s390/pai: Add support for PAI Extension 1 NNPA counters

PMU device driver perf_paiext supports Processor Activity
Instrumentation Extension (PAIE1), available with IBM z16:
- maps a 512 byte block to lowcore address 0x1508 called PAIE1 control
  block.
- maps a 1024 byte block at PAIE1 control block entry with index 2.
- uses control register bit 14 to enable PAIE1 control block lookup.
- turn PAIE1 nnpa counting on and off by setting bit 63 in
  PAIE1 control block entry with index 2.
- creates a sample with raw data on each context switch out when
  at context switch some mapped counters have a value of nonzero.
This device driver only supports CPU wide context, no task context
is allowed.

Support for counting:
- one or more counters can be specified using
  perf stat -e pai_ext/xxx/
  where xxx stands for the counter event name. Multiple invocation
  of this command is possible. The counter names are listed in
  /sys/devices/pai_ext/events directory.
- one special counters can be specified using
  perf stat -e pai_ext/NNPA_ALL/
  which returns the sum of all incremented nnpa counters.
- multiple counting events can run in parallel.

Support for Sampling:
- one event pai_ext/NNPA_ALL/ is reserved for sampling.
  The event collects data at context switch out and saves them in
  the ring buffer.
- no multiple invocations are possible.

The PAIE1 nnpa counter events are system wide. No task context is
supported.  Therefore some restrictions documented in function
paiext_busy() apply.

Extend qpaci assembly instruction to query supported memory mapped nnpa
counters. It returns the number of counters (no holes allowed in that
range).

PAIE1 nnpa counter events can not be created when a CPU hot plug
add is processed. This means a CPU hot plug add does not get
the necessary PAIE1 event to record PAIE1 nnpa counter increments
on the newly added CPU. CPU hot plug remove removes the event and
terminates the counting of PAIE1 counters immediately.

Signed-off-by: Thomas Richter <[email protected]>
Reviewed-by: Sumanth Korikkar <[email protected]>
Reviewed-by: Sven Schnelle <[email protected]>
Signed-off-by: Vasily Gorbik <[email protected]>

Author: Thomas Richter

arch/s390/include/asm/ctl_reg.h

@@ -95,7 +95,8 @@ union ctlreg0 {
 					   Interruption-Filtering Override */
 		unsigned long	   : 3;
 		unsigned long ccc  : 1; /* Cryptography counter control */
-		unsigned long	   : 18;
+		unsigned long pec  : 1; /* PAI extension control */
+		unsigned long	   : 17;
 		unsigned long	   : 3;
 		unsigned long lap  : 1; /* Low-address-protection control */
 		unsigned long	   : 4;

arch/s390/include/asm/lowcore.h

@@ -203,7 +203,9 @@ struct lowcore {
 	__u8	pad_0x1400[0x1500-0x1400];	/* 0x1400 */
 	/* Cryptography-counter designation */
 	__u64	ccd;				/* 0x1500 */
-	__u8	pad_0x1508[0x1800-0x1508];	/* 0x1508 */
+	/* AI-extension counter designation */
+	__u64	aicd;				/* 0x1508 */
+	__u8	pad_0x1510[0x1800-0x1510];	/* 0x1510 */
 
 	/* Transaction abort diagnostic block */
 	struct pgm_tdb pgm_tdb;			/* 0x1800 */

arch/s390/include/asm/pai.h

@@ -17,7 +17,9 @@ struct qpaci_info_block {
 	struct {
 		u64 : 8;
 		u64 num_cc : 8;	/* # of supported crypto counters */
-		u64 : 48;
+		u64 : 9;
+		u64 num_nnpa : 7;	/* # of supported NNPA counters */
+		u64 : 32;
 	};
 };
 
@@ -42,6 +44,8 @@ static inline int qpaci(struct qpaci_info_block *info)
 #define PAI_CRYPTO_BASE			0x1000	/* First event number */
 #define PAI_CRYPTO_MAXCTR		256	/* Max # of event counters */
 #define PAI_CRYPTO_KERNEL_OFFSET	2048
+#define PAI_NNPA_BASE			0x1800	/* First event number */
+#define PAI_NNPA_MAXCTR			128	/* Max # of event counters */
 
 DECLARE_STATIC_KEY_FALSE(pai_key);
 

arch/s390/kernel/Makefile

@@ -72,7 +72,7 @@ obj-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT)	+= ima_arch.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf_common.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf.o perf_cpum_sf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf_events.o perf_regs.o
-obj-$(CONFIG_PERF_EVENTS)	+= perf_pai_crypto.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_pai_crypto.o perf_pai_ext.o
 
 obj-$(CONFIG_TRACEPOINTS)	+= trace.o
 obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE))	+= uv.o