Merge branch 'PTP-support-for-the-SJA1105-DSA-driver'

Vladimir Oltean says:

====================
PTP support for the SJA1105 DSA driver

This patchset adds the following:

 - A timecounter/cyclecounter based PHC for the free-running
   timestamping clock of this switch.

 - A state machine implemented in the DSA tagger for SJA1105, which
   keeps track of metadata follow-up Ethernet frames (the switch's way
   of transmitting RX timestamps).

Clock manipulations on the actual hardware PTP clock will have to be
implemented anyway, for the TTEthernet block and the time-based ingress
policer.

v3 patchset can be found at:
https://lkml.org/lkml/2019/6/4/954

Changes from v3:

- Made it compile with the SJA1105 DSA driver and PTP driver as modules.

- Reworked/simplified/fixed some issues in 03/17
  (dsa_8021q_remove_header) and added an ASCII image that
  illustrates the transformation that is taking place.

- Removed a useless check for sja1105_is_link_local from 16/17 (RX
  timestamping) which also made previous 08/17 patch ("Move
  sja1105_is_link_local to include/linux") useless and therefore dropped.

v2 patchset can be found at:
https://lkml.org/lkml/2019/6/2/146

Changes from v2:

- Broke previous 09/10 patch (timestamping) into multiple smaller
  patches.

- Every patch in the series compiles.

v1 patchset can be found at:
https://lkml.org/lkml/2019/5/28/1093

Changes from v1:

- Removed the addition of the DSA .can_timestamp callback.

- Waiting for meta frames is done completely inside the tagger, and all
  frames emitted on RX are already partially timestamped.

- Added a global data structure for the tagger common to all ports.

- Made PTP work with ports in standalone mode, by limiting use of the
  DMAC-mangling "incl_srcpt" mode only when ports are bridged, aka when
  the DSA master is already promiscuous and can receive anything.
  Also changed meta frames to be sent at the 01-80-C2-00-00-0E DMAC.

- Made some progress w.r.t. observed negative path delay.  Apparently it
  only appears when the delay mechanism is the delay request-response
  (end-to-end) one. If peer delay is used (-P), the path delay is
  positive and appears reasonable for an 1000Base-T link (485 ns in
  steady state).

  SJA1105 as PTP slave (OC) with E2E path delay:

ptp4l[55.600]: master offset          8 s2 freq  +83677 path delay     -2390
ptp4l[56.600]: master offset         17 s2 freq  +83688 path delay     -2391
ptp4l[57.601]: master offset          6 s2 freq  +83682 path delay     -2391
ptp4l[58.601]: master offset         -1 s2 freq  +83677 path delay     -2391

  SJA1105 as PTP slave (OC) with P2P path delay:

ptp4l[48.343]: master offset          5 s2 freq  +83715 path delay       484
ptp4l[48.468]: master offset         -3 s2 freq  +83705 path delay       485
ptp4l[48.593]: master offset          0 s2 freq  +83708 path delay       485
ptp4l[48.718]: master offset          1 s2 freq  +83710 path delay       485
ptp4l[48.844]: master offset          1 s2 freq  +83710 path delay       485
ptp4l[48.969]: master offset         -5 s2 freq  +83702 path delay       485
ptp4l[49.094]: master offset          3 s2 freq  +83712 path delay       485
ptp4l[49.219]: master offset          4 s2 freq  +83714 path delay       485
ptp4l[49.344]: master offset         -5 s2 freq  +83702 path delay       485
ptp4l[49.469]: master offset          3 s2 freq  +83713 path delay       487
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/dsa/sja1105/Kconfig

@@ -16,3 +16,10 @@ tristate "NXP SJA1105 Ethernet switch family support"
 	    - SJA1105Q (Gen. 2, No SGMII, TT-Ethernet)
 	    - SJA1105R (Gen. 2, SGMII, No TT-Ethernet)
 	    - SJA1105S (Gen. 2, SGMII, TT-Ethernet)
+
+config NET_DSA_SJA1105_PTP
+tristate "Support for the PTP clock on the NXP SJA1105 Ethernet switch"
+	depends on NET_DSA_SJA1105
+	help
+	  This enables support for timestamping and PTP clock manipulations in
+	  the SJA1105 DSA driver.

drivers/net/dsa/sja1105/Makefile

 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_NET_DSA_SJA1105) += sja1105.o
+obj-$(CONFIG_NET_DSA_SJA1105_PTP) += sja1105_ptp.o
 
 sja1105-objs := \
     sja1105_spi.o \

drivers/net/dsa/sja1105/sja1105.h

@@ -5,6 +5,8 @@
 #ifndef _SJA1105_H
 #define _SJA1105_H
 
+#include <linux/ptp_clock_kernel.h>
+#include <linux/timecounter.h>
 #include <linux/dsa/sja1105.h>
 #include <net/dsa.h>
 #include <linux/mutex.h>
@@ -27,6 +29,11 @@ struct sja1105_regs {
 	u64 rgu;
 	u64 config;
 	u64 rmii_pll1;
+	u64 ptp_control;
+	u64 ptpclk;
+	u64 ptpclkrate;
+	u64 ptptsclk;
+	u64 ptpegr_ts[SJA1105_NUM_PORTS];
 	u64 pad_mii_tx[SJA1105_NUM_PORTS];
 	u64 cgu_idiv[SJA1105_NUM_PORTS];
 	u64 rgmii_pad_mii_tx[SJA1105_NUM_PORTS];
@@ -50,9 +57,19 @@ struct sja1105_info {
 	 * switch core and device_id)
 	 */
 	u64 part_no;
+	/* E/T and P/Q/R/S have partial timestamps of different sizes.
+	 * They must be reconstructed on both families anyway to get the full
+	 * 64-bit values back.
+	 */
+	int ptp_ts_bits;
+	/* Also SPI commands are of different sizes to retrieve
+	 * the egress timestamps.
+	 */
+	int ptpegr_ts_bytes;
 	const struct sja1105_dynamic_table_ops *dyn_ops;
 	const struct sja1105_table_ops *static_ops;
 	const struct sja1105_regs *regs;
+	int (*ptp_cmd)(const void *ctx, const void *data);
 	int (*reset_cmd)(const void *ctx, const void *data);
 	int (*setup_rgmii_delay)(const void *ctx, int port);
 	/* Prototypes from include/net/dsa.h */
@@ -72,13 +89,25 @@ struct sja1105_private {
 	struct spi_device *spidev;
 	struct dsa_switch *ds;
 	struct sja1105_port ports[SJA1105_NUM_PORTS];
+	struct ptp_clock_info ptp_caps;
+	struct ptp_clock *clock;
+	/* The cycle counter translates the PTP timestamps (based on
+	 * a free-running counter) into a software time domain.
+	 */
+	struct cyclecounter tstamp_cc;
+	struct timecounter tstamp_tc;
+	struct delayed_work refresh_work;
+	/* Serializes all operations on the cycle counter */
+	struct mutex ptp_lock;
 	/* Serializes transmission of management frames so that
 	 * the switch doesn't confuse them with one another.
 	 */
 	struct mutex mgmt_lock;
+	struct sja1105_tagger_data tagger_data;
 };
 
 #include "sja1105_dynamic_config.h"
+#include "sja1105_ptp.h"
 
 struct sja1105_spi_message {
 	u64 access;

drivers/net/dsa/sja1105/sja1105_dynamic_config.c

@@ -378,6 +378,7 @@ struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = {
 		.addr = 0x38,
 	},
 	[BLK_IDX_L2_FORWARDING_PARAMS] = {0},
+	[BLK_IDX_AVB_PARAMS] = {0},
 	[BLK_IDX_GENERAL_PARAMS] = {
 		.entry_packing = sja1105et_general_params_entry_packing,
 		.cmd_packing = sja1105et_general_params_cmd_packing,
@@ -441,6 +442,7 @@ struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = {
 		.addr = 0x38,
 	},
 	[BLK_IDX_L2_FORWARDING_PARAMS] = {0},
+	[BLK_IDX_AVB_PARAMS] = {0},
 	[BLK_IDX_GENERAL_PARAMS] = {
 		.entry_packing = sja1105et_general_params_entry_packing,
 		.cmd_packing = sja1105et_general_params_cmd_packing,

drivers/net/dsa/sja1105/sja1105_ptp.h

+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#ifndef _SJA1105_PTP_H
+#define _SJA1105_PTP_H
+
+#if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP)
+
+int sja1105_ptp_clock_register(struct sja1105_private *priv);
+
+void sja1105_ptp_clock_unregister(struct sja1105_private *priv);
+
+int sja1105_ptpegr_ts_poll(struct sja1105_private *priv, int port, u64 *ts);
+
+int sja1105et_ptp_cmd(const void *ctx, const void *data);
+
+int sja1105pqrs_ptp_cmd(const void *ctx, const void *data);
+
+int sja1105_get_ts_info(struct dsa_switch *ds, int port,
+			struct ethtool_ts_info *ts);
+
+u64 sja1105_tstamp_reconstruct(struct sja1105_private *priv, u64 now,
+			       u64 ts_partial);
+
+int sja1105_ptp_reset(struct sja1105_private *priv);
+
+#else
+
+static inline int sja1105_ptp_clock_register(struct sja1105_private *priv)
+{
+	return 0;
+}
+
+static inline void sja1105_ptp_clock_unregister(struct sja1105_private *priv)
+{
+	return;
+}
+
+static inline int
+sja1105_ptpegr_ts_poll(struct sja1105_private *priv, int port, u64 *ts)
+{
+	return 0;
+}
+
+static inline u64 sja1105_tstamp_reconstruct(struct sja1105_private *priv,
+					     u64 now, u64 ts_partial)
+{
+	return 0;
+}
+
+static inline int sja1105_ptp_reset(struct sja1105_private *priv)
+{
+	return 0;
+}
+
+#define sja1105et_ptp_cmd NULL
+
+#define sja1105pqrs_ptp_cmd NULL
+
+#define sja1105_get_ts_info NULL
+
+#endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */
+
+#endif /* _SJA1105_PTP_H */

drivers/net/dsa/sja1105/sja1105_spi.c

@@ -100,6 +100,7 @@ int sja1105_spi_send_packed_buf(const struct sja1105_private *priv,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(sja1105_spi_send_packed_buf);
 
 /* If @rw is:
  * - SPI_WRITE: creates and sends an SPI write message at absolute
@@ -135,6 +136,7 @@ int sja1105_spi_send_int(const struct sja1105_private *priv,
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(sja1105_spi_send_int);
 
 /* Should be used if a @packed_buf larger than SJA1105_SIZE_SPI_MSG_MAXLEN
  * must be sent/received. Splitting the buffer into chunks and assembling
@@ -478,7 +480,12 @@ int sja1105_static_config_upload(struct sja1105_private *priv)
 		dev_info(dev, "Succeeded after %d tried\n", RETRIES - retries);
 	}
 
+	rc = sja1105_ptp_reset(priv);
+	if (rc < 0)
+		dev_err(dev, "Failed to reset PTP clock: %d\n", rc);
+
 	dev_info(dev, "Reset switch and programmed static config\n");
+
 out:
 	kfree(config_buf);
 	return rc;
@@ -507,6 +514,11 @@ static struct sja1105_regs sja1105et_regs = {
 	.rgmii_tx_clk = {0x100016, 0x10001D, 0x100024, 0x10002B, 0x100032},
 	.rmii_ref_clk = {0x100015, 0x10001C, 0x100023, 0x10002A, 0x100031},
 	.rmii_ext_tx_clk = {0x100018, 0x10001F, 0x100026, 0x10002D, 0x100034},
+	.ptpegr_ts = {0xC0, 0xC2, 0xC4, 0xC6, 0xC8},
+	.ptp_control = 0x17,
+	.ptpclk = 0x18, /* Spans 0x18 to 0x19 */
+	.ptpclkrate = 0x1A,
+	.ptptsclk = 0x1B, /* Spans 0x1B to 0x1C */
 };
 
 static struct sja1105_regs sja1105pqrs_regs = {
@@ -533,6 +545,11 @@ static struct sja1105_regs sja1105pqrs_regs = {
 	.rmii_ref_clk = {0x100015, 0x10001B, 0x100021, 0x100027, 0x10002D},
 	.rmii_ext_tx_clk = {0x100017, 0x10001D, 0x100023, 0x100029, 0x10002F},
 	.qlevel = {0x604, 0x614, 0x624, 0x634, 0x644},
+	.ptpegr_ts = {0xC0, 0xC4, 0xC8, 0xCC, 0xD0},
+	.ptp_control = 0x18,
+	.ptpclk = 0x19,
+	.ptpclkrate = 0x1B,
+	.ptptsclk = 0x1C,
 };
 
 struct sja1105_info sja1105e_info = {
@@ -540,9 +557,12 @@ struct sja1105_info sja1105e_info = {
 	.part_no		= SJA1105ET_PART_NO,
 	.static_ops		= sja1105e_table_ops,
 	.dyn_ops		= sja1105et_dyn_ops,
+	.ptp_ts_bits		= 24,
+	.ptpegr_ts_bytes	= 4,
 	.reset_cmd		= sja1105et_reset_cmd,
 	.fdb_add_cmd		= sja1105et_fdb_add,
 	.fdb_del_cmd		= sja1105et_fdb_del,
+	.ptp_cmd		= sja1105et_ptp_cmd,
 	.regs			= &sja1105et_regs,
 	.name			= "SJA1105E",
 };
@@ -551,9 +571,12 @@ struct sja1105_info sja1105t_info = {
 	.part_no		= SJA1105ET_PART_NO,
 	.static_ops		= sja1105t_table_ops,
 	.dyn_ops		= sja1105et_dyn_ops,
+	.ptp_ts_bits		= 24,
+	.ptpegr_ts_bytes	= 4,
 	.reset_cmd		= sja1105et_reset_cmd,
 	.fdb_add_cmd		= sja1105et_fdb_add,
 	.fdb_del_cmd		= sja1105et_fdb_del,
+	.ptp_cmd		= sja1105et_ptp_cmd,
 	.regs			= &sja1105et_regs,
 	.name			= "SJA1105T",
 };
@@ -562,9 +585,12 @@ struct sja1105_info sja1105p_info = {
 	.part_no		= SJA1105P_PART_NO,
 	.static_ops		= sja1105p_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
+	.ptp_ts_bits		= 32,
+	.ptpegr_ts_bytes	= 8,
 	.reset_cmd		= sja1105pqrs_reset_cmd,
 	.fdb_add_cmd		= sja1105pqrs_fdb_add,
 	.fdb_del_cmd		= sja1105pqrs_fdb_del,
+	.ptp_cmd		= sja1105pqrs_ptp_cmd,
 	.regs			= &sja1105pqrs_regs,
 	.name			= "SJA1105P",
 };
@@ -573,9 +599,12 @@ struct sja1105_info sja1105q_info = {
 	.part_no		= SJA1105Q_PART_NO,
 	.static_ops		= sja1105q_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
+	.ptp_ts_bits		= 32,
+	.ptpegr_ts_bytes	= 8,
 	.reset_cmd		= sja1105pqrs_reset_cmd,
 	.fdb_add_cmd		= sja1105pqrs_fdb_add,
 	.fdb_del_cmd		= sja1105pqrs_fdb_del,
+	.ptp_cmd		= sja1105pqrs_ptp_cmd,
 	.regs			= &sja1105pqrs_regs,
 	.name			= "SJA1105Q",
 };
@@ -584,9 +613,12 @@ struct sja1105_info sja1105r_info = {
 	.part_no		= SJA1105R_PART_NO,
 	.static_ops		= sja1105r_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
+	.ptp_ts_bits		= 32,
+	.ptpegr_ts_bytes	= 8,
 	.reset_cmd		= sja1105pqrs_reset_cmd,
 	.fdb_add_cmd		= sja1105pqrs_fdb_add,
 	.fdb_del_cmd		= sja1105pqrs_fdb_del,
+	.ptp_cmd		= sja1105pqrs_ptp_cmd,
 	.regs			= &sja1105pqrs_regs,
 	.name			= "SJA1105R",
 };
@@ -596,8 +628,11 @@ struct sja1105_info sja1105s_info = {
 	.static_ops		= sja1105s_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
 	.regs			= &sja1105pqrs_regs,
+	.ptp_ts_bits		= 32,
+	.ptpegr_ts_bytes	= 8,
 	.reset_cmd		= sja1105pqrs_reset_cmd,
 	.fdb_add_cmd		= sja1105pqrs_fdb_add,
 	.fdb_del_cmd		= sja1105pqrs_fdb_del,
+	.ptp_cmd		= sja1105pqrs_ptp_cmd,
 	.name			= "SJA1105S",
 };

drivers/net/dsa/sja1105/sja1105_static_config.c

@@ -35,6 +35,7 @@ void sja1105_pack(void *buf, const u64 *val, int start, int end, size_t len)
 	}
 	dump_stack();
 }
+EXPORT_SYMBOL_GPL(sja1105_pack);
 
 void sja1105_unpack(const void *buf, u64 *val, int start, int end, size_t len)
 {
@@ -52,6 +53,7 @@ void sja1105_unpack(const void *buf, u64 *val, int start, int end, size_t len)
 		       start, end);
 	dump_stack();
 }
+EXPORT_SYMBOL_GPL(sja1105_unpack);
 
 void sja1105_packing(void *buf, u64 *val, int start, int end,
 		     size_t len, enum packing_op op)
@@ -74,6 +76,7 @@ void sja1105_packing(void *buf, u64 *val, int start, int end,
 	}
 	dump_stack();
 }
+EXPORT_SYMBOL_GPL(sja1105_packing);
 
 /* Little-endian Ethernet CRC32 of data packed as big-endian u32 words */
 u32 sja1105_crc32(const void *buf, size_t len)
@@ -91,6 +94,28 @@ u32 sja1105_crc32(const void *buf, size_t len)
 	return ~crc;
 }
 
+static size_t sja1105et_avb_params_entry_packing(void *buf, void *entry_ptr,
+						 enum packing_op op)
+{
+	const size_t size = SJA1105ET_SIZE_AVB_PARAMS_ENTRY;
+	struct sja1105_avb_params_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->destmeta, 95, 48, size, op);
+	sja1105_packing(buf, &entry->srcmeta,  47,  0, size, op);
+	return size;
+}
+
+static size_t sja1105pqrs_avb_params_entry_packing(void *buf, void *entry_ptr,
+						   enum packing_op op)
+{
+	const size_t size = SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY;
+	struct sja1105_avb_params_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->destmeta,   125,  78, size, op);
+	sja1105_packing(buf, &entry->srcmeta,     77,  30, size, op);
+	return size;
+}
+
 static size_t sja1105et_general_params_entry_packing(void *buf, void *entry_ptr,
 						     enum packing_op op)
 {
@@ -423,6 +448,7 @@ static u64 blk_id_map[BLK_IDX_MAX] = {
 	[BLK_IDX_MAC_CONFIG] = BLKID_MAC_CONFIG,
 	[BLK_IDX_L2_LOOKUP_PARAMS] = BLKID_L2_LOOKUP_PARAMS,
 	[BLK_IDX_L2_FORWARDING_PARAMS] = BLKID_L2_FORWARDING_PARAMS,
+	[BLK_IDX_AVB_PARAMS] = BLKID_AVB_PARAMS,
 	[BLK_IDX_GENERAL_PARAMS] = BLKID_GENERAL_PARAMS,
 	[BLK_IDX_XMII_PARAMS] = BLKID_XMII_PARAMS,
 };
@@ -624,6 +650,12 @@ struct sja1105_table_ops sja1105e_table_ops[BLK_IDX_MAX] = {
 		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
 		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
 	},
+	[BLK_IDX_AVB_PARAMS] = {
+		.packing = sja1105et_avb_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_avb_params_entry),
+		.packed_entry_size = SJA1105ET_SIZE_AVB_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT,
+	},
 	[BLK_IDX_GENERAL_PARAMS] = {
 		.packing = sja1105et_general_params_entry_packing,
 		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
@@ -682,6 +714,12 @@ struct sja1105_table_ops sja1105t_table_ops[BLK_IDX_MAX] = {
 		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
 		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
 	},
+	[BLK_IDX_AVB_PARAMS] = {
+		.packing = sja1105et_avb_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_avb_params_entry),
+		.packed_entry_size = SJA1105ET_SIZE_AVB_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT,
+	},
 	[BLK_IDX_GENERAL_PARAMS] = {
 		.packing = sja1105et_general_params_entry_packing,
 		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
@@ -740,6 +778,12 @@ struct sja1105_table_ops sja1105p_table_ops[BLK_IDX_MAX] = {
 		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
 		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
 	},
+	[BLK_IDX_AVB_PARAMS] = {
+		.packing = sja1105pqrs_avb_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_avb_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT,
+	},
 	[BLK_IDX_GENERAL_PARAMS] = {
 		.packing = sja1105pqrs_general_params_entry_packing,
 		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
@@ -798,6 +842,12 @@ struct sja1105_table_ops sja1105q_table_ops[BLK_IDX_MAX] = {
 		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
 		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
 	},
+	[BLK_IDX_AVB_PARAMS] = {
+		.packing = sja1105pqrs_avb_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_avb_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT,
+	},
 	[BLK_IDX_GENERAL_PARAMS] = {
 		.packing = sja1105pqrs_general_params_entry_packing,
 		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
@@ -856,6 +906,12 @@ struct sja1105_table_ops sja1105r_table_ops[BLK_IDX_MAX] = {
 		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
 		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
 	},
+	[BLK_IDX_AVB_PARAMS] = {
+		.packing = sja1105pqrs_avb_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_avb_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT,
+	},
 	[BLK_IDX_GENERAL_PARAMS] = {
 		.packing = sja1105pqrs_general_params_entry_packing,
 		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
@@ -914,6 +970,12 @@ struct sja1105_table_ops sja1105s_table_ops[BLK_IDX_MAX] = {
 		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
 		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
 	},
+	[BLK_IDX_AVB_PARAMS] = {
+		.packing = sja1105pqrs_avb_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_avb_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT,
+	},
 	[BLK_IDX_GENERAL_PARAMS] = {
 		.packing = sja1105pqrs_general_params_entry_packing,
 		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),

drivers/net/dsa/sja1105/sja1105_static_config.h

@@ -20,10 +20,12 @@
 #define SJA1105ET_SIZE_MAC_CONFIG_ENTRY			28
 #define SJA1105ET_SIZE_L2_LOOKUP_PARAMS_ENTRY		4
 #define SJA1105ET_SIZE_GENERAL_PARAMS_ENTRY		40
+#define SJA1105ET_SIZE_AVB_PARAMS_ENTRY			12
 #define SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY		20
 #define SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY		32
 #define SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY		16
 #define SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY		44
+#define SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY		16
 
 /* UM10944.pdf Page 11, Table 2. Configuration Blocks */
 enum {
@@ -34,6 +36,7 @@ enum {
 	BLKID_MAC_CONFIG				= 0x09,
 	BLKID_L2_LOOKUP_PARAMS				= 0x0D,
 	BLKID_L2_FORWARDING_PARAMS			= 0x0E,
+	BLKID_AVB_PARAMS				= 0x10,
 	BLKID_GENERAL_PARAMS				= 0x11,
 	BLKID_XMII_PARAMS				= 0x4E,
 };
@@ -46,6 +49,7 @@ enum sja1105_blk_idx {
 	BLK_IDX_MAC_CONFIG,
 	BLK_IDX_L2_LOOKUP_PARAMS,
 	BLK_IDX_L2_FORWARDING_PARAMS,
+	BLK_IDX_AVB_PARAMS,
 	BLK_IDX_GENERAL_PARAMS,
 	BLK_IDX_XMII_PARAMS,
 	BLK_IDX_MAX,
@@ -64,6 +68,7 @@ enum sja1105_blk_idx {
 #define SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT		1
 #define SJA1105_MAX_GENERAL_PARAMS_COUNT		1
 #define SJA1105_MAX_XMII_PARAMS_COUNT			1
+#define SJA1105_MAX_AVB_PARAMS_COUNT			1
 
 #define SJA1105_MAX_FRAME_MEMORY			929
 
@@ -179,6 +184,11 @@ struct sja1105_l2_policing_entry {
 	u64 partition;
 };
 
+struct sja1105_avb_params_entry {
+	u64 destmeta;
+	u64 srcmeta;
+};
+
 struct sja1105_mac_config_entry {
 	u64 top[8];
 	u64 base[8];

include/linux/dsa/8021q.h

@@ -20,9 +20,6 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
 struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
 			       u16 tpid, u16 tci);
 
-struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev,
-			      struct packet_type *pt, u16 *tpid, u16 *tci);
-
 u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port);
 
 u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port);
@@ -31,6 +28,8 @@ int dsa_8021q_rx_switch_id(u16 vid);
 
 int dsa_8021q_rx_source_port(u16 vid);
 
+struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb);
+
 #else
 
 int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
@@ -45,12 +44,6 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
 	return NULL;
 }
 
-struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev,
-			      struct packet_type *pt, u16 *tpid, u16 *tci)
-{
-	return NULL;
-}
-
 u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port)
 {
 	return 0;
@@ -71,6 +64,11 @@ int dsa_8021q_rx_source_port(u16 vid)
 	return 0;
 }
 
+struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb)
+{
+	return NULL;
+}
+
 #endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */
 
 #endif /* _NET_DSA_8021Q_H */

include/linux/dsa/sja1105.h

@@ -12,6 +12,7 @@
 #include <net/dsa.h>
 
 #define ETH_P_SJA1105				ETH_P_DSA_8021Q
+#define ETH_P_SJA1105_META			0x0008
 
 /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */
 #define SJA1105_LINKLOCAL_FILTER_A		0x0180C2000000ull
@@ -20,8 +21,41 @@
 #define SJA1105_LINKLOCAL_FILTER_B		0x011B19000000ull
 #define SJA1105_LINKLOCAL_FILTER_B_MASK		0xFFFFFF000000ull
 
+/* Source and Destination MAC of follow-up meta frames.
+ * Whereas the choice of SMAC only affects the unique identification of the
+ * switch as sender of meta frames, the DMAC must be an address that is present
+ * in the DSA master port's multicast MAC filter.
+ * 01-80-C2-00-00-0E is a good choice for this, as all profiles of IEEE 1588
+ * over L2 use this address for some purpose already.
+ */
+#define SJA1105_META_SMAC			0x222222222222ull
+#define SJA1105_META_DMAC			0x0180C200000Eull
+
+/* Global tagger data: each struct sja1105_port has a reference to
+ * the structure defined in struct sja1105_private.
+ */
+struct sja1105_tagger_data {
+	struct sk_buff_head skb_rxtstamp_queue;
+	struct work_struct rxtstamp_work;
+	struct sk_buff *stampable_skb;
+	/* Protects concurrent access to the meta state machine
+	 * from taggers running on multiple ports on SMP systems
+	 */
+	spinlock_t meta_lock;
+	bool hwts_rx_en;
+};
+
+struct sja1105_skb_cb {
+	u32 meta_tstamp;
+};
+
+#define SJA1105_SKB_CB(skb) \
+	((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb))
+
 struct sja1105_port {
+	struct sja1105_tagger_data *data;
 	struct dsa_port *dp;
+	bool hwts_tx_en;
 	int mgmt_slot;
 };
 

include/net/dsa.h

@@ -357,6 +357,7 @@ struct dsa_switch_ops {
 						  int port);
 
 	int	(*setup)(struct dsa_switch *ds);
+	void	(*teardown)(struct dsa_switch *ds);
 	u32	(*get_phy_flags)(struct dsa_switch *ds, int port);
 
 	/*

net/dsa/dsa2.c

@@ -408,6 +408,9 @@ static void dsa_switch_teardown(struct dsa_switch *ds)
 
 	dsa_switch_unregister_notifier(ds);
 
+	if (ds->ops->teardown)
+		ds->ops->teardown(ds);
+
 	if (ds->devlink) {
 		devlink_unregister(ds->devlink);
 		devlink_free(ds->devlink);

net/dsa/slave.c

@@ -423,6 +423,8 @@ static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p,
 	if (!clone)
 		return;
 
+	DSA_SKB_CB(skb)->clone = clone;
+
 	if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type))
 		return;
 
@@ -460,6 +462,7 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 	u64_stats_update_end(&s->syncp);
 
 	DSA_SKB_CB(skb)->deferred_xmit = false;
+	DSA_SKB_CB(skb)->clone = NULL;
 
 	/* Identify PTP protocol packets, clone them, and pass them to the
 	 * switch driver

net/dsa/tag_8021q.c

@@ -235,31 +235,48 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
 }
 EXPORT_SYMBOL_GPL(dsa_8021q_xmit);
 
-struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev,
-			      struct packet_type *pt, u16 *tpid, u16 *tci)
-{
-	struct vlan_ethhdr *tag;
-
-	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
-		return NULL;
-
-	tag = vlan_eth_hdr(skb);
-	*tpid = ntohs(tag->h_vlan_proto);
-	*tci = ntohs(tag->h_vlan_TCI);
-
-	/* skb->data points in the middle of the VLAN tag,
-	 * after tpid and before tci. This is because so far,
-	 * ETH_HLEN (DMAC, SMAC, EtherType) bytes were pulled.
+/* In the DSA packet_type handler, skb->data points in the middle of the VLAN
+ * tag, after tpid and before tci. This is because so far, ETH_HLEN
+ * (DMAC, SMAC, EtherType) bytes were pulled.
  * There are 2 bytes of VLAN tag left in skb->data, and upper
  * layers expect the 'real' EtherType to be consumed as well.
  * Coincidentally, a VLAN header is also of the same size as
  * the number of bytes that need to be pulled.
+ *
+ * skb_mac_header                                      skb->data
+ * |                                                       |
+ * v                                                       v
+ * |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |
+ * +-----------------------+-----------------------+-------+-------+-------+
+ * |    Destination MAC    |      Source MAC       |  TPID |  TCI  | EType |
+ * +-----------------------+-----------------------+-------+-------+-------+
+ * ^                                               |               |
+ * |<--VLAN_HLEN-->to                              <---VLAN_HLEN--->
+ * from            |
+ *       >>>>>>>   v
+ *       >>>>>>>   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |
+ *       >>>>>>>   +-----------------------+-----------------------+-------+
+ *       >>>>>>>   |    Destination MAC    |      Source MAC       | EType |
+ *                 +-----------------------+-----------------------+-------+
+ *                 ^                                                       ^
+ * (now part of    |                                                       |
+ *  skb->head)     skb_mac_header                                  skb->data
  */
-	skb_pull_rcsum(skb, VLAN_HLEN);
+struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb)
+{
+	u8 *from = skb_mac_header(skb);
+	u8 *dest = from + VLAN_HLEN;
+
+	memmove(dest, from, ETH_HLEN - VLAN_HLEN);
+	skb_pull(skb, VLAN_HLEN);
+	skb_push(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+	skb_pull_rcsum(skb, ETH_HLEN);
 
 	return skb;
 }
-EXPORT_SYMBOL_GPL(dsa_8021q_rcv);
+EXPORT_SYMBOL_GPL(dsa_8021q_remove_header);
 
 static const struct dsa_device_ops dsa_8021q_netdev_ops = {
 	.name		= "8021q",

net/dsa/tag_sja1105.c

@@ -13,6 +13,8 @@ static inline bool sja1105_is_link_local(const struct sk_buff *skb)
 	const struct ethhdr *hdr = eth_hdr(skb);
 	u64 dmac = ether_addr_to_u64(hdr->h_dest);
 
+	if (ntohs(hdr->h_proto) == ETH_P_SJA1105_META)
+		return false;
 	if ((dmac & SJA1105_LINKLOCAL_FILTER_A_MASK) ==
 		    SJA1105_LINKLOCAL_FILTER_A)
 		return true;
@@ -22,15 +24,61 @@ static inline bool sja1105_is_link_local(const struct sk_buff *skb)
 	return false;
 }
 
+struct sja1105_meta {
+	u64 tstamp;
+	u64 dmac_byte_4;
+	u64 dmac_byte_3;
+	u64 source_port;
+	u64 switch_id;
+};
+
+static void sja1105_meta_unpack(const struct sk_buff *skb,
+				struct sja1105_meta *meta)
+{
+	u8 *buf = skb_mac_header(skb) + ETH_HLEN;
+
+	/* UM10944.pdf section 4.2.17 AVB Parameters:
+	 * Structure of the meta-data follow-up frame.
+	 * It is in network byte order, so there are no quirks
+	 * while unpacking the meta frame.
+	 *
+	 * Also SJA1105 E/T only populates bits 23:0 of the timestamp
+	 * whereas P/Q/R/S does 32 bits. Since the structure is the
+	 * same and the E/T puts zeroes in the high-order byte, use
+	 * a unified unpacking command for both device series.
+	 */
+	packing(buf,     &meta->tstamp,     31, 0, 4, UNPACK, 0);
+	packing(buf + 4, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0);
+	packing(buf + 5, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0);
+	packing(buf + 6, &meta->source_port, 7, 0, 1, UNPACK, 0);
+	packing(buf + 7, &meta->switch_id,   7, 0, 1, UNPACK, 0);
+}
+
+static inline bool sja1105_is_meta_frame(const struct sk_buff *skb)
+{
+	const struct ethhdr *hdr = eth_hdr(skb);
+	u64 smac = ether_addr_to_u64(hdr->h_source);
+	u64 dmac = ether_addr_to_u64(hdr->h_dest);
+
+	if (smac != SJA1105_META_SMAC)
+		return false;
+	if (dmac != SJA1105_META_DMAC)
+		return false;
+	if (ntohs(hdr->h_proto) != ETH_P_SJA1105_META)
+		return false;
+	return true;
+}
+
 /* This is the first time the tagger sees the frame on RX.
- * Figure out if we can decode it, and if we can, annotate skb->cb with how we
- * plan to do that, so we don't need to check again in the rcv function.
+ * Figure out if we can decode it.
  */
 static bool sja1105_filter(const struct sk_buff *skb, struct net_device *dev)
 {
+	if (!dsa_port_is_vlan_filtering(dev->dsa_ptr))
+		return true;
 	if (sja1105_is_link_local(skb))
 		return true;
-	if (!dsa_port_is_vlan_filtering(dev->dsa_ptr))
+	if (sja1105_is_meta_frame(skb))
 		return true;
 	return false;
 }
@@ -62,25 +110,152 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb,
 			     ((pcp << VLAN_PRIO_SHIFT) | tx_vid));
 }
 
+static void sja1105_transfer_meta(struct sk_buff *skb,
+				  const struct sja1105_meta *meta)
+{
+	struct ethhdr *hdr = eth_hdr(skb);
+
+	hdr->h_dest[3] = meta->dmac_byte_3;
+	hdr->h_dest[4] = meta->dmac_byte_4;
+	SJA1105_SKB_CB(skb)->meta_tstamp = meta->tstamp;
+}
+
+/* This is a simple state machine which follows the hardware mechanism of
+ * generating RX timestamps:
+ *
+ * After each timestampable skb (all traffic for which send_meta1 and
+ * send_meta0 is true, aka all MAC-filtered link-local traffic) a meta frame
+ * containing a partial timestamp is immediately generated by the switch and
+ * sent as a follow-up to the link-local frame on the CPU port.
+ *
+ * The meta frames have no unique identifier (such as sequence number) by which
+ * one may pair them to the correct timestampable frame.
+ * Instead, the switch has internal logic that ensures no frames are sent on
+ * the CPU port between a link-local timestampable frame and its corresponding
+ * meta follow-up. It also ensures strict ordering between ports (lower ports
+ * have higher priority towards the CPU port). For this reason, a per-port
+ * data structure is not needed/desirable.
+ *
+ * This function pairs the link-local frame with its partial timestamp from the
+ * meta follow-up frame. The full timestamp will be reconstructed later in a
+ * work queue.
+ */
+static struct sk_buff
+*sja1105_rcv_meta_state_machine(struct sk_buff *skb,
+				struct sja1105_meta *meta,
+				bool is_link_local,
+				bool is_meta)
+{
+	struct sja1105_port *sp;
+	struct dsa_port *dp;
+
+	dp = dsa_slave_to_port(skb->dev);
+	sp = dp->priv;
+
+	/* Step 1: A timestampable frame was received.
+	 * Buffer it until we get its meta frame.
+	 */
+	if (is_link_local && sp->data->hwts_rx_en) {
+		spin_lock(&sp->data->meta_lock);
+		/* Was this a link-local frame instead of the meta
+		 * that we were expecting?
+		 */
+		if (sp->data->stampable_skb) {
+			dev_err_ratelimited(dp->ds->dev,
+					    "Expected meta frame, is %12llx "
+					    "in the DSA master multicast filter?\n",
+					    SJA1105_META_DMAC);
+		}
+
+		/* Hold a reference to avoid dsa_switch_rcv
+		 * from freeing the skb.
+		 */
+		sp->data->stampable_skb = skb_get(skb);
+		spin_unlock(&sp->data->meta_lock);
+
+		/* Tell DSA we got nothing */
+		return NULL;
+
+	/* Step 2: The meta frame arrived.
+	 * Time to take the stampable skb out of the closet, annotate it
+	 * with the partial timestamp, and pretend that we received it
+	 * just now (basically masquerade the buffered frame as the meta
+	 * frame, which serves no further purpose).
+	 */
+	} else if (is_meta) {
+		struct sk_buff *stampable_skb;
+
+		spin_lock(&sp->data->meta_lock);
+
+		stampable_skb = sp->data->stampable_skb;
+		sp->data->stampable_skb = NULL;
+
+		/* Was this a meta frame instead of the link-local
+		 * that we were expecting?
+		 */
+		if (!stampable_skb) {
+			dev_err_ratelimited(dp->ds->dev,
+					    "Unexpected meta frame\n");
+			spin_unlock(&sp->data->meta_lock);
+			return NULL;
+		}
+
+		if (stampable_skb->dev != skb->dev) {
+			dev_err_ratelimited(dp->ds->dev,
+					    "Meta frame on wrong port\n");
+			spin_unlock(&sp->data->meta_lock);
+			return NULL;
+		}
+
+		/* Free the meta frame and give DSA the buffered stampable_skb
+		 * for further processing up the network stack.
+		 */
+		kfree_skb(skb);
+
+		skb = skb_copy(stampable_skb, GFP_ATOMIC);
+		if (!skb) {
+			dev_err_ratelimited(dp->ds->dev,
+					    "Failed to copy stampable skb\n");
+			return NULL;
+		}
+		sja1105_transfer_meta(skb, meta);
+		/* The cached copy will be freed now */
+		skb_unref(stampable_skb);
+
+		spin_unlock(&sp->data->meta_lock);
+	}
+
+	return skb;
+}
+
 static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 				   struct net_device *netdev,
 				   struct packet_type *pt)
 {
-	struct ethhdr *hdr = eth_hdr(skb);
-	u64 source_port, switch_id;
-	struct sk_buff *nskb;
+	struct sja1105_meta meta = {0};
+	int source_port, switch_id;
+	struct vlan_ethhdr *hdr;
 	u16 tpid, vid, tci;
+	bool is_link_local;
 	bool is_tagged;
+	bool is_meta;
 
-	nskb = dsa_8021q_rcv(skb, netdev, pt, &tpid, &tci);
-	is_tagged = (nskb && tpid == ETH_P_SJA1105);
-
-	skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
-	vid = tci & VLAN_VID_MASK;
+	hdr = vlan_eth_hdr(skb);
+	tpid = ntohs(hdr->h_vlan_proto);
+	is_tagged = (tpid == ETH_P_SJA1105);
+	is_link_local = sja1105_is_link_local(skb);
+	is_meta = sja1105_is_meta_frame(skb);
 
 	skb->offload_fwd_mark = 1;
 
-	if (sja1105_is_link_local(skb)) {
+	if (is_tagged) {
+		/* Normal traffic path. */
+		tci = ntohs(hdr->h_vlan_TCI);
+		vid = tci & VLAN_VID_MASK;
+		source_port = dsa_8021q_rx_source_port(vid);
+		switch_id = dsa_8021q_rx_switch_id(vid);
+		skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+	} else if (is_link_local) {
 		/* Management traffic path. Switch embeds the switch ID and
 		 * port ID into bytes of the destination MAC, courtesy of
 		 * the incl_srcpt options.
@@ -90,10 +265,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 		/* Clear the DMAC bytes that were mangled by the switch */
 		hdr->h_dest[3] = 0;
 		hdr->h_dest[4] = 0;
+	} else if (is_meta) {
+		sja1105_meta_unpack(skb, &meta);
+		source_port = meta.source_port;
+		switch_id = meta.switch_id;
 	} else {
-		/* Normal traffic path. */
-		source_port = dsa_8021q_rx_source_port(vid);
-		switch_id = dsa_8021q_rx_switch_id(vid);
+		return NULL;
 	}
 
 	skb->dev = dsa_master_find_slave(netdev, switch_id, source_port);
@@ -106,10 +283,10 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 	 * it there, see dsa_switch_rcv: skb_push(skb, ETH_HLEN).
 	 */
 	if (is_tagged)
-		memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - VLAN_HLEN,
-			ETH_HLEN - VLAN_HLEN);
+		skb = dsa_8021q_remove_header(skb);
 
-	return skb;
+	return sja1105_rcv_meta_state_machine(skb, &meta, is_link_local,
+					      is_meta);
 }
 
 static struct dsa_device_ops sja1105_netdev_ops = {