Merge branch 'fortglx/4.6/time' of https://git.linaro.org/people/john…

….stultz/linux into timers/core

Pull the cross-timestamp infrastructure from John Stultz.

Allows precise correlation of device timestamps with system time. Primary use
cases being PTP and audio.

Documentation/ptp/testptp.c

@@ -277,13 +277,15 @@ int main(int argc, char *argv[])
 			       "  %d external time stamp channels\n"
 			       "  %d programmable periodic signals\n"
 			       "  %d pulse per second\n"
-			       "  %d programmable pins\n",
+			       "  %d programmable pins\n"
+			       "  %d cross timestamping\n",
 			       caps.max_adj,
 			       caps.n_alarm,
 			       caps.n_ext_ts,
 			       caps.n_per_out,
 			       caps.pps,
-			       caps.n_pins);
+			       caps.n_pins,
+			       caps.cross_timestamping);
 		}
 	}
 

arch/x86/include/asm/cpufeature.h

@@ -85,7 +85,7 @@
 #define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
 #define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_ART		(3*32+10) /* Platform has always running timer (ART) */
 #define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
 #define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */

arch/x86/include/asm/tsc.h

@@ -29,6 +29,8 @@ static inline cycles_t get_cycles(void)
 	return rdtsc();
 }
 
+extern struct system_counterval_t convert_art_to_tsc(cycle_t art);
+
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);

arch/x86/kernel/tsc.c

@@ -43,6 +43,11 @@ static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
 
+static u32 art_to_tsc_numerator;
+static u32 art_to_tsc_denominator;
+static u64 art_to_tsc_offset;
+struct clocksource *art_related_clocksource;
+
 /*
  * Use a ring-buffer like data structure, where a writer advances the head by
  * writing a new data entry and a reader advances the tail when it observes a
@@ -964,6 +969,37 @@ core_initcall(cpufreq_tsc);
 
 #endif /* CONFIG_CPU_FREQ */
 
+#define ART_CPUID_LEAF (0x15)
+#define ART_MIN_DENOMINATOR (1)
+
+
+/*
+ * If ART is present detect the numerator:denominator to convert to TSC
+ */
+static void detect_art(void)
+{
+	unsigned int unused[2];
+
+	if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF)
+		return;
+
+	cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator,
+	      &art_to_tsc_numerator, unused, unused+1);
+
+	/* Don't enable ART in a VM, non-stop TSC required */
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR) ||
+	    !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) ||
+	    art_to_tsc_denominator < ART_MIN_DENOMINATOR)
+		return;
+
+	if (rdmsrl_safe(MSR_IA32_TSC_ADJUST, &art_to_tsc_offset))
+		return;
+
+	/* Make this sticky over multiple CPU init calls */
+	setup_force_cpu_cap(X86_FEATURE_ART);
+}
+
+
 /* clocksource code */
 
 static struct clocksource clocksource_tsc;
@@ -1071,6 +1107,25 @@ int unsynchronized_tsc(void)
 	return 0;
 }
 
+/*
+ * Convert ART to TSC given numerator/denominator found in detect_art()
+ */
+struct system_counterval_t convert_art_to_tsc(cycle_t art)
+{
+	u64 tmp, res, rem;
+
+	rem = do_div(art, art_to_tsc_denominator);
+
+	res = art * art_to_tsc_numerator;
+	tmp = rem * art_to_tsc_numerator;
+
+	do_div(tmp, art_to_tsc_denominator);
+	res += tmp + art_to_tsc_offset;
+
+	return (struct system_counterval_t) {.cs = art_related_clocksource,
+			.cycles = res};
+}
+EXPORT_SYMBOL(convert_art_to_tsc);
 
 static void tsc_refine_calibration_work(struct work_struct *work);
 static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
@@ -1142,6 +1197,8 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 		(unsigned long)tsc_khz % 1000);
 
 out:
+	if (boot_cpu_has(X86_FEATURE_ART))
+		art_related_clocksource = &clocksource_tsc;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
@@ -1235,6 +1292,8 @@ void __init tsc_init(void)
 		mark_tsc_unstable("TSCs unsynchronized");
 
 	check_system_tsc_reliable();
+
+	detect_art();
 }
 
 #ifdef CONFIG_SMP

drivers/net/ethernet/intel/Kconfig

@@ -83,6 +83,15 @@ config E1000E
 	  To compile this driver as a module, choose M here. The module
 	  will be called e1000e.
 
+config E1000E_HWTS
+	bool "Support HW cross-timestamp on PCH devices"
+	default y
+	depends on E1000E && X86
+	---help---
+	 Say Y to enable hardware supported cross-timestamping on PCH
+	 devices. The cross-timestamp is available through the PTP clock
+	 driver precise cross-timestamp ioctl (PTP_SYS_OFFSET_PRECISE).
+
 config IGB
 	tristate "Intel(R) 82575/82576 PCI-Express Gigabit Ethernet support"
 	depends on PCI

drivers/net/ethernet/intel/e1000e/defines.h

@@ -528,6 +528,11 @@
 #define E1000_RXCW_C          0x20000000        /* Receive config */
 #define E1000_RXCW_SYNCH      0x40000000        /* Receive config synch */
 
+/* HH Time Sync */
+#define E1000_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK	0x0000F000 /* max delay */
+#define E1000_TSYNCTXCTL_SYNC_COMP		0x40000000 /* sync complete */
+#define E1000_TSYNCTXCTL_START_SYNC		0x80000000 /* initiate sync */
+
 #define E1000_TSYNCTXCTL_VALID		0x00000001 /* Tx timestamp valid */
 #define E1000_TSYNCTXCTL_ENABLED	0x00000010 /* enable Tx timestamping */
 

drivers/net/ethernet/intel/e1000e/ptp.c

@@ -26,6 +26,12 @@
 
 #include "e1000.h"
 
+#ifdef CONFIG_E1000E_HWTS
+#include <linux/clocksource.h>
+#include <linux/ktime.h>
+#include <asm/tsc.h>
+#endif
+
 /**
  * e1000e_phc_adjfreq - adjust the frequency of the hardware clock
  * @ptp: ptp clock structure
@@ -98,6 +104,78 @@ static int e1000e_phc_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
+#ifdef CONFIG_E1000E_HWTS
+#define MAX_HW_WAIT_COUNT (3)
+
+/**
+ * e1000e_phc_get_syncdevicetime - Callback given to timekeeping code reads system/device registers
+ * @device: current device time
+ * @system: system counter value read synchronously with device time
+ * @ctx: context provided by timekeeping code
+ *
+ * Read device and system (ART) clock simultaneously and return the corrected
+ * clock values in ns.
+ **/
+static int e1000e_phc_get_syncdevicetime(ktime_t *device,
+					 struct system_counterval_t *system,
+					 void *ctx)
+{
+	struct e1000_adapter *adapter = (struct e1000_adapter *)ctx;
+	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
+	int i;
+	u32 tsync_ctrl;
+	cycle_t dev_cycles;
+	cycle_t sys_cycles;
+
+	tsync_ctrl = er32(TSYNCTXCTL);
+	tsync_ctrl |= E1000_TSYNCTXCTL_START_SYNC |
+		E1000_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK;
+	ew32(TSYNCTXCTL, tsync_ctrl);
+	for (i = 0; i < MAX_HW_WAIT_COUNT; ++i) {
+		udelay(1);
+		tsync_ctrl = er32(TSYNCTXCTL);
+		if (tsync_ctrl & E1000_TSYNCTXCTL_SYNC_COMP)
+			break;
+	}
+
+	if (i == MAX_HW_WAIT_COUNT)
+		return -ETIMEDOUT;
+
+	dev_cycles = er32(SYSSTMPH);
+	dev_cycles <<= 32;
+	dev_cycles |= er32(SYSSTMPL);
+	spin_lock_irqsave(&adapter->systim_lock, flags);
+	*device = ns_to_ktime(timecounter_cyc2time(&adapter->tc, dev_cycles));
+	spin_unlock_irqrestore(&adapter->systim_lock, flags);
+
+	sys_cycles = er32(PLTSTMPH);
+	sys_cycles <<= 32;
+	sys_cycles |= er32(PLTSTMPL);
+	*system = convert_art_to_tsc(sys_cycles);
+
+	return 0;
+}
+
+/**
+ * e1000e_phc_getsynctime - Reads the current system/device cross timestamp
+ * @ptp: ptp clock structure
+ * @cts: structure containing timestamp
+ *
+ * Read device and system (ART) clock simultaneously and return the scaled
+ * clock values in ns.
+ **/
+static int e1000e_phc_getcrosststamp(struct ptp_clock_info *ptp,
+				     struct system_device_crosststamp *xtstamp)
+{
+	struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter,
+						     ptp_clock_info);
+
+	return get_device_system_crosststamp(e1000e_phc_get_syncdevicetime,
+						adapter, NULL, xtstamp);
+}
+#endif/*CONFIG_E1000E_HWTS*/
+
 /**
  * e1000e_phc_gettime - Reads the current time from the hardware clock
  * @ptp: ptp clock structure
@@ -236,6 +314,13 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 		break;
 	}
 
+#ifdef CONFIG_E1000E_HWTS
+	/* CPU must have ART and GBe must be from Sunrise Point or greater */
+	if (hw->mac.type >= e1000_pch_spt && boot_cpu_has(X86_FEATURE_ART))
+		adapter->ptp_clock_info.getcrosststamp =
+			e1000e_phc_getcrosststamp;
+#endif/*CONFIG_E1000E_HWTS*/
+
 	INIT_DELAYED_WORK(&adapter->systim_overflow_work,
 			  e1000e_systim_overflow_work);
 

drivers/net/ethernet/intel/e1000e/regs.h

@@ -245,6 +245,10 @@
 #define E1000_SYSTIML	0x0B600	/* System time register Low - RO */
 #define E1000_SYSTIMH	0x0B604	/* System time register High - RO */
 #define E1000_TIMINCA	0x0B608	/* Increment attributes register - RW */
+#define E1000_SYSSTMPL  0x0B648 /* HH Timesync system stamp low register */
+#define E1000_SYSSTMPH  0x0B64C /* HH Timesync system stamp hi register */
+#define E1000_PLTSTMPL  0x0B640 /* HH Timesync platform stamp low register */
+#define E1000_PLTSTMPH  0x0B644 /* HH Timesync platform stamp hi register */
 #define E1000_RXMTRL	0x0B634	/* Time sync Rx EtherType and Msg Type - RW */
 #define E1000_RXUDP	0x0B638	/* Time Sync Rx UDP Port - RW */
 

drivers/ptp/ptp_chardev.c

@@ -22,6 +22,7 @@
 #include <linux/poll.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/timekeeping.h>
 
 #include "ptp_private.h"
 
@@ -120,11 +121,13 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 	struct ptp_clock_caps caps;
 	struct ptp_clock_request req;
 	struct ptp_sys_offset *sysoff = NULL;
+	struct ptp_sys_offset_precise precise_offset;
 	struct ptp_pin_desc pd;
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
 	struct ptp_clock_info *ops = ptp->info;
 	struct ptp_clock_time *pct;
 	struct timespec64 ts;
+	struct system_device_crosststamp xtstamp;
 	int enable, err = 0;
 	unsigned int i, pin_index;
 
@@ -138,6 +141,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		caps.n_per_out = ptp->info->n_per_out;
 		caps.pps = ptp->info->pps;
 		caps.n_pins = ptp->info->n_pins;
+		caps.cross_timestamping = ptp->info->getcrosststamp != NULL;
 		if (copy_to_user((void __user *)arg, &caps, sizeof(caps)))
 			err = -EFAULT;
 		break;
@@ -180,6 +184,29 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		err = ops->enable(ops, &req, enable);
 		break;
 
+	case PTP_SYS_OFFSET_PRECISE:
+		if (!ptp->info->getcrosststamp) {
+			err = -EOPNOTSUPP;
+			break;
+		}
+		err = ptp->info->getcrosststamp(ptp->info, &xtstamp);
+		if (err)
+			break;
+
+		ts = ktime_to_timespec64(xtstamp.device);
+		precise_offset.device.sec = ts.tv_sec;
+		precise_offset.device.nsec = ts.tv_nsec;
+		ts = ktime_to_timespec64(xtstamp.sys_realtime);
+		precise_offset.sys_realtime.sec = ts.tv_sec;
+		precise_offset.sys_realtime.nsec = ts.tv_nsec;
+		ts = ktime_to_timespec64(xtstamp.sys_monoraw);
+		precise_offset.sys_monoraw.sec = ts.tv_sec;
+		precise_offset.sys_monoraw.nsec = ts.tv_nsec;
+		if (copy_to_user((void __user *)arg, &precise_offset,
+				 sizeof(precise_offset)))
+			err = -EFAULT;
+		break;
+
 	case PTP_SYS_OFFSET:
 		sysoff = kmalloc(sizeof(*sysoff), GFP_KERNEL);
 		if (!sysoff) {

include/linux/pps_kernel.h

@@ -111,22 +111,17 @@ static inline void timespec_to_pps_ktime(struct pps_ktime *kt,
 	kt->nsec = ts.tv_nsec;
 }
 
-#ifdef CONFIG_NTP_PPS
-
 static inline void pps_get_ts(struct pps_event_time *ts)
 {
-	ktime_get_raw_and_real_ts64(&ts->ts_raw, &ts->ts_real);
-}
+	struct system_time_snapshot snap;
 
-#else /* CONFIG_NTP_PPS */
-
-static inline void pps_get_ts(struct pps_event_time *ts)
-{
-	ktime_get_real_ts64(&ts->ts_real);
+	ktime_get_snapshot(&snap);
+	ts->ts_real = ktime_to_timespec64(snap.real);
+#ifdef CONFIG_NTP_PPS
+	ts->ts_raw = ktime_to_timespec64(snap.raw);
+#endif
 }
 
-#endif /* CONFIG_NTP_PPS */
-
 /* Subtract known time delay from PPS event time(s) */
 static inline void pps_sub_ts(struct pps_event_time *ts, struct timespec64 delta)
 {

include/linux/ptp_clock_kernel.h

@@ -38,6 +38,7 @@ struct ptp_clock_request {
 	};
 };
 
+struct system_device_crosststamp;
 /**
  * struct ptp_clock_info - decribes a PTP hardware clock
  *
@@ -67,6 +68,11 @@ struct ptp_clock_request {
  * @gettime64:  Reads the current time from the hardware clock.
  *              parameter ts: Holds the result.
  *
+ * @getcrosststamp:  Reads the current time from the hardware clock and
+ *                   system clock simultaneously.
+ *                   parameter cts: Contains timestamp (device,system) pair,
+ *                   where system time is realtime and monotonic.
+ *
  * @settime64:  Set the current time on the hardware clock.
  *              parameter ts: Time value to set.
  *
@@ -105,6 +111,8 @@ struct ptp_clock_info {
 	int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta);
 	int (*adjtime)(struct ptp_clock_info *ptp, s64 delta);
 	int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts);
+	int (*getcrosststamp)(struct ptp_clock_info *ptp,
+			      struct system_device_crosststamp *cts);
 	int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts);
 	int (*enable)(struct ptp_clock_info *ptp,
 		      struct ptp_clock_request *request, int on);