[PATCH 3/3 RESEND] perf/amd/uncore: Add support for Family 19h L3 PMU

From: Kim Phillips
Date: Wed Mar 11 2020 - 15:14:13 EST


Family 19h introduces a change in slice, core and thread specification
in its L3 Performance Event Select (ChL3PmcCfg) register. We implement
the new bitmask conversions in a new path in l3_thread_slice_mask()
based on a family 19h-and-above check.

We also change the uncore_init() family check to 19h-and-above, so as
to not revert to the Family 16h-or-below L2/NB code paths in the driver.

Signed-off-by: Kim Phillips <kim.phillips@xxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Michael Petlan <mpetlan@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: x86@xxxxxxxxxx
---
RESEND. No changes since original submission:

https://lkml.org/lkml/2020/2/19/1193

arch/x86/events/amd/uncore.c | 20 ++++++++++++++------
arch/x86/include/asm/perf_event.h | 15 +++++++++++++--
2 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index e635c40ca9c4..78b4fb917ad6 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -191,10 +191,18 @@ static u64 l3_thread_slice_mask(int cpu)
if (topology_smt_supported() && !topology_is_primary_thread(cpu))
thread = 1;

- shift = AMD64_L3_THREAD_SHIFT + 2 * (core % 4) + thread;
+ if (boot_cpu_data.x86 <= 0x18) {
+ shift = AMD64_L3_THREAD_SHIFT + 2 * (core % 4) + thread;
+ thread_mask = BIT_ULL(shift);
+
+ return AMD64_L3_SLICE_MASK | thread_mask;
+ }
+
+ core = (core << AMD64_L3_COREID_SHIFT) & AMD64_L3_COREID_MASK;
+ shift = AMD64_L3_THREAD_SHIFT + thread;
thread_mask = BIT_ULL(shift);

- return AMD64_L3_SLICE_MASK | thread_mask;
+ return AMD64_L3_EN_ALL_SLICES | core | thread_mask;
}

static int amd_uncore_event_init(struct perf_event *event)
@@ -220,8 +228,8 @@ static int amd_uncore_event_init(struct perf_event *event)
return -EINVAL;

/*
- * SliceMask and ThreadMask need to be set for certain L3 events in
- * Family 17h. For other events, the two fields do not affect the count.
+ * SliceMask and ThreadMask need to be set for certain L3 events.
+ * For other events, the two fields do not affect the count.
*/
if (l3_mask && is_llc_event(event))
hwc->config |= l3_thread_slice_mask(event->cpu);
@@ -530,9 +538,9 @@ static int __init amd_uncore_init(void)
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
return -ENODEV;

- if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) {
+ if (boot_cpu_data.x86 >= 0x17) {
/*
- * For F17h or F18h, the Northbridge counters are
+ * For F17h and above, the Northbridge counters are
* repurposed as Data Fabric counters. Also, L3
* counters are supported too. The PMUs are exported
* based on family as either L2 or L3 and NB or DF.
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 29964b0e1075..e855e9cf2c37 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -50,11 +50,22 @@

#define AMD64_L3_SLICE_SHIFT 48
#define AMD64_L3_SLICE_MASK \
- ((0xFULL) << AMD64_L3_SLICE_SHIFT)
+ (0xFULL << AMD64_L3_SLICE_SHIFT)
+#define AMD64_L3_SLICEID_MASK \
+ (0x7ULL << AMD64_L3_SLICE_SHIFT)

#define AMD64_L3_THREAD_SHIFT 56
#define AMD64_L3_THREAD_MASK \
- ((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+ (0xFFULL << AMD64_L3_THREAD_SHIFT)
+#define AMD64_L3_F19H_THREAD_MASK \
+ (0x3ULL << AMD64_L3_THREAD_SHIFT)
+
+#define AMD64_L3_EN_ALL_CORES BIT_ULL(47)
+#define AMD64_L3_EN_ALL_SLICES BIT_ULL(46)
+
+#define AMD64_L3_COREID_SHIFT 42
+#define AMD64_L3_COREID_MASK \
+ (0x7ULL << AMD64_L3_COREID_SHIFT)

#define X86_RAW_EVENT_MASK \
(ARCH_PERFMON_EVENTSEL_EVENT | \
--
2.25.1