[PATCH v2] x86/tsc: Allow quick PIT calibration despite interruptions

[Jan H. SchÃnherr]

Some systems experience regular interruptions (60 Hz SMI?), that prevent
the quick PIT calibration from succeeding: individual interruptions can be
so long, that the PIT MSB is observed to decrement by 2 or 3 instead of 1.
The existing code cannot recover from this.

The system in question is an AMD Ryzen Threadripper 2950X, microcode
0x800820b, on an ASRock Fatal1ty X399 Professional Gaming, BIOS P3.30.

Change the code to handle (almost) arbitrary interruptions, as long
as they happen only once in a while and they do not take too long.
Specifically, also cover an interruption during the very first reads.

Signed-off-by: Jan H. SchÃnherr <jan@xxxxxxxxxx>
---

v2:
- Dropped the other hacky patch for the time being.
- Fixed the early exit check.
- Hopefully fixed all inaccurate math in v1.
- Extended comments.

 arch/x86/kernel/tsc.c | 91 +++++++++++++++++++++++++++----------------
 1 file changed, 57 insertions(+), 34 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e9f777bfed40..aced427371f7 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -485,7 +485,7 @@ static inline int pit_verify_msb(unsigned char val)
 static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap)
 {
 	int count;
-	u64 tsc = 0, prev_tsc = 0;
+	u64 tsc = get_cycles(), prev_tsc = 0;
 
 	for (count = 0; count < 50000; count++) {
 		if (!pit_verify_msb(val))
@@ -500,7 +500,7 @@ static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *de
 	 * We require _some_ success, but the quality control
 	 * will be based on the error terms on the TSC values.
 	 */
-	return count > 5;
+	return count > 0 && pit_verify_msb(val - 1);
 }
 
 /*
@@ -515,7 +515,8 @@ static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *de
 static unsigned long quick_pit_calibrate(void)
 {
 	int i;
-	u64 tsc, delta;
+	u64 tsc = 0, delta;
+	unsigned char start;
 	unsigned long d1, d2;
 
 	if (!has_legacy_pic())
@@ -547,43 +548,65 @@ static unsigned long quick_pit_calibrate(void)
 	 */
 	pit_verify_msb(0);
 
-	if (pit_expect_msb(0xff, &tsc, &d1)) {
-		for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) {
-			if (!pit_expect_msb(0xff-i, &delta, &d2))
-				break;
-
-			delta -= tsc;
-
-			/*
-			 * Extrapolate the error and fail fast if the error will
-			 * never be below 500 ppm.
-			 */
-			if (i == 1 &&
-			    d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11)
-				return 0;
-
-			/*
-			 * Iterate until the error is less than 500 ppm
-			 */
-			if (d1+d2 >= delta >> 11)
-				continue;
-
-			/*
-			 * Check the PIT one more time to verify that
-			 * all TSC reads were stable wrt the PIT.
-			 *
-			 * This also guarantees serialization of the
-			 * last cycle read ('d2') in pit_expect_msb.
-			 */
-			if (!pit_verify_msb(0xfe - i))
-				break;
-			goto success;
+	/*
+	 * Reading the PIT may fail or experience unexpected delays (due to
+	 * SMIs, for example). Assuming, that these underlying interruptions
+	 * happen only once in a while, we wait for two successful reads.
+	 * Of these, we assume that the better one was not delayed and use
+	 * it as the base for later calculations.
+	 */
+	for (i = 0; i <= MAX_QUICK_PIT_ITERATIONS; i++) {
+		if (!pit_expect_msb(0xff - i, &delta, &d2))
+			continue;
+
+		if (!tsc) {
+			/* first success */
+			start = i;
+			tsc = delta;
+			d1 = d2;
+			continue;
 		}
+
+		/* second success */
+		delta -= tsc;
+		do_div(delta, i - start);
+		if (d2 < d1) {
+			start = i;
+			tsc += delta;
+			d1 = d2;
+		}
+		goto calibrate;
+	}
+
+	pr_info("Fast TSC calibration failed (couldn't even start)\n");
+	return 0;
+
+calibrate:
+	/*
+	 * Extrapolate the error based on the better of the first two successes
+	 * and fail fast if the error will never be below 500 ppm.
+	 */
+	if (d1 + d1 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11) {
+		pr_info("Fast TSC calibration failed (wouldn't work)\n");
+		return 0;
 	}
+
+	for (i++; i <= MAX_QUICK_PIT_ITERATIONS; i++) {
+		if (!pit_expect_msb(0xff - i, &delta, &d2))
+			continue;
+
+		delta -= tsc;
+
+		/* Stop when the error is less than 500 ppm */
+		if (d1 + d2 < delta >> 11)
+			goto success;
+	}
+
 	pr_info("Fast TSC calibration failed\n");
 	return 0;
 
 success:
+	i -= start;
 	/*
 	 * Ok, if we get here, then we've seen the
 	 * MSB of the PIT decrement 'i' times, and the
-- 
2.19.2