arm64/boot: Disable trapping of PMZR_EL0 writes to EL2grafted

__init_el2_fgt2() writes one mask to both HDFGRTR2_EL2 and HDFGWTR2_EL2.
PMZR_EL0 is write-only, so its trap bit, nPMZR_EL0, exists only in
HDFGWTR2_EL2 and is therefore never set: a PMZR_EL0 write from the host
traps to EL2, where the nVHE hypervisor has no handler and BUG()s. The
kernel never writes PMZR_EL0, but kernel.perf_user_access=1 has the PMU
driver set PMUSERENR_EL0.UEN for a task with a user-read event, so a
write from EL0 reaches the trap and takes the host down without a panic
message.

Accumulate the HDFGWTR2_EL2 bits separately, as __init_el2_fgt() already
does for HDFGWTR_EL2, and set nPMZR_EL0 with the other FEAT_PMUv3p9
bits.

Fixes: 858c7bfcb35e1 ("arm64/boot: Enable EL2 requirements for FEAT_PMUv3p9")
Cc: stable@vger.kernel.org
Signed-off-by: Fuad Tabba <fuad.tabba@linux.dev>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Oliver Upton <oupton@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 68 insertions, 0 deletions

diff --git a/include/trace/events/devfreq.h b/include/trace/events/devfreq.h
new file mode 100644
index 000000000..6cbc4d59f
--- /dev/null
+++ b/include/trace/events/devfreq.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM devfreq
+
+#if !defined(_TRACE_DEVFREQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_DEVFREQ_H
+
+#include <linux/devfreq.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(devfreq_frequency,
+	TP_PROTO(struct devfreq *devfreq, unsigned long freq,
+		 unsigned long prev_freq),
+
+	TP_ARGS(devfreq, freq, prev_freq),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(&devfreq->dev))
+		__field(unsigned long, freq)
+		__field(unsigned long, prev_freq)
+		__field(unsigned long, busy_time)
+		__field(unsigned long, total_time)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name);
+		__entry->freq = freq;
+		__entry->prev_freq = prev_freq;
+		__entry->busy_time = devfreq->last_status.busy_time;
+		__entry->total_time = devfreq->last_status.total_time;
+	),
+
+	TP_printk("dev_name=%-30s freq=%-12lu prev_freq=%-12lu load=%-2lu",
+		__get_str(dev_name), __entry->freq, __entry->prev_freq,
+		__entry->total_time == 0 ? 0 :
+			(100 * __entry->busy_time) / __entry->total_time)
+);
+
+TRACE_EVENT(devfreq_monitor,
+	TP_PROTO(struct devfreq *devfreq),
+
+	TP_ARGS(devfreq),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, freq)
+		__field(unsigned long, busy_time)
+		__field(unsigned long, total_time)
+		__field(unsigned int, polling_ms)
+		__string(dev_name, dev_name(&devfreq->dev))
+	),
+
+	TP_fast_assign(
+		__entry->freq = devfreq->previous_freq;
+		__entry->busy_time = devfreq->last_status.busy_time;
+		__entry->total_time = devfreq->last_status.total_time;
+		__entry->polling_ms = devfreq->profile->polling_ms;
+		__assign_str(dev_name);
+	),
+
+	TP_printk("dev_name=%-30s freq=%-12lu polling_ms=%-3u load=%-2lu",
+		__get_str(dev_name), __entry->freq, __entry->polling_ms,
+		__entry->total_time == 0 ? 0 :
+			(100 * __entry->busy_time) / __entry->total_time)
+);
+#endif /* _TRACE_DEVFREQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>