Handle 32-bit overflows in disk utilization stats

Linux prints [1] some of the values reported in block device's `stat`
sysfs file as 32-bit unsigned integers. fio interprets them as 64-bit
integers when reading that sysfs file and performs further arithmetics
on them in 64-bits. If the reported value overflows during fio run,
a huge bogus value is reported in the "disk utilization" block instead.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/block/genhd.c#n962

Signed-off-by: Alexey Neyman <aneyman@google.com>

diskutil.c

@@ -77,7 +77,24 @@ static int get_io_ticks(struct disk_util *du, struct disk_util_stat *dus)
 	return ret != 10;
 }
 
-static void update_io_tick_disk(struct disk_util *du)
+static uint64_t safe_32bit_diff(uint64_t nval, uint64_t oval)
+{
+	/* Linux kernel prints some of the stat fields as 32-bit integers. It is
+	 * possible that the value overflows, but since fio uses unsigned 64-bit
+	 * arithmetic in update_io_tick_disk(), it instead results in a huge
+	 * bogus value being added to the respective accumulating field. Just
+	 * in case Linux starts reporting these metrics as 64-bit values in the
+	 * future, check that overflow actually happens around the 32-bit
+	 * unsigned boundary; assume overflow only happens once between
+	 * successive polls.
+	 */
+	if (oval <= nval || oval >= (1ull << 32))
+		return nval - oval;
+	else
+		return (1ull << 32) + nval - oval;
+}
+
+static void __attribute__((noinline)) update_io_tick_disk(struct disk_util *du)
 {
 	struct disk_util_stat __dus, *dus, *ldus;
 	struct timespec t;
@@ -96,14 +113,21 @@ static void update_io_tick_disk(struct disk_util *du)
 	dus->s.ios[1] += (__dus.s.ios[1] - ldus->s.ios[1]);
 	dus->s.merges[0] += (__dus.s.merges[0] - ldus->s.merges[0]);
 	dus->s.merges[1] += (__dus.s.merges[1] - ldus->s.merges[1]);
-	dus->s.ticks[0] += (__dus.s.ticks[0] - ldus->s.ticks[0]);
-	dus->s.ticks[1] += (__dus.s.ticks[1] - ldus->s.ticks[1]);
-	dus->s.io_ticks += (__dus.s.io_ticks - ldus->s.io_ticks);
-	dus->s.time_in_queue += (__dus.s.time_in_queue - ldus->s.time_in_queue);
+	dus->s.ticks[0] += safe_32bit_diff(__dus.s.ticks[0], ldus->s.ticks[0]);
+	dus->s.ticks[1] += safe_32bit_diff(__dus.s.ticks[1], ldus->s.ticks[1]);
+	dus->s.io_ticks += safe_32bit_diff(__dus.s.io_ticks, ldus->s.io_ticks);
+	dus->s.time_in_queue +=
+			safe_32bit_diff(__dus.s.time_in_queue, ldus->s.time_in_queue);
 
 	fio_gettime(&t, NULL);
 	dus->s.msec += mtime_since(&du->time, &t);
 	memcpy(&du->time, &t, sizeof(t));
+
+// memcpy() below triggers a spurious warning at -O2 or above, starting with
+// GCC11.
+#if defined(__GNUC__) && __GNUC__ >= 11
+#pragma GCC diagnostic ignored "-Wstringop-overflow"
+#endif
 	memcpy(&ldus->s, &__dus.s, sizeof(__dus.s));
 }
 
@@ -121,6 +145,13 @@ int update_io_ticks(void)
 		flist_for_each(entry, &disk_list) {
 			du = flist_entry(entry, struct disk_util, list);
 			update_io_tick_disk(du);
+
+// Re-enable the warning turned off in update_io_tick_disk().
+// Warning suppression has to be in effect up to the location where the
+// function is inlined.
+#if defined(__GNUC__) && __GNUC__ >= 11
+#pragma GCC diagnostic warning "-Wstringop-overflow"
+#endif
 		}
 	} else
 		ret = 1;