svn commit: r302252 - head/sys/kern
Konstantin Belousov
kostikbel at gmail.com
Fri Jul 1 14:25:31 UTC 2016
On Fri, Jul 01, 2016 at 08:39:48PM +1000, Bruce Evans wrote:
> It seems simple and clean enough, but is too much during a re freeze.
>
> I will only make some minor comments about style.
Well, it is not only about style. If you have no more comments, I will
ask for testing. The patch is about fixing bugs, although in somewhat
extended scope, so I think it is still fine as the things do not explode.
I added the stats to the patch, it is not that intrusive actually.
I still do not see why/do not want to use spinlock for the tc_windup()
exclusion. Patch is at the end of the message.
>
> > diff --git a/sys/compat/linprocfs/linprocfs.c b/sys/compat/linprocfs/linprocfs.c
> > index 56b2ade..a0dce47 100644
> > --- a/sys/compat/linprocfs/linprocfs.c
> > +++ b/sys/compat/linprocfs/linprocfs.c
> > @@ -447,9 +447,11 @@ linprocfs_dostat(PFS_FILL_ARGS)
> > struct pcpu *pcpu;
> > long cp_time[CPUSTATES];
> > long *cp;
> > + struct timeval boottime;
> > int i;
> >
> > read_cpu_time(cp_time);
> > + getboottime(&boottime);
>
> This is used surprisingly often by too many subsystems. With the value still
> broken so that locking it doesn't help much, I would leave it as a global.
I prefer to keep the KPI consistent.
> > + .th_generation = 0,
> > + .th_next = &th0
> > +};
>
> This shouldn't spell out all the 0 initializers. That was only needed to
> reach the non-0 initializer at the end of the initializer.
I thought about it, but initially did not liked the implicit initialization.
Changed.
> > static int
> > sysctl_kern_boottime(SYSCTL_HANDLER_ARGS)
> > {
> > + struct bintime boottimebin;
> > + struct timeval boottime;
> > +
> > + binuptime1(NULL, &boottimebin);
> > + bintime2timeval(&boottimebin, &boottime);
>
> Use the wrapper function getboottime() if you keep it.
Yes, I wrote this before I added the helper.
> So maybe use a new general function that returns boottimebin for the
> non-uptime functions only. Possibly it can add the offset directly.
I changed getbintime() and getboottimebin() to use the fenced magic and
fetch boottime inside the loop. This removed the need for binuptime1().
>
> > @@ -1116,8 +1170,10 @@ sysclock_snap2bintime(struct sysclock_snap *cs, struct bintime *bt,
> > if (cs->delta > 0)
> > bintime_addx(bt, cs->fb_info.th_scale * cs->delta);
> >
> > - if ((flags & FBCLOCK_UPTIME) == 0)
> > + if ((flags & FBCLOCK_UPTIME) == 0) {
> > + binuptime1(NULL, &boottimebin);
>
> Perhaps use a more direct way to get boottimebin(). binuptime1() is
> pessimized by null pointer checks for both its args. Use the new
> function getboottimebin() even if is not direct.
Used it, and now it is a direct interface into timehands as well.
>
> > ...
> > diff --git a/sys/net/bpf.c b/sys/net/bpf.c
> > index 3b12cf4..4251f71 100644
> > --- a/sys/net/bpf.c
> > +++ b/sys/net/bpf.c
> > @@ -2328,12 +2328,13 @@ bpf_hdrlen(struct bpf_d *d)
> > static void
> > bpf_bintime2ts(struct bintime *bt, struct bpf_ts *ts, int tstype)
> > {
> > - struct bintime bt2;
> > + struct bintime bt2, boottimebin;
> > struct timeval tsm;
> > struct timespec tsn;
> >
> > if ((tstype & BPF_T_MONOTONIC) == 0) {
> > bt2 = *bt;
> > + getboottimebin(&boottimebin);
> > bintime_add(&bt2, &boottimebin);
> > bt = &bt2;
> > }
>
> This is still too chummy with the (mis)implementation. I think it is to
> convert a relative CLOCK_MONOTONIC time to an absolute CLOCK_REALTIME
> time. That should be done in the time subsystem. It is unclear if
> we care about strict real time with leap seconds adjustments.
>
> BPF_T_MONOTONIC is not documented in any man page or used in any library
> or applicatiion in /usr/src. BPF_T_BINTIME is documented bpf(4) but not
> used in any library or application in /usr/src. Similarly for all of
> BPF_T_*. contrib/libpcap has 47 lines matching timeval, 2 matching
> timespec and 0 matching bintime.
I will leave this to bpf maintainers.
>
> > diff --git a/sys/netpfil/ipfw/ip_fw_sockopt.c b/sys/netpfil/ipfw/ip_fw_sockopt.c
> > index d186ba5..7faf99f 100644
> > --- a/sys/netpfil/ipfw/ip_fw_sockopt.c
> > +++ b/sys/netpfil/ipfw/ip_fw_sockopt.c
> > @@ -395,6 +395,7 @@ swap_map(struct ip_fw_chain *chain, struct ip_fw **new_map, int new_len)
> > static void
> > export_cntr1_base(struct ip_fw *krule, struct ip_fw_bcounter *cntr)
> > {
> > + struct timeval boottime;
> >
> > cntr->size = sizeof(*cntr);
> >
> > @@ -403,21 +404,26 @@ export_cntr1_base(struct ip_fw *krule, struct ip_fw_bcounter *cntr)
> > cntr->bcnt = counter_u64_fetch(krule->cntr + 1);
> > cntr->timestamp = krule->timestamp;
> > }
> > - if (cntr->timestamp > 0)
> > + if (cntr->timestamp > 0) {
> > + getboottime(&boottime);
> > cntr->timestamp += boottime.tv_sec;
> > + }
> > }
>
> Looks like another home made conversion from CLOCK_MONOTONIC to
> CLOCK_REALTIME. Easier to understand since it is actually used.
> ipfw seems to use only getmicrouptime() for timestamping. There are
> good reasons for using monotonic time for everything except presenting
> the time to the user and the conversion for that should be more careful
> than the above.
I leave this one to net- people as well.
> > diff --git a/sys/rpc/rpcsec_gss/svc_rpcsec_gss.c b/sys/rpc/rpcsec_gss/svc_rpcsec_gss.c
> > index 1d07943..0879299 100644
> > --- a/sys/rpc/rpcsec_gss/svc_rpcsec_gss.c
> > +++ b/sys/rpc/rpcsec_gss/svc_rpcsec_gss.c
> > @@ -504,11 +504,13 @@ svc_rpc_gss_find_client(struct svc_rpc_gss_clientid *id)
> > {
> > struct svc_rpc_gss_client *client;
> > struct svc_rpc_gss_client_list *list;
> > + struct timeval boottime;
> > unsigned long hostid;
> >
> > rpc_gss_log_debug("in svc_rpc_gss_find_client(%d)", id->ci_id);
> >
> > getcredhostid(curthread->td_ucred, &hostid);
> > + getboottime(&boottime);
> > if (id->ci_hostid != hostid || id->ci_boottime != boottime.tv_sec)
> > return (NULL);
>
> Here it is hopefully just a magic id, with the user being a remote system.
> Any time that doesn't go backwards or forwards so far that it is in the
> lieftime of an old or new boot instance works well for identifying the
> boot instance.
It does not work for leap seconds in the same way as is does not work after
setclock(). So I just leave this conversion as is.
sys/compat/linprocfs/linprocfs.c | 4 +
sys/fs/devfs/devfs_vnops.c | 4 +-
sys/fs/fdescfs/fdesc_vnops.c | 2 +
sys/fs/nfs/nfsport.h | 2 +-
sys/fs/procfs/procfs_status.c | 2 +
sys/kern/kern_acct.c | 2 +-
sys/kern/kern_ntptime.c | 55 +++++-------
sys/kern/kern_proc.c | 2 +
sys/kern/kern_tc.c | 161 +++++++++++++++++++++++++-----------
sys/kern/kern_time.c | 8 +-
sys/kern/subr_rtc.c | 2 +-
sys/kern/sys_procdesc.c | 3 +-
sys/net/bpf.c | 3 +-
sys/netpfil/ipfw/ip_fw_sockopt.c | 12 ++-
sys/nfs/nfs_lock.c | 2 +
sys/rpc/rpcsec_gss/svc_rpcsec_gss.c | 4 +
sys/sys/time.h | 5 +-
17 files changed, 174 insertions(+), 99 deletions(-)
diff --git a/sys/compat/linprocfs/linprocfs.c b/sys/compat/linprocfs/linprocfs.c
index 56b2ade..a0dce47 100644
--- a/sys/compat/linprocfs/linprocfs.c
+++ b/sys/compat/linprocfs/linprocfs.c
@@ -447,9 +447,11 @@ linprocfs_dostat(PFS_FILL_ARGS)
struct pcpu *pcpu;
long cp_time[CPUSTATES];
long *cp;
+ struct timeval boottime;
int i;
read_cpu_time(cp_time);
+ getboottime(&boottime);
sbuf_printf(sb, "cpu %ld %ld %ld %ld\n",
T2J(cp_time[CP_USER]),
T2J(cp_time[CP_NICE]),
@@ -624,10 +626,12 @@ static int
linprocfs_doprocstat(PFS_FILL_ARGS)
{
struct kinfo_proc kp;
+ struct timeval boottime;
char state;
static int ratelimit = 0;
vm_offset_t startcode, startdata;
+ getboottime(&boottime);
sx_slock(&proctree_lock);
PROC_LOCK(p);
fill_kinfo_proc(p, &kp);
diff --git a/sys/fs/devfs/devfs_vnops.c b/sys/fs/devfs/devfs_vnops.c
index 7cc0f9e..afa3da4 100644
--- a/sys/fs/devfs/devfs_vnops.c
+++ b/sys/fs/devfs/devfs_vnops.c
@@ -707,10 +707,11 @@ devfs_getattr(struct vop_getattr_args *ap)
{
struct vnode *vp = ap->a_vp;
struct vattr *vap = ap->a_vap;
- int error;
struct devfs_dirent *de;
struct devfs_mount *dmp;
struct cdev *dev;
+ struct timeval boottime;
+ int error;
error = devfs_populate_vp(vp);
if (error != 0)
@@ -740,6 +741,7 @@ devfs_getattr(struct vop_getattr_args *ap)
vap->va_blocksize = DEV_BSIZE;
vap->va_type = vp->v_type;
+ getboottime(&boottime);
#define fix(aa) \
do { \
if ((aa).tv_sec <= 3600) { \
diff --git a/sys/fs/fdescfs/fdesc_vnops.c b/sys/fs/fdescfs/fdesc_vnops.c
index 4f6e1b9..65b8a54 100644
--- a/sys/fs/fdescfs/fdesc_vnops.c
+++ b/sys/fs/fdescfs/fdesc_vnops.c
@@ -394,7 +394,9 @@ fdesc_getattr(struct vop_getattr_args *ap)
{
struct vnode *vp = ap->a_vp;
struct vattr *vap = ap->a_vap;
+ struct timeval boottime;
+ getboottime(&boottime);
vap->va_mode = S_IRUSR|S_IXUSR|S_IRGRP|S_IXGRP|S_IROTH|S_IXOTH;
vap->va_fileid = VTOFDESC(vp)->fd_ix;
vap->va_uid = 0;
diff --git a/sys/fs/nfs/nfsport.h b/sys/fs/nfs/nfsport.h
index 921df2d..6b41e2f 100644
--- a/sys/fs/nfs/nfsport.h
+++ b/sys/fs/nfs/nfsport.h
@@ -872,7 +872,7 @@ int newnfs_realign(struct mbuf **, int);
/*
* Set boottime.
*/
-#define NFSSETBOOTTIME(b) ((b) = boottime)
+#define NFSSETBOOTTIME(b) (getboottime(&b))
/*
* The size of directory blocks in the buffer cache.
diff --git a/sys/fs/procfs/procfs_status.c b/sys/fs/procfs/procfs_status.c
index 5a00ee1..defdec3 100644
--- a/sys/fs/procfs/procfs_status.c
+++ b/sys/fs/procfs/procfs_status.c
@@ -70,6 +70,7 @@ procfs_doprocstatus(PFS_FILL_ARGS)
const char *wmesg;
char *pc;
char *sep;
+ struct timeval boottime;
int pid, ppid, pgid, sid;
int i;
@@ -129,6 +130,7 @@ procfs_doprocstatus(PFS_FILL_ARGS)
calcru(p, &ut, &st);
PROC_STATUNLOCK(p);
start = p->p_stats->p_start;
+ getboottime(&boottime);
timevaladd(&start, &boottime);
sbuf_printf(sb, " %jd,%ld %jd,%ld %jd,%ld",
(intmax_t)start.tv_sec, start.tv_usec,
diff --git a/sys/kern/kern_acct.c b/sys/kern/kern_acct.c
index ef3fd2e..46e6d9b 100644
--- a/sys/kern/kern_acct.c
+++ b/sys/kern/kern_acct.c
@@ -389,7 +389,7 @@ acct_process(struct thread *td)
acct.ac_stime = encode_timeval(st);
/* (4) The elapsed time the command ran (and its starting time) */
- tmp = boottime;
+ getboottime(&tmp);
timevaladd(&tmp, &p->p_stats->p_start);
acct.ac_btime = tmp.tv_sec;
microuptime(&tmp);
diff --git a/sys/kern/kern_ntptime.c b/sys/kern/kern_ntptime.c
index d352ee7..efc3713 100644
--- a/sys/kern/kern_ntptime.c
+++ b/sys/kern/kern_ntptime.c
@@ -162,29 +162,12 @@ static l_fp time_adj; /* tick adjust (ns/s) */
static int64_t time_adjtime; /* correction from adjtime(2) (usec) */
-static struct mtx ntpadj_lock;
-MTX_SYSINIT(ntpadj, &ntpadj_lock, "ntpadj",
-#ifdef PPS_SYNC
- MTX_SPIN
-#else
- MTX_DEF
-#endif
-);
+static struct mtx ntp_lock;
+MTX_SYSINIT(ntp, &ntp_lock, "ntp", MTX_SPIN);
-/*
- * When PPS_SYNC is defined, hardpps() function is provided which can
- * be legitimately called from interrupt filters. Due to this, use
- * spinlock for ntptime state protection, otherwise sleepable mutex is
- * adequate.
- */
-#ifdef PPS_SYNC
-#define NTPADJ_LOCK() mtx_lock_spin(&ntpadj_lock)
-#define NTPADJ_UNLOCK() mtx_unlock_spin(&ntpadj_lock)
-#else
-#define NTPADJ_LOCK() mtx_lock(&ntpadj_lock)
-#define NTPADJ_UNLOCK() mtx_unlock(&ntpadj_lock)
-#endif
-#define NTPADJ_ASSERT_LOCKED() mtx_assert(&ntpadj_lock, MA_OWNED)
+#define NTP_LOCK() mtx_lock_spin(&ntp_lock)
+#define NTP_UNLOCK() mtx_unlock_spin(&ntp_lock)
+#define NTP_ASSERT_LOCKED() mtx_assert(&ntp_lock, MA_OWNED)
#ifdef PPS_SYNC
/*
@@ -271,7 +254,7 @@ ntp_gettime1(struct ntptimeval *ntvp)
{
struct timespec atv; /* nanosecond time */
- NTPADJ_ASSERT_LOCKED();
+ NTP_ASSERT_LOCKED();
nanotime(&atv);
ntvp->time.tv_sec = atv.tv_sec;
@@ -302,9 +285,9 @@ sys_ntp_gettime(struct thread *td, struct ntp_gettime_args *uap)
{
struct ntptimeval ntv;
- NTPADJ_LOCK();
+ NTP_LOCK();
ntp_gettime1(&ntv);
- NTPADJ_UNLOCK();
+ NTP_UNLOCK();
td->td_retval[0] = ntv.time_state;
return (copyout(&ntv, uap->ntvp, sizeof(ntv)));
@@ -315,9 +298,9 @@ ntp_sysctl(SYSCTL_HANDLER_ARGS)
{
struct ntptimeval ntv; /* temporary structure */
- NTPADJ_LOCK();
+ NTP_LOCK();
ntp_gettime1(&ntv);
- NTPADJ_UNLOCK();
+ NTP_UNLOCK();
return (sysctl_handle_opaque(oidp, &ntv, sizeof(ntv), req));
}
@@ -382,7 +365,7 @@ sys_ntp_adjtime(struct thread *td, struct ntp_adjtime_args *uap)
error = priv_check(td, PRIV_NTP_ADJTIME);
if (error != 0)
return (error);
- NTPADJ_LOCK();
+ NTP_LOCK();
if (modes & MOD_MAXERROR)
time_maxerror = ntv.maxerror;
if (modes & MOD_ESTERROR)
@@ -484,7 +467,7 @@ sys_ntp_adjtime(struct thread *td, struct ntp_adjtime_args *uap)
ntv.stbcnt = pps_stbcnt;
#endif /* PPS_SYNC */
retval = ntp_is_time_error(time_status) ? TIME_ERROR : time_state;
- NTPADJ_UNLOCK();
+ NTP_UNLOCK();
error = copyout((caddr_t)&ntv, (caddr_t)uap->tp, sizeof(ntv));
if (error == 0)
@@ -506,6 +489,8 @@ ntp_update_second(int64_t *adjustment, time_t *newsec)
int tickrate;
l_fp ftemp; /* 32/64-bit temporary */
+ NTP_LOCK();
+
/*
* On rollover of the second both the nanosecond and microsecond
* clocks are updated and the state machine cranked as
@@ -627,6 +612,8 @@ ntp_update_second(int64_t *adjustment, time_t *newsec)
else
time_status &= ~STA_PPSSIGNAL;
#endif /* PPS_SYNC */
+
+ NTP_UNLOCK();
}
/*
@@ -690,7 +677,7 @@ hardupdate(offset)
long mtemp;
l_fp ftemp;
- NTPADJ_ASSERT_LOCKED();
+ NTP_ASSERT_LOCKED();
/*
* Select how the phase is to be controlled and from which
@@ -772,7 +759,7 @@ hardpps(tsp, nsec)
long u_sec, u_nsec, v_nsec; /* temps */
l_fp ftemp;
- NTPADJ_LOCK();
+ NTP_LOCK();
/*
* The signal is first processed by a range gate and frequency
@@ -956,7 +943,7 @@ hardpps(tsp, nsec)
time_freq = pps_freq;
out:
- NTPADJ_UNLOCK();
+ NTP_UNLOCK();
}
#endif /* PPS_SYNC */
@@ -999,11 +986,11 @@ kern_adjtime(struct thread *td, struct timeval *delta, struct timeval *olddelta)
return (error);
ltw = (int64_t)delta->tv_sec * 1000000 + delta->tv_usec;
}
- NTPADJ_LOCK();
+ NTP_LOCK();
ltr = time_adjtime;
if (delta != NULL)
time_adjtime = ltw;
- NTPADJ_UNLOCK();
+ NTP_UNLOCK();
if (olddelta != NULL) {
atv.tv_sec = ltr / 1000000;
atv.tv_usec = ltr % 1000000;
diff --git a/sys/kern/kern_proc.c b/sys/kern/kern_proc.c
index 2f1f620..892b23a 100644
--- a/sys/kern/kern_proc.c
+++ b/sys/kern/kern_proc.c
@@ -872,6 +872,7 @@ fill_kinfo_proc_only(struct proc *p, struct kinfo_proc *kp)
struct session *sp;
struct ucred *cred;
struct sigacts *ps;
+ struct timeval boottime;
/* For proc_realparent. */
sx_assert(&proctree_lock, SX_LOCKED);
@@ -953,6 +954,7 @@ fill_kinfo_proc_only(struct proc *p, struct kinfo_proc *kp)
kp->ki_nice = p->p_nice;
kp->ki_fibnum = p->p_fibnum;
kp->ki_start = p->p_stats->p_start;
+ getboottime(&boottime);
timevaladd(&kp->ki_start, &boottime);
PROC_STATLOCK(p);
rufetch(p, &kp->ki_rusage);
diff --git a/sys/kern/kern_tc.c b/sys/kern/kern_tc.c
index 0f015b3..c9676fc 100644
--- a/sys/kern/kern_tc.c
+++ b/sys/kern/kern_tc.c
@@ -70,31 +70,22 @@ struct timehands {
struct bintime th_offset;
struct timeval th_microtime;
struct timespec th_nanotime;
+ struct bintime th_boottime;
/* Fields not to be copied in tc_windup start with th_generation. */
u_int th_generation;
struct timehands *th_next;
};
static struct timehands th0;
-static struct timehands th9 = { NULL, 0, 0, 0, {0, 0}, {0, 0}, {0, 0}, 0, &th0};
-static struct timehands th8 = { NULL, 0, 0, 0, {0, 0}, {0, 0}, {0, 0}, 0, &th9};
-static struct timehands th7 = { NULL, 0, 0, 0, {0, 0}, {0, 0}, {0, 0}, 0, &th8};
-static struct timehands th6 = { NULL, 0, 0, 0, {0, 0}, {0, 0}, {0, 0}, 0, &th7};
-static struct timehands th5 = { NULL, 0, 0, 0, {0, 0}, {0, 0}, {0, 0}, 0, &th6};
-static struct timehands th4 = { NULL, 0, 0, 0, {0, 0}, {0, 0}, {0, 0}, 0, &th5};
-static struct timehands th3 = { NULL, 0, 0, 0, {0, 0}, {0, 0}, {0, 0}, 0, &th4};
-static struct timehands th2 = { NULL, 0, 0, 0, {0, 0}, {0, 0}, {0, 0}, 0, &th3};
-static struct timehands th1 = { NULL, 0, 0, 0, {0, 0}, {0, 0}, {0, 0}, 0, &th2};
+static struct timehands th1 = {
+ .th_next = &th0
+};
static struct timehands th0 = {
- &dummy_timecounter,
- 0,
- (uint64_t)-1 / 1000000,
- 0,
- {1, 0},
- {0, 0},
- {0, 0},
- 1,
- &th1
+ .th_counter = &dummy_timecounter,
+ .th_scale = (uint64_t)-1 / 1000000,
+ .th_offset = {1, 0},
+ .th_generation = 1,
+ .th_next = &th1
};
static struct timehands *volatile timehands = &th0;
@@ -106,8 +97,6 @@ int tc_min_ticktock_freq = 1;
volatile time_t time_second = 1;
volatile time_t time_uptime = 1;
-struct bintime boottimebin;
-struct timeval boottime;
static int sysctl_kern_boottime(SYSCTL_HANDLER_ARGS);
SYSCTL_PROC(_kern, KERN_BOOTTIME, boottime, CTLTYPE_STRUCT|CTLFLAG_RD,
NULL, 0, sysctl_kern_boottime, "S,timeval", "System boottime");
@@ -135,7 +124,8 @@ SYSCTL_PROC(_kern_timecounter, OID_AUTO, alloweddeviation,
static int tc_chosen; /* Non-zero if a specific tc was chosen via sysctl. */
-static void tc_windup(void);
+static void tc_windup(bool top_call, struct bintime *new_boottimebin);
+static void tc_windup_locked(struct bintime *new_boottimebin);
static void cpu_tick_calibrate(int);
void dtrace_getnanotime(struct timespec *tsp);
@@ -143,6 +133,10 @@ void dtrace_getnanotime(struct timespec *tsp);
static int
sysctl_kern_boottime(SYSCTL_HANDLER_ARGS)
{
+ struct timeval boottime;
+
+ getboottime(&boottime);
+
#ifndef __mips__
#ifdef SCTL_MASK32
int tv[2];
@@ -150,11 +144,11 @@ sysctl_kern_boottime(SYSCTL_HANDLER_ARGS)
if (req->flags & SCTL_MASK32) {
tv[0] = boottime.tv_sec;
tv[1] = boottime.tv_usec;
- return SYSCTL_OUT(req, tv, sizeof(tv));
- } else
+ return (SYSCTL_OUT(req, tv, sizeof(tv)));
+ }
#endif
#endif
- return SYSCTL_OUT(req, &boottime, sizeof(boottime));
+ return (SYSCTL_OUT(req, &boottime, sizeof(boottime)));
}
static int
@@ -164,7 +158,7 @@ sysctl_kern_timecounter_get(SYSCTL_HANDLER_ARGS)
struct timecounter *tc = arg1;
ncount = tc->tc_get_timecount(tc);
- return sysctl_handle_int(oidp, &ncount, 0, req);
+ return (sysctl_handle_int(oidp, &ncount, 0, req));
}
static int
@@ -174,7 +168,7 @@ sysctl_kern_timecounter_freq(SYSCTL_HANDLER_ARGS)
struct timecounter *tc = arg1;
freq = tc->tc_frequency;
- return sysctl_handle_64(oidp, &freq, 0, req);
+ return (sysctl_handle_64(oidp, &freq, 0, req));
}
/*
@@ -198,7 +192,7 @@ tc_delta(struct timehands *th)
*/
#ifdef FFCLOCK
-void
+static void
fbclock_binuptime(struct bintime *bt)
{
struct timehands *th;
@@ -234,8 +228,18 @@ fbclock_microuptime(struct timeval *tvp)
void
fbclock_bintime(struct bintime *bt)
{
+ struct bintime boottimebin;
+ struct timehands *th;
+ unsigned int gen;
- fbclock_binuptime(bt);
+ do {
+ th = timehands;
+ gen = atomic_load_acq_int(&th->th_generation);
+ *bt = th->th_offset;
+ bintime_addx(bt, th->th_scale * tc_delta(th));
+ boottimebin = th->th_boottime;
+ atomic_thread_fence_acq();
+ } while (gen == 0 || gen != th->th_generation);
bintime_add(bt, &boottimebin);
}
@@ -303,12 +307,14 @@ void
fbclock_getbintime(struct bintime *bt)
{
struct timehands *th;
+ struct bintime boottimebin;
unsigned int gen;
do {
th = timehands;
gen = atomic_load_acq_int(&th->th_generation);
*bt = th->th_offset;
+ boottimebin = th->th_boottime;
atomic_thread_fence_acq();
} while (gen == 0 || gen != th->th_generation);
bintime_add(bt, &boottimebin);
@@ -378,8 +384,18 @@ microuptime(struct timeval *tvp)
void
bintime(struct bintime *bt)
{
+ struct bintime boottimebin;
+ struct timehands *th;
+ u_int gen;
- binuptime(bt);
+ do {
+ th = timehands;
+ gen = atomic_load_acq_int(&th->th_generation);
+ *bt = th->th_offset;
+ bintime_addx(bt, th->th_scale * tc_delta(th));
+ boottimebin = th->th_boottime;
+ atomic_thread_fence_acq();
+ } while (gen == 0 || gen != th->th_generation);
bintime_add(bt, &boottimebin);
}
@@ -447,12 +463,14 @@ void
getbintime(struct bintime *bt)
{
struct timehands *th;
+ struct bintime boottimebin;
u_int gen;
do {
th = timehands;
gen = atomic_load_acq_int(&th->th_generation);
*bt = th->th_offset;
+ boottimebin = th->th_boottime;
atomic_thread_fence_acq();
} while (gen == 0 || gen != th->th_generation);
bintime_add(bt, &boottimebin);
@@ -487,6 +505,29 @@ getmicrotime(struct timeval *tvp)
}
#endif /* FFCLOCK */
+void
+getboottime(struct timeval *boottime)
+{
+ struct bintime boottimebin;
+
+ getboottimebin(&boottimebin);
+ bintime2timeval(&boottimebin, boottime);
+}
+
+void
+getboottimebin(struct bintime *boottimebin)
+{
+ struct timehands *th;
+ u_int gen;
+
+ do {
+ th = timehands;
+ gen = atomic_load_acq_int(&th->th_generation);
+ *boottimebin = th->th_boottime;
+ atomic_thread_fence_acq();
+ } while (gen == 0 || gen != th->th_generation);
+}
+
#ifdef FFCLOCK
/*
* Support for feed-forward synchronization algorithms. This is heavily inspired
@@ -1103,6 +1144,7 @@ int
sysclock_snap2bintime(struct sysclock_snap *cs, struct bintime *bt,
int whichclock, uint32_t flags)
{
+ struct bintime boottimebin;
#ifdef FFCLOCK
struct bintime bt2;
uint64_t period;
@@ -1116,8 +1158,10 @@ sysclock_snap2bintime(struct sysclock_snap *cs, struct bintime *bt,
if (cs->delta > 0)
bintime_addx(bt, cs->fb_info.th_scale * cs->delta);
- if ((flags & FBCLOCK_UPTIME) == 0)
+ if ((flags & FBCLOCK_UPTIME) == 0) {
+ getboottimebin(&boottimebin);
bintime_add(bt, &boottimebin);
+ }
break;
#ifdef FFCLOCK
case SYSCLOCK_FFWD:
@@ -1226,10 +1270,12 @@ tc_getfrequency(void)
return (timehands->th_counter->tc_frequency);
}
+static struct mtx tc_setclock_mtx;
+MTX_SYSINIT(tc_setclock_init, &tc_setclock_mtx, "tcsetc", MTX_DEF);
+
/*
* Step our concept of UTC. This is done by modifying our estimate of
* when we booted.
- * XXX: not locked.
*/
void
tc_setclock(struct timespec *ts)
@@ -1237,26 +1283,43 @@ tc_setclock(struct timespec *ts)
struct timespec tbef, taft;
struct bintime bt, bt2;
- cpu_tick_calibrate(1);
- nanotime(&tbef);
timespec2bintime(ts, &bt);
+ nanotime(&tbef);
+ mtx_lock(&tc_setclock_mtx);
+ critical_enter();
+ cpu_tick_calibrate(1);
binuptime(&bt2);
bintime_sub(&bt, &bt2);
- bintime_add(&bt2, &boottimebin);
- boottimebin = bt;
- bintime2timeval(&bt, &boottime);
/* XXX fiddle all the little crinkly bits around the fiords... */
- tc_windup();
- nanotime(&taft);
+ tc_windup(true, &bt);
+ critical_exit();
+ mtx_unlock(&tc_setclock_mtx);
if (timestepwarnings) {
+ nanotime(&taft);
log(LOG_INFO,
"Time stepped from %jd.%09ld to %jd.%09ld (%jd.%09ld)\n",
(intmax_t)tbef.tv_sec, tbef.tv_nsec,
(intmax_t)taft.tv_sec, taft.tv_nsec,
(intmax_t)ts->tv_sec, ts->tv_nsec);
}
- cpu_tick_calibrate(1);
+}
+
+static volatile int tc_windup_lock;
+static void
+tc_windup(bool top_call, struct bintime *new_boottimebin)
+{
+
+ for (;;) {
+ if (atomic_cmpset_int(&tc_windup_lock, 0, 1)) {
+ atomic_thread_fence_acq();
+ tc_windup_locked(new_boottimebin);
+ atomic_store_rel_int(&tc_windup_lock, 0);
+ break;
+ } else if (!top_call) {
+ break;
+ }
+ }
}
/*
@@ -1265,7 +1328,7 @@ tc_setclock(struct timespec *ts)
* timecounter and/or do seconds processing in NTP. Slightly magic.
*/
static void
-tc_windup(void)
+tc_windup_locked(struct bintime *new_boottimebin)
{
struct bintime bt;
struct timehands *th, *tho;
@@ -1289,6 +1352,8 @@ tc_windup(void)
th->th_generation = 0;
atomic_thread_fence_rel();
bcopy(tho, th, offsetof(struct timehands, th_generation));
+ if (new_boottimebin != NULL)
+ th->th_boottime = *new_boottimebin;
/*
* Capture a timecounter delta on the current timecounter and if
@@ -1338,7 +1403,7 @@ tc_windup(void)
* case we missed a leap second.
*/
bt = th->th_offset;
- bintime_add(&bt, &boottimebin);
+ bintime_add(&bt, &th->th_boottime);
i = bt.sec - tho->th_microtime.tv_sec;
if (i > LARGE_STEP)
i = 2;
@@ -1346,7 +1411,7 @@ tc_windup(void)
t = bt.sec;
ntp_update_second(&th->th_adjustment, &bt.sec);
if (bt.sec != t)
- boottimebin.sec += bt.sec - t;
+ th->th_boottime.sec += bt.sec - t;
}
/* Update the UTC timestamps used by the get*() functions. */
/* XXX shouldn't do this here. Should force non-`get' versions. */
@@ -1769,7 +1834,7 @@ pps_event(struct pps_state *pps, int event)
tcount &= pps->capth->th_counter->tc_counter_mask;
bt = pps->capth->th_offset;
bintime_addx(&bt, pps->capth->th_scale * tcount);
- bintime_add(&bt, &boottimebin);
+ bintime_add(&bt, &pps->capth->th_boottime);
bintime2timespec(&bt, &ts);
/* If the timecounter was wound up underneath us, bail out. */
@@ -1846,7 +1911,7 @@ tc_ticktock(int cnt)
if (count < tc_tick)
return;
count = 0;
- tc_windup();
+ tc_windup(false, NULL);
}
static void __inline
@@ -1921,7 +1986,7 @@ inittimecounter(void *dummy)
/* warm up new timecounter (again) and get rolling. */
(void)timecounter->tc_get_timecount(timecounter);
(void)timecounter->tc_get_timecount(timecounter);
- tc_windup();
+ tc_windup(true, NULL);
}
SYSINIT(timecounter, SI_SUB_CLOCKS, SI_ORDER_SECOND, inittimecounter, NULL);
@@ -2095,7 +2160,7 @@ tc_fill_vdso_timehands(struct vdso_timehands *vdso_th)
vdso_th->th_offset_count = th->th_offset_count;
vdso_th->th_counter_mask = th->th_counter->tc_counter_mask;
vdso_th->th_offset = th->th_offset;
- vdso_th->th_boottime = boottimebin;
+ vdso_th->th_boottime = th->th_boottime;
enabled = cpu_fill_vdso_timehands(vdso_th, th->th_counter);
if (!vdso_th_enable)
enabled = 0;
@@ -2116,8 +2181,8 @@ tc_fill_vdso_timehands32(struct vdso_timehands32 *vdso_th32)
vdso_th32->th_counter_mask = th->th_counter->tc_counter_mask;
vdso_th32->th_offset.sec = th->th_offset.sec;
*(uint64_t *)&vdso_th32->th_offset.frac[0] = th->th_offset.frac;
- vdso_th32->th_boottime.sec = boottimebin.sec;
- *(uint64_t *)&vdso_th32->th_boottime.frac[0] = boottimebin.frac;
+ vdso_th32->th_boottime.sec = th->th_boottime.sec;
+ *(uint64_t *)&vdso_th32->th_boottime.frac[0] = th->th_boottime.frac;
enabled = cpu_fill_vdso_timehands32(vdso_th32, th->th_counter);
if (!vdso_th_enable)
enabled = 0;
diff --git a/sys/kern/kern_time.c b/sys/kern/kern_time.c
index 148da2b..82710f7 100644
--- a/sys/kern/kern_time.c
+++ b/sys/kern/kern_time.c
@@ -115,9 +115,7 @@ settime(struct thread *td, struct timeval *tv)
struct timeval delta, tv1, tv2;
static struct timeval maxtime, laststep;
struct timespec ts;
- int s;
- s = splclock();
microtime(&tv1);
delta = *tv;
timevalsub(&delta, &tv1);
@@ -147,10 +145,8 @@ settime(struct thread *td, struct timeval *tv)
printf("Time adjustment clamped to -1 second\n");
}
} else {
- if (tv1.tv_sec == laststep.tv_sec) {
- splx(s);
+ if (tv1.tv_sec == laststep.tv_sec)
return (EPERM);
- }
if (delta.tv_sec > 1) {
tv->tv_sec = tv1.tv_sec + 1;
printf("Time adjustment clamped to +1 second\n");
@@ -161,10 +157,8 @@ settime(struct thread *td, struct timeval *tv)
ts.tv_sec = tv->tv_sec;
ts.tv_nsec = tv->tv_usec * 1000;
- mtx_lock(&Giant);
tc_setclock(&ts);
resettodr();
- mtx_unlock(&Giant);
return (0);
}
diff --git a/sys/kern/subr_rtc.c b/sys/kern/subr_rtc.c
index dbad36d..4bac324 100644
--- a/sys/kern/subr_rtc.c
+++ b/sys/kern/subr_rtc.c
@@ -172,11 +172,11 @@ resettodr(void)
if (disable_rtc_set || clock_dev == NULL)
return;
- mtx_lock(&resettodr_lock);
getnanotime(&ts);
timespecadd(&ts, &clock_adj);
ts.tv_sec -= utc_offset();
/* XXX: We should really set all registered RTCs */
+ mtx_lock(&resettodr_lock);
error = CLOCK_SETTIME(clock_dev, &ts);
mtx_unlock(&resettodr_lock);
if (error != 0)
diff --git a/sys/kern/sys_procdesc.c b/sys/kern/sys_procdesc.c
index 37139c1..f47ae7c 100644
--- a/sys/kern/sys_procdesc.c
+++ b/sys/kern/sys_procdesc.c
@@ -517,7 +517,7 @@ procdesc_stat(struct file *fp, struct stat *sb, struct ucred *active_cred,
struct thread *td)
{
struct procdesc *pd;
- struct timeval pstart;
+ struct timeval pstart, boottime;
/*
* XXXRW: Perhaps we should cache some more information from the
@@ -532,6 +532,7 @@ procdesc_stat(struct file *fp, struct stat *sb, struct ucred *active_cred,
/* Set birth and [acm] times to process start time. */
pstart = pd->pd_proc->p_stats->p_start;
+ getboottime(&boottime);
timevaladd(&pstart, &boottime);
TIMEVAL_TO_TIMESPEC(&pstart, &sb->st_birthtim);
sb->st_atim = sb->st_birthtim;
diff --git a/sys/net/bpf.c b/sys/net/bpf.c
index 3b12cf4..4251f71 100644
--- a/sys/net/bpf.c
+++ b/sys/net/bpf.c
@@ -2328,12 +2328,13 @@ bpf_hdrlen(struct bpf_d *d)
static void
bpf_bintime2ts(struct bintime *bt, struct bpf_ts *ts, int tstype)
{
- struct bintime bt2;
+ struct bintime bt2, boottimebin;
struct timeval tsm;
struct timespec tsn;
if ((tstype & BPF_T_MONOTONIC) == 0) {
bt2 = *bt;
+ getboottimebin(&boottimebin);
bintime_add(&bt2, &boottimebin);
bt = &bt2;
}
diff --git a/sys/netpfil/ipfw/ip_fw_sockopt.c b/sys/netpfil/ipfw/ip_fw_sockopt.c
index d186ba5..7faf99f 100644
--- a/sys/netpfil/ipfw/ip_fw_sockopt.c
+++ b/sys/netpfil/ipfw/ip_fw_sockopt.c
@@ -395,6 +395,7 @@ swap_map(struct ip_fw_chain *chain, struct ip_fw **new_map, int new_len)
static void
export_cntr1_base(struct ip_fw *krule, struct ip_fw_bcounter *cntr)
{
+ struct timeval boottime;
cntr->size = sizeof(*cntr);
@@ -403,21 +404,26 @@ export_cntr1_base(struct ip_fw *krule, struct ip_fw_bcounter *cntr)
cntr->bcnt = counter_u64_fetch(krule->cntr + 1);
cntr->timestamp = krule->timestamp;
}
- if (cntr->timestamp > 0)
+ if (cntr->timestamp > 0) {
+ getboottime(&boottime);
cntr->timestamp += boottime.tv_sec;
+ }
}
static void
export_cntr0_base(struct ip_fw *krule, struct ip_fw_bcounter0 *cntr)
{
+ struct timeval boottime;
if (krule->cntr != NULL) {
cntr->pcnt = counter_u64_fetch(krule->cntr);
cntr->bcnt = counter_u64_fetch(krule->cntr + 1);
cntr->timestamp = krule->timestamp;
}
- if (cntr->timestamp > 0)
+ if (cntr->timestamp > 0) {
+ getboottime(&boottime);
cntr->timestamp += boottime.tv_sec;
+ }
}
/*
@@ -2048,11 +2054,13 @@ ipfw_getrules(struct ip_fw_chain *chain, void *buf, size_t space)
char *ep = bp + space;
struct ip_fw *rule;
struct ip_fw_rule0 *dst;
+ struct timeval boottime;
int error, i, l, warnflag;
time_t boot_seconds;
warnflag = 0;
+ getboottime(&boottime);
boot_seconds = boottime.tv_sec;
for (i = 0; i < chain->n_rules; i++) {
rule = chain->map[i];
diff --git a/sys/nfs/nfs_lock.c b/sys/nfs/nfs_lock.c
index 7d11672..c84413e 100644
--- a/sys/nfs/nfs_lock.c
+++ b/sys/nfs/nfs_lock.c
@@ -241,6 +241,7 @@ nfs_dolock(struct vop_advlock_args *ap)
struct flock *fl;
struct proc *p;
struct nfsmount *nmp;
+ struct timeval boottime;
td = curthread;
p = td->td_proc;
@@ -284,6 +285,7 @@ nfs_dolock(struct vop_advlock_args *ap)
p->p_nlminfo = malloc(sizeof(struct nlminfo),
M_NLMINFO, M_WAITOK | M_ZERO);
p->p_nlminfo->pid_start = p->p_stats->p_start;
+ getboottime(&boottime);
timevaladd(&p->p_nlminfo->pid_start, &boottime);
}
msg.lm_msg_ident.pid_start = p->p_nlminfo->pid_start;
diff --git a/sys/rpc/rpcsec_gss/svc_rpcsec_gss.c b/sys/rpc/rpcsec_gss/svc_rpcsec_gss.c
index 1d07943..0879299 100644
--- a/sys/rpc/rpcsec_gss/svc_rpcsec_gss.c
+++ b/sys/rpc/rpcsec_gss/svc_rpcsec_gss.c
@@ -504,11 +504,13 @@ svc_rpc_gss_find_client(struct svc_rpc_gss_clientid *id)
{
struct svc_rpc_gss_client *client;
struct svc_rpc_gss_client_list *list;
+ struct timeval boottime;
unsigned long hostid;
rpc_gss_log_debug("in svc_rpc_gss_find_client(%d)", id->ci_id);
getcredhostid(curthread->td_ucred, &hostid);
+ getboottime(&boottime);
if (id->ci_hostid != hostid || id->ci_boottime != boottime.tv_sec)
return (NULL);
@@ -537,6 +539,7 @@ svc_rpc_gss_create_client(void)
{
struct svc_rpc_gss_client *client;
struct svc_rpc_gss_client_list *list;
+ struct timeval boottime;
unsigned long hostid;
rpc_gss_log_debug("in svc_rpc_gss_create_client()");
@@ -547,6 +550,7 @@ svc_rpc_gss_create_client(void)
sx_init(&client->cl_lock, "GSS-client");
getcredhostid(curthread->td_ucred, &hostid);
client->cl_id.ci_hostid = hostid;
+ getboottime(&boottime);
client->cl_id.ci_boottime = boottime.tv_sec;
client->cl_id.ci_id = svc_rpc_gss_next_clientid++;
list = &svc_rpc_gss_client_hash[client->cl_id.ci_id % CLIENT_HASH_SIZE];
diff --git a/sys/sys/time.h b/sys/sys/time.h
index 395e888..659f8e0 100644
--- a/sys/sys/time.h
+++ b/sys/sys/time.h
@@ -372,8 +372,6 @@ void resettodr(void);
extern volatile time_t time_second;
extern volatile time_t time_uptime;
-extern struct bintime boottimebin;
-extern struct timeval boottime;
extern struct bintime tc_tick_bt;
extern sbintime_t tc_tick_sbt;
extern struct bintime tick_bt;
@@ -440,6 +438,9 @@ void getbintime(struct bintime *bt);
void getnanotime(struct timespec *tsp);
void getmicrotime(struct timeval *tvp);
+void getboottime(struct timeval *boottime);
+void getboottimebin(struct bintime *boottimebin);
+
/* Other functions */
int itimerdecr(struct itimerval *itp, int usec);
int itimerfix(struct timeval *tv);
More information about the svn-src-head
mailing list