hwpmc: add summary command and further metadata extensions

metadata changes:
- log pmc sample rate with pmcallocate
- log proc flags with thread / process logging
  to identify user vs kernel threads

fixes:
- use log cpuid to translate event id to event name

Implement rudimentary summary command to track sample
counts by thread and process name within a pmc log.

% make -j4 buildkernel >& /dev/null &
% sudo pmcstat -S unhalted_core_cycles -S llc-misses -O foo sleep 15
% pmc summary foo
cpu_clk_unhalted.thread_p_any:
        idle: 138108207162
        clang-6.0: 105336158004
        sh: 72340108510
        make: 8642012963
        kernel: 7754011631
longest_lat_cache.miss:
        clang-6.0: 87502625
        sh: 40901227
        make: 5500165
        kernel: 3300099
        awk: 2000060

%  pmc summary -f ~/foo
idx: 278 name: cpu_clk_unhalted.thread_p_any rate: 2000003
idle: 69054
clang-6.0: 52668
sh: 36170
make: 4321
kernel: 3877
hwpmc: proc(7445): 3319
awk: 1289
xargs: 357
rand_harvestq: 181
mtree: 102
intr: 53
zfskern: 31
usb: 7
pagedaemon: 4
ntpd: 3
syslogd: 1
acpi_thermal: 1
logger: 1
syncer: 1
snmptrapd: 1
sleep: 1
idx: 17 name: longest_lat_cache.miss rate: 100003
clang-6.0: 875
sh: 409
make: 55
kernel: 33
awk: 20
hwpmc: proc(7445): 14
xargs: 9
idle: 8
intr: 3
zfskern: 2

2 files changed, 15 insertions, 3 deletions

diff --git a/sys/dev/hwpmc/hwpmc_logging.c b/sys/dev/hwpmc/hwpmc_logging.c
index 49996229480b..1f314518549a 100644
--- a/sys/dev/hwpmc/hwpmc_logging.c
+++ b/sys/dev/hwpmc/hwpmc_logging.c
@@ -194,7 +194,7 @@ CTASSERT(sizeof(struct pmclog_map_in) == PATH_MAX +
 CTASSERT(offsetof(struct pmclog_map_in,pl_pathname) ==
     4*4 + sizeof(uintfptr_t));
 CTASSERT(sizeof(struct pmclog_map_out) == 4*4 + 2*sizeof(uintfptr_t));
-CTASSERT(sizeof(struct pmclog_pmcallocate) == 6*4);
+CTASSERT(sizeof(struct pmclog_pmcallocate) == 8*4);
 CTASSERT(sizeof(struct pmclog_pmcattach) == 6*4 + PATH_MAX);
 CTASSERT(offsetof(struct pmclog_pmcattach,pl_pathname) == 6*4);
 CTASSERT(sizeof(struct pmclog_pmcdetach) == 6*4);
@@ -991,6 +991,7 @@ pmclog_process_pmcallocate(struct pmc *pm)
 		PMCLOG_EMIT32(pm->pm_id);
 		PMCLOG_EMIT32(pm->pm_event);
 		PMCLOG_EMIT32(pm->pm_flags);
+		PMCLOG_EMIT64(pm->pm_sc.pm_reloadcount);
 		ps = pmc_soft_ev_acquire(pm->pm_event);
 		if (ps != NULL)
 			PMCLOG_EMITSTRING(ps->ps_ev.pm_ev_name,PMC_NAME_MAX);
@@ -1004,6 +1005,7 @@ pmclog_process_pmcallocate(struct pmc *pm)
 		PMCLOG_EMIT32(pm->pm_id);
 		PMCLOG_EMIT32(pm->pm_event);
 		PMCLOG_EMIT32(pm->pm_flags);
+		PMCLOG_EMIT64(pm->pm_sc.pm_reloadcount);
 		PMCLOG_DESPATCH_SYNC(po);
 	}
 }
@@ -1050,11 +1052,15 @@ pmclog_process_proccreate(struct pmc_owner *po, struct proc *p, int sync)
 	if (sync) {
 		PMCLOG_RESERVE(po, PROC_CREATE, sizeof(struct pmclog_proccreate));
 		PMCLOG_EMIT32(p->p_pid);
+		PMCLOG_EMIT32(p->p_flag);
+		PMCLOG_EMIT32(0);
 		PMCLOG_EMITSTRING(p->p_comm, MAXCOMLEN+1);
 		PMCLOG_DESPATCH_SYNC(po);
 	} else {
 		PMCLOG_RESERVE(po, PROC_CREATE, sizeof(struct pmclog_proccreate));
 		PMCLOG_EMIT32(p->p_pid);
+		PMCLOG_EMIT32(p->p_flag);
+		PMCLOG_EMIT32(0);
 		PMCLOG_EMITSTRING(p->p_comm, MAXCOMLEN+1);
 		PMCLOG_DESPATCH(po);
 	}
@@ -1163,14 +1169,14 @@ pmclog_process_threadcreate(struct pmc_owner *po, struct thread *td, int sync)
 		PMCLOG_RESERVE(po, THR_CREATE, sizeof(struct pmclog_threadcreate));
 		PMCLOG_EMIT32(td->td_tid);
 		PMCLOG_EMIT32(p->p_pid);
-		PMCLOG_EMIT32(0);
+		PMCLOG_EMIT32(p->p_flag);
 		PMCLOG_EMITSTRING(td->td_name, MAXCOMLEN+1);
 		PMCLOG_DESPATCH_SYNC(po);
 	} else {
 		PMCLOG_RESERVE(po, THR_CREATE, sizeof(struct pmclog_threadcreate));
 		PMCLOG_EMIT32(td->td_tid);
 		PMCLOG_EMIT32(p->p_pid);
-		PMCLOG_EMIT32(0);
+		PMCLOG_EMIT32(p->p_flag);
 		PMCLOG_EMITSTRING(td->td_name, MAXCOMLEN+1);
 		PMCLOG_DESPATCH(po);
 	}
diff --git a/sys/dev/hwpmc/hwpmc_mod.c b/sys/dev/hwpmc/hwpmc_mod.c
index 191f2554ee60..cb09592a61d1 100644
--- a/sys/dev/hwpmc/hwpmc_mod.c
+++ b/sys/dev/hwpmc/hwpmc_mod.c
@@ -3925,6 +3925,12 @@ pmc_syscall_handler(struct thread *td, void *syscall_args)
 		pmc->pm_caps  = caps;
 		pmc->pm_flags = pa.pm_flags;
 
+		/* XXX set lower bound on sampling for process counters */
+		if (PMC_IS_SAMPLING_MODE(mode))
+			pmc->pm_sc.pm_reloadcount = pa.pm_count;
+		else
+			pmc->pm_sc.pm_initial = pa.pm_count;
+
 		/* switch thread to CPU 'cpu' */
 		pmc_save_cpu_binding(&pb);