* 'nfs-for-2.6.37' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6: (67 commits)
SUNRPC: Cleanup duplicate assignment in rpcauth_refreshcred
nfs: fix unchecked value
Ask for time_delta during fsinfo probe
Revalidate caches on lock
SUNRPC: After calling xprt_release(), we must restart from call_reserve
NFSv4: Fix up the 'dircount' hint in encode_readdir
NFSv4: Clean up nfs4_decode_dirent
NFSv4: nfs4_decode_dirent must clear entry->fattr->valid
NFSv4: Fix a regression in decode_getfattr
NFSv4: Fix up decode_attr_filehandle() to handle the case of empty fh pointer
NFS: Ensure we check all allocation return values in new readdir code
NFS: Readdir plus in v4
NFS: introduce generic decode_getattr function
NFS: check xdr_decode for errors
NFS: nfs_readdir_filler catch all errors
NFS: readdir with vmapped pages
NFS: remove page size checking code
NFS: decode_dirent should use an xdr_stream
SUNRPC: Add a helper function xdr_inline_peek
NFS: remove readdir plus limit
...
AVR32 AVR32 architecture is enabled.
AX25 Appropriate AX.25 support is enabled.
BLACKFIN Blackfin architecture is enabled.
- DRM Direct Rendering Management support is enabled.
EDD BIOS Enhanced Disk Drive Services (EDD) is enabled
EFI EFI Partitioning (GPT) is enabled
EIDE EIDE/ATAPI support is enabled.
+ DRM Direct Rendering Management support is enabled.
+ DYNAMIC_DEBUG Build in debug messages and enable them at runtime
FB The frame buffer device is enabled.
GCOV GCOV profiling is enabled.
HW Appropriate hardware is enabled.
[ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
pxa_timer,timer3,32k_counter,timer0_1
[AVR32] avr32
- [X86-32] pit,hpet,tsc,vmi-timer;
+ [X86-32] pit,hpet,tsc;
scx200_hrt on Geode; cyclone on IBM x440
[MIPS] MIPS
[PARISC] cr16
Format: <port#>,<type>
See also Documentation/input/joystick-parport.txt
+ ddebug_query= [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
+ time. See Documentation/dynamic-debug-howto.txt for
+ details.
+
debug [KNL] Enable kernel debugging (events log level).
debug_locks_verbose=
kvm.oos_shadow= [KVM] Disable out-of-sync shadow paging.
Default is 1 (enabled)
- kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
+ kvm.mmu_audit= [KVM] This is a R/W parameter which allows audit
+ KVM MMU at runtime.
Default is 0 (off)
+ kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
+ Default is 1 (enabled)
+
kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU)
for all guests.
Default is 1 (enabled) if in 64bit or 32bit-PAE mode
1 to enable accounting
Default value is 0.
- nfsaddrs= [NFS]
+ nfsaddrs= [NFS] Deprecated. Use ip= instead.
See Documentation/filesystems/nfs/nfsroot.txt.
nfsroot= [NFS] nfs root filesystem for disk-less boxes.
See Documentation/filesystems/nfs/nfsroot.txt.
+ nfsrootdebug [NFS] enable nfsroot debugging messages.
+ See Documentation/filesystems/nfs/nfsroot.txt.
+
nfs.callback_tcpport=
[NFS] set the TCP port on which the NFSv4 callback
channel should listen.
nojitter [IA64] Disables jitter checking for ITC timers.
+ no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
+
nolapic [X86-32,APIC] Do not enable or use the local APIC.
nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
norandmaps Don't use address space randomization. Equivalent to
echo 0 > /proc/sys/kernel/randomize_va_space
- noreplace-paravirt [X86-32,PV_OPS] Don't patch paravirt_ops
+ noreplace-paravirt [X86,IA-64,PV_OPS] Don't patch paravirt_ops
noreplace-smp [X86-32,SMP] Don't replace SMP instructions
with UP alternatives
force Enable ASPM even on devices that claim not to support it.
WARNING: Forcing ASPM on may cause system lockups.
+ pcie_ports= [PCIE] PCIe ports handling:
+ auto Ask the BIOS whether or not to use native PCIe services
+ associated with PCIe ports (PME, hot-plug, AER). Use
+ them only if that is allowed by the BIOS.
+ native Use native PCIe services associated with PCIe ports
+ unconditionally.
+ compat Treat PCIe ports as PCI-to-PCI bridges, disable the PCIe
+ ports driver.
+
pcie_pme= [PCIE,PM] Native PCIe PME signaling options:
- Format: {auto|force}[,nomsi]
- auto Use native PCIe PME signaling if the BIOS allows the
- kernel to control PCIe config registers of root ports.
- force Use native PCIe PME signaling even if the BIOS refuses
- to allow the kernel to control the relevant PCIe config
- registers.
nomsi Do not use MSI for native PCIe PME signaling (this makes
- all PCIe root ports use INTx for everything).
+ all PCIe root ports use INTx for all services).
pcmv= [HW,PCMCIA] BadgePAD 4
Reserves a hole at the top of the kernel virtual
address space.
+ reservelow= [X86]
+ Format: nn[K]
+ Set the amount of memory to reserve for BIOS at
+ the bottom of the address space.
+
reset_devices [KNL] Force drivers to reset the underlying device
during initialization.
in <PAGE_SIZE> units (needed only for swap files).
See Documentation/power/swsusp-and-swap-files.txt
+ hibernate= [HIBERNATION]
+ noresume Don't check if there's a hibernation image
+ present during boot.
+ nocompress Don't compress/decompress hibernation images.
+
retain_initrd [RAM] Keep initrd memory after extraction
rhash_entries= [KNL,NET]
switches= [HW,M68k]
+ sysfs.deprecated=0|1 [KNL]
+ Enable/disable old style sysfs layout for old udev
+ on older distributions. When this option is enabled
+ very new udev will not work anymore. When this option
+ is disabled (or CONFIG_SYSFS_DEPRECATED not compiled)
+ in older udev will not work anymore.
+ Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in
+ the kernel configuration.
+
sysrq_always_enabled
[KNL]
Ignore sysrq setting - this boot parameter will
topology informations if the hardware supports these.
The scheduler will make use of these informations and
e.g. base its process migration decisions on it.
- Default is off.
+ Default is on.
tp720= [HW,PS2]
disables clocksource verification at runtime.
Used to enable high-resolution timer mode on older
hardware, and in virtualized environment.
+ [x86] noirqtime: Do not use TSC to do irq accounting.
+ Used to run time disable IRQ_TIME_ACCOUNTING on any
+ platforms where RDTSC is slow and this accounting
+ can add overhead.
turbografx.map[2|3]= [HW,JOY]
TurboGraFX parallel port interface
config NFS_FS
tristate "NFS client support"
depends on INET && FILE_LOCKING
+ depends on BKL # fix as soon as lockd is done
select LOCKD
select SUNRPC
select NFS_ACL_SUPPORT if NFS_V3_ACL
config NFS_V4
bool "NFS client support for NFS version 4"
depends on NFS_FS
+ select SUNRPC_GSS
help
This option enables support for version 4 of the NFS protocol
(RFC 3530) in the kernel's NFS client.
select DNS_RESOLVER
select KEYS
default y
+
+ config NFS_USE_NEW_IDMAPPER
+ bool "Use the new idmapper upcall routine"
+ depends on NFS_V4 && KEYS
+ help
+ Say Y here if you want NFS to use the new idmapper upcall functions.
+ You will need /sbin/request-key (usually provided by the keyutils
+ package). For details, read
+ <file:Documentation/filesystems/nfs/idmapper.txt>.
+
+ If you are unsure, say N.
sin1->sin6_scope_id != sin2->sin6_scope_id)
return 0;
- return ipv6_addr_equal(&sin1->sin6_addr, &sin1->sin6_addr);
+ return ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr);
}
#else /* !defined(CONFIG_IPV6) && !defined(CONFIG_IPV6_MODULE) */
static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1,
*/
static void nfs_destroy_server(struct nfs_server *server)
{
- if (!(server->flags & NFS_MOUNT_NONLM))
+ if (!(server->flags & NFS_MOUNT_LOCAL_FLOCK) ||
+ !(server->flags & NFS_MOUNT_LOCAL_FCNTL))
nlmclnt_done(server->nlm_host);
}
if (nlm_init.nfs_version > 3)
return 0;
- if (server->flags & NFS_MOUNT_NONLM)
+ if ((server->flags & NFS_MOUNT_LOCAL_FLOCK) &&
+ (server->flags & NFS_MOUNT_LOCAL_FCNTL))
return 0;
switch (clp->cl_proto) {
server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
server->dtsize = nfs_block_size(fsinfo->dtpref, NULL);
- if (server->dtsize > PAGE_CACHE_SIZE)
- server->dtsize = PAGE_CACHE_SIZE;
+ if (server->dtsize > PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES)
+ server->dtsize = PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES;
if (server->dtsize > server->rsize)
server->dtsize = server->rsize;
server->maxfilesize = fsinfo->maxfilesize;
+ server->time_delta = fsinfo->time_delta;
+
/* We're airborne Set socket buffersize */
rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
}
/* Initialise the client representation from the mount data */
server->flags = data->flags;
- server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|
- NFS_CAP_POSIX_LOCK;
+ server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
+ if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+ server->caps |= NFS_CAP_READDIRPLUS;
server->options = data->options;
/* Get a client record */
struct file *filp = vma->vm_file;
struct dentry *dentry = filp->f_path.dentry;
unsigned pagelen;
- int ret = -EINVAL;
+ int ret = VM_FAULT_NOPAGE;
struct address_space *mapping;
dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%s/%s(%ld), offset %lld)\n",
if (mapping != dentry->d_inode->i_mapping)
goto out_unlock;
- ret = 0;
pagelen = nfs_page_length(page);
if (pagelen == 0)
goto out_unlock;
- ret = nfs_flush_incompatible(filp, page);
- if (ret != 0)
- goto out_unlock;
+ ret = VM_FAULT_LOCKED;
+ if (nfs_flush_incompatible(filp, page) == 0 &&
+ nfs_updatepage(filp, page, 0, pagelen) == 0)
+ goto out;
- ret = nfs_updatepage(filp, page, 0, pagelen);
+ ret = VM_FAULT_SIGBUS;
out_unlock:
- if (!ret)
- return VM_FAULT_LOCKED;
unlock_page(page);
- return VM_FAULT_SIGBUS;
+ out:
+ return ret;
}
static const struct vm_operations_struct nfs_file_vm_ops = {
return ret;
}
- static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
+ static int
+ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
struct inode *inode = filp->f_mapping->host;
int status = 0;
if (nfs_have_delegation(inode, FMODE_READ))
goto out_noconflict;
- if (NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM)
+ if (is_local)
goto out_noconflict;
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
default:
BUG();
}
- if (res < 0)
- dprintk(KERN_WARNING "%s: VFS is out of sync with lock manager"
- " - error %d!\n",
- __func__, res);
return res;
}
- static int do_unlk(struct file *filp, int cmd, struct file_lock *fl)
+ static int
+ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
struct inode *inode = filp->f_mapping->host;
int status;
* If we're signalled while cleaning up locks on process exit, we
* still need to complete the unlock.
*/
- /* Use local locking if mounted with "-onolock" */
- if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
+ /*
+ * Use local locking if mounted with "-onolock" or with appropriate
+ * "-olocal_lock="
+ */
+ if (!is_local)
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
else
status = do_vfs_lock(filp, fl);
return status;
}
- static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
+ static int
+ is_time_granular(struct timespec *ts) {
+ return ((ts->tv_sec == 0) && (ts->tv_nsec <= 1000));
+ }
+
+ static int
+ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
struct inode *inode = filp->f_mapping->host;
int status;
if (status != 0)
goto out;
- /* Use local locking if mounted with "-onolock" */
- if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
+ /*
+ * Use local locking if mounted with "-onolock" or with appropriate
+ * "-olocal_lock="
+ */
+ if (!is_local)
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
else
status = do_vfs_lock(filp, fl);
if (status < 0)
goto out;
+
/*
- * Make sure we clear the cache whenever we try to get the lock.
+ * Revalidate the cache if the server has time stamps granular
+ * enough to detect subsecond changes. Otherwise, clear the
+ * cache to prevent missing any changes.
+ *
* This makes locking act as a cache coherency point.
*/
nfs_sync_mapping(filp->f_mapping);
- if (!nfs_have_delegation(inode, FMODE_READ))
- nfs_zap_caches(inode);
+ if (!nfs_have_delegation(inode, FMODE_READ)) {
+ if (is_time_granular(&NFS_SERVER(inode)->time_delta))
+ __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ else
+ nfs_zap_caches(inode);
+ }
out:
return status;
}
{
struct inode *inode = filp->f_mapping->host;
int ret = -ENOLCK;
+ int is_local = 0;
dprintk("NFS: lock(%s/%s, t=%x, fl=%x, r=%lld:%lld)\n",
filp->f_path.dentry->d_parent->d_name.name,
if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
goto out_err;
+ if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL)
+ is_local = 1;
+
if (NFS_PROTO(inode)->lock_check_bounds != NULL) {
ret = NFS_PROTO(inode)->lock_check_bounds(fl);
if (ret < 0)
}
if (IS_GETLK(cmd))
- ret = do_getlk(filp, cmd, fl);
+ ret = do_getlk(filp, cmd, fl, is_local);
else if (fl->fl_type == F_UNLCK)
- ret = do_unlk(filp, cmd, fl);
+ ret = do_unlk(filp, cmd, fl, is_local);
else
- ret = do_setlk(filp, cmd, fl);
+ ret = do_setlk(filp, cmd, fl, is_local);
out_err:
return ret;
}
*/
static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
{
+ struct inode *inode = filp->f_mapping->host;
+ int is_local = 0;
+
dprintk("NFS: flock(%s/%s, t=%x, fl=%x)\n",
filp->f_path.dentry->d_parent->d_name.name,
filp->f_path.dentry->d_name.name,
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
+ if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
+ is_local = 1;
+
/* We're simulating flock() locks using posix locks on the server */
fl->fl_owner = (fl_owner_t)filp;
fl->fl_start = 0;
fl->fl_end = OFFSET_MAX;
if (fl->fl_type == F_UNLCK)
- return do_unlk(filp, cmd, fl);
- return do_setlk(filp, cmd, fl);
+ return do_unlk(filp, cmd, fl, is_local);
+ return do_setlk(filp, cmd, fl, is_local);
}
/*
#include <linux/kernel.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/fs.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_idmap.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/random.h>
+ #include <linux/ratelimit.h>
#include <linux/workqueue.h>
#include <linux/bitops.h>
/* Guard against delegation returns and new lock/unlock calls */
down_write(&nfsi->rwsem);
/* Protect inode->i_flock using the BKL */
- lock_kernel();
+ lock_flocks();
for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
continue;
if (nfs_file_open_context(fl->fl_file)->state != state)
continue;
- unlock_kernel();
+ unlock_flocks();
status = ops->recover_lock(state, fl);
switch (status) {
case 0:
/* kill_proc(fl->fl_pid, SIGLOST, 1); */
status = 0;
}
- lock_kernel();
+ lock_flocks();
}
- unlock_kernel();
+ unlock_flocks();
out:
up_write(&nfsi->rwsem);
return status;
/* Mark the file as being 'closed' */
state->state = 0;
break;
+ case -EKEYEXPIRED:
+ /*
+ * User RPCSEC_GSS context has expired.
+ * We cannot recover this stateid now, so
+ * skip it and allow recovery thread to
+ * proceed.
+ */
+ break;
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_BAD_STATEID:
(void)ops->reclaim_complete(clp);
}
- static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
+ static int nfs4_state_clear_reclaim_reboot(struct nfs_client *clp)
{
struct nfs4_state_owner *sp;
struct rb_node *pos;
struct nfs4_state *state;
if (!test_and_clear_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
- return;
-
- nfs4_reclaim_complete(clp, clp->cl_mvops->reboot_recovery_ops);
+ return 0;
for (pos = rb_first(&clp->cl_state_owners); pos != NULL; pos = rb_next(pos)) {
sp = rb_entry(pos, struct nfs4_state_owner, so_client_node);
}
nfs_delegation_reap_unclaimed(clp);
+ return 1;
+ }
+
+ static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
+ {
+ if (!nfs4_state_clear_reclaim_reboot(clp))
+ return;
+ nfs4_reclaim_complete(clp, clp->cl_mvops->reboot_recovery_ops);
}
static void nfs_delegation_clear_all(struct nfs_client *clp)
nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce);
}
+ static void nfs4_warn_keyexpired(const char *s)
+ {
+ printk_ratelimited(KERN_WARNING "Error: state manager"
+ " encountered RPCSEC_GSS session"
+ " expired against NFSv4 server %s.\n",
+ s);
+ }
+
static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
{
switch (error) {
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_LEASE_MOVED:
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
- nfs4_state_end_reclaim_reboot(clp);
+ nfs4_state_clear_reclaim_reboot(clp);
nfs4_state_start_reclaim_reboot(clp);
break;
case -NFS4ERR_EXPIRED:
set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
/* Zero session reset errors */
return 0;
+ case -EKEYEXPIRED:
+ /* Nothing we can do */
+ nfs4_warn_keyexpired(clp->cl_hostname);
+ return 0;
}
return error;
}
case -NFS4ERR_DELAY:
case -NFS4ERR_CLID_INUSE:
case -EAGAIN:
- case -EKEYEXPIRED:
break;
+ case -EKEYEXPIRED:
+ nfs4_warn_keyexpired(clp->cl_hostname);
case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
* in nfs4_exchange_id */
default:
Opt_addr, Opt_mountaddr, Opt_clientaddr,
Opt_lookupcache,
Opt_fscache_uniq,
+ Opt_local_lock,
/* Special mount options */
Opt_userspace, Opt_deprecated, Opt_sloppy,
{ Opt_lookupcache, "lookupcache=%s" },
{ Opt_fscache_uniq, "fsc=%s" },
+ { Opt_local_lock, "local_lock=%s" },
{ Opt_err, NULL }
};
{ Opt_lookupcache_err, NULL }
};
+ enum {
+ Opt_local_lock_all, Opt_local_lock_flock, Opt_local_lock_posix,
+ Opt_local_lock_none,
+
+ Opt_local_lock_err
+ };
+
+ static match_table_t nfs_local_lock_tokens = {
+ { Opt_local_lock_all, "all" },
+ { Opt_local_lock_flock, "flock" },
+ { Opt_local_lock_posix, "posix" },
+ { Opt_local_lock_none, "none" },
+
+ { Opt_local_lock_err, NULL }
+ };
+
static void nfs_umount_begin(struct super_block *);
static int nfs_statfs(struct dentry *, struct kstatfs *);
goto out_err;
error = server->nfs_client->rpc_ops->statfs(server, fh, &res);
-
+ if (unlikely(error == -ESTALE)) {
+ struct dentry *pd_dentry;
+
+ pd_dentry = dget_parent(dentry);
+ if (pd_dentry != NULL) {
+ nfs_zap_caches(pd_dentry->d_inode);
+ dput(pd_dentry);
+ }
+ }
nfs_free_fattr(res.fattr);
if (error < 0)
goto out_err;
const struct proc_nfs_info *nfs_infop;
struct nfs_client *clp = nfss->nfs_client;
u32 version = clp->rpc_ops->version;
+ int local_flock, local_fcntl;
seq_printf(m, ",vers=%u", version);
seq_printf(m, ",rsize=%u", nfss->rsize);
else
seq_printf(m, ",lookupcache=pos");
}
+
+ local_flock = nfss->flags & NFS_MOUNT_LOCAL_FLOCK;
+ local_fcntl = nfss->flags & NFS_MOUNT_LOCAL_FCNTL;
+
+ if (!local_flock && !local_fcntl)
+ seq_printf(m, ",local_lock=none");
+ else if (local_flock && local_fcntl)
+ seq_printf(m, ",local_lock=all");
+ else if (local_flock)
+ seq_printf(m, ",local_lock=flock");
+ else
+ seq_printf(m, ",local_lock=posix");
}
/*
break;
case Opt_lock:
mnt->flags &= ~NFS_MOUNT_NONLM;
+ mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK |
+ NFS_MOUNT_LOCAL_FCNTL);
break;
case Opt_nolock:
mnt->flags |= NFS_MOUNT_NONLM;
+ mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK |
+ NFS_MOUNT_LOCAL_FCNTL);
break;
case Opt_v2:
mnt->flags &= ~NFS_MOUNT_VER3;
mnt->fscache_uniq = string;
mnt->options |= NFS_OPTION_FSCACHE;
break;
+ case Opt_local_lock:
+ string = match_strdup(args);
+ if (string == NULL)
+ goto out_nomem;
+ token = match_token(string, nfs_local_lock_tokens,
+ args);
+ kfree(string);
+ switch (token) {
+ case Opt_local_lock_all:
+ mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK |
+ NFS_MOUNT_LOCAL_FCNTL);
+ break;
+ case Opt_local_lock_flock:
+ mnt->flags |= NFS_MOUNT_LOCAL_FLOCK;
+ break;
+ case Opt_local_lock_posix:
+ mnt->flags |= NFS_MOUNT_LOCAL_FCNTL;
+ break;
+ case Opt_local_lock_none:
+ mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK |
+ NFS_MOUNT_LOCAL_FCNTL);
+ break;
+ default:
+ dfprintk(MOUNT, "NFS: invalid "
+ "local_lock argument\n");
+ return 0;
+ };
+ break;
/*
* Special options
if (!args->nfs_server.hostname)
goto out_nomem;
+ if (!(data->flags & NFS_MOUNT_NONLM))
+ args->flags &= ~(NFS_MOUNT_LOCAL_FLOCK|
+ NFS_MOUNT_LOCAL_FCNTL);
+ else
+ args->flags |= (NFS_MOUNT_LOCAL_FLOCK|
+ NFS_MOUNT_LOCAL_FCNTL);
/*
* The legacy version 6 binary mount data from userspace has a
* field used only to transport selinux information into the
static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args)
{
- args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3);
+ args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3|
+ NFS_MOUNT_LOCAL_FLOCK|NFS_MOUNT_LOCAL_FCNTL);
}
static int nfs4_validate_text_mount_data(void *options,
struct nfs4_cached_acl *nfs4_acl;
/* NFSv4 state */
struct list_head open_states;
- struct nfs_delegation *delegation;
+ struct nfs_delegation __rcu *delegation;
fmode_t delegation_state;
struct rw_semaphore rwsem;
#endif /* CONFIG_NFS_V4*/
extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx);
extern void put_nfs_open_context(struct nfs_open_context *ctx);
extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode);
+ extern struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct rpc_cred *cred, fmode_t f_mode);
+ extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx);
extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx);
extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx);
extern u64 nfs_compat_user_ino64(u64 fileid);
extern void nfs_fattr_init(struct nfs_fattr *fattr);
+ extern unsigned long nfs_inc_attr_generation_counter(void);
extern struct nfs_fattr *nfs_alloc_fattr(void);
kfree(fh);
}
+ /*
+ * linux/fs/nfs/nfsroot.c
+ */
+ extern int nfs_root_data(char **root_device, char **root_data); /*__init*/
/* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */
extern __be32 root_nfs_parse_addr(char *name); /*__init*/
- extern unsigned long nfs_inc_attr_generation_counter(void);
/*
* linux/fs/nfs/file.c
/*
* linux/fs/nfs/unlink.c
*/
- extern int nfs_async_unlink(struct inode *dir, struct dentry *dentry);
extern void nfs_complete_unlink(struct dentry *dentry, struct inode *);
extern void nfs_block_sillyrename(struct dentry *dentry);
extern void nfs_unblock_sillyrename(struct dentry *dentry);
+ extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry);
/*
* linux/fs/nfs/write.c
return ino;
}
- /* NFS root */
-
- extern void * nfs_root_data(void);
-
#define nfs_wait_event(clnt, wq, condition) \
({ \
int __retval = wait_event_killable(wq, condition); \
* The high-level client handle
*/
struct rpc_clnt {
- struct kref cl_kref; /* Number of references */
+ atomic_t cl_count; /* Number of references */
struct list_head cl_clients; /* Global list of clients */
struct list_head cl_tasks; /* List of tasks */
spinlock_t cl_lock; /* spinlock */
int rpcb_v4_register(const u32 program, const u32 version,
const struct sockaddr *address,
const char *netid);
- int rpcb_getport_sync(struct sockaddr_in *, u32, u32, int);
void rpcb_getport_async(struct rpc_task *);
void rpc_call_start(struct rpc_task *);
__setup("ro", readonly);
__setup("rw", readwrite);
+#ifdef CONFIG_BLOCK
+/**
+ * match_dev_by_uuid - callback for finding a partition using its uuid
+ * @dev: device passed in by the caller
+ * @data: opaque pointer to a 36 byte char array with a UUID
+ *
+ * Returns 1 if the device matches, and 0 otherwise.
+ */
+static int match_dev_by_uuid(struct device *dev, void *data)
+{
+ u8 *uuid = data;
+ struct hd_struct *part = dev_to_part(dev);
+
+ if (!part->info)
+ goto no_match;
+
+ if (memcmp(uuid, part->info->uuid, sizeof(part->info->uuid)))
+ goto no_match;
+
+ return 1;
+no_match:
+ return 0;
+}
+
+
+/**
+ * devt_from_partuuid - looks up the dev_t of a partition by its UUID
+ * @uuid: 36 byte char array containing a hex ascii UUID
+ *
+ * The function will return the first partition which contains a matching
+ * UUID value in its partition_meta_info struct. This does not search
+ * by filesystem UUIDs.
+ *
+ * Returns the matching dev_t on success or 0 on failure.
+ */
+static dev_t __init devt_from_partuuid(char *uuid_str)
+{
+ dev_t res = 0;
+ struct device *dev = NULL;
+ u8 uuid[16];
+
+ /* Pack the requested UUID in the expected format. */
+ part_pack_uuid(uuid_str, uuid);
+
+ dev = class_find_device(&block_class, NULL, uuid, &match_dev_by_uuid);
+ if (!dev)
+ goto done;
+
+ res = dev->devt;
+ put_device(dev);
+
+done:
+ return res;
+}
+#endif
+
/*
* Convert a name into device number. We accept the following variants:
*
* of partition - device number of disk plus the partition number
* 5) /dev/<disk_name>p<decimal> - same as the above, that form is
* used when disk name of partitioned disk ends on a digit.
+ * 6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
+ * unique id of a partition if the partition table provides it.
*
* If name doesn't have fall into the categories above, we return (0,0).
* block_class is used to check if something is a disk name. If the disk
dev_t res = 0;
int part;
+#ifdef CONFIG_BLOCK
+ if (strncmp(name, "PARTUUID=", 9) == 0) {
+ name += 9;
+ if (strlen(name) != 36)
+ goto fail;
+ res = devt_from_partuuid(name);
+ if (!res)
+ goto fail;
+ goto done;
+ }
+#endif
+
if (strncmp(name, "/dev/", 5) != 0) {
unsigned maj, min;
#ifdef CONFIG_ROOT_NFS
static int __init mount_nfs_root(void)
{
- void *data = nfs_root_data();
+ char *root_dev, *root_data;
- create_dev("/dev/root", ROOT_DEV);
- if (data &&
- do_mount_root("/dev/root", "nfs", root_mountflags, data) == 0)
- return 1;
- return 0;
+ if (nfs_root_data(&root_dev, &root_data) != 0)
+ return 0;
+ if (do_mount_root(root_dev, "nfs", root_mountflags, root_data) != 0)
+ return 0;
+ return 1;
}
#endif
static LIST_HEAD(cred_unused);
static unsigned long number_cred_unused;
-#define MAX_HASHTABLE_BITS (10)
+#define MAX_HASHTABLE_BITS (14)
static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp)
{
unsigned long num;
int
rpcauth_refreshcred(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_rqstp->rq_cred;
+ struct rpc_cred *cred;
int err;
cred = task->tk_rqstp->rq_cred;
goto out_no_principal;
}
- kref_init(&clnt->cl_kref);
+ atomic_set(&clnt->cl_count, 1);
err = rpc_setup_pipedir(clnt, program->pipe_dir_name);
if (err < 0)
if (new->cl_principal == NULL)
goto out_no_principal;
}
- kref_init(&new->cl_kref);
+ atomic_set(&new->cl_count, 1);
err = rpc_setup_pipedir(new, clnt->cl_program->pipe_dir_name);
if (err != 0)
goto out_no_path;
if (new->cl_auth)
atomic_inc(&new->cl_auth->au_count);
xprt_get(clnt->cl_xprt);
- kref_get(&clnt->cl_kref);
+ atomic_inc(&clnt->cl_count);
rpc_register_client(new);
rpciod_up();
return new;
* Free an RPC client
*/
static void
-rpc_free_client(struct kref *kref)
+rpc_free_client(struct rpc_clnt *clnt)
{
- struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref);
-
dprintk("RPC: destroying %s client for %s\n",
clnt->cl_protname, clnt->cl_server);
if (!IS_ERR(clnt->cl_path.dentry)) {
* Free an RPC client
*/
static void
-rpc_free_auth(struct kref *kref)
+rpc_free_auth(struct rpc_clnt *clnt)
{
- struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref);
-
if (clnt->cl_auth == NULL) {
- rpc_free_client(kref);
+ rpc_free_client(clnt);
return;
}
* release remaining GSS contexts. This mechanism ensures
* that it can do so safely.
*/
- kref_init(kref);
+ atomic_inc(&clnt->cl_count);
rpcauth_release(clnt->cl_auth);
clnt->cl_auth = NULL;
- kref_put(kref, rpc_free_client);
+ if (atomic_dec_and_test(&clnt->cl_count))
+ rpc_free_client(clnt);
}
/*
if (list_empty(&clnt->cl_tasks))
wake_up(&destroy_wait);
- kref_put(&clnt->cl_kref, rpc_free_auth);
+ if (atomic_dec_and_test(&clnt->cl_count))
+ rpc_free_auth(clnt);
}
/**
if (clnt != NULL) {
rpc_task_release_client(task);
task->tk_client = clnt;
- kref_get(&clnt->cl_kref);
+ atomic_inc(&clnt->cl_count);
if (clnt->cl_softrtry)
task->tk_flags |= RPC_TASK_SOFT;
/* Add to the client's list of all tasks */
task->tk_status = 0;
if (status >= 0) {
if (task->tk_rqstp) {
- task->tk_action = call_allocate;
+ task->tk_action = call_refresh;
return;
}
}
/*
- * 2. Allocate the buffer. For details, see sched.c:rpc_malloc.
+ * 2. Bind and/or refresh the credentials
+ */
+static void
+call_refresh(struct rpc_task *task)
+{
+ dprint_status(task);
+
+ task->tk_action = call_refreshresult;
+ task->tk_status = 0;
+ task->tk_client->cl_stats->rpcauthrefresh++;
+ rpcauth_refreshcred(task);
+}
+
+/*
+ * 2a. Process the results of a credential refresh
+ */
+static void
+call_refreshresult(struct rpc_task *task)
+{
+ int status = task->tk_status;
+
+ dprint_status(task);
+
+ task->tk_status = 0;
+ task->tk_action = call_allocate;
+ if (status >= 0 && rpcauth_uptodatecred(task))
+ return;
+ switch (status) {
+ case -EACCES:
+ rpc_exit(task, -EACCES);
+ return;
+ case -ENOMEM:
+ rpc_exit(task, -ENOMEM);
+ return;
+ case -ETIMEDOUT:
+ rpc_delay(task, 3*HZ);
+ }
+ task->tk_action = call_refresh;
+}
+
+/*
+ * 2b. Allocate the buffer. For details, see sched.c:rpc_malloc.
* (Note: buffer memory is freed in xprt_release).
*/
static void
call_allocate(struct rpc_task *task)
{
- unsigned int slack = task->tk_client->cl_auth->au_cslack;
+ unsigned int slack = task->tk_rqstp->rq_cred->cr_auth->au_cslack;
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = task->tk_xprt;
struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
dprint_status(task);
task->tk_status = 0;
- task->tk_action = call_refresh;
+ task->tk_action = call_bind;
if (req->rq_buffer)
return;
rpc_exit(task, -ERESTARTSYS);
}
-/*
- * 2a. Bind and/or refresh the credentials
- */
-static void
-call_refresh(struct rpc_task *task)
-{
- dprint_status(task);
-
- task->tk_action = call_refreshresult;
- task->tk_status = 0;
- task->tk_client->cl_stats->rpcauthrefresh++;
- rpcauth_refreshcred(task);
-}
-
-/*
- * 2b. Process the results of a credential refresh
- */
-static void
-call_refreshresult(struct rpc_task *task)
-{
- int status = task->tk_status;
-
- dprint_status(task);
-
- task->tk_status = 0;
- task->tk_action = call_bind;
- if (status >= 0 && rpcauth_uptodatecred(task))
- return;
- switch (status) {
- case -EACCES:
- rpc_exit(task, -EACCES);
- return;
- case -ENOMEM:
- rpc_exit(task, -ENOMEM);
- return;
- case -ETIMEDOUT:
- rpc_delay(task, 3*HZ);
- }
- task->tk_action = call_refresh;
-}
-
static inline int
rpc_task_need_encode(struct rpc_task *task)
{
rpcauth_invalcred(task);
/* Ensure we obtain a new XID! */
xprt_release(task);
- task->tk_action = call_refresh;
+ task->tk_action = call_reserve;
goto out_retry;
case RPC_AUTH_BADCRED:
case RPC_AUTH_BADVERF:
spin_lock_bh(&queue->lock);
res = queue->qlen;
spin_unlock_bh(&queue->lock);
- return (res == 0);
+ return res == 0;
}
EXPORT_SYMBOL_GPL(rpc_queue_empty);
* Create the rpciod thread and wait for it to start.
*/
dprintk("RPC: creating workqueue rpciod\n");
- wq = create_workqueue("rpciod");
+ wq = alloc_workqueue("rpciod", WQ_RESCUER, 0);
rpciod_workqueue = wq;
return rpciod_workqueue != NULL;
}