Merge branch 'support-exposing-raw-cycle-counters-in-ptp-and-mlx5'

Tariq Toukan says:

====================
Support exposing raw cycle counters in PTP and mlx5

This series by Carolina adds support in ptp and usage in mlx5 for
exposing the raw free-running cycle counter of PTP hardware clocks.

This is V2. Find previous one here:
https://lore.kernel.org/all/1752556533-39218-1-git-send-email-tariqt@nvidia.com/

Find detailed description by Carolina below [1].

[1]
This patch series introduces support for exposing the raw free-running
cycle counter of PTP hardware clocks. When the device is in free-running
mode, it emits timestamps as raw cycle values instead of nanoseconds.
These values may be passed directly to user space through:

- fwctl: exposes internal device event records that include raw
         cycle-based timestamps.

- DPDK: retrieves CQEs that contain raw cycle counters, which are passed
        to user space unmodified.

To address this, the series introduces two new ioctl commands that allow
userspace to query the device's raw cycle counter together with host
time:

 - PTP_SYS_OFFSET_PRECISE_CYCLES

 - PTP_SYS_OFFSET_EXTENDED_CYCLES

These commands work like their existing counterparts but return the
device timestamp in cycle units instead of real-time nanoseconds.  This
allows user space to collect (cycle, time) pairs and build a mapping
between the device’s free-running clock and host time.

This can also be useful in the XDP fast path: if a driver inserts the
raw cycle value into metadata instead of a real-time timestamp, it can
avoid the overhead of converting cycles to time in the kernel. Then
userspace can resolve the cycle-to-time mapping using this ioctl when
needed.

The ioctl enables user space to correlate those with host time, without
requiring the PHC to be synchronized, so long as the drift remains
stable during collection.

Adds the new PTP ioctls and integrates support in ptp_ioctl():
- ptp: Add ioctl commands to expose raw cycle counter values

Support for exposing raw cycles in mlx5:
- net/mlx5: Extract MTCTR register read logic into helper function
- net/mlx5: Support getcyclesx and getcrosscycles
====================

Link: https://patch.msgid.link/1755008228-88881-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c

@@ -247,27 +247,24 @@ static bool mlx5_is_ptm_source_time_available(struct mlx5_core_dev *dev)
 	return !!MLX5_GET(mtptm_reg, out, psta);
 }
 
-static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
-				     struct system_counterval_t *sys_counterval,
-				     void *ctx)
+static int mlx5_mtctr_read(struct mlx5_core_dev *mdev,
+			   bool real_time_mode,
+			   struct system_counterval_t *sys_counterval,
+			   u64 *device)
 {
 	u32 out[MLX5_ST_SZ_DW(mtctr_reg)] = {0};
 	u32 in[MLX5_ST_SZ_DW(mtctr_reg)] = {0};
-	struct mlx5_core_dev *mdev = ctx;
-	bool real_time_mode;
-	u64 host, device;
+	u64 host;
 	int err;
 
-	real_time_mode = mlx5_real_time_mode(mdev);
-
 	MLX5_SET(mtctr_reg, in, first_clock_timestamp_request,
 		 MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK);
 	MLX5_SET(mtctr_reg, in, second_clock_timestamp_request,
 		 real_time_mode ? MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK :
-		 MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER);
+				  MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER);
 
-	err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTCTR,
-				   0, 0);
+	err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTCTR, 0, 0);
 	if (err)
 		return err;
 
@@ -281,8 +278,26 @@ static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
 			.cs_id = CSID_X86_ART,
 			.use_nsecs = true,
 	};
+	*device = MLX5_GET64(mtctr_reg, out, second_clock_timestamp);
+
+	return 0;
+}
+
+static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
+				     struct system_counterval_t *sys_counterval,
+				     void *ctx)
+{
+	struct mlx5_core_dev *mdev = ctx;
+	bool real_time_mode;
+	u64 device;
+	int err;
+
+	real_time_mode = mlx5_real_time_mode(mdev);
+
+	err = mlx5_mtctr_read(mdev, real_time_mode, sys_counterval, &device);
+	if (err)
+		return err;
 
-	device = MLX5_GET64(mtctr_reg, out, second_clock_timestamp);
 	if (real_time_mode)
 		*device_time = ns_to_ktime(REAL_TIME_TO_NS(device >> 32, device & U32_MAX));
 	else
@@ -291,6 +306,23 @@ static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
 	return 0;
 }
 
+static int
+mlx5_mtctr_syncdevicecyclestime(ktime_t *device_time,
+				struct system_counterval_t *sys_counterval,
+				void *ctx)
+{
+	struct mlx5_core_dev *mdev = ctx;
+	u64 device;
+	int err;
+
+	err = mlx5_mtctr_read(mdev, false, sys_counterval, &device);
+	if (err)
+		return err;
+	*device_time = ns_to_ktime(device);
+
+	return 0;
+}
+
 static int mlx5_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 				   struct system_device_crosststamp *cts)
 {
@@ -315,6 +347,32 @@ unlock:
 	mlx5_clock_unlock(clock);
 	return err;
 }
+
+static int mlx5_ptp_getcrosscycles(struct ptp_clock_info *ptp,
+				   struct system_device_crosststamp *cts)
+{
+	struct mlx5_clock *clock =
+		container_of(ptp, struct mlx5_clock, ptp_info);
+	struct system_time_snapshot history_begin = {0};
+	struct mlx5_core_dev *mdev;
+	int err;
+
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+
+	if (!mlx5_is_ptm_source_time_available(mdev)) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	ktime_get_snapshot(&history_begin);
+
+	err = get_device_system_crosststamp(mlx5_mtctr_syncdevicecyclestime,
+					    mdev, &history_begin, cts);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
+}
 #endif /* CONFIG_X86 */
 
 static u64 mlx5_read_time(struct mlx5_core_dev *dev,
@@ -513,6 +571,24 @@ out:
 	return 0;
 }
 
+static int mlx5_ptp_getcyclesx(struct ptp_clock_info *ptp,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
+						ptp_info);
+	struct mlx5_core_dev *mdev;
+	u64 cycles;
+
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+
+	cycles = mlx5_read_time(mdev, sts, false);
+	*ts = ns_to_timespec64(cycles);
+	mlx5_clock_unlock(clock);
+	return 0;
+}
+
 static int mlx5_ptp_adjtime_real_time(struct mlx5_core_dev *mdev, s64 delta)
 {
 	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
@@ -1229,6 +1305,7 @@ static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
 static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_clock *clock = mdev->clock;
+	bool expose_cycles;
 
 	/* Configure the PHC */
 	clock->ptp_info = mlx5_ptp_clock_info;
@@ -1236,12 +1313,22 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 	if (MLX5_CAP_MCAM_REG(mdev, mtutc))
 		mlx5_init_timer_max_freq_adjustment(mdev);
 
+	expose_cycles = !MLX5_CAP_GEN(mdev, disciplined_fr_counter) ||
+			!mlx5_real_time_mode(mdev);
+
 #ifdef CONFIG_X86
 	if (MLX5_CAP_MCAM_REG3(mdev, mtptm) &&
-	    MLX5_CAP_MCAM_REG3(mdev, mtctr) && boot_cpu_has(X86_FEATURE_ART))
+	    MLX5_CAP_MCAM_REG3(mdev, mtctr) && boot_cpu_has(X86_FEATURE_ART)) {
 		clock->ptp_info.getcrosststamp = mlx5_ptp_getcrosststamp;
+		if (expose_cycles)
+			clock->ptp_info.getcrosscycles =
+				mlx5_ptp_getcrosscycles;
+	}
 #endif /* CONFIG_X86 */
 
+	if (expose_cycles)
+		clock->ptp_info.getcyclesx64 = mlx5_ptp_getcyclesx;
+
 	mlx5_timecounter_init(mdev);
 	mlx5_init_clock_info(mdev);
 	mlx5_init_overflow_period(mdev);

drivers/ptp/ptp_chardev.c

@@ -285,17 +285,21 @@ static long ptp_enable_pps(struct ptp_clock *ptp, bool enable)
 		return ops->enable(ops, &req, enable);
 }
 
-static long ptp_sys_offset_precise(struct ptp_clock *ptp, void __user *arg)
+typedef int (*ptp_crosststamp_fn)(struct ptp_clock_info *,
+				  struct system_device_crosststamp *);
+
+static long ptp_sys_offset_precise(struct ptp_clock *ptp, void __user *arg,
+				   ptp_crosststamp_fn crosststamp_fn)
 {
 	struct ptp_sys_offset_precise precise_offset;
 	struct system_device_crosststamp xtstamp;
 	struct timespec64 ts;
 	int err;
 
-	if (!ptp->info->getcrosststamp)
+	if (!crosststamp_fn)
 		return -EOPNOTSUPP;
 
-	err = ptp->info->getcrosststamp(ptp->info, &xtstamp);
+	err = crosststamp_fn(ptp->info, &xtstamp);
 	if (err)
 		return err;
 
@@ -313,12 +317,17 @@ static long ptp_sys_offset_precise(struct ptp_clock *ptp, void __user *arg)
 	return copy_to_user(arg, &precise_offset, sizeof(precise_offset)) ? -EFAULT : 0;
 }
 
-static long ptp_sys_offset_extended(struct ptp_clock *ptp, void __user *arg)
+typedef int (*ptp_gettimex_fn)(struct ptp_clock_info *,
+			       struct timespec64 *,
+			       struct ptp_system_timestamp *);
+
+static long ptp_sys_offset_extended(struct ptp_clock *ptp, void __user *arg,
+				    ptp_gettimex_fn gettimex_fn)
 {
 	struct ptp_sys_offset_extended *extoff __free(kfree) = NULL;
 	struct ptp_system_timestamp sts;
 
-	if (!ptp->info->gettimex64)
+	if (!gettimex_fn)
 		return -EOPNOTSUPP;
 
 	extoff = memdup_user(arg, sizeof(*extoff));
@@ -346,7 +355,7 @@ static long ptp_sys_offset_extended(struct ptp_clock *ptp, void __user *arg)
 		struct timespec64 ts;
 		int err;
 
-		err = ptp->info->gettimex64(ptp->info, &ts, &sts);
+		err = gettimex_fn(ptp->info, &ts, &sts);
 		if (err)
 			return err;
 
@@ -497,11 +506,13 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 
 	case PTP_SYS_OFFSET_PRECISE:
 	case PTP_SYS_OFFSET_PRECISE2:
-		return ptp_sys_offset_precise(ptp, argptr);
+		return ptp_sys_offset_precise(ptp, argptr,
+					      ptp->info->getcrosststamp);
 
 	case PTP_SYS_OFFSET_EXTENDED:
 	case PTP_SYS_OFFSET_EXTENDED2:
-		return ptp_sys_offset_extended(ptp, argptr);
+		return ptp_sys_offset_extended(ptp, argptr,
+					       ptp->info->gettimex64);
 
 	case PTP_SYS_OFFSET:
 	case PTP_SYS_OFFSET2:
@@ -523,6 +534,13 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 	case PTP_MASK_EN_SINGLE:
 		return ptp_mask_en_single(pccontext->private_clkdata, argptr);
 
+	case PTP_SYS_OFFSET_PRECISE_CYCLES:
+		return ptp_sys_offset_precise(ptp, argptr,
+					      ptp->info->getcrosscycles);
+
+	case PTP_SYS_OFFSET_EXTENDED_CYCLES:
+		return ptp_sys_offset_extended(ptp, argptr,
+					       ptp->info->getcyclesx64);
 	default:
 		return -ENOTTY;
 	}

include/uapi/linux/ptp_clock.h

@@ -245,6 +245,10 @@ struct ptp_pin_desc {
 	_IOWR(PTP_CLK_MAGIC, 18, struct ptp_sys_offset_extended)
 #define PTP_MASK_CLEAR_ALL  _IO(PTP_CLK_MAGIC, 19)
 #define PTP_MASK_EN_SINGLE  _IOW(PTP_CLK_MAGIC, 20, unsigned int)
+#define PTP_SYS_OFFSET_PRECISE_CYCLES \
+	_IOWR(PTP_CLK_MAGIC, 21, struct ptp_sys_offset_precise)
+#define PTP_SYS_OFFSET_EXTENDED_CYCLES \
+	_IOWR(PTP_CLK_MAGIC, 22, struct ptp_sys_offset_extended)
 
 struct ptp_extts_event {
 	struct ptp_clock_time t; /* Time event occurred. */