hwpmc: Fix amd/arm64/armv7/uncore sampling overflow race

If a counter more than overflows just as we read it on switch out then,
if using sampling mode, we will negate this small value to give a huge
reload count, and if we later switch back in that context we will
validate that value against pm_reloadcount and panic an INVARIANTS
kernel with:

  panic: [pmc,1470] pmcval outside of expected range cpu=2 ri=16 pmcval=fffff292 pm_reloadcount=10000

or similar. Presumably in a non-INVARIANTS kernel we will instead just
use the provided value as the reload count, which would lead to the
overflow not happing for a very long time (e.g. 78 minutes for a 48-bit
counter incrementing at an averate rate of 1GHz).

Instead, clamp the reload count to 0 (which corresponds precisely to the
value we would compute if it had just overflowed and no more), which
will result in hwpmc using the full original reload count again. This is
the approach used by core for Intel (for both fixed and programmable
counters).

As part of this, armv7 and arm64 are made conceptually simpler; rather
than skipping modifying the overflow count for sampling mode counters so
it's always kept as ~0, those special cases are removed so it's always
applicable and the concatentation of it and the hardware counter can
always be viewed as a 64-bit counter, which also makes them look more
like other architectures.

Whilst here, fix an instance of UB (shifting a 1 into the sign bit) for
amd in its sign-extension code.

Reviewed by:	andrew, mhorne, kib
MFC after:	1 week
Differential Revision:	https://reviews.freebsd.org/D33654

1 files changed, 16 insertions, 9 deletions

diff --git a/sys/dev/hwpmc/hwpmc_arm64.c b/sys/dev/hwpmc/hwpmc_arm64.c
index 14c176894c6a..988cd1744a07 100644
--- a/sys/dev/hwpmc/hwpmc_arm64.c
+++ b/sys/dev/hwpmc/hwpmc_arm64.c
@@ -218,8 +218,7 @@ arm64_read_pmc(int cpu, int ri, pmc_value_t *v)
 	if ((READ_SPECIALREG(pmovsclr_el0) & reg) != 0) {
 		/* Clear Overflow Flag */
 		WRITE_SPECIALREG(pmovsclr_el0, reg);
-		if (!PMC_IS_SAMPLING_MODE(PMC_TO_MODE(pm)))
-			pm->pm_pcpu_state[cpu].pps_overflowcnt++;
+		pm->pm_pcpu_state[cpu].pps_overflowcnt++;
 
 		/* Reread counter in case we raced. */
 		tmp = arm64_pmcn_read(ri);
@@ -228,10 +227,18 @@ arm64_read_pmc(int cpu, int ri, pmc_value_t *v)
 	intr_restore(s);
 
 	PMCDBG2(MDP, REA, 2, "arm64-read id=%d -> %jd", ri, tmp);
-	if (PMC_IS_SAMPLING_MODE(PMC_TO_MODE(pm)))
-		*v = ARMV8_PERFCTR_VALUE_TO_RELOAD_COUNT(tmp);
-	else
-		*v = tmp;
+	if (PMC_IS_SAMPLING_MODE(PMC_TO_MODE(pm))) {
+		/*
+		 * Clamp value to 0 if the counter just overflowed,
+		 * otherwise the returned reload count would wrap to a
+		 * huge value.
+		 */
+		if ((tmp & (1ull << 63)) == 0)
+			tmp = 0;
+		else
+			tmp = ARMV8_PERFCTR_VALUE_TO_RELOAD_COUNT(tmp);
+	}
+	*v = tmp;
 
 	return (0);
 }
@@ -379,10 +386,10 @@ arm64_intr(struct trapframe *tf)
 
 		retval = 1; /* Found an interrupting PMC. */
 
-		if (!PMC_IS_SAMPLING_MODE(PMC_TO_MODE(pm))) {
-			pm->pm_pcpu_state[cpu].pps_overflowcnt += 1;
+		pm->pm_pcpu_state[cpu].pps_overflowcnt += 1;
+
+		if (!PMC_IS_SAMPLING_MODE(PMC_TO_MODE(pm)))
 			continue;
-		}
 
 		if (pm->pm_state != PMC_STATE_RUNNING)
 			continue;