Third stage of unbreaking printing of pseudo-nice values (realtime

priorities, etc.) in the NICE field:

Use a combination of pri_native and pri_user instead of pri_level to
guess the original realtime priority.  Using pri_level here has been
wrong since 2001/02/12.  Using only pri_native here would be correct
if the kernel actually initialized it reasonably.  (The kernel exports
its raw td_base_priority as pri_native, but userland mostly wants a
refined base priority).  Give up on waiting pri_native to work correctly
and only use it when there is nothing better (for kthreads).

This should reduce printing of bizarre pseudo-nice values.  Bizarre
values are still printed if we observe a transient borrowed priority
for a kthread (transient borrowing is the main thing that makes the
raw td_base_priority almost useless in userland), or if there is a
kernel bug.  One current kernel bug involves the kernel idprio thread
pagezero permanently changing its priority from PRI_MAX_IDLE (255) to
PUSER (160).  Then the bizarre value "ki-6" is printed instead of
"ki31".  Here "-6" is PRI_MIN_IDLE - PUSER = -64 truncated to 2
characters.  We are observing a transient borrowed priority that has
become permanent due to a bug.

ps/print.c:priorityr() needs similar changes (including ones in stage 2
here).

1 files changed, 25 insertions, 2 deletions

diff --git a/usr.bin/top/machine.c b/usr.bin/top/machine.c
index 083055f..b7e03f4 100644
--- a/usr.bin/top/machine.c
+++ b/usr.bin/top/machine.c
@@ -892,7 +892,28 @@ format_nice(const struct kinfo_proc *pp)
 	case PRI_ITHD:
 		return ("-");
 	case PRI_REALTIME:
-		rtpri = pp->ki_pri.pri_level - PRI_MIN_REALTIME;
+		/*
+		 * XXX: the kernel doesn't tell us the original rtprio and
+		 * doesn't really know what it was, so to recover it we
+		 * must be more chummy with the implementation than the
+		 * implementation is with itself.  pri_user gives a
+		 * constant "base" priority, but is only initialized
+		 * properly for user threads.  pri_native gives what the
+		 * kernel calls the "base" priority, but it isn't constant
+		 * since it is changed by priority propagation.  pri_native
+		 * also isn't properly initialized for all threads, but it
+		 * is properly initialized for kernel realtime and idletime
+		 * threads.  Thus we use pri_user for the base priority of
+		 * user threads (it is always correct) and pri_native for
+		 * the base priority of kernel realtime and idletime threads
+		 * (there is nothing better, and it is usually correct).
+		 *
+		 * The field width and thus the buffer are too small for
+		 * values like "kr31F", but such values shouldn't occur,
+		 * and if they do then the tailing "F" is not displayed.
+		 */
+		rtpri = ((pp->ki_flag & P_KTHREAD) ? pp->ki_pri.pri_native :
+		    pp->ki_pri.pri_user) - PRI_MIN_REALTIME;
 		snprintf(nicebuf, sizeof(nicebuf), "%sr%d%s",
 		    kthread, rtpri, fifo);
 		break;
@@ -902,7 +923,9 @@ format_nice(const struct kinfo_proc *pp)
 		snprintf(nicebuf, sizeof(nicebuf), "%d", pp->ki_nice - NZERO);
 		break;
 	case PRI_IDLE:
-		rtpri = pp->ki_pri.pri_level - PRI_MIN_IDLE;
+		/* XXX: as above. */
+		rtpri = ((pp->ki_flag & P_KTHREAD) ? pp->ki_pri.pri_native :
+		    pp->ki_pri.pri_user) - PRI_MIN_IDLE;
 		snprintf(nicebuf, sizeof(nicebuf), "%si%d%s",
 		    kthread, rtpri, fifo);
 		break;