linux-sg2042/fs/lockd/mon.c

556 lines
14 KiB
C
Raw Normal View History

/*
* linux/fs/lockd/mon.c
*
* The kernel statd client.
*
* Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
*/
#include <linux/types.h>
#include <linux/utsname.h>
#include <linux/kernel.h>
NSM: Replace IP address as our nlm_reboot lookup key NLM provides file locking services for NFS files. Part of this service includes a second protocol, known as NSM, which is a reboot notification service. NLM uses this service to determine when to reclaim locks or enter a grace period after a client or server reboots. The NLM service (implemented by lockd in the Linux kernel) contacts the local NSM service (implemented by rpc.statd in Linux user space) via NSM protocol upcalls to register a callback when a particular remote peer reboots. To match the callback to the correct remote peer, the NLM service constructs a cookie that it passes in the request. The NSM service passes that cookie back to the NLM service when it is notified that the given remote peer has indeed rebooted. Currently on Linux, the cookie is the raw 32-bit IPv4 address of the remote peer. To support IPv6 addresses, which are larger, we could use all 16 bytes of the cookie to represent a full IPv6 address, although we still can't represent an IPv6 address with a scope ID in just 16 bytes. Instead, to avoid the need for future changes to support additional address types, we'll use a manufactured value for the cookie, and use that to find the corresponding nsm_handle struct in the kernel during the NLMPROC_SM_NOTIFY callback. This should provide complete support in the kernel's NSM implementation for IPv6 hosts, while remaining backwards compatible with older rpc.statd implementations. Note we also deal with another case where nsm_use_hostnames can change while there are outstanding notifications, possibly resulting in the loss of reboot notifications. After this patch, the priv cookie is always used to lookup rebooted hosts in the kernel. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-12-12 06:56:07 +08:00
#include <linux/ktime.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
NSM: Replace IP address as our nlm_reboot lookup key NLM provides file locking services for NFS files. Part of this service includes a second protocol, known as NSM, which is a reboot notification service. NLM uses this service to determine when to reclaim locks or enter a grace period after a client or server reboots. The NLM service (implemented by lockd in the Linux kernel) contacts the local NSM service (implemented by rpc.statd in Linux user space) via NSM protocol upcalls to register a callback when a particular remote peer reboots. To match the callback to the correct remote peer, the NLM service constructs a cookie that it passes in the request. The NSM service passes that cookie back to the NLM service when it is notified that the given remote peer has indeed rebooted. Currently on Linux, the cookie is the raw 32-bit IPv4 address of the remote peer. To support IPv6 addresses, which are larger, we could use all 16 bytes of the cookie to represent a full IPv6 address, although we still can't represent an IPv6 address with a scope ID in just 16 bytes. Instead, to avoid the need for future changes to support additional address types, we'll use a manufactured value for the cookie, and use that to find the corresponding nsm_handle struct in the kernel during the NLMPROC_SM_NOTIFY callback. This should provide complete support in the kernel's NSM implementation for IPv6 hosts, while remaining backwards compatible with older rpc.statd implementations. Note we also deal with another case where nsm_use_hostnames can change while there are outstanding notifications, possibly resulting in the loss of reboot notifications. After this patch, the priv cookie is always used to lookup rebooted hosts in the kernel. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-12-12 06:56:07 +08:00
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/xprtsock.h>
#include <linux/sunrpc/svc.h>
#include <linux/lockd/lockd.h>
#include <asm/unaligned.h>
#define NLMDBG_FACILITY NLMDBG_MONITOR
#define NSM_PROGRAM 100024
#define NSM_VERSION 1
enum {
NSMPROC_NULL,
NSMPROC_STAT,
NSMPROC_MON,
NSMPROC_UNMON,
NSMPROC_UNMON_ALL,
NSMPROC_SIMU_CRASH,
NSMPROC_NOTIFY,
};
struct nsm_args {
struct nsm_private *priv;
u32 prog; /* RPC callback info */
u32 vers;
u32 proc;
char *mon_name;
};
struct nsm_res {
u32 status;
u32 state;
};
static struct rpc_program nsm_program;
static LIST_HEAD(nsm_handles);
static DEFINE_SPINLOCK(nsm_lock);
/*
* Local NSM state
*/
lockd: Update NSM state from SM_MON replies When rpc.statd starts up in user space at boot time, it attempts to write the latest NSM local state number into /proc/sys/fs/nfs/nsm_local_state. If lockd.ko isn't loaded yet (as is the case in most configurations), that file doesn't exist, thus the kernel's NSM state remains set to its initial value of zero during lockd operation. This is a problem because rpc.statd and lockd use the NSM state number to prevent repeated lock recovery on rebooted hosts. If lockd sends a zero NSM state, but then a delayed SM_NOTIFY with a real NSM state number is received, there is no way for lockd or rpc.statd to distinguish that stale SM_NOTIFY from an actual reboot. Thus lock recovery could be performed after the rebooted host has already started reclaiming locks, and those locks will be lost. We could change /etc/init.d/nfslock so it always modprobes lockd.ko before starting rpc.statd. However, if lockd.ko is ever unloaded and reloaded, we are back at square one, since the NSM state is not preserved across an unload/reload cycle. This may happen frequently on clients that use automounter. A period of NFS inactivity causes lockd.ko to be unloaded, and the kernel loses its NSM state setting. Instead, let's use the fact that rpc.statd plants the local system's NSM state in every SM_MON (and SM_UNMON) reply. lockd performs a synchronous SM_MON upcall to the local rpc.statd _before_ sending its first NLM request to a new remote. This would permit rpc.statd to provide the current NSM state to lockd, even after lockd.ko had been unloaded and reloaded. Note that NLMPROC_LOCK arguments are constructed before the nsm_monitor() call, so we have to rearrange argument construction very slightly to make this all work out. And, the kernel appears to treat NSM state as a u32 (see struct nlm_args and nsm_res). Make nsm_local_state a u32 as well, to ensure we don't get bogus comparison results. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-06-18 09:02:10 +08:00
u32 __read_mostly nsm_local_state;
int __read_mostly nsm_use_hostnames;
static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm)
{
return (struct sockaddr *)&nsm->sm_addr;
}
static struct rpc_clnt *nsm_create(void)
{
struct sockaddr_in sin = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
};
struct rpc_create_args args = {
.net = &init_net,
.protocol = XPRT_TRANSPORT_UDP,
.address = (struct sockaddr *)&sin,
.addrsize = sizeof(sin),
.servername = "rpc.statd",
.program = &nsm_program,
.version = NSM_VERSION,
.authflavor = RPC_AUTH_NULL,
.flags = RPC_CLNT_CREATE_NOPING,
};
return rpc_create(&args);
}
static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
{
struct rpc_clnt *clnt;
int status;
struct nsm_args args = {
.priv = &nsm->sm_priv,
.prog = NLM_PROGRAM,
.vers = 3,
.proc = NLMPROC_NSM_NOTIFY,
NSM: Support IPv6 version of mon_name The "mon_name" argument of the NSMPROC_MON and NSMPROC_UNMON upcalls is a string that contains the hostname or IP address of the remote peer to be notified when this host has rebooted. The sm-notify command uses this identifier to contact the peer when we reboot, so it must be either a well-qualified DNS hostname or a presentation format IP address string. When the "nsm_use_hostnames" sysctl is set to zero, the kernel's NSM provides a presentation format IP address in the "mon_name" argument. Otherwise, the "caller_name" argument from NLM requests is used, which is usually just the DNS hostname of the peer. To support IPv6 addresses for the mon_name argument, we use the nsm_handle's address eye-catcher, which already contains an appropriate presentation format address string. Using the eye-catcher string obviates the need to use a large buffer on the stack to form the presentation address string for the upcall. This patch also addresses a subtle bug. An NSMPROC_MON request and the subsequent NSMPROC_UNMON request for the same peer are required to use the same value for the "mon_name" argument. Otherwise, rpc.statd's NSMPROC_UNMON processing cannot locate the database entry for that peer and remove it. If the setting of nsm_use_hostnames is changed between the time the kernel sends an NSMPROC_MON request and the time it sends the NSMPROC_UNMON request for the same peer, the "mon_name" argument for these two requests may not be the same. This is because the value of "mon_name" is currently chosen at the moment the call is made based on the setting of nsm_use_hostnames To ensure both requests pass identical contents in the "mon_name" argument, we now select which string to use for the argument in the nsm_monitor() function. A pointer to this string is saved in the nsm_handle so it can be used for a subsequent NSMPROC_UNMON upcall. NB: There are other potential problems, such as how nlm_host_rebooted() might behave if nsm_use_hostnames were changed while hosts are still being monitored. This patch does not attempt to address those problems. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-12-05 03:20:46 +08:00
.mon_name = nsm->sm_mon_name,
};
struct rpc_message msg = {
.rpc_argp = &args,
.rpc_resp = res,
};
clnt = nsm_create();
if (IS_ERR(clnt)) {
status = PTR_ERR(clnt);
dprintk("lockd: failed to create NSM upcall transport, "
"status=%d\n", status);
goto out;
}
memset(res, 0, sizeof(*res));
msg.rpc_proc = &clnt->cl_procinfo[proc];
status = rpc_call_sync(clnt, &msg, 0);
if (status < 0)
dprintk("lockd: NSM upcall RPC failed, status=%d\n",
status);
else
status = 0;
rpc_shutdown_client(clnt);
out:
return status;
}
/**
* nsm_monitor - Notify a peer in case we reboot
* @host: pointer to nlm_host of peer to notify
*
* If this peer is not already monitored, this function sends an
* upcall to the local rpc.statd to record the name/address of
* the peer to notify in case we reboot.
*
* Returns zero if the peer is monitored by the local rpc.statd;
* otherwise a negative errno value is returned.
*/
int nsm_monitor(const struct nlm_host *host)
{
struct nsm_handle *nsm = host->h_nsmhandle;
struct nsm_res res;
int status;
dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name);
if (nsm->sm_monitored)
return 0;
NSM: Support IPv6 version of mon_name The "mon_name" argument of the NSMPROC_MON and NSMPROC_UNMON upcalls is a string that contains the hostname or IP address of the remote peer to be notified when this host has rebooted. The sm-notify command uses this identifier to contact the peer when we reboot, so it must be either a well-qualified DNS hostname or a presentation format IP address string. When the "nsm_use_hostnames" sysctl is set to zero, the kernel's NSM provides a presentation format IP address in the "mon_name" argument. Otherwise, the "caller_name" argument from NLM requests is used, which is usually just the DNS hostname of the peer. To support IPv6 addresses for the mon_name argument, we use the nsm_handle's address eye-catcher, which already contains an appropriate presentation format address string. Using the eye-catcher string obviates the need to use a large buffer on the stack to form the presentation address string for the upcall. This patch also addresses a subtle bug. An NSMPROC_MON request and the subsequent NSMPROC_UNMON request for the same peer are required to use the same value for the "mon_name" argument. Otherwise, rpc.statd's NSMPROC_UNMON processing cannot locate the database entry for that peer and remove it. If the setting of nsm_use_hostnames is changed between the time the kernel sends an NSMPROC_MON request and the time it sends the NSMPROC_UNMON request for the same peer, the "mon_name" argument for these two requests may not be the same. This is because the value of "mon_name" is currently chosen at the moment the call is made based on the setting of nsm_use_hostnames To ensure both requests pass identical contents in the "mon_name" argument, we now select which string to use for the argument in the nsm_monitor() function. A pointer to this string is saved in the nsm_handle so it can be used for a subsequent NSMPROC_UNMON upcall. NB: There are other potential problems, such as how nlm_host_rebooted() might behave if nsm_use_hostnames were changed while hosts are still being monitored. This patch does not attempt to address those problems. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-12-05 03:20:46 +08:00
/*
* Choose whether to record the caller_name or IP address of
* this peer in the local rpc.statd's database.
*/
nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
status = nsm_mon_unmon(nsm, NSMPROC_MON, &res);
lockd: Update NSM state from SM_MON replies When rpc.statd starts up in user space at boot time, it attempts to write the latest NSM local state number into /proc/sys/fs/nfs/nsm_local_state. If lockd.ko isn't loaded yet (as is the case in most configurations), that file doesn't exist, thus the kernel's NSM state remains set to its initial value of zero during lockd operation. This is a problem because rpc.statd and lockd use the NSM state number to prevent repeated lock recovery on rebooted hosts. If lockd sends a zero NSM state, but then a delayed SM_NOTIFY with a real NSM state number is received, there is no way for lockd or rpc.statd to distinguish that stale SM_NOTIFY from an actual reboot. Thus lock recovery could be performed after the rebooted host has already started reclaiming locks, and those locks will be lost. We could change /etc/init.d/nfslock so it always modprobes lockd.ko before starting rpc.statd. However, if lockd.ko is ever unloaded and reloaded, we are back at square one, since the NSM state is not preserved across an unload/reload cycle. This may happen frequently on clients that use automounter. A period of NFS inactivity causes lockd.ko to be unloaded, and the kernel loses its NSM state setting. Instead, let's use the fact that rpc.statd plants the local system's NSM state in every SM_MON (and SM_UNMON) reply. lockd performs a synchronous SM_MON upcall to the local rpc.statd _before_ sending its first NLM request to a new remote. This would permit rpc.statd to provide the current NSM state to lockd, even after lockd.ko had been unloaded and reloaded. Note that NLMPROC_LOCK arguments are constructed before the nsm_monitor() call, so we have to rearrange argument construction very slightly to make this all work out. And, the kernel appears to treat NSM state as a u32 (see struct nlm_args and nsm_res). Make nsm_local_state a u32 as well, to ensure we don't get bogus comparison results. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-06-18 09:02:10 +08:00
if (unlikely(res.status != 0))
status = -EIO;
lockd: Update NSM state from SM_MON replies When rpc.statd starts up in user space at boot time, it attempts to write the latest NSM local state number into /proc/sys/fs/nfs/nsm_local_state. If lockd.ko isn't loaded yet (as is the case in most configurations), that file doesn't exist, thus the kernel's NSM state remains set to its initial value of zero during lockd operation. This is a problem because rpc.statd and lockd use the NSM state number to prevent repeated lock recovery on rebooted hosts. If lockd sends a zero NSM state, but then a delayed SM_NOTIFY with a real NSM state number is received, there is no way for lockd or rpc.statd to distinguish that stale SM_NOTIFY from an actual reboot. Thus lock recovery could be performed after the rebooted host has already started reclaiming locks, and those locks will be lost. We could change /etc/init.d/nfslock so it always modprobes lockd.ko before starting rpc.statd. However, if lockd.ko is ever unloaded and reloaded, we are back at square one, since the NSM state is not preserved across an unload/reload cycle. This may happen frequently on clients that use automounter. A period of NFS inactivity causes lockd.ko to be unloaded, and the kernel loses its NSM state setting. Instead, let's use the fact that rpc.statd plants the local system's NSM state in every SM_MON (and SM_UNMON) reply. lockd performs a synchronous SM_MON upcall to the local rpc.statd _before_ sending its first NLM request to a new remote. This would permit rpc.statd to provide the current NSM state to lockd, even after lockd.ko had been unloaded and reloaded. Note that NLMPROC_LOCK arguments are constructed before the nsm_monitor() call, so we have to rearrange argument construction very slightly to make this all work out. And, the kernel appears to treat NSM state as a u32 (see struct nlm_args and nsm_res). Make nsm_local_state a u32 as well, to ensure we don't get bogus comparison results. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-06-18 09:02:10 +08:00
if (unlikely(status < 0)) {
printk(KERN_NOTICE "lockd: cannot monitor %s\n", nsm->sm_name);
lockd: Update NSM state from SM_MON replies When rpc.statd starts up in user space at boot time, it attempts to write the latest NSM local state number into /proc/sys/fs/nfs/nsm_local_state. If lockd.ko isn't loaded yet (as is the case in most configurations), that file doesn't exist, thus the kernel's NSM state remains set to its initial value of zero during lockd operation. This is a problem because rpc.statd and lockd use the NSM state number to prevent repeated lock recovery on rebooted hosts. If lockd sends a zero NSM state, but then a delayed SM_NOTIFY with a real NSM state number is received, there is no way for lockd or rpc.statd to distinguish that stale SM_NOTIFY from an actual reboot. Thus lock recovery could be performed after the rebooted host has already started reclaiming locks, and those locks will be lost. We could change /etc/init.d/nfslock so it always modprobes lockd.ko before starting rpc.statd. However, if lockd.ko is ever unloaded and reloaded, we are back at square one, since the NSM state is not preserved across an unload/reload cycle. This may happen frequently on clients that use automounter. A period of NFS inactivity causes lockd.ko to be unloaded, and the kernel loses its NSM state setting. Instead, let's use the fact that rpc.statd plants the local system's NSM state in every SM_MON (and SM_UNMON) reply. lockd performs a synchronous SM_MON upcall to the local rpc.statd _before_ sending its first NLM request to a new remote. This would permit rpc.statd to provide the current NSM state to lockd, even after lockd.ko had been unloaded and reloaded. Note that NLMPROC_LOCK arguments are constructed before the nsm_monitor() call, so we have to rearrange argument construction very slightly to make this all work out. And, the kernel appears to treat NSM state as a u32 (see struct nlm_args and nsm_res). Make nsm_local_state a u32 as well, to ensure we don't get bogus comparison results. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-06-18 09:02:10 +08:00
return status;
}
nsm->sm_monitored = 1;
if (unlikely(nsm_local_state != res.state)) {
nsm_local_state = res.state;
dprintk("lockd: NSM state changed to %d\n", nsm_local_state);
}
return 0;
}
/**
* nsm_unmonitor - Unregister peer notification
* @host: pointer to nlm_host of peer to stop monitoring
*
* If this peer is monitored, this function sends an upcall to
* tell the local rpc.statd not to send this peer a notification
* when we reboot.
*/
void nsm_unmonitor(const struct nlm_host *host)
{
struct nsm_handle *nsm = host->h_nsmhandle;
struct nsm_res res;
int status;
if (atomic_read(&nsm->sm_count) == 1
&& nsm->sm_monitored && !nsm->sm_sticky) {
dprintk("lockd: nsm_unmonitor(%s)\n", nsm->sm_name);
status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res);
if (res.status != 0)
status = -EIO;
if (status < 0)
printk(KERN_NOTICE "lockd: cannot unmonitor %s\n",
nsm->sm_name);
else
nsm->sm_monitored = 0;
}
}
static struct nsm_handle *nsm_lookup_hostname(const char *hostname,
const size_t len)
{
struct nsm_handle *nsm;
list_for_each_entry(nsm, &nsm_handles, sm_link)
if (strlen(nsm->sm_name) == len &&
memcmp(nsm->sm_name, hostname, len) == 0)
return nsm;
return NULL;
}
static struct nsm_handle *nsm_lookup_addr(const struct sockaddr *sap)
{
struct nsm_handle *nsm;
list_for_each_entry(nsm, &nsm_handles, sm_link)
if (rpc_cmp_addr(nsm_addr(nsm), sap))
return nsm;
return NULL;
}
static struct nsm_handle *nsm_lookup_priv(const struct nsm_private *priv)
{
struct nsm_handle *nsm;
list_for_each_entry(nsm, &nsm_handles, sm_link)
if (memcmp(nsm->sm_priv.data, priv->data,
sizeof(priv->data)) == 0)
return nsm;
return NULL;
}
/*
* Construct a unique cookie to match this nsm_handle to this monitored
* host. It is passed to the local rpc.statd via NSMPROC_MON, and
* returned via NLMPROC_SM_NOTIFY, in the "priv" field of these
* requests.
*
NSM: Replace IP address as our nlm_reboot lookup key NLM provides file locking services for NFS files. Part of this service includes a second protocol, known as NSM, which is a reboot notification service. NLM uses this service to determine when to reclaim locks or enter a grace period after a client or server reboots. The NLM service (implemented by lockd in the Linux kernel) contacts the local NSM service (implemented by rpc.statd in Linux user space) via NSM protocol upcalls to register a callback when a particular remote peer reboots. To match the callback to the correct remote peer, the NLM service constructs a cookie that it passes in the request. The NSM service passes that cookie back to the NLM service when it is notified that the given remote peer has indeed rebooted. Currently on Linux, the cookie is the raw 32-bit IPv4 address of the remote peer. To support IPv6 addresses, which are larger, we could use all 16 bytes of the cookie to represent a full IPv6 address, although we still can't represent an IPv6 address with a scope ID in just 16 bytes. Instead, to avoid the need for future changes to support additional address types, we'll use a manufactured value for the cookie, and use that to find the corresponding nsm_handle struct in the kernel during the NLMPROC_SM_NOTIFY callback. This should provide complete support in the kernel's NSM implementation for IPv6 hosts, while remaining backwards compatible with older rpc.statd implementations. Note we also deal with another case where nsm_use_hostnames can change while there are outstanding notifications, possibly resulting in the loss of reboot notifications. After this patch, the priv cookie is always used to lookup rebooted hosts in the kernel. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-12-12 06:56:07 +08:00
* The NSM protocol requires that these cookies be unique while the
* system is running. We prefer a stronger requirement of making them
* unique across reboots. If user space bugs cause a stale cookie to
* be sent to the kernel, it could cause the wrong host to lose its
* lock state if cookies were not unique across reboots.
*
* The cookies are exposed only to local user space via loopback. They
* do not appear on the physical network. If we want greater security
* for some reason, nsm_init_private() could perform a one-way hash to
* obscure the contents of the cookie.
*/
static void nsm_init_private(struct nsm_handle *nsm)
{
NSM: Replace IP address as our nlm_reboot lookup key NLM provides file locking services for NFS files. Part of this service includes a second protocol, known as NSM, which is a reboot notification service. NLM uses this service to determine when to reclaim locks or enter a grace period after a client or server reboots. The NLM service (implemented by lockd in the Linux kernel) contacts the local NSM service (implemented by rpc.statd in Linux user space) via NSM protocol upcalls to register a callback when a particular remote peer reboots. To match the callback to the correct remote peer, the NLM service constructs a cookie that it passes in the request. The NSM service passes that cookie back to the NLM service when it is notified that the given remote peer has indeed rebooted. Currently on Linux, the cookie is the raw 32-bit IPv4 address of the remote peer. To support IPv6 addresses, which are larger, we could use all 16 bytes of the cookie to represent a full IPv6 address, although we still can't represent an IPv6 address with a scope ID in just 16 bytes. Instead, to avoid the need for future changes to support additional address types, we'll use a manufactured value for the cookie, and use that to find the corresponding nsm_handle struct in the kernel during the NLMPROC_SM_NOTIFY callback. This should provide complete support in the kernel's NSM implementation for IPv6 hosts, while remaining backwards compatible with older rpc.statd implementations. Note we also deal with another case where nsm_use_hostnames can change while there are outstanding notifications, possibly resulting in the loss of reboot notifications. After this patch, the priv cookie is always used to lookup rebooted hosts in the kernel. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-12-12 06:56:07 +08:00
u64 *p = (u64 *)&nsm->sm_priv.data;
struct timespec ts;
s64 ns;
NSM: Replace IP address as our nlm_reboot lookup key NLM provides file locking services for NFS files. Part of this service includes a second protocol, known as NSM, which is a reboot notification service. NLM uses this service to determine when to reclaim locks or enter a grace period after a client or server reboots. The NLM service (implemented by lockd in the Linux kernel) contacts the local NSM service (implemented by rpc.statd in Linux user space) via NSM protocol upcalls to register a callback when a particular remote peer reboots. To match the callback to the correct remote peer, the NLM service constructs a cookie that it passes in the request. The NSM service passes that cookie back to the NLM service when it is notified that the given remote peer has indeed rebooted. Currently on Linux, the cookie is the raw 32-bit IPv4 address of the remote peer. To support IPv6 addresses, which are larger, we could use all 16 bytes of the cookie to represent a full IPv6 address, although we still can't represent an IPv6 address with a scope ID in just 16 bytes. Instead, to avoid the need for future changes to support additional address types, we'll use a manufactured value for the cookie, and use that to find the corresponding nsm_handle struct in the kernel during the NLMPROC_SM_NOTIFY callback. This should provide complete support in the kernel's NSM implementation for IPv6 hosts, while remaining backwards compatible with older rpc.statd implementations. Note we also deal with another case where nsm_use_hostnames can change while there are outstanding notifications, possibly resulting in the loss of reboot notifications. After this patch, the priv cookie is always used to lookup rebooted hosts in the kernel. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-12-12 06:56:07 +08:00
ktime_get_ts(&ts);
ns = timespec_to_ns(&ts);
put_unaligned(ns, p);
put_unaligned((unsigned long)nsm, p + 1);
}
static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap,
const size_t salen,
const char *hostname,
const size_t hostname_len)
{
struct nsm_handle *new;
new = kzalloc(sizeof(*new) + hostname_len + 1, GFP_KERNEL);
if (unlikely(new == NULL))
return NULL;
atomic_set(&new->sm_count, 1);
new->sm_name = (char *)(new + 1);
memcpy(nsm_addr(new), sap, salen);
new->sm_addrlen = salen;
nsm_init_private(new);
if (rpc_ntop(nsm_addr(new), new->sm_addrbuf,
sizeof(new->sm_addrbuf)) == 0)
(void)snprintf(new->sm_addrbuf, sizeof(new->sm_addrbuf),
"unsupported address family");
memcpy(new->sm_name, hostname, hostname_len);
new->sm_name[hostname_len] = '\0';
return new;
}
/**
* nsm_get_handle - Find or create a cached nsm_handle
* @sap: pointer to socket address of handle to find
* @salen: length of socket address
* @hostname: pointer to C string containing hostname to find
* @hostname_len: length of C string
*
* Behavior is modulated by the global nsm_use_hostnames variable.
*
* Returns a cached nsm_handle after bumping its ref count, or
* returns a fresh nsm_handle if a handle that matches @sap and/or
* @hostname cannot be found in the handle cache. Returns NULL if
* an error occurs.
*/
struct nsm_handle *nsm_get_handle(const struct sockaddr *sap,
const size_t salen, const char *hostname,
const size_t hostname_len)
{
struct nsm_handle *cached, *new = NULL;
if (hostname && memchr(hostname, '/', hostname_len) != NULL) {
if (printk_ratelimit()) {
printk(KERN_WARNING "Invalid hostname \"%.*s\" "
"in NFS lock request\n",
(int)hostname_len, hostname);
}
return NULL;
}
retry:
spin_lock(&nsm_lock);
if (nsm_use_hostnames && hostname != NULL)
cached = nsm_lookup_hostname(hostname, hostname_len);
else
cached = nsm_lookup_addr(sap);
if (cached != NULL) {
atomic_inc(&cached->sm_count);
spin_unlock(&nsm_lock);
kfree(new);
dprintk("lockd: found nsm_handle for %s (%s), "
"cnt %d\n", cached->sm_name,
cached->sm_addrbuf,
atomic_read(&cached->sm_count));
return cached;
}
if (new != NULL) {
list_add(&new->sm_link, &nsm_handles);
spin_unlock(&nsm_lock);
dprintk("lockd: created nsm_handle for %s (%s)\n",
new->sm_name, new->sm_addrbuf);
return new;
}
spin_unlock(&nsm_lock);
new = nsm_create_handle(sap, salen, hostname, hostname_len);
if (unlikely(new == NULL))
return NULL;
goto retry;
}
/**
* nsm_reboot_lookup - match NLMPROC_SM_NOTIFY arguments to an nsm_handle
* @info: pointer to NLMPROC_SM_NOTIFY arguments
*
* Returns a matching nsm_handle if found in the nsm cache. The returned
* nsm_handle's reference count is bumped. Otherwise returns NULL if some
* error occurred.
*/
struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info)
{
struct nsm_handle *cached;
spin_lock(&nsm_lock);
NSM: Replace IP address as our nlm_reboot lookup key NLM provides file locking services for NFS files. Part of this service includes a second protocol, known as NSM, which is a reboot notification service. NLM uses this service to determine when to reclaim locks or enter a grace period after a client or server reboots. The NLM service (implemented by lockd in the Linux kernel) contacts the local NSM service (implemented by rpc.statd in Linux user space) via NSM protocol upcalls to register a callback when a particular remote peer reboots. To match the callback to the correct remote peer, the NLM service constructs a cookie that it passes in the request. The NSM service passes that cookie back to the NLM service when it is notified that the given remote peer has indeed rebooted. Currently on Linux, the cookie is the raw 32-bit IPv4 address of the remote peer. To support IPv6 addresses, which are larger, we could use all 16 bytes of the cookie to represent a full IPv6 address, although we still can't represent an IPv6 address with a scope ID in just 16 bytes. Instead, to avoid the need for future changes to support additional address types, we'll use a manufactured value for the cookie, and use that to find the corresponding nsm_handle struct in the kernel during the NLMPROC_SM_NOTIFY callback. This should provide complete support in the kernel's NSM implementation for IPv6 hosts, while remaining backwards compatible with older rpc.statd implementations. Note we also deal with another case where nsm_use_hostnames can change while there are outstanding notifications, possibly resulting in the loss of reboot notifications. After this patch, the priv cookie is always used to lookup rebooted hosts in the kernel. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-12-12 06:56:07 +08:00
cached = nsm_lookup_priv(&info->priv);
if (unlikely(cached == NULL)) {
spin_unlock(&nsm_lock);
dprintk("lockd: never saw rebooted peer '%.*s' before\n",
info->len, info->mon);
return cached;
}
atomic_inc(&cached->sm_count);
spin_unlock(&nsm_lock);
dprintk("lockd: host %s (%s) rebooted, cnt %d\n",
cached->sm_name, cached->sm_addrbuf,
atomic_read(&cached->sm_count));
return cached;
}
/**
* nsm_release - Release an NSM handle
* @nsm: pointer to handle to be released
*
*/
void nsm_release(struct nsm_handle *nsm)
{
if (atomic_dec_and_lock(&nsm->sm_count, &nsm_lock)) {
list_del(&nsm->sm_link);
spin_unlock(&nsm_lock);
dprintk("lockd: destroyed nsm_handle for %s (%s)\n",
nsm->sm_name, nsm->sm_addrbuf);
kfree(nsm);
}
}
/*
* XDR functions for NSM.
*
* See http://www.opengroup.org/ for details on the Network
* Status Monitor wire protocol.
*/
static void encode_nsm_string(struct xdr_stream *xdr, const char *string)
{
const u32 len = strlen(string);
__be32 *p;
BUG_ON(len > SM_MAXSTRLEN);
p = xdr_reserve_space(xdr, 4 + len);
xdr_encode_opaque(p, string, len);
}
/*
* "mon_name" specifies the host to be monitored.
*/
static void encode_mon_name(struct xdr_stream *xdr, const struct nsm_args *argp)
{
encode_nsm_string(xdr, argp->mon_name);
}
/*
* The "my_id" argument specifies the hostname and RPC procedure
* to be called when the status manager receives notification
* (via the NLMPROC_SM_NOTIFY call) that the state of host "mon_name"
* has changed.
*/
static void encode_my_id(struct xdr_stream *xdr, const struct nsm_args *argp)
{
__be32 *p;
encode_nsm_string(xdr, utsname()->nodename);
p = xdr_reserve_space(xdr, 4 + 4 + 4);
*p++ = cpu_to_be32(argp->prog);
*p++ = cpu_to_be32(argp->vers);
*p = cpu_to_be32(argp->proc);
}
/*
* The "mon_id" argument specifies the non-private arguments
* of an NSMPROC_MON or NSMPROC_UNMON call.
*/
static void encode_mon_id(struct xdr_stream *xdr, const struct nsm_args *argp)
{
encode_mon_name(xdr, argp);
encode_my_id(xdr, argp);
}
/*
* The "priv" argument may contain private information required
* by the NSMPROC_MON call. This information will be supplied in the
* NLMPROC_SM_NOTIFY call.
*/
static void encode_priv(struct xdr_stream *xdr, const struct nsm_args *argp)
{
__be32 *p;
p = xdr_reserve_space(xdr, SM_PRIV_SIZE);
xdr_encode_opaque_fixed(p, argp->priv->data, SM_PRIV_SIZE);
}
static void nsm_xdr_enc_mon(struct rpc_rqst *req, struct xdr_stream *xdr,
const struct nsm_args *argp)
{
encode_mon_id(xdr, argp);
encode_priv(xdr, argp);
}
static void nsm_xdr_enc_unmon(struct rpc_rqst *req, struct xdr_stream *xdr,
const struct nsm_args *argp)
{
encode_mon_id(xdr, argp);
}
static int nsm_xdr_dec_stat_res(struct rpc_rqst *rqstp,
struct xdr_stream *xdr,
struct nsm_res *resp)
{
__be32 *p;
p = xdr_inline_decode(xdr, 4 + 4);
if (unlikely(p == NULL))
return -EIO;
resp->status = be32_to_cpup(p++);
resp->state = be32_to_cpup(p);
dprintk("lockd: %s status %d state %d\n",
__func__, resp->status, resp->state);
return 0;
}
static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp,
struct xdr_stream *xdr,
struct nsm_res *resp)
{
__be32 *p;
p = xdr_inline_decode(xdr, 4);
if (unlikely(p == NULL))
return -EIO;
resp->state = be32_to_cpup(p);
dprintk("lockd: %s state %d\n", __func__, resp->state);
return 0;
}
#define SM_my_name_sz (1+XDR_QUADLEN(SM_MAXSTRLEN))
#define SM_my_id_sz (SM_my_name_sz+3)
#define SM_mon_name_sz (1+XDR_QUADLEN(SM_MAXSTRLEN))
#define SM_mon_id_sz (SM_mon_name_sz+SM_my_id_sz)
#define SM_priv_sz (XDR_QUADLEN(SM_PRIV_SIZE))
#define SM_mon_sz (SM_mon_id_sz+SM_priv_sz)
#define SM_monres_sz 2
#define SM_unmonres_sz 1
static struct rpc_procinfo nsm_procedures[] = {
[NSMPROC_MON] = {
.p_proc = NSMPROC_MON,
.p_encode = (kxdreproc_t)nsm_xdr_enc_mon,
.p_decode = (kxdrdproc_t)nsm_xdr_dec_stat_res,
.p_arglen = SM_mon_sz,
.p_replen = SM_monres_sz,
.p_statidx = NSMPROC_MON,
.p_name = "MONITOR",
},
[NSMPROC_UNMON] = {
.p_proc = NSMPROC_UNMON,
.p_encode = (kxdreproc_t)nsm_xdr_enc_unmon,
.p_decode = (kxdrdproc_t)nsm_xdr_dec_stat,
.p_arglen = SM_mon_id_sz,
.p_replen = SM_unmonres_sz,
.p_statidx = NSMPROC_UNMON,
.p_name = "UNMONITOR",
},
};
static struct rpc_version nsm_version1 = {
.number = 1,
.nrprocs = ARRAY_SIZE(nsm_procedures),
.procs = nsm_procedures
};
static struct rpc_version * nsm_version[] = {
[1] = &nsm_version1,
};
static struct rpc_stat nsm_stats;
static struct rpc_program nsm_program = {
.name = "statd",
.number = NSM_PROGRAM,
.nrvers = ARRAY_SIZE(nsm_version),
.version = nsm_version,
.stats = &nsm_stats
};