%patch
Index: linux-2.6.7/arch/ia64/kernel/cyclone.c
===================================================================
--- linux-2.6.7.orig/arch/ia64/kernel/cyclone.c
+++ linux-2.6.7/arch/ia64/kernel/cyclone.c
@@ -16,62 +16,10 @@
return 1;
}
-static u32* volatile cyclone_timer; /* Cyclone MPMC0 register */
-static u32 last_update_cyclone;
-
-static unsigned long offset_base;
-
-static unsigned long get_offset_cyclone(void)
-{
- u32 now;
- unsigned long offset;
-
- /* Read the cyclone timer */
- now = readl(cyclone_timer);
- /* .. relative to previous update*/
- offset = now - last_update_cyclone;
-
- /* convert cyclone ticks to nanoseconds */
- offset = (offset*NSEC_PER_SEC)/CYCLONE_TIMER_FREQ;
-
- /* our adjusted time in nanoseconds */
- return offset_base + offset;
-}
-
-static void update_cyclone(long delta_nsec)
-{
- u32 now;
- unsigned long offset;
-
- /* Read the cyclone timer */
- now = readl(cyclone_timer);
- /* .. relative to previous update*/
- offset = now - last_update_cyclone;
-
- /* convert cyclone ticks to nanoseconds */
- offset = (offset*NSEC_PER_SEC)/CYCLONE_TIMER_FREQ;
-
- offset += offset_base;
-
- /* Be careful about signed/unsigned comparisons here: */
- if (delta_nsec < 0 || (unsigned long) delta_nsec < offset)
- offset_base = offset - delta_nsec;
- else
- offset_base = 0;
-
- last_update_cyclone = now;
-}
-
-static void reset_cyclone(void)
-{
- offset_base = 0;
- last_update_cyclone = readl(cyclone_timer);
-}
struct time_interpolator cyclone_interpolator = {
- .get_offset = get_offset_cyclone,
- .update = update_cyclone,
- .reset = reset_cyclone,
+ .source = TIME_SOURCE_MMIO32,
+ .shift = 32,
.frequency = CYCLONE_TIMER_FREQ,
.drift = -100,
};
@@ -82,6 +30,7 @@
u64 base; /* saved cyclone base address */
u64 offset; /* offset from pageaddr to cyclone_timer register */
int i;
+ u32* volatile cyclone_timer; /* Cyclone MPMC0 register */
if (!use_cyclone)
return -ENODEV;
@@ -149,7 +98,7 @@
}
}
/* initialize last tick */
- last_update_cyclone = readl(cyclone_timer);
+ cyclone_interpolator.addr = cyclone_timer;
register_time_interpolator(&cyclone_interpolator);
return 0;
Index: linux-2.6.7/arch/ia64/kernel/fsys.S
===================================================================
--- linux-2.6.7.orig/arch/ia64/kernel/fsys.S
+++ linux-2.6.7/arch/ia64/kernel/fsys.S
@@ -8,6 +8,8 @@
* 18-Feb-03 louisk Implement fsys_gettimeofday().
* 28-Feb-03 davidm Fixed several bugs in fsys_gettimeofday(). Tuned it some more,
* probably broke it along the way... ;-)
+ * 13-Jul-04 clameter Implement fsys_clock_gettime and revise fsys_gettimeofday to make
+ * it capable of using memory based clocks without falling back to C code.
*/
#include <asm/asmmacro.h>
@@ -144,195 +146,237 @@
END(fsys_set_tid_address)
/*
- * Note 1: This routine uses floating-point registers, but only with registers that
- * operate on integers. Because of that, we don't need to set ar.fpsr to the
- * kernel default value.
- *
- * Note 2: For now, we will assume that all CPUs run at the same clock-frequency.
- * If that wasn't the case, we would have to disable preemption (e.g.,
- * by disabling interrupts) between reading the ITC and reading
- * local_cpu_data->nsec_per_cyc.
- *
- * Note 3: On platforms where the ITC-drift bit is set in the SAL feature vector,
- * we ought to either skip the ITC-based interpolation or run an ntp-like
- * daemon to keep the ITCs from drifting too far apart.
+ * Ensure that the time interpolator structure is compatible with the asm code
*/
-
+#if IA64_TIME_INTERPOLATOR_SOURCE_OFFSET !=0 || IA64_TIME_INTERPOLATOR_SHIFT_OFFSET != 2 || IA64_TIME_INTERPOLATOR_NSEC_OFFSET != 4
+#error fsys_gettimeofday incompatible with changes to struct time_interpolator
+#endif
ENTRY(fsys_gettimeofday)
+ // Register map
+ // r2,r3 = general short term
+ // r20 = initial sequence number
+ // r21 = result seconds
+ // r22 = result nanoseconds
+ // r23 = time interpolator first quad with sourcetype, shift, nsec_per_cyc
+ // r24 = time interpolator_last_counter
+ // r25 = new sequence number
+ // r28 = pointer to nsec portion of argument (r32+8)
+ // r29 = time interpolator counter address
+ // r30 = pointer to struct time_interpolator
+ // r31 = address of seqlock
+ // r32 = address of tv->sec (first argument)
.prologue
.altrp b6
.body
- add r9=TI_FLAGS+IA64_TASK_SIZE,r16
- addl r3=THIS_CPU(cpu_info),r0
-
- mov.m r31=ar.itc // put time stamp into r31 (ITC) == now (35 cyc)
-#ifdef CONFIG_SMP
- movl r10=__per_cpu_offset
- movl r2=sal_platform_features
+ add r2 = TI_FLAGS+IA64_TASK_SIZE,r16
+ tnat.nz p6,p7 = r32 // guard against NaT argument
;;
-
- ld8 r2=[r2]
- movl r19=xtime // xtime is a timespec struct
-
- ld8 r10=[r10] // r10 <- __per_cpu_offset[0]
- addl r21=THIS_CPU(cpu_info),r0
+ ld4 r2 = [r2]
+ movl r31 = xtime_lock
+(p7) tnat.nz p6,p0 = r33 // guard against NaT argument
+ movl r30 = time_interpolator
+ ;;
+ ld8 r30 = [r30]
+ and r2 = TIF_ALLWORK_MASK,r2
+ ;;
+(p6) br.cond.spnt.few .fail_einval
+ add r28 = 8,r32
+ cmp.ne p6, p0 = 0, r2 // Fallback if work is scheduled
+(p6) br.spnt.many fsys_fallback_syscall
+ ;;
+.timeofday_retry:
+ ld8 r23 = [r30],IA64_TIME_INTERPOLATOR_ADDRESS_OFFSET // time_interpolator->source/shift/nsec_per_cyc
+ ;;
+ extr r2 = r23,0,16 // time_interpolator->source
+ ld8 r29 = [r30],-IA64_TIME_INTERPOLATOR_ADDRESS_OFFSET
+ extr r3 = r23,32,32 // time_interpolator->nsec_per_cyc
+ ;;
+ extr r23 = r23,16,16 // time_interpolator->shift
+ movl r24 = time_interpolator_last_counter
+ movl r21 = xtime
+ setf.sig f7 = r3
+ cmp4.eq p6, p0 = IA64_TIME_SOURCE_CPU, r2
+ cmp4.eq p7, p0 = IA64_TIME_SOURCE_MMIO64, r2
+ cmp4.eq p8, p0 = IA64_TIME_SOURCE_MMIO32, r2
+ cmp4.lt p9, p0 = IA64_TIME_SOURCE_MMIO32, r2
+ ld4.acq r20 = [r31] // xtime_lock.sequence
+ ;;
+ .pred.rel.mutex p6,p7,p8,p9
+ ld8 r24 = [r24] // time_interpolator_last_counter
+(p6) mov r2 = ar.itc // CPU_TIMER
+(p9) br.spnt.many fsys_fallback_syscall
+(p7) ld8 r2 = [r29] // readq
+(p8) ld4 r2 = [r29] // readw
+ and r20 = ~1,r20 // Make sequence even to force retry if odd
+ add r22 = 8,r21
+ ;;
+ sub r2 = r2, r24 // current_counter - last_counter
+ ld8 r21 = [r21] // xtime.tv_sec
+ ld8 r22 = [r22] // xtime.tv_nsec
+ ;;
+ setf.sig f8 = r2
;;
- add r10=r21, r10 // r10 <- &cpu_data(time_keeper_id)
- tbit.nz p8,p0 = r2, IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT_BIT
-(p8) br.spnt.many fsys_fallback_syscall
-#else
+ xmpy.l f8 = f8,f7 // nsec_per_cyc*(counter-last_counter)
;;
- mov r10=r3
- movl r19=xtime // xtime is a timespec struct
-#endif
- ld4 r9=[r9]
- movl r17=xtime_lock
+ getf.sig r2 = f8
+ movl r3 = time_interpolator_offset
;;
-
- // r32, r33 should contain the 2 args of gettimeofday
- adds r21=IA64_CPUINFO_ITM_NEXT_OFFSET, r10
- mov r2=-1
- tnat.nz p6,p7=r32 // guard against NaT args
+ shr.u r2 = r2,r23
+ ld8 r3 = [r3] // time_interpolator_offset
;;
-
- adds r10=IA64_CPUINFO_ITM_DELTA_OFFSET, r10
-(p7) tnat.nz p6,p0=r33
-(p6) br.cond.spnt.few .fail_einval
-
- adds r8=IA64_CPUINFO_NSEC_PER_CYC_OFFSET, r3
- movl r24=2361183241434822607 // for division hack (only for / 1000)
+ mf
+ add r2 = r2,r3 // Add time interpolator offset
+ ld4 r25 = [r31] // xtime_lock.sequence
;;
-
- ldf8 f7=[r10] // f7 now contains itm_delta
- setf.sig f11=r2
- adds r10=8, r32
-
- adds r20=IA64_TIMESPEC_TV_NSEC_OFFSET, r19 // r20 = &xtime->tv_nsec
- movl r26=jiffies
-
- setf.sig f9=r24 // f9 is used for division hack
- movl r27=wall_jiffies
-
- and r9=TIF_ALLWORK_MASK,r9
- movl r25=last_nsec_offset
+ add r22 = r22,r2 // Add xtime.nsecs
+ cmp4.ne p6,p0 = r25,r20
+(p6) br.cond.dpnt .timeofday_retry // sequence number changed
+ // now r21=tv->tv_nsec and r22=tv->tv_sec
+ movl r2 = 1000000000
;;
-
- /*
- * Verify that we have permission to write to struct timeval. Note:
- * Another thread might unmap the mapping before we actually get
- * to store the result. That's OK as long as the stores are also
- * protect by EX().
- */
-EX(.fail_efault, probe.w.fault r32, 3) // this must come _after_ NaT-check
-EX(.fail_efault, probe.w.fault r10, 3) // this must come _after_ NaT-check
- nop 0
-
- ldf8 f10=[r8] // f10 <- local_cpu_data->nsec_per_cyc value
- cmp.ne p8, p0=0, r9
-(p8) br.spnt.many fsys_fallback_syscall
+.timeofday_checkagain:
+ cmp.ge p6,p0 = r22,r2
;;
-.retry: // *** seq = read_seqbegin(&xtime_lock); ***
- ld4.acq r23=[r17] // since &xtime_lock == &xtime_lock->sequence
- ld8 r14=[r25] // r14 (old) = last_nsec_offset
-
- ld8 r28=[r26] // r28 = jiffies
- ld8 r29=[r27] // r29 = wall_jiffies
+(p6) sub r22 = r22,r2
+(p6) add r21 = 1,r21
+(p6) br.cond.dpnt .timeofday_checkagain
;;
+ // now r21,r22 contain the normalized time
- ldf8 f8=[r21] // f8 now contains itm_next
- sub r28=r29, r28, 1 // r28 now contains "-(lost + 1)"
- tbit.nz p9, p10=r23, 0 // p9 <- is_odd(r23), p10 <- is_even(r23)
- ;;
-
- ld8 r2=[r19] // r2 = sec = xtime.tv_sec
- ld8 r29=[r20] // r29 = nsec = xtime.tv_nsec
+EX(.fail_efault, st8 [r32] = r21) // tv->tv_sec = seconds
- setf.sig f6=r28 // f6 <- -(lost + 1) (6 cyc)
+ // The only thing left to do is to divide nsecs in r22 by 1000. sigh
+ shr.u r22 = r22, 3
+ movl r3 = 2361183241434822607 // Prep for / 1000 hack
;;
-
- mf
- xma.l f8=f6, f7, f8 // f8 (last_tick) <- -(lost + 1)*itm_delta + itm_next (5 cyc)
- nop 0
-
- setf.sig f12=r31 // f12 <- ITC (6 cyc)
- // *** if (unlikely(read_seqretry(&xtime_lock, seq))) continue; ***
- ld4 r24=[r17] // r24 = xtime_lock->sequence (re-read)
- nop 0
+ // Divided by 8. Now divide by 125
+ // The compiler is able to do that with a multiply
+ // and a shift and we do the same
+ setf.sig f8 = r22
+ setf.sig f7 = r3
;;
-
- mov r31=ar.itc // re-read ITC in case we .retry (35 cyc)
- xma.l f8=f11, f8, f12 // f8 (elapsed_cycles) <- (-1*last_tick + now) = (now - last_tick)
- nop 0
+ xmpy.hu f8 = f8, f7
;;
-
- getf.sig r18=f8 // r18 <- (now - last_tick)
- xmpy.l f8=f8, f10 // f8 <- elapsed_cycles*nsec_per_cyc (5 cyc)
- add r3=r29, r14 // r3 = (nsec + old)
+ getf.sig r2 = f8
;;
-
- cmp.lt p7, p8=r18, r0 // if now < last_tick, set p7 = 1, p8 = 0
- getf.sig r18=f8 // r18 = elapsed_cycles*nsec_per_cyc (6 cyc)
- nop 0
+ shr.u r2 = r2, 4
;;
+EX(.fail_efault, st8 [r28] = r2)
-(p10) cmp.ne p9, p0=r23, r24 // if xtime_lock->sequence != seq, set p9
- shr.u r18=r18, IA64_NSEC_PER_CYC_SHIFT // r18 <- offset
-(p9) br.spnt.many .retry
- ;;
+ mov r8 = r0
+ mov r10 = r0
+ FSYS_RETURN
+.fail_einval:
+ mov r8 = EINVAL
+ mov r10 = -1
+ FSYS_RETURN
- mov ar.ccv=r14 // ar.ccv = old (1 cyc)
- cmp.leu p7, p8=r18, r14 // if (offset <= old), set p7 = 1, p8 = 0
- ;;
+.fail_efault:
+ mov r8 = EFAULT
+ mov r10 = -1
+ FSYS_RETURN
+END(fsys_gettimeofday)
-(p8) cmpxchg8.rel r24=[r25], r18, ar.ccv // compare-and-exchange (atomic!)
-(p8) add r3=r29, r18 // r3 = (nsec + offset)
- ;;
- shr.u r3=r3, 3 // initiate dividing r3 by 1000
- ;;
- setf.sig f8=r3 // (6 cyc)
- mov r10=1000000 // r10 = 1000000
+ENTRY(fsys_clock_gettime)
+ // Register map
+ // r2,r3 = scratch
+ // r20 = initial sequence number
+ // r21 = result seconds
+ // r22 = result nanoseconds
+ // r23 = time interpolator first quad with sourcetype, shift, nsec_per_cyc
+ // r24 = time interpolator_last_counter
+ // r25 = new sequence number
+ // r28 = pointer to nsec portion of timespec structure (r33+8)
+ // r29 = time interpolator counter address
+ // r30 = pointer to struct time_interpolator
+ // r31 = address of seqlock
+ // r32 = type of timer desired (argument 1)
+ // r33 = pointer to sec portion of timespec structure (argument 2)
+ .prologue
+ .altrp b6
+ .body
+ add r2 = TI_FLAGS+IA64_TASK_SIZE,r16
+ movl r30 = time_interpolator
;;
-(p8) cmp.ne.unc p9, p0=r24, r14
- xmpy.hu f6=f8, f9 // (5 cyc)
-(p9) br.spnt.many .retry
+ ld4 r2 = [r2]
+ tnat.nz p6,p0 = r33
+ ld8 r30 = [r30]
+ ;;
+ and r2 = TIF_ALLWORK_MASK,r2
+ add r28 = 8,r33
+(p6) br.cond.spnt.few .fail_einval
+ ;;
+ cmp.ne p6, p7 = 0, r2 // Fallback if work is scheduled
+ ;;
+(p7) cmp.ne p6, p0 = 0, r32 // Fallback if this is not CLOCK_REALTIME
+(p6) br.spnt.many fsys_fallback_syscall
+ movl r31 = xtime_lock
+
+.gettime_retry:
+ ld8 r23 = [r30],IA64_TIME_INTERPOLATOR_ADDRESS_OFFSET // time_interpolator->source/shift/nsec_per_cyc
+ movl r24 = time_interpolator_last_counter
+ ;;
+ ld8 r29 = [r30],-IA64_TIME_INTERPOLATOR_ADDRESS_OFFSET
+ extr r2 = r23,0,16
+ extr r3 = r23,32,32 // time_interpolator->nsec_per_cyc
+ ld4.acq r20 = [r31] // xtime_lock.sequence
+ ;;
+ ld8 r24 = [r24] // time_interpolator_last_counter
+ extr r23 = r23,16,16 // time_interpolator->shift
+ cmp4.eq p6, p0 = IA64_TIME_SOURCE_CPU, r2
+ cmp4.eq p7, p0 = IA64_TIME_SOURCE_MMIO64, r2
+ cmp4.eq p8, p0 = IA64_TIME_SOURCE_MMIO32, r2
+ cmp4.lt p9, p0 = IA64_TIME_SOURCE_MMIO32, r2
+ and r20 = ~1,r20 // Make seq.number even to insure retry if odd
+ movl r21 = xtime
+ ;;
+ .pred.rel.mutex p6,p7,p8,p9
+(p6) mov r2 = ar.itc // CPU_TIMER
+(p7) ld8 r2 = [r29] // readq
+(p8) ld4 r2 = [r29] // readw
+(p9) br.spnt.many fsys_fallback_syscall // Cannot do function call -> fallback
+ add r22 = 8,r21
+ ;;
+ sub r2 = r2, r24
+ ld8 r21 = [r21] // xtime.tv_sec
+ ld8 r22 = [r22] // xtime.tv_nsec
+ ;;
+ setf.sig f6 = r2
+ setf.sig f7 = r3
+ ;;
+ xmpy.l f6 = f6,f7 // nsec_per_cyc*(timeval-last_counter)
;;
-
- getf.sig r3=f6 // (6 cyc)
+ getf.sig r2 = f6
+ movl r24 = time_interpolator_offset
;;
- shr.u r3=r3, 4 // end of division, r3 is divided by 1000 (=usec)
+ ld8 r24 = [r24] // time_interpolator_offset
+ shr.u r2 = r2,r23
;;
-
-1: cmp.geu p7, p0=r3, r10 // while (usec >= 1000000)
+ add r2 = r2,r24 // result plus interpolator_offset
+ mf
;;
-(p7) sub r3=r3, r10 // usec -= 1000000
-(p7) adds r2=1, r2 // ++sec
-(p7) br.spnt.many 1b
-
- // finally: r2 = sec, r3 = usec
-EX(.fail_efault, st8 [r32]=r2)
- adds r9=8, r32
- mov r8=r0 // success
+ add r22 = r22,r2 // Add nsec
+ ld4 r2 = [r31] // xtime_lock.sequence
;;
-EX(.fail_efault, st8 [r9]=r3) // store them in the timeval struct
- mov r10=0
+ cmp4.ne p6,p0 = r2,r20
+(p6) br.cond.dpnt .gettime_retry
+ // now r21=tv->tv_nsec and r22=tv->tv_sec
+ movl r2 = 1000000000
+ ;;
+.gettime_checkagain:
+ cmp.ge p6,p0 = r22,r2
+ ;;
+(p6) sub r22 = r22,r2
+(p6) add r21 = 1,r21
+(p6) br.cond.dpnt .gettime_checkagain
+ ;;
+ // now r21,r22 contain the normalized time
+EX(.fail_efault, st8 [r33] = r21) // tv->tv_sec = seconds
+EX(.fail_efault, st8 [r28] = r22) // tv->tv_nsec = nanosecs
+ mov r8 = r0
+ mov r10 = r0
FSYS_RETURN
- /*
- * Note: We are NOT clearing the scratch registers here. Since the only things
- * in those registers are time-related variables and some addresses (which
- * can be obtained from System.map), none of this should be security-sensitive
- * and we should be fine.
- */
-
-.fail_einval:
- mov r8=EINVAL // r8 = EINVAL
- mov r10=-1 // r10 = -1
- FSYS_RETURN
-
-.fail_efault:
- mov r8=EFAULT // r8 = EFAULT
- mov r10=-1 // r10 = -1
- FSYS_RETURN
-END(fsys_gettimeofday)
+END(fsys_gettime)
/*
* long fsys_rt_sigprocmask (int how, sigset_t *set, sigset_t *oset, size_t sigsetsize).
@@ -839,7 +883,7 @@
data8 0 // timer_getoverrun
data8 0 // timer_delete
data8 0 // clock_settime
- data8 0 // clock_gettime
+ data8 fsys_clock_gettime // clock_gettime
data8 0 // clock_getres // 1255
data8 0 // clock_nanosleep
data8 0 // fstatfs64
Index: linux-2.6.7/arch/ia64/kernel/time.c
===================================================================
--- linux-2.6.7.orig/arch/ia64/kernel/time.c
+++ linux-2.6.7/arch/ia64/kernel/time.c
@@ -45,46 +45,7 @@
#endif
-static void
-itc_reset (void)
-{
-}
-
-/*
- * Adjust for the fact that xtime has been advanced by delta_nsec (may be negative and/or
- * larger than NSEC_PER_SEC.
- */
-static void
-itc_update (long delta_nsec)
-{
-}
-
-/*
- * Return the number of nano-seconds that elapsed since the last
- * update to jiffy. It is quite possible that the timer interrupt
- * will interrupt this and result in a race for any of jiffies,
- * wall_jiffies or itm_next. Thus, the xtime_lock must be at least
- * read synchronised when calling this routine (see do_gettimeofday()
- * below for an example).
- */
-unsigned long
-itc_get_offset (void)
-{
- unsigned long elapsed_cycles, lost = jiffies - wall_jiffies;
- unsigned long now = ia64_get_itc(), last_tick;
-
- last_tick = (cpu_data(TIME_KEEPER_ID)->itm_next
- - (lost + 1)*cpu_data(TIME_KEEPER_ID)->itm_delta);
-
- elapsed_cycles = now - last_tick;
- return (elapsed_cycles*local_cpu_data->nsec_per_cyc) >> IA64_NSEC_PER_CYC_SHIFT;
-}
-
-static struct time_interpolator itc_interpolator = {
- .get_offset = itc_get_offset,
- .update = itc_update,
- .reset = itc_reset
-};
+static struct time_interpolator itc_interpolator;
int
do_settimeofday (struct timespec *tv)
@@ -127,53 +88,15 @@
void
do_gettimeofday (struct timeval *tv)
{
- unsigned long seq, nsec, usec, sec, old, offset;
-
- while (1) {
+ unsigned long seq, nsec, usec, sec, offset;
+ do {
seq = read_seqbegin(&xtime_lock);
- {
- old = last_nsec_offset;
- offset = time_interpolator_get_offset();
- sec = xtime.tv_sec;
- nsec = xtime.tv_nsec;
- }
- if (unlikely(read_seqretry(&xtime_lock, seq)))
- continue;
- /*
- * Ensure that for any pair of causally ordered gettimeofday() calls, time
- * never goes backwards (even when ITC on different CPUs are not perfectly
- * synchronized). (A pair of concurrent calls to gettimeofday() is by
- * definition non-causal and hence it makes no sense to talk about
- * time-continuity for such calls.)
- *
- * Doing this in a lock-free and race-free manner is tricky. Here is why
- * it works (most of the time): read_seqretry() just succeeded, which
- * implies we calculated a consistent (valid) value for "offset". If the
- * cmpxchg() below succeeds, we further know that last_nsec_offset still
- * has the same value as at the beginning of the loop, so there was
- * presumably no timer-tick or other updates to last_nsec_offset in the
- * meantime. This isn't 100% true though: there _is_ a possibility of a
- * timer-tick occurring right right after read_seqretry() and then getting
- * zero or more other readers which will set last_nsec_offset to the same
- * value as the one we read at the beginning of the loop. If this
- * happens, we'll end up returning a slightly newer time than we ought to
- * (the jump forward is at most "offset" nano-seconds). There is no
- * danger of causing time to go backwards, though, so we are safe in that
- * sense. We could make the probability of this unlucky case occurring
- * arbitrarily small by encoding a version number in last_nsec_offset, but
- * even without versioning, the probability of this unlucky case should be
- * so small that we won't worry about it.
- */
- if (offset <= old) {
- offset = old;
- break;
- } else if (likely(cmpxchg(&last_nsec_offset, old, offset) == old))
- break;
-
- /* someone else beat us to updating last_nsec_offset; try again */
- }
+ offset = time_interpolator_get_offset();
+ sec = xtime.tv_sec;
+ nsec = xtime.tv_nsec;
+ } while (unlikely(read_seqretry(&xtime_lock, seq)));
- usec = (nsec + offset) / 1000;
+ usec = (nsec + offset) / 1000;
while (unlikely(usec >= USEC_PER_SEC)) {
usec -= USEC_PER_SEC;
@@ -385,7 +308,10 @@
if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT)) {
itc_interpolator.frequency = local_cpu_data->itc_freq;
+ itc_interpolator.shift = 0;
itc_interpolator.drift = itc_drift;
+ itc_interpolator.source = TIME_SOURCE_CPU;
+ itc_interpolator.addr = NULL;
register_time_interpolator(&itc_interpolator);
}
Index: linux-2.6.7/arch/ia64/sn/kernel/sn2/timer.c
===================================================================
--- linux-2.6.7.orig/arch/ia64/sn/kernel/sn2/timer.c
+++ linux-2.6.7/arch/ia64/sn/kernel/sn2/timer.c
@@ -20,57 +20,16 @@
extern unsigned long sn_rtc_cycles_per_second;
-static volatile unsigned long last_wall_rtc;
-static unsigned long rtc_offset; /* updated only when xtime write-lock is held! */
-static long rtc_nsecs_per_cycle;
-static long rtc_per_timer_tick;
-
-static unsigned long
-getoffset(void)
-{
- return rtc_offset + (GET_RTC_COUNTER() - last_wall_rtc)*rtc_nsecs_per_cycle;
-}
-
-
-static void
-update(long delta_nsec)
-{
- unsigned long rtc_counter = GET_RTC_COUNTER();
- unsigned long offset = rtc_offset + (rtc_counter - last_wall_rtc)*rtc_nsecs_per_cycle;
-
- /* Be careful about signed/unsigned comparisons here: */
- if (delta_nsec < 0 || (unsigned long) delta_nsec < offset)
- rtc_offset = offset - delta_nsec;
- else
- rtc_offset = 0;
- last_wall_rtc = rtc_counter;
-}
-
-
-static void
-reset(void)
-{
- rtc_offset = 0;
- last_wall_rtc = GET_RTC_COUNTER();
-}
-
-
-static struct time_interpolator sn2_interpolator = {
- .get_offset = getoffset,
- .update = update,
- .reset = reset
-};
+static struct time_interpolator sn2_interpolator;
void __init
sn_timer_init(void)
{
sn2_interpolator.frequency = sn_rtc_cycles_per_second;
sn2_interpolator.drift = -1; /* unknown */
+ sn2_interpolator.shift = 0; /* RTC is 54 bits maximum shift is 10 */
+ sn2_interpolator.addr = RTC_COUNTER_ADDR;
+ sn2_interpolator.source = TIME_SOURCE_MMIO64;
register_time_interpolator(&sn2_interpolator);
-
- rtc_per_timer_tick = sn_rtc_cycles_per_second / HZ;
- rtc_nsecs_per_cycle = 1000000000 / sn_rtc_cycles_per_second;
-
- last_wall_rtc = GET_RTC_COUNTER();
}
Index: linux-2.6.7/include/linux/timex.h
===================================================================
--- linux-2.6.7.orig/include/linux/timex.h
+++ linux-2.6.7/include/linux/timex.h
@@ -55,6 +55,7 @@
#include <linux/compiler.h>
#include <asm/param.h>
+#include <asm/io.h>
/*
* The following defines establish the engineering parameters of the PLL
@@ -320,81 +321,92 @@
#ifdef CONFIG_TIME_INTERPOLATION
-struct time_interpolator {
- /* cache-hot stuff first: */
- unsigned long (*get_offset) (void);
- void (*update) (long);
- void (*reset) (void);
+#define TIME_SOURCE_CPU 0
+#define TIME_SOURCE_MMIO64 1
+#define TIME_SOURCE_MMIO32 2
+#define TIME_SOURCE_FUNCTION 3
- /* cache-cold stuff follows here: */
- struct time_interpolator *next;
+struct time_interpolator {
+ unsigned short source; /* type of time source */
+ unsigned short shift; /* increases accuracy of multiply by shifting. */
+ /* Note that bits may be lost if shift is set too high */
+ unsigned nsec_per_cyc; /* set by register_time_interpolator() */
+ void *addr; /* address of counter or function */
unsigned long frequency; /* frequency in counts/second */
long drift; /* drift in parts-per-million (or -1) */
+ struct time_interpolator *next;
};
-extern volatile unsigned long last_nsec_offset;
-#ifndef __HAVE_ARCH_CMPXCHG
-extern spin_lock_t last_nsec_offset_lock;
-#endif
extern struct time_interpolator *time_interpolator;
-extern void register_time_interpolator(struct time_interpolator *);
-extern void unregister_time_interpolator(struct time_interpolator *);
-
-/* Called with xtime WRITE-lock acquired. */
-static inline void
-time_interpolator_update(long delta_nsec)
+static inline unsigned long
+time_interpolator_get_counter(void)
{
- struct time_interpolator *ti = time_interpolator;
+ unsigned long (*x)(void);
- if (last_nsec_offset > 0) {
-#ifdef __HAVE_ARCH_CMPXCHG
- unsigned long new, old;
-
- do {
- old = last_nsec_offset;
- if (old > delta_nsec)
- new = old - delta_nsec;
- else
- new = 0;
- } while (cmpxchg(&last_nsec_offset, old, new) != old);
-#else
- /*
- * This really hurts, because it serializes gettimeofday(), but without an
- * atomic single-word compare-and-exchange, there isn't all that much else
- * we can do.
- */
- spin_lock(&last_nsec_offset_lock);
- {
- last_nsec_offset -= min(last_nsec_offset, delta_nsec);
- }
- spin_unlock(&last_nsec_offset_lock);
-#endif
+ switch (time_interpolator->source)
+ {
+ case TIME_SOURCE_FUNCTION:
+ x=time_interpolator->addr;
+ return x();
+
+ case TIME_SOURCE_MMIO64 : return readq(time_interpolator->addr);
+ case TIME_SOURCE_MMIO32 : return readl(time_interpolator->addr);
+ default: return get_cycles();
}
-
- if (ti)
- (*ti->update)(delta_nsec);
}
-/* Called with xtime WRITE-lock acquired. */
+/* Offset from last_counter in nsecs */
+extern unsigned long time_interpolator_offset;
+
+/* Counter value in units of the counter */
+extern unsigned long time_interpolator_last_counter;
+
+extern void register_time_interpolator(struct time_interpolator *);
+extern void unregister_time_interpolator(struct time_interpolator *);
+
static inline void
time_interpolator_reset(void)
{
- struct time_interpolator *ti = time_interpolator;
-
- last_nsec_offset = 0;
- if (ti)
- (*ti->reset)();
+ time_interpolator_offset = 0;
+ time_interpolator_last_counter = time_interpolator_get_counter();
}
-/* Called with xtime READ-lock acquired. */
+#define GET_TI_NSECS(count,i) ((((count) - time_interpolator_last_counter) * i->nsec_per_cyc) >> i->shift )
+
static inline unsigned long
time_interpolator_get_offset(void)
{
- struct time_interpolator *ti = time_interpolator;
- if (ti)
- return (*ti->get_offset)();
- return last_nsec_offset;
+ return time_interpolator_offset +
+ GET_TI_NSECS(time_interpolator_get_counter(),time_interpolator);
+}
+
+static inline void time_interpolator_update(long delta_nsec)
+{
+ unsigned long counter=time_interpolator_get_counter();
+ unsigned long offset=time_interpolator_offset + GET_TI_NSECS(counter,time_interpolator);
+
+ /* Traditional mysterious code piece for time interpolators.
+ If the correction forward would result in a negative offset
+ then the offset is reset to zero thereby providing
+ a means for synchronization. This will occur because
+ 1. The scaling factor has been calculated in such a way as
+ to insure that the time interpolator runs SLOWER than real time.
+ Timer interrupts on time will therefore reset the time interpolator in regular
+ intervals. A late timer interrupt will leave the offset running.
+ (this may lead to a minimal time jump forward before a tick but insures
+ that time never goes backward)
+ 2. warp_clock and leap seconds since the delta_nsec specified
+ in these situations is far too large.
+ 3. After the interpolator initialization when the first call to
+ time_interpolator_update by the timer code occurs which will specify
+ a delta that is too large.
+ */
+ if (delta_nsec < 0 || (unsigned long) delta_nsec < offset)
+ time_interpolator_offset = offset - delta_nsec;
+ else
+ time_interpolator_offset = 0;
+ time_interpolator_last_counter = counter;
}
#else /* !CONFIG_TIME_INTERPOLATION */
Index: linux-2.6.7/kernel/timer.c
===================================================================
--- linux-2.6.7.orig/kernel/timer.c
+++ linux-2.6.7/kernel/timer.c
@@ -1425,31 +1425,36 @@
}
#ifdef CONFIG_TIME_INTERPOLATION
-volatile unsigned long last_nsec_offset;
-#ifndef __HAVE_ARCH_CMPXCHG
-spinlock_t last_nsec_offset_lock = SPIN_LOCK_UNLOCKED;
-#endif
struct time_interpolator *time_interpolator;
static struct time_interpolator *time_interpolator_list;
static spinlock_t time_interpolator_lock = SPIN_LOCK_UNLOCKED;
+unsigned long time_interpolator_offset;
+unsigned long time_interpolator_last_counter;
static inline int
is_better_time_interpolator(struct time_interpolator *new)
{
if (!time_interpolator)
return 1;
- return new->frequency > 2*time_interpolator->frequency ||
+ return new->frequency > 2 * time_interpolator->frequency ||
(unsigned long)new->drift < (unsigned long)time_interpolator->drift;
}
void
register_time_interpolator(struct time_interpolator *ti)
{
+ /* Must not round up. The interpolator update code relies on offsets
+ being calculated too short so that a resync can take place once in a while
+ */
+ ti->nsec_per_cyc = (NSEC_PER_SEC << ti->shift) / ti->frequency;
spin_lock(&time_interpolator_lock);
write_seqlock_irq(&xtime_lock);
if (is_better_time_interpolator(ti))
+ {
time_interpolator = ti;
+ time_interpolator_reset();
+ }
write_sequnlock_irq(&xtime_lock);
ti->next = time_interpolator_list;
@@ -1480,6 +1485,7 @@
for (curr = time_interpolator_list; curr; curr = curr->next)
if (is_better_time_interpolator(curr))
time_interpolator = curr;
+ time_interpolator_reset();
}
write_sequnlock_irq(&xtime_lock);
spin_unlock(&time_interpolator_lock);
Index: linux-2.6.7/arch/ia64/kernel/asm-offsets.c
===================================================================
--- linux-2.6.7.orig/arch/ia64/kernel/asm-offsets.c
+++ linux-2.6.7/arch/ia64/kernel/asm-offsets.c
@@ -208,4 +208,12 @@
BLANK();
DEFINE(IA64_MCA_TLB_INFO_SIZE, sizeof (struct ia64_mca_tlb_info));
+ BLANK();
+ DEFINE(IA64_TIME_INTERPOLATOR_ADDRESS_OFFSET, offsetof (struct time_interpolator, addr));
+ DEFINE(IA64_TIME_INTERPOLATOR_SOURCE_OFFSET, offsetof (struct time_interpolator, source));
+ DEFINE(IA64_TIME_INTERPOLATOR_SHIFT_OFFSET, offsetof (struct time_interpolator, shift));
+ DEFINE(IA64_TIME_INTERPOLATOR_NSEC_OFFSET, offsetof (struct time_interpolator, nsec_per_cyc));
+ DEFINE(IA64_TIME_SOURCE_CPU,TIME_SOURCE_CPU);
+ DEFINE(IA64_TIME_SOURCE_MMIO64, TIME_SOURCE_MMIO64);
+ DEFINE(IA64_TIME_SOURCE_MMIO32, TIME_SOURCE_MMIO32);
}