[PATCH v2 2/2] x86/resctrl: Add tracepoint for llc_occupancy tracking

[Haifeng Xu]

In our production environment, after removing monitor groups, those unused
RMIDs get stuck in the limbo list forever because their llc_occupancy are
always larger than the threshold. But the unused RMIDs can be successfully
freed by turning up the threshold.

In order to know how much the threshold should be, the following steps can
be taken to acquire the llc_occupancy of RMIDs in each rdt domain:

1) perf probe -a '__rmid_read eventid rmid'
   perf probe -a '__rmid_read%return $retval'
2) perf record -e probe:__rmid_read -e probe:__rmid_read__return -aR sleep 10
3) perf script > __rmid_read.txt
4) cat __rmid_read.txt | grep "eventid=0x1 " -A 1 | grep "kworker" > llc_occupnacy.txt

Instead of using perf tool to track llc_occupancy and filter the log manually,
it is more convenient for users to use tracepoint to do this work. So add a new
tracepoint that shows the llc_occupancy of busy RMIDs when scanning the limbo
list.

Signed-off-by: Haifeng Xu <haifeng.xu@xxxxxxxxxx>
Suggested-by: Reinette Chatre <reinette.chatre@xxxxxxxxx>
---
 arch/x86/kernel/cpu/resctrl/monitor.c |  2 ++
 arch/x86/kernel/cpu/resctrl/trace.h   | 13 +++++++++++++
 2 files changed, 15 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f136ac046851..1533b1932b49 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -23,6 +23,7 @@
 #include <asm/resctrl.h>
 
 #include "internal.h"
+#include "trace.h"
 
 struct rmid_entry {
 	u32				rmid;
@@ -302,6 +303,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 			}
 		}
 		crmid = nrmid + 1;
+		trace_mon_llc_occupancy_limbo(nrmid, d->id, val);
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/trace.h b/arch/x86/kernel/cpu/resctrl/trace.h
index 495fb90c8572..4bf95b7b4db8 100644
--- a/arch/x86/kernel/cpu/resctrl/trace.h
+++ b/arch/x86/kernel/cpu/resctrl/trace.h
@@ -35,6 +35,19 @@ TRACE_EVENT(pseudo_lock_l3,
 	    TP_printk("hits=%llu miss=%llu",
 		      __entry->l3_hits, __entry->l3_miss));
 
+TRACE_EVENT(mon_llc_occupancy_limbo,
+	    TP_PROTO(u32 mon_hw_id, int id, u64 occupancy),
+	    TP_ARGS(mon_hw_id, id, occupancy),
+	    TP_STRUCT__entry(__field(u32, mon_hw_id)
+			     __field(int, id)
+			     __field(u64, occupancy)),
+	    TP_fast_assign(__entry->mon_hw_id = mon_hw_id;
+			   __entry->id = id;
+			   __entry->occupancy = occupancy;),
+	    TP_printk("mon_hw_id=%u domain=%d llc_occupancy=%llu",
+		      __entry->mon_hw_id, __entry->id, __entry->occupancy)
+	   );
+
 #endif /* _TRACE_RESCTRL_H */
 
 #undef TRACE_INCLUDE_PATH
-- 
2.25.1