[IA64] Convert to generic timekeeping/clocksource
This is a merge of Peter Keilty's initial patch (which was
revived by Bob Picco) for this with Hidetoshi Seto's fixes
and scaling improvements.
Acked-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index 3f926c2..4484197 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -147,12 +147,11 @@
FSYS_RETURN
END(fsys_set_tid_address)
-/*
- * 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_JITTER_OFFSET != 3 || IA64_TIME_INTERPOLATOR_NSEC_OFFSET != 4
-#error fsys_gettimeofday incompatible with changes to struct time_interpolator
+#if IA64_GTOD_LOCK_OFFSET !=0
+#error fsys_gettimeofday incompatible with changes to struct fsyscall_gtod_data_t
+#endif
+#if IA64_ITC_JITTER_OFFSET !=0
+#error fsys_gettimeofday incompatible with changes to struct itc_jitter_data_t
#endif
#define CLOCK_REALTIME 0
#define CLOCK_MONOTONIC 1
@@ -179,126 +178,124 @@
// r11 = preserved: saved ar.pfs
// r12 = preserved: memory stack
// r13 = preserved: thread pointer
- // r14 = address of mask / mask
+ // r14 = address of mask / mask value
// r15 = preserved: system call number
// r16 = preserved: current task pointer
- // r17 = wall to monotonic use
- // r18 = time_interpolator->offset
- // r19 = address of wall_to_monotonic
- // r20 = pointer to struct time_interpolator / pointer to time_interpolator->address
- // r21 = shift factor
- // r22 = address of time interpolator->last_counter
- // r23 = address of time_interpolator->last_cycle
- // r24 = adress of time_interpolator->offset
- // r25 = last_cycle value
- // r26 = last_counter value
- // r27 = pointer to xtime
+ // r17 = (not used)
+ // r18 = (not used)
+ // r19 = address of itc_lastcycle
+ // r20 = struct fsyscall_gtod_data (= address of gtod_lock.sequence)
+ // r21 = address of mmio_ptr
+ // r22 = address of wall_time or monotonic_time
+ // r23 = address of shift / value
+ // r24 = address mult factor / cycle_last value
+ // r25 = itc_lastcycle value
+ // r26 = address clocksource cycle_last
+ // r27 = (not used)
// r28 = sequence number at the beginning of critcal section
- // r29 = address of seqlock
+ // r29 = address of itc_jitter
// r30 = time processing flags / memory address
// r31 = pointer to result
// Predicates
// p6,p7 short term use
// p8 = timesource ar.itc
// p9 = timesource mmio64
- // p10 = timesource mmio32
+ // p10 = timesource mmio32 - not used
// p11 = timesource not to be handled by asm code
- // p12 = memory time source ( = p9 | p10)
- // p13 = do cmpxchg with time_interpolator_last_cycle
+ // p12 = memory time source ( = p9 | p10) - not used
+ // p13 = do cmpxchg with itc_lastcycle
// p14 = Divide by 1000
// p15 = Add monotonic
//
- // Note that instructions are optimized for McKinley. McKinley can process two
- // bundles simultaneously and therefore we continuously try to feed the CPU
- // two bundles and then a stop.
- tnat.nz p6,p0 = r31 // branch deferred since it does not fit into bundle structure
+ // Note that instructions are optimized for McKinley. McKinley can
+ // process two bundles simultaneously and therefore we continuously
+ // try to feed the CPU two bundles and then a stop.
+ //
+ // Additional note that code has changed a lot. Optimization is TBD.
+ // Comments begin with "?" are maybe outdated.
+ tnat.nz p6,p0 = r31 // ? branch deferred to fit later bundle
mov pr = r30,0xc000 // Set predicates according to function
add r2 = TI_FLAGS+IA64_TASK_SIZE,r16
- movl r20 = time_interpolator
+ movl r20 = fsyscall_gtod_data // load fsyscall gettimeofday data address
;;
- ld8 r20 = [r20] // get pointer to time_interpolator structure
- movl r29 = xtime_lock
+ movl r29 = itc_jitter_data // itc_jitter
+ add r22 = IA64_GTOD_WALL_TIME_OFFSET,r20 // wall_time
ld4 r2 = [r2] // process work pending flags
- movl r27 = xtime
- ;; // only one bundle here
- ld8 r21 = [r20] // first quad with control information
- and r2 = TIF_ALLWORK_MASK,r2
-(p6) br.cond.spnt.few .fail_einval // deferred branch
;;
- add r10 = IA64_TIME_INTERPOLATOR_ADDRESS_OFFSET,r20
- extr r3 = r21,32,32 // time_interpolator->nsec_per_cyc
- extr r8 = r21,0,16 // time_interpolator->source
+(p15) add r22 = IA64_GTOD_MONO_TIME_OFFSET,r20 // monotonic_time
+ add r21 = IA64_CLKSRC_MMIO_OFFSET,r20
+ add r19 = IA64_ITC_LASTCYCLE_OFFSET,r29
+ and r2 = TIF_ALLWORK_MASK,r2
+(p6) br.cond.spnt.few .fail_einval // ? deferred branch
+ ;;
+ add r26 = IA64_CLKSRC_CYCLE_LAST_OFFSET,r20 // clksrc_cycle_last
cmp.ne p6, p0 = 0, r2 // Fallback if work is scheduled
(p6) br.cond.spnt.many fsys_fallback_syscall
;;
- cmp.eq p8,p12 = 0,r8 // Check for cpu timer
- cmp.eq p9,p0 = 1,r8 // MMIO64 ?
- extr r2 = r21,24,8 // time_interpolator->jitter
- cmp.eq p10,p0 = 2,r8 // MMIO32 ?
- cmp.ltu p11,p0 = 2,r8 // function or other clock
-(p11) br.cond.spnt.many fsys_fallback_syscall
- ;;
- setf.sig f7 = r3 // Setup for scaling of counter
-(p15) movl r19 = wall_to_monotonic
-(p12) ld8 r30 = [r10]
- cmp.ne p13,p0 = r2,r0 // need jitter compensation?
- extr r21 = r21,16,8 // shift factor
- ;;
+ // Begin critical section
.time_redo:
- .pred.rel.mutex p8,p9,p10
- ld4.acq r28 = [r29] // xtime_lock.sequence. Must come first for locking purposes
+ ld4.acq r28 = [r20] // gtod_lock.sequence, Must take first
;;
- and r28 = ~1,r28 // Make sequence even to force retry if odd
+ and r28 = ~1,r28 // And make sequence even to force retry if odd
;;
+ ld8 r30 = [r21] // clocksource->mmio_ptr
+ add r24 = IA64_CLKSRC_MULT_OFFSET,r20
+ ld4 r2 = [r29] // itc_jitter value
+ add r23 = IA64_CLKSRC_SHIFT_OFFSET,r20
+ add r14 = IA64_CLKSRC_MASK_OFFSET,r20
+ ;;
+ ld4 r3 = [r24] // clocksource mult value
+ ld8 r14 = [r14] // clocksource mask value
+ cmp.eq p8,p9 = 0,r30 // use cpu timer if no mmio_ptr
+ ;;
+ setf.sig f7 = r3 // Setup for mult scaling of counter
+(p8) cmp.ne p13,p0 = r2,r0 // need itc_jitter compensation, set p13
+ ld4 r23 = [r23] // clocksource shift value
+ ld8 r24 = [r26] // get clksrc_cycle_last value
+(p9) cmp.eq p13,p0 = 0,r30 // if mmio_ptr, clear p13 jitter control
+ ;;
+ .pred.rel.mutex p8,p9
(p8) mov r2 = ar.itc // CPU_TIMER. 36 clocks latency!!!
- add r22 = IA64_TIME_INTERPOLATOR_LAST_COUNTER_OFFSET,r20
-(p9) ld8 r2 = [r30] // readq(ti->address). Could also have latency issues..
-(p10) ld4 r2 = [r30] // readw(ti->address)
-(p13) add r23 = IA64_TIME_INTERPOLATOR_LAST_CYCLE_OFFSET,r20
- ;; // could be removed by moving the last add upward
- ld8 r26 = [r22] // time_interpolator->last_counter
-(p13) ld8 r25 = [r23] // time interpolator->last_cycle
- add r24 = IA64_TIME_INTERPOLATOR_OFFSET_OFFSET,r20
-(p15) ld8 r17 = [r19],IA64_TIMESPEC_TV_NSEC_OFFSET
- ld8 r9 = [r27],IA64_TIMESPEC_TV_NSEC_OFFSET
- add r14 = IA64_TIME_INTERPOLATOR_MASK_OFFSET, r20
+(p9) ld8 r2 = [r30] // MMIO_TIMER. Could also have latency issues..
+(p13) ld8 r25 = [r19] // get itc_lastcycle value
+ ;; // ? could be removed by moving the last add upward
+ ld8 r9 = [r22],IA64_TIMESPEC_TV_NSEC_OFFSET // tv_sec
;;
- ld8 r18 = [r24] // time_interpolator->offset
- ld8 r8 = [r27],-IA64_TIMESPEC_TV_NSEC_OFFSET // xtime.tv_nsec
-(p13) sub r3 = r25,r2 // Diff needed before comparison (thanks davidm)
+ ld8 r8 = [r22],-IA64_TIMESPEC_TV_NSEC_OFFSET // tv_nsec
+(p13) sub r3 = r25,r2 // Diff needed before comparison (thanks davidm)
;;
- ld8 r14 = [r14] // time_interpolator->mask
-(p13) cmp.gt.unc p6,p7 = r3,r0 // check if it is less than last. p6,p7 cleared
- sub r10 = r2,r26 // current_counter - last_counter
+(p13) cmp.gt.unc p6,p7 = r3,r0 // check if it is less than last. p6,p7 cleared
+ sub r10 = r2,r24 // current_cycle - last_cycle
;;
-(p6) sub r10 = r25,r26 // time we got was less than last_cycle
+(p6) sub r10 = r25,r24 // time we got was less than last_cycle
(p7) mov ar.ccv = r25 // more than last_cycle. Prep for cmpxchg
;;
+(p7) cmpxchg8.rel r3 = [r19],r2,ar.ccv
+ ;;
+(p7) cmp.ne p7,p0 = r25,r3 // if cmpxchg not successful
+ ;;
+(p7) sub r10 = r3,r24 // then use new last_cycle instead
+ ;;
and r10 = r10,r14 // Apply mask
;;
setf.sig f8 = r10
nop.i 123
;;
-(p7) cmpxchg8.rel r3 = [r23],r2,ar.ccv
-EX(.fail_efault, probe.w.fault r31, 3) // This takes 5 cycles and we have spare time
+ // fault check takes 5 cycles and we have spare time
+EX(.fail_efault, probe.w.fault r31, 3)
xmpy.l f8 = f8,f7 // nsec_per_cyc*(counter-last_counter)
-(p15) add r9 = r9,r17 // Add wall to monotonic.secs to result secs
;;
-(p15) ld8 r17 = [r19],-IA64_TIMESPEC_TV_NSEC_OFFSET
-(p7) cmp.ne p7,p0 = r25,r3 // if cmpxchg not successful redo
- // simulate tbit.nz.or p7,p0 = r28,0
+ // ? simulate tbit.nz.or p7,p0 = r28,0
getf.sig r2 = f8
mf
- add r8 = r8,r18 // Add time interpolator offset
;;
- ld4 r10 = [r29] // xtime_lock.sequence
-(p15) add r8 = r8, r17 // Add monotonic.nsecs to nsecs
- shr.u r2 = r2,r21
- ;; // overloaded 3 bundles!
- // End critical section.
+ ld4 r10 = [r20] // gtod_lock.sequence
+ shr.u r2 = r2,r23 // shift by factor
+ ;; // ? overloaded 3 bundles!
add r8 = r8,r2 // Add xtime.nsecs
- cmp4.ne.or p7,p0 = r28,r10
-(p7) br.cond.dpnt.few .time_redo // sequence number changed ?
+ cmp4.ne p7,p0 = r28,r10
+(p7) br.cond.dpnt.few .time_redo // sequence number changed, redo
+ // End critical section.
// Now r8=tv->tv_nsec and r9=tv->tv_sec
mov r10 = r0
movl r2 = 1000000000
@@ -308,19 +305,19 @@
.time_normalize:
mov r21 = r8
cmp.ge p6,p0 = r8,r2
-(p14) shr.u r20 = r8, 3 // We can repeat this if necessary just wasting some time
+(p14) shr.u r20 = r8, 3 // We can repeat this if necessary just wasting time
;;
(p14) setf.sig f8 = r20
(p6) sub r8 = r8,r2
-(p6) add r9 = 1,r9 // two nops before the branch.
-(p14) setf.sig f7 = r3 // Chances for repeats are 1 in 10000 for gettod
+(p6) add r9 = 1,r9 // two nops before the branch.
+(p14) setf.sig f7 = r3 // Chances for repeats are 1 in 10000 for gettod
(p6) br.cond.dpnt.few .time_normalize
;;
// Divided by 8 though shift. Now divide by 125
// The compiler was able to do that with a multiply
// and a shift and we do the same
-EX(.fail_efault, probe.w.fault r23, 3) // This also costs 5 cycles
-(p14) xmpy.hu f8 = f8, f7 // xmpy has 5 cycles latency so use it...
+EX(.fail_efault, probe.w.fault r23, 3) // This also costs 5 cycles
+(p14) xmpy.hu f8 = f8, f7 // xmpy has 5 cycles latency so use it
;;
mov r8 = r0
(p14) getf.sig r2 = f8