Merge tag 'x86-timers-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 timer updates from Thomas Gleixner:
 "A series of commits to make the MSR derived CPU and TSC frequency more
  accurate.

  It turned out that the frequency tables which have been taken from the
  SDM are inaccurate because the SDM provides truncated and rounded
  values, e.g. 83.3Mhz (83.3333...) or 116.7Mhz (116.6666...).

  This causes time drift in the range of ~1 second per hour (20-30
  seconds per day). On some of these SoCs it's not possible to
  recalibrate the TSC because there is no reference (PIT, HPET)
  available.

  With some reverse engineering it was established that the possible
  frequencies are derived from the base clock with fixed multiplier /
  divider pairs.

  For the CPU models which have a known crystal frequency the kernel now
  uses multiplier / divider pairs which bring the frequencies closer to
  reality and fix the observed time drift issues"

* tag 'x86-timers-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/tsc_msr: Make MSR derived TSC frequency more accurate
  x86/tsc_msr: Fix MSR_FSB_FREQ mask for Cherry Trail devices
  x86/tsc_msr: Use named struct initializers

arch/x86/kernel/tsc_msr.c

@@ -15,18 +15,46 @@
 #include <asm/param.h>
 #include <asm/tsc.h>
 
-#define MAX_NUM_FREQS	9
+#define MAX_NUM_FREQS	16 /* 4 bits to select the frequency */
+
+/*
+ * The frequency numbers in the SDM are e.g. 83.3 MHz, which does not contain a
+ * lot of accuracy which leads to clock drift. As far as we know Bay Trail SoCs
+ * use a 25 MHz crystal and Cherry Trail uses a 19.2 MHz crystal, the crystal
+ * is the source clk for a root PLL which outputs 1600 and 100 MHz. It is
+ * unclear if the root PLL outputs are used directly by the CPU clock PLL or
+ * if there is another PLL in between.
+ * This does not matter though, we can model the chain of PLLs as a single PLL
+ * with a quotient equal to the quotients of all PLLs in the chain multiplied.
+ * So we can create a simplified model of the CPU clock setup using a reference
+ * clock of 100 MHz plus a quotient which gets us as close to the frequency
+ * from the SDM as possible.
+ * For the 83.3 MHz example from above this would give us 100 MHz * 5 / 6 =
+ * 83 and 1/3 MHz, which matches exactly what has been measured on actual hw.
+ */
+#define TSC_REFERENCE_KHZ 100000
+
+struct muldiv {
+	u32 multiplier;
+	u32 divider;
+};
 
 /*
  * If MSR_PERF_STAT[31] is set, the maximum resolved bus ratio can be
  * read in MSR_PLATFORM_ID[12:8], otherwise in MSR_PERF_STAT[44:40].
  * Unfortunately some Intel Atom SoCs aren't quite compliant to this,
  * so we need manually differentiate SoC families. This is what the
- * field msr_plat does.
+ * field use_msr_plat does.
  */
 struct freq_desc {
-	u8 msr_plat;	/* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */
+	bool use_msr_plat;
+	struct muldiv muldiv[MAX_NUM_FREQS];
+	/*
+	 * Some CPU frequencies in the SDM do not map to known PLL freqs, in
+	 * that case the muldiv array is empty and the freqs array is used.
+	 */
 	u32 freqs[MAX_NUM_FREQS];
+	u32 mask;
 };
 
 /*
@@ -35,31 +63,81 @@ struct freq_desc {
  * by MSR based on SDM.
  */
 static const struct freq_desc freq_desc_pnw = {
-	0, { 0, 0, 0, 0, 0, 99840, 0, 83200 }
+	.use_msr_plat = false,
+	.freqs = { 0, 0, 0, 0, 0, 99840, 0, 83200 },
+	.mask = 0x07,
 };
 
 static const struct freq_desc freq_desc_clv = {
-	0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 }
+	.use_msr_plat = false,
+	.freqs = { 0, 133200, 0, 0, 0, 99840, 0, 83200 },
+	.mask = 0x07,
 };
 
+/*
+ * Bay Trail SDM MSR_FSB_FREQ frequencies simplified PLL model:
+ *  000:   100 *  5 /  6  =  83.3333 MHz
+ *  001:   100 *  1 /  1  = 100.0000 MHz
+ *  010:   100 *  4 /  3  = 133.3333 MHz
+ *  011:   100 *  7 /  6  = 116.6667 MHz
+ *  100:   100 *  4 /  5  =  80.0000 MHz
+ */
 static const struct freq_desc freq_desc_byt = {
-	1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 }
+	.use_msr_plat = true,
+	.muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 7, 6 },
+		    { 4, 5 } },
+	.mask = 0x07,
 };
 
+/*
+ * Cherry Trail SDM MSR_FSB_FREQ frequencies simplified PLL model:
+ * 0000:   100 *  5 /  6  =  83.3333 MHz
+ * 0001:   100 *  1 /  1  = 100.0000 MHz
+ * 0010:   100 *  4 /  3  = 133.3333 MHz
+ * 0011:   100 *  7 /  6  = 116.6667 MHz
+ * 0100:   100 *  4 /  5  =  80.0000 MHz
+ * 0101:   100 * 14 / 15  =  93.3333 MHz
+ * 0110:   100 *  9 / 10  =  90.0000 MHz
+ * 0111:   100 *  8 /  9  =  88.8889 MHz
+ * 1000:   100 *  7 /  8  =  87.5000 MHz
+ */
 static const struct freq_desc freq_desc_cht = {
-	1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 }
+	.use_msr_plat = true,
+	.muldiv = { { 5, 6 }, {  1,  1 }, { 4,  3 }, { 7, 6 },
+		    { 4, 5 }, { 14, 15 }, { 9, 10 }, { 8, 9 },
+		    { 7, 8 } },
+	.mask = 0x0f,
 };
 
+/*
+ * Merriefield SDM MSR_FSB_FREQ frequencies simplified PLL model:
+ * 0001:   100 *  1 /  1  = 100.0000 MHz
+ * 0010:   100 *  4 /  3  = 133.3333 MHz
+ */
 static const struct freq_desc freq_desc_tng = {
-	1, { 0, 100000, 133300, 0, 0, 0, 0, 0 }
+	.use_msr_plat = true,
+	.muldiv = { { 0, 0 }, { 1, 1 }, { 4, 3 } },
+	.mask = 0x07,
 };
 
+/*
+ * Moorefield SDM MSR_FSB_FREQ frequencies simplified PLL model:
+ * 0000:   100 *  5 /  6  =  83.3333 MHz
+ * 0001:   100 *  1 /  1  = 100.0000 MHz
+ * 0010:   100 *  4 /  3  = 133.3333 MHz
+ * 0011:   100 *  1 /  1  = 100.0000 MHz
+ */
 static const struct freq_desc freq_desc_ann = {
-	1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 }
+	.use_msr_plat = true,
+	.muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 1, 1 } },
+	.mask = 0x0f,
 };
 
+/* 24 MHz crystal? : 24 * 13 / 4 = 78 MHz */
 static const struct freq_desc freq_desc_lgm = {
-	1, { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 }
+	.use_msr_plat = true,
+	.freqs = { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 },
+	.mask = 0x0f,
 };
 
 static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
@@ -81,17 +159,19 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
  */
 unsigned long cpu_khz_from_msr(void)
 {
-	u32 lo, hi, ratio, freq;
+	u32 lo, hi, ratio, freq, tscref;
 	const struct freq_desc *freq_desc;
 	const struct x86_cpu_id *id;
+	const struct muldiv *md;
 	unsigned long res;
+	int index;
 
 	id = x86_match_cpu(tsc_msr_cpu_ids);
 	if (!id)
 		return 0;
 
 	freq_desc = (struct freq_desc *)id->driver_data;
-	if (freq_desc->msr_plat) {
+	if (freq_desc->use_msr_plat) {
 		rdmsr(MSR_PLATFORM_INFO, lo, hi);
 		ratio = (lo >> 8) & 0xff;
 	} else {
@@ -101,12 +181,28 @@ unsigned long cpu_khz_from_msr(void)
 
 	/* Get FSB FREQ ID */
 	rdmsr(MSR_FSB_FREQ, lo, hi);
+	index = lo & freq_desc->mask;
+	md = &freq_desc->muldiv[index];
 
-	/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
-	freq = freq_desc->freqs[lo & 0x7];
-
-	/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
+	/*
+	 * Note this also catches cases where the index points to an unpopulated
+	 * part of muldiv, in that case the else will set freq and res to 0.
+	 */
+	if (md->divider) {
+		tscref = TSC_REFERENCE_KHZ * md->multiplier;
+		freq = DIV_ROUND_CLOSEST(tscref, md->divider);
+		/*
+		 * Multiplying by ratio before the division has better
+		 * accuracy than just calculating freq * ratio.
+		 */
+		res = DIV_ROUND_CLOSEST(tscref * ratio, md->divider);
+	} else {
+		freq = freq_desc->freqs[index];
 		res = freq * ratio;
+	}
+
+	if (freq == 0)
+		pr_err("Error MSR_FSB_FREQ index %d is unknown\n", index);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	lapic_timer_period = (freq * 1000) / HZ;