x86/perf: Add hardware performance events support for Zhaoxin CPU.

Zhaoxin CPU has provided facilities for monitoring performance
via PMU (Performance Monitor Unit), but the functionality is unused so far.
Therefore, add support for zhaoxin pmu to make performance related
hardware events available.

The PMU is mostly an Intel Architectural PerfMon-v2 with a novel
errata for the ZXC line. It supports the following events:

  -----------------------------------------------------------------------------------------------------------------------------------
  Event                      | Event  | Umask |          Description
			     | Select |       |
  -----------------------------------------------------------------------------------------------------------------------------------
  cpu-cycles                 |  82h   |  00h  | unhalt core clock
  instructions               |  00h   |  00h  | number of instructions at retirement.
  cache-references           |  15h   |  05h  | number of fillq pushs at the current cycle.
  cache-misses               |  1ah   |  05h  | number of l2 miss pushed by fillq.
  branch-instructions        |  28h   |  00h  | counts the number of branch instructions retired.
  branch-misses              |  29h   |  00h  | mispredicted branch instructions at retirement.
  bus-cycles                 |  83h   |  00h  | unhalt bus clock
  stalled-cycles-frontend    |  01h   |  01h  | Increments each cycle the # of Uops issued by the RAT to RS.
  stalled-cycles-backend     |  0fh   |  04h  | RS0/1/2/3/45 empty
  L1-dcache-loads            |  68h   |  05h  | number of retire/commit load.
  L1-dcache-load-misses      |  4bh   |  05h  | retired load uops whose data source followed an L1 miss.
  L1-dcache-stores           |  69h   |  06h  | number of retire/commit Store,no LEA
  L1-dcache-store-misses     |  62h   |  05h  | cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.
  L1-icache-loads            |  00h   |  03h  | number of l1i cache access for valid normal fetch,including un-cacheable access.
  L1-icache-load-misses      |  01h   |  03h  | number of l1i cache miss for valid normal fetch,including un-cacheable miss.
  L1-icache-prefetches       |  0ah   |  03h  | number of prefetch.
  L1-icache-prefetch-misses  |  0bh   |  03h  | number of prefetch miss.
  dTLB-loads                 |  68h   |  05h  | number of retire/commit load
  dTLB-load-misses           |  2ch   |  05h  | number of load operations miss all level tlbs and cause a tablewalk.
  dTLB-stores                |  69h   |  06h  | number of retire/commit Store,no LEA
  dTLB-store-misses          |  30h   |  05h  | number of store operations miss all level tlbs and cause a tablewalk.
  dTLB-prefetches            |  64h   |  05h  | number of hardware pte prefetch requests dispatched out of the prefetch FIFO.
  dTLB-prefetch-misses       |  65h   |  05h  | number of hardware pte prefetch requests miss the l1d data cache.
  iTLB-load                  |  00h   |  00h  | actually counter instructions.
  iTLB-load-misses           |  34h   |  05h  | number of code operations miss all level tlbs and cause a tablewalk.
  -----------------------------------------------------------------------------------------------------------------------------------
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: CodyYao-oc <CodyYao-oc@zhaoxin.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1586747669-4827-1-git-send-email-CodyYao-oc@zhaoxin.com

arch/x86/events/Makefile

@@ -3,3 +3,5 @@ obj-y					+= core.o probe.o
 obj-y					+= amd/
 obj-$(CONFIG_X86_LOCAL_APIC)            += msr.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/
+obj-$(CONFIG_CPU_SUP_CENTAUR)		+= zhaoxin/
+obj-$(CONFIG_CPU_SUP_ZHAOXIN)		+= zhaoxin/

arch/x86/events/core.c

@@ -1839,6 +1839,10 @@ static int __init init_hw_perf_events(void)
 		err = amd_pmu_init();
 		x86_pmu.name = "HYGON";
 		break;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		err = zhaoxin_pmu_init();
+		break;
 	default:
 		err = -ENOTSUPP;
 	}

arch/x86/events/perf_event.h

@@ -618,6 +618,7 @@ struct x86_pmu {
 
 	/* PMI handler bits */
 	unsigned int	late_ack		:1,
+			enabled_ack		:1,
 			counter_freezing	:1;
 	/*
 	 * sysfs attrs
@@ -1133,3 +1134,12 @@ static inline int is_ht_workaround_enabled(void)
 	return 0;
 }
 #endif /* CONFIG_CPU_SUP_INTEL */
+
+#if ((defined CONFIG_CPU_SUP_CENTAUR) || (defined CONFIG_CPU_SUP_ZHAOXIN))
+int zhaoxin_pmu_init(void);
+#else
+static inline int zhaoxin_pmu_init(void)
+{
+	return 0;
+}
+#endif /*CONFIG_CPU_SUP_CENTAUR or CONFIG_CPU_SUP_ZHAOXIN*/

arch/x86/events/zhaoxin/Makefile

+# SPDX-License-Identifier: GPL-2.0
+obj-y	+= core.o

arch/x86/kernel/cpu/perfctr-watchdog.c

@@ -63,6 +63,10 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BPU_PERFCTR0;
 		}
+		fallthrough;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		return msr - MSR_ARCH_PERFMON_PERFCTR0;
 	}
 	return 0;
 }
@@ -92,6 +96,10 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BSU_ESCR0;
 		}
+		fallthrough;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		return msr - MSR_ARCH_PERFMON_EVENTSEL0;
 	}
 	return 0;