[PATCH v3] ptp: Add vDSO-style vmclock support

[Michael S. Tsirkin]

On Mon, Jul 29, 2024 at 11:42:22AM +0100, David Woodhouse wrote:
> +struct vmclock_abi {
> +	/* CONSTANT FIELDS */
> +	uint32_t magic;
> +#define VMCLOCK_MAGIC	0x4b4c4356 /* "VCLK" */
> +	uint32_t size;		/* Size of region containing this structure */
> +	uint16_t version;	/* 1 */
> +	uint8_t counter_id; /* Matches VIRTIO_RTC_COUNTER_xxx except INVALID */
> +#define VMCLOCK_COUNTER_ARM_VCNT	0
> +#define VMCLOCK_COUNTER_X86_TSC		1
> +#define VMCLOCK_COUNTER_INVALID		0xff
> +	uint8_t time_type; /* Matches VIRTIO_RTC_TYPE_xxx */
> +#define VMCLOCK_TIME_UTC			0	/* Since 1970-01-01 00:00:00z */
> +#define VMCLOCK_TIME_TAI			1	/* Since 1970-01-01 00:00:00z */
> +#define VMCLOCK_TIME_MONOTONIC			2	/* Since undefined epoch */
> +#define VMCLOCK_TIME_INVALID_SMEARED		3	/* Not supported */
> +#define VMCLOCK_TIME_INVALID_MAYBE_SMEARED	4	/* Not supported */
> +
> +	/* NON-CONSTANT FIELDS PROTECTED BY SEQCOUNT LOCK */
> +	uint32_t seq_count;	/* Low bit means an update is in progress */
> +	/*
> +	 * This field changes to another non-repeating value when the CPU
> +	 * counter is disrupted, for example on live migration. This lets
> +	 * the guest know that it should discard any calibration it has
> +	 * performed of the counter against external sources (NTP/PTP/etc.).
> +	 */
> +	uint64_t disruption_marker;
> +	uint64_t flags;
> +	/* Indicates that the tai_offset_sec field is valid */
> +#define VMCLOCK_FLAG_TAI_OFFSET_VALID		(1 << 0)
> +	/*
> +	 * Optionally used to notify guests of pending maintenance events.
> +	 * A guest which provides latency-sensitive services may wish to
> +	 * remove itself from service if an event is coming up. Two flags
> +	 * indicate the approximate imminence of the event.
> +	 */
> +#define VMCLOCK_FLAG_DISRUPTION_SOON		(1 << 1) /* About a day */
> +#define VMCLOCK_FLAG_DISRUPTION_IMMINENT	(1 << 2) /* About an hour */
> +#define VMCLOCK_FLAG_PERIOD_ESTERROR_VALID	(1 << 3)
> +#define VMCLOCK_FLAG_PERIOD_MAXERROR_VALID	(1 << 4)
> +#define VMCLOCK_FLAG_TIME_ESTERROR_VALID	(1 << 5)
> +#define VMCLOCK_FLAG_TIME_MAXERROR_VALID	(1 << 6)
> +	/*
> +	 * If the MONOTONIC flag is set then (other than leap seconds) it is
> +	 * guaranteed that the time calculated according this structure at
> +	 * any given moment shall never appear to be later than the time
> +	 * calculated via the structure at any *later* moment.
> +	 *
> +	 * In particular, a timestamp based on a counter reading taken
> +	 * immediately after setting the low bit of seq_count (and the
> +	 * associated memory barrier), using the previously-valid time and
> +	 * period fields, shall never be later than a timestamp based on
> +	 * a counter reading taken immediately before *clearing* the low
> +	 * bit again after the update, using the about-to-be-valid fields.
> +	 */
> +#define VMCLOCK_FLAG_TIME_MONOTONIC		(1 << 7)
> +
> +	uint8_t pad[2];
> +	uint8_t clock_status;
> +#define VMCLOCK_STATUS_UNKNOWN		0
> +#define VMCLOCK_STATUS_INITIALIZING	1
> +#define VMCLOCK_STATUS_SYNCHRONIZED	2
> +#define VMCLOCK_STATUS_FREERUNNING	3
> +#define VMCLOCK_STATUS_UNRELIABLE	4
> +
> +	/*
> +	 * The time exposed through this device is never smeared. This field
> +	 * corresponds to the 'subtype' field in virtio-rtc, which indicates
> +	 * the smearing method. However in this case it provides a *hint* to
> +	 * the guest operating system, such that *if* the guest OS wants to
> +	 * provide its users with an alternative clock which does not follow
> +	 * UTC, it may do so in a fashion consistent with the other systems
> +	 * in the nearby environment.
> +	 */
> +	uint8_t leap_second_smearing_hint; /* Matches VIRTIO_RTC_SUBTYPE_xxx */
> +#define VMCLOCK_SMEARING_STRICT		0
> +#define VMCLOCK_SMEARING_NOON_LINEAR	1
> +#define VMCLOCK_SMEARING_UTC_SLS	2
> +	int16_t tai_offset_sec;
> +	uint8_t leap_indicator;
> +	/*
> +	 * This field is based on the the VIRTIO_RTC_LEAP_xxx values as
> +	 * defined in the current draft of virtio-rtc, but since smearing
> +	 * cannot be used with the shared memory device, some values are
> +	 * not used.
> +	 *
> +	 * The _POST_POS and _POST_NEG values allow the guest to perform
> +	 * its own smearing during the day or so after a leap second when
> +	 * such smearing may need to continue being applied for a leap
> +	 * second which is now theoretically "historical".
> +	 */
> +#define VMCLOCK_LEAP_NONE	0x00	/* No known nearby leap second */
> +#define VMCLOCK_LEAP_PRE_POS	0x01	/* Positive leap second at EOM */
> +#define VMCLOCK_LEAP_PRE_NEG	0x02	/* Negative leap second at EOM */
> +#define VMCLOCK_LEAP_POS	0x03	/* Set during 23:59:60 second */
> +#define VMCLOCK_LEAP_POST_POS	0x04
> +#define VMCLOCK_LEAP_POST_NEG	0x05
> +
> +	/* Bit shift for counter_period_frac_sec and its error rate */
> +	uint8_t counter_period_shift;
> +	/*
> +	 * Paired values of counter and UTC at a given point in time.
> +	 */
> +	uint64_t counter_value;
> +	/*
> +	 * Counter period, and error margin of same. The unit of these
> +	 * fields is 1/2^(64 + counter_period_shift) of a second.
> +	 */
> +	uint64_t counter_period_frac_sec;
> +	uint64_t counter_period_esterror_rate_frac_sec;
> +	uint64_t counter_period_maxerror_rate_frac_sec;
> +
> +	/*
> +	 * Time according to time_type field above.
> +	 */
> +	uint64_t time_sec;		/* Seconds since time_type epoch */
> +	uint64_t time_frac_sec;		/* Units of 1/2^64 of a second */
> +	uint64_t time_esterror_nanosec;
> +	uint64_t time_maxerror_nanosec;
> +};
> +
> +#endif /*  __VMCLOCK_ABI_H__ */
> -- 
> 2.44.0
> 
> 



you said you will use __le here?