[PATCH v2 phy-next 0/8] RCW override for 10G Lynx dynamic protocol reconfiguration

[PATCH v2 phy-next 0/8] RCW override for 10G Lynx dynamic protocol reconfiguration

[Vladimir Oltean]

Previous set "New Generic PHY driver for Lynx 10G SerDes":
https://lore.kernel.org/linux-phy/20260610151952.2141019-1-vladimir.oltean@nxp.com/
introduced the 10G Lynx SerDes driver with a reduced functionality set.
Namely, only minor protocol changes are supported (1GbE <-> 2.5GbE).
The major protocol changes need a procedure named RCW override,
explained in more detail in commits 6/8 and 7/8.

This series adds kernel and device tree binding support for RCW
override, completing the SerDes PHY driver functionality.

Two components are involved:
- drivers/soc/fsl/guts.c (binding is fsl,layerscape-dcfg.yaml) - Device
  Configuration Unit, this is API provider for the SerDes driver to
  request RCW override depending on SoC
- drivers/phy/freescale/phy-fsl-lynx-10g.c - SerDes PHY driver, this is
  API consumer

The guts driver probes on DCFG blocks from multiple Freescale SoC
generations:
- MPC85xx, BSC and QorIQ (PowerPC) are all covered by the
  Documentation/devicetree/bindings/soc/fsl/guts.txt schema
- Layerscape (Arm) is covered by
  Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml

It is ultimately the same hardware block, just that (from what I can
tell) the Layerscape nodes are also compatible with syscon, and PowerPC
aren't.

RCW override has only been validated on select Layerscape SoCs, so
converting guts.txt to a PowerPC schema is out of scope for this
series - we don't even touch that (just in case it gets asked).

Using syscon to map the DCFG_DCSR register block in the Lynx SerDes
driver instead of creating this guts <-> lynx API was considered, but
because the RCW procedure is SoC-specific, it was ruled out for
polluting the SerDes driver. The guts driver is all about SoC awareness
anyway, and it offers some abstraction of all the gory details.

Resending because Sashiko didn't run on v1 (it runs on linux-phy/master
instead of linux-phy/next, and linux-next, used as fallback when
applying to linux-phy/master fails, wasn't regenerated to include the
Lynx 10G base patches at the time v1 was sent). There was a build
failure on most arches except arm64 anyway, so it's good to have that
fixed.

Changes since v1:
- add Conor's review tag on 6/8
- update email addresses of DT maintainers
- drop DT maintainers from explicit CC on patch 7/8
- keep devicetree@vger.kernel.org CCed on entire series
- include missing <linux/bitfield.h> in patch 7/8
- namespace SRDS_PRTCL values for LS1046A and LS1088A, even if they are
  the same. For LS1028A (not covered here) they are not.
- prefix SRDS_CLK_SEL_{GMII,XGMII} with LS2088A_
- reorder alphanumerically (LS1046A should come before LS1088A)

Change log also in individual patches.

v1 at:
https://lore.kernel.org/linux-phy/20260611193940.44416-1-vladimir.oltean@nxp.com/

Cc: Conor Dooley <conor+dt@kernel.org>
Cc: Krzysztof Kozlowski <krzk+dt@kernel.org>
Cc: Rob Herring <robh@kernel.org>

Ioana Ciornei (5):
  soc: fsl: guts: use a macro to encode the DCFG CCSR space
  soc: fsl: guts: add a global structure to hold state
  soc: fsl: guts: add a central fsl_guts_read() function
  soc: fsl: guts: make it easier to determine on which SoC we are
    running
  soc: fsl: guts: implement the RCW override procedure

Vladimir Oltean (3):
  soc: fsl: guts: make fsl_soc_data available after fsl_guts_init()
  dt-bindings: fsl: layerscape-dcfg: define DCFG_DCSR region
  phy: lynx-10g: use RCW override procedure for dynamic protocol change

 .../bindings/soc/fsl/fsl,layerscape-dcfg.yaml |  15 +-
 drivers/phy/freescale/Kconfig                 |   1 +
 drivers/phy/freescale/phy-fsl-lynx-10g.c      |  24 +-
 drivers/soc/fsl/guts.c                        | 369 ++++++++++++++++--
 include/linux/fsl/guts.h                      |  20 +-
 5 files changed, 393 insertions(+), 36 deletions(-)

-- 
2.34.1


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v2 phy-next 1/8] soc: fsl: guts: use a macro to encode the DCFG CCSR space

[Vladimir Oltean]

From: Ioana Ciornei <ioana.ciornei@nxp.com>

Instead of using a hardcoded value when iomapping the DCFG CCSR space,
add a new macro for it. The code will be easier to follow this way,
especially when we add support for the DCFG DCSR space as well.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
v1->v2: none
---
 drivers/soc/fsl/guts.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
index 9bee7baec2b9..f87ee47c1503 100644
--- a/drivers/soc/fsl/guts.c
+++ b/drivers/soc/fsl/guts.c
@@ -14,6 +14,8 @@
 #include <linux/platform_device.h>
 #include <linux/fsl/guts.h>
 
+#define DCFG_CCSR	0
+
 struct fsl_soc_die_attr {
 	char	*die;
 	u32	svr;
@@ -197,7 +199,7 @@ static int __init fsl_guts_init(void)
 		return 0;
 	soc_data = match->data;
 
-	regs = of_iomap(np, 0);
+	regs = of_iomap(np, DCFG_CCSR);
 	if (!regs) {
 		of_node_put(np);
 		return -ENOMEM;
-- 
2.34.1


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v2 phy-next 2/8] soc: fsl: guts: add a global structure to hold state

[Vladimir Oltean]

From: Ioana Ciornei <ioana.ciornei@nxp.com>

Add the fsl_soc_guts structure in order to pass information like base
addresses, endianness etc between the init time and the runtime
operations (RCW override) which will get added in future patches.
There is no point in mapping and unmapping the DCFG CCSR space every
time we need to make a read, just map it once and keep its reference in
this new global struture.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
v1->v2: none
---
 drivers/soc/fsl/guts.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
index f87ee47c1503..a0a52a5603a5 100644
--- a/drivers/soc/fsl/guts.c
+++ b/drivers/soc/fsl/guts.c
@@ -106,6 +106,11 @@ static const struct fsl_soc_die_attr fsl_soc_die[] = {
 	{ },
 };
 
+static struct fsl_soc_guts {
+	struct ccsr_guts __iomem *dcfg_ccsr;
+	bool little_endian;
+} soc;
+
 static const struct fsl_soc_die_attr *fsl_soc_die_match(
 	u32 svr, const struct fsl_soc_die_attr *matches)
 {
@@ -187,9 +192,7 @@ static int __init fsl_guts_init(void)
 	const struct fsl_soc_die_attr *soc_die;
 	const struct fsl_soc_data *soc_data;
 	const struct of_device_id *match;
-	struct ccsr_guts __iomem *regs;
 	struct device_node *np;
-	bool little_endian;
 	u64 soc_uid = 0;
 	u32 svr;
 	int ret;
@@ -199,18 +202,17 @@ static int __init fsl_guts_init(void)
 		return 0;
 	soc_data = match->data;
 
-	regs = of_iomap(np, DCFG_CCSR);
-	if (!regs) {
+	soc.dcfg_ccsr = of_iomap(np, DCFG_CCSR);
+	if (!soc.dcfg_ccsr) {
 		of_node_put(np);
 		return -ENOMEM;
 	}
 
-	little_endian = of_property_read_bool(np, "little-endian");
-	if (little_endian)
-		svr = ioread32(&regs->svr);
+	soc.little_endian = of_property_read_bool(np, "little-endian");
+	if (soc.little_endian)
+		svr = ioread32(&soc.dcfg_ccsr->svr);
 	else
-		svr = ioread32be(&regs->svr);
-	iounmap(regs);
+		svr = ioread32be(&soc.dcfg_ccsr->svr);
 	of_node_put(np);
 
 	/* Register soc device */
@@ -263,6 +265,8 @@ static int __init fsl_guts_init(void)
 
 err_nomem:
 	ret = -ENOMEM;
+
+	iounmap(soc.dcfg_ccsr);
 err:
 	kfree(soc_dev_attr->family);
 	kfree(soc_dev_attr->soc_id);
-- 
2.34.1


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v2 phy-next 3/8] soc: fsl: guts: add a central fsl_guts_read() function

[Vladimir Oltean]

From: Ioana Ciornei <ioana.ciornei@nxp.com>

Add a central fsl_guts_read() function which will take into account the
endianness that was already determined. No point is duplicating the
if-else statement each time we need to read a DCFG register.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
v1->v2: none
---
 drivers/soc/fsl/guts.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
index a0a52a5603a5..dc1a42cd9544 100644
--- a/drivers/soc/fsl/guts.c
+++ b/drivers/soc/fsl/guts.c
@@ -111,6 +111,14 @@ static struct fsl_soc_guts {
 	bool little_endian;
 } soc;
 
+static unsigned int fsl_guts_read(const void __iomem *reg)
+{
+	if (soc.little_endian)
+		return ioread32(reg);
+
+	return ioread32be(reg);
+}
+
 static const struct fsl_soc_die_attr *fsl_soc_die_match(
 	u32 svr, const struct fsl_soc_die_attr *matches)
 {
@@ -209,10 +217,7 @@ static int __init fsl_guts_init(void)
 	}
 
 	soc.little_endian = of_property_read_bool(np, "little-endian");
-	if (soc.little_endian)
-		svr = ioread32(&soc.dcfg_ccsr->svr);
-	else
-		svr = ioread32be(&soc.dcfg_ccsr->svr);
+	svr = fsl_guts_read(&soc.dcfg_ccsr->svr);
 	of_node_put(np);
 
 	/* Register soc device */
-- 
2.34.1


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v2 phy-next 4/8] soc: fsl: guts: make it easier to determine on which SoC we are running

[Vladimir Oltean]

From: Ioana Ciornei <ioana.ciornei@nxp.com>

The guts driver will need to easily determine on which SoC it's running
when it will need to perform RCW override at runtime. The guts driver
knows this already because fsl_guts_init() reads the QorIQ/Layerscape
architectural System Version Register (SVR), but it doesn't save this
for later lookups.

Add a new qoriq_die enum to be used as an index in the fsl_soc_die
array. A new fsl_soc_die_match_one() function is also added so that we
can directly determine if the SVR is a match with a specific die.
The SVR value read from the DCFG CCSR is also kept in the global soc
structure so that it can be accessed when needed.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
v1->v2: none
---
 drivers/soc/fsl/guts.c | 47 ++++++++++++++++++++++++++++++++++++------
 1 file changed, 41 insertions(+), 6 deletions(-)

diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
index dc1a42cd9544..1494b545bbb4 100644
--- a/drivers/soc/fsl/guts.c
+++ b/drivers/soc/fsl/guts.c
@@ -27,6 +27,23 @@ struct fsl_soc_data {
 	u32 uid_offset;
 };
 
+enum qoriq_die {
+	DIE_T4240,
+	DIE_T1040,
+	DIE_T2080,
+	DIE_T1024,
+	DIE_LS1043A,
+	DIE_LS2080A,
+	DIE_LS1088A,
+	DIE_LS1012A,
+	DIE_LS1046A,
+	DIE_LS2088A,
+	DIE_LS1021A,
+	DIE_LX2160A,
+	DIE_LS1028A,
+	DIE_MAX,
+};
+
 /* SoC die attribute definition for QorIQ platform */
 static const struct fsl_soc_die_attr fsl_soc_die[] = {
 	/*
@@ -34,21 +51,25 @@ static const struct fsl_soc_die_attr fsl_soc_die[] = {
 	 */
 
 	/* Die: T4240, SoC: T4240/T4160/T4080 */
+	[DIE_T4240] =
 	{ .die		= "T4240",
 	  .svr		= 0x82400000,
 	  .mask		= 0xfff00000,
 	},
 	/* Die: T1040, SoC: T1040/T1020/T1042/T1022 */
+	[DIE_T1040] =
 	{ .die		= "T1040",
 	  .svr		= 0x85200000,
 	  .mask		= 0xfff00000,
 	},
 	/* Die: T2080, SoC: T2080/T2081 */
+	[DIE_T2080] =
 	{ .die		= "T2080",
 	  .svr		= 0x85300000,
 	  .mask		= 0xfff00000,
 	},
 	/* Die: T1024, SoC: T1024/T1014/T1023/T1013 */
+	[DIE_T1024] =
 	{ .die		= "T1024",
 	  .svr		= 0x85400000,
 	  .mask		= 0xfff00000,
@@ -59,46 +80,55 @@ static const struct fsl_soc_die_attr fsl_soc_die[] = {
 	 */
 
 	/* Die: LS1043A, SoC: LS1043A/LS1023A */
+	[DIE_LS1043A] =
 	{ .die		= "LS1043A",
 	  .svr		= 0x87920000,
 	  .mask		= 0xffff0000,
 	},
 	/* Die: LS2080A, SoC: LS2080A/LS2040A/LS2085A */
+	[DIE_LS2080A] =
 	{ .die		= "LS2080A",
 	  .svr		= 0x87010000,
 	  .mask		= 0xff3f0000,
 	},
 	/* Die: LS1088A, SoC: LS1088A/LS1048A/LS1084A/LS1044A */
+	[DIE_LS1088A] =
 	{ .die		= "LS1088A",
 	  .svr		= 0x87030000,
 	  .mask		= 0xff3f0000,
 	},
 	/* Die: LS1012A, SoC: LS1012A */
+	[DIE_LS1012A] =
 	{ .die		= "LS1012A",
 	  .svr		= 0x87040000,
 	  .mask		= 0xffff0000,
 	},
 	/* Die: LS1046A, SoC: LS1046A/LS1026A */
+	[DIE_LS1046A] =
 	{ .die		= "LS1046A",
 	  .svr		= 0x87070000,
 	  .mask		= 0xffff0000,
 	},
 	/* Die: LS2088A, SoC: LS2088A/LS2048A/LS2084A/LS2044A */
+	[DIE_LS2088A] =
 	{ .die		= "LS2088A",
 	  .svr		= 0x87090000,
 	  .mask		= 0xff3f0000,
 	},
 	/* Die: LS1021A, SoC: LS1021A/LS1020A/LS1022A */
+	[DIE_LS1021A] =
 	{ .die		= "LS1021A",
 	  .svr		= 0x87000000,
 	  .mask		= 0xfff70000,
 	},
 	/* Die: LX2160A, SoC: LX2160A/LX2120A/LX2080A */
+	[DIE_LX2160A] =
 	{ .die          = "LX2160A",
 	  .svr          = 0x87360000,
 	  .mask         = 0xff3f0000,
 	},
 	/* Die: LS1028A, SoC: LS1028A */
+	[DIE_LS1028A] =
 	{ .die          = "LS1028A",
 	  .svr          = 0x870b0000,
 	  .mask         = 0xff3f0000,
@@ -109,6 +139,7 @@ static const struct fsl_soc_die_attr fsl_soc_die[] = {
 static struct fsl_soc_guts {
 	struct ccsr_guts __iomem *dcfg_ccsr;
 	bool little_endian;
+	u32 svr;
 } soc;
 
 static unsigned int fsl_guts_read(const void __iomem *reg)
@@ -119,11 +150,16 @@ static unsigned int fsl_guts_read(const void __iomem *reg)
 	return ioread32be(reg);
 }
 
+static bool fsl_soc_die_match_one(u32 svr, const struct fsl_soc_die_attr *match)
+{
+	return match->svr == (svr & match->mask);
+}
+
 static const struct fsl_soc_die_attr *fsl_soc_die_match(
 	u32 svr, const struct fsl_soc_die_attr *matches)
 {
 	while (matches->svr) {
-		if (matches->svr == (svr & matches->mask))
+		if (fsl_soc_die_match_one(svr, matches))
 			return matches;
 		matches++;
 	}
@@ -202,7 +238,6 @@ static int __init fsl_guts_init(void)
 	const struct of_device_id *match;
 	struct device_node *np;
 	u64 soc_uid = 0;
-	u32 svr;
 	int ret;
 
 	np = of_find_matching_node_and_match(NULL, fsl_guts_of_match, &match);
@@ -217,7 +252,7 @@ static int __init fsl_guts_init(void)
 	}
 
 	soc.little_endian = of_property_read_bool(np, "little-endian");
-	svr = fsl_guts_read(&soc.dcfg_ccsr->svr);
+	soc.svr = fsl_guts_read(&soc.dcfg_ccsr->svr);
 	of_node_put(np);
 
 	/* Register soc device */
@@ -229,7 +264,7 @@ static int __init fsl_guts_init(void)
 	if (ret)
 		of_machine_read_compatible(&soc_dev_attr->machine, 0);
 
-	soc_die = fsl_soc_die_match(svr, fsl_soc_die);
+	soc_die = fsl_soc_die_match(soc.svr, fsl_soc_die);
 	if (soc_die) {
 		soc_dev_attr->family = kasprintf(GFP_KERNEL, "QorIQ %s",
 						 soc_die->die);
@@ -239,12 +274,12 @@ static int __init fsl_guts_init(void)
 	if (!soc_dev_attr->family)
 		goto err_nomem;
 
-	soc_dev_attr->soc_id = kasprintf(GFP_KERNEL, "svr:0x%08x", svr);
+	soc_dev_attr->soc_id = kasprintf(GFP_KERNEL, "svr:0x%08x", soc.svr);
 	if (!soc_dev_attr->soc_id)
 		goto err_nomem;
 
 	soc_dev_attr->revision = kasprintf(GFP_KERNEL, "%d.%d",
-					   (svr >>  4) & 0xf, svr & 0xf);
+					   (soc.svr >>  4) & 0xf, soc.svr & 0xf);
 	if (!soc_dev_attr->revision)
 		goto err_nomem;
 
-- 
2.34.1


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v2 phy-next 5/8] soc: fsl: guts: make fsl_soc_data available after fsl_guts_init()

[Vladimir Oltean]

In a future change, struct fsl_soc_data will be extended with methods
for performing RCW override.

Since this will be performed from a calling context outside
fsl_guts_init(), we need to keep track of the soc_data that we determine
at fsl_guts_init() time, so we can reference it later.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
v1->v2: none
---
 drivers/soc/fsl/guts.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
index 1494b545bbb4..9f2aff07a274 100644
--- a/drivers/soc/fsl/guts.c
+++ b/drivers/soc/fsl/guts.c
@@ -138,6 +138,7 @@ static const struct fsl_soc_die_attr fsl_soc_die[] = {
 
 static struct fsl_soc_guts {
 	struct ccsr_guts __iomem *dcfg_ccsr;
+	const struct fsl_soc_data *data;
 	bool little_endian;
 	u32 svr;
 } soc;
@@ -234,7 +235,6 @@ static int __init fsl_guts_init(void)
 	struct soc_device_attribute *soc_dev_attr;
 	static struct soc_device *soc_dev;
 	const struct fsl_soc_die_attr *soc_die;
-	const struct fsl_soc_data *soc_data;
 	const struct of_device_id *match;
 	struct device_node *np;
 	u64 soc_uid = 0;
@@ -243,7 +243,7 @@ static int __init fsl_guts_init(void)
 	np = of_find_matching_node_and_match(NULL, fsl_guts_of_match, &match);
 	if (!np)
 		return 0;
-	soc_data = match->data;
+	soc.data = match->data;
 
 	soc.dcfg_ccsr = of_iomap(np, DCFG_CCSR);
 	if (!soc.dcfg_ccsr) {
@@ -283,9 +283,9 @@ static int __init fsl_guts_init(void)
 	if (!soc_dev_attr->revision)
 		goto err_nomem;
 
-	if (soc_data)
-		soc_uid = fsl_guts_get_soc_uid(soc_data->sfp_compat,
-					       soc_data->uid_offset);
+	if (soc.data)
+		soc_uid = fsl_guts_get_soc_uid(soc.data->sfp_compat,
+					       soc.data->uid_offset);
 	if (soc_uid)
 		soc_dev_attr->serial_number = kasprintf(GFP_KERNEL, "%016llX",
 							soc_uid);
-- 
2.34.1


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v2 phy-next 6/8] dt-bindings: fsl: layerscape-dcfg: define DCFG_DCSR region

[Vladimir Oltean]

In Layerscape (Arm) and QorIQ (PowerPC) devices, hardware peripherals
are accessed by the CPU through a portion of the SoC address space
called CCSR ("Configuration, Control, and Status Registers"). All
hardware IP blocks have their registers mapped here, and the Device
Configuration block makes no exception.

However, there exists a secondary range of the address space named DCSR
("Debug Control and Status Registers") which, like CCSR, also holds
registers of hardware IP blocks, except the DCSR contents is hidden in
all public reference manuals.

The intention of the CCSR/DCSR split, to the best of my knowledge, was
to place the functionality that is too low level for normal use, and
which is necessary only for debug, in a completely separate address
space which can be hidden.

A use case has appeared where networking SerDes lanes need to be
reconfigured at runtime for a different protocol (example: 10GBase-R to
SGMII), and the architecture of the SoCs does not normally permit that.
The Reset Configuration Word (RCW) is a data structure read by the SoC
preboot loader (PBL) which contains stuff like pinmuxing and SerDes
protocol mapping for each lane.

The RCW that the PBL has loaded is visible in the DCFG block's normal
status registers (from CCSR), as read only. Turns out, the RCW is also
mapped in the DCFG's shadow register map (in DCSR), in a write-only
form. Writing to the RCW registers from the DCFG's DCSR space to change
what the PBL has loaded is called "RCW override".

It has been validated that the RCW override procedure is necessary to
reconfigure the networking data path when a SerDes lane performs a major
protocol change. It changes some internal muxes which connect the PCS to
either the 10G MAC or to the 1G MAC.

Defining the DCSR area of the DCFG as a secondary 'reg' array element
allows operating systems to perform RCW overrides. Since it is
introduced late in the binding's lifetime, it is optional. It can be
identified by name, but also by index (first 'reg' is CCSR).

Note that while all SoCs should have a DCFG register block in DCSR, we
only need to expose it for the SoCs where the RCW override procedure is
known to be needed and has been validated.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
---
Cc: Conor Dooley <conor+dt@kernel.org>
Cc: Krzysztof Kozlowski <krzk+dt@kernel.org>
Cc: Rob Herring <robh@kernel.org>

v1->v2:
- add Conor's review tag
- update email addresses of DT maintainers
---
 .../bindings/soc/fsl/fsl,layerscape-dcfg.yaml     | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml
index 3fb0534ea597..fc14fd0bf84b 100644
--- a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml
+++ b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml
@@ -36,7 +36,20 @@ properties:
           - const: simple-mfd
 
   reg:
-    maxItems: 1
+    minItems: 1
+    items:
+      - description:
+          Customer-visible DCFG register map from CCSR address space
+          (Configuration, Control and Status Registers)
+      - description:
+          Customer-hidden DCFG register map from DCSR address space
+          (Debug Control and Status Registers)
+
+  reg-names:
+    minItems: 1
+    items:
+      - const: dcfg_ccsr
+      - const: dcfg_dcsr
 
   little-endian: true
   big-endian: true
-- 
2.34.1


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v2 phy-next 7/8] soc: fsl: guts: implement the RCW override procedure

[Vladimir Oltean]

From: Ioana Ciornei <ioana.ciornei@nxp.com>

Add support for the RCW override procedure which enables runtime
reconfiguration of the protocol running on a SerDes lane. The procedure
is done through the DCFG DCSR space which now can be defined as the
second memory region of the guts DT node.
Support is added on the following SoCs: LS1046A, LS1088A, LS2088A.

The procedure is exported to the "client" driver - the Lynx10G SerDes
PHY driver - through the following functions:
- fsl_guts_lane_init() used to notify the initial / boot time lane mode
  running on a SerDes lane.
- fsl_guts_lane_validate() used to validate that changing the protocol
  on a specific lane is supported.
- fsl_guts_lane_set_mode() which can be used to request the RCW
  procedure be executed for a specific lane.

Since the RCW override procedure is different depending on the SoC, the
private fsl_soc_data structure is updated with two new per SoC callbacks
(.serdes_get_rcw_override() and .serdes_init_rcwcr()) which get used
from the generic fsl_guts_lane_set_mode() function. These two callbacks
hide all the SoC specific register offsets, masks and values so that the
_set_mode() procedure is straightforward.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
v1->v2:
- drop DT maintainers from explicit CC
- keep devicetree@vger.kernel.org CCed on entire series
- include missing <linux/bitfield.h>
- namespace SRDS_PRTCL values for LS1046A and LS1088A, even if they are
  the same. For LS1028A (not covered here) they are not.
- prefix SRDS_CLK_SEL_{GMII,XGMII} with LS2088A_
- reorder alphanumerically (LS1046A should come before LS1088A)
---
 drivers/soc/fsl/guts.c   | 285 ++++++++++++++++++++++++++++++++++++++-
 include/linux/fsl/guts.h |  20 ++-
 2 files changed, 298 insertions(+), 7 deletions(-)

diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
index 9f2aff07a274..0fa2bd99d3c1 100644
--- a/drivers/soc/fsl/guts.c
+++ b/drivers/soc/fsl/guts.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2016 Freescale Semiconductor, Inc.
  */
 
+#include <linux/bitfield.h>
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -15,6 +16,28 @@
 #include <linux/fsl/guts.h>
 
 #define DCFG_CCSR	0
+#define DCFG_DCSR	1
+
+#define MAX_NUM_LANES	8
+#define MAX_NUM_SERDES	2
+
+#define LS1046A_RCWSR5_SRDS_PRTCL_S1(lane)	\
+	GENMASK(19 + 4 * (lane), 16 + 4 * (lane))
+#define LS1046A_SRDS_PRTCL_XFI				1
+#define LS1046A_SRDS_PRTCL_100BASEX_SGMII		3
+
+#define LS1088A_RCWSR29_SRDS_PRTCL_S1_LNn(lane)	\
+	GENMASK(19 + 4 * (3 - lane), 16 + 4 * (3 - lane))
+#define LS1088A_RCWSR30_SRDS_PRTCL_S2_LNn(lane)	\
+	GENMASK(3 + 4 * (3 - lane), 4 * (3 - lane))
+#define LS1088A_SRDS_PRTCL_XFI				1
+#define LS1088A_SRDS_PRTCL_100BASEX_SGMII		3
+
+#define LS2088A_RCWSR30_SRDS_CLK_EN_SEL_XGMII_S1	BIT(14)
+#define LS2088A_RCWSR30_SRDS_CLK_SEL_XGMII_Ln_S1(lane)	BIT(6 + (7 - (lane)))
+#define LS2088A_RCWSR30_SRDS_CLK_SEL_MSK		GENMASK(13, 6)
+#define LS2088A_SRDS_CLK_SEL_XGMII			1
+#define LS2088A_SRDS_CLK_SEL_GMII			0
 
 struct fsl_soc_die_attr {
 	char	*die;
@@ -22,9 +45,19 @@ struct fsl_soc_die_attr {
 	u32	mask;
 };
 
+struct fsl_soc_serdes_rcw_override {
+	int offset;
+	int mask;
+	int val;
+};
+
 struct fsl_soc_data {
 	const char *sfp_compat;
 	u32 uid_offset;
+	int (*serdes_get_rcw_override)(int index, int lane,
+				       enum lynx_lane_mode lane_mode,
+				       struct fsl_soc_serdes_rcw_override *override);
+	void (*serdes_init_rcwcr)(int index);
 };
 
 enum qoriq_die {
@@ -138,9 +171,13 @@ static const struct fsl_soc_die_attr fsl_soc_die[] = {
 
 static struct fsl_soc_guts {
 	struct ccsr_guts __iomem *dcfg_ccsr;
+	struct ccsr_guts __iomem *dcfg_dcsr;
 	const struct fsl_soc_data *data;
 	bool little_endian;
 	u32 svr;
+	enum lynx_lane_mode lane_mode[MAX_NUM_SERDES][MAX_NUM_LANES];
+	bool rcwcr_init_done;
+	spinlock_t rcwcr_lock; /* serializes concurrent writes to the RCWCR */
 } soc;
 
 static unsigned int fsl_guts_read(const void __iomem *reg)
@@ -151,6 +188,28 @@ static unsigned int fsl_guts_read(const void __iomem *reg)
 	return ioread32be(reg);
 }
 
+static void fsl_guts_write(void __iomem *reg, u32 val)
+{
+	if (soc.little_endian)
+		iowrite32(val, reg);
+	else
+		iowrite32be(val, reg);
+}
+
+/* Some fields of the Reset Configuration Word (RCW) can be overridden at
+ * runtime by writing to the RCWCRn registers contained within the DCSR space
+ * of the Device Configuration (DCFG) block. The layout of the RCWCRn registers
+ * is identical with the read-only RCWSRn from the CCSR space.
+ */
+static void fsl_guts_rmw(int offset, u32 val, u32 mask)
+{
+	u32 tmp = fsl_guts_read(&soc.dcfg_ccsr->rcwsr[offset]);
+
+	tmp &= ~mask;
+	tmp |= val;
+	fsl_guts_write(&soc.dcfg_dcsr->rcwcr[offset], tmp);
+}
+
 static bool fsl_soc_die_match_one(u32 svr, const struct fsl_soc_die_attr *match)
 {
 	return match->svr == (svr & match->mask);
@@ -167,6 +226,97 @@ static const struct fsl_soc_die_attr *fsl_soc_die_match(
 	return NULL;
 }
 
+static int
+fsl_guts_serdes_get_rcw_override(int serdes_idx, int lane,
+				 enum lynx_lane_mode lane_mode,
+				 struct fsl_soc_serdes_rcw_override *override)
+{
+	if ((!fsl_soc_die_match_one(soc.svr, &fsl_soc_die[DIE_LS1088A]) &&
+	     !fsl_soc_die_match_one(soc.svr, &fsl_soc_die[DIE_LS2088A]) &&
+	     !fsl_soc_die_match_one(soc.svr, &fsl_soc_die[DIE_LS1046A])) ||
+	    !soc.data || !soc.data->serdes_get_rcw_override) {
+		pr_debug("RCW override not implemented for SoC\n");
+		return -EINVAL;
+	}
+
+	if (!soc.dcfg_dcsr) {
+		pr_debug("Device tree does not define DCFG_DCSR region necessary for RCW override\n");
+		return -EINVAL;
+	}
+
+	return soc.data->serdes_get_rcw_override(serdes_idx, lane, lane_mode,
+						 override);
+}
+
+/**
+ * fsl_guts_lane_init() - Notify guts module of SerDes lane configuration
+ * @serdes_idx: zero-based SerDes block index
+ * @lane: zero-based lane index within SerDes
+ * @lane_mode: initial / boot time SerDes protocol for lane
+ *
+ * On the LS208xA SoC, the RCW override procedure needs to be aware of all link
+ * modes which are configured on a SerDes block.
+ */
+void fsl_guts_lane_init(int serdes_idx, int lane, enum lynx_lane_mode lane_mode)
+{
+	soc.lane_mode[serdes_idx - 1][lane] = lane_mode;
+}
+EXPORT_SYMBOL_NS_GPL(fsl_guts_lane_init, "FSL_GUTS");
+
+/**
+ * fsl_guts_lane_validate() - Validate that SerDes protocol is implemented and
+ *	supported on current SoC
+ * @serdes_idx: zero-based SerDes block index
+ * @lane: zero-based lane index within SerDes
+ * @lane_mode: requested SerDes protocol
+ *
+ * Should be called before actually requesting the RCW override procedure to be
+ * applied using %fsl_guts_lane_set_mode()
+ *
+ * Return: 0 if RCW override to protocol is possible, negative error otherwise
+ */
+int fsl_guts_lane_validate(int serdes_idx, int lane, enum lynx_lane_mode lane_mode)
+{
+	struct fsl_soc_serdes_rcw_override override;
+
+	return fsl_guts_serdes_get_rcw_override(serdes_idx, lane, lane_mode,
+						&override);
+}
+EXPORT_SYMBOL_NS_GPL(fsl_guts_lane_validate, "FSL_GUTS");
+
+/**
+ * fsl_guts_lane_set_mode() - apply RCW override procedure for SerDes lane
+ * @serdes_idx: zero-based SerDes block index
+ * @lane: zero-based lane index within SerDes
+ * @lane_mode: requested SerDes protocol
+ *
+ * Return: 0 on success, negative error otherwise
+ */
+int fsl_guts_lane_set_mode(int serdes_idx, int lane, enum lynx_lane_mode lane_mode)
+{
+	struct fsl_soc_serdes_rcw_override override;
+	int err;
+
+	err = fsl_guts_serdes_get_rcw_override(serdes_idx, lane, lane_mode,
+					       &override);
+	if (err)
+		return err;
+
+	spin_lock(&soc.rcwcr_lock);
+
+	if (soc.data->serdes_init_rcwcr)
+		soc.data->serdes_init_rcwcr(serdes_idx);
+
+	fsl_guts_rmw(override.offset, override.val << __bf_shf(override.mask),
+		     override.mask);
+	soc.lane_mode[serdes_idx - 1][lane] = lane_mode;
+
+	spin_unlock(&soc.rcwcr_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(fsl_guts_lane_set_mode, "FSL_GUTS");
+
 static u64 fsl_guts_get_soc_uid(const char *compat, unsigned int offset)
 {
 	struct device_node *np;
@@ -193,6 +343,128 @@ static u64 fsl_guts_get_soc_uid(const char *compat, unsigned int offset)
 	return uid;
 }
 
+static int ls1046a_serdes_get_rcw_override(int index, int lane,
+					   enum lynx_lane_mode lane_mode,
+					   struct fsl_soc_serdes_rcw_override *override)
+{
+	/* The RCW override procedure has to write to different registers
+	 * depending on the SerDes block index.
+	 */
+	switch (index) {
+	case 1:
+		override->offset = 4;
+		override->mask = LS1046A_RCWSR5_SRDS_PRTCL_S1(lane);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (lynx_lane_mode_uses_xgmii_mac(lane_mode))
+		override->val = LS1046A_SRDS_PRTCL_XFI;
+	else if (lynx_lane_mode_uses_gmii_mac(lane_mode))
+		override->val = LS1046A_SRDS_PRTCL_100BASEX_SGMII;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ls1088a_serdes_get_rcw_override(int index, int lane,
+					   enum lynx_lane_mode lane_mode,
+					   struct fsl_soc_serdes_rcw_override *override)
+{
+	/* The RCW override procedure has to write to different registers
+	 * depending on the SerDes block index.
+	 */
+	switch (index) {
+	case 1:
+		override->offset = 28;
+		override->mask = LS1088A_RCWSR29_SRDS_PRTCL_S1_LNn(lane);
+		break;
+	case 2:
+		override->offset = 29;
+		override->mask = LS1088A_RCWSR30_SRDS_PRTCL_S2_LNn(lane);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (lynx_lane_mode_uses_xgmii_mac(lane_mode))
+		override->val = LS1088A_SRDS_PRTCL_XFI;
+	else if (lynx_lane_mode_uses_gmii_mac(lane_mode))
+		override->val = LS1088A_SRDS_PRTCL_100BASEX_SGMII;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ls2088a_serdes_get_rcw_override(int index, int lane,
+					   enum lynx_lane_mode lane_mode,
+					   struct fsl_soc_serdes_rcw_override *override)
+{
+	switch (index) {
+	case 1:
+		override->offset = 29;
+		override->mask = LS2088A_RCWSR30_SRDS_CLK_SEL_XGMII_Ln_S1(lane);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (lynx_lane_mode_uses_xgmii_mac(lane_mode))
+		override->val = LS2088A_SRDS_CLK_SEL_XGMII;
+	else if (lynx_lane_mode_uses_gmii_mac(lane_mode))
+		override->val = LS2088A_SRDS_CLK_SEL_GMII;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static void ls2088a_serdes_init_rcwcr(int serdes_idx)
+{
+	u32 reg;
+	int i;
+
+	if (serdes_idx != 1)
+		return;
+	if (soc.rcwcr_init_done)
+		return;
+
+	/* SRDS_CLK_EN_SEL_XGMII_S1: SerDes Clock Enable Select XGMII Serdes 1:
+	 * Enables to select GMII/XGMII clock according to
+	 * SRDS_CLK_SEL_XGMII_Ln_S1
+	 */
+	reg = LS2088A_RCWSR30_SRDS_CLK_EN_SEL_XGMII_S1;
+
+	/* We need to configure the initial state of all lanes for
+	 * the SerDes block #1
+	 */
+	for (i = 0; i < MAX_NUM_LANES; i++)
+		if (lynx_lane_mode_uses_xgmii_mac(soc.lane_mode[serdes_idx - 1][i]))
+			reg |= LS2088A_RCWSR30_SRDS_CLK_SEL_XGMII_Ln_S1(i);
+
+	fsl_guts_rmw(29, reg,
+		     LS2088A_RCWSR30_SRDS_CLK_EN_SEL_XGMII_S1 |
+		     LS2088A_RCWSR30_SRDS_CLK_SEL_MSK);
+
+	soc.rcwcr_init_done = true;
+}
+
+static const struct fsl_soc_data ls1088a_data = {
+	.serdes_get_rcw_override = ls1088a_serdes_get_rcw_override,
+};
+
+static const struct fsl_soc_data ls1046a_data = {
+	.serdes_get_rcw_override = ls1046a_serdes_get_rcw_override,
+};
+
+static const struct fsl_soc_data ls2088a_data = {
+	.serdes_get_rcw_override = ls2088a_serdes_get_rcw_override,
+	.serdes_init_rcwcr = ls2088a_serdes_init_rcwcr,
+};
+
 static const struct fsl_soc_data ls1028a_data = {
 	.sfp_compat = "fsl,ls1028a-sfp",
 	.uid_offset = 0x21c,
@@ -221,10 +493,10 @@ static const struct of_device_id fsl_guts_of_match[] = {
 	{ .compatible = "fsl,mpc8572-guts", },
 	{ .compatible = "fsl,ls1021a-dcfg", },
 	{ .compatible = "fsl,ls1043a-dcfg", },
-	{ .compatible = "fsl,ls2080a-dcfg", },
-	{ .compatible = "fsl,ls1088a-dcfg", },
+	{ .compatible = "fsl,ls2080a-dcfg", .data = &ls2088a_data},
+	{ .compatible = "fsl,ls1088a-dcfg", .data = &ls1088a_data},
 	{ .compatible = "fsl,ls1012a-dcfg", },
-	{ .compatible = "fsl,ls1046a-dcfg", },
+	{ .compatible = "fsl,ls1046a-dcfg", .data = &ls1046a_data},
 	{ .compatible = "fsl,lx2160a-dcfg", },
 	{ .compatible = "fsl,ls1028a-dcfg", .data = &ls1028a_data},
 	{}
@@ -250,6 +522,8 @@ static int __init fsl_guts_init(void)
 		of_node_put(np);
 		return -ENOMEM;
 	}
+	/* DCFG_DCSR is optional */
+	soc.dcfg_dcsr = of_iomap(np, DCFG_DCSR);
 
 	soc.little_endian = of_property_read_bool(np, "little-endian");
 	soc.svr = fsl_guts_read(&soc.dcfg_ccsr->svr);
@@ -296,6 +570,8 @@ static int __init fsl_guts_init(void)
 		goto err;
 	}
 
+	spin_lock_init(&soc.rcwcr_lock);
+
 	pr_info("Machine: %s\n", soc_dev_attr->machine);
 	pr_info("SoC family: %s\n", soc_dev_attr->family);
 	pr_info("SoC ID: %s, Revision: %s\n",
@@ -305,7 +581,8 @@ static int __init fsl_guts_init(void)
 
 err_nomem:
 	ret = -ENOMEM;
-
+	if (soc.dcfg_dcsr)
+		iounmap(soc.dcfg_dcsr);
 	iounmap(soc.dcfg_ccsr);
 err:
 	kfree(soc_dev_attr->family);
diff --git a/include/linux/fsl/guts.h b/include/linux/fsl/guts.h
index fdb55ca47a4f..176842531241 100644
--- a/include/linux/fsl/guts.h
+++ b/include/linux/fsl/guts.h
@@ -13,6 +13,7 @@
 
 #include <linux/types.h>
 #include <linux/io.h>
+#include <soc/fsl/phy-fsl-lynx.h>
 
 /*
  * Global Utility Registers.
@@ -91,9 +92,15 @@ struct ccsr_guts {
 	u32	iovselsr;	/* 0x.00c0 - I/O voltage select status register
 					     Called 'elbcvselcr' on 86xx SOCs */
 	u8	res0c4[0x100 - 0xc4];
-	u32	rcwsr[16];	/* 0x.0100 - Reset Control Word Status registers
-					     There are 16 registers */
-	u8	res140[0x224 - 0x140];
+	/* 0x.0100 - read-only Reset Configuration Word Status registers in
+	 * CCSR, or write-only Reset Configuration Word Control registers in
+	 * DCSR. In both cases there are 32 registers.
+	 */
+	union {
+		u32	rcwsr[32];
+		u32	rcwcr[32];
+	};
+	u8	res180[0x224 - 0x180];
 	u32	iodelay1;	/* 0x.0224 - IO delay control register 1 */
 	u32	iodelay2;	/* 0x.0228 - IO delay control register 2 */
 	u8	res22c[0x604 - 0x22c];
@@ -131,6 +138,13 @@ struct ccsr_guts {
 	u32	srds2cr1;	/* 0x.0f44 - SerDes2 Control Register 0 */
 } __attribute__ ((packed));
 
+void fsl_guts_lane_init(int serdes_idx, int lane,
+			enum lynx_lane_mode lane_mode);
+int fsl_guts_lane_validate(int serdes_idx, int lane,
+			   enum lynx_lane_mode lane_mode);
+int fsl_guts_lane_set_mode(int serdes_idx, int lane,
+			   enum lynx_lane_mode lane_mode);
+
 /* Alternate function signal multiplex control */
 #define MPC85xx_PMUXCR_QE(x) (0x8000 >> (x))
 
-- 
2.34.1


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v2 phy-next 8/8] phy: lynx-10g: use RCW override procedure for dynamic protocol change

[Vladimir Oltean]

Up until this patch, the only protocol change supported was between
1000Base-X/SGMII and 2500Base-X. The others require an RCW override
procedure which was lacking.

Since now the guts driver provides the means of applying this procedure,
make use of it and remove any comment which mentioned the limitation.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
v1->v2: none
---
 drivers/phy/freescale/Kconfig            |  1 +
 drivers/phy/freescale/phy-fsl-lynx-10g.c | 24 +++++++++++++++---------
 2 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/phy/freescale/Kconfig b/drivers/phy/freescale/Kconfig
index 5bf3864fbe64..d4e189fffbf8 100644
--- a/drivers/phy/freescale/Kconfig
+++ b/drivers/phy/freescale/Kconfig
@@ -58,6 +58,7 @@ config PHY_FSL_LYNX_10G
 	tristate "Freescale Layerscape Lynx 10G SerDes PHY support"
 	depends on OF
 	depends on ARCH_LAYERSCAPE || COMPILE_TEST
+	select FSL_GUTS
 	select GENERIC_PHY
 	select PHY_FSL_LYNX_CORE
 	help
diff --git a/drivers/phy/freescale/phy-fsl-lynx-10g.c b/drivers/phy/freescale/phy-fsl-lynx-10g.c
index 38def160ef1a..5ece7889aed7 100644
--- a/drivers/phy/freescale/phy-fsl-lynx-10g.c
+++ b/drivers/phy/freescale/phy-fsl-lynx-10g.c
@@ -8,6 +8,7 @@
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/workqueue.h>
+#include <linux/fsl/guts.h>
 
 #include "phy-fsl-lynx-core.h"
 
@@ -446,6 +447,7 @@ static void lynx_10g_lane_read_configuration(struct lynx_lane *lane)
 	}
 
 	lynx_10g_backup_pccr_val(lane);
+	fsl_guts_lane_init(priv->info->index, lane->id, lane->mode);
 }
 
 static int ls1028a_get_pccr(enum lynx_lane_mode lane_mode, int lane,
@@ -1167,14 +1169,7 @@ static bool lynx_10g_lane_mode_needs_rcw_override(struct lynx_lane *lane,
 
 	/* Major protocol changes, which involve changing the PCS connection to
 	 * the GMII MAC with the one to the XGMII MAC, require an RCW override
-	 * procedure to reconfigure an internal mux, as documented here:
-	 * https://lore.kernel.org/linux-phy/20230810102631.bvozjer3t67r67iy@skbuf/
-	 * This is SoC-specific, and not yet implemented in drivers/soc/fsl/guts.c.
-	 *
-	 * So the supported set of protocols depends on the initial lane mode.
-	 *
-	 * Minor protocol changes (SGMII <-> 1000Base-X <-> 2500Base-X or
-	 * 10GBase-R <-> USXGMII) are supported.
+	 * procedure to reconfigure an internal mux.
 	 */
 	if ((lynx_lane_mode_uses_gmii_mac(curr) &&
 	     lynx_lane_mode_uses_xgmii_mac(new)) ||
@@ -1189,6 +1184,7 @@ static int lynx_10g_validate(struct phy *phy, enum phy_mode mode, int submode,
 			     union phy_configure_opts *opts)
 {
 	struct lynx_lane *lane = phy_get_drvdata(phy);
+	struct lynx_priv *priv = lane->priv;
 	enum lynx_lane_mode lane_mode;
 	int err;
 
@@ -1197,7 +1193,8 @@ static int lynx_10g_validate(struct phy *phy, enum phy_mode mode, int submode,
 		return err;
 
 	if (lynx_10g_lane_mode_needs_rcw_override(lane, lane_mode))
-		return -EINVAL;
+		return fsl_guts_lane_validate(priv->info->index, lane->id,
+					      lane_mode);
 
 	return 0;
 }
@@ -1205,6 +1202,7 @@ static int lynx_10g_validate(struct phy *phy, enum phy_mode mode, int submode,
 static int lynx_10g_set_mode(struct phy *phy, enum phy_mode mode, int submode)
 {
 	struct lynx_lane *lane = phy_get_drvdata(phy);
+	struct lynx_priv *priv = lane->priv;
 	bool powered_up = lane->powered_up;
 	enum lynx_lane_mode lane_mode;
 	int err;
@@ -1225,6 +1223,13 @@ static int lynx_10g_set_mode(struct phy *phy, enum phy_mode mode, int submode)
 	if (powered_up)
 		lynx_10g_lane_halt(phy);
 
+	if (lynx_10g_lane_mode_needs_rcw_override(lane, lane_mode)) {
+		err = fsl_guts_lane_set_mode(priv->info->index, lane->id,
+					     lane_mode);
+		if (err)
+			goto out;
+	}
+
 	err = lynx_10g_lane_disable_pcvt(lane, lane->mode);
 	if (err)
 		goto out;
@@ -1314,6 +1319,7 @@ static struct platform_driver lynx_10g_driver = {
 };
 module_platform_driver(lynx_10g_driver);
 
+MODULE_IMPORT_NS("FSL_GUTS");
 MODULE_IMPORT_NS("PHY_FSL_LYNX");
 MODULE_AUTHOR("Ioana Ciornei <ioana.ciornei@nxp.com>");
 MODULE_AUTHOR("Vladimir Oltean <vladimir.oltean@nxp.com>");
-- 
2.34.1


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

Re: [PATCH v2 phy-next 2/8] soc: fsl: guts: add a global structure to hold state

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] The global `soc.dcfg_ccsr` pointer is not cleared after being unmapped on the error path, resulting in a dangling pointer.
- [Medium] The globally mapped `soc.dcfg_ccsr` is leaked on multiple error paths during initialization.
--

commit 28927a6c50db9adc7ddb8b131d5e08a366298fb3
Author: Ioana Ciornei <ioana.ciornei@nxp.com>

soc: fsl: guts: add a global structure to hold state

Add the fsl_soc_guts structure in order to pass information like base
addresses, endianness etc between the init time and the runtime
operations. There is no point in mapping and unmapping the DCFG CCSR
space every time we need to make a read, just map it once and keep its
reference in this new global structure.

> diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
> index f87ee47c15035..a0a52a5603a5f 100644
> --- a/drivers/soc/fsl/guts.c
> +++ b/drivers/soc/fsl/guts.c

[ ... ]

> @@ -199,18 +202,17 @@ static int __init fsl_guts_init(void)
>  		return 0;
>  	soc_data = match->data;
>  
> -	regs = of_iomap(np, DCFG_CCSR);
> -	if (!regs) {
> +	soc.dcfg_ccsr = of_iomap(np, DCFG_CCSR);
> +	if (!soc.dcfg_ccsr) {
>  		of_node_put(np);
>  		return -ENOMEM;
>  	}
>  
> -	little_endian = of_property_read_bool(np, "little-endian");
> -	if (little_endian)
> -		svr = ioread32(&regs->svr);
> +	soc.little_endian = of_property_read_bool(np, "little-endian");
> +	if (soc.little_endian)
> +		svr = ioread32(&soc.dcfg_ccsr->svr);
>  	else
> -		svr = ioread32be(&regs->svr);
> -	iounmap(regs);
> +		svr = ioread32be(&soc.dcfg_ccsr->svr);
>  	of_node_put(np);
>  
>  	/* Register soc device */

[Severity: Medium]
Since the iounmap() was removed here to keep soc.dcfg_ccsr mapped, what
happens if the subsequent soc_dev_attr allocation fails?

fsl_guts_init()
	/* Register soc device */
	soc_dev_attr = kzalloc_obj(*soc_dev_attr);
	if (!soc_dev_attr)
		return -ENOMEM;

Does this direct return leak the soc.dcfg_ccsr mapping?

Also, if soc_device_register() fails later in this function, the code does a
goto err:

	soc_dev = soc_device_register(soc_dev_attr);
	if (IS_ERR(soc_dev)) {
		ret = PTR_ERR(soc_dev);
		goto err;
	}

Because this bypasses the err_nomem label, does it also leak the
soc.dcfg_ccsr mapping?

> @@ -263,6 +265,8 @@ static int __init fsl_guts_init(void)
>  
>  err_nomem:
>  	ret = -ENOMEM;
> +
> +	iounmap(soc.dcfg_ccsr);

[Severity: High]
Since soc is a static global structure, does calling iounmap() here leave
soc.dcfg_ccsr with a dangling, non-NULL pointer?

If a client driver later attempts to use the API and checks this pointer
after an initialization failure, could it lead to a kernel oops?

>  err:
>  	kfree(soc_dev_attr->family);
>  	kfree(soc_dev_attr->soc_id);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260612210859.266759-1-vladimir.oltean@nxp.com?part=2

-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

Re: [PATCH v2 phy-next 5/8] soc: fsl: guts: make fsl_soc_data available after fsl_guts_init()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] The iomem mappings `soc.dcfg_ccsr` and `soc.dcfg_dcsr` are leaked on multiple error paths during initialization.
- [High] The global `soc.data`, `soc.dcfg_ccsr` and `soc.dcfg_dcsr` pointers are not cleared on error paths, leading to dangling pointers, Use-After-Free, and uninitialized spinlock access.
--

commit 9f45015d702d2f4ca41d93015c23b3d9950743a7
Author: Vladimir Oltean <vladimir.oltean@nxp.com>

soc: fsl: guts: make fsl_soc_data available after fsl_guts_init()

In a future change, struct fsl_soc_data will be extended with methods
for performing RCW override.

Since this will be performed from a calling context outside
fsl_guts_init(), we need to keep track of the soc_data that we determine
at fsl_guts_init() time, so we can reference it later.

> diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
> index 1494b545bbb47..9f2aff07a2744 100644
> --- a/drivers/soc/fsl/guts.c
> +++ b/drivers/soc/fsl/guts.c
> @@ -243,7 +243,7 @@ static int __init fsl_guts_init(void)
>  	np = of_find_matching_node_and_match(NULL, fsl_guts_of_match, &match);
>  	if (!np)
>  		return 0;
> -	soc_data = match->data;
> +	soc.data = match->data;
>  
>  	soc.dcfg_ccsr = of_iomap(np, DCFG_CCSR);
>  	if (!soc.dcfg_ccsr) {

[Severity: High]
Does this code leak the soc.dcfg_ccsr and soc.dcfg_dcsr mappings on error paths?

Looking at fsl_guts_init(), if the soc_dev_attr allocation fails, the function
returns directly, leaking the mappings:

fsl_guts_init() {
    ...
	soc_dev_attr = kzalloc_obj(*soc_dev_attr);
	if (!soc_dev_attr)
		return -ENOMEM;
    ...
}

If soc_device_register() fails, the code jumps to the err label, which bypasses
the err_nomem block where iounmap() is called, also leaking the mappings:

fsl_guts_init() {
    ...
	soc_dev = soc_device_register(soc_dev_attr);
	if (IS_ERR(soc_dev)) {
		ret = PTR_ERR(soc_dev);
		goto err;
	}
    ...
err_nomem:
	ret = -ENOMEM;

	iounmap(soc.dcfg_ccsr);
err:
    ...
}

Could the error paths be updated to ensure iounmap() is called when these
failures occur?

[Severity: High]
Are the global soc.data, soc.dcfg_ccsr, and soc.dcfg_dcsr pointers cleared on
error paths?

In fsl_guts_init(), global state is set early:

fsl_guts_init() {
    ...
	soc.data = match->data;

	soc.dcfg_ccsr = of_iomap(np, DCFG_CCSR);
    ...
}

If an error occurs later, the memory is unmapped but the global pointers are
not cleared to NULL:

fsl_guts_init() {
    ...
err_nomem:
	ret = -ENOMEM;
	if (soc.dcfg_dcsr)
		iounmap(soc.dcfg_dcsr);
	iounmap(soc.dcfg_ccsr);
    ...
}

External callers checking if the driver is initialized via if (!soc.data) or
if (!soc.dcfg_dcsr) could bypass the checks and access the unmapped IO memory
or an uninitialized spinlock:

fsl_guts_lane_set_mode() {
    ...
	spin_lock(&soc.rcwcr_lock);

	if (soc.data->serdes_init_rcwcr)
		soc.data->serdes_init_rcwcr(serdes_idx);

	fsl_guts_rmw(override.offset, override.val << __bf_shf(override.mask),
		     override.mask);
    ...
}

Could the error paths be updated to set these pointers to NULL?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260612210859.266759-1-vladimir.oltean@nxp.com?part=5

-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

Re: [PATCH v2 phy-next 7/8] soc: fsl: guts: implement the RCW override procedure

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:
- [High] Failure to clear global pointers on error paths allows exported APIs to operate on dangling I/O pointers.
- [High] The Read-Modify-Write logic relies on a read-only boot status register, causing runtime overrides on other lanes to be silently discarded.
- [Medium] Direct returns and bypassed error labels in `fsl_guts_init` leak I/O memory mappings.
- [Medium] Exported APIs contradict their own zero-based indexing documentation and lack parameter bounds checking.
--

commit 2b919af199a087611275f238825912a50ae47330
Author: Ioana Ciornei <ioana.ciornei@nxp.com>
Date:   Fri Jun 12 21:08:58 2026 +0000

    soc: fsl: guts: implement the RCW override procedure
    
    Add support for the RCW override procedure which enables runtime
    reconfiguration of the protocol running on a SerDes lane. The procedure
    is done through the DCFG DCSR space which now can be defined as the
    second memory region of the guts DT node.

> diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
> index 9f2aff07a2744..0fa2bd99d3c10 100644
> --- a/drivers/soc/fsl/guts.c
> +++ b/drivers/soc/fsl/guts.c

[ ... ]

> +/* Some fields of the Reset Configuration Word (RCW) can be overridden at
> + * runtime by writing to the RCWCRn registers contained within the DCSR space
> + * of the Device Configuration (DCFG) block. The layout of the RCWCRn registers
> + * is identical with the read-only RCWSRn from the CCSR space.
> + */
> +static void fsl_guts_rmw(int offset, u32 val, u32 mask)
> +{
> +	u32 tmp = fsl_guts_read(&soc.dcfg_ccsr->rcwsr[offset]);
> +
> +	tmp &= ~mask;
> +	tmp |= val;
> +	fsl_guts_write(&soc.dcfg_dcsr->rcwcr[offset], tmp);
> +}

[Severity: High]
Does this read-modify-write logic accidentally discard previous runtime
overrides?

Since rcwsr is a read-only boot status register, it reflects the static boot
state. If multiple lanes share the same register, reading from rcwsr to update
a subsequent lane will overwrite any dynamic configurations previously written
to the write-only rcwcr register. 

Would it be safer to use a software shadow register to track the runtime state
of rcwcr?

[ ... ]

> +/**
> + * fsl_guts_lane_init() - Notify guts module of SerDes lane configuration
> + * @serdes_idx: zero-based SerDes block index
> + * @lane: zero-based lane index within SerDes
> + *
> + * On the LS208xA SoC, the RCW override procedure needs to be aware of all link
> + * modes which are configured on a SerDes block.
> + */
> +void fsl_guts_lane_init(int serdes_idx, int lane, enum lynx_lane_mode lane_mode)
> +{
> +	soc.lane_mode[serdes_idx - 1][lane] = lane_mode;
> +}
> +EXPORT_SYMBOL_NS_GPL(fsl_guts_lane_init, "FSL_GUTS");

[Severity: Medium]
Is the documentation out of sync with the implementation?

The docstring specifies that serdes_idx is a zero-based index, but the code
subtracts 1. If a caller follows the documentation and passes 0, won't this
result in an out-of-bounds array access?

Additionally, is there a risk of out-of-bounds access if the lane parameter
exceeds MAX_NUM_LANES? An unvalidated lane value could also cause undefined
behavior later when expanded by the GENMASK macros in the override lookup
functions.

[ ... ]

> @@ -250,6 +522,8 @@ static int __init fsl_guts_init(void)
>  		of_node_put(np);
>  		return -ENOMEM;
>  	}
> +	/* DCFG_DCSR is optional */
> +	soc.dcfg_dcsr = of_iomap(np, DCFG_DCSR);
>  
>  	soc.little_endian = of_property_read_bool(np, "little-endian");
>  	soc.svr = fsl_guts_read(&soc.dcfg_ccsr->svr);
> @@ -274,7 +548,7 @@ static int __init fsl_guts_init(void)
>  	/* Register soc device */
>  	soc_dev_attr = kzalloc_obj(*soc_dev_attr);
>  	if (!soc_dev_attr)
>  		return -ENOMEM;

[Severity: Medium]
Will this direct return leak the I/O memory mapped earlier?

If kzalloc_obj() fails, the function returns immediately without unmapping
soc.dcfg_ccsr or the newly added soc.dcfg_dcsr.

[ ... ]

> @@ -296,6 +570,8 @@ static int __init fsl_guts_init(void)
>  		goto err;
>  	}

[Severity: Medium]
Does jumping to the err label skip the necessary unmapping?

If soc_device_register() fails, the code uses goto err. Because err is
placed after err_nomem, the iounmap() calls are bypassed, leaving the memory
mappings leaked.

[ ... ]

>  err_nomem:
>  	ret = -ENOMEM;
> -
> +	if (soc.dcfg_dcsr)
> +		iounmap(soc.dcfg_dcsr);
>  	iounmap(soc.dcfg_ccsr);
>  err:
>  	kfree(soc_dev_attr->family);

[Severity: High]
Should the global pointers be set to NULL after unmapping?

If fsl_guts_init() fails, it unmaps soc.dcfg_ccsr and soc.dcfg_dcsr but
leaves the global pointers dangling. Since this is a core_initcall, the boot
process will continue even if initialization fails.

If an exported API like fsl_guts_lane_set_mode() is called later, it checks
the pointer validity:

	if (!soc.dcfg_dcsr) {
		pr_debug("Device tree does not define DCFG_DCSR...");
		return -EINVAL;
	}

Since the pointer isn't NULL, this validation passes, which could lead to a
use-after-free when the driver attempts to write to the unmapped memory or
acquires the uninitialized spinlock.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260612210859.266759-1-vladimir.oltean@nxp.com?part=7

-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

Re: [PATCH v2 phy-next 8/8] phy: lynx-10g: use RCW override procedure for dynamic protocol change

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] Read-modify-write in `fsl_guts_rmw()` drops dynamic overrides of other lanes sharing the same register.
- [High] If `fsl_guts_init()` fails during `soc_device_register()`, the newly added call to `fsl_guts_lane_set_mode()` will trigger an uninitialized spinlock BUG.
--

commit b8f6b1d355d36a951d62ed32d06cbd69afef40c2
Author: Vladimir Oltean <vladimir.oltean@nxp.com>

phy: lynx-10g: use RCW override procedure for dynamic protocol change

This patch enables dynamic protocol changes beyond 1000Base-X/SGMII and
2500Base-X. It removes the previous limitations by utilizing the RCW
override procedure provided by the guts driver.

diff --git a/drivers/phy/freescale/phy-fsl-lynx-10g.c b/drivers/phy/freescale/phy-fsl-lynx-10g.c
index 38def160ef1aa..5ece7889aed7b 100644
--- a/drivers/phy/freescale/phy-fsl-lynx-10g.c
+++ b/drivers/phy/freescale/phy-fsl-lynx-10g.c

[ ... ]

@@ -1225,6 +1223,13 @@ static int lynx_10g_set_mode(struct phy *phy, enum phy_mode mode, int submode)
 	if (powered_up)
 		lynx_10g_lane_halt(phy);
 
+	if (lynx_10g_lane_mode_needs_rcw_override(lane, lane_mode)) {
+		err = fsl_guts_lane_set_mode(priv->info->index, lane->id,
+					     lane_mode);
                 ^^^^^^^^^^^^^^^^^^^^^^

[Severity: High]
This isn't a bug introduced by this patch, but does calling
fsl_guts_lane_set_mode() here expose a bug in fsl_guts_rmw() where dynamic
overrides on other lanes are dropped?

When fsl_guts_lane_set_mode() calls fsl_guts_rmw() to update the hardware mux,
it incorrectly reads from the boot-time status register (RCWSR) instead of the
control register (RCWCR):

drivers/soc/fsl/guts.c:fsl_guts_rmw() {
    ...
    u32 tmp = fsl_guts_read(&soc.dcfg_ccsr->rcwsr[offset]);

    tmp &= ~mask;
    tmp |= val;
    fsl_guts_write(&soc.dcfg_dcsr->rcwcr[offset], tmp);
    ...
}

Because RCWSR is read-only and reflects the boot-time configuration, and
multiple lanes share the same register, won't dynamically changing the
protocol of one lane revert any previous dynamic changes applied to the other
lanes?

[Severity: High]
This is a pre-existing issue, but could this also trigger an uninitialized
spinlock BUG if fsl_guts_init() fails?

In drivers/soc/fsl/guts.c, if fsl_guts_init() fails during
soc_device_register(), the error path doesn't clean up the global soc.data
and skips initializing soc.rcwcr_lock:

drivers/soc/fsl/guts.c:fsl_guts_init() {
    ...
    soc_dev = soc_device_register(soc_dev_attr);
    if (IS_ERR(soc_dev)) {
        ret = PTR_ERR(soc_dev);
        goto err;
    }

    spin_lock_init(&soc.rcwcr_lock);
    ...
}

Since soc.data is left populated, the readiness check in
fsl_guts_lane_set_mode() will pass. Won't this then proceed to acquire the
uninitialized soc.rcwcr_lock, triggering a SPIN_BUG_ON?

> +		if (err)
> +			goto out;
> +	}
> +
> 	err = lynx_10g_lane_disable_pcvt(lane, lane->mode);
> 	if (err)

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260612210859.266759-1-vladimir.oltean@nxp.com?part=8

-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy