igc: Add support for PTP getcrosststamp()

i225 supports PCIe Precision Time Measurement (PTM), allowing us to
support the PTP_SYS_OFFSET_PRECISE ioctl() in the driver via the
getcrosststamp() function.

The easiest way to expose the PTM registers would be to configure the PTM
dialogs to run periodically, but the PTP_SYS_OFFSET_PRECISE ioctl()
semantics are more aligned to using a kind of "one-shot" way of retrieving
the PTM timestamps. But this causes a bit more code to be written: the
trigger registers for the PTM dialogs are not cleared automatically.

i225 can be configured to send "fake" packets with the PTM
information, adding support for handling these types of packets is
left for the future.

PTM improves the accuracy of time synchronization, for example, using
phc2sys, while a simple application is sending packets as fast as
possible. First, without .getcrosststamp():

phc2sys[191.382]: enp4s0 sys offset      -959 s2 freq    -454 delay   4492
phc2sys[191.482]: enp4s0 sys offset       798 s2 freq   +1015 delay   4069
phc2sys[191.583]: enp4s0 sys offset       962 s2 freq   +1418 delay   3849
phc2sys[191.683]: enp4s0 sys offset       924 s2 freq   +1669 delay   3753
phc2sys[191.783]: enp4s0 sys offset       664 s2 freq   +1686 delay   3349
phc2sys[191.883]: enp4s0 sys offset       218 s2 freq   +1439 delay   2585
phc2sys[191.983]: enp4s0 sys offset       761 s2 freq   +2048 delay   3750
phc2sys[192.083]: enp4s0 sys offset       756 s2 freq   +2271 delay   4061
phc2sys[192.183]: enp4s0 sys offset       809 s2 freq   +2551 delay   4384
phc2sys[192.283]: enp4s0 sys offset      -108 s2 freq   +1877 delay   2480
phc2sys[192.383]: enp4s0 sys offset     -1145 s2 freq    +807 delay   4438
phc2sys[192.484]: enp4s0 sys offset       571 s2 freq   +2180 delay   3849
phc2sys[192.584]: enp4s0 sys offset       241 s2 freq   +2021 delay   3389
phc2sys[192.684]: enp4s0 sys offset       405 s2 freq   +2257 delay   3829
phc2sys[192.784]: enp4s0 sys offset        17 s2 freq   +1991 delay   3273
phc2sys[192.884]: enp4s0 sys offset       152 s2 freq   +2131 delay   3948
phc2sys[192.984]: enp4s0 sys offset      -187 s2 freq   +1837 delay   3162
phc2sys[193.084]: enp4s0 sys offset     -1595 s2 freq    +373 delay   4557
phc2sys[193.184]: enp4s0 sys offset       107 s2 freq   +1597 delay   3740
phc2sys[193.284]: enp4s0 sys offset       199 s2 freq   +1721 delay   4010
phc2sys[193.385]: enp4s0 sys offset      -169 s2 freq   +1413 delay   3701
phc2sys[193.485]: enp4s0 sys offset       -47 s2 freq   +1484 delay   3581
phc2sys[193.585]: enp4s0 sys offset       -65 s2 freq   +1452 delay   3778
phc2sys[193.685]: enp4s0 sys offset        95 s2 freq   +1592 delay   3888
phc2sys[193.785]: enp4s0 sys offset       206 s2 freq   +1732 delay   4445
phc2sys[193.885]: enp4s0 sys offset      -652 s2 freq    +936 delay   2521
phc2sys[193.985]: enp4s0 sys offset      -203 s2 freq   +1189 delay   3391
phc2sys[194.085]: enp4s0 sys offset      -376 s2 freq    +955 delay   2951
phc2sys[194.185]: enp4s0 sys offset      -134 s2 freq   +1084 delay   3330
phc2sys[194.285]: enp4s0 sys offset       -22 s2 freq   +1156 delay   3479
phc2sys[194.386]: enp4s0 sys offset        32 s2 freq   +1204 delay   3602
phc2sys[194.486]: enp4s0 sys offset       122 s2 freq   +1303 delay   3731

Statistics for this run (total of 2179 lines), in nanoseconds:
  average: -1.12
  stdev: 634.80
  max: 1551
  min: -2215

With .getcrosststamp() via PCIe PTM:

phc2sys[367.859]: enp4s0 sys offset         6 s2 freq   +1727 delay      0
phc2sys[367.959]: enp4s0 sys offset        -2 s2 freq   +1721 delay      0
phc2sys[368.059]: enp4s0 sys offset         5 s2 freq   +1727 delay      0
phc2sys[368.160]: enp4s0 sys offset        -1 s2 freq   +1723 delay      0
phc2sys[368.260]: enp4s0 sys offset        -4 s2 freq   +1719 delay      0
phc2sys[368.360]: enp4s0 sys offset        -5 s2 freq   +1717 delay      0
phc2sys[368.460]: enp4s0 sys offset         1 s2 freq   +1722 delay      0
phc2sys[368.560]: enp4s0 sys offset        -3 s2 freq   +1718 delay      0
phc2sys[368.660]: enp4s0 sys offset         5 s2 freq   +1725 delay      0
phc2sys[368.760]: enp4s0 sys offset        -1 s2 freq   +1721 delay      0
phc2sys[368.860]: enp4s0 sys offset         0 s2 freq   +1721 delay      0
phc2sys[368.960]: enp4s0 sys offset         0 s2 freq   +1721 delay      0
phc2sys[369.061]: enp4s0 sys offset         4 s2 freq   +1725 delay      0
phc2sys[369.161]: enp4s0 sys offset         1 s2 freq   +1724 delay      0
phc2sys[369.261]: enp4s0 sys offset         4 s2 freq   +1727 delay      0
phc2sys[369.361]: enp4s0 sys offset         8 s2 freq   +1732 delay      0
phc2sys[369.461]: enp4s0 sys offset         7 s2 freq   +1733 delay      0
phc2sys[369.561]: enp4s0 sys offset         4 s2 freq   +1733 delay      0
phc2sys[369.661]: enp4s0 sys offset         1 s2 freq   +1731 delay      0
phc2sys[369.761]: enp4s0 sys offset         1 s2 freq   +1731 delay      0
phc2sys[369.861]: enp4s0 sys offset        -5 s2 freq   +1725 delay      0
phc2sys[369.961]: enp4s0 sys offset        -4 s2 freq   +1725 delay      0
phc2sys[370.062]: enp4s0 sys offset         2 s2 freq   +1730 delay      0
phc2sys[370.162]: enp4s0 sys offset        -7 s2 freq   +1721 delay      0
phc2sys[370.262]: enp4s0 sys offset        -3 s2 freq   +1723 delay      0
phc2sys[370.362]: enp4s0 sys offset         1 s2 freq   +1726 delay      0
phc2sys[370.462]: enp4s0 sys offset        -3 s2 freq   +1723 delay      0
phc2sys[370.562]: enp4s0 sys offset        -1 s2 freq   +1724 delay      0
phc2sys[370.662]: enp4s0 sys offset        -4 s2 freq   +1720 delay      0
phc2sys[370.762]: enp4s0 sys offset        -7 s2 freq   +1716 delay      0
phc2sys[370.862]: enp4s0 sys offset        -2 s2 freq   +1719 delay      0

Statistics for this run (total of 2179 lines), in nanoseconds:
  average: 0.14
  stdev: 5.03
  max: 48
  min: -27

For reference, the statistics for runs without PCIe congestion show
that the improvements from enabling PTM are less dramatic. For two
runs of 16466 entries:
  without PTM: avg -0.04 stdev 10.57 max 39 min -42
  with PTM: avg 0.01 stdev 4.20 max 19 min -16

One possible explanation is that when PTM is not enabled, and there's a lot
of traffic in the PCIe fabric, some register reads will take more time
than the others because of congestion on the PCIe fabric.

When PTM is enabled, even if the PTM dialogs take more time to
complete under heavy traffic, the time measurements do not depend on
the time to read the registers.

This was implemented following the i225 EAS version 0.993.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Tested-by: Dvora Fuxbrumer <dvorax.fuxbrumer@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

1 files changed, 31 insertions, 0 deletions

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index c6315690e20f..c40563350a5e 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -523,6 +523,37 @@
 #define IGC_RXCSUM_CRCOFL	0x00000800   /* CRC32 offload enable */
 #define IGC_RXCSUM_PCSD		0x00002000   /* packet checksum disabled */
 
+/* PCIe PTM Control */
+#define IGC_PTM_CTRL_START_NOW	BIT(29) /* Start PTM Now */
+#define IGC_PTM_CTRL_EN		BIT(30) /* Enable PTM */
+#define IGC_PTM_CTRL_TRIG	BIT(31) /* PTM Cycle trigger */
+#define IGC_PTM_CTRL_SHRT_CYC(usec)	(((usec) & 0x2f) << 2)
+#define IGC_PTM_CTRL_PTM_TO(usec)	(((usec) & 0xff) << 8)
+
+#define IGC_PTM_SHORT_CYC_DEFAULT	10  /* Default Short/interrupted cycle interval */
+#define IGC_PTM_CYC_TIME_DEFAULT	5   /* Default PTM cycle time */
+#define IGC_PTM_TIMEOUT_DEFAULT		255 /* Default timeout for PTM errors */
+
+/* PCIe Digital Delay */
+#define IGC_PCIE_DIG_DELAY_DEFAULT	0x01440000
+
+/* PCIe PHY Delay */
+#define IGC_PCIE_PHY_DELAY_DEFAULT	0x40900000
+
+#define IGC_TIMADJ_ADJUST_METH		0x40000000
+
+/* PCIe PTM Status */
+#define IGC_PTM_STAT_VALID		BIT(0) /* PTM Status */
+#define IGC_PTM_STAT_RET_ERR		BIT(1) /* Root port timeout */
+#define IGC_PTM_STAT_BAD_PTM_RES	BIT(2) /* PTM Response msg instead of PTM Response Data */
+#define IGC_PTM_STAT_T4M1_OVFL		BIT(3) /* T4 minus T1 overflow */
+#define IGC_PTM_STAT_ADJUST_1ST		BIT(4) /* 1588 timer adjusted during 1st PTM cycle */
+#define IGC_PTM_STAT_ADJUST_CYC		BIT(5) /* 1588 timer adjusted during non-1st PTM cycle */
+
+/* PCIe PTM Cycle Control */
+#define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec)	((msec) & 0x3ff) /* PTM Cycle Time (msec) */
+#define IGC_PTM_CYCLE_CTRL_AUTO_CYC_EN		BIT(31) /* PTM Cycle Control */
+
 /* GPY211 - I225 defines */
 #define GPY_MMD_MASK		0xFFFF0000
 #define GPY_MMD_SHIFT		16