon_gid;
gi = groups_alloc(rqgi->ngroups);
@@ -58,7 +58,7 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
for (i = 0; i < rqgi->ngroups; i++) {
if (gid_eq(GLOBAL_ROOT_GID, GROUP_AT(rqgi, i)))
- GROUP_AT(gi, i) = make_kgid(&init_user_ns, exp->ex_anon_gid);
+ GROUP_AT(gi, i) = exp->ex_anon_gid;
else
GROUP_AT(gi, i) = GROUP_AT(rqgi, i);
}
@@ -66,9 +66,9 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
gi = get_group_info(rqgi);
}
- if (new->fsuid == (uid_t) -1)
+ if (uid_eq(new->fsuid, INVALID_UID))
new->fsuid = exp->ex_anon_uid;
- if (new->fsgid == (gid_t) -1)
+ if (gid_eq(new->fsgid, INVALID_GID))
new->fsgid = exp->ex_anon_gid;
ret = set_groups(new, gi);
@@ -76,7 +76,7 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
if (ret < 0)
goto error;
- if (new->fsuid)
+ if (!uid_eq(new->fsuid, GLOBAL_ROOT_UID))
new->cap_effective = cap_drop_nfsd_set(new->cap_effective);
else
new->cap_effective = cap_raise_nfsd_set(new->cap_effective,
diff --git a/fs/nfsd/auth.h b/fs/nfsd/auth.h
index 78b3c0e93822..53325a12ba62 100644
--- a/fs/nfsd/auth.h
+++ b/fs/nfsd/auth.h
@@ -1,6 +1,5 @@
/*
* nfsd-specific authentication stuff.
- * uid/gid mapping not yet implemented.
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
@@ -8,11 +7,6 @@
#ifndef LINUX_NFSD_AUTH_H
#define LINUX_NFSD_AUTH_H
-#define nfsd_luid(rq, uid) ((u32)(uid))
-#define nfsd_lgid(rq, gid) ((u32)(gid))
-#define nfsd_ruid(rq, uid) ((u32)(uid))
-#define nfsd_rgid(rq, gid) ((u32)(gid))
-
/*
* Set the current process's fsuid/fsgid etc to those of the NFS
* client user
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index 93cc9d34c459..87fd1410b737 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -12,6 +12,10 @@
/*
* Representation of a reply cache entry.
+ *
+ * Note that we use a sockaddr_in6 to hold the address instead of the more
+ * typical sockaddr_storage. This is for space reasons, since sockaddr_storage
+ * is much larger than a sockaddr_in6.
*/
struct svc_cacherep {
struct hlist_node c_hash;
@@ -20,11 +24,13 @@ struct svc_cacherep {
unsigned char c_state, /* unused, inprog, done */
c_type, /* status, buffer */
c_secure : 1; /* req came from port < 1024 */
- struct sockaddr_in c_addr;
+ struct sockaddr_in6 c_addr;
__be32 c_xid;
u32 c_prot;
u32 c_proc;
u32 c_vers;
+ unsigned int c_len;
+ __wsum c_csum;
unsigned long c_timestamp;
union {
struct kvec u_vec;
@@ -46,8 +52,7 @@ enum {
enum {
RC_DROPIT,
RC_REPLY,
- RC_DOIT,
- RC_INTR
+ RC_DOIT
};
/*
@@ -67,6 +72,12 @@ enum {
*/
#define RC_DELAY (HZ/5)
+/* Cache entries expire after this time period */
+#define RC_EXPIRE (120 * HZ)
+
+/* Checksum this amount of the request */
+#define RC_CSUMLEN (256U)
+
int nfsd_reply_cache_init(void);
void nfsd_reply_cache_shutdown(void);
int nfsd_cache_lookup(struct svc_rqst *);
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index a3946cf13fc8..5f38ea36e266 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -67,11 +67,6 @@ static void expkey_request(struct cache_detail *cd,
(*bpp)[-1] = '\n';
}
-static int expkey_upcall(struct cache_detail *cd, struct cache_head *h)
-{
- return sunrpc_cache_pipe_upcall(cd, h, expkey_request);
-}
-
static struct svc_expkey *svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new,
struct svc_expkey *old);
static struct svc_expkey *svc_expkey_lookup(struct cache_detail *cd, struct svc_expkey *);
@@ -245,7 +240,7 @@ static struct cache_detail svc_expkey_cache_template = {
.hash_size = EXPKEY_HASHMAX,
.name = "nfsd.fh",
.cache_put = expkey_put,
- .cache_upcall = expkey_upcall,
+ .cache_request = expkey_request,
.cache_parse = expkey_parse,
.cache_show = expkey_show,
.match = expkey_match,
@@ -315,6 +310,7 @@ static void svc_export_put(struct kref *ref)
path_put(&exp->ex_path);
auth_domain_put(exp->ex_client);
nfsd4_fslocs_free(&exp->ex_fslocs);
+ kfree(exp->ex_uuid);
kfree(exp);
}
@@ -337,11 +333,6 @@ static void svc_export_request(struct cache_detail *cd,
(*bpp)[-1] = '\n';
}
-static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h)
-{
- return sunrpc_cache_pipe_upcall(cd, h, svc_export_request);
-}
-
static struct svc_export *svc_export_update(struct svc_export *new,
struct svc_export *old);
static struct svc_export *svc_export_lookup(struct svc_export *);
@@ -544,13 +535,17 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
err = get_int(&mesg, &an_int);
if (err)
goto out3;
- exp.ex_anon_uid= an_int;
+ exp.ex_anon_uid= make_kuid(&init_user_ns, an_int);
+ if (!uid_valid(exp.ex_anon_uid))
+ goto out3;
/* anon gid */
err = get_int(&mesg, &an_int);
if (err)
goto out3;
- exp.ex_anon_gid= an_int;
+ exp.ex_anon_gid= make_kgid(&init_user_ns, an_int);
+ if (!gid_valid(exp.ex_anon_gid))
+ goto out3;
/* fsid */
err = get_int(&mesg, &an_int);
@@ -613,7 +608,7 @@ out:
}
static void exp_flags(struct seq_file *m, int flag, int fsid,
- uid_t anonu, uid_t anong, struct nfsd4_fs_locations *fslocs);
+ kuid_t anonu, kgid_t anong, struct nfsd4_fs_locations *fslocs);
static void show_secinfo(struct seq_file *m, struct svc_export *exp);
static int svc_export_show(struct seq_file *m,
@@ -670,6 +665,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
new->ex_fslocs.locations = NULL;
new->ex_fslocs.locations_count = 0;
new->ex_fslocs.migrated = 0;
+ new->ex_uuid = NULL;
new->cd = item->cd;
}
@@ -711,7 +707,7 @@ static struct cache_detail svc_export_cache_template = {
.hash_size = EXPORT_HASHMAX,
.name = "nfsd.export",
.cache_put = svc_export_put,
- .cache_upcall = svc_export_upcall,
+ .cache_request = svc_export_request,
.cache_parse = svc_export_parse,
.cache_show = svc_export_show,
.match = svc_export_match,
@@ -1179,15 +1175,17 @@ static void show_secinfo(struct seq_file *m, struct svc_export *exp)
}
static void exp_flags(struct seq_file *m, int flag, int fsid,
- uid_t anonu, uid_t anong, struct nfsd4_fs_locations *fsloc)
+ kuid_t anonu, kgid_t anong, struct nfsd4_fs_locations *fsloc)
{
show_expflags(m, flag, NFSEXP_ALLFLAGS);
if (flag & NFSEXP_FSID)
seq_printf(m, ",fsid=%d", fsid);
- if (anonu != (uid_t)-2 && anonu != (0x10000-2))
- seq_printf(m, ",anonuid=%u", anonu);
- if (anong != (gid_t)-2 && anong != (0x10000-2))
- seq_printf(m, ",anongid=%u", anong);
+ if (!uid_eq(anonu, make_kuid(&init_user_ns, (uid_t)-2)) &&
+ !uid_eq(anonu, make_kuid(&init_user_ns, 0x10000-2)))
+ seq_printf(m, ",anonuid=%u", from_kuid(&init_user_ns, anonu));
+ if (!gid_eq(anong, make_kgid(&init_user_ns, (gid_t)-2)) &&
+ !gid_eq(anong, make_kgid(&init_user_ns, 0x10000-2)))
+ seq_printf(m, ",anongid=%u", from_kgid(&init_user_ns, anong));
if (fsloc && fsloc->locations_count > 0) {
char *loctype = (fsloc->migrated) ? "refer" : "replicas";
int i;
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index e6c38159622f..d620e7f81429 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -8,61 +8,144 @@
#include <linux/fs.h>
#include <linux/debugfs.h>
#include <linux/module.h>
+#include <linux/nsproxy.h>
+#include <linux/sunrpc/addr.h>
+#include <asm/uaccess.h>
#include "state.h"
-#include "fault_inject.h"
+#include "netns.h"
struct nfsd_fault_inject_op {
char *file;
- void (*func)(u64);
+ u64 (*forget)(struct nfs4_client *, u64);
+ u64 (*print)(struct nfs4_client *, u64);
};
static struct nfsd_fault_inject_op inject_ops[] = {
{
.file = "forget_clients",
- .func = nfsd_forget_clients,
+ .forget = nfsd_forget_client,
+ .print = nfsd_print_client,
},
{
.file = "forget_locks",
- .func = nfsd_forget_locks,
+ .forget = nfsd_forget_client_locks,
+ .print = nfsd_print_client_locks,
},
{
.file = "forget_openowners",
- .func = nfsd_forget_openowners,
+ .forget = nfsd_forget_client_openowners,
+ .print = nfsd_print_client_openowners,
},
{
.file = "forget_delegations",
- .func = nfsd_forget_delegations,
+ .forget = nfsd_forget_client_delegations,
+ .print = nfsd_print_client_delegations,
},
{
.file = "recall_delegations",
- .func = nfsd_recall_delegations,
+ .forget = nfsd_recall_client_delegations,
+ .print = nfsd_print_client_delegations,
},
};
static long int NUM_INJECT_OPS = sizeof(inject_ops) / sizeof(struct nfsd_fault_inject_op);
static struct dentry *debug_dir;
-static int nfsd_inject_set(void *op_ptr, u64 val)
+static void nfsd_inject_set(struct nfsd_fault_inject_op *op, u64 val)
{
- struct nfsd_fault_inject_op *op = op_ptr;
+ u64 count = 0;
if (val == 0)
printk(KERN_INFO "NFSD Fault Injection: %s (all)", op->file);
else
printk(KERN_INFO "NFSD Fault Injection: %s (n = %llu)", op->file, val);
- op->func(val);
- return 0;
+ nfs4_lock_state();
+ count = nfsd_for_n_state(val, op->forget);
+ nfs4_unlock_state();
+ printk(KERN_INFO "NFSD: %s: found %llu", op->file, count);
}
-static int nfsd_inject_get(void *data, u64 *val)
+static void nfsd_inject_set_client(struct nfsd_fault_inject_op *op,
+ struct sockaddr_storage *addr,
+ size_t addr_size)
{
- *val = 0;
- return 0;
+ char buf[INET6_ADDRSTRLEN];
+ struct nfs4_client *clp;
+ u64 count;
+
+ nfs4_lock_state();
+ clp = nfsd_find_client(addr, addr_size);
+ if (clp) {
+ count = op->forget(clp, 0);
+ rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf));
+ printk(KERN_INFO "NFSD [%s]: Client %s had %llu state object(s)\n", op->file, buf, count);
+ }
+ nfs4_unlock_state();
+}
+
+static void nfsd_inject_get(struct nfsd_fault_inject_op *op, u64 *val)
+{
+ nfs4_lock_state();
+ *val = nfsd_for_n_state(0, op->print);
+ nfs4_unlock_state();
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_nfsd, nfsd_inject_get, nfsd_inject_set, "%llu\n");
+static ssize_t fault_inject_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ static u64 val;
+ char read_buf[25];
+ size_t size, ret;
+ loff_t pos = *ppos;
+
+ if (!pos)
+ nfsd_inject_get(file_inode(file)->i_private, &val);
+ size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val);
+
+ if (pos < 0)
+ return -EINVAL;
+ if (pos >= size || !len)
+ return 0;
+ if (len > size - pos)
+ len = size - pos;
+ ret = copy_to_user(buf, read_buf + pos, len);
+ if (ret == len)
+ return -EFAULT;
+ len -= ret;
+ *ppos = pos + len;
+ return len;
+}
+
+static ssize_t fault_inject_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ char write_buf[INET6_ADDRSTRLEN];
+ size_t size = min(sizeof(write_buf) - 1, len);
+ struct net *net = current->nsproxy->net_ns;
+ struct sockaddr_storage sa;
+ u64 val;
+
+ if (copy_from_user(write_buf, buf, size))
+ return -EFAULT;
+ write_buf[size] = '\0';
+
+ size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa));
+ if (size > 0)
+ nfsd_inject_set_client(file_inode(file)->i_private, &sa, size);
+ else {
+ val = simple_strtoll(write_buf, NULL, 0);
+ nfsd_inject_set(file_inode(file)->i_private, val);
+ }
+ return len; /* on success, claim we got the whole input */
+}
+
+static const struct file_operations fops_nfsd = {
+ .owner = THIS_MODULE,
+ .read = fault_inject_read,
+ .write = fault_inject_write,
+};
void nfsd_fault_inject_cleanup(void)
{
diff --git a/fs/nfsd/fault_inject.h b/fs/nfsd/fault_inject.h
deleted file mode 100644
index 90bd0570956c..000000000000
--- a/fs/nfsd/fault_inject.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (c) 2011 Bryan Schumaker <bjschuma@netapp.com>
- *
- * Function definitions for fault injection
- */
-
-#ifndef LINUX_NFSD_FAULT_INJECT_H
-#define LINUX_NFSD_FAULT_INJECT_H
-
-#ifdef CONFIG_NFSD_FAULT_INJECTION
-int nfsd_fault_inject_init(void);
-void nfsd_fault_inject_cleanup(void);
-void nfsd_forget_clients(u64);
-void nfsd_forget_locks(u64);
-void nfsd_forget_openowners(u64);
-void nfsd_forget_delegations(u64);
-void nfsd_recall_delegations(u64);
-#else /* CONFIG_NFSD_FAULT_INJECTION */
-static inline int nfsd_fault_inject_init(void) { return 0; }
-static inline void nfsd_fault_inject_cleanup(void) {}
-static inline void nfsd_forget_clients(u64 num) {}
-static inline void nfsd_forget_locks(u64 num) {}
-static inline void nfsd_forget_openowners(u64 num) {}
-static inline void nfsd_forget_delegations(u64 num) {}
-static inline void nfsd_recall_delegations(u64 num) {}
-#endif /* CONFIG_NFSD_FAULT_INJECTION */
-
-#endif /* LINUX_NFSD_FAULT_INJECT_H */
diff --git a/fs/nfsd/idmap.h b/fs/nfsd/idmap.h
index 9d513efc01ba..bf95f6b817a4 100644
--- a/fs/nfsd/idmap.h
+++ b/fs/nfsd/idmap.h
@@ -54,9 +54,9 @@ static inline void nfsd_idmap_shutdown(struct net *net)
}
#endif
-__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, __u32 *);
-__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, __u32 *);
-int nfsd_map_uid_to_name(struct svc_rqst *, __u32, char *);
-int nfsd_map_gid_to_name(struct svc_rqst *, __u32, char *);
+__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, kuid_t *);
+__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, kgid_t *);
+int nfsd_map_uid_to_name(struct svc_rqst *, kuid_t, char *);
+int nfsd_map_gid_to_name(struct svc_rqst *, kgid_t, char *);
#endif /* LINUX_NFSD_IDMAP_H */
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 65c2431ea32f..1051bebff1b0 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -24,7 +24,18 @@
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+/* Hash tables for nfs4_clientid state */
+#define CLIENT_HASH_BITS 4
+#define CLIENT_HASH_SIZE (1 << CLIENT_HASH_BITS)
+#define CLIENT_HASH_MASK (CLIENT_HASH_SIZE - 1)
+
+#define LOCKOWNER_INO_HASH_BITS 8
+#define LOCKOWNER_INO_HASH_SIZE (1 << LOCKOWNER_INO_HASH_BITS)
+
+#define SESSION_HASH_SIZE 512
+
struct cld_net;
+struct nfsd4_client_tracking_ops;
struct nfsd_net {
struct cld_net *cld_net;
@@ -38,7 +49,62 @@ struct nfsd_net {
struct lock_manager nfsd4_manager;
bool grace_ended;
time_t boot_time;
+
+ /*
+ * reclaim_str_hashtbl[] holds known client info from previous reset/reboot
+ * used in reboot/reset lease grace period processing
+ *
+ * conf_id_hashtbl[], and conf_name_tree hold confirmed
+ * setclientid_confirmed info.
+ *
+ * unconf_str_hastbl[] and unconf_name_tree hold unconfirmed
+ * setclientid info.
+ */
+ struct list_head *reclaim_str_hashtbl;
+ int reclaim_str_hashtbl_size;
+ struct list_head *conf_id_hashtbl;
+ struct rb_root conf_name_tree;
+ struct list_head *unconf_id_hashtbl;
+ struct rb_root unconf_name_tree;
+ struct list_head *ownerstr_hashtbl;
+ struct list_head *lockowner_ino_hashtbl;
+ struct list_head *sessionid_hashtbl;
+ /*
+ * client_lru holds client queue ordered by nfs4_client.cl_time
+ * for lease renewal.
+ *
+ * close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time
+ * for last close replay.
+ *
+ * All of the above fields are protected by the client_mutex.
+ */
+ struct list_head client_lru;
+ struct list_head close_lru;
+
+ struct delayed_work laundromat_work;
+
+ /* client_lock protects the client lru list and session hash table */
+ spinlock_t client_lock;
+
+ struct file *rec_file;
+ bool in_grace;
+ struct nfsd4_client_tracking_ops *client_tracking_ops;
+
+ time_t nfsd4_lease;
+ time_t nfsd4_grace;
+
+ bool nfsd_net_up;
+
+ /*
+ * Time of server startup
+ */
+ struct timeval nfssvc_boot;
+
+ struct svc_serv *nfsd_serv;
};
+/* Simple check to find out if a given net was properly initialized */
+#define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl)
+
extern int nfsd_net_id;
#endif /* __NFSD_NETNS_H__ */
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index b314888825d5..95d76dc6c5da 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -45,6 +45,10 @@ static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp,
RETURN_STATUS(nfserr_inval);
resp->mask = argp->mask;
+ nfserr = fh_getattr(fh, &resp->stat);
+ if (nfserr)
+ goto fail;
+
if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
acl = nfsd_get_posix_acl(fh, ACL_TYPE_ACCESS);
if (IS_ERR(acl)) {
@@ -115,6 +119,9 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
nfserr = nfserrno( nfsd_set_posix_acl(
fh, ACL_TYPE_DEFAULT, argp->acl_default) );
}
+ if (!nfserr) {
+ nfserr = fh_getattr(fh, &resp->stat);
+ }
/* argp->acl_{access,default} may have been allocated in
nfssvc_decode_setaclargs. */
@@ -129,10 +136,15 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
struct nfsd_fhandle *argp, struct nfsd_attrstat *resp)
{
+ __be32 nfserr;
dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh));
fh_copy(&resp->fh, &argp->fh);
- return fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+ nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+ if (nfserr)
+ return nfserr;
+ nfserr = fh_getattr(&resp->fh, &resp->stat);
+ return nfserr;
}
/*
@@ -150,6 +162,9 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessarg
fh_copy(&resp->fh, &argp->fh);
resp->access = argp->access;
nfserr = nfsd_access(rqstp, &resp->fh, &resp->access, NULL);
+ if (nfserr)
+ return nfserr;
+ nfserr = fh_getattr(&resp->fh, &resp->stat);
return nfserr;
}
@@ -243,7 +258,7 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
return 0;
inode = dentry->d_inode;
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh);
+ p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
*p++ = htonl(resp->mask);
if (!xdr_ressize_check(rqstp, p))
return 0;
@@ -253,7 +268,7 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
(resp->mask & NFS_ACL) ? resp->acl_access : NULL,
(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
while (w > 0) {
- if (!rqstp->rq_respages[rqstp->rq_resused++])
+ if (!*(rqstp->rq_next_page++))
return 0;
w -= PAGE_SIZE;
}
@@ -274,7 +289,7 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_attrstat *resp)
{
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh);
+ p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
return xdr_ressize_check(rqstp, p);
}
@@ -282,7 +297,7 @@ static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p,
static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_accessres *resp)
{
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh);
+ p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
*p++ = htonl(resp->access);
return xdr_ressize_check(rqstp, p);
}
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index a596e9d987e4..9cbc1a841f87 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -184,7 +184,7 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
(resp->mask & NFS_ACL) ? resp->acl_access : NULL,
(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
while (w > 0) {
- if (!rqstp->rq_respages[rqstp->rq_resused++])
+ if (!*(rqstp->rq_next_page++))
return 0;
w -= PAGE_SIZE;
}
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 97d90d1c8608..401289913130 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -43,7 +43,6 @@ static __be32
nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp,
struct nfsd3_attrstat *resp)
{
- int err;
__be32 nfserr;
dprintk("nfsd: GETATTR(3) %s\n",
@@ -55,9 +54,7 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp,
if (nfserr)
RETURN_STATUS(nfserr);
- err = vfs_getattr(resp->fh.fh_export->ex_path.mnt,
- resp->fh.fh_dentry, &resp->stat);
- nfserr = nfserrno(err);
+ nfserr = fh_getattr(&resp->fh, &resp->stat);
RETURN_STATUS(nfserr);
}
@@ -460,7 +457,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
__be32 nfserr;
int count = 0;
loff_t offset;
- int i;
+ struct page **p;
caddr_t page_addr = NULL;
dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n",
@@ -484,8 +481,8 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
&resp->common,
nfs3svc_encode_entry_plus);
memcpy(resp->verf, argp->verf, 8);
- for (i=1; i<rqstp->rq_resused ; i++) {
- page_addr = page_address(rqstp->rq_respages[i]);
+ for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
+ page_addr = page_address(*p);
if (((caddr_t)resp->buffer >= page_addr) &&
((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 43f46cd9edea..14d9ecb96cff 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -7,8 +7,11 @@
*/
#include <linux/namei.h>
+#include <linux/sunrpc/svc_xprt.h>
#include "xdr3.h"
#include "auth.h"
+#include "netns.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_XDR
@@ -103,12 +106,14 @@ decode_sattr3(__be32 *p, struct iattr *iap)
iap->ia_mode = ntohl(*p++);
}
if (*p++) {
- iap->ia_valid |= ATTR_UID;
- iap->ia_uid = ntohl(*p++);
+ iap->ia_uid = make_kuid(&init_user_ns, ntohl(*p++));
+ if (uid_valid(iap->ia_uid))
+ iap->ia_valid |= ATTR_UID;
}
if (*p++) {
- iap->ia_valid |= ATTR_GID;
- iap->ia_gid = ntohl(*p++);
+ iap->ia_gid = make_kgid(&init_user_ns, ntohl(*p++));
+ if (gid_valid(iap->ia_gid))
+ iap->ia_valid |= ATTR_GID;
}
if (*p++) {
u64 newsize;
@@ -165,8 +170,8 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
*p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
*p++ = htonl((u32) stat->mode);
*p++ = htonl((u32) stat->nlink);
- *p++ = htonl((u32) nfsd_ruid(rqstp, stat->uid));
- *p++ = htonl((u32) nfsd_rgid(rqstp, stat->gid));
+ *p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid));
+ *p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid));
if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN) {
p = xdr_encode_hyper(p, (u64) NFS3_MAXPATHLEN);
} else {
@@ -202,10 +207,10 @@ encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
{
struct dentry *dentry = fhp->fh_dentry;
if (dentry && dentry->d_inode) {
- int err;
+ __be32 err;
struct kstat stat;
- err = vfs_getattr(fhp->fh_export->ex_path.mnt, dentry, &stat);
+ err = fh_getattr(fhp, &stat);
if (!err) {
*p++ = xdr_one; /* attributes follow */
lease_get_mtime(dentry->d_inode, &stat.mtime);
@@ -252,13 +257,12 @@ encode_wcc_data(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
*/
void fill_post_wcc(struct svc_fh *fhp)
{
- int err;
+ __be32 err;
if (fhp->fh_post_saved)
printk("nfsd: inode locked twice during operation.\n");
- err = vfs_getattr(fhp->fh_export->ex_path.mnt, fhp->fh_dentry,
- &fhp->fh_post_attr);
+ err = fh_getattr(fhp, &fhp->fh_post_attr);
fhp->fh_post_change = fhp->fh_dentry->d_inode->i_version;
if (err) {
fhp->fh_post_saved = 0;
@@ -323,7 +327,7 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_readargs *args)
{
unsigned int len;
- int v,pn;
+ int v;
u32 max_blocksize = svc_max_payload(rqstp);
if (!(p = decode_fh(p, &args->fh)))
@@ -338,8 +342,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
/* set up the kvec */
v=0;
while (len > 0) {
- pn = rqstp->rq_resused++;
- rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_respages[pn]);
+ struct page *p = *(rqstp->rq_next_page++);
+
+ rqstp->rq_vec[v].iov_base = page_address(p);
rqstp->rq_vec[v].iov_len = len < PAGE_SIZE? len : PAGE_SIZE;
len -= rqstp->rq_vec[v].iov_len;
v++;
@@ -461,8 +466,7 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
len = ntohl(*p++);
if (len == 0 || len > NFS3_MAXPATHLEN || len >= PAGE_SIZE)
return 0;
- args->tname = new =
- page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+ args->tname = new = page_address(*(rqstp->rq_next_page++));
args->tlen = len;
/* first copy and check from the first page */
old = (char*)p;
@@ -533,8 +537,7 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
{
if (!(p = decode_fh(p, &args->fh)))
return 0;
- args->buffer =
- page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+ args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}
@@ -565,8 +568,7 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
if (args->count > PAGE_SIZE)
args->count = PAGE_SIZE;
- args->buffer =
- page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+ args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}
@@ -575,7 +577,7 @@ int
nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_readdirargs *args)
{
- int len, pn;
+ int len;
u32 max_blocksize = svc_max_payload(rqstp);
if (!(p = decode_fh(p, &args->fh)))
@@ -590,9 +592,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
args->count = len;
while (len > 0) {
- pn = rqstp->rq_resused++;
+ struct page *p = *(rqstp->rq_next_page++);
if (!args->buffer)
- args->buffer = page_address(rqstp->rq_respages[pn]);
+ args->buffer = page_address(p);
len -= PAGE_SIZE;
}
@@ -720,12 +722,14 @@ int
nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_writeres *resp)
{
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
p = encode_wcc_data(rqstp, p, &resp->fh);
if (resp->status == 0) {
*p++ = htonl(resp->count);
*p++ = htonl(resp->committed);
- *p++ = htonl(nfssvc_boot.tv_sec);
- *p++ = htonl(nfssvc_boot.tv_usec);
+ *p++ = htonl(nn->nfssvc_boot.tv_sec);
+ *p++ = htonl(nn->nfssvc_boot.tv_usec);
}
return xdr_ressize_check(rqstp, p);
}
@@ -876,7 +880,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
common);
__be32 *p = cd->buffer;
caddr_t curr_page_addr = NULL;
- int pn; /* current page number */
+ struct page ** page;
int slen; /* string (name) length */
int elen; /* estimated entry length in words */
int num_entry_words = 0; /* actual number of words */
@@ -913,8 +917,9 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
}
/* determine which page in rq_respages[] we are currently filling */
- for (pn=1; pn < cd->rqstp->rq_resused; pn++) {
- curr_page_addr = page_address(cd->rqstp->rq_respages[pn]);
+ for (page = cd->rqstp->rq_respages + 1;
+ page < cd->rqstp->rq_next_page; page++) {
+ curr_page_addr = page_address(*page);
if (((caddr_t)cd->buffer >= curr_page_addr) &&
((caddr_t)cd->buffer < curr_page_addr + PAGE_SIZE))
@@ -929,14 +934,14 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
if (plus)
p = encode_entryplus_baggage(cd, p, name, namlen);
num_entry_words = p - cd->buffer;
- } else if (cd->rqstp->rq_respages[pn+1] != NULL) {
+ } else if (*(page+1) != NULL) {
/* temporarily encode entry into next page, then move back to
* current and next page in rq_respages[] */
__be32 *p1, *tmp;
int len1, len2;
/* grab next page for temporary storage of entry */
- p1 = tmp = page_address(cd->rqstp->rq_respages[pn+1]);
+ p1 = tmp = page_address(*(page+1));
p1 = encode_entry_baggage(cd, p1, name, namlen, ino);
@@ -1082,11 +1087,13 @@ int
nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_commitres *resp)
{
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
p = encode_wcc_data(rqstp, p, &resp->fh);
/* Write verifier */
if (resp->status == 0) {
- *p++ = htonl(nfssvc_boot.tv_sec);
- *p++ = htonl(nfssvc_boot.tv_usec);
+ *p++ = htonl(nn->nfssvc_boot.tv_sec);
+ *p++ = htonl(nn->nfssvc_boot.tv_usec);
}
return xdr_ressize_check(rqstp, p);
}
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 9c51aff02ae2..8a50b3c18093 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -264,7 +264,7 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
ace->flag = eflag;
ace->access_mask = deny_mask_from_posix(deny, flags);
ace->whotype = NFS4_ACL_WHO_NAMED;
- ace->who = pa->e_id;
+ ace->who_uid = pa->e_uid;
ace++;
acl->naces++;
}
@@ -273,7 +273,7 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
flags);
ace->whotype = NFS4_ACL_WHO_NAMED;
- ace->who = pa->e_id;
+ ace->who_uid = pa->e_uid;
ace++;
acl->naces++;
pa++;
@@ -300,7 +300,7 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
flags);
ace->whotype = NFS4_ACL_WHO_NAMED;
- ace->who = pa->e_id;
+ ace->who_gid = pa->e_gid;
ace++;
acl->naces++;
pa++;
@@ -329,7 +329,7 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
ace->access_mask = deny_mask_from_posix(deny, flags);
ace->whotype = NFS4_ACL_WHO_NAMED;
- ace->who = pa->e_id;
+ ace->who_gid = pa->e_gid;
ace++;
acl->naces++;
}
@@ -345,6 +345,18 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
acl->naces++;
}
+static bool
+pace_gt(struct posix_acl_entry *pace1, struct posix_acl_entry *pace2)
+{
+ if (pace1->e_tag != pace2->e_tag)
+ return pace1->e_tag > pace2->e_tag;
+ if (pace1->e_tag == ACL_USER)
+ return uid_gt(pace1->e_uid, pace2->e_uid);
+ if (pace1->e_tag == ACL_GROUP)
+ return gid_gt(pace1->e_gid, pace2->e_gid);
+ return false;
+}
+
static void
sort_pacl_range(struct posix_acl *pacl, int start, int end) {
int sorted = 0, i;
@@ -355,8 +367,8 @@ sort_pacl_range(struct posix_acl *pacl, int start, int end) {
while (!sorted) {
sorted = 1;
for (i = start; i < end; i++) {
- if (pacl->a_entries[i].e_id
- > pacl->a_entries[i+1].e_id) {
+ if (pace_gt(&pacl->a_entries[i],
+ &pacl->a_entries[i+1])) {
sorted = 0;
tmp = pacl->a_entries[i];
pacl->a_entries[i] = pacl->a_entries[i+1];
@@ -398,7 +410,10 @@ struct posix_ace_state {
};
struct posix_user_ace_state {
- uid_t uid;
+ union {
+ kuid_t uid;
+ kgid_t gid;
+ };
struct posix_ace_state perms;
};
@@ -521,7 +536,6 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
if (error)
goto out_err;
low_mode_from_nfs4(state->owner.allow, &pace->e_perm, flags);
- pace->e_id = ACL_UNDEFINED_ID;
for (i=0; i < state->users->n; i++) {
pace++;
@@ -531,7 +545,7 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
goto out_err;
low_mode_from_nfs4(state->users->aces[i].perms.allow,
&pace->e_perm, flags);
- pace->e_id = state->users->aces[i].uid;
+ pace->e_uid = state->users->aces[i].uid;
add_to_mask(state, &state->users->aces[i].perms);
}
@@ -541,7 +555,6 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
if (error)
goto out_err;
low_mode_from_nfs4(state->group.allow, &pace->e_perm, flags);
- pace->e_id = ACL_UNDEFINED_ID;
add_to_mask(state, &state->group);
for (i=0; i < state->groups->n; i++) {
@@ -552,14 +565,13 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
goto out_err;
low_mode_from_nfs4(state->groups->aces[i].perms.allow,
&pace->e_perm, flags);
- pace->e_id = state->groups->aces[i].uid;
+ pace->e_gid = state->groups->aces[i].gid;
add_to_mask(state, &state->groups->aces[i].perms);
}
pace++;
pace->e_tag = ACL_MASK;
low_mode_from_nfs4(state->mask.allow, &pace->e_perm, flags);
- pace->e_id = ACL_UNDEFINED_ID;
pace++;
pace->e_tag = ACL_OTHER;
@@ -567,7 +579,6 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
if (error)
goto out_err;
low_mode_from_nfs4(state->other.allow, &pace->e_perm, flags);
- pace->e_id = ACL_UNDEFINED_ID;
return pacl;
out_err:
@@ -587,12 +598,13 @@ static inline void deny_bits(struct posix_ace_state *astate, u32 mask)
astate->deny |= mask & ~astate->allow;
}
-static int find_uid(struct posix_acl_state *state, struct posix_ace_state_array *a, uid_t uid)
+static int find_uid(struct posix_acl_state *state, kuid_t uid)
{
+ struct posix_ace_state_array *a = state->users;
int i;
for (i = 0; i < a->n; i++)
- if (a->aces[i].uid == uid)
+ if (uid_eq(a->aces[i].uid, uid))
return i;
/* Not found: */
a->n++;
@@ -603,6 +615,23 @@ static int find_uid(struct posix_acl_state *state, struct posix_ace_state_array
return i;
}
+static int find_gid(struct posix_acl_state *state, kgid_t gid)
+{
+ struct posix_ace_state_array *a = state->groups;
+ int i;
+
+ for (i = 0; i < a->n; i++)
+ if (gid_eq(a->aces[i].gid, gid))
+ return i;
+ /* Not found: */
+ a->n++;
+ a->aces[i].gid = gid;
+ a->aces[i].perms.allow = state->everyone.allow;
+ a->aces[i].perms.deny = state->everyone.deny;
+
+ return i;
+}
+
static void deny_bits_array(struct posix_ace_state_array *a, u32 mask)
{
int i;
@@ -636,7 +665,7 @@ static void process_one_v4_ace(struct posix_acl_state *state,
}
break;
case ACL_USER:
- i = find_uid(state, state->users, ace->who);
+ i = find_uid(state, ace->who_uid);
if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
allow_bits(&state->users->aces[i].perms, mask);
} else {
@@ -658,7 +687,7 @@ static void process_one_v4_ace(struct posix_acl_state *state,
}
break;
case ACL_GROUP:
- i = find_uid(state, state->groups, ace->who);
+ i = find_gid(state, ace->who_gid);
if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
allow_bits(&state->groups->aces[i].perms, mask);
} else {
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index bdf29c96e4cd..99bc85ff0217 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -36,6 +36,7 @@
#include <linux/slab.h>
#include "nfsd.h"
#include "state.h"
+#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -625,20 +626,46 @@ static const struct rpc_program cb_program = {
.pipe_dir_name = "nfsd4_cb",
};
-static int max_cb_time(void)
+static int max_cb_time(struct net *net)
{
- return max(nfsd4_lease/10, (time_t)1) * HZ;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ return max(nn->nfsd4_lease/10, (time_t)1) * HZ;
}
+static struct rpc_cred *callback_cred;
+
+int set_callback_cred(void)
+{
+ if (callback_cred)
+ return 0;
+ callback_cred = rpc_lookup_machine_cred("nfs");
+ if (!callback_cred)
+ return -ENOMEM;
+ return 0;
+}
+
+static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses)
+{
+ if (clp->cl_minorversion == 0) {
+ return get_rpccred(callback_cred);
+ } else {
+ struct rpc_auth *auth = client->cl_auth;
+ struct auth_cred acred = {};
+
+ acred.uid = ses->se_cb_sec.uid;
+ acred.gid = ses->se_cb_sec.gid;
+ return auth->au_ops->lookup_cred(client->cl_auth, &acred, 0);
+ }
+}
static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
{
struct rpc_timeout timeparms = {
- .to_initval = max_cb_time(),
+ .to_initval = max_cb_time(clp->net),
.to_retries = 0,
};
struct rpc_create_args args = {
- .net = &init_net,
+ .net = clp->net,
.address = (struct sockaddr *) &conn->cb_addr,
.addrsize = conn->cb_addrlen,
.saddress = (struct sockaddr *) &conn->cb_saddr,
@@ -648,6 +675,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
.flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
};
struct rpc_clnt *client;
+ struct rpc_cred *cred;
if (clp->cl_minorversion == 0) {
if (!clp->cl_cred.cr_principal &&
@@ -666,7 +694,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
args.bc_xprt = conn->cb_xprt;
args.prognumber = clp->cl_cb_session->se_cb_prog;
args.protocol = XPRT_TRANSPORT_BC_TCP;
- args.authflavor = RPC_AUTH_UNIX;
+ args.authflavor = ses->se_cb_sec.flavor;
}
/* Create RPC client */
client = rpc_create(&args);
@@ -675,9 +703,14 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
PTR_ERR(client));
return PTR_ERR(client);
}
+ cred = get_backchannel_cred(clp, client, ses);
+ if (IS_ERR(cred)) {
+ rpc_shutdown_client(client);
+ return PTR_ERR(cred);
+ }
clp->cl_cb_client = client;
+ clp->cl_cb_cred = cred;
return 0;
-
}
static void warn_no_callback_path(struct nfs4_client *clp, int reason)
@@ -714,18 +747,6 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = {
.rpc_call_done = nfsd4_cb_probe_done,
};
-static struct rpc_cred *callback_cred;
-
-int set_callback_cred(void)
-{
- if (callback_cred)
- return 0;
- callback_cred = rpc_lookup_machine_cred("nfs");
- if (!callback_cred)
- return -ENOMEM;
- return 0;
-}
-
static struct workqueue_struct *callback_wq;
static void run_nfsd4_cb(struct nfsd4_callback *cb)
@@ -743,7 +764,6 @@ static void do_probe_callback(struct nfs4_client *clp)
cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL];
cb->cb_msg.rpc_argp = NULL;
cb->cb_msg.rpc_resp = NULL;
- cb->cb_msg.rpc_cred = callback_cred;
cb->cb_ops = &nfsd4_cb_probe_ops;
@@ -962,6 +982,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
if (clp->cl_cb_client) {
rpc_shutdown_client(clp->cl_cb_client);
clp->cl_cb_client = NULL;
+ put_rpccred(clp->cl_cb_cred);
+ clp->cl_cb_cred = NULL;
}
if (clp->cl_cb_conn.cb_xprt) {
svc_xprt_put(clp->cl_cb_conn.cb_xprt);
@@ -995,7 +1017,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
run_nfsd4_cb(cb);
}
-void nfsd4_do_callback_rpc(struct work_struct *w)
+static void nfsd4_do_callback_rpc(struct work_struct *w)
{
struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work);
struct nfs4_client *clp = cb->cb_clp;
@@ -1010,10 +1032,16 @@ void nfsd4_do_callback_rpc(struct work_struct *w)
nfsd4_release_cb(cb);
return;
}
+ cb->cb_msg.rpc_cred = clp->cl_cb_cred;
rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
cb->cb_ops, cb);
}
+void nfsd4_init_callback(struct nfsd4_callback *cb)
+{
+ INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
+}
+
void nfsd4_cb_recall(struct nfs4_delegation *dp)
{
struct nfsd4_callback *cb = &dp->dl_recall;
@@ -1025,7 +1053,6 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL];
cb->cb_msg.rpc_argp = cb;
cb->cb_msg.rpc_resp = cb;
- cb->cb_msg.rpc_cred = callback_cred;
cb->cb_ops = &nfsd4_cb_recall_ops;
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index a1f10c0a6255..4832fd819f88 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -65,7 +65,7 @@ MODULE_PARM_DESC(nfs4_disable_idmapping,
struct ent {
struct cache_head h;
int type; /* User / Group */
- uid_t id;
+ u32 id;
char name[IDMAP_NAMESZ];
char authname[IDMAP_NAMESZ];
};
@@ -140,12 +140,6 @@ idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
}
static int
-idtoname_upcall(struct cache_detail *cd, struct cache_head *ch)
-{
- return sunrpc_cache_pipe_upcall(cd, ch, idtoname_request);
-}
-
-static int
idtoname_match(struct cache_head *ca, struct cache_head *cb)
{
struct ent *a = container_of(ca, struct ent, h);
@@ -192,7 +186,7 @@ static struct cache_detail idtoname_cache_template = {
.hash_size = ENT_HASHMAX,
.name = "nfs4.idtoname",
.cache_put = ent_put,
- .cache_upcall = idtoname_upcall,
+ .cache_request = idtoname_request,
.cache_parse = idtoname_parse,
.cache_show = idtoname_show,
.warn_no_listener = warn_no_idmapd,
@@ -321,12 +315,6 @@ nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
}
static int
-nametoid_upcall(struct cache_detail *cd, struct cache_head *ch)
-{
- return sunrpc_cache_pipe_upcall(cd, ch, nametoid_request);
-}
-
-static int
nametoid_match(struct cache_head *ca, struct cache_head *cb)
{
struct ent *a = container_of(ca, struct ent, h);
@@ -365,7 +353,7 @@ static struct cache_detail nametoid_cache_template = {
.hash_size = ENT_HASHMAX,
.name = "nfs4.nametoid",
.cache_put = ent_put,
- .cache_upcall = nametoid_upcall,
+ .cache_request = nametoid_request,
.cache_parse = nametoid_parse,
.cache_show = nametoid_show,
.warn_no_listener = warn_no_idmapd,
@@ -540,7 +528,7 @@ rqst_authname(struct svc_rqst *rqstp)
static __be32
idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen,
- uid_t *id)
+ u32 *id)
{
struct ent *item, key = {
.type = type,
@@ -564,7 +552,7 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen
}
static int
-idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
+idmap_id_to_name(struct svc_rqst *rqstp, int type, u32 id, char *name)
{
struct ent *item, key = {
.id = id,
@@ -587,7 +575,7 @@ idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
}
static bool
-numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id)
+numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
{
int ret;
char buf[11];
@@ -603,7 +591,7 @@ numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namel
}
static __be32
-do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id)
+do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
{
if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
if (numeric_name_to_id(rqstp, type, name, namelen, id))
@@ -616,7 +604,7 @@ do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u
}
static int
-do_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
+do_id_to_name(struct svc_rqst *rqstp, int type, u32 id, char *name)
{
if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
return sprintf(name, "%u", id);
@@ -625,26 +613,40 @@ do_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
__be32
nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen,
- __u32 *id)
+ kuid_t *uid)
{
- return do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, id);
+ __be32 status;
+ u32 id = -1;
+ status = do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, &id);
+ *uid = make_kuid(&init_user_ns, id);
+ if (!uid_valid(*uid))
+ status = nfserr_badowner;
+ return status;
}
__be32
nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
- __u32 *id)
+ kgid_t *gid)
{
- return do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, id);
+ __be32 status;
+ u32 id = -1;
+ status = do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, &id);
+ *gid = make_kgid(&init_user_ns, id);
+ if (!gid_valid(*gid))
+ status = nfserr_badowner;
+ return status;
}
int
-nfsd_map_uid_to_name(struct svc_rqst *rqstp, __u32 id, char *name)
+nfsd_map_uid_to_name(struct svc_rqst *rqstp, kuid_t uid, char *name)
{
+ u32 id = from_kuid(&init_user_ns, uid);
return do_id_to_name(rqstp, IDMAP_TYPE_USER, id, name);
}
int
-nfsd_map_gid_to_name(struct svc_rqst *rqstp, __u32 id, char *name)
+nfsd_map_gid_to_name(struct svc_rqst *rqstp, kgid_t gid, char *name)
{
+ u32 id = from_kgid(&init_user_ns, gid);
return do_id_to_name(rqstp, IDMAP_TYPE_GROUP, id, name);
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 6c9a4b291dba..ae73175e6e68 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -40,6 +40,7 @@
#include "xdr4.h"
#include "vfs.h"
#include "current_stateid.h"
+#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -194,6 +195,7 @@ static __be32
do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
struct svc_fh *resfh;
+ int accmode;
__be32 status;
resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
@@ -253,9 +255,10 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
/* set reply cache */
fh_copy_shallow(&open->op_openowner->oo_owner.so_replay.rp_openfh,
&resfh->fh_handle);
- if (!open->op_created)
- status = do_open_permission(rqstp, resfh, open,
- NFSD_MAY_NOP);
+ accmode = NFSD_MAY_NOP;
+ if (open->op_created)
+ accmode |= NFSD_MAY_OWNER_OVERRIDE;
+ status = do_open_permission(rqstp, resfh, open, accmode);
set_change_info(&open->op_cinfo, current_fh);
fh_dup2(current_fh, resfh);
out:
@@ -304,6 +307,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
__be32 status;
struct nfsd4_compoundres *resp;
+ struct net *net = SVC_NET(rqstp);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
dprintk("NFSD: nfsd4_open filename %.*s op_openowner %p\n",
(int)open->op_fname.len, open->op_fname.data,
@@ -331,7 +336,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
/* check seqid for replay. set nfs4_owner */
resp = rqstp->rq_resp;
- status = nfsd4_process_open1(&resp->cstate, open);
+ status = nfsd4_process_open1(&resp->cstate, open, nn);
if (status == nfserr_replay_me) {
struct nfs4_replay *rp = &open->op_openowner->oo_owner.so_replay;
fh_put(&cstate->current_fh);
@@ -354,10 +359,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
/* Openowner is now set, so sequence id will get bumped. Now we need
* these checks before we do any creates: */
status = nfserr_grace;
- if (locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
+ if (locks_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
goto out;
status = nfserr_no_grace;
- if (!locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
+ if (!locks_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
goto out;
switch (open->op_claim_type) {
@@ -370,7 +375,9 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
break;
case NFS4_OPEN_CLAIM_PREVIOUS:
open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
- status = nfs4_check_open_reclaim(&open->op_clientid, cstate->minorversion);
+ status = nfs4_check_open_reclaim(&open->op_clientid,
+ cstate->minorversion,
+ nn);
if (status)
goto out;
case NFS4_OPEN_CLAIM_FH:
@@ -490,12 +497,13 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
&access->ac_supported);
}
-static void gen_boot_verifier(nfs4_verifier *verifier)
+static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net)
{
__be32 verf[2];
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- verf[0] = (__be32)nfssvc_boot.tv_sec;
- verf[1] = (__be32)nfssvc_boot.tv_usec;
+ verf[0] = (__be32)nn->nfssvc_boot.tv_sec;
+ verf[1] = (__be32)nn->nfssvc_boot.tv_usec;
memcpy(verifier->data, verf, sizeof(verifier->data));
}
@@ -503,7 +511,7 @@ static __be32
nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_commit *commit)
{
- gen_boot_verifier(&commit->co_verf);
+ gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp));
return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
commit->co_count);
}
@@ -684,6 +692,17 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (read->rd_offset >= OFFSET_MAX)
return nfserr_inval;
+ /*
+ * If we do a zero copy read, then a client will see read data
+ * that reflects the state of the file *after* performing the
+ * following compound.
+ *
+ * To ensure proper ordering, we therefore turn off zero copy if
+ * the client wants us to do more in this compound:
+ */
+ if (!nfsd4_last_compound_op(rqstp))
+ rqstp->rq_splice_ok = false;
+
nfs4_lock_state();
/* check stateid */
if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
@@ -876,6 +895,24 @@ out:
return status;
}
+static int fill_in_write_vector(struct kvec *vec, struct nfsd4_write *write)
+{
+ int i = 1;
+ int buflen = write->wr_buflen;
+
+ vec[0].iov_base = write->wr_head.iov_base;
+ vec[0].iov_len = min_t(int, buflen, write->wr_head.iov_len);
+ buflen -= vec[0].iov_len;
+
+ while (buflen) {
+ vec[i].iov_base = page_address(write->wr_pagelist[i - 1]);
+ vec[i].iov_len = min_t(int, PAGE_SIZE, buflen);
+ buflen -= vec[i].iov_len;
+ i++;
+ }
+ return i;
+}
+
static __be32
nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_write *write)
@@ -884,6 +921,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct file *filp = NULL;
__be32 status = nfs_ok;
unsigned long cnt;
+ int nvecs;
/* no need to check permission - this will be done in nfsd_write() */
@@ -904,10 +942,13 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
cnt = write->wr_buflen;
write->wr_how_written = write->wr_stable_how;
- gen_boot_verifier(&write->wr_verifier);
+ gen_boot_verifier(&write->wr_verifier, SVC_NET(rqstp));
+
+ nvecs = fill_in_write_vector(rqstp->rq_vec, write);
+ WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
status = nfsd_write(rqstp, &cstate->current_fh, filp,
- write->wr_offset, rqstp->rq_vec, write->wr_vlen,
+ write->wr_offset, rqstp->rq_vec, nvecs,
&cnt, &write->wr_how_written);
if (filp)
fput(filp);
@@ -952,14 +993,15 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (!buf)
return nfserr_jukebox;
+ p = buf;
status = nfsd4_encode_fattr(&cstate->current_fh,
cstate->current_fh.fh_export,
- cstate->current_fh.fh_dentry, buf,
- &count, verify->ve_bmval,
+ cstate->current_fh.fh_dentry, &p,
+ count, verify->ve_bmval,
rqstp, 0);
/* this means that nfsd4_encode_fattr() ran out of space */
- if (status == nfserr_resource && count == 0)
+ if (status == nfserr_resource)
status = nfserr_not_same;
if (status)
goto out_kfree;
@@ -1666,6 +1708,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
.op_name = "OP_EXCHANGE_ID",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_exchange_id_rsize,
},
+ [OP_BACKCHANNEL_CTL] = {
+ .op_func = (nfsd4op_func)nfsd4_backchannel_ctl,
+ .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
+ .op_name = "OP_BACKCHANNEL_CTL",
+ .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+ },
[OP_BIND_CONN_TO_SESSION] = {
.op_func = (nfsd4op_func)nfsd4_bind_conn_to_session,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
@@ -1719,6 +1767,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
.op_func = (nfsd4op_func)nfsd4_free_stateid,
.op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
.op_name = "OP_FREE_STATEID",
+ .op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
};
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 43295d45cc2b..899ca26dd194 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -58,13 +58,11 @@ struct nfsd4_client_tracking_ops {
void (*create)(struct nfs4_client *);
void (*remove)(struct nfs4_client *);
int (*check)(struct nfs4_client *);
- void (*grace_done)(struct net *, time_t);
+ void (*grace_done)(struct nfsd_net *, time_t);
};
/* Globals */
-static struct file *rec_file;
static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
-static struct nfsd4_client_tracking_ops *client_tracking_ops;
static int
nfs4_save_creds(const struct cred **original_creds)
@@ -75,8 +73,8 @@ nfs4_save_creds(const struct cred **original_creds)
if (!new)
return -ENOMEM;
- new->fsuid = 0;
- new->fsgid = 0;
+ new->fsuid = GLOBAL_ROOT_UID;
+ new->fsgid = GLOBAL_ROOT_GID;
*original_creds = override_creds(new);
put_cred(new);
return 0;
@@ -102,33 +100,39 @@ md5_to_hex(char *out, char *md5)
*out = '\0';
}
-__be32
-nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
+static int
+nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
{
struct xdr_netobj cksum;
struct hash_desc desc;
struct scatterlist sg;
- __be32 status = nfserr_jukebox;
+ int status;
dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
clname->len, clname->data);
desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
desc.tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(desc.tfm))
+ if (IS_ERR(desc.tfm)) {
+ status = PTR_ERR(desc.tfm);
goto out_no_tfm;
+ }
+
cksum.len = crypto_hash_digestsize(desc.tfm);
cksum.data = kmalloc(cksum.len, GFP_KERNEL);
- if (cksum.data == NULL)
+ if (cksum.data == NULL) {
+ status = -ENOMEM;
goto out;
+ }
sg_init_one(&sg, clname->data, clname->len);
- if (crypto_hash_digest(&desc, &sg, sg.length, cksum.data))
+ status = crypto_hash_digest(&desc, &sg, sg.length, cksum.data);
+ if (status)
goto out;
md5_to_hex(dname, cksum.data);
- status = nfs_ok;
+ status = 0;
out:
kfree(cksum.data);
crypto_free_hash(desc.tfm);
@@ -136,29 +140,61 @@ out_no_tfm:
return status;
}
+/*
+ * If we had an error generating the recdir name for the legacy tracker
+ * then warn the admin. If the error doesn't appear to be transient,
+ * then disable recovery tracking.
+ */
+static void
+legacy_recdir_name_error(int error)
+{
+ printk(KERN_ERR "NFSD: unable to generate recoverydir "
+ "name (%d).\n", error);
+
+ /*
+ * if the algorithm just doesn't exist, then disable the recovery
+ * tracker altogether. The crypto libs will generally return this if
+ * FIPS is enabled as well.
+ */
+ if (error == -ENOENT) {
+ printk(KERN_ERR "NFSD: disabling legacy clientid tracking. "
+ "Reboot recovery will not function correctly!\n");
+
+ /* the argument is ignored by the legacy exit function */
+ nfsd4_client_tracking_exit(NULL);
+ }
+}
+
static void
nfsd4_create_clid_dir(struct nfs4_client *clp)
{
const struct cred *original_cred;
- char *dname = clp->cl_recdir;
+ char dname[HEXDIR_LEN];
struct dentry *dir, *dentry;
+ struct nfs4_client_reclaim *crp;
int status;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname);
if (test_and_set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return;
- if (!rec_file)
+ if (!nn->rec_file)
return;
+
+ status = nfs4_make_rec_clidname(dname, &clp->cl_name);
+ if (status)
+ return legacy_recdir_name_error(status);
+
status = nfs4_save_creds(&original_cred);
if (status < 0)
return;
- status = mnt_want_write_file(rec_file);
+ status = mnt_want_write_file(nn->rec_file);
if (status)
return;
- dir = rec_file->f_path.dentry;
+ dir = nn->rec_file->f_path.dentry;
/* lock the parent */
mutex_lock(&dir->d_inode->i_mutex);
@@ -182,18 +218,24 @@ out_put:
dput(dentry);
out_unlock:
mutex_unlock(&dir->d_inode->i_mutex);
- if (status == 0)
- vfs_fsync(rec_file, 0);
- else
+ if (status == 0) {
+ if (nn->in_grace) {
+ crp = nfs4_client_to_reclaim(dname, nn);
+ if (crp)
+ crp->cr_clp = clp;
+ }
+ vfs_fsync(nn->rec_file, 0);
+ } else {
printk(KERN_ERR "NFSD: failed to write recovery record"
" (err %d); please check that %s exists"
" and is writeable", status,
user_recovery_dirname);
- mnt_drop_write_file(rec_file);
+ }
+ mnt_drop_write_file(nn->rec_file);
nfs4_reset_creds(original_cred);
}
-typedef int (recdir_func)(struct dentry *, struct dentry *);
+typedef int (recdir_func)(struct dentry *, struct dentry *, struct nfsd_net *);
struct name_list {
char name[HEXDIR_LEN];
@@ -219,10 +261,10 @@ nfsd4_build_namelist(void *arg, const char *name, int namlen,
}
static int
-nfsd4_list_rec_dir(recdir_func *f)
+nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
{
const struct cred *original_cred;
- struct dentry *dir = rec_file->f_path.dentry;
+ struct dentry *dir = nn->rec_file->f_path.dentry;
LIST_HEAD(names);
int status;
@@ -230,13 +272,13 @@ nfsd4_list_rec_dir(recdir_func *f)
if (status < 0)
return status;
- status = vfs_llseek(rec_file, 0, SEEK_SET);
+ status = vfs_llseek(nn->rec_file, 0, SEEK_SET);
if (status < 0) {
nfs4_reset_creds(original_cred);
return status;
}
- status = vfs_readdir(rec_file, nfsd4_build_namelist, &names);
+ status = vfs_readdir(nn->rec_file, nfsd4_build_namelist, &names);
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
while (!list_empty(&names)) {
struct name_list *entry;
@@ -248,7 +290,7 @@ nfsd4_list_rec_dir(recdir_func *f)
status = PTR_ERR(dentry);
break;
}
- status = f(dir, dentry);
+ status = f(dir, dentry, nn);
dput(dentry);
}
list_del(&entry->list);
@@ -260,14 +302,14 @@ nfsd4_list_rec_dir(recdir_func *f)
}
static int
-nfsd4_unlink_clid_dir(char *name, int namlen)
+nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn)
{
struct dentry *dir, *dentry;
int status;
dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name);
- dir = rec_file->f_path.dentry;
+ dir = nn->rec_file->f_path.dentry;
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_one_len(name, dir, namlen);
if (IS_ERR(dentry)) {
@@ -289,37 +331,52 @@ static void
nfsd4_remove_clid_dir(struct nfs4_client *clp)
{
const struct cred *original_cred;
+ struct nfs4_client_reclaim *crp;
+ char dname[HEXDIR_LEN];
int status;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- if (!rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+ if (!nn->rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return;
- status = mnt_want_write_file(rec_file);
+ status = nfs4_make_rec_clidname(dname, &clp->cl_name);
+ if (status)
+ return legacy_recdir_name_error(status);
+
+ status = mnt_want_write_file(nn->rec_file);
if (status)
goto out;
clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
status = nfs4_save_creds(&original_cred);
if (status < 0)
- goto out;
+ goto out_drop_write;
- status = nfsd4_unlink_clid_dir(clp->cl_recdir, HEXDIR_LEN-1);
+ status = nfsd4_unlink_clid_dir(dname, HEXDIR_LEN-1, nn);
nfs4_reset_creds(original_cred);
- if (status == 0)
- vfs_fsync(rec_file, 0);
- mnt_drop_write_file(rec_file);
+ if (status == 0) {
+ vfs_fsync(nn->rec_file, 0);
+ if (nn->in_grace) {
+ /* remove reclaim record */
+ crp = nfsd4_find_reclaim_client(dname, nn);
+ if (crp)
+ nfs4_remove_reclaim_record(crp, nn);
+ }
+ }
+out_drop_write:
+ mnt_drop_write_file(nn->rec_file);
out:
if (status)
printk("NFSD: Failed to remove expired client state directory"
- " %.*s\n", HEXDIR_LEN, clp->cl_recdir);
+ " %.*s\n", HEXDIR_LEN, dname);
}
static int
-purge_old(struct dentry *parent, struct dentry *child)
+purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
{
int status;
- if (nfs4_has_reclaimed_state(child->d_name.name, false))
+ if (nfs4_has_reclaimed_state(child->d_name.name, nn))
return 0;
status = vfs_rmdir(parent->d_inode, child);
@@ -331,27 +388,29 @@ purge_old(struct dentry *parent, struct dentry *child)
}
static void
-nfsd4_recdir_purge_old(struct net *net, time_t boot_time)
+nfsd4_recdir_purge_old(struct nfsd_net *nn, time_t boot_time)
{
int status;
- if (!rec_file)
+ nn->in_grace = false;
+ if (!nn->rec_file)
return;
- status = mnt_want_write_file(rec_file);
+ status = mnt_want_write_file(nn->rec_file);
if (status)
goto out;
- status = nfsd4_list_rec_dir(purge_old);
+ status = nfsd4_list_rec_dir(purge_old, nn);
if (status == 0)
- vfs_fsync(rec_file, 0);
- mnt_drop_write_file(rec_file);
+ vfs_fsync(nn->rec_file, 0);
+ mnt_drop_write_file(nn->rec_file);
out:
+ nfs4_release_reclaim(nn);
if (status)
printk("nfsd4: failed to purge old clients from recovery"
- " directory %s\n", rec_file->f_path.dentry->d_name.name);
+ " directory %s\n", nn->rec_file->f_path.dentry->d_name.name);
}
static int
-load_recdir(struct dentry *parent, struct dentry *child)
+load_recdir(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
{
if (child->d_name.len != HEXDIR_LEN - 1) {
printk("nfsd4: illegal name %s in recovery directory\n",
@@ -359,21 +418,22 @@ load_recdir(struct dentry *parent, struct dentry *child)
/* Keep trying; maybe the others are OK: */
return 0;
}
- nfs4_client_to_reclaim(child->d_name.name);
+ nfs4_client_to_reclaim(child->d_name.name, nn);
return 0;
}
static int
-nfsd4_recdir_load(void) {
+nfsd4_recdir_load(struct net *net) {
int status;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- if (!rec_file)
+ if (!nn->rec_file)
return 0;
- status = nfsd4_list_rec_dir(load_recdir);
+ status = nfsd4_list_rec_dir(load_recdir, nn);
if (status)
printk("nfsd4: failed loading clients from recovery"
- " directory %s\n", rec_file->f_path.dentry->d_name.name);
+ " directory %s\n", nn->rec_file->f_path.dentry->d_name.name);
return status;
}
@@ -382,15 +442,16 @@ nfsd4_recdir_load(void) {
*/
static int
-nfsd4_init_recdir(void)
+nfsd4_init_recdir(struct net *net)
{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
const struct cred *original_cred;
int status;
printk("NFSD: Using %s as the NFSv4 state recovery directory\n",
user_recovery_dirname);
- BUG_ON(rec_file);
+ BUG_ON(nn->rec_file);
status = nfs4_save_creds(&original_cred);
if (status < 0) {
@@ -400,23 +461,65 @@ nfsd4_init_recdir(void)
return status;
}
- rec_file = filp_open(user_recovery_dirname, O_RDONLY | O_DIRECTORY, 0);
- if (IS_ERR(rec_file)) {
+ nn->rec_file = filp_open(user_recovery_dirname, O_RDONLY | O_DIRECTORY, 0);
+ if (IS_ERR(nn->rec_file)) {
printk("NFSD: unable to find recovery directory %s\n",
user_recovery_dirname);
- status = PTR_ERR(rec_file);
- rec_file = NULL;
+ status = PTR_ERR(nn->rec_file);
+ nn->rec_file = NULL;
}
nfs4_reset_creds(original_cred);
+ if (!status)
+ nn->in_grace = true;
return status;
}
+
+static int
+nfs4_legacy_state_init(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ int i;
+
+ nn->reclaim_str_hashtbl = kmalloc(sizeof(struct list_head) *
+ CLIENT_HASH_SIZE, GFP_KERNEL);
+ if (!nn->reclaim_str_hashtbl)
+ return -ENOMEM;
+
+ for (i = 0; i < CLIENT_HASH_SIZE; i++)
+ INIT_LIST_HEAD(&nn->reclaim_str_hashtbl[i]);
+ nn->reclaim_str_hashtbl_size = 0;
+
+ return 0;
+}
+
+static void
+nfs4_legacy_state_shutdown(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ kfree(nn->reclaim_str_hashtbl);
+}
+
static int
nfsd4_load_reboot_recovery_data(struct net *net)
{
int status;
+ status = nfsd4_init_recdir(net);
+ if (!status)
+ status = nfsd4_recdir_load(net);
+ if (status)
+ printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
+ return status;
+}
+
+static int
+nfsd4_legacy_tracking_init(struct net *net)
+{
+ int status;
+
/* XXX: The legacy code won't work in a container */
if (net != &init_net) {
WARN(1, KERN_ERR "NFSD: attempt to initialize legacy client "
@@ -424,30 +527,37 @@ nfsd4_load_reboot_recovery_data(struct net *net)
return -EINVAL;
}
- nfs4_lock_state();
- status = nfsd4_init_recdir();
- if (!status)
- status = nfsd4_recdir_load();
- nfs4_unlock_state();
+ status = nfs4_legacy_state_init(net);
if (status)
- printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
+ return status;
+
+ status = nfsd4_load_reboot_recovery_data(net);
+ if (status)
+ goto err;
+ return 0;
+
+err:
+ nfs4_legacy_state_shutdown(net);
return status;
}
static void
-nfsd4_shutdown_recdir(void)
+nfsd4_shutdown_recdir(struct nfsd_net *nn)
{
- if (!rec_file)
+ if (!nn->rec_file)
return;
- fput(rec_file);
- rec_file = NULL;
+ fput(nn->rec_file);
+ nn->rec_file = NULL;
}
static void
nfsd4_legacy_tracking_exit(struct net *net)
{
- nfs4_release_reclaim();
- nfsd4_shutdown_recdir();
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ nfs4_release_reclaim(nn);
+ nfsd4_shutdown_recdir(nn);
+ nfs4_legacy_state_shutdown(net);
}
/*
@@ -480,13 +590,26 @@ nfs4_recoverydir(void)
static int
nfsd4_check_legacy_client(struct nfs4_client *clp)
{
+ int status;
+ char dname[HEXDIR_LEN];
+ struct nfs4_client_reclaim *crp;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
/* did we already find that this client is stable? */
if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return 0;
+ status = nfs4_make_rec_clidname(dname, &clp->cl_name);
+ if (status) {
+ legacy_recdir_name_error(status);
+ return status;
+ }
+
/* look for it in the reclaim hashtable otherwise */
- if (nfsd4_find_reclaim_client(clp)) {
+ crp = nfsd4_find_reclaim_client(dname, nn);
+ if (crp) {
set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+ crp->cr_clp = clp;
return 0;
}
@@ -494,7 +617,7 @@ nfsd4_check_legacy_client(struct nfs4_client *clp)
}
static struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
- .init = nfsd4_load_reboot_recovery_data,
+ .init = nfsd4_legacy_tracking_init,
.exit = nfsd4_legacy_tracking_exit,
.create = nfsd4_create_clid_dir,
.remove = nfsd4_remove_clid_dir,
@@ -785,8 +908,7 @@ nfsd4_cld_create(struct nfs4_client *clp)
{
int ret;
struct cld_upcall *cup;
- /* FIXME: determine net from clp */
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
/* Don't upcall if it's already stored */
@@ -823,8 +945,7 @@ nfsd4_cld_remove(struct nfs4_client *clp)
{
int ret;
struct cld_upcall *cup;
- /* FIXME: determine net from clp */
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
/* Don't upcall if it's already removed */
@@ -861,8 +982,7 @@ nfsd4_cld_check(struct nfs4_client *clp)
{
int ret;
struct cld_upcall *cup;
- /* FIXME: determine net from clp */
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
/* Don't upcall if one was already stored during this grace pd */
@@ -892,11 +1012,10 @@ nfsd4_cld_check(struct nfs4_client *clp)
}
static void
-nfsd4_cld_grace_done(struct net *net, time_t boot_time)
+nfsd4_cld_grace_done(struct nfsd_net *nn, time_t boot_time)
{
int ret;
struct cld_upcall *cup;
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
cup = alloc_cld_upcall(cn);
@@ -926,28 +1045,267 @@ static struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = {
.grace_done = nfsd4_cld_grace_done,
};
+/* upcall via usermodehelper */
+static char cltrack_prog[PATH_MAX] = "/sbin/nfsdcltrack";
+module_param_string(cltrack_prog, cltrack_prog, sizeof(cltrack_prog),
+ S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(cltrack_prog, "Path to the nfsdcltrack upcall program");
+
+static bool cltrack_legacy_disable;
+module_param(cltrack_legacy_disable, bool, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(cltrack_legacy_disable,
+ "Disable legacy recoverydir conversion. Default: false");
+
+#define LEGACY_TOPDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_TOPDIR="
+#define LEGACY_RECDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_RECDIR="
+
+static char *
+nfsd4_cltrack_legacy_topdir(void)
+{
+ int copied;
+ size_t len;
+ char *result;
+
+ if (cltrack_legacy_disable)
+ return NULL;
+
+ len = strlen(LEGACY_TOPDIR_ENV_PREFIX) +
+ strlen(nfs4_recoverydir()) + 1;
+
+ result = kmalloc(len, GFP_KERNEL);
+ if (!result)
+ return result;
+
+ copied = snprintf(result, len, LEGACY_TOPDIR_ENV_PREFIX "%s",
+ nfs4_recoverydir());
+ if (copied >= len) {
+ /* just return nothing if output was truncated */
+ kfree(result);
+ return NULL;
+ }
+
+ return result;
+}
+
+static char *
+nfsd4_cltrack_legacy_recdir(const struct xdr_netobj *name)
+{
+ int copied;
+ size_t len;
+ char *result;
+
+ if (cltrack_legacy_disable)
+ return NULL;
+
+ /* +1 is for '/' between "topdir" and "recdir" */
+ len = strlen(LEGACY_RECDIR_ENV_PREFIX) +
+ strlen(nfs4_recoverydir()) + 1 + HEXDIR_LEN;
+
+ result = kmalloc(len, GFP_KERNEL);
+ if (!result)
+ return result;
+
+ copied = snprintf(result, len, LEGACY_RECDIR_ENV_PREFIX "%s/",
+ nfs4_recoverydir());
+ if (copied > (len - HEXDIR_LEN)) {
+ /* just return nothing if output will be truncated */
+ kfree(result);
+ return NULL;
+ }
+
+ copied = nfs4_make_rec_clidname(result + copied, name);
+ if (copied) {
+ kfree(result);
+ return NULL;
+ }
+
+ return result;
+}
+
+static int
+nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *legacy)
+{
+ char *envp[2];
+ char *argv[4];
+ int ret;
+
+ if (unlikely(!cltrack_prog[0])) {
+ dprintk("%s: cltrack_prog is disabled\n", __func__);
+ return -EACCES;
+ }
+
+ dprintk("%s: cmd: %s\n", __func__, cmd);
+ dprintk("%s: arg: %s\n", __func__, arg ? arg : "(null)");
+ dprintk("%s: legacy: %s\n", __func__, legacy ? legacy : "(null)");
+
+ envp[0] = legacy;
+ envp[1] = NULL;
+
+ argv[0] = (char *)cltrack_prog;
+ argv[1] = cmd;
+ argv[2] = arg;
+ argv[3] = NULL;
+
+ ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+ /*
+ * Disable the upcall mechanism if we're getting an ENOENT or EACCES
+ * error. The admin can re-enable it on the fly by using sysfs
+ * once the problem has been fixed.
+ */
+ if (ret == -ENOENT || ret == -EACCES) {
+ dprintk("NFSD: %s was not found or isn't executable (%d). "
+ "Setting cltrack_prog to blank string!",
+ cltrack_prog, ret);
+ cltrack_prog[0] = '\0';
+ }
+ dprintk("%s: %s return value: %d\n", __func__, cltrack_prog, ret);
+
+ return ret;
+}
+
+static char *
+bin_to_hex_dup(const unsigned char *src, int srclen)
+{
+ int i;
+ char *buf, *hex;
+
+ /* +1 for terminating NULL */
+ buf = kmalloc((srclen * 2) + 1, GFP_KERNEL);
+ if (!buf)
+ return buf;
+
+ hex = buf;
+ for (i = 0; i < srclen; i++) {
+ sprintf(hex, "%2.2x", *src++);
+ hex += 2;
+ }
+ return buf;
+}
+
+static int
+nfsd4_umh_cltrack_init(struct net __attribute__((unused)) *net)
+{
+ /* XXX: The usermode helper s not working in container yet. */
+ if (net != &init_net) {
+ WARN(1, KERN_ERR "NFSD: attempt to initialize umh client "
+ "tracking in a container!\n");
+ return -EINVAL;
+ }
+ return nfsd4_umh_cltrack_upcall("init", NULL, NULL);
+}
+
+static void
+nfsd4_umh_cltrack_create(struct nfs4_client *clp)
+{
+ char *hexid;
+
+ hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
+ if (!hexid) {
+ dprintk("%s: can't allocate memory for upcall!\n", __func__);
+ return;
+ }
+ nfsd4_umh_cltrack_upcall("create", hexid, NULL);
+ kfree(hexid);
+}
+
+static void
+nfsd4_umh_cltrack_remove(struct nfs4_client *clp)
+{
+ char *hexid;
+
+ hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
+ if (!hexid) {
+ dprintk("%s: can't allocate memory for upcall!\n", __func__);
+ return;
+ }
+ nfsd4_umh_cltrack_upcall("remove", hexid, NULL);
+ kfree(hexid);
+}
+
+static int
+nfsd4_umh_cltrack_check(struct nfs4_client *clp)
+{
+ int ret;
+ char *hexid, *legacy;
+
+ hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
+ if (!hexid) {
+ dprintk("%s: can't allocate memory for upcall!\n", __func__);
+ return -ENOMEM;
+ }
+ legacy = nfsd4_cltrack_legacy_recdir(&clp->cl_name);
+ ret = nfsd4_umh_cltrack_upcall("check", hexid, legacy);
+ kfree(legacy);
+ kfree(hexid);
+ return ret;
+}
+
+static void
+nfsd4_umh_cltrack_grace_done(struct nfsd_net __attribute__((unused)) *nn,
+ time_t boot_time)
+{
+ char *legacy;
+ char timestr[22]; /* FIXME: better way to determine max size? */
+
+ sprintf(timestr, "%ld", boot_time);
+ legacy = nfsd4_cltrack_legacy_topdir();
+ nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy);
+ kfree(legacy);
+}
+
+static struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = {
+ .init = nfsd4_umh_cltrack_init,
+ .exit = NULL,
+ .create = nfsd4_umh_cltrack_create,
+ .remove = nfsd4_umh_cltrack_remove,
+ .check = nfsd4_umh_cltrack_check,
+ .grace_done = nfsd4_umh_cltrack_grace_done,
+};
+
int
nfsd4_client_tracking_init(struct net *net)
{
int status;
struct path path;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- if (!client_tracking_ops) {
- client_tracking_ops = &nfsd4_cld_tracking_ops;
- status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
- if (!status) {
- if (S_ISDIR(path.dentry->d_inode->i_mode))
- client_tracking_ops =
- &nfsd4_legacy_tracking_ops;
- path_put(&path);
- }
+ /* just run the init if it the method is already decided */
+ if (nn->client_tracking_ops)
+ goto do_init;
+
+ /*
+ * First, try a UMH upcall. It should succeed or fail quickly, so
+ * there's little harm in trying that first.
+ */
+ nn->client_tracking_ops = &nfsd4_umh_tracking_ops;
+ status = nn->client_tracking_ops->init(net);
+ if (!status)
+ return status;
+
+ /*
+ * See if the recoverydir exists and is a directory. If it is,
+ * then use the legacy ops.
+ */
+ nn->client_tracking_ops = &nfsd4_legacy_tracking_ops;
+ status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
+ if (!status) {
+ status = S_ISDIR(path.dentry->d_inode->i_mode);
+ path_put(&path);
+ if (status)
+ goto do_init;
}
- status = client_tracking_ops->init(net);
+ /* Finally, try to use nfsdcld */
+ nn->client_tracking_ops = &nfsd4_cld_tracking_ops;
+ printk(KERN_WARNING "NFSD: the nfsdcld client tracking upcall will be "
+ "removed in 3.10. Please transition to using "
+ "nfsdcltrack.\n");
+do_init:
+ status = nn->client_tracking_ops->init(net);
if (status) {
printk(KERN_WARNING "NFSD: Unable to initialize client "
"recovery tracking! (%d)\n", status);
- client_tracking_ops = NULL;
+ nn->client_tracking_ops = NULL;
}
return status;
}
@@ -955,40 +1313,49 @@ nfsd4_client_tracking_init(struct net *net)
void
nfsd4_client_tracking_exit(struct net *net)
{
- if (client_tracking_ops) {
- client_tracking_ops->exit(net);
- client_tracking_ops = NULL;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ if (nn->client_tracking_ops) {
+ if (nn->client_tracking_ops->exit)
+ nn->client_tracking_ops->exit(net);
+ nn->client_tracking_ops = NULL;
}
}
void
nfsd4_client_record_create(struct nfs4_client *clp)
{
- if (client_tracking_ops)
- client_tracking_ops->create(clp);
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ if (nn->client_tracking_ops)
+ nn->client_tracking_ops->create(clp);
}
void
nfsd4_client_record_remove(struct nfs4_client *clp)
{
- if (client_tracking_ops)
- client_tracking_ops->remove(clp);
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ if (nn->client_tracking_ops)
+ nn->client_tracking_ops->remove(clp);
}
int
nfsd4_client_record_check(struct nfs4_client *clp)
{
- if (client_tracking_ops)
- return client_tracking_ops->check(clp);
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ if (nn->client_tracking_ops)
+ return nn->client_tracking_ops->check(clp);
return -EOPNOTSUPP;
}
void
-nfsd4_record_grace_done(struct net *net, time_t boot_time)
+nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time)
{
- if (client_tracking_ops)
- client_tracking_ops->grace_done(net, boot_time);
+ if (nn->client_tracking_ops)
+ nn->client_tracking_ops->grace_done(nn, boot_time);
}
static int
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d0237f872cc4..2e27430b9070 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -40,20 +40,15 @@
#include <linux/pagemap.h>
#include <linux/ratelimit.h>
#include <linux/sunrpc/svcauth_gss.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include "xdr4.h"
#include "vfs.h"
#include "current_stateid.h"
-#include "fault_inject.h"
#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
-/* Globals */
-time_t nfsd4_lease = 90; /* default lease time */
-time_t nfsd4_grace = 90;
-
#define all_ones {{~0,~0},~0}
static const stateid_t one_stateid = {
.si_generation = ~0,
@@ -156,7 +151,7 @@ get_nfs4_file(struct nfs4_file *fi)
}
static int num_delegations;
-unsigned int max_delegations;
+unsigned long max_delegations;
/*
* Open owner state (share locks)
@@ -176,8 +171,6 @@ static unsigned int ownerstr_hashval(u32 clientid, struct xdr_netobj *ownername)
return ret & OWNER_HASH_MASK;
}
-static struct list_head ownerstr_hashtbl[OWNER_HASH_SIZE];
-
/* hash table for nfs4_file */
#define FILE_HASH_BITS 8
#define FILE_HASH_SIZE (1 << FILE_HASH_BITS)
@@ -192,7 +185,7 @@ static struct list_head file_hashtbl[FILE_HASH_SIZE];
static void __nfs4_file_get_access(struct nfs4_file *fp, int oflag)
{
- BUG_ON(!(fp->fi_fds[oflag] || fp->fi_fds[O_RDWR]));
+ WARN_ON_ONCE(!(fp->fi_fds[oflag] || fp->fi_fds[O_RDWR]));
atomic_inc(&fp->fi_access[oflag]);
}
@@ -237,21 +230,28 @@ static void nfs4_file_put_access(struct nfs4_file *fp, int oflag)
__nfs4_file_put_access(fp, oflag);
}
-static inline int get_new_stid(struct nfs4_stid *stid)
+static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct
+kmem_cache *slab)
{
+ struct idr *stateids = &cl->cl_stateids;
static int min_stateid = 0;
- struct idr *stateids = &stid->sc_client->cl_stateids;
- int new_stid;
- int error;
+ struct nfs4_stid *stid;
+ int new_id;
+
+ stid = kmem_cache_alloc(slab, GFP_KERNEL);
+ if (!stid)
+ return NULL;
+
+ new_id = idr_alloc(stateids, stid, min_stateid, 0, GFP_KERNEL);
+ if (new_id < 0)
+ goto out_free;
+ stid->sc_client = cl;
+ stid->sc_type = 0;
+ stid->sc_stateid.si_opaque.so_id = new_id;
+ stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
+ /* Will be incremented before return to client: */
+ stid->sc_stateid.si_generation = 0;
- error = idr_get_new_above(stateids, stid, min_stateid, &new_stid);
- /*
- * Note: the necessary preallocation was done in
- * nfs4_alloc_stateid(). The idr code caps the number of
- * preallocations that can exist at a time, but the state lock
- * prevents anyone from using ours before we get here:
- */
- BUG_ON(error);
/*
* It shouldn't be a problem to reuse an opaque stateid value.
* I don't think it is for 4.1. But with 4.0 I worry that, for
@@ -262,39 +262,13 @@ static inline int get_new_stid(struct nfs4_stid *stid)
* "increase" (mod INT_MAX):
*/
- min_stateid = new_stid+1;
+ min_stateid = new_id+1;
if (min_stateid == INT_MAX)
min_stateid = 0;
- return new_stid;
-}
-
-static void init_stid(struct nfs4_stid *stid, struct nfs4_client *cl, unsigned char type)
-{
- stateid_t *s = &stid->sc_stateid;
- int new_id;
-
- stid->sc_type = type;
- stid->sc_client = cl;
- s->si_opaque.so_clid = cl->cl_clientid;
- new_id = get_new_stid(stid);
- s->si_opaque.so_id = (u32)new_id;
- /* Will be incremented before return to client: */
- s->si_generation = 0;
-}
-
-static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab)
-{
- struct idr *stateids = &cl->cl_stateids;
-
- if (!idr_pre_get(stateids, GFP_KERNEL))
- return NULL;
- /*
- * Note: if we fail here (or any time between now and the time
- * we actually get the new idr), we won't need to undo the idr
- * preallocation, since the idr code caps the number of
- * preallocated entries.
- */
- return kmem_cache_alloc(slab, GFP_KERNEL);
+ return stid;
+out_free:
+ kfree(stid);
+ return NULL;
}
static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp)
@@ -323,7 +297,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
if (dp == NULL)
return dp;
- init_stid(&dp->dl_stid, clp, NFS4_DELEG_STID);
+ dp->dl_stid.sc_type = NFS4_DELEG_STID;
/*
* delegation seqid's are never incremented. The 4.1 special
* meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -340,17 +314,25 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
fh_copy_shallow(&dp->dl_fh, &current_fh->fh_handle);
dp->dl_time = 0;
atomic_set(&dp->dl_count, 1);
- INIT_WORK(&dp->dl_recall.cb_work, nfsd4_do_callback_rpc);
+ nfsd4_init_callback(&dp->dl_recall);
return dp;
}
+static void free_stid(struct nfs4_stid *s, struct kmem_cache *slab)
+{
+ struct idr *stateids = &s->sc_client->cl_stateids;
+
+ idr_remove(stateids, s->sc_stateid.si_opaque.so_id);
+ kmem_cache_free(slab, s);
+}
+
void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
if (atomic_dec_and_test(&dp->dl_count)) {
dprintk("NFSD: freeing dp %p\n",dp);
put_nfs4_file(dp->dl_file);
- kmem_cache_free(deleg_slab, dp);
+ free_stid(&dp->dl_stid, deleg_slab);
num_delegations--;
}
}
@@ -367,9 +349,7 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp)
static void unhash_stid(struct nfs4_stid *s)
{
- struct idr *stateids = &s->sc_client->cl_stateids;
-
- idr_remove(stateids, s->sc_stateid.si_opaque.so_id);
+ s->sc_type = 0;
}
/* Called under the state lock. */
@@ -390,14 +370,6 @@ unhash_delegation(struct nfs4_delegation *dp)
* SETCLIENTID state
*/
-/* client_lock protects the client lru list and session hash table */
-static DEFINE_SPINLOCK(client_lock);
-
-/* Hash tables for nfs4_clientid state */
-#define CLIENT_HASH_BITS 4
-#define CLIENT_HASH_SIZE (1 << CLIENT_HASH_BITS)
-#define CLIENT_HASH_MASK (CLIENT_HASH_SIZE - 1)
-
static unsigned int clientid_hashval(u32 id)
{
return id & CLIENT_HASH_MASK;
@@ -409,31 +381,6 @@ static unsigned int clientstr_hashval(const char *name)
}
/*
- * reclaim_str_hashtbl[] holds known client info from previous reset/reboot
- * used in reboot/reset lease grace period processing
- *
- * conf_id_hashtbl[], and conf_str_hashtbl[] hold confirmed
- * setclientid_confirmed info.
- *
- * unconf_str_hastbl[] and unconf_id_hashtbl[] hold unconfirmed
- * setclientid info.
- *
- * client_lru holds client queue ordered by nfs4_client.cl_time
- * for lease renewal.
- *
- * close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time
- * for last close replay.
- */
-static struct list_head reclaim_str_hashtbl[CLIENT_HASH_SIZE];
-static int reclaim_str_hashtbl_size = 0;
-static struct list_head conf_id_hashtbl[CLIENT_HASH_SIZE];
-static struct list_head conf_str_hashtbl[CLIENT_HASH_SIZE];
-static struct list_head unconf_str_hashtbl[CLIENT_HASH_SIZE];
-static struct list_head unconf_id_hashtbl[CLIENT_HASH_SIZE];
-static struct list_head client_lru;
-static struct list_head close_lru;
-
-/*
* We store the NONE, READ, WRITE, and BOTH bits separately in the
* st_{access,deny}_bmap field of the stateid, in order to track not
* only what share bits are currently in force, but also what
@@ -526,7 +473,8 @@ static int nfs4_access_to_omode(u32 access)
case NFS4_SHARE_ACCESS_BOTH:
return O_RDWR;
}
- BUG();
+ WARN_ON_ONCE(1);
+ return O_RDONLY;
}
/* release all access and file references for a given stateid */
@@ -558,7 +506,7 @@ static void close_generic_stateid(struct nfs4_ol_stateid *stp)
static void free_generic_stateid(struct nfs4_ol_stateid *stp)
{
- kmem_cache_free(stateid_slab, stp);
+ free_stid(&stp->st_stid, stateid_slab);
}
static void release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -652,9 +600,6 @@ static void release_openowner(struct nfs4_openowner *oo)
nfs4_free_openowner(oo);
}
-#define SESSION_HASH_SIZE 512
-static struct list_head sessionid_hashtbl[SESSION_HASH_SIZE];
-
static inline int
hash_sessionid(struct nfs4_sessionid *sessionid)
{
@@ -742,8 +687,8 @@ static int nfsd4_get_drc_mem(int slotsize, u32 num)
num = min_t(u32, num, NFSD_MAX_SLOTS_PER_SESSION);
spin_lock(&nfsd_drc_lock);
- avail = min_t(int, NFSD_MAX_MEM_PER_SESSION,
- nfsd_drc_max_mem - nfsd_drc_mem_used);
+ avail = min((unsigned long)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);
@@ -785,9 +730,12 @@ out_free:
return NULL;
}
-static void init_forechannel_attrs(struct nfsd4_channel_attrs *new, struct nfsd4_channel_attrs *req, int numslots, int slotsize)
+static void init_forechannel_attrs(struct nfsd4_channel_attrs *new,
+ struct nfsd4_channel_attrs *req,
+ int numslots, int slotsize,
+ struct nfsd_net *nn)
{
- u32 maxrpc = nfsd_serv->sv_max_mesg;
+ u32 maxrpc = nn->nfsd_serv->sv_max_mesg;
new->maxreqs = numslots;
new->maxresp_cached = min_t(u32, req->maxresp_cached,
@@ -906,21 +854,27 @@ static void __free_session(struct nfsd4_session *ses)
static void free_session(struct kref *kref)
{
struct nfsd4_session *ses;
+ struct nfsd_net *nn;
- lockdep_assert_held(&client_lock);
ses = container_of(kref, struct nfsd4_session, se_ref);
+ nn = net_generic(ses->se_client->net, nfsd_net_id);
+
+ lockdep_assert_held(&nn->client_lock);
nfsd4_del_conns(ses);
__free_session(ses);
}
void nfsd4_put_session(struct nfsd4_session *ses)
{
- spin_lock(&client_lock);
+ struct nfsd_net *nn = net_generic(ses->se_client->net, nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
nfsd4_put_session_locked(ses);
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
}
-static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fchan)
+static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fchan,
+ struct nfsd_net *nn)
{
struct nfsd4_session *new;
int numslots, slotsize;
@@ -938,16 +892,17 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fchan)
new = __alloc_session(slotsize, numslots);
if (!new) {
- nfsd4_put_drc_mem(slotsize, fchan->maxreqs);
+ nfsd4_put_drc_mem(slotsize, numslots);
return NULL;
}
- init_forechannel_attrs(&new->se_fchannel, fchan, numslots, slotsize);
+ init_forechannel_attrs(&new->se_fchannel, fchan, numslots, slotsize, nn);
return new;
}
-static struct nfsd4_session *init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses)
+static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses)
{
int idx;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
new->se_client = clp;
gen_sessionid(new);
@@ -957,14 +912,15 @@ static struct nfsd4_session *init_session(struct svc_rqst *rqstp, struct nfsd4_s
new->se_cb_seq_nr = 1;
new->se_flags = cses->flags;
new->se_cb_prog = cses->callback_prog;
+ new->se_cb_sec = cses->cb_sec;
kref_init(&new->se_ref);
idx = hash_sessionid(&new->se_sessionid);
- spin_lock(&client_lock);
- list_add(&new->se_hash, &sessionid_hashtbl[idx]);
+ spin_lock(&nn->client_lock);
+ list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]);
spin_lock(&clp->cl_lock);
list_add(&new->se_perclnt, &clp->cl_sessions);
spin_unlock(&clp->cl_lock);
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
if (cses->flags & SESSION4_BACK_CHAN) {
struct sockaddr *sa = svc_addr(rqstp);
@@ -978,20 +934,20 @@ static struct nfsd4_session *init_session(struct svc_rqst *rqstp, struct nfsd4_s
rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa);
clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa);
}
- return new;
}
/* caller must hold client_lock */
static struct nfsd4_session *
-find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid)
+find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net)
{
struct nfsd4_session *elem;
int idx;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
dump_sessionid(__func__, sessionid);
idx = hash_sessionid(sessionid);
/* Search in the appropriate list */
- list_for_each_entry(elem, &sessionid_hashtbl[idx], se_hash) {
+ list_for_each_entry(elem, &nn->sessionid_hashtbl[idx], se_hash) {
if (!memcmp(elem->se_sessionid.data, sessionid->data,
NFS4_MAX_SESSIONID_LEN)) {
return elem;
@@ -1016,6 +972,8 @@ unhash_session(struct nfsd4_session *ses)
static inline void
renew_client_locked(struct nfs4_client *clp)
{
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
if (is_client_expired(clp)) {
WARN_ON(1);
printk("%s: client (clientid %08x/%08x) already expired\n",
@@ -1028,16 +986,18 @@ renew_client_locked(struct nfs4_client *clp)
dprintk("renewing client (clientid %08x/%08x)\n",
clp->cl_clientid.cl_boot,
clp->cl_clientid.cl_id);
- list_move_tail(&clp->cl_lru, &client_lru);
+ list_move_tail(&clp->cl_lru, &nn->client_lru);
clp->cl_time = get_seconds();
}
static inline void
renew_client(struct nfs4_client *clp)
{
- spin_lock(&client_lock);
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
renew_client_locked(clp);
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
}
/* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */
@@ -1075,7 +1035,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
static inline void
free_client(struct nfs4_client *clp)
{
- lockdep_assert_held(&client_lock);
+ struct nfsd_net __maybe_unused *nn = net_generic(clp->net, nfsd_net_id);
+
+ lockdep_assert_held(&nn->client_lock);
while (!list_empty(&clp->cl_sessions)) {
struct nfsd4_session *ses;
ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
@@ -1085,6 +1047,7 @@ free_client(struct nfs4_client *clp)
}
free_svc_cred(&clp->cl_cred);
kfree(clp->cl_name.data);
+ idr_destroy(&clp->cl_stateids);
kfree(clp);
}
@@ -1092,15 +1055,16 @@ void
release_session_client(struct nfsd4_session *session)
{
struct nfs4_client *clp = session->se_client;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- if (!atomic_dec_and_lock(&clp->cl_refcount, &client_lock))
+ if (!atomic_dec_and_lock(&clp->cl_refcount, &nn->client_lock))
return;
if (is_client_expired(clp)) {
free_client(clp);
session->se_client = NULL;
} else
renew_client_locked(clp);
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
}
/* must be called under the client_lock */
@@ -1123,6 +1087,7 @@ destroy_client(struct nfs4_client *clp)
struct nfs4_openowner *oo;
struct nfs4_delegation *dp;
struct list_head reaplist;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
INIT_LIST_HEAD(&reaplist);
spin_lock(&recall_lock);
@@ -1144,12 +1109,15 @@ destroy_client(struct nfs4_client *clp)
if (clp->cl_cb_conn.cb_xprt)
svc_xprt_put(clp->cl_cb_conn.cb_xprt);
list_del(&clp->cl_idhash);
- list_del(&clp->cl_strhash);
- spin_lock(&client_lock);
+ if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
+ rb_erase(&clp->cl_namenode, &nn->conf_name_tree);
+ else
+ rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
+ spin_lock(&nn->client_lock);
unhash_client_locked(clp);
if (atomic_read(&clp->cl_refcount) == 0)
free_client(clp);
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
}
static void expire_client(struct nfs4_client *clp)
@@ -1187,6 +1155,17 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source)
return 0;
}
+static long long
+compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2)
+{
+ long long res;
+
+ res = o1->len - o2->len;
+ if (res)
+ return res;
+ return (long long)memcmp(o1->data, o2->data, o1->len);
+}
+
static int same_name(const char *n1, const char *n2)
{
return 0 == memcmp(n1, n2, HEXDIR_LEN);
@@ -1211,7 +1190,7 @@ static bool groups_equal(struct group_info *g1, struct group_info *g2)
if (g1->ngroups != g2->ngroups)
return false;
for (i=0; i<g1->ngroups; i++)
- if (GROUP_AT(g1, i) != GROUP_AT(g2, i))
+ if (!gid_eq(GROUP_AT(g1, i), GROUP_AT(g2, i)))
return false;
return true;
}
@@ -1236,8 +1215,8 @@ static bool
same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
{
if ((is_gss_cred(cr1) != is_gss_cred(cr2))
- || (cr1->cr_uid != cr2->cr_uid)
- || (cr1->cr_gid != cr2->cr_gid)
+ || (!uid_eq(cr1->cr_uid, cr2->cr_uid))
+ || (!gid_eq(cr1->cr_gid, cr2->cr_gid))
|| !groups_equal(cr1->cr_group_info, cr2->cr_group_info))
return false;
if (cr1->cr_principal == cr2->cr_principal)
@@ -1247,10 +1226,9 @@ same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
return 0 == strcmp(cr1->cr_principal, cr2->cr_principal);
}
-static void gen_clid(struct nfs4_client *clp)
+static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn)
{
static u32 current_clientid = 1;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
clp->cl_clientid.cl_boot = nn->boot_time;
clp->cl_clientid.cl_id = current_clientid++;
@@ -1268,7 +1246,12 @@ static void gen_confirm(struct nfs4_client *clp)
static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
{
- return idr_find(&cl->cl_stateids, t->si_opaque.so_id);
+ struct nfs4_stid *ret;
+
+ ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id);
+ if (!ret || !ret->sc_type)
+ return NULL;
+ return ret;
}
static struct nfs4_stid *find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
@@ -1283,12 +1266,14 @@ static struct nfs4_stid *find_stateid_by_type(struct nfs4_client *cl, stateid_t
return NULL;
}
-static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir,
+static struct nfs4_client *create_client(struct xdr_netobj name,
struct svc_rqst *rqstp, nfs4_verifier *verf)
{
struct nfs4_client *clp;
struct sockaddr *sa = svc_addr(rqstp);
int ret;
+ struct net *net = SVC_NET(rqstp);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
clp = alloc_client(name);
if (clp == NULL)
@@ -1297,23 +1282,21 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir,
INIT_LIST_HEAD(&clp->cl_sessions);
ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred);
if (ret) {
- spin_lock(&client_lock);
+ spin_lock(&nn->client_lock);
free_client(clp);
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
return NULL;
}
idr_init(&clp->cl_stateids);
- memcpy(clp->cl_recdir, recdir, HEXDIR_LEN);
atomic_set(&clp->cl_refcount, 0);
clp->cl_cb_state = NFSD4_CB_UNKNOWN;
INIT_LIST_HEAD(&clp->cl_idhash);
- INIT_LIST_HEAD(&clp->cl_strhash);
INIT_LIST_HEAD(&clp->cl_openowners);
INIT_LIST_HEAD(&clp->cl_delegations);
INIT_LIST_HEAD(&clp->cl_lru);
INIT_LIST_HEAD(&clp->cl_callbacks);
spin_lock_init(&clp->cl_lock);
- INIT_WORK(&clp->cl_cb_null.cb_work, nfsd4_do_callback_rpc);
+ nfsd4_init_callback(&clp->cl_cb_null);
clp->cl_time = get_seconds();
clear_bit(0, &clp->cl_cb_slot_busy);
rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
@@ -1321,17 +1304,60 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir,
rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa);
gen_confirm(clp);
clp->cl_cb_session = NULL;
+ clp->net = net;
return clp;
}
static void
-add_to_unconfirmed(struct nfs4_client *clp, unsigned int strhashval)
+add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+ struct nfs4_client *clp;
+
+ while (*new) {
+ clp = rb_entry(*new, struct nfs4_client, cl_namenode);
+ parent = *new;
+
+ if (compare_blob(&clp->cl_name, &new_clp->cl_name) > 0)
+ new = &((*new)->rb_left);
+ else
+ new = &((*new)->rb_right);
+ }
+
+ rb_link_node(&new_clp->cl_namenode, parent, new);
+ rb_insert_color(&new_clp->cl_namenode, root);
+}
+
+static struct nfs4_client *
+find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root)
+{
+ long long cmp;
+ struct rb_node *node = root->rb_node;
+ struct nfs4_client *clp;
+
+ while (node) {
+ clp = rb_entry(node, struct nfs4_client, cl_namenode);
+ cmp = compare_blob(&clp->cl_name, name);
+ if (cmp > 0)
+ node = node->rb_left;
+ else if (cmp < 0)
+ node = node->rb_right;
+ else
+ return clp;
+ }
+ return NULL;
+}
+
+static void
+add_to_unconfirmed(struct nfs4_client *clp)
{
unsigned int idhashval;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- list_add(&clp->cl_strhash, &unconf_str_hashtbl[strhashval]);
+ clear_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
+ add_clp_to_name_tree(clp, &nn->unconf_name_tree);
idhashval = clientid_hashval(clp->cl_clientid.cl_id);
- list_add(&clp->cl_idhash, &unconf_id_hashtbl[idhashval]);
+ list_add(&clp->cl_idhash, &nn->unconf_id_hashtbl[idhashval]);
renew_client(clp);
}
@@ -1339,22 +1365,23 @@ static void
move_to_confirmed(struct nfs4_client *clp)
{
unsigned int idhashval = clientid_hashval(clp->cl_clientid.cl_id);
- unsigned int strhashval;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
dprintk("NFSD: move_to_confirm nfs4_client %p\n", clp);
- list_move(&clp->cl_idhash, &conf_id_hashtbl[idhashval]);
- strhashval = clientstr_hashval(clp->cl_recdir);
- list_move(&clp->cl_strhash, &conf_str_hashtbl[strhashval]);
+ list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]);
+ rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
+ add_clp_to_name_tree(clp, &nn->conf_name_tree);
+ set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
renew_client(clp);
}
static struct nfs4_client *
-find_confirmed_client(clientid_t *clid, bool sessions)
+find_confirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn)
{
struct nfs4_client *clp;
unsigned int idhashval = clientid_hashval(clid->cl_id);
- list_for_each_entry(clp, &conf_id_hashtbl[idhashval], cl_idhash) {
+ list_for_each_entry(clp, &nn->conf_id_hashtbl[idhashval], cl_idhash) {
if (same_clid(&clp->cl_clientid, clid)) {
if ((bool)clp->cl_minorversion != sessions)
return NULL;
@@ -1366,12 +1393,12 @@ find_confirmed_client(clientid_t *clid, bool sessions)
}
static struct nfs4_client *
-find_unconfirmed_client(clientid_t *clid, bool sessions)
+find_unconfirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn)
{
struct nfs4_client *clp;
unsigned int idhashval = clientid_hashval(clid->cl_id);
- list_for_each_entry(clp, &unconf_id_hashtbl[idhashval], cl_idhash) {
+ list_for_each_entry(clp, &nn->unconf_id_hashtbl[idhashval], cl_idhash) {
if (same_clid(&clp->cl_clientid, clid)) {
if ((bool)clp->cl_minorversion != sessions)
return NULL;
@@ -1387,27 +1414,15 @@ static bool clp_used_exchangeid(struct nfs4_client *clp)
}
static struct nfs4_client *
-find_confirmed_client_by_str(const char *dname, unsigned int hashval)
+find_confirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn)
{
- struct nfs4_client *clp;
-
- list_for_each_entry(clp, &conf_str_hashtbl[hashval], cl_strhash) {
- if (same_name(clp->cl_recdir, dname))
- return clp;
- }
- return NULL;
+ return find_clp_in_name_tree(name, &nn->conf_name_tree);
}
static struct nfs4_client *
-find_unconfirmed_client_by_str(const char *dname, unsigned int hashval)
+find_unconfirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn)
{
- struct nfs4_client *clp;
-
- list_for_each_entry(clp, &unconf_str_hashtbl[hashval], cl_strhash) {
- if (same_name(clp->cl_recdir, dname))
- return clp;
- }
- return NULL;
+ return find_clp_in_name_tree(name, &nn->unconf_name_tree);
}
static void
@@ -1428,7 +1443,7 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_r
else
goto out_err;
- conn->cb_addrlen = rpc_uaddr2sockaddr(&init_net, se->se_callback_addr_val,
+ conn->cb_addrlen = rpc_uaddr2sockaddr(clp->net, se->se_callback_addr_val,
se->se_callback_addr_len,
(struct sockaddr *)&conn->cb_addr,
sizeof(conn->cb_addr));
@@ -1572,12 +1587,11 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
{
struct nfs4_client *unconf, *conf, *new;
__be32 status;
- unsigned int strhashval;
- char dname[HEXDIR_LEN];
char addr_str[INET6_ADDRSTRLEN];
nfs4_verifier verf = exid->verifier;
struct sockaddr *sa = svc_addr(rqstp);
bool update = exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
rpc_ntop(sa, addr_str, sizeof(addr_str));
dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p "
@@ -1592,24 +1606,16 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
switch (exid->spa_how) {
case SP4_NONE:
break;
+ default: /* checked by xdr code */
+ WARN_ON_ONCE(1);
case SP4_SSV:
- return nfserr_serverfault;
- default:
- BUG(); /* checked by xdr code */
case SP4_MACH_CRED:
return nfserr_serverfault; /* no excuse :-/ */
}
- status = nfs4_make_rec_clidname(dname, &exid->clname);
-
- if (status)
- return status;
-
- strhashval = clientstr_hashval(dname);
-
/* Cases below refer to rfc 5661 section 18.35.4: */
nfs4_lock_state();
- conf = find_confirmed_client_by_str(dname, strhashval);
+ conf = find_confirmed_client_by_name(&exid->clname, nn);
if (conf) {
bool creds_match = same_creds(&conf->cl_cred, &rqstp->rq_cred);
bool verfs_match = same_verf(&verf, &conf->cl_verifier);
@@ -1654,21 +1660,21 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
goto out;
}
- unconf = find_unconfirmed_client_by_str(dname, strhashval);
+ unconf = find_unconfirmed_client_by_name(&exid->clname, nn);
if (unconf) /* case 4, possible retry or client restart */
expire_client(unconf);
/* case 1 (normal case) */
out_new:
- new = create_client(exid->clname, dname, rqstp, &verf);
+ new = create_client(exid->clname, rqstp, &verf);
if (new == NULL) {
status = nfserr_jukebox;
goto out;
}
new->cl_minorversion = 1;
- gen_clid(new);
- add_to_unconfirmed(new, strhashval);
+ gen_clid(new, nn);
+ add_to_unconfirmed(new);
out_copy:
exid->clientid.cl_boot = new->cl_clientid.cl_boot;
exid->clientid.cl_id = new->cl_clientid.cl_id;
@@ -1761,12 +1767,13 @@ nfsd4_create_session(struct svc_rqst *rqstp,
struct nfsd4_conn *conn;
struct nfsd4_clid_slot *cs_slot = NULL;
__be32 status = 0;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
if (cr_ses->flags & ~SESSION4_FLAG_MASK_A)
return nfserr_inval;
if (check_forechannel_attrs(cr_ses->fore_channel))
return nfserr_toosmall;
- new = alloc_session(&cr_ses->fore_channel);
+ new = alloc_session(&cr_ses->fore_channel, nn);
if (!new)
return nfserr_jukebox;
status = nfserr_jukebox;
@@ -1775,8 +1782,8 @@ nfsd4_create_session(struct svc_rqst *rqstp,
goto out_free_session;
nfs4_lock_state();
- unconf = find_unconfirmed_client(&cr_ses->clientid, true);
- conf = find_confirmed_client(&cr_ses->clientid, true);
+ unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn);
+ conf = find_confirmed_client(&cr_ses->clientid, true, nn);
if (conf) {
cs_slot = &conf->cl_cs_slot;
@@ -1789,7 +1796,6 @@ nfsd4_create_session(struct svc_rqst *rqstp,
goto out_free_conn;
}
} else if (unconf) {
- unsigned int hash;
struct nfs4_client *old;
if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) ||
!rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) {
@@ -1803,8 +1809,7 @@ nfsd4_create_session(struct svc_rqst *rqstp,
status = nfserr_seq_misordered;
goto out_free_conn;
}
- hash = clientstr_hashval(unconf->cl_recdir);
- old = find_confirmed_client_by_str(unconf->cl_recdir, hash);
+ old = find_confirmed_client_by_name(&unconf->cl_name, nn);
if (old)
expire_client(old);
move_to_confirmed(unconf);
@@ -1832,25 +1837,18 @@ nfsd4_create_session(struct svc_rqst *rqstp,
/* cache solo and embedded create sessions under the state lock */
nfsd4_cache_create_session(cr_ses, cs_slot, status);
-out:
nfs4_unlock_state();
+out:
dprintk("%s returns %d\n", __func__, ntohl(status));
return status;
out_free_conn:
+ nfs4_unlock_state();
free_conn(conn);
out_free_session:
__free_session(new);
goto out;
}
-static bool nfsd4_last_compound_op(struct svc_rqst *rqstp)
-{
- struct nfsd4_compoundres *resp = rqstp->rq_resp;
- struct nfsd4_compoundargs *argp = rqstp->rq_argp;
-
- return argp->opcnt == resp->opcnt;
-}
-
static __be32 nfsd4_map_bcts_dir(u32 *dir)
{
switch (*dir) {
@@ -1865,24 +1863,40 @@ static __be32 nfsd4_map_bcts_dir(u32 *dir)
return nfserr_inval;
}
+__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_backchannel_ctl *bc)
+{
+ struct nfsd4_session *session = cstate->session;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
+ session->se_cb_prog = bc->bc_cb_program;
+ session->se_cb_sec = bc->bc_cb_sec;
+ spin_unlock(&nn->client_lock);
+
+ nfsd4_probe_callback(session->se_client);
+
+ return nfs_ok;
+}
+
__be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
struct nfsd4_bind_conn_to_session *bcts)
{
__be32 status;
struct nfsd4_conn *conn;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
if (!nfsd4_last_compound_op(rqstp))
return nfserr_not_only_op;
- spin_lock(&client_lock);
- cstate->session = find_in_sessionid_hashtbl(&bcts->sessionid);
+ spin_lock(&nn->client_lock);
+ cstate->session = find_in_sessionid_hashtbl(&bcts->sessionid, SVC_NET(rqstp));
/* Sorta weird: we only need the refcnt'ing because new_conn acquires
* client_lock iself: */
if (cstate->session) {
nfsd4_get_session(cstate->session);
atomic_inc(&cstate->session->se_client->cl_refcount);
}
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
if (!cstate->session)
return nfserr_badsession;
@@ -1910,6 +1924,7 @@ nfsd4_destroy_session(struct svc_rqst *r,
{
struct nfsd4_session *ses;
__be32 status = nfserr_badsession;
+ struct nfsd_net *nn = net_generic(SVC_NET(r), nfsd_net_id);
/* Notes:
* - The confirmed nfs4_client->cl_sessionid holds destroyed sessinid
@@ -1923,24 +1938,24 @@ nfsd4_destroy_session(struct svc_rqst *r,
return nfserr_not_only_op;
}
dump_sessionid(__func__, &sessionid->sessionid);
- spin_lock(&client_lock);
- ses = find_in_sessionid_hashtbl(&sessionid->sessionid);
+ spin_lock(&nn->client_lock);
+ ses = find_in_sessionid_hashtbl(&sessionid->sessionid, SVC_NET(r));
if (!ses) {
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
goto out;
}
unhash_session(ses);
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
nfs4_lock_state();
nfsd4_probe_callback_sync(ses->se_client);
nfs4_unlock_state();
- spin_lock(&client_lock);
+ spin_lock(&nn->client_lock);
nfsd4_del_conns(ses);
nfsd4_put_session_locked(ses);
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
status = nfs_ok;
out:
dprintk("%s returns %d\n", __func__, ntohl(status));
@@ -2006,6 +2021,7 @@ nfsd4_sequence(struct svc_rqst *rqstp,
struct nfsd4_slot *slot;
struct nfsd4_conn *conn;
__be32 status;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
if (resp->opcnt != 1)
return nfserr_sequence_pos;
@@ -2018,9 +2034,9 @@ nfsd4_sequence(struct svc_rqst *rqstp,
if (!conn)
return nfserr_jukebox;
- spin_lock(&client_lock);
+ spin_lock(&nn->client_lock);
status = nfserr_badsession;
- session = find_in_sessionid_hashtbl(&seq->sessionid);
+ session = find_in_sessionid_hashtbl(&seq->sessionid, SVC_NET(rqstp));
if (!session)
goto out;
@@ -2094,7 +2110,7 @@ out:
}
}
kfree(conn);
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
dprintk("%s: return %d\n", __func__, ntohl(status));
return status;
}
@@ -2104,10 +2120,11 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
{
struct nfs4_client *conf, *unconf, *clp;
__be32 status = 0;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
nfs4_lock_state();
- unconf = find_unconfirmed_client(&dc->clientid, true);
- conf = find_confirmed_client(&dc->clientid, true);
+ unconf = find_unconfirmed_client(&dc->clientid, true, nn);
+ conf = find_confirmed_client(&dc->clientid, true, nn);
if (conf) {
clp = conf;
@@ -2181,20 +2198,13 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
struct xdr_netobj clname = setclid->se_name;
nfs4_verifier clverifier = setclid->se_verf;
- unsigned int strhashval;
struct nfs4_client *conf, *unconf, *new;
__be32 status;
- char dname[HEXDIR_LEN];
-
- status = nfs4_make_rec_clidname(dname, &clname);
- if (status)
- return status;
-
- strhashval = clientstr_hashval(dname);
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
/* Cases below refer to rfc 3530 section 14.2.33: */
nfs4_lock_state();
- conf = find_confirmed_client_by_str(dname, strhashval);
+ conf = find_confirmed_client_by_name(&clname, nn);
if (conf) {
/* case 0: */
status = nfserr_clid_inuse;
@@ -2209,21 +2219,21 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
}
}
- unconf = find_unconfirmed_client_by_str(dname, strhashval);
+ unconf = find_unconfirmed_client_by_name(&clname, nn);
if (unconf)
expire_client(unconf);
status = nfserr_jukebox;
- new = create_client(clname, dname, rqstp, &clverifier);
+ new = create_client(clname, rqstp, &clverifier);
if (new == NULL)
goto out;
if (conf && same_verf(&conf->cl_verifier, &clverifier))
/* case 1: probable callback update */
copy_clid(new, conf);
else /* case 4 (new client) or cases 2, 3 (client reboot): */
- gen_clid(new);
+ gen_clid(new, nn);
new->cl_minorversion = 0;
gen_callback(new, setclid, rqstp);
- add_to_unconfirmed(new, strhashval);
+ add_to_unconfirmed(new);
setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot;
setclid->se_clientid.cl_id = new->cl_clientid.cl_id;
memcpy(setclid->se_confirm.data, new->cl_confirm.data, sizeof(setclid->se_confirm.data));
@@ -2243,14 +2253,14 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
nfs4_verifier confirm = setclientid_confirm->sc_confirm;
clientid_t * clid = &setclientid_confirm->sc_clientid;
__be32 status;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
if (STALE_CLIENTID(clid, nn))
return nfserr_stale_clientid;
nfs4_lock_state();
- conf = find_confirmed_client(clid, false);
- unconf = find_unconfirmed_client(clid, false);
+ conf = find_confirmed_client(clid, false, nn);
+ unconf = find_unconfirmed_client(clid, false, nn);
/*
* We try hard to give out unique clientid's, so if we get an
* attempt to confirm the same clientid with a different cred,
@@ -2276,9 +2286,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
nfsd4_probe_callback(conf);
expire_client(unconf);
} else { /* case 3: normal case; new or rebooted client */
- unsigned int hash = clientstr_hashval(unconf->cl_recdir);
-
- conf = find_confirmed_client_by_str(unconf->cl_recdir, hash);
+ conf = find_confirmed_client_by_name(&unconf->cl_name, nn);
if (conf)
expire_client(conf);
move_to_confirmed(unconf);
@@ -2340,7 +2348,7 @@ nfsd4_init_slabs(void)
if (openowner_slab == NULL)
goto out_nomem;
lockowner_slab = kmem_cache_create("nfsd4_lockowners",
- sizeof(struct nfs4_openowner), 0, 0, NULL);
+ sizeof(struct nfs4_lockowner), 0, 0, NULL);
if (lockowner_slab == NULL)
goto out_nomem;
file_slab = kmem_cache_create("nfsd4_files",
@@ -2404,7 +2412,9 @@ static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj
static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, unsigned int strhashval)
{
- list_add(&oo->oo_owner.so_strhash, &ownerstr_hashtbl[strhashval]);
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ list_add(&oo->oo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
list_add(&oo->oo_perclient, &clp->cl_openowners);
}
@@ -2427,9 +2437,8 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
struct nfs4_openowner *oo = open->op_openowner;
- struct nfs4_client *clp = oo->oo_owner.so_client;
- init_stid(&stp->st_stid, clp, NFS4_OPEN_STID);
+ stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_lockowners);
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
list_add(&stp->st_perfile, &fp->fi_stateids);
@@ -2444,11 +2453,13 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
}
static void
-move_to_close_lru(struct nfs4_openowner *oo)
+move_to_close_lru(struct nfs4_openowner *oo, struct net *net)
{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
dprintk("NFSD: move_to_close_lru nfs4_openowner %p\n", oo);
- list_move_tail(&oo->oo_close_lru, &close_lru);
+ list_move_tail(&oo->oo_close_lru, &nn->close_lru);
oo->oo_time = get_seconds();
}
@@ -2462,13 +2473,14 @@ same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner,
}
static struct nfs4_openowner *
-find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, bool sessions)
+find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
+ bool sessions, struct nfsd_net *nn)
{
struct nfs4_stateowner *so;
struct nfs4_openowner *oo;
struct nfs4_client *clp;
- list_for_each_entry(so, &ownerstr_hashtbl[hashval], so_strhash) {
+ list_for_each_entry(so, &nn->ownerstr_hashtbl[hashval], so_strhash) {
if (!so->so_is_open_owner)
continue;
if (same_owner_str(so, &open->op_owner, &open->op_clientid)) {
@@ -2555,9 +2567,14 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
struct nfs4_file *fp = (struct nfs4_file *)fl->fl_owner;
struct nfs4_delegation *dp;
- BUG_ON(!fp);
- /* We assume break_lease is only called once per lease: */
- BUG_ON(fp->fi_had_conflict);
+ if (!fp) {
+ WARN(1, "(%p)->fl_owner NULL\n", fl);
+ return;
+ }
+ if (fp->fi_had_conflict) {
+ WARN(1, "duplicate break on %p\n", fp);
+ return;
+ }
/*
* We don't want the locks code to timeout the lease for us;
* we'll remove it ourself if a delegation isn't returned
@@ -2599,14 +2616,13 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4
__be32
nfsd4_process_open1(struct nfsd4_compound_state *cstate,
- struct nfsd4_open *open)
+ struct nfsd4_open *open, struct nfsd_net *nn)
{
clientid_t *clientid = &open->op_clientid;
struct nfs4_client *clp = NULL;
unsigned int strhashval;
struct nfs4_openowner *oo = NULL;
__be32 status;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
if (STALE_CLIENTID(&open->op_clientid, nn))
return nfserr_stale_clientid;
@@ -2619,10 +2635,11 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
return nfserr_jukebox;
strhashval = ownerstr_hashval(clientid->cl_id, &open->op_owner);
- oo = find_openstateowner_str(strhashval, open, cstate->minorversion);
+ oo = find_openstateowner_str(strhashval, open, cstate->minorversion, nn);
open->op_openowner = oo;
if (!oo) {
- clp = find_confirmed_client(clientid, cstate->minorversion);
+ clp = find_confirmed_client(clientid, cstate->minorversion,
+ nn);
if (clp == NULL)
return nfserr_expired;
goto new_owner;
@@ -2891,7 +2908,7 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
open->op_why_no_deleg = WND4_CANCELLED;
break;
case NFS4_SHARE_WANT_NO_DELEG:
- BUG(); /* not supposed to get here */
+ WARN_ON_ONCE(1);
}
}
}
@@ -2959,6 +2976,7 @@ out:
}
return;
out_free:
+ unhash_stid(&dp->dl_stid);
nfs4_put_delegation(dp);
out_no_deleg:
flag = NFS4_OPEN_DELEGATE_NONE;
@@ -3104,27 +3122,32 @@ void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status)
free_generic_stateid(open->op_stp);
}
+static __be32 lookup_clientid(clientid_t *clid, bool session, struct nfsd_net *nn, struct nfs4_client **clp)
+{
+ struct nfs4_client *found;
+
+ if (STALE_CLIENTID(clid, nn))
+ return nfserr_stale_clientid;
+ found = find_confirmed_client(clid, session, nn);
+ if (clp)
+ *clp = found;
+ return found ? nfs_ok : nfserr_expired;
+}
+
__be32
nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
clientid_t *clid)
{
struct nfs4_client *clp;
__be32 status;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
nfs4_lock_state();
dprintk("process_renew(%08x/%08x): starting\n",
clid->cl_boot, clid->cl_id);
- status = nfserr_stale_clientid;
- if (STALE_CLIENTID(clid, nn))
- goto out;
- clp = find_confirmed_client(clid, cstate->minorversion);
- status = nfserr_expired;
- if (clp == NULL) {
- /* We assume the client took too long to RENEW. */
- dprintk("nfsd4_renew: clientid not found!\n");
+ status = lookup_clientid(clid, cstate->minorversion, nn, &clp);
+ if (status)
goto out;
- }
status = nfserr_cb_path_down;
if (!list_empty(&clp->cl_delegations)
&& clp->cl_cb_state != NFSD4_CB_UP)
@@ -3136,44 +3159,42 @@ out:
}
static void
-nfsd4_end_grace(struct net *net)
+nfsd4_end_grace(struct nfsd_net *nn)
{
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-
/* do nothing if grace period already ended */
if (nn->grace_ended)
return;
dprintk("NFSD: end of grace period\n");
nn->grace_ended = true;
- nfsd4_record_grace_done(net, nn->boot_time);
+ nfsd4_record_grace_done(nn, nn->boot_time);
locks_end_grace(&nn->nfsd4_manager);
/*
* Now that every NFSv4 client has had the chance to recover and
* to see the (possibly new, possibly shorter) lease time, we
* can safely set the next grace time to the current lease time:
*/
- nfsd4_grace = nfsd4_lease;
+ nn->nfsd4_grace = nn->nfsd4_lease;
}
static time_t
-nfs4_laundromat(void)
+nfs4_laundromat(struct nfsd_net *nn)
{
struct nfs4_client *clp;
struct nfs4_openowner *oo;
struct nfs4_delegation *dp;
struct list_head *pos, *next, reaplist;
- time_t cutoff = get_seconds() - nfsd4_lease;
- time_t t, clientid_val = nfsd4_lease;
- time_t u, test_val = nfsd4_lease;
+ time_t cutoff = get_seconds() - nn->nfsd4_lease;
+ time_t t, clientid_val = nn->nfsd4_lease;
+ time_t u, test_val = nn->nfsd4_lease;
nfs4_lock_state();
dprintk("NFSD: laundromat service - starting\n");
- nfsd4_end_grace(&init_net);
+ nfsd4_end_grace(nn);
INIT_LIST_HEAD(&reaplist);
- spin_lock(&client_lock);
- list_for_each_safe(pos, next, &client_lru) {
+ spin_lock(&nn->client_lock);
+ list_for_each_safe(pos, next, &nn->client_lru) {
clp = list_entry(pos, struct nfs4_client, cl_lru);
if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) {
t = clp->cl_time - cutoff;
@@ -3189,7 +3210,7 @@ nfs4_laundromat(void)
unhash_client_locked(clp);
list_add(&clp->cl_lru, &reaplist);
}
- spin_unlock(&client_lock);
+ spin_unlock(&nn->client_lock);
list_for_each_safe(pos, next, &reaplist) {
clp = list_entry(pos, struct nfs4_client, cl_lru);
dprintk("NFSD: purging unused client (clientid %08x)\n",
@@ -3199,6 +3220,8 @@ nfs4_laundromat(void)
spin_lock(&recall_lock);
list_for_each_safe(pos, next, &del_recall_lru) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
+ if (net_generic(dp->dl_stid.sc_client->net, nfsd_net_id) != nn)
+ continue;
if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) {
u = dp->dl_time - cutoff;
if (test_val > u)
@@ -3212,8 +3235,8 @@ nfs4_laundromat(void)
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
unhash_delegation(dp);
}
- test_val = nfsd4_lease;
- list_for_each_safe(pos, next, &close_lru) {
+ test_val = nn->nfsd4_lease;
+ list_for_each_safe(pos, next, &nn->close_lru) {
oo = container_of(pos, struct nfs4_openowner, oo_close_lru);
if (time_after((unsigned long)oo->oo_time, (unsigned long)cutoff)) {
u = oo->oo_time - cutoff;
@@ -3231,16 +3254,19 @@ nfs4_laundromat(void)
static struct workqueue_struct *laundry_wq;
static void laundromat_main(struct work_struct *);
-static DECLARE_DELAYED_WORK(laundromat_work, laundromat_main);
static void
-laundromat_main(struct work_struct *not_used)
+laundromat_main(struct work_struct *laundry)
{
time_t t;
+ struct delayed_work *dwork = container_of(laundry, struct delayed_work,
+ work);
+ struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+ laundromat_work);
- t = nfs4_laundromat();
+ t = nfs4_laundromat(nn);
dprintk("NFSD: laundromat_main - sleeping for %ld seconds\n", t);
- queue_delayed_work(laundry_wq, &laundromat_work, t*HZ);
+ queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
}
static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp)
@@ -3385,16 +3411,17 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
return nfs_ok;
}
-static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, bool sessions)
+static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask,
+ struct nfs4_stid **s, bool sessions,
+ struct nfsd_net *nn)
{
struct nfs4_client *cl;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
return nfserr_bad_stateid;
if (STALE_STATEID(stateid, nn))
return nfserr_stale_stateid;
- cl = find_confirmed_client(&stateid->si_opaque.so_clid, sessions);
+ cl = find_confirmed_client(&stateid->si_opaque.so_clid, sessions, nn);
if (!cl)
return nfserr_expired;
*s = find_stateid_by_type(cl, stateid, typemask);
@@ -3416,6 +3443,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
struct nfs4_delegation *dp = NULL;
struct svc_fh *current_fh = &cstate->current_fh;
struct inode *ino = current_fh->fh_dentry->d_inode;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
__be32 status;
if (filpp)
@@ -3427,7 +3455,8 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
return check_special_stateids(net, current_fh, stateid, flags);
- status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s, cstate->minorversion);
+ status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
+ &s, cstate->minorversion, nn);
if (status)
return status;
status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate));
@@ -3441,7 +3470,11 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
goto out;
if (filpp) {
*filpp = dp->dl_file->fi_deleg_file;
- BUG_ON(!*filpp);
+ if (!*filpp) {
+ WARN_ON_ONCE(1);
+ status = nfserr_serverfault;
+ goto out;
+ }
}
break;
case NFS4_OPEN_STID:
@@ -3568,7 +3601,8 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
static __be32
nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
stateid_t *stateid, char typemask,
- struct nfs4_ol_stateid **stpp)
+ struct nfs4_ol_stateid **stpp,
+ struct nfsd_net *nn)
{
__be32 status;
struct nfs4_stid *s;
@@ -3577,7 +3611,8 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
seqid, STATEID_VAL(stateid));
*stpp = NULL;
- status = nfsd4_lookup_stateid(stateid, typemask, &s, cstate->minorversion);
+ status = nfsd4_lookup_stateid(stateid, typemask, &s,
+ cstate->minorversion, nn);
if (status)
return status;
*stpp = openlockstateid(s);
@@ -3586,13 +3621,14 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
return nfs4_seqid_op_checks(cstate, stateid, seqid, *stpp);
}
-static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, stateid_t *stateid, struct nfs4_ol_stateid **stpp)
+static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
+ stateid_t *stateid, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn)
{
__be32 status;
struct nfs4_openowner *oo;
status = nfs4_preprocess_seqid_op(cstate, seqid, stateid,
- NFS4_OPEN_STID, stpp);
+ NFS4_OPEN_STID, stpp, nn);
if (status)
return status;
oo = openowner((*stpp)->st_stateowner);
@@ -3608,6 +3644,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
__be32 status;
struct nfs4_openowner *oo;
struct nfs4_ol_stateid *stp;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
dprintk("NFSD: nfsd4_open_confirm on file %.*s\n",
(int)cstate->current_fh.fh_dentry->d_name.len,
@@ -3621,7 +3658,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfs4_preprocess_seqid_op(cstate,
oc->oc_seqid, &oc->oc_req_stateid,
- NFS4_OPEN_STID, &stp);
+ NFS4_OPEN_STID, &stp, nn);
if (status)
goto out;
oo = openowner(stp->st_stateowner);
@@ -3664,7 +3701,7 @@ static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_ac
case NFS4_SHARE_ACCESS_BOTH:
break;
default:
- BUG();
+ WARN_ON_ONCE(1);
}
}
@@ -3685,6 +3722,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
{
__be32 status;
struct nfs4_ol_stateid *stp;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
dprintk("NFSD: nfsd4_open_downgrade on file %.*s\n",
(int)cstate->current_fh.fh_dentry->d_name.len,
@@ -3697,7 +3735,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
nfs4_lock_state();
status = nfs4_preprocess_confirmed_seqid_op(cstate, od->od_seqid,
- &od->od_stateid, &stp);
+ &od->od_stateid, &stp, nn);
if (status)
goto out;
status = nfserr_inval;
@@ -3760,6 +3798,8 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
__be32 status;
struct nfs4_openowner *oo;
struct nfs4_ol_stateid *stp;
+ struct net *net = SVC_NET(rqstp);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
dprintk("NFSD: nfsd4_close on file %.*s\n",
(int)cstate->current_fh.fh_dentry->d_name.len,
@@ -3769,7 +3809,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid,
&close->cl_stateid,
NFS4_OPEN_STID|NFS4_CLOSED_STID,
- &stp);
+ &stp, nn);
if (status)
goto out;
oo = openowner(stp->st_stateowner);
@@ -3791,7 +3831,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
* little while to handle CLOSE replay.
*/
if (list_empty(&oo->oo_owner.so_stateids))
- move_to_close_lru(oo);
+ move_to_close_lru(oo, SVC_NET(rqstp));
}
}
out:
@@ -3807,15 +3847,15 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfs4_delegation *dp;
stateid_t *stateid = &dr->dr_stateid;
struct nfs4_stid *s;
- struct inode *inode;
__be32 status;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
return status;
- inode = cstate->current_fh.fh_dentry->d_inode;
nfs4_lock_state();
- status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID, &s, cstate->minorversion);
+ status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID, &s,
+ cstate->minorversion, nn);
if (status)
goto out;
dp = delegstateid(s);
@@ -3833,8 +3873,6 @@ out:
#define LOFF_OVERFLOW(start, len) ((u64)(len) > ~(u64)(start))
-#define LOCKOWNER_INO_HASH_BITS 8
-#define LOCKOWNER_INO_HASH_SIZE (1 << LOCKOWNER_INO_HASH_BITS)
#define LOCKOWNER_INO_HASH_MASK (LOCKOWNER_INO_HASH_SIZE - 1)
static inline u64
@@ -3852,7 +3890,7 @@ last_byte_offset(u64 start, u64 len)
{
u64 end;
- BUG_ON(!len);
+ WARN_ON_ONCE(!len);
end = start + len;
return end > start ? end - 1: NFS4_MAX_UINT64;
}
@@ -3864,8 +3902,6 @@ static unsigned int lockowner_ino_hashval(struct inode *inode, u32 cl_id, struct
& LOCKOWNER_INO_HASH_MASK;
}
-static struct list_head lockowner_ino_hashtbl[LOCKOWNER_INO_HASH_SIZE];
-
/*
* TODO: Linux file offsets are _signed_ 64-bit quantities, which means that
* we can't properly handle lock requests that go beyond the (2^63 - 1)-th
@@ -3931,12 +3967,12 @@ static bool same_lockowner_ino(struct nfs4_lockowner *lo, struct inode *inode, c
static struct nfs4_lockowner *
find_lockowner_str(struct inode *inode, clientid_t *clid,
- struct xdr_netobj *owner)
+ struct xdr_netobj *owner, struct nfsd_net *nn)
{
unsigned int hashval = lockowner_ino_hashval(inode, clid->cl_id, owner);
struct nfs4_lockowner *lo;
- list_for_each_entry(lo, &lockowner_ino_hashtbl[hashval], lo_owner_ino_hash) {
+ list_for_each_entry(lo, &nn->lockowner_ino_hashtbl[hashval], lo_owner_ino_hash) {
if (same_lockowner_ino(lo, inode, clid, owner))
return lo;
}
@@ -3948,9 +3984,10 @@ static void hash_lockowner(struct nfs4_lockowner *lo, unsigned int strhashval, s
struct inode *inode = open_stp->st_file->fi_inode;
unsigned int inohash = lockowner_ino_hashval(inode,
clp->cl_clientid.cl_id, &lo->lo_owner.so_owner);
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- list_add(&lo->lo_owner.so_strhash, &ownerstr_hashtbl[strhashval]);
- list_add(&lo->lo_owner_ino_hash, &lockowner_ino_hashtbl[inohash]);
+ list_add(&lo->lo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
+ list_add(&lo->lo_owner_ino_hash, &nn->lockowner_ino_hashtbl[inohash]);
list_add(&lo->lo_perstateid, &open_stp->st_lockowners);
}
@@ -3987,7 +4024,7 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
stp = nfs4_alloc_stateid(clp);
if (stp == NULL)
return NULL;
- init_stid(&stp->st_stid, clp, NFS4_LOCK_STID);
+ stp->st_stid.sc_type = NFS4_LOCK_STID;
list_add(&stp->st_perfile, &fp->fi_stateids);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
stp->st_stateowner = &lo->lo_owner;
@@ -4024,8 +4061,10 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, s
struct nfs4_client *cl = oo->oo_owner.so_client;
struct nfs4_lockowner *lo;
unsigned int strhashval;
+ struct nfsd_net *nn = net_generic(cl->net, nfsd_net_id);
- lo = find_lockowner_str(fi->fi_inode, &cl->cl_clientid, &lock->v.new.owner);
+ lo = find_lockowner_str(fi->fi_inode, &cl->cl_clientid,
+ &lock->v.new.owner, nn);
if (lo) {
if (!cstate->minorversion)
return nfserr_bad_seqid;
@@ -4065,7 +4104,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
bool new_state = false;
int lkflg;
int err;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct net *net = SVC_NET(rqstp);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
dprintk("NFSD: nfsd4_lock: start=%Ld length=%Ld\n",
(long long) lock->lk_offset,
@@ -4099,7 +4139,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfs4_preprocess_confirmed_seqid_op(cstate,
lock->lk_new_open_seqid,
&lock->lk_new_open_stateid,
- &open_stp);
+ &open_stp, nn);
if (status)
goto out;
open_sop = openowner(open_stp->st_stateowner);
@@ -4113,7 +4153,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfs4_preprocess_seqid_op(cstate,
lock->lk_old_lock_seqid,
&lock->lk_old_lock_stateid,
- NFS4_LOCK_STID, &lock_stp);
+ NFS4_LOCK_STID, &lock_stp, nn);
if (status)
goto out;
lock_sop = lockowner(lock_stp->st_stateowner);
@@ -4124,10 +4164,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
status = nfserr_grace;
- if (locks_in_grace(SVC_NET(rqstp)) && !lock->lk_reclaim)
+ if (locks_in_grace(net) && !lock->lk_reclaim)
goto out;
status = nfserr_no_grace;
- if (!locks_in_grace(SVC_NET(rqstp)) && lock->lk_reclaim)
+ if (!locks_in_grace(net) && lock->lk_reclaim)
goto out;
file_lock = locks_alloc_lock();
@@ -4238,7 +4278,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct file_lock *file_lock = NULL;
struct nfs4_lockowner *lo;
__be32 status;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
if (locks_in_grace(SVC_NET(rqstp)))
return nfserr_grace;
@@ -4248,9 +4288,11 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfs4_lock_state();
- status = nfserr_stale_clientid;
- if (!nfsd4_has_session(cstate) && STALE_CLIENTID(&lockt->lt_clientid, nn))
- goto out;
+ if (!nfsd4_has_session(cstate)) {
+ status = lookup_clientid(&lockt->lt_clientid, false, nn, NULL);
+ if (status)
+ goto out;
+ }
if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
goto out;
@@ -4278,7 +4320,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
}
- lo = find_lockowner_str(inode, &lockt->lt_clientid, &lockt->lt_owner);
+ lo = find_lockowner_str(inode, &lockt->lt_clientid, &lockt->lt_owner, nn);
if (lo)
file_lock->fl_owner = (fl_owner_t)lo;
file_lock->fl_pid = current->tgid;
@@ -4313,7 +4355,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct file_lock *file_lock = NULL;
__be32 status;
int err;
-
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
dprintk("NFSD: nfsd4_locku: start=%Ld length=%Ld\n",
(long long) locku->lu_offset,
(long long) locku->lu_length);
@@ -4324,7 +4367,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfs4_lock_state();
status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid,
- &locku->lu_stateid, NFS4_LOCK_STID, &stp);
+ &locku->lu_stateid, NFS4_LOCK_STID,
+ &stp, nn);
if (status)
goto out;
filp = find_any_file(stp->st_file);
@@ -4414,23 +4458,21 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
struct list_head matches;
unsigned int hashval = ownerstr_hashval(clid->cl_id, owner);
__be32 status;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
clid->cl_boot, clid->cl_id);
- /* XXX check for lease expiration */
-
- status = nfserr_stale_clientid;
- if (STALE_CLIENTID(clid, nn))
- return status;
-
nfs4_lock_state();
+ status = lookup_clientid(clid, cstate->minorversion, nn, NULL);
+ if (status)
+ goto out;
+
status = nfserr_locks_held;
INIT_LIST_HEAD(&matches);
- list_for_each_entry(sop, &ownerstr_hashtbl[hashval], so_strhash) {
+ list_for_each_entry(sop, &nn->ownerstr_hashtbl[hashval], so_strhash) {
if (sop->so_is_open_owner)
continue;
if (!same_owner_str(sop, owner, clid))
@@ -4466,73 +4508,74 @@ alloc_reclaim(void)
return kmalloc(sizeof(struct nfs4_client_reclaim), GFP_KERNEL);
}
-int
-nfs4_has_reclaimed_state(const char *name, bool use_exchange_id)
+bool
+nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn)
{
- unsigned int strhashval = clientstr_hashval(name);
- struct nfs4_client *clp;
+ struct nfs4_client_reclaim *crp;
- clp = find_confirmed_client_by_str(name, strhashval);
- if (!clp)
- return 0;
- return test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+ crp = nfsd4_find_reclaim_client(name, nn);
+ return (crp && crp->cr_clp);
}
/*
* failure => all reset bets are off, nfserr_no_grace...
*/
-int
-nfs4_client_to_reclaim(const char *name)
+struct nfs4_client_reclaim *
+nfs4_client_to_reclaim(const char *name, struct nfsd_net *nn)
{
unsigned int strhashval;
- struct nfs4_client_reclaim *crp = NULL;
+ struct nfs4_client_reclaim *crp;
dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", HEXDIR_LEN, name);
crp = alloc_reclaim();
- if (!crp)
- return 0;
- strhashval = clientstr_hashval(name);
- INIT_LIST_HEAD(&crp->cr_strhash);
- list_add(&crp->cr_strhash, &reclaim_str_hashtbl[strhashval]);
- memcpy(crp->cr_recdir, name, HEXDIR_LEN);
- reclaim_str_hashtbl_size++;
- return 1;
+ if (crp) {
+ strhashval = clientstr_hashval(name);
+ INIT_LIST_HEAD(&crp->cr_strhash);
+ list_add(&crp->cr_strhash, &nn->reclaim_str_hashtbl[strhashval]);
+ memcpy(crp->cr_recdir, name, HEXDIR_LEN);
+ crp->cr_clp = NULL;
+ nn->reclaim_str_hashtbl_size++;
+ }
+ return crp;
}
void
-nfs4_release_reclaim(void)
+nfs4_remove_reclaim_record(struct nfs4_client_reclaim *crp, struct nfsd_net *nn)
+{
+ list_del(&crp->cr_strhash);
+ kfree(crp);
+ nn->reclaim_str_hashtbl_size--;
+}
+
+void
+nfs4_release_reclaim(struct nfsd_net *nn)
{
struct nfs4_client_reclaim *crp = NULL;
int i;
for (i = 0; i < CLIENT_HASH_SIZE; i++) {
- while (!list_empty(&reclaim_str_hashtbl[i])) {
- crp = list_entry(reclaim_str_hashtbl[i].next,
+ while (!list_empty(&nn->reclaim_str_hashtbl[i])) {
+ crp = list_entry(nn->reclaim_str_hashtbl[i].next,
struct nfs4_client_reclaim, cr_strhash);
- list_del(&crp->cr_strhash);
- kfree(crp);
- reclaim_str_hashtbl_size--;
+ nfs4_remove_reclaim_record(crp, nn);
}
}
- BUG_ON(reclaim_str_hashtbl_size);
+ WARN_ON_ONCE(nn->reclaim_str_hashtbl_size);
}
/*
* called from OPEN, CLAIM_PREVIOUS with a new clientid. */
struct nfs4_client_reclaim *
-nfsd4_find_reclaim_client(struct nfs4_client *clp)
+nfsd4_find_reclaim_client(const char *recdir, struct nfsd_net *nn)
{
unsigned int strhashval;
struct nfs4_client_reclaim *crp = NULL;
- dprintk("NFSD: nfs4_find_reclaim_client for %.*s with recdir %s\n",
- clp->cl_name.len, clp->cl_name.data,
- clp->cl_recdir);
+ dprintk("NFSD: nfs4_find_reclaim_client for recdir %s\n", recdir);
- /* find clp->cl_name in reclaim_str_hashtbl */
- strhashval = clientstr_hashval(clp->cl_recdir);
- list_for_each_entry(crp, &reclaim_str_hashtbl[strhashval], cr_strhash) {
- if (same_name(crp->cr_recdir, clp->cl_recdir)) {
+ strhashval = clientstr_hashval(recdir);
+ list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) {
+ if (same_name(crp->cr_recdir, recdir)) {
return crp;
}
}
@@ -4543,12 +4586,12 @@ nfsd4_find_reclaim_client(struct nfs4_client *clp)
* Called from OPEN. Look for clientid in reclaim list.
*/
__be32
-nfs4_check_open_reclaim(clientid_t *clid, bool sessions)
+nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn)
{
struct nfs4_client *clp;
/* find clientid in conf_id_hashtbl */
- clp = find_confirmed_client(clid, sessions);
+ clp = find_confirmed_client(clid, sessions, nn);
if (clp == NULL)
return nfserr_reclaim_bad;
@@ -4557,124 +4600,177 @@ nfs4_check_open_reclaim(clientid_t *clid, bool sessions)
#ifdef CONFIG_NFSD_FAULT_INJECTION
-void nfsd_forget_clients(u64 num)
+u64 nfsd_forget_client(struct nfs4_client *clp, u64 max)
{
- struct nfs4_client *clp, *next;
- int count = 0;
-
- nfs4_lock_state();
- list_for_each_entry_safe(clp, next, &client_lru, cl_lru) {
- expire_client(clp);
- if (++count == num)
- break;
- }
- nfs4_unlock_state();
-
- printk(KERN_INFO "NFSD: Forgot %d clients", count);
+ expire_client(clp);
+ return 1;
}
-static void release_lockowner_sop(struct nfs4_stateowner *sop)
+u64 nfsd_print_client(struct nfs4_client *clp, u64 num)
{
- release_lockowner(lockowner(sop));
+ char buf[INET6_ADDRSTRLEN];
+ rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf));
+ printk(KERN_INFO "NFS Client: %s\n", buf);
+ return 1;
}
-static void release_openowner_sop(struct nfs4_stateowner *sop)
+static void nfsd_print_count(struct nfs4_client *clp, unsigned int count,
+ const char *type)
{
- release_openowner(openowner(sop));
+ char buf[INET6_ADDRSTRLEN];
+ rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf));
+ printk(KERN_INFO "NFS Client: %s has %u %s\n", buf, count, type);
}
-static int nfsd_release_n_owners(u64 num, bool is_open_owner,
- void (*release_sop)(struct nfs4_stateowner *))
+static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max, void (*func)(struct nfs4_lockowner *))
{
- int i, count = 0;
- struct nfs4_stateowner *sop, *next;
+ struct nfs4_openowner *oop;
+ struct nfs4_lockowner *lop, *lo_next;
+ struct nfs4_ol_stateid *stp, *st_next;
+ u64 count = 0;
- for (i = 0; i < OWNER_HASH_SIZE; i++) {
- list_for_each_entry_safe(sop, next, &ownerstr_hashtbl[i], so_strhash) {
- if (sop->so_is_open_owner != is_open_owner)
- continue;
- release_sop(sop);
- if (++count == num)
- return count;
+ list_for_each_entry(oop, &clp->cl_openowners, oo_perclient) {
+ list_for_each_entry_safe(stp, st_next, &oop->oo_owner.so_stateids, st_perstateowner) {
+ list_for_each_entry_safe(lop, lo_next, &stp->st_lockowners, lo_perstateid) {
+ if (func)
+ func(lop);
+ if (++count == max)
+ return count;
+ }
}
}
+
return count;
}
-void nfsd_forget_locks(u64 num)
+u64 nfsd_forget_client_locks(struct nfs4_client *clp, u64 max)
{
- int count;
-
- nfs4_lock_state();
- count = nfsd_release_n_owners(num, false, release_lockowner_sop);
- nfs4_unlock_state();
+ return nfsd_foreach_client_lock(clp, max, release_lockowner);
+}
- printk(KERN_INFO "NFSD: Forgot %d locks", count);
+u64 nfsd_print_client_locks(struct nfs4_client *clp, u64 max)
+{
+ u64 count = nfsd_foreach_client_lock(clp, max, NULL);
+ nfsd_print_count(clp, count, "locked files");
+ return count;
}
-void nfsd_forget_openowners(u64 num)
+static u64 nfsd_foreach_client_open(struct nfs4_client *clp, u64 max, void (*func)(struct nfs4_openowner *))
{
- int count;
+ struct nfs4_openowner *oop, *next;
+ u64 count = 0;
- nfs4_lock_state();
- count = nfsd_release_n_owners(num, true, release_openowner_sop);
- nfs4_unlock_state();
+ list_for_each_entry_safe(oop, next, &clp->cl_openowners, oo_perclient) {
+ if (func)
+ func(oop);
+ if (++count == max)
+ break;
+ }
- printk(KERN_INFO "NFSD: Forgot %d open owners", count);
+ return count;
}
-static int nfsd_process_n_delegations(u64 num, struct list_head *list)
+u64 nfsd_forget_client_openowners(struct nfs4_client *clp, u64 max)
{
- int i, count = 0;
- struct nfs4_file *fp, *fnext;
- struct nfs4_delegation *dp, *dnext;
+ return nfsd_foreach_client_open(clp, max, release_openowner);
+}
- for (i = 0; i < FILE_HASH_SIZE; i++) {
- list_for_each_entry_safe(fp, fnext, &file_hashtbl[i], fi_hash) {
- list_for_each_entry_safe(dp, dnext, &fp->fi_delegations, dl_perfile) {
- list_move(&dp->dl_recall_lru, list);
- if (++count == num)
- return count;
- }
- }
- }
+u64 nfsd_print_client_openowners(struct nfs4_client *clp, u64 max)
+{
+ u64 count = nfsd_foreach_client_open(clp, max, NULL);
+ nfsd_print_count(clp, count, "open files");
+ return count;
+}
+
+static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max,
+ struct list_head *victims)
+{
+ struct nfs4_delegation *dp, *next;
+ u64 count = 0;
+ list_for_each_entry_safe(dp, next, &clp->cl_delegations, dl_perclnt) {
+ if (victims)
+ list_move(&dp->dl_recall_lru, victims);
+ if (++count == max)
+ break;
+ }
return count;
}
-void nfsd_forget_delegations(u64 num)
+u64 nfsd_forget_client_delegations(struct nfs4_client *clp, u64 max)
{
- unsigned int count;
+ struct nfs4_delegation *dp, *next;
LIST_HEAD(victims);
- struct nfs4_delegation *dp, *dnext;
+ u64 count;
spin_lock(&recall_lock);
- count = nfsd_process_n_delegations(num, &victims);
+ count = nfsd_find_all_delegations(clp, max, &victims);
spin_unlock(&recall_lock);
- nfs4_lock_state();
- list_for_each_entry_safe(dp, dnext, &victims, dl_recall_lru)
+ list_for_each_entry_safe(dp, next, &victims, dl_recall_lru)
unhash_delegation(dp);
- nfs4_unlock_state();
- printk(KERN_INFO "NFSD: Forgot %d delegations", count);
+ return count;
}
-void nfsd_recall_delegations(u64 num)
+u64 nfsd_recall_client_delegations(struct nfs4_client *clp, u64 max)
{
- unsigned int count;
+ struct nfs4_delegation *dp, *next;
LIST_HEAD(victims);
- struct nfs4_delegation *dp, *dnext;
+ u64 count;
spin_lock(&recall_lock);
- count = nfsd_process_n_delegations(num, &victims);
- list_for_each_entry_safe(dp, dnext, &victims, dl_recall_lru) {
- list_del(&dp->dl_recall_lru);
+ count = nfsd_find_all_delegations(clp, max, &victims);
+ list_for_each_entry_safe(dp, next, &victims, dl_recall_lru)
nfsd_break_one_deleg(dp);
- }
spin_unlock(&recall_lock);
- printk(KERN_INFO "NFSD: Recalled %d delegations", count);
+ return count;
+}
+
+u64 nfsd_print_client_delegations(struct nfs4_client *clp, u64 max)
+{
+ u64 count = 0;
+
+ spin_lock(&recall_lock);
+ count = nfsd_find_all_delegations(clp, max, NULL);
+ spin_unlock(&recall_lock);
+
+ nfsd_print_count(clp, count, "delegations");
+ return count;
+}
+
+u64 nfsd_for_n_state(u64 max, u64 (*func)(struct nfs4_client *, u64))
+{
+ struct nfs4_client *clp, *next;
+ u64 count = 0;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, nfsd_net_id);
+
+ if (!nfsd_netns_ready(nn))
+ return 0;
+
+ list_for_each_entry_safe(clp, next, &nn->client_lru, cl_lru) {
+ count += func(clp, max - count);
+ if ((max != 0) && (count >= max))
+ break;
+ }
+
+ return count;
+}
+
+struct nfs4_client *nfsd_find_client(struct sockaddr_storage *addr, size_t addr_size)
+{
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, nfsd_net_id);
+
+ if (!nfsd_netns_ready(nn))
+ return NULL;
+
+ list_for_each_entry(clp, &nn->client_lru, cl_lru) {
+ if (memcmp(&clp->cl_addr, addr, addr_size) == 0)
+ return clp;
+ }
+ return NULL;
}
#endif /* CONFIG_NFSD_FAULT_INJECTION */
@@ -4686,27 +4782,10 @@ nfs4_state_init(void)
{
int i;
- for (i = 0; i < CLIENT_HASH_SIZE; i++) {
- INIT_LIST_HEAD(&conf_id_hashtbl[i]);
- INIT_LIST_HEAD(&conf_str_hashtbl[i]);
- INIT_LIST_HEAD(&unconf_str_hashtbl[i]);
- INIT_LIST_HEAD(&unconf_id_hashtbl[i]);
- INIT_LIST_HEAD(&reclaim_str_hashtbl[i]);
- }
- for (i = 0; i < SESSION_HASH_SIZE; i++)
- INIT_LIST_HEAD(&sessionid_hashtbl[i]);
for (i = 0; i < FILE_HASH_SIZE; i++) {
INIT_LIST_HEAD(&file_hashtbl[i]);
}
- for (i = 0; i < OWNER_HASH_SIZE; i++) {
- INIT_LIST_HEAD(&ownerstr_hashtbl[i]);
- }
- for (i = 0; i < LOCKOWNER_INO_HASH_SIZE; i++)
- INIT_LIST_HEAD(&lockowner_ino_hashtbl[i]);
- INIT_LIST_HEAD(&close_lru);
- INIT_LIST_HEAD(&client_lru);
INIT_LIST_HEAD(&del_recall_lru);
- reclaim_str_hashtbl_size = 0;
}
/*
@@ -4730,34 +4809,126 @@ set_max_delegations(void)
max_delegations = nr_free_buffer_pages() >> (20 - 2 - PAGE_SHIFT);
}
-/* initialization to perform when the nfsd service is started: */
+static int nfs4_state_create_net(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ int i;
+
+ nn->conf_id_hashtbl = kmalloc(sizeof(struct list_head) *
+ CLIENT_HASH_SIZE, GFP_KERNEL);
+ if (!nn->conf_id_hashtbl)
+ goto err;
+ nn->unconf_id_hashtbl = kmalloc(sizeof(struct list_head) *
+ CLIENT_HASH_SIZE, GFP_KERNEL);
+ if (!nn->unconf_id_hashtbl)
+ goto err_unconf_id;
+ nn->ownerstr_hashtbl = kmalloc(sizeof(struct list_head) *
+ OWNER_HASH_SIZE, GFP_KERNEL);
+ if (!nn->ownerstr_hashtbl)
+ goto err_ownerstr;
+ nn->lockowner_ino_hashtbl = kmalloc(sizeof(struct list_head) *
+ LOCKOWNER_INO_HASH_SIZE, GFP_KERNEL);
+ if (!nn->lockowner_ino_hashtbl)
+ goto err_lockowner_ino;
+ nn->sessionid_hashtbl = kmalloc(sizeof(struct list_head) *
+ SESSION_HASH_SIZE, GFP_KERNEL);
+ if (!nn->sessionid_hashtbl)
+ goto err_sessionid;
+
+ for (i = 0; i < CLIENT_HASH_SIZE; i++) {
+ INIT_LIST_HEAD(&nn->conf_id_hashtbl[i]);
+ INIT_LIST_HEAD(&nn->unconf_id_hashtbl[i]);
+ }
+ for (i = 0; i < OWNER_HASH_SIZE; i++)
+ INIT_LIST_HEAD(&nn->ownerstr_hashtbl[i]);
+ for (i = 0; i < LOCKOWNER_INO_HASH_SIZE; i++)
+ INIT_LIST_HEAD(&nn->lockowner_ino_hashtbl[i]);
+ for (i = 0; i < SESSION_HASH_SIZE; i++)
+ INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]);
+ nn->conf_name_tree = RB_ROOT;
+ nn->unconf_name_tree = RB_ROOT;
+ INIT_LIST_HEAD(&nn->client_lru);
+ INIT_LIST_HEAD(&nn->close_lru);
+ spin_lock_init(&nn->client_lock);
+
+ INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
+ get_net(net);
+
+ return 0;
+
+err_sessionid:
+ kfree(nn->lockowner_ino_hashtbl);
+err_lockowner_ino:
+ kfree(nn->ownerstr_hashtbl);
+err_ownerstr:
+ kfree(nn->unconf_id_hashtbl);
+err_unconf_id:
+ kfree(nn->conf_id_hashtbl);
+err:
+ return -ENOMEM;
+}
+
+static void
+nfs4_state_destroy_net(struct net *net)
+{
+ int i;
+ struct nfs4_client *clp = NULL;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct rb_node *node, *tmp;
+
+ for (i = 0; i < CLIENT_HASH_SIZE; i++) {
+ while (!list_empty(&nn->conf_id_hashtbl[i])) {
+ clp = list_entry(nn->conf_id_hashtbl[i].next, struct nfs4_client, cl_idhash);
+ destroy_client(clp);
+ }
+ }
+
+ node = rb_first(&nn->unconf_name_tree);
+ while (node != NULL) {
+ tmp = node;
+ node = rb_next(tmp);
+ clp = rb_entry(tmp, struct nfs4_client, cl_namenode);
+ rb_erase(tmp, &nn->unconf_name_tree);
+ destroy_client(clp);
+ }
+
+ kfree(nn->sessionid_hashtbl);
+ kfree(nn->lockowner_ino_hashtbl);
+ kfree(nn->ownerstr_hashtbl);
+ kfree(nn->unconf_id_hashtbl);
+ kfree(nn->conf_id_hashtbl);
+ put_net(net);
+}
int
-nfs4_state_start(void)
+nfs4_state_start_net(struct net *net)
{
- struct net *net = &init_net;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int ret;
- /*
- * FIXME: For now, we hang most of the pernet global stuff off of
- * init_net until nfsd is fully containerized. Eventually, we'll
- * need to pass a net pointer into this function, take a reference
- * to that instead and then do most of the rest of this on a per-net
- * basis.
- */
- get_net(net);
+ ret = nfs4_state_create_net(net);
+ if (ret)
+ return ret;
nfsd4_client_tracking_init(net);
nn->boot_time = get_seconds();
locks_start_grace(net, &nn->nfsd4_manager);
nn->grace_ended = false;
- printk(KERN_INFO "NFSD: starting %ld-second grace period\n",
- nfsd4_grace);
+ printk(KERN_INFO "NFSD: starting %ld-second grace period (net %p)\n",
+ nn->nfsd4_grace, net);
+ queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ);
+ return 0;
+}
+
+/* initialization to perform when the nfsd service is started: */
+
+int
+nfs4_state_start(void)
+{
+ int ret;
+
ret = set_callback_cred();
- if (ret) {
- ret = -ENOMEM;
- goto out_recovery;
- }
+ if (ret)
+ return -ENOMEM;
laundry_wq = create_singlethread_workqueue("nfsd4");
if (laundry_wq == NULL) {
ret = -ENOMEM;
@@ -4766,39 +4937,34 @@ nfs4_state_start(void)
ret = nfsd4_create_callback_queue();
if (ret)
goto out_free_laundry;
- queue_delayed_work(laundry_wq, &laundromat_work, nfsd4_grace * HZ);
+
set_max_delegations();
+
return 0;
+
out_free_laundry:
destroy_workqueue(laundry_wq);
out_recovery:
- nfsd4_client_tracking_exit(net);
- put_net(net);
return ret;
}
-static void
-__nfs4_state_shutdown(void)
+/* should be called with the state lock held */
+void
+nfs4_state_shutdown_net(struct net *net)
{
- int i;
- struct nfs4_client *clp = NULL;
struct nfs4_delegation *dp = NULL;
struct list_head *pos, *next, reaplist;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ cancel_delayed_work_sync(&nn->laundromat_work);
+ locks_end_grace(&nn->nfsd4_manager);
- for (i = 0; i < CLIENT_HASH_SIZE; i++) {
- while (!list_empty(&conf_id_hashtbl[i])) {
- clp = list_entry(conf_id_hashtbl[i].next, struct nfs4_client, cl_idhash);
- destroy_client(clp);
- }
- while (!list_empty(&unconf_str_hashtbl[i])) {
- clp = list_entry(unconf_str_hashtbl[i].next, struct nfs4_client, cl_strhash);
- destroy_client(clp);
- }
- }
INIT_LIST_HEAD(&reaplist);
spin_lock(&recall_lock);
list_for_each_safe(pos, next, &del_recall_lru) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
+ if (dp->dl_stid.sc_client->net != net)
+ continue;
list_move(&dp->dl_recall_lru, &reaplist);
}
spin_unlock(&recall_lock);
@@ -4807,22 +4973,14 @@ __nfs4_state_shutdown(void)
unhash_delegation(dp);
}
- nfsd4_client_tracking_exit(&init_net);
- put_net(&init_net);
+ nfsd4_client_tracking_exit(net);
+ nfs4_state_destroy_net(net);
}
void
nfs4_state_shutdown(void)
{
- struct net *net = &init_net;
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-
- cancel_delayed_work_sync(&laundromat_work);
destroy_workqueue(laundry_wq);
- locks_end_grace(&nn->nfsd4_manager);
- nfs4_lock_state();
- __nfs4_state_shutdown();
- nfs4_unlock_state();
nfsd4_destroy_callback_queue();
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index fd548d155088..01168865dd37 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -53,6 +53,7 @@
#include "vfs.h"
#include "state.h"
#include "cache.h"
+#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_XDR
@@ -65,17 +66,17 @@
#define NFS4_REFERRAL_FSID_MINOR 0x8000000ULL
static __be32
-check_filename(char *str, int len, __be32 err)
+check_filename(char *str, int len)
{
int i;
if (len == 0)
return nfserr_inval;
if (isdotent(str, len))
- return err;
+ return nfserr_badname;
for (i = 0; i < len; i++)
if (str[i] == '/')
- return err;
+ return nfserr_badname;
return 0;
}
@@ -292,13 +293,13 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
ace->whotype = nfs4_acl_get_whotype(buf, dummy32);
status = nfs_ok;
if (ace->whotype != NFS4_ACL_WHO_NAMED)
- ace->who = 0;
+ ;
else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
status = nfsd_map_name_to_gid(argp->rqstp,
- buf, dummy32, &ace->who);
+ buf, dummy32, &ace->who_gid);
else
status = nfsd_map_name_to_uid(argp->rqstp,
- buf, dummy32, &ace->who);
+ buf, dummy32, &ace->who_uid);
if (status)
return status;
}
@@ -422,6 +423,93 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access
DECODE_TAIL;
}
+static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs)
+{
+ DECODE_HEAD;
+ u32 dummy, uid, gid;
+ char *machine_name;
+ int i;
+ int nr_secflavs;
+
+ /* callback_sec_params4 */
+ READ_BUF(4);
+ READ32(nr_secflavs);
+ cbs->flavor = (u32)(-1);
+ for (i = 0; i < nr_secflavs; ++i) {
+ READ_BUF(4);
+ READ32(dummy);
+ switch (dummy) {
+ case RPC_AUTH_NULL:
+ /* Nothing to read */
+ if (cbs->flavor == (u32)(-1))
+ cbs->flavor = RPC_AUTH_NULL;
+ break;
+ case RPC_AUTH_UNIX:
+ READ_BUF(8);
+ /* stamp */
+ READ32(dummy);
+
+ /* machine name */
+ READ32(dummy);
+ READ_BUF(dummy);
+ SAVEMEM(machine_name, dummy);
+
+ /* uid, gid */
+ READ_BUF(8);
+ READ32(uid);
+ READ32(gid);
+
+ /* more gids */
+ READ_BUF(4);
+ READ32(dummy);
+ READ_BUF(dummy * 4);
+ if (cbs->flavor == (u32)(-1)) {
+ kuid_t kuid = make_kuid(&init_user_ns, uid);
+ kgid_t kgid = make_kgid(&init_user_ns, gid);
+ if (uid_valid(kuid) && gid_valid(kgid)) {
+ cbs->uid = kuid;
+ cbs->gid = kgid;
+ cbs->flavor = RPC_AUTH_UNIX;
+ } else {
+ dprintk("RPC_AUTH_UNIX with invalid"
+ "uid or gid ignoring!\n");
+ }
+ }
+ break;
+ case RPC_AUTH_GSS:
+ dprintk("RPC_AUTH_GSS callback secflavor "
+ "not supported!\n");
+ READ_BUF(8);
+ /* gcbp_service */
+ READ32(dummy);
+ /* gcbp_handle_from_server */
+ READ32(dummy);
+ READ_BUF(dummy);
+ p += XDR_QUADLEN(dummy);
+ /* gcbp_handle_from_client */
+ READ_BUF(4);
+ READ32(dummy);
+ READ_BUF(dummy);
+ break;
+ default:
+ dprintk("Illegal callback secflavor\n");
+ return nfserr_inval;
+ }
+ }
+ DECODE_TAIL;
+}
+
+static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc)
+{
+ DECODE_HEAD;
+
+ READ_BUF(4);
+ READ32(bc->bc_cb_program);
+ nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec);
+
+ DECODE_TAIL;
+}
+
static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts)
{
DECODE_HEAD;
@@ -490,7 +578,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
READ32(create->cr_namelen);
READ_BUF(create->cr_namelen);
SAVEMEM(create->cr_name, create->cr_namelen);
- if ((status = check_filename(create->cr_name, create->cr_namelen, nfserr_inval)))
+ if ((status = check_filename(create->cr_name, create->cr_namelen)))
return status;
status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr,
@@ -522,7 +610,7 @@ nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link)
READ32(link->li_namelen);
READ_BUF(link->li_namelen);
SAVEMEM(link->li_name, link->li_namelen);
- if ((status = check_filename(link->li_name, link->li_namelen, nfserr_inval)))
+ if ((status = check_filename(link->li_name, link->li_namelen)))
return status;
DECODE_TAIL;
@@ -616,7 +704,7 @@ nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup
READ32(lookup->lo_len);
READ_BUF(lookup->lo_len);
SAVEMEM(lookup->lo_name, lookup->lo_len);
- if ((status = check_filename(lookup->lo_name, lookup->lo_len, nfserr_noent)))
+ if ((status = check_filename(lookup->lo_name, lookup->lo_len)))
return status;
DECODE_TAIL;
@@ -780,7 +868,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
READ32(open->op_fname.len);
READ_BUF(open->op_fname.len);
SAVEMEM(open->op_fname.data, open->op_fname.len);
- if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval)))
+ if ((status = check_filename(open->op_fname.data, open->op_fname.len)))
return status;
break;
case NFS4_OPEN_CLAIM_PREVIOUS:
@@ -795,7 +883,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
READ32(open->op_fname.len);
READ_BUF(open->op_fname.len);
SAVEMEM(open->op_fname.data, open->op_fname.len);
- if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval)))
+ if ((status = check_filename(open->op_fname.data, open->op_fname.len)))
return status;
break;
case NFS4_OPEN_CLAIM_FH:
@@ -907,7 +995,7 @@ nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove
READ32(remove->rm_namelen);
READ_BUF(remove->rm_namelen);
SAVEMEM(remove->rm_name, remove->rm_namelen);
- if ((status = check_filename(remove->rm_name, remove->rm_namelen, nfserr_noent)))
+ if ((status = check_filename(remove->rm_name, remove->rm_namelen)))
return status;
DECODE_TAIL;
@@ -925,9 +1013,9 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename
READ32(rename->rn_tnamelen);
READ_BUF(rename->rn_tnamelen);
SAVEMEM(rename->rn_tname, rename->rn_tnamelen);
- if ((status = check_filename(rename->rn_sname, rename->rn_snamelen, nfserr_noent)))
+ if ((status = check_filename(rename->rn_sname, rename->rn_snamelen)))
return status;
- if ((status = check_filename(rename->rn_tname, rename->rn_tnamelen, nfserr_inval)))
+ if ((status = check_filename(rename->rn_tname, rename->rn_tnamelen)))
return status;
DECODE_TAIL;
@@ -954,8 +1042,7 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp,
READ32(secinfo->si_namelen);
READ_BUF(secinfo->si_namelen);
SAVEMEM(secinfo->si_name, secinfo->si_namelen);
- status = check_filename(secinfo->si_name, secinfo->si_namelen,
- nfserr_noent);
+ status = check_filename(secinfo->si_name, secinfo->si_namelen);
if (status)
return status;
DECODE_TAIL;
@@ -1026,31 +1113,14 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s
static __be32
nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify)
{
-#if 0
- struct nfsd4_compoundargs save = {
- .p = argp->p,
- .end = argp->end,
- .rqstp = argp->rqstp,
- };
- u32 ve_bmval[2];
- struct iattr ve_iattr; /* request */
- struct nfs4_acl *ve_acl; /* request */
-#endif
DECODE_HEAD;
if ((status = nfsd4_decode_bitmap(argp, verify->ve_bmval)))
goto out;
/* For convenience's sake, we compare raw xdr'd attributes in
- * nfsd4_proc_verify; however we still decode here just to return
- * correct error in case of bad xdr. */
-#if 0
- status = nfsd4_decode_fattr(ve_bmval, &ve_iattr, &ve_acl);
- if (status == nfserr_inval) {
- status = nfserrno(status);
- goto out;
- }
-#endif
+ * nfsd4_proc_verify */
+
READ_BUF(4);
READ32(verify->ve_attrlen);
READ_BUF(verify->ve_attrlen);
@@ -1063,7 +1133,6 @@ static __be32
nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
{
int avail;
- int v;
int len;
DECODE_HEAD;
@@ -1087,27 +1156,26 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
__FILE__, __LINE__);
goto xdr_error;
}
- argp->rqstp->rq_vec[0].iov_base = p;
- argp->rqstp->rq_vec[0].iov_len = avail;
- v = 0;
- len = write->wr_buflen;
- while (len > argp->rqstp->rq_vec[v].iov_len) {
- len -= argp->rqstp->rq_vec[v].iov_len;
- v++;
- argp->rqstp->rq_vec[v].iov_base = page_address(argp->pagelist[0]);
- argp->pagelist++;
- if (argp->pagelen >= PAGE_SIZE) {
- argp->rqstp->rq_vec[v].iov_len = PAGE_SIZE;
- argp->pagelen -= PAGE_SIZE;
- } else {
- argp->rqstp->rq_vec[v].iov_len = argp->pagelen;
- argp->pagelen -= len;
- }
+ write->wr_head.iov_base = p;
+ write->wr_head.iov_len = avail;
+ WARN_ON(avail != (XDR_QUADLEN(avail) << 2));
+ write->wr_pagelist = argp->pagelist;
+
+ len = XDR_QUADLEN(write->wr_buflen) << 2;
+ if (len >= avail) {
+ int pages;
+
+ len -= avail;
+
+ pages = len >> PAGE_SHIFT;
+ argp->pagelist += pages;
+ argp->pagelen -= pages * PAGE_SIZE;
+ len -= pages * PAGE_SIZE;
+
+ argp->p = (__be32 *)page_address(argp->pagelist[0]);
+ argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE);
}
- argp->end = (__be32*) (argp->rqstp->rq_vec[v].iov_base + argp->rqstp->rq_vec[v].iov_len);
- argp->p = (__be32*) (argp->rqstp->rq_vec[v].iov_base + (XDR_QUADLEN(len) << 2));
- argp->rqstp->rq_vec[v].iov_len = len;
- write->wr_vlen = v+1;
+ argp->p += XDR_QUADLEN(len);
DECODE_TAIL;
}
@@ -1237,11 +1305,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
struct nfsd4_create_session *sess)
{
DECODE_HEAD;
-
u32 dummy;
- char *machine_name;
- int i;
- int nr_secflavs;
READ_BUF(16);
COPYMEM(&sess->clientid, 8);
@@ -1282,58 +1346,9 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
goto xdr_error;
}
- READ_BUF(8);
+ READ_BUF(4);
READ32(sess->callback_prog);
-
- /* callback_sec_params4 */
- READ32(nr_secflavs);
- for (i = 0; i < nr_secflavs; ++i) {
- READ_BUF(4);
- READ32(dummy);
- switch (dummy) {
- case RPC_AUTH_NULL:
- /* Nothing to read */
- break;
- case RPC_AUTH_UNIX:
- READ_BUF(8);
- /* stamp */
- READ32(dummy);
-
- /* machine name */
- READ32(dummy);
- READ_BUF(dummy);
- SAVEMEM(machine_name, dummy);
-
- /* uid, gid */
- READ_BUF(8);
- READ32(sess->uid);
- READ32(sess->gid);
-
- /* more gids */
- READ_BUF(4);
- READ32(dummy);
- READ_BUF(dummy * 4);
- break;
- case RPC_AUTH_GSS:
- dprintk("RPC_AUTH_GSS callback secflavor "
- "not supported!\n");
- READ_BUF(8);
- /* gcbp_service */
- READ32(dummy);
- /* gcbp_handle_from_server */
- READ32(dummy);
- READ_BUF(dummy);
- p += XDR_QUADLEN(dummy);
- /* gcbp_handle_from_client */
- READ_BUF(4);
- READ32(dummy);
- READ_BUF(dummy);
- break;
- default:
- dprintk("Illegal callback secflavor\n");
- return nfserr_inval;
- }
- }
+ nfsd4_decode_cb_sec(argp, &sess->cb_sec);
DECODE_TAIL;
}
@@ -1528,7 +1543,7 @@ static nfsd4_dec nfsd41_dec_ops[] = {
[OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_notsupp,
/* new operations for NFSv4.1 */
- [OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_backchannel_ctl,
[OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session,
[OP_EXCHANGE_ID] = (nfsd4_dec)nfsd4_decode_exchange_id,
[OP_CREATE_SESSION] = (nfsd4_dec)nfsd4_decode_create_session,
@@ -1568,12 +1583,6 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
bool cachethis = false;
int i;
- /*
- * XXX: According to spec, we should check the tag
- * for UTF-8 compliance. I'm postponing this for
- * now because it seems that some clients do use
- * binary tags.
- */
READ_BUF(4);
READ32(argp->taglen);
READ_BUF(argp->taglen + 8);
@@ -1603,38 +1612,8 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
op = &argp->ops[i];
op->replay = NULL;
- /*
- * We can't use READ_BUF() here because we need to handle
- * a missing opcode as an OP_WRITE + 1. So we need to check
- * to see if we're truly at the end of our buffer or if there
- * is another page we need to flip to.
- */
-
- if (argp->p == argp->end) {
- if (argp->pagelen < 4) {
- /* There isn't an opcode still on the wire */
- op->opnum = OP_WRITE + 1;
- op->status = nfserr_bad_xdr;
- argp->opcnt = i+1;
- break;
- }
-
- /*
- * False alarm. We just hit a page boundary, but there
- * is still data available. Move pointer across page
- * boundary. *snip from READ_BUF*
- */
- argp->p = page_address(argp->pagelist[0]);
- argp->pagelist++;
- if (argp->pagelen < PAGE_SIZE) {
- argp->end = argp->p + (argp->pagelen>>2);
- argp->pagelen = 0;
- } else {
- argp->end = argp->p + (PAGE_SIZE>>2);
- argp->pagelen -= PAGE_SIZE;
- }
- }
- op->opnum = ntohl(*argp->p++);
+ READ_BUF(4);
+ READ32(op->opnum);
if (op->opnum >= FIRST_NFS4_OP && op->opnum <= LAST_NFS4_OP)
op->status = ops->decoders[op->opnum](argp, &op->u);
@@ -1954,7 +1933,7 @@ static u32 nfs4_file_type(umode_t mode)
}
static __be32
-nfsd4_encode_name(struct svc_rqst *rqstp, int whotype, uid_t id, int group,
+nfsd4_encode_name(struct svc_rqst *rqstp, int whotype, kuid_t uid, kgid_t gid,
__be32 **p, int *buflen)
{
int status;
@@ -1963,10 +1942,10 @@ nfsd4_encode_name(struct svc_rqst *rqstp, int whotype, uid_t id, int group,
return nfserr_resource;
if (whotype != NFS4_ACL_WHO_NAMED)
status = nfs4_acl_write_who(whotype, (u8 *)(*p + 1));
- else if (group)
- status = nfsd_map_gid_to_name(rqstp, id, (u8 *)(*p + 1));
+ else if (gid_valid(gid))
+ status = nfsd_map_gid_to_name(rqstp, gid, (u8 *)(*p + 1));
else
- status = nfsd_map_uid_to_name(rqstp, id, (u8 *)(*p + 1));
+ status = nfsd_map_uid_to_name(rqstp, uid, (u8 *)(*p + 1));
if (status < 0)
return nfserrno(status);
*p = xdr_encode_opaque(*p, NULL, status);
@@ -1976,22 +1955,33 @@ nfsd4_encode_name(struct svc_rqst *rqstp, int whotype, uid_t id, int group,
}
static inline __be32
-nfsd4_encode_user(struct svc_rqst *rqstp, uid_t uid, __be32 **p, int *buflen)
+nfsd4_encode_user(struct svc_rqst *rqstp, kuid_t user, __be32 **p, int *buflen)
{
- return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, uid, 0, p, buflen);
+ return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, user, INVALID_GID,
+ p, buflen);
}
static inline __be32
-nfsd4_encode_group(struct svc_rqst *rqstp, uid_t gid, __be32 **p, int *buflen)
+nfsd4_encode_group(struct svc_rqst *rqstp, kgid_t group, __be32 **p, int *buflen)
{
- return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, gid, 1, p, buflen);
+ return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, INVALID_UID, group,
+ p, buflen);
}
static inline __be32
-nfsd4_encode_aclname(struct svc_rqst *rqstp, int whotype, uid_t id, int group,
+nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace,
__be32 **p, int *buflen)
{
- return nfsd4_encode_name(rqstp, whotype, id, group, p, buflen);
+ kuid_t uid = INVALID_UID;
+ kgid_t gid = INVALID_GID;
+
+ if (ace->whotype == NFS4_ACL_WHO_NAMED) {
+ if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
+ gid = ace->who_gid;
+ else
+ uid = ace->who_uid;
+ }
+ return nfsd4_encode_name(rqstp, ace->whotype, uid, gid, p, buflen);
}
#define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
@@ -2014,16 +2004,31 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
return 0;
}
+
+static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
+{
+ struct path path = exp->ex_path;
+ int err;
+
+ path_get(&path);
+ while (follow_up(&path)) {
+ if (path.dentry != path.mnt->mnt_root)
+ break;
+ }
+ err = vfs_getattr(&path, stat);
+ path_put(&path);
+ return err;
+}
+
/*
* Note: @fhp can be NULL; in this case, we might have to compose the filehandle
* ourselves.
*
- * @countp is the buffer size in _words_; upon successful return this becomes
- * replaced with the number of words written.
+ * countp is the buffer size in _words_
*/
__be32
nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
- struct dentry *dentry, __be32 *buffer, int *countp, u32 *bmval,
+ struct dentry *dentry, __be32 **buffer, int count, u32 *bmval,
struct svc_rqst *rqstp, int ignore_crossmnt)
{
u32 bmval0 = bmval[0];
@@ -2032,12 +2037,12 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
struct kstat stat;
struct svc_fh tempfh;
struct kstatfs statfs;
- int buflen = *countp << 2;
+ int buflen = count << 2;
__be32 *attrlenp;
u32 dummy;
u64 dummy64;
u32 rdattr_err = 0;
- __be32 *p = buffer;
+ __be32 *p = *buffer;
__be32 status;
int err;
int aclsupport = 0;
@@ -2048,6 +2053,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
.mnt = exp->ex_path.mnt,
.dentry = dentry,
};
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1);
BUG_ON(bmval0 & ~nfsd_suppattrs0(minorversion));
@@ -2061,7 +2067,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
goto out;
}
- err = vfs_getattr(exp->ex_path.mnt, dentry, &stat);
+ err = vfs_getattr(&path, &stat);
if (err)
goto out_nfserr;
if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL |
@@ -2208,7 +2214,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
if (bmval0 & FATTR4_WORD0_LEASE_TIME) {
if ((buflen -= 4) < 0)
goto out_resource;
- WRITE32(nfsd4_lease);
+ WRITE32(nn->nfsd4_lease);
}
if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) {
if ((buflen -= 4) < 0)
@@ -2235,9 +2241,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
WRITE32(ace->type);
WRITE32(ace->flag);
WRITE32(ace->access_mask & NFS4_ACE_MASK_ALL);
- status = nfsd4_encode_aclname(rqstp, ace->whotype,
- ace->who, ace->flag & NFS4_ACE_IDENTIFIER_GROUP,
- &p, &buflen);
+ status = nfsd4_encode_aclname(rqstp, ace, &p, &buflen);
if (status == nfserr_resource)
goto out_resource;
if (status)
@@ -2430,18 +2434,8 @@ out_acl:
* and this is the root of a cross-mounted filesystem.
*/
if (ignore_crossmnt == 0 &&
- dentry == exp->ex_path.mnt->mnt_root) {
- struct path path = exp->ex_path;
- path_get(&path);
- while (follow_up(&path)) {
- if (path.dentry != path.mnt->mnt_root)
- break;
- }
- err = vfs_getattr(path.mnt, path.dentry, &stat);
- path_put(&path);
- if (err)
- goto out_nfserr;
- }
+ dentry == exp->ex_path.mnt->mnt_root)
+ get_parent_attributes(exp, &stat);
WRITE64(stat.ino);
}
if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
@@ -2452,7 +2446,7 @@ out_acl:
}
*attrlenp = htonl((char *)p - (char *)attrlenp - 4);
- *countp = p - buffer;
+ *buffer = p;
status = nfs_ok;
out:
@@ -2464,7 +2458,6 @@ out_nfserr:
status = nfserrno(err);
goto out;
out_resource:
- *countp = 0;
status = nfserr_resource;
goto out;
out_serverfault:
@@ -2483,7 +2476,7 @@ static inline int attributes_need_mount(u32 *bmval)
static __be32
nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
- const char *name, int namlen, __be32 *p, int *buflen)
+ const char *name, int namlen, __be32 **p, int buflen)
{
struct svc_export *exp = cd->rd_fhp->fh_export;
struct dentry *dentry;
@@ -2589,10 +2582,9 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */
p = xdr_encode_array(p, name, namlen); /* name length & name */
- nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, p, &buflen);
+ nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, &p, buflen);
switch (nfserr) {
case nfs_ok:
- p += buflen;
break;
case nfserr_resource:
nfserr = nfserr_toosmall;
@@ -2719,10 +2711,8 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2);
nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry,
- resp->p, &buflen, getattr->ga_bmval,
+ &resp->p, buflen, getattr->ga_bmval,
resp->rqstp, 0);
- if (!nfserr)
- resp->p += buflen;
return nfserr;
}
@@ -2927,7 +2917,8 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_read *read)
{
u32 eof;
- int v, pn;
+ int v;
+ struct page *page;
unsigned long maxcount;
long len;
__be32 *p;
@@ -2946,11 +2937,15 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
len = maxcount;
v = 0;
while (len > 0) {
- pn = resp->rqstp->rq_resused++;
- resp->rqstp->rq_vec[v].iov_base =
- page_address(resp->rqstp->rq_respages[pn]);
+ page = *(resp->rqstp->rq_next_page);
+ if (!page) { /* ran out of pages */
+ maxcount -= len;
+ break;
+ }
+ resp->rqstp->rq_vec[v].iov_base = page_address(page);
resp->rqstp->rq_vec[v].iov_len =
len < PAGE_SIZE ? len : PAGE_SIZE;
+ resp->rqstp->rq_next_page++;
v++;
len -= PAGE_SIZE;
}
@@ -2996,8 +2991,10 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
return nfserr;
if (resp->xbuf->page_len)
return nfserr_resource;
+ if (!*resp->rqstp->rq_next_page)
+ return nfserr_resource;
- page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]);
+ page = page_address(*(resp->rqstp->rq_next_page++));
maxcount = PAGE_SIZE;
RESERVE_SPACE(4);
@@ -3045,6 +3042,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
return nfserr;
if (resp->xbuf->page_len)
return nfserr_resource;
+ if (!*resp->rqstp->rq_next_page)
+ return nfserr_resource;
RESERVE_SPACE(NFS4_VERIFIER_SIZE);
savep = p;
@@ -3071,7 +3070,7 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
goto err_no_verf;
}
- page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]);
+ page = page_address(*(resp->rqstp->rq_next_page++));
readdir->common.err = 0;
readdir->buflen = maxcount;
readdir->buffer = page;
@@ -3094,8 +3093,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
p = readdir->buffer;
*p++ = 0; /* no more entries */
*p++ = htonl(readdir->common.err == nfserr_eof);
- resp->xbuf->page_len = ((char*)p) - (char*)page_address(
- resp->rqstp->rq_respages[resp->rqstp->rq_resused-1]);
+ resp->xbuf->page_len = ((char*)p) -
+ (char*)page_address(*(resp->rqstp->rq_next_page-1));
/* Use rest of head for padding and remaining ops: */
resp->xbuf->tail[0].iov_base = tailbase;
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 2cbac34a55da..62c1ee128aeb 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -9,22 +9,22 @@
*/
#include <linux/slab.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/highmem.h>
+#include <net/checksum.h>
#include "nfsd.h"
#include "cache.h"
-/* Size of reply cache. Common values are:
- * 4.3BSD: 128
- * 4.4BSD: 256
- * Solaris2: 1024
- * DEC Unix: 512-4096
- */
-#define CACHESIZE 1024
+#define NFSDDBG_FACILITY NFSDDBG_REPCACHE
+
#define HASHSIZE 64
static struct hlist_head * cache_hash;
static struct list_head lru_head;
-static int cache_disabled = 1;
+static struct kmem_cache *drc_slab;
+static unsigned int num_drc_entries;
+static unsigned int max_drc_entries;
/*
* Calculate the hash index from an XID.
@@ -37,6 +37,14 @@ static inline u32 request_hash(u32 xid)
}
static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
+static void cache_cleaner_func(struct work_struct *unused);
+static int nfsd_reply_cache_shrink(struct shrinker *shrink,
+ struct shrink_control *sc);
+
+struct shrinker nfsd_reply_cache_shrinker = {
+ .shrink = nfsd_reply_cache_shrink,
+ .seeks = 1,
+};
/*
* locking for the reply cache:
@@ -44,30 +52,86 @@ static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
* Otherwise, it when accessing _prev or _next, the lock must be held.
*/
static DEFINE_SPINLOCK(cache_lock);
+static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func);
-int nfsd_reply_cache_init(void)
+/*
+ * Put a cap on the size of the DRC based on the amount of available
+ * low memory in the machine.
+ *
+ * 64MB: 8192
+ * 128MB: 11585
+ * 256MB: 16384
+ * 512MB: 23170
+ * 1GB: 32768
+ * 2GB: 46340
+ * 4GB: 65536
+ * 8GB: 92681
+ * 16GB: 131072
+ *
+ * ...with a hard cap of 256k entries. In the worst case, each entry will be
+ * ~1k, so the above numbers should give a rough max of the amount of memory
+ * used in k.
+ */
+static unsigned int
+nfsd_cache_size_limit(void)
+{
+ unsigned int limit;
+ unsigned long low_pages = totalram_pages - totalhigh_pages;
+
+ limit = (16 * int_sqrt(low_pages)) << (PAGE_SHIFT-10);
+ return min_t(unsigned int, limit, 256*1024);
+}
+
+static struct svc_cacherep *
+nfsd_reply_cache_alloc(void)
{
struct svc_cacherep *rp;
- int i;
- INIT_LIST_HEAD(&lru_head);
- i = CACHESIZE;
- while (i) {
- rp = kmalloc(sizeof(*rp), GFP_KERNEL);
- if (!rp)
- goto out_nomem;
- list_add(&rp->c_lru, &lru_head);
+ rp = kmem_cache_alloc(drc_slab, GFP_KERNEL);
+ if (rp) {
rp->c_state = RC_UNUSED;
rp->c_type = RC_NOCACHE;
+ INIT_LIST_HEAD(&rp->c_lru);
INIT_HLIST_NODE(&rp->c_hash);
- i--;
}
+ return rp;
+}
+
+static void
+nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
+{
+ if (rp->c_type == RC_REPLBUFF)
+ kfree(rp->c_replvec.iov_base);
+ hlist_del(&rp->c_hash);
+ list_del(&rp->c_lru);
+ --num_drc_entries;
+ kmem_cache_free(drc_slab, rp);
+}
+
+static void
+nfsd_reply_cache_free(struct svc_cacherep *rp)
+{
+ spin_lock(&cache_lock);
+ nfsd_reply_cache_free_locked(rp);
+ spin_unlock(&cache_lock);
+}
+
+int nfsd_reply_cache_init(void)
+{
+ register_shrinker(&nfsd_reply_cache_shrinker);
+ drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep),
+ 0, 0, NULL);
+ if (!drc_slab)
+ goto out_nomem;
- cache_hash = kcalloc (HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
+ cache_hash = kcalloc(HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
if (!cache_hash)
goto out_nomem;
- cache_disabled = 0;
+ INIT_LIST_HEAD(&lru_head);
+ max_drc_entries = nfsd_cache_size_limit();
+ num_drc_entries = 0;
+
return 0;
out_nomem:
printk(KERN_ERR "nfsd: failed to allocate reply cache\n");
@@ -79,27 +143,33 @@ void nfsd_reply_cache_shutdown(void)
{
struct svc_cacherep *rp;
+ unregister_shrinker(&nfsd_reply_cache_shrinker);
+ cancel_delayed_work_sync(&cache_cleaner);
+
while (!list_empty(&lru_head)) {
rp = list_entry(lru_head.next, struct svc_cacherep, c_lru);
- if (rp->c_state == RC_DONE && rp->c_type == RC_REPLBUFF)
- kfree(rp->c_replvec.iov_base);
- list_del(&rp->c_lru);
- kfree(rp);
+ nfsd_reply_cache_free_locked(rp);
}
- cache_disabled = 1;
-
kfree (cache_hash);
cache_hash = NULL;
+
+ if (drc_slab) {
+ kmem_cache_destroy(drc_slab);
+ drc_slab = NULL;
+ }
}
/*
- * Move cache entry to end of LRU list
+ * Move cache entry to end of LRU list, and queue the cleaner to run if it's
+ * not already scheduled.
*/
static void
lru_put_end(struct svc_cacherep *rp)
{
+ rp->c_timestamp = jiffies;
list_move_tail(&rp->c_lru, &lru_head);
+ schedule_delayed_work(&cache_cleaner, RC_EXPIRE);
}
/*
@@ -112,83 +182,214 @@ hash_refile(struct svc_cacherep *rp)
hlist_add_head(&rp->c_hash, cache_hash + request_hash(rp->c_xid));
}
+static inline bool
+nfsd_cache_entry_expired(struct svc_cacherep *rp)
+{
+ return rp->c_state != RC_INPROG &&
+ time_after(jiffies, rp->c_timestamp + RC_EXPIRE);
+}
+
+/*
+ * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
+ * Also prune the oldest ones when the total exceeds the max number of entries.
+ */
+static void
+prune_cache_entries(void)
+{
+ struct svc_cacherep *rp, *tmp;
+
+ list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
+ if (!nfsd_cache_entry_expired(rp) &&
+ num_drc_entries <= max_drc_entries)
+ break;
+ nfsd_reply_cache_free_locked(rp);
+ }
+
+ /*
+ * Conditionally rearm the job. If we cleaned out the list, then
+ * cancel any pending run (since there won't be any work to do).
+ * Otherwise, we rearm the job or modify the existing one to run in
+ * RC_EXPIRE since we just ran the pruner.
+ */
+ if (list_empty(&lru_head))
+ cancel_delayed_work(&cache_cleaner);
+ else
+ mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
+}
+
+static void
+cache_cleaner_func(struct work_struct *unused)
+{
+ spin_lock(&cache_lock);
+ prune_cache_entries();
+ spin_unlock(&cache_lock);
+}
+
+static int
+nfsd_reply_cache_shrink(struct shrinker *shrink, struct shrink_control *sc)
+{
+ unsigned int num;
+
+ spin_lock(&cache_lock);
+ if (sc->nr_to_scan)
+ prune_cache_entries();
+ num = num_drc_entries;
+ spin_unlock(&cache_lock);
+
+ return num;
+}
+
+/*
+ * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
+ */
+static __wsum
+nfsd_cache_csum(struct svc_rqst *rqstp)
+{
+ int idx;
+ unsigned int base;
+ __wsum csum;
+ struct xdr_buf *buf = &rqstp->rq_arg;
+ const unsigned char *p = buf->head[0].iov_base;
+ size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len,
+ RC_CSUMLEN);
+ size_t len = min(buf->head[0].iov_len, csum_len);
+
+ /* rq_arg.head first */
+ csum = csum_partial(p, len, 0);
+ csum_len -= len;
+
+ /* Continue into page array */
+ idx = buf->page_base / PAGE_SIZE;
+ base = buf->page_base & ~PAGE_MASK;
+ while (csum_len) {
+ p = page_address(buf->pages[idx]) + base;
+ len = min_t(size_t, PAGE_SIZE - base, csum_len);
+ csum = csum_partial(p, len, csum);
+ csum_len -= len;
+ base = 0;
+ ++idx;
+ }
+ return csum;
+}
+
+/*
+ * Search the request hash for an entry that matches the given rqstp.
+ * Must be called with cache_lock held. Returns the found entry or
+ * NULL on failure.
+ */
+static struct svc_cacherep *
+nfsd_cache_search(struct svc_rqst *rqstp, __wsum csum)
+{
+ struct svc_cacherep *rp;
+ struct hlist_head *rh;
+ __be32 xid = rqstp->rq_xid;
+ u32 proto = rqstp->rq_prot,
+ vers = rqstp->rq_vers,
+ proc = rqstp->rq_proc;
+
+ rh = &cache_hash[request_hash(xid)];
+ hlist_for_each_entry(rp, rh, c_hash) {
+ if (xid == rp->c_xid && proc == rp->c_proc &&
+ proto == rp->c_prot && vers == rp->c_vers &&
+ rqstp->rq_arg.len == rp->c_len && csum == rp->c_csum &&
+ rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) &&
+ rpc_get_port(svc_addr(rqstp)) == rpc_get_port((struct sockaddr *)&rp->c_addr))
+ return rp;
+ }
+ return NULL;
+}
+
/*
* Try to find an entry matching the current call in the cache. When none
- * is found, we grab the oldest unlocked entry off the LRU list.
- * Note that no operation within the loop may sleep.
+ * is found, we try to grab the oldest expired entry off the LRU list. If
+ * a suitable one isn't there, then drop the cache_lock and allocate a
+ * new one, then search again in case one got inserted while this thread
+ * didn't hold the lock.
*/
int
nfsd_cache_lookup(struct svc_rqst *rqstp)
{
- struct hlist_node *hn;
- struct hlist_head *rh;
- struct svc_cacherep *rp;
+ struct svc_cacherep *rp, *found;
__be32 xid = rqstp->rq_xid;
u32 proto = rqstp->rq_prot,
vers = rqstp->rq_vers,
proc = rqstp->rq_proc;
+ __wsum csum;
unsigned long age;
int type = rqstp->rq_cachetype;
int rtn;
rqstp->rq_cacherep = NULL;
- if (cache_disabled || type == RC_NOCACHE) {
+ if (type == RC_NOCACHE) {
nfsdstats.rcnocache++;
return RC_DOIT;
}
+ csum = nfsd_cache_csum(rqstp);
+
spin_lock(&cache_lock);
rtn = RC_DOIT;
- rh = &cache_hash[request_hash(xid)];
- hlist_for_each_entry(rp, hn, rh, c_hash) {
- if (rp->c_state != RC_UNUSED &&
- xid == rp->c_xid && proc == rp->c_proc &&
- proto == rp->c_prot && vers == rp->c_vers &&
- time_before(jiffies, rp->c_timestamp + 120*HZ) &&
- memcmp((char*)&rqstp->rq_addr, (char*)&rp->c_addr, sizeof(rp->c_addr))==0) {
- nfsdstats.rchits++;
- goto found_entry;
+ rp = nfsd_cache_search(rqstp, csum);
+ if (rp)
+ goto found_entry;
+
+ /* Try to use the first entry on the LRU */
+ if (!list_empty(&lru_head)) {
+ rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
+ if (nfsd_cache_entry_expired(rp) ||
+ num_drc_entries >= max_drc_entries) {
+ lru_put_end(rp);
+ prune_cache_entries();
+ goto setup_entry;
}
}
- nfsdstats.rcmisses++;
- /* This loop shouldn't take more than a few iterations normally */
- {
- int safe = 0;
- list_for_each_entry(rp, &lru_head, c_lru) {
- if (rp->c_state != RC_INPROG)
- break;
- if (safe++ > CACHESIZE) {
- printk("nfsd: loop in repcache LRU list\n");
- cache_disabled = 1;
- goto out;
- }
+ /* Drop the lock and allocate a new entry */
+ spin_unlock(&cache_lock);
+ rp = nfsd_reply_cache_alloc();
+ if (!rp) {
+ dprintk("nfsd: unable to allocate DRC entry!\n");
+ return RC_DOIT;
}
+ spin_lock(&cache_lock);
+ ++num_drc_entries;
+
+ /*
+ * Must search again just in case someone inserted one
+ * after we dropped the lock above.
+ */
+ found = nfsd_cache_search(rqstp, csum);
+ if (found) {
+ nfsd_reply_cache_free_locked(rp);
+ rp = found;
+ goto found_entry;
}
- /* All entries on the LRU are in-progress. This should not happen */
- if (&rp->c_lru == &lru_head) {
- static int complaints;
-
- printk(KERN_WARNING "nfsd: all repcache entries locked!\n");
- if (++complaints > 5) {
- printk(KERN_WARNING "nfsd: disabling repcache.\n");
- cache_disabled = 1;
- }
- goto out;
- }
+ /*
+ * We're keeping the one we just allocated. Are we now over the
+ * limit? Prune one off the tip of the LRU in trade for the one we
+ * just allocated if so.
+ */
+ if (num_drc_entries >= max_drc_entries)
+ nfsd_reply_cache_free_locked(list_first_entry(&lru_head,
+ struct svc_cacherep, c_lru));
+setup_entry:
+ nfsdstats.rcmisses++;
rqstp->rq_cacherep = rp;
rp->c_state = RC_INPROG;
rp->c_xid = xid;
rp->c_proc = proc;
- memcpy(&rp->c_addr, svc_addr_in(rqstp), sizeof(rp->c_addr));
+ rpc_copy_addr((struct sockaddr *)&rp->c_addr, svc_addr(rqstp));
+ rpc_set_port((struct sockaddr *)&rp->c_addr, rpc_get_port(svc_addr(rqstp)));
rp->c_prot = proto;
rp->c_vers = vers;
- rp->c_timestamp = jiffies;
+ rp->c_len = rqstp->rq_arg.len;
+ rp->c_csum = csum;
hash_refile(rp);
+ lru_put_end(rp);
/* release any buffer */
if (rp->c_type == RC_REPLBUFF) {
@@ -201,9 +402,9 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
return rtn;
found_entry:
+ nfsdstats.rchits++;
/* We found a matching entry which is either in progress or done. */
age = jiffies - rp->c_timestamp;
- rp->c_timestamp = jiffies;
lru_put_end(rp);
rtn = RC_DROPIT;
@@ -232,7 +433,7 @@ found_entry:
break;
default:
printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type);
- rp->c_state = RC_UNUSED;
+ nfsd_reply_cache_free_locked(rp);
}
goto out;
@@ -257,11 +458,11 @@ found_entry:
void
nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
{
- struct svc_cacherep *rp;
+ struct svc_cacherep *rp = rqstp->rq_cacherep;
struct kvec *resv = &rqstp->rq_res.head[0], *cachv;
int len;
- if (!(rp = rqstp->rq_cacherep) || cache_disabled)
+ if (!rp)
return;
len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
@@ -269,7 +470,7 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
/* Don't cache excessive amounts of data and XDR failures */
if (!statp || len > (256 >> 2)) {
- rp->c_state = RC_UNUSED;
+ nfsd_reply_cache_free(rp);
return;
}
@@ -283,21 +484,21 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
cachv = &rp->c_replvec;
cachv->iov_base = kmalloc(len << 2, GFP_KERNEL);
if (!cachv->iov_base) {
- spin_lock(&cache_lock);
- rp->c_state = RC_UNUSED;
- spin_unlock(&cache_lock);
+ nfsd_reply_cache_free(rp);
return;
}
cachv->iov_len = len << 2;
memcpy(cachv->iov_base, statp, len << 2);
break;
+ case RC_NOCACHE:
+ nfsd_reply_cache_free(rp);
+ return;
}
spin_lock(&cache_lock);
lru_put_end(rp);
rp->c_secure = rqstp->rq_secure;
rp->c_type = cachetype;
rp->c_state = RC_DONE;
- rp->c_timestamp = jiffies;
spin_unlock(&cache_lock);
return;
}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index dab350dfc376..f33455b4d957 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -10,7 +10,7 @@
#include <linux/sunrpc/svcsock.h>
#include <linux/lockd/lockd.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/gss_api.h>
#include <linux/sunrpc/gss_krb5_enctypes.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
@@ -19,7 +19,7 @@
#include "idmap.h"
#include "nfsd.h"
#include "cache.h"
-#include "fault_inject.h"
+#include "state.h"
#include "netns.h"
/*
@@ -85,7 +85,7 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = {
static ssize_t nfsctl_transaction_write(struct file *file, const char __user *buf, size_t size, loff_t *pos)
{
- ino_t ino = file->f_path.dentry->d_inode->i_ino;
+ ino_t ino = file_inode(file)->i_ino;
char *data;
ssize_t rv;
@@ -125,11 +125,11 @@ static const struct file_operations transaction_ops = {
.llseek = default_llseek,
};
-static int exports_open(struct inode *inode, struct file *file)
+static int exports_net_open(struct net *net, struct file *file)
{
int err;
struct seq_file *seq;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
err = seq_open(file, &nfs_exports_op);
if (err)
@@ -140,8 +140,26 @@ static int exports_open(struct inode *inode, struct file *file)
return 0;
}
-static const struct file_operations exports_operations = {
- .open = exports_open,
+static int exports_proc_open(struct inode *inode, struct file *file)
+{
+ return exports_net_open(current->nsproxy->net_ns, file);
+}
+
+static const struct file_operations exports_proc_operations = {
+ .open = exports_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+ .owner = THIS_MODULE,
+};
+
+static int exports_nfsd_open(struct inode *inode, struct file *file)
+{
+ return exports_net_open(inode->i_sb->s_fs_info, file);
+}
+
+static const struct file_operations exports_nfsd_operations = {
+ .open = exports_nfsd_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
@@ -186,9 +204,6 @@ static struct file_operations supported_enctypes_ops = {
};
#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */
-extern int nfsd_pool_stats_open(struct inode *inode, struct file *file);
-extern int nfsd_pool_stats_release(struct inode *inode, struct file *file);
-
static const struct file_operations pool_stats_operations = {
.open = nfsd_pool_stats_open,
.read = seq_read,
@@ -223,6 +238,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
struct sockaddr *sap = (struct sockaddr *)&address;
size_t salen = sizeof(address);
char *fo_path;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
/* sanity check */
if (size == 0)
@@ -235,7 +251,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
if (qword_get(&buf, fo_path, size) < 0)
return -EINVAL;
- if (rpc_pton(&init_net, fo_path, size, sap, salen) == 0)
+ if (rpc_pton(net, fo_path, size, sap, salen) == 0)
return -EINVAL;
return nlmsvc_unlock_all_by_ip(sap);
@@ -320,6 +336,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
int len;
struct auth_domain *dom;
struct knfsd_fh fh;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
if (size == 0)
return -EINVAL;
@@ -355,7 +372,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
if (!dom)
return -ENOMEM;
- len = exp_rootfh(&init_net, dom, path, &fh, maxsize);
+ len = exp_rootfh(net, dom, path, &fh, maxsize);
auth_domain_put(dom);
if (len)
return len;
@@ -399,6 +416,8 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
{
char *mesg = buf;
int rv;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+
if (size > 0) {
int newthreads;
rv = get_int(&mesg, &newthreads);
@@ -406,11 +425,11 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
return rv;
if (newthreads < 0)
return -EINVAL;
- rv = nfsd_svc(newthreads);
+ rv = nfsd_svc(newthreads, net);
if (rv < 0)
return rv;
} else
- rv = nfsd_nrthreads();
+ rv = nfsd_nrthreads(net);
return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", rv);
}
@@ -448,9 +467,10 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
int len;
int npools;
int *nthreads;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
mutex_lock(&nfsd_mutex);
- npools = nfsd_nrpools();
+ npools = nfsd_nrpools(net);
if (npools == 0) {
/*
* NFS is shut down. The admin can start it by
@@ -478,12 +498,12 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
if (nthreads[i] < 0)
goto out_free;
}
- rv = nfsd_set_nrthreads(i, nthreads);
+ rv = nfsd_set_nrthreads(i, nthreads, net);
if (rv)
goto out_free;
}
- rv = nfsd_get_nrthreads(npools, nthreads);
+ rv = nfsd_get_nrthreads(npools, nthreads, net);
if (rv)
goto out_free;
@@ -510,11 +530,13 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
unsigned minor;
ssize_t tlen = 0;
char *sep;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (size>0) {
- if (nfsd_serv)
+ if (nn->nfsd_serv)
/* Cannot change versions without updating
- * nfsd_serv->sv_xdrsize, and reallocing
+ * nn->nfsd_serv->sv_xdrsize, and reallocing
* rq_argp and rq_resp
*/
return -EBUSY;
@@ -532,7 +554,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
else
num = simple_strtol(vers, &minorp, 0);
if (*minorp == '.') {
- if (num < 4)
+ if (num != 4)
return -EINVAL;
minor = simple_strtoul(minorp+1, NULL, 0);
if (minor == 0)
@@ -645,11 +667,13 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size)
* Zero-length write. Return a list of NFSD's current listener
* transports.
*/
-static ssize_t __write_ports_names(char *buf)
+static ssize_t __write_ports_names(char *buf, struct net *net)
{
- if (nfsd_serv == NULL)
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ if (nn->nfsd_serv == NULL)
return 0;
- return svc_xprt_names(nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT);
+ return svc_xprt_names(nn->nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT);
}
/*
@@ -657,28 +681,28 @@ static ssize_t __write_ports_names(char *buf)
* a socket of a supported family/protocol, and we use it as an
* nfsd listener.
*/
-static ssize_t __write_ports_addfd(char *buf)
+static ssize_t __write_ports_addfd(char *buf, struct net *net)
{
char *mesg = buf;
int fd, err;
- struct net *net = &init_net;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
err = get_int(&mesg, &fd);
if (err != 0 || fd < 0)
return -EINVAL;
- err = nfsd_create_serv();
+ err = nfsd_create_serv(net);
if (err != 0)
return err;
- err = svc_addsock(nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT);
+ err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT);
if (err < 0) {
nfsd_destroy(net);
return err;
}
/* Decrease the count, but don't shut down the service */
- nfsd_serv->sv_nrthreads--;
+ nn->nfsd_serv->sv_nrthreads--;
return err;
}
@@ -686,12 +710,12 @@ static ssize_t __write_ports_addfd(char *buf)
* A transport listener is added by writing it's transport name and
* a port number.
*/
-static ssize_t __write_ports_addxprt(char *buf)
+static ssize_t __write_ports_addxprt(char *buf, struct net *net)
{
char transport[16];
struct svc_xprt *xprt;
int port, err;
- struct net *net = &init_net;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (sscanf(buf, "%15s %5u", transport, &port) != 2)
return -EINVAL;
@@ -699,25 +723,25 @@ static ssize_t __write_ports_addxprt(char *buf)
if (port < 1 || port > USHRT_MAX)
return -EINVAL;
- err = nfsd_create_serv();
+ err = nfsd_create_serv(net);
if (err != 0)
return err;
- err = svc_create_xprt(nfsd_serv, transport, net,
+ err = svc_create_xprt(nn->nfsd_serv, transport, net,
PF_INET, port, SVC_SOCK_ANONYMOUS);
if (err < 0)
goto out_err;
- err = svc_create_xprt(nfsd_serv, transport, net,
+ err = svc_create_xprt(nn->nfsd_serv, transport, net,
PF_INET6, port, SVC_SOCK_ANONYMOUS);
if (err < 0 && err != -EAFNOSUPPORT)
goto out_close;
/* Decrease the count, but don't shut down the service */
- nfsd_serv->sv_nrthreads--;
+ nn->nfsd_serv->sv_nrthreads--;
return 0;
out_close:
- xprt = svc_find_xprt(nfsd_serv, transport, net, PF_INET, port);
+ xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port);
if (xprt != NULL) {
svc_close_xprt(xprt);
svc_xprt_put(xprt);
@@ -727,16 +751,17 @@ out_err:
return err;
}
-static ssize_t __write_ports(struct file *file, char *buf, size_t size)
+static ssize_t __write_ports(struct file *file, char *buf, size_t size,
+ struct net *net)
{
if (size == 0)
- return __write_ports_names(buf);
+ return __write_ports_names(buf, net);
if (isdigit(buf[0]))
- return __write_ports_addfd(buf);
+ return __write_ports_addfd(buf, net);
if (isalpha(buf[0]))
- return __write_ports_addxprt(buf);
+ return __write_ports_addxprt(buf, net);
return -EINVAL;
}
@@ -787,9 +812,10 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size)
static ssize_t write_ports(struct file *file, char *buf, size_t size)
{
ssize_t rv;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
mutex_lock(&nfsd_mutex);
- rv = __write_ports(file, buf, size);
+ rv = __write_ports(file, buf, size, net);
mutex_unlock(&nfsd_mutex);
return rv;
}
@@ -821,6 +847,9 @@ int nfsd_max_blksize;
static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
{
char *mesg = buf;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
if (size > 0) {
int bsize;
int rv = get_int(&mesg, &bsize);
@@ -835,7 +864,7 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
bsize = NFSSVC_MAXBLKSIZE;
bsize &= ~(1024-1);
mutex_lock(&nfsd_mutex);
- if (nfsd_serv) {
+ if (nn->nfsd_serv) {
mutex_unlock(&nfsd_mutex);
return -EBUSY;
}
@@ -848,13 +877,14 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
}
#ifdef CONFIG_NFSD_V4
-static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, time_t *time)
+static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size,
+ time_t *time, struct nfsd_net *nn)
{
char *mesg = buf;
int rv, i;
if (size > 0) {
- if (nfsd_serv)
+ if (nn->nfsd_serv)
return -EBUSY;
rv = get_int(&mesg, &i);
if (rv)
@@ -879,12 +909,13 @@ static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, tim
return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%ld\n", *time);
}
-static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, time_t *time)
+static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size,
+ time_t *time, struct nfsd_net *nn)
{
ssize_t rv;
mutex_lock(&nfsd_mutex);
- rv = __nfsd4_write_time(file, buf, size, time);
+ rv = __nfsd4_write_time(file, buf, size, time, nn);
mutex_unlock(&nfsd_mutex);
return rv;
}
@@ -912,7 +943,9 @@ static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, time_
*/
static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
{
- return nfsd4_write_time(file, buf, size, &nfsd4_lease);
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn);
}
/**
@@ -927,17 +960,20 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
*/
static ssize_t write_gracetime(struct file *file, char *buf, size_t size)
{
- return nfsd4_write_time(file, buf, size, &nfsd4_grace);
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
}
-static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size)
+static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
+ struct nfsd_net *nn)
{
char *mesg = buf;
char *recdir;
int len, status;
if (size > 0) {
- if (nfsd_serv)
+ if (nn->nfsd_serv)
return -EBUSY;
if (size > PATH_MAX || buf[size-1] != '\n')
return -EINVAL;
@@ -981,9 +1017,11 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size)
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
{
ssize_t rv;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
mutex_lock(&nfsd_mutex);
- rv = __write_recoverydir(file, buf, size);
+ rv = __write_recoverydir(file, buf, size, nn);
mutex_unlock(&nfsd_mutex);
return rv;
}
@@ -998,7 +1036,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
{
static struct tree_descr nfsd_files[] = {
- [NFSD_List] = {"exports", &exports_operations, S_IRUGO},
+ [NFSD_List] = {"exports", &exports_nfsd_operations, S_IRUGO},
[NFSD_Export_features] = {"export_features",
&export_features_operations, S_IRUGO},
[NFSD_FO_UnlockIP] = {"unlock_ip",
@@ -1022,21 +1060,37 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
#endif
/* last one */ {""}
};
- return simple_fill_super(sb, 0x6e667364, nfsd_files);
+ struct net *net = data;
+ int ret;
+
+ ret = simple_fill_super(sb, 0x6e667364, nfsd_files);
+ if (ret)
+ return ret;
+ sb->s_fs_info = get_net(net);
+ return 0;
}
static struct dentry *nfsd_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
- return mount_single(fs_type, flags, data, nfsd_fill_super);
+ return mount_ns(fs_type, flags, current->nsproxy->net_ns, nfsd_fill_super);
+}
+
+static void nfsd_umount(struct super_block *sb)
+{
+ struct net *net = sb->s_fs_info;
+
+ kill_litter_super(sb);
+ put_net(net);
}
static struct file_system_type nfsd_fs_type = {
.owner = THIS_MODULE,
.name = "nfsd",
.mount = nfsd_mount,
- .kill_sb = kill_litter_super,
+ .kill_sb = nfsd_umount,
};
+MODULE_ALIAS_FS("nfsd");
#ifdef CONFIG_PROC_FS
static int create_proc_exports_entry(void)
@@ -1046,7 +1100,8 @@ static int create_proc_exports_entry(void)
entry = proc_mkdir("fs/nfs", NULL);
if (!entry)
return -ENOMEM;
- entry = proc_create("exports", 0, entry, &exports_operations);
+ entry = proc_create("exports", 0, entry,
+ &exports_proc_operations);
if (!entry)
return -ENOMEM;
return 0;
@@ -1063,6 +1118,7 @@ int nfsd_net_id;
static __net_init int nfsd_init_net(struct net *net)
{
int retval;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
retval = nfsd_export_init(net);
if (retval)
@@ -1070,6 +1126,8 @@ static __net_init int nfsd_init_net(struct net *net)
retval = nfsd_idmap_init(net);
if (retval)
goto out_idmap_error;
+ nn->nfsd4_lease = 90; /* default lease time */
+ nn->nfsd4_grace = 90;
return 0;
out_idmap_error:
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 80d5ce40aadb..07a473fd49bc 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -55,36 +55,26 @@ extern struct svc_version nfsd_version2, nfsd_version3,
nfsd_version4;
extern u32 nfsd_supported_minorversion;
extern struct mutex nfsd_mutex;
-extern struct svc_serv *nfsd_serv;
extern spinlock_t nfsd_drc_lock;
-extern unsigned int nfsd_drc_max_mem;
-extern unsigned int nfsd_drc_mem_used;
+extern unsigned long nfsd_drc_max_mem;
+extern unsigned long nfsd_drc_mem_used;
extern const struct seq_operations nfs_exports_op;
/*
* Function prototypes.
*/
-int nfsd_svc(int nrservs);
+int nfsd_svc(int nrservs, struct net *net);
int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp);
-int nfsd_nrthreads(void);
-int nfsd_nrpools(void);
-int nfsd_get_nrthreads(int n, int *);
-int nfsd_set_nrthreads(int n, int *);
+int nfsd_nrthreads(struct net *);
+int nfsd_nrpools(struct net *);
+int nfsd_get_nrthreads(int n, int *, struct net *);
+int nfsd_set_nrthreads(int n, int *, struct net *);
int nfsd_pool_stats_open(struct inode *, struct file *);
int nfsd_pool_stats_release(struct inode *, struct file *);
-static inline void nfsd_destroy(struct net *net)
-{
- int destroy = (nfsd_serv->sv_nrthreads == 1);
-
- if (destroy)
- svc_shutdown_net(nfsd_serv, net);
- svc_destroy(nfsd_serv);
- if (destroy)
- nfsd_serv = NULL;
-}
+void nfsd_destroy(struct net *net);
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
#ifdef CONFIG_NFSD_V2_ACL
@@ -103,7 +93,7 @@ enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL };
int nfsd_vers(int vers, enum vers_op change);
int nfsd_minorversion(u32 minorversion, enum vers_op change);
void nfsd_reset_versions(void);
-int nfsd_create_serv(void);
+int nfsd_create_serv(struct net *net);
extern int nfsd_max_blksize;
@@ -116,12 +106,14 @@ static inline int nfsd_v4client(struct svc_rqst *rq)
* NFSv4 State
*/
#ifdef CONFIG_NFSD_V4
-extern unsigned int max_delegations;
+extern unsigned long max_delegations;
void nfs4_state_init(void);
int nfsd4_init_slabs(void);
void nfsd4_free_slabs(void);
int nfs4_state_start(void);
+int nfs4_state_start_net(struct net *net);
void nfs4_state_shutdown(void);
+void nfs4_state_shutdown_net(struct net *net);
void nfs4_reset_lease(time_t leasetime);
int nfs4_reset_recoverydir(char *recdir);
char * nfs4_recoverydir(void);
@@ -130,7 +122,9 @@ static inline void nfs4_state_init(void) { }
static inline int nfsd4_init_slabs(void) { return 0; }
static inline void nfsd4_free_slabs(void) { }
static inline int nfs4_state_start(void) { return 0; }
+static inline int nfs4_state_start_net(struct net *net) { return 0; }
static inline void nfs4_state_shutdown(void) { }
+static inline void nfs4_state_shutdown_net(struct net *net) { }
static inline void nfs4_reset_lease(time_t leasetime) { }
static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
static inline char * nfs4_recoverydir(void) {return NULL; }
@@ -265,16 +259,8 @@ void nfsd_lockd_shutdown(void);
/* Check for dir entries '.' and '..' */
#define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.'))
-/*
- * Time of server startup
- */
-extern struct timeval nfssvc_boot;
-
#ifdef CONFIG_NFSD_V4
-extern time_t nfsd4_lease;
-extern time_t nfsd4_grace;
-
/* before processing a COMPOUND operation, we have to check that there
* is enough space in the buffer for XDR encode to succeed. otherwise,
* we might process an operation with side effects, and be unable to
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 032af381b3aa..814afaa4458a 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -572,7 +572,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
if (inode)
_fh_update(fhp, exp, dentry);
- if (fhp->fh_handle.fh_fileid_type == 255) {
+ if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
fh_put(fhp);
return nfserr_opnotsupp;
}
@@ -603,7 +603,7 @@ fh_update(struct svc_fh *fhp)
goto out;
_fh_update(fhp, fhp->fh_export, dentry);
- if (fhp->fh_handle.fh_fileid_type == 255)
+ if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
return nfserr_opnotsupp;
}
out:
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index aad6d457b9e8..54c6b3d3cc79 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -26,17 +26,13 @@ static __be32
nfsd_return_attrs(__be32 err, struct nfsd_attrstat *resp)
{
if (err) return err;
- return nfserrno(vfs_getattr(resp->fh.fh_export->ex_path.mnt,
- resp->fh.fh_dentry,
- &resp->stat));
+ return fh_getattr(&resp->fh, &resp->stat);
}
static __be32
nfsd_return_dirop(__be32 err, struct nfsd_diropres *resp)
{
if (err) return err;
- return nfserrno(vfs_getattr(resp->fh.fh_export->ex_path.mnt,
- resp->fh.fh_dentry,
- &resp->stat));
+ return fh_getattr(&resp->fh, &resp->stat);
}
/*
* Get a file's attributes
@@ -150,9 +146,7 @@ nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp,
&resp->count);
if (nfserr) return nfserr;
- return nfserrno(vfs_getattr(resp->fh.fh_export->ex_path.mnt,
- resp->fh.fh_dentry,
- &resp->stat));
+ return fh_getattr(&resp->fh, &resp->stat);
}
/*
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 2013aa001dab..262df5ccbf59 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -11,7 +11,6 @@
#include <linux/module.h>
#include <linux/fs_struct.h>
#include <linux/swap.h>
-#include <linux/nsproxy.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/svcsock.h>
@@ -22,19 +21,19 @@
#include "nfsd.h"
#include "cache.h"
#include "vfs.h"
+#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_SVC
extern struct svc_program nfsd_program;
static int nfsd(void *vrqstp);
-struct timeval nfssvc_boot;
/*
- * nfsd_mutex protects nfsd_serv -- both the pointer itself and the members
+ * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members
* of the svc_serv struct. In particular, ->sv_nrthreads but also to some
* extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt
*
- * If (out side the lock) nfsd_serv is non-NULL, then it must point to a
+ * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
* properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number
* of nfsd threads must exist and each must listed in ->sp_all_threads in each
* entry of ->sv_pools[].
@@ -52,7 +51,6 @@ struct timeval nfssvc_boot;
* nfsd_versions
*/
DEFINE_MUTEX(nfsd_mutex);
-struct svc_serv *nfsd_serv;
/*
* nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used.
@@ -61,8 +59,8 @@ struct svc_serv *nfsd_serv;
* nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
*/
spinlock_t nfsd_drc_lock;
-unsigned int nfsd_drc_max_mem;
-unsigned int nfsd_drc_mem_used;
+unsigned long nfsd_drc_max_mem;
+unsigned long nfsd_drc_mem_used;
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
static struct svc_stat nfsd_acl_svcstats;
@@ -173,28 +171,32 @@ int nfsd_minorversion(u32 minorversion, enum vers_op change)
*/
#define NFSD_MAXSERVS 8192
-int nfsd_nrthreads(void)
+int nfsd_nrthreads(struct net *net)
{
int rv = 0;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
mutex_lock(&nfsd_mutex);
- if (nfsd_serv)
- rv = nfsd_serv->sv_nrthreads;
+ if (nn->nfsd_serv)
+ rv = nn->nfsd_serv->sv_nrthreads;
mutex_unlock(&nfsd_mutex);
return rv;
}
-static int nfsd_init_socks(void)
+static int nfsd_init_socks(struct net *net)
{
int error;
- if (!list_empty(&nfsd_serv->sv_permsocks))
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ if (!list_empty(&nn->nfsd_serv->sv_permsocks))
return 0;
- error = svc_create_xprt(nfsd_serv, "udp", &init_net, PF_INET, NFS_PORT,
+ error = svc_create_xprt(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT,
SVC_SOCK_DEFAULTS);
if (error < 0)
return error;
- error = svc_create_xprt(nfsd_serv, "tcp", &init_net, PF_INET, NFS_PORT,
+ error = svc_create_xprt(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT,
SVC_SOCK_DEFAULTS);
if (error < 0)
return error;
@@ -202,14 +204,15 @@ static int nfsd_init_socks(void)
return 0;
}
-static bool nfsd_up = false;
+static int nfsd_users = 0;
-static int nfsd_startup(int nrservs)
+static int nfsd_startup_generic(int nrservs)
{
int ret;
- if (nfsd_up)
+ if (nfsd_users++)
return 0;
+
/*
* Readahead param cache - will no-op if it already exists.
* (Note therefore results will be suboptimal if number of
@@ -218,43 +221,79 @@ static int nfsd_startup(int nrservs)
ret = nfsd_racache_init(2*nrservs);
if (ret)
return ret;
- ret = nfsd_init_socks();
+ ret = nfs4_state_start();
if (ret)
goto out_racache;
- ret = lockd_up(&init_net);
+ return 0;
+
+out_racache:
+ nfsd_racache_shutdown();
+ return ret;
+}
+
+static void nfsd_shutdown_generic(void)
+{
+ if (--nfsd_users)
+ return;
+
+ nfs4_state_shutdown();
+ nfsd_racache_shutdown();
+}
+
+static int nfsd_startup_net(int nrservs, struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ int ret;
+
+ if (nn->nfsd_net_up)
+ return 0;
+
+ ret = nfsd_startup_generic(nrservs);
if (ret)
- goto out_racache;
- ret = nfs4_state_start();
+ return ret;
+ ret = nfsd_init_socks(net);
+ if (ret)
+ goto out_socks;
+ ret = lockd_up(net);
+ if (ret)
+ goto out_socks;
+ ret = nfs4_state_start_net(net);
if (ret)
goto out_lockd;
- nfsd_up = true;
+
+ nn->nfsd_net_up = true;
return 0;
+
out_lockd:
- lockd_down(&init_net);
-out_racache:
- nfsd_racache_shutdown();
+ lockd_down(net);
+out_socks:
+ nfsd_shutdown_generic();
return ret;
}
-static void nfsd_shutdown(void)
+static void nfsd_shutdown_net(struct net *net)
{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ nfs4_state_shutdown_net(net);
+ lockd_down(net);
+ nn->nfsd_net_up = false;
+ nfsd_shutdown_generic();
+}
+
+static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
/*
* write_ports can create the server without actually starting
* any threads--if we get shut down before any threads are
* started, then nfsd_last_thread will be run before any of this
* other initialization has been done.
*/
- if (!nfsd_up)
+ if (!nn->nfsd_net_up)
return;
- nfs4_state_shutdown();
- lockd_down(&init_net);
- nfsd_racache_shutdown();
- nfsd_up = false;
-}
-
-static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
-{
- nfsd_shutdown();
+ nfsd_shutdown_net(net);
svc_rpcb_cleanup(serv, net);
@@ -303,7 +342,7 @@ static void set_max_drc(void)
>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
nfsd_drc_mem_used = 0;
spin_lock_init(&nfsd_drc_lock);
- dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
+ dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem);
}
static int nfsd_get_default_max_blksize(void)
@@ -327,69 +366,84 @@ static int nfsd_get_default_max_blksize(void)
return ret;
}
-int nfsd_create_serv(void)
+int nfsd_create_serv(struct net *net)
{
int error;
- struct net *net = current->nsproxy->net_ns;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
WARN_ON(!mutex_is_locked(&nfsd_mutex));
- if (nfsd_serv) {
- svc_get(nfsd_serv);
+ if (nn->nfsd_serv) {
+ svc_get(nn->nfsd_serv);
return 0;
}
if (nfsd_max_blksize == 0)
nfsd_max_blksize = nfsd_get_default_max_blksize();
nfsd_reset_versions();
- nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
+ nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
nfsd_last_thread, nfsd, THIS_MODULE);
- if (nfsd_serv == NULL)
+ if (nn->nfsd_serv == NULL)
return -ENOMEM;
- error = svc_bind(nfsd_serv, net);
+ error = svc_bind(nn->nfsd_serv, net);
if (error < 0) {
- svc_destroy(nfsd_serv);
+ svc_destroy(nn->nfsd_serv);
return error;
}
set_max_drc();
- do_gettimeofday(&nfssvc_boot); /* record boot time */
+ do_gettimeofday(&nn->nfssvc_boot); /* record boot time */
return 0;
}
-int nfsd_nrpools(void)
+int nfsd_nrpools(struct net *net)
{
- if (nfsd_serv == NULL)
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ if (nn->nfsd_serv == NULL)
return 0;
else
- return nfsd_serv->sv_nrpools;
+ return nn->nfsd_serv->sv_nrpools;
}
-int nfsd_get_nrthreads(int n, int *nthreads)
+int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
{
int i = 0;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- if (nfsd_serv != NULL) {
- for (i = 0; i < nfsd_serv->sv_nrpools && i < n; i++)
- nthreads[i] = nfsd_serv->sv_pools[i].sp_nrthreads;
+ if (nn->nfsd_serv != NULL) {
+ for (i = 0; i < nn->nfsd_serv->sv_nrpools && i < n; i++)
+ nthreads[i] = nn->nfsd_serv->sv_pools[i].sp_nrthreads;
}
return 0;
}
-int nfsd_set_nrthreads(int n, int *nthreads)
+void nfsd_destroy(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ int destroy = (nn->nfsd_serv->sv_nrthreads == 1);
+
+ if (destroy)
+ svc_shutdown_net(nn->nfsd_serv, net);
+ svc_destroy(nn->nfsd_serv);
+ if (destroy)
+ nn->nfsd_serv = NULL;
+}
+
+int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
{
int i = 0;
int tot = 0;
int err = 0;
- struct net *net = &init_net;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
WARN_ON(!mutex_is_locked(&nfsd_mutex));
- if (nfsd_serv == NULL || n <= 0)
+ if (nn->nfsd_serv == NULL || n <= 0)
return 0;
- if (n > nfsd_serv->sv_nrpools)
- n = nfsd_serv->sv_nrpools;
+ if (n > nn->nfsd_serv->sv_nrpools)
+ n = nn->nfsd_serv->sv_nrpools;
/* enforce a global maximum number of threads */
tot = 0;
@@ -419,9 +473,9 @@ int nfsd_set_nrthreads(int n, int *nthreads)
nthreads[0] = 1;
/* apply the new numbers */
- svc_get(nfsd_serv);
+ svc_get(nn->nfsd_serv);
for (i = 0; i < n; i++) {
- err = svc_set_num_threads(nfsd_serv, &nfsd_serv->sv_pools[i],
+ err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i],
nthreads[i]);
if (err)
break;
@@ -436,11 +490,11 @@ int nfsd_set_nrthreads(int n, int *nthreads)
* this is the first time nrservs is nonzero.
*/
int
-nfsd_svc(int nrservs)
+nfsd_svc(int nrservs, struct net *net)
{
int error;
bool nfsd_up_before;
- struct net *net = &init_net;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
mutex_lock(&nfsd_mutex);
dprintk("nfsd: creating service\n");
@@ -449,29 +503,29 @@ nfsd_svc(int nrservs)
if (nrservs > NFSD_MAXSERVS)
nrservs = NFSD_MAXSERVS;
error = 0;
- if (nrservs == 0 && nfsd_serv == NULL)
+ if (nrservs == 0 && nn->nfsd_serv == NULL)
goto out;
- error = nfsd_create_serv();
+ error = nfsd_create_serv(net);
if (error)
goto out;
- nfsd_up_before = nfsd_up;
+ nfsd_up_before = nn->nfsd_net_up;
- error = nfsd_startup(nrservs);
+ error = nfsd_startup_net(nrservs, net);
if (error)
goto out_destroy;
- error = svc_set_num_threads(nfsd_serv, NULL, nrservs);
+ error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs);
if (error)
goto out_shutdown;
- /* We are holding a reference to nfsd_serv which
+ /* We are holding a reference to nn->nfsd_serv which
* we don't want to count in the return value,
* so subtract 1
*/
- error = nfsd_serv->sv_nrthreads - 1;
+ error = nn->nfsd_serv->sv_nrthreads - 1;
out_shutdown:
if (error < 0 && !nfsd_up_before)
- nfsd_shutdown();
+ nfsd_shutdown_net(net);
out_destroy:
nfsd_destroy(net); /* Release server */
out:
@@ -487,6 +541,8 @@ static int
nfsd(void *vrqstp)
{
struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp;
+ struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list);
+ struct net *net = perm_sock->xpt_net;
int err;
/* Lock module and set up kernel thread */
@@ -551,7 +607,7 @@ out:
/* Release the thread */
svc_exit_thread(rqstp);
- nfsd_destroy(&init_net);
+ nfsd_destroy(net);
/* Release module */
mutex_unlock(&nfsd_mutex);
@@ -596,7 +652,6 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
/* Check whether we have this call in the cache. */
switch (nfsd_cache_lookup(rqstp)) {
- case RC_INTR:
case RC_DROPIT:
return 0;
case RC_REPLY:
@@ -640,21 +695,23 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
}
/* Store reply in cache. */
- nfsd_cache_update(rqstp, proc->pc_cachetype, statp + 1);
+ nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1);
return 1;
}
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
{
int ret;
+ struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
+
mutex_lock(&nfsd_mutex);
- if (nfsd_serv == NULL) {
+ if (nn->nfsd_serv == NULL) {
mutex_unlock(&nfsd_mutex);
return -ENODEV;
}
/* bump up the psudo refcount while traversing */
- svc_get(nfsd_serv);
- ret = svc_pool_stats_open(nfsd_serv, file);
+ svc_get(nn->nfsd_serv);
+ ret = svc_pool_stats_open(nn->nfsd_serv, file);
mutex_unlock(&nfsd_mutex);
return ret;
}
@@ -662,7 +719,7 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file)
int nfsd_pool_stats_release(struct inode *inode, struct file *file)
{
int ret = seq_release(inode, file);
- struct net *net = &init_net;
+ struct net *net = inode->i_sb->s_fs_info;
mutex_lock(&nfsd_mutex);
/* this function really, really should have been called svc_put() */
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 65ec595e2226..9c769a47ac5a 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -4,6 +4,7 @@
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
+#include "vfs.h"
#include "xdr.h"
#include "auth.h"
@@ -100,12 +101,14 @@ decode_sattr(__be32 *p, struct iattr *iap)
iap->ia_mode = tmp;
}
if ((tmp = ntohl(*p++)) != (u32)-1) {
- iap->ia_valid |= ATTR_UID;
- iap->ia_uid = tmp;
+ iap->ia_uid = make_kuid(&init_user_ns, tmp);
+ if (uid_valid(iap->ia_uid))
+ iap->ia_valid |= ATTR_UID;
}
if ((tmp = ntohl(*p++)) != (u32)-1) {
- iap->ia_valid |= ATTR_GID;
- iap->ia_gid = tmp;
+ iap->ia_gid = make_kgid(&init_user_ns, tmp);
+ if (gid_valid(iap->ia_gid))
+ iap->ia_valid |= ATTR_GID;
}
if ((tmp = ntohl(*p++)) != (u32)-1) {
iap->ia_valid |= ATTR_SIZE;
@@ -151,8 +154,8 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
*p++ = htonl(nfs_ftypes[type >> 12]);
*p++ = htonl((u32) stat->mode);
*p++ = htonl((u32) stat->nlink);
- *p++ = htonl((u32) nfsd_ruid(rqstp, stat->uid));
- *p++ = htonl((u32) nfsd_rgid(rqstp, stat->gid));
+ *p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid));
+ *p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid));
if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN) {
*p++ = htonl(NFS_MAXPATHLEN);
@@ -194,11 +197,9 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
}
/* Helper function for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat)
{
- struct kstat stat;
- vfs_getattr(fhp->fh_export->ex_path.mnt, fhp->fh_dentry, &stat);
- return encode_fattr(rqstp, p, fhp, &stat);
+ return encode_fattr(rqstp, p, fhp, stat);
}
/*
@@ -246,7 +247,7 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_readargs *args)
{
unsigned int len;
- int v,pn;
+ int v;
if (!(p = decode_fh(p, &args->fh)))
return 0;
@@ -262,8 +263,9 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
*/
v=0;
while (len > 0) {
- pn = rqstp->rq_resused++;
- rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_respages[pn]);
+ struct page *p = *(rqstp->rq_next_page++);
+
+ rqstp->rq_vec[v].iov_base = page_address(p);
rqstp->rq_vec[v].iov_len = len < PAGE_SIZE?len:PAGE_SIZE;
len -= rqstp->rq_vec[v].iov_len;
v++;
@@ -355,7 +357,7 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli
{
if (!(p = decode_fh(p, &args->fh)))
return 0;
- args->buffer = page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+ args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}
@@ -396,7 +398,7 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
if (args->count > PAGE_SIZE)
args->count = PAGE_SIZE;
- args->buffer = page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+ args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index e036894bce57..1a8c7391f7ae 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -150,6 +150,12 @@ struct nfsd4_channel_attrs {
u32 rdma_attrs;
};
+struct nfsd4_cb_sec {
+ u32 flavor; /* (u32)(-1) used to mean "no valid flavor" */
+ kuid_t uid;
+ kgid_t gid;
+};
+
struct nfsd4_create_session {
clientid_t clientid;
struct nfs4_sessionid sessionid;
@@ -158,8 +164,12 @@ struct nfsd4_create_session {
struct nfsd4_channel_attrs fore_channel;
struct nfsd4_channel_attrs back_channel;
u32 callback_prog;
- u32 uid;
- u32 gid;
+ struct nfsd4_cb_sec cb_sec;
+};
+
+struct nfsd4_backchannel_ctl {
+ u32 bc_cb_program;
+ struct nfsd4_cb_sec bc_cb_sec;
};
struct nfsd4_bind_conn_to_session {
@@ -192,6 +202,7 @@ struct nfsd4_session {
struct nfs4_sessionid se_sessionid;
struct nfsd4_channel_attrs se_fchannel;
struct nfsd4_channel_attrs se_bchannel;
+ struct nfsd4_cb_sec se_cb_sec;
struct list_head se_conns;
u32 se_cb_prog;
u32 se_cb_seq_nr;
@@ -221,13 +232,12 @@ struct nfsd4_sessionid {
*/
struct nfs4_client {
struct list_head cl_idhash; /* hash by cl_clientid.id */
- struct list_head cl_strhash; /* hash by cl_name */
+ struct rb_node cl_namenode; /* link into by-name trees */
struct list_head cl_openowners;
struct idr cl_stateids; /* stateid lookup */
struct list_head cl_delegations;
struct list_head cl_lru; /* tail queue */
struct xdr_netobj cl_name; /* id generated by client */
- char cl_recdir[HEXDIR_LEN]; /* recovery dir */
nfs4_verifier cl_verifier; /* generated by client */
time_t cl_time; /* time of last lease renewal */
struct sockaddr_storage cl_addr; /* client ipaddress */
@@ -242,9 +252,11 @@ struct nfs4_client {
#define NFSD4_CLIENT_CB_KILL (1)
#define NFSD4_CLIENT_STABLE (2) /* client on stable storage */
#define NFSD4_CLIENT_RECLAIM_COMPLETE (3) /* reclaim_complete done */
+#define NFSD4_CLIENT_CONFIRMED (4) /* client is confirmed */
#define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \
1 << NFSD4_CLIENT_CB_KILL)
unsigned long cl_flags;
+ struct rpc_cred *cl_cb_cred;
struct rpc_clnt *cl_cb_client;
u32 cl_cb_ident;
#define NFSD4_CB_UP 0
@@ -271,6 +283,7 @@ struct nfs4_client {
unsigned long cl_cb_slot_busy;
struct rpc_wait_queue cl_cb_waitq; /* backchannel callers may */
/* wait here for slots */
+ struct net *net;
};
static inline void
@@ -292,6 +305,7 @@ is_client_expired(struct nfs4_client *clp)
*/
struct nfs4_client_reclaim {
struct list_head cr_strhash; /* hash by cr_name */
+ struct nfs4_client *cr_clp; /* pointer to associated clp */
char cr_recdir[HEXDIR_LEN]; /* recover dir */
};
@@ -452,25 +466,26 @@ extern __be32 nfs4_preprocess_stateid_op(struct net *net,
stateid_t *stateid, int flags, struct file **filp);
extern void nfs4_lock_state(void);
extern void nfs4_unlock_state(void);
-extern int nfs4_in_grace(void);
-extern void nfs4_release_reclaim(void);
-extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(struct nfs4_client *crp);
-extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions);
+void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
+extern void nfs4_release_reclaim(struct nfsd_net *);
+extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
+ struct nfsd_net *nn);
+extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn);
extern void nfs4_free_openowner(struct nfs4_openowner *);
extern void nfs4_free_lockowner(struct nfs4_lockowner *);
extern int set_callback_cred(void);
+extern void nfsd4_init_callback(struct nfsd4_callback *);
extern void nfsd4_probe_callback(struct nfs4_client *clp);
extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
-extern void nfsd4_do_callback_rpc(struct work_struct *);
extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
extern int nfsd4_create_callback_queue(void);
extern void nfsd4_destroy_callback_queue(void);
extern void nfsd4_shutdown_callback(struct nfs4_client *);
extern void nfs4_put_delegation(struct nfs4_delegation *dp);
-extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname);
-extern int nfs4_client_to_reclaim(const char *name);
-extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
+extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
+ struct nfsd_net *nn);
+extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn);
extern void release_session_client(struct nfsd4_session *);
extern void nfsd4_purge_closed_stateid(struct nfs4_stateowner *);
@@ -480,5 +495,28 @@ extern void nfsd4_client_tracking_exit(struct net *net);
extern void nfsd4_client_record_create(struct nfs4_client *clp);
extern void nfsd4_client_record_remove(struct nfs4_client *clp);
extern int nfsd4_client_record_check(struct nfs4_client *clp);
-extern void nfsd4_record_grace_done(struct net *net, time_t boot_time);
+extern void nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time);
+
+/* nfs fault injection functions */
+#ifdef CONFIG_NFSD_FAULT_INJECTION
+int nfsd_fault_inject_init(void);
+void nfsd_fault_inject_cleanup(void);
+u64 nfsd_for_n_state(u64, u64 (*)(struct nfs4_client *, u64));
+struct nfs4_client *nfsd_find_client(struct sockaddr_storage *, size_t);
+
+u64 nfsd_forget_client(struct nfs4_client *, u64);
+u64 nfsd_forget_client_locks(struct nfs4_client*, u64);
+u64 nfsd_forget_client_openowners(struct nfs4_client *, u64);
+u64 nfsd_forget_client_delegations(struct nfs4_client *, u64);
+u64 nfsd_recall_client_delegations(struct nfs4_client *, u64);
+
+u64 nfsd_print_client(struct nfs4_client *, u64);
+u64 nfsd_print_client_locks(struct nfs4_client *, u64);
+u64 nfsd_print_client_openowners(struct nfs4_client *, u64);
+u64 nfsd_print_client_delegations(struct nfs4_client *, u64);
+#else /* CONFIG_NFSD_FAULT_INJECTION */
+static inline int nfsd_fault_inject_init(void) { return 0; }
+static inline void nfsd_fault_inject_cleanup(void) {}
+#endif /* CONFIG_NFSD_FAULT_INJECTION */
+
#endif /* NFSD4_STATE_H */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c120b48ec305..2a7eb536de0b 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -401,8 +401,8 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
/* Revoke setuid/setgid on chown */
if (!S_ISDIR(inode->i_mode) &&
- (((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) ||
- ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid))) {
+ (((iap->ia_valid & ATTR_UID) && !uid_eq(iap->ia_uid, inode->i_uid)) ||
+ ((iap->ia_valid & ATTR_GID) && !gid_eq(iap->ia_gid, inode->i_gid)))) {
iap->ia_valid |= ATTR_KILL_PRIV;
if (iap->ia_valid & ATTR_MODE) {
/* we're setting mode too, just clear the s*id bits */
@@ -886,7 +886,7 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct svc_rqst *rqstp = sd->u.data;
- struct page **pp = rqstp->rq_respages + rqstp->rq_resused;
+ struct page **pp = rqstp->rq_next_page;
struct page *page = buf->page;
size_t size;
@@ -894,17 +894,15 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
if (rqstp->rq_res.page_len == 0) {
get_page(page);
- put_page(*pp);
- *pp = page;
- rqstp->rq_resused++;
+ put_page(*rqstp->rq_next_page);
+ *(rqstp->rq_next_page++) = page;
rqstp->rq_res.page_base = buf->offset;
rqstp->rq_res.page_len = size;
} else if (page != pp[-1]) {
get_page(page);
- if (*pp)
- put_page(*pp);
- *pp = page;
- rqstp->rq_resused++;
+ if (*rqstp->rq_next_page)
+ put_page(*rqstp->rq_next_page);
+ *(rqstp->rq_next_page++) = page;
rqstp->rq_res.page_len += size;
} else
rqstp->rq_res.page_len += size;
@@ -936,7 +934,7 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
.u.data = rqstp,
};
- rqstp->rq_resused = 1;
+ rqstp->rq_next_page = rqstp->rq_respages + 1;
host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
} else {
oldfs = get_fs();
@@ -981,7 +979,7 @@ static void kill_suid(struct dentry *dentry)
*/
static int wait_for_concurrent_writes(struct file *file)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
static ino_t last_ino;
static dev_t last_dev;
int err = 0;
@@ -1020,28 +1018,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
inode = dentry->d_inode;
exp = fhp->fh_export;
- /*
- * Request sync writes if
- * - the sync export option has been set, or
- * - the client requested O_SYNC behavior (NFSv3 feature).
- * - The file system doesn't support fsync().
- * When NFSv2 gathered writes have been configured for this volume,
- * flushing the data to disk is handled separately below.
- */
use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
- if (!file->f_op->fsync) {/* COMMIT3 cannot work */
- stable = 2;
- *stablep = 2; /* FILE_SYNC */
- }
-
if (!EX_ISSYNC(exp))
stable = 0;
- if (stable && !use_wgather) {
- spin_lock(&file->f_lock);
- file->f_flags |= O_SYNC;
- spin_unlock(&file->f_lock);
- }
/* Write the data. */
oldfs = get_fs(); set_fs(KERNEL_DS);
@@ -1057,8 +1037,12 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
if (inode->i_mode & (S_ISUID | S_ISGID))
kill_suid(dentry);
- if (stable && use_wgather)
- host_err = wait_for_concurrent_writes(file);
+ if (stable) {
+ if (use_wgather)
+ host_err = wait_for_concurrent_writes(file);
+ else
+ host_err = vfs_fsync_range(file, offset, offset+*cnt, 0);
+ }
out_nfserr:
dprintk("nfsd: write complete host_err=%d\n", host_err);
@@ -1086,7 +1070,7 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (err)
return err;
- inode = file->f_path.dentry->d_inode;
+ inode = file_inode(file);
/* Get readahead parameters */
ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
@@ -1221,7 +1205,7 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
* send along the gid on create when it tries to implement
* setgid directories via NFS:
*/
- if (current_fsuid() != 0)
+ if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
iap->ia_valid &= ~(ATTR_UID|ATTR_GID);
if (iap->ia_valid)
return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
@@ -1485,13 +1469,19 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
case NFS3_CREATE_EXCLUSIVE:
if ( dchild->d_inode->i_mtime.tv_sec == v_mtime
&& dchild->d_inode->i_atime.tv_sec == v_atime
- && dchild->d_inode->i_size == 0 )
+ && dchild->d_inode->i_size == 0 ) {
+ if (created)
+ *created = 1;
break;
+ }
case NFS4_CREATE_EXCLUSIVE4_1:
if ( dchild->d_inode->i_mtime.tv_sec == v_mtime
&& dchild->d_inode->i_atime.tv_sec == v_atime
- && dchild->d_inode->i_size == 0 )
+ && dchild->d_inode->i_size == 0 ) {
+ if (created)
+ *created = 1;
goto set_attr;
+ }
/* fallthru */
case NFS3_CREATE_GUARDED:
err = nfserr_exist;
@@ -1967,7 +1957,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func,
offset = *offsetp;
while (1) {
- struct inode *dir_inode = file->f_path.dentry->d_inode;
+ struct inode *dir_inode = file_inode(file);
unsigned int reclen;
cdp->err = nfserr_eof; /* will be cleared on successful read */
@@ -2160,7 +2150,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
* with NFSv3.
*/
if ((acc & NFSD_MAY_OWNER_OVERRIDE) &&
- inode->i_uid == current_fsuid())
+ uid_eq(inode->i_uid, current_fsuid()))
return 0;
/* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 359594c393d2..5b5894159f22 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -6,6 +6,7 @@
#define LINUX_NFSD_VFS_H
#include "nfsfh.h"
+#include "nfsd.h"
/*
* Flags for nfsd_permission
@@ -125,4 +126,11 @@ static inline void fh_drop_write(struct svc_fh *fh)
}
}
+static inline __be32 fh_getattr(struct svc_fh *fh, struct kstat *stat)
+{
+ struct path p = {.mnt = fh->fh_export->ex_path.mnt,
+ .dentry = fh->fh_dentry};
+ return nfserrno(vfs_getattr(&p, stat));
+}
+
#endif /* LINUX_NFSD_VFS_H */
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 53b1863dd8f6..4f0481d63804 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -167,7 +167,7 @@ int nfssvc_encode_entry(void *, const char *name,
int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
/* Helper functions for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp);
+__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat);
__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp);
#endif /* LINUX_NFSD_H */
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 7df980eb0562..b6d5542a4ac8 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -136,6 +136,7 @@ struct nfsd3_accessres {
__be32 status;
struct svc_fh fh;
__u32 access;
+ struct kstat stat;
};
struct nfsd3_readlinkres {
@@ -225,6 +226,7 @@ struct nfsd3_getaclres {
int mask;
struct posix_acl *acl_access;
struct posix_acl *acl_default;
+ struct kstat stat;
};
/* dummy type for release */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index acd127d4ee82..546f8983ecf1 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -385,7 +385,8 @@ struct nfsd4_write {
u64 wr_offset; /* request */
u32 wr_stable_how; /* request */
u32 wr_buflen; /* request */
- int wr_vlen;
+ struct kvec wr_head;
+ struct page ** wr_pagelist; /* request */
u32 wr_bytes_written; /* response */
u32 wr_how_written; /* response */
@@ -462,6 +463,7 @@ struct nfsd4_op {
/* NFSv4.1 */
struct nfsd4_exchange_id exchange_id;
+ struct nfsd4_backchannel_ctl backchannel_ctl;
struct nfsd4_bind_conn_to_session bind_conn_to_session;
struct nfsd4_create_session create_session;
struct nfsd4_destroy_session destroy_session;
@@ -526,6 +528,14 @@ static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
|| nfsd4_is_solo_sequence(resp);
}
+static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp)
+{
+ struct nfsd4_compoundres *resp = rqstp->rq_resp;
+ struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+
+ return argp->opcnt == resp->opcnt;
+}
+
#define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs)
static inline void
@@ -553,7 +563,7 @@ __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op);
__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
- struct dentry *dentry, __be32 *buffer, int *countp,
+ struct dentry *dentry, __be32 **buffer, int countp,
u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
struct nfsd4_compound_state *,
@@ -566,6 +576,7 @@ extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
struct nfsd4_sequence *seq);
extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
struct nfsd4_compound_state *, struct nfsd4_exchange_id *);
+extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_backchannel_ctl *);
extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *);
extern __be32 nfsd4_create_session(struct svc_rqst *,
struct nfsd4_compound_state *,
@@ -579,7 +590,7 @@ extern __be32 nfsd4_destroy_session(struct svc_rqst *,
extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_clientid *);
__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_reclaim_complete *);
extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *,
- struct nfsd4_open *open);
+ struct nfsd4_open *open, struct nfsd_net *nn);
extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp,
struct svc_fh *current_fh, struct nfsd4_open *open);
extern void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status);