- USIII-based machines can consist of CPUs running at different

  frequencies (and having different cache sizes) so use the STICK
  (System TICK) timer, which was introduced due to this and is
  driven by the same frequency across all CPUs, instead of the
  TICK timer, whose frequency varies with the CPU clock, to drive
  hardclock. We try to use the STICK counter with all CPUs that are
  USIII or beyond, even when not necessary due to identical CPUs,
  as we can can also avoid the workaround for the BlackBird erratum
  #1 there. Unfortunately, using the STICK counter currently causes
  a hang with USIIIi MP machines for reasons unknown, so we still
  use the TICK timer there (which is okay as they can only consist
  of identical CPUs).
- Given that we only (try to) synchronize the (S)TICK timers of APs
  with the BSP during startup, we could end up spinning forever in
  DELAY(9) if that function is migrated to another CPU while we're
  spinning due to clock drift afterwards, so pin to the CPU in order
  to avoid migration. Unfortunately, pinning doesn't work at the
  point DELAY(9) is required by the low-level console drivers, yet,
  so switch to a function pointer, which is updated accordingly, for
  implementing DELAY(9). For USIII and beyond, this would also allow
  to easily use the STICK counter instead of the TICK one here,
  there's no benefit in doing so however.
  While at it, use cpu_spinwait(9) for spinning in the delay-
  functions. This currently is a NOP though.
- Don't set the TICK timer of the BSP to 0 during at startup as
  there's no need to do so.
- Implement cpu_est_clockrate().
- Unfortunately, USIIIi-based machines don't provide a timecounter
  device besides the STICK and TICK counters (well, in theory the
  Tomatillo bridges have a performance counter that can be (ab)used
  as timecounter by configuring it to count bus cycles, though unlike
  the performance counter of Schizo bridges, the Tomatillo one is
  broken and counts Sun knows what in this mode). This means that
  we've to use a (S)TICK counter for timecounting, which has the old
  problem of not being in sync across CPUs, so provide an additional
  timecounter function which binds itself to the BSP but has an
  adequate low priority.

6 files changed, 25 insertions, 7 deletions

diff --git a/sys/sparc64/include/clock.h b/sys/sparc64/include/clock.h
index b0e4c0b..fd57731 100644
--- a/sys/sparc64/include/clock.h
+++ b/sys/sparc64/include/clock.h
@@ -29,8 +29,10 @@
 #ifndef	_MACHINE_CLOCK_H_
 #define	_MACHINE_CLOCK_H_
 
-extern u_long tick_increment;
-extern u_long tick_freq;
-extern u_long tick_MHz;
+extern void (*delay_func)(int usec);
+extern u_long clock_boot;
+
+void delay_boot(int usec);
+void delay_tick(int usec);
 
 #endif /* !_MACHINE_CLOCK_H_ */
diff --git a/sys/sparc64/include/cpufunc.h b/sys/sparc64/include/cpufunc.h
index fca5984..60533f8 100644
--- a/sys/sparc64/include/cpufunc.h
+++ b/sys/sparc64/include/cpufunc.h
@@ -174,6 +174,15 @@ int fasword32(u_long asi, void *addr, uint32_t *val);
 } while (0)
 
 /*
+ * Trick GAS/GCC into compiling access to STICK/STICK_COMPARE independently
+ * of the selected instruction set.
+ */
+#define	rdstick()		rd(asr24)
+#define	rdstickcmpr()		rd(asr25)
+#define	wrstick(val, xor)	wr(asr24, (val), (xor))
+#define	wrstickcmpr(val, xor)	wr(asr25, (val), (xor))
+
+/*
  * Macro intended to be used instead of wr(asr23, val, xor) for writing to
  * the TICK_COMPARE register in order to avoid a bug in BlackBird CPUs that
  * can cause these writes to fail under certain condidtions which in turn
diff --git a/sys/sparc64/include/pcpu.h b/sys/sparc64/include/pcpu.h
index 2ccdbd9..efb5174 100644
--- a/sys/sparc64/include/pcpu.h
+++ b/sys/sparc64/include/pcpu.h
@@ -53,6 +53,7 @@ struct pmap;
 	vm_offset_t pc_addr;						\
 	u_long	pc_tickref;						\
 	u_long	pc_tickadj;						\
+	u_int	pc_clock;						\
 	u_int	pc_mid;							\
 	u_int	pc_node;						\
 	u_int	pc_tlb_ctx;						\
diff --git a/sys/sparc64/include/smp.h b/sys/sparc64/include/smp.h
index 3e1d9ac..23076ef 100644
--- a/sys/sparc64/include/smp.h
+++ b/sys/sparc64/include/smp.h
@@ -29,9 +29,10 @@
 #ifndef	_MACHINE_SMP_H_
 #define	_MACHINE_SMP_H_
 
-#define	CPU_CLKSYNC		1
-#define	CPU_INIT		2
-#define	CPU_BOOTSTRAP		3
+#define	CPU_TICKSYNC		1
+#define	CPU_STICKSYNC		2
+#define	CPU_INIT		3
+#define	CPU_BOOTSTRAP		4
 
 #ifndef	LOCORE
 
@@ -62,6 +63,7 @@ struct cpu_start_args {
 	u_int	csa_state;
 	vm_offset_t csa_pcpu;
 	u_long	csa_tick;
+	u_long	csa_stick;
 	u_long	csa_ver;
 	struct	tte csa_ttes[PCPU_PAGES];
 };
diff --git a/sys/sparc64/include/tick.h b/sys/sparc64/include/tick.h
index 8586a0d..456e9f0 100644
--- a/sys/sparc64/include/tick.h
+++ b/sys/sparc64/include/tick.h
@@ -29,7 +29,7 @@
 #ifndef _MACHINE_TICK_H_
 #define	_MACHINE_TICK_H_
 
-void	tick_init(u_long clock);
+void	tick_clear(void);
 void	tick_start(void);
 void	tick_stop(void);
 
diff --git a/sys/sparc64/include/ver.h b/sys/sparc64/include/ver.h
index 78e57d8..0fb7933 100644
--- a/sys/sparc64/include/ver.h
+++ b/sys/sparc64/include/ver.h
@@ -41,6 +41,8 @@
 #define	VER_MAXTL_SIZE		(8)
 #define	VER_MAXWIN_SIZE		(5)
 
+#ifndef LOCORE
+
 #define	VER_MANUF_MASK		(((1L<<VER_MANUF_SIZE)-1)<<VER_MANUF_SHIFT)
 #define	VER_IMPL_MASK		(((1L<<VER_IMPL_SIZE)-1)<<VER_IMPL_SHIFT)
 #define	VER_MASK_MASK		(((1L<<VER_MASK_SIZE)-1)<<VER_MASK_SHIFT)
@@ -61,6 +63,8 @@
 extern int cpu_impl;
 extern char sparc64_model[];
 
+#endif /* !LOCORE */
+
 /* Known implementations. */
 #define	CPU_IMPL_SPARC64		0x01
 #define	CPU_IMPL_ULTRASPARCI		0x10