KVM: SEV: Do cache maintenance on the source VM during intra-host migrationgrafted

Manually perform cache maintenance on the source VM during intra-host
migration to ensure no stale data is left in CPU caches after the VM is
destroyed.  Because the source VM is "converted" to a non-SEV VM, KVM's
memory reclaim flows won't trigger cache maintenance, e.g. when all guest
memory is reclaimed in response to detaching from the mmu_notifier.

Note, relying on the destination VM to do cache maintenance isn't an option
as KVM doesn't require identical guest memory configurations, i.e. the
source VM may have access to memory that the destination VM does not.
Enforcing equivalent memory configurations is infeasible, as it would
require a *deep* comparison of memslots, e.g. to verify that not only are
the memslot identical, but what the memslots point at is also identical.

Fixes: b56639318bb2 ("KVM: SEV: Add support for SEV intra host migration")
Cc: stable@vger.kernel.org
Reported-by: Stefan Teodorescu <fane@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20260923163721.1584779-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

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>