[RFC PATCH v2 08/28] cxl/port: Introduce a port driver

[Ben Widawsky <ben.widawsky@intel.com>]

The CXL port driver will be responsible for managing the decoder
resources contained within the port. It will also provide APIs that
other drivers will consume for managing these resources.

Since the port driver is responsible for instantiating new decoders, and
it does so during probe(), a new API is needed to add decoders for
callers which already hold the device lock of the port.

This patch has no functional change because no driver is registering new
ports and the root ports that are already registered should be skipped.

Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
---
 .../driver-api/cxl/memory-devices.rst         |   5 +
 drivers/cxl/Makefile                          |   2 +
 drivers/cxl/acpi.c                            |   1 +
 drivers/cxl/core/bus.c                        |  44 +++-
 drivers/cxl/core/regs.c                       |   6 +-
 drivers/cxl/cxl.h                             |  31 ++-
 drivers/cxl/port.c                            | 242 ++++++++++++++++++
 7 files changed, 315 insertions(+), 16 deletions(-)
 create mode 100644 drivers/cxl/port.c

diff --git a/Documentation/driver-api/cxl/memory-devices.rst b/Documentation/driver-api/cxl/memory-devices.rst
index 3b8f41395f6b..fbf0393cdddc 100644
--- a/Documentation/driver-api/cxl/memory-devices.rst
+++ b/Documentation/driver-api/cxl/memory-devices.rst
@@ -28,6 +28,11 @@ CXL Memory Device
 .. kernel-doc:: drivers/cxl/pci.c
    :internal:
 
+CXL Port
+--------
+.. kernel-doc:: drivers/cxl/port.c
+   :doc: cxl port
+
 CXL Core
 --------
 .. kernel-doc:: drivers/cxl/cxl.h
diff --git a/drivers/cxl/Makefile b/drivers/cxl/Makefile
index cf07ae6cea17..40b386aaedf7 100644
--- a/drivers/cxl/Makefile
+++ b/drivers/cxl/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_CXL_BUS) += core/
+obj-$(CONFIG_CXL_MEM) += cxl_port.o
 obj-$(CONFIG_CXL_PCI) += cxl_pci.o
 obj-$(CONFIG_CXL_ACPI) += cxl_acpi.o
 obj-$(CONFIG_CXL_PMEM) += cxl_pmem.o
@@ -7,3 +8,4 @@ obj-$(CONFIG_CXL_PMEM) += cxl_pmem.o
 cxl_pci-y := pci.o
 cxl_acpi-y := acpi.o
 cxl_pmem-y := pmem.o
+cxl_port-y := port.o
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index b972abc9f6ef..d61397055e9f 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -491,3 +491,4 @@ static struct platform_driver cxl_acpi_driver = {
 module_platform_driver(cxl_acpi_driver);
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);
+MODULE_SOFTDEP("pre: cxl_port");
diff --git a/drivers/cxl/core/bus.c b/drivers/cxl/core/bus.c
index 5f2bde47a5c2..dffbd0ac64af 100644
--- a/drivers/cxl/core/bus.c
+++ b/drivers/cxl/core/bus.c
@@ -266,6 +266,7 @@ struct cxl_port *to_cxl_port(struct device *dev)
 		return NULL;
 	return container_of(dev, struct cxl_port, dev);
 }
+EXPORT_SYMBOL_GPL(to_cxl_port);
 
 static void unregister_port(void *_port)
 {
@@ -537,11 +538,21 @@ struct cxl_decoder *cxl_decoder_alloc(struct cxl_port *port,
 }
 EXPORT_SYMBOL_GPL(cxl_decoder_alloc);
 
-int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map)
+/**
+ * cxl_decoder_add_locked() - Adds a decoder with port locked.
+ * @cxld: Decoder to be added
+ * @target_map: Downstream port array of port ids
+ *
+ * The parent port owning the @cxld must have its device mutex locked before
+ * calling this function.
+ *
+ * Returns 0 if successful; otherwise, a negative error code is returned.
+ */
+int cxl_decoder_add_locked(struct cxl_decoder *cxld, int *target_map)
 {
 	struct cxl_port *port;
 	struct device *dev;
-	int rc = 0;
+	int rc;
 
 	if (WARN_ON_ONCE(!cxld))
 		return -EINVAL;
@@ -556,12 +567,11 @@ int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map)
 
 	port = to_cxl_port(cxld->dev.parent);
 
-	device_lock(&port->dev);
-	if (!is_endpoint_decoder(dev))
+	if (!is_endpoint_decoder(dev)) {
 		rc = decoder_populate_targets(cxld, port, target_map);
-	device_unlock(&port->dev);
-	if (rc)
-		return rc;
+		if (rc)
+			return rc;
+	}
 
 	rc = dev_set_name(dev, "decoder%d.%d", port->id, cxld->id);
 	if (rc)
@@ -569,6 +579,24 @@ int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map)
 
 	return device_add(dev);
 }
+EXPORT_SYMBOL_GPL(cxl_decoder_add_locked);
+
+int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map)
+{
+	int rc;
+
+	if (WARN_ON_ONCE(!cxld))
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(IS_ERR(cxld)))
+		return PTR_ERR(cxld);
+
+	device_lock(&to_cxl_port(cxld->dev.parent)->dev);
+	rc = cxl_decoder_add_locked(cxld, target_map);
+	device_unlock(&to_cxl_port(cxld->dev.parent)->dev);
+
+	return rc;
+}
 EXPORT_SYMBOL_GPL(cxl_decoder_add);
 
 static void cxld_unregister(void *dev)
@@ -627,6 +655,8 @@ static int cxl_device_id(struct device *dev)
 		return CXL_DEVICE_NVDIMM_BRIDGE;
 	if (dev->type == &cxl_nvdimm_type)
 		return CXL_DEVICE_NVDIMM;
+	if (dev->type == &cxl_port_type)
+		return CXL_DEVICE_PORT;
 	return 0;
 }
 
diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
index 40598905c080..c8ab8880b81b 100644
--- a/drivers/cxl/core/regs.c
+++ b/drivers/cxl/core/regs.c
@@ -159,9 +159,8 @@ void cxl_probe_device_regs(struct device *dev, void __iomem *base,
 }
 EXPORT_SYMBOL_GPL(cxl_probe_device_regs);
 
-static void __iomem *devm_cxl_iomap_block(struct device *dev,
-					  resource_size_t addr,
-					  resource_size_t length)
+void __iomem *devm_cxl_iomap_block(struct device *dev, resource_size_t addr,
+				   resource_size_t length)
 {
 	void __iomem *ret_val;
 	struct resource *res;
@@ -180,6 +179,7 @@ static void __iomem *devm_cxl_iomap_block(struct device *dev,
 
 	return ret_val;
 }
+EXPORT_SYMBOL_GPL(devm_cxl_iomap_block);
 
 int cxl_map_component_regs(struct pci_dev *pdev,
 			   struct cxl_component_regs *regs,
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 91b8fd54bc93..ad22caf9135c 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -17,6 +17,9 @@
  * (port-driver, region-driver, nvdimm object-drivers... etc).
  */
 
+/* CXL 2.0 8.2.4 CXL Component Register Layout and Definition */
+#define CXL_COMPONENT_REG_BLOCK_SIZE SZ_64K
+
 /* CXL 2.0 8.2.5 CXL.cache and CXL.mem Registers*/
 #define CXL_CM_OFFSET 0x1000
 #define CXL_CM_CAP_HDR_OFFSET 0x0
@@ -36,11 +39,22 @@
 #define CXL_HDM_DECODER_CAP_OFFSET 0x0
 #define   CXL_HDM_DECODER_COUNT_MASK GENMASK(3, 0)
 #define   CXL_HDM_DECODER_TARGET_COUNT_MASK GENMASK(7, 4)
-#define CXL_HDM_DECODER0_BASE_LOW_OFFSET 0x10
-#define CXL_HDM_DECODER0_BASE_HIGH_OFFSET 0x14
-#define CXL_HDM_DECODER0_SIZE_LOW_OFFSET 0x18
-#define CXL_HDM_DECODER0_SIZE_HIGH_OFFSET 0x1c
-#define CXL_HDM_DECODER0_CTRL_OFFSET 0x20
+#define   CXL_HDM_DECODER_INTERLEAVE_11_8 BIT(8)
+#define   CXL_HDM_DECODER_INTERLEAVE_14_12 BIT(9)
+#define CXL_HDM_DECODER_CTRL_OFFSET 0x4
+#define   CXL_HDM_DECODER_ENABLE BIT(1)
+#define CXL_HDM_DECODER0_BASE_LOW_OFFSET(i) (0x20 * (i) + 0x10)
+#define CXL_HDM_DECODER0_BASE_HIGH_OFFSET(i) (0x20 * (i) + 0x14)
+#define CXL_HDM_DECODER0_SIZE_LOW_OFFSET(i) (0x20 * (i) + 0x18)
+#define CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(i) (0x20 * (i) + 0x1c)
+#define CXL_HDM_DECODER0_CTRL_OFFSET(i) (0x20 * (i) + 0x20)
+#define   CXL_HDM_DECODER0_CTRL_IG_MASK GENMASK(3, 0)
+#define   CXL_HDM_DECODER0_CTRL_IW_MASK GENMASK(7, 4)
+#define   CXL_HDM_DECODER0_CTRL_COMMIT BIT(9)
+#define   CXL_HDM_DECODER0_CTRL_COMMITTED BIT(10)
+#define   CXL_HDM_DECODER0_CTRL_TYPE BIT(12)
+#define CXL_HDM_DECODER0_TL_LOW(i) (0x20 * (i) + 0x24)
+#define CXL_HDM_DECODER0_TL_HIGH(i) (0x20 * (i) + 0x28)
 
 static inline int cxl_hdm_decoder_count(u32 cap_hdr)
 {
@@ -164,6 +178,8 @@ int cxl_map_device_regs(struct pci_dev *pdev,
 enum cxl_regloc_type;
 int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type,
 		      struct cxl_register_map *map);
+void __iomem *devm_cxl_iomap_block(struct device *dev, resource_size_t addr,
+				   resource_size_t length);
 
 #define CXL_RESOURCE_NONE ((resource_size_t) -1)
 #define CXL_TARGET_STRLEN 20
@@ -178,7 +194,8 @@ int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type,
 #define CXL_DECODER_F_TYPE2 BIT(2)
 #define CXL_DECODER_F_TYPE3 BIT(3)
 #define CXL_DECODER_F_LOCK  BIT(4)
-#define CXL_DECODER_F_MASK  GENMASK(4, 0)
+#define CXL_DECODER_F_EN    BIT(5)
+#define CXL_DECODER_F_MASK  GENMASK(5, 0)
 
 enum cxl_decoder_type {
        CXL_DECODER_ACCELERATOR = 2,
@@ -295,6 +312,7 @@ struct cxl_decoder *to_cxl_decoder(struct device *dev);
 bool is_root_decoder(struct device *dev);
 struct cxl_decoder *cxl_decoder_alloc(struct cxl_port *port,
 				      unsigned int nr_targets);
+int cxl_decoder_add_locked(struct cxl_decoder *cxld, int *target_map);
 int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map);
 int cxl_decoder_autoremove(struct device *host, struct cxl_decoder *cxld);
 
@@ -323,6 +341,7 @@ void cxl_driver_unregister(struct cxl_driver *cxl_drv);
 
 #define CXL_DEVICE_NVDIMM_BRIDGE	1
 #define CXL_DEVICE_NVDIMM		2
+#define CXL_DEVICE_PORT			3
 
 #define MODULE_ALIAS_CXL(type) MODULE_ALIAS("cxl:t" __stringify(type) "*")
 #define CXL_MODALIAS_FMT "cxl:t%d"
diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
new file mode 100644
index 000000000000..ebbfb72ae995
--- /dev/null
+++ b/drivers/cxl/port.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2021 Intel Corporation. All rights reserved. */
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include "cxlmem.h"
+
+/**
+ * DOC: cxl port
+ *
+ * The port driver implements the set of functionality needed to allow full
+ * decoder enumeration and routing. A CXL port is an abstraction of a CXL
+ * component that implements some amount of CXL decoding of CXL.mem traffic.
+ * As of the CXL 2.0 spec, this includes:
+ *
+ *	.. list-table:: CXL Components w/ Ports
+ *		:widths: 25 25 50
+ *		:header-rows: 1
+ *
+ *		* - component
+ *		  - upstream
+ *		  - downstream
+ *		* - Hostbridge
+ *		  - ACPI0016
+ *		  - root port
+ *		* - Switch
+ *		  - Switch Upstream Port
+ *		  - Switch Downstream Port
+ *		* - Endpoint (not yet implemented)
+ *		  - Endpoint Port
+ *		  - N/A
+ *
+ * The primary service this driver provides is enumerating HDM decoders and
+ * presenting APIs to other drivers to utilize the decoders.
+ */
+
+struct cxl_port_data {
+	struct cxl_component_regs regs;
+
+	struct port_caps {
+		unsigned int count;
+		unsigned int tc;
+		unsigned int interleave11_8;
+		unsigned int interleave14_12;
+	} caps;
+};
+
+static inline int cxl_hdm_decoder_ig(u32 ctrl)
+{
+	int val = FIELD_GET(CXL_HDM_DECODER0_CTRL_IG_MASK, ctrl);
+
+	return 8 + val;
+}
+
+static inline int cxl_hdm_decoder_iw(u32 ctrl)
+{
+	int val = FIELD_GET(CXL_HDM_DECODER0_CTRL_IW_MASK, ctrl);
+
+	return 1 << val;
+}
+
+static void get_caps(struct cxl_port *port, struct cxl_port_data *cpd)
+{
+	void __iomem *hdm_decoder = cpd->regs.hdm_decoder;
+	struct port_caps *caps = &cpd->caps;
+	u32 hdm_cap;
+
+	hdm_cap = readl(hdm_decoder + CXL_HDM_DECODER_CAP_OFFSET);
+
+	caps->count = cxl_hdm_decoder_count(hdm_cap);
+	caps->tc = FIELD_GET(CXL_HDM_DECODER_TARGET_COUNT_MASK, hdm_cap);
+	caps->interleave11_8 =
+		FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_11_8, hdm_cap);
+	caps->interleave14_12 =
+		FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_14_12, hdm_cap);
+}
+
+static int map_regs(struct cxl_port *port, void __iomem *crb,
+		    struct cxl_port_data *cpd)
+{
+	struct cxl_register_map map;
+	struct cxl_component_reg_map *comp_map = &map.component_map;
+
+	cxl_probe_component_regs(&port->dev, crb, comp_map);
+	if (!comp_map->hdm_decoder.valid) {
+		dev_err(&port->dev, "HDM decoder registers invalid\n");
+		return -ENXIO;
+	}
+
+	cpd->regs.hdm_decoder = crb + comp_map->hdm_decoder.offset;
+
+	return 0;
+}
+
+static u64 get_decoder_size(void __iomem *hdm_decoder, int n)
+{
+	u32 ctrl = readl(hdm_decoder + CXL_HDM_DECODER0_CTRL_OFFSET(n));
+
+	if (!!FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl))
+		return 0;
+
+	return ioread64_hi_lo(hdm_decoder +
+			      CXL_HDM_DECODER0_SIZE_LOW_OFFSET(n));
+}
+
+static bool is_endpoint_port(struct cxl_port *port)
+{
+	if (!port->uport->driver)
+		return false;
+
+	return to_cxl_drv(port->uport->driver)->id ==
+	       CXL_DEVICE_MEMORY_EXPANDER;
+}
+
+static int enumerate_hdm_decoders(struct cxl_port *port,
+				  struct cxl_port_data *portdata)
+{
+	int i = 0;
+
+	for (i = 0; i < portdata->caps.count; i++) {
+		int iw = 1, ig = 0, rc, target_count = portdata->caps.tc;
+		void __iomem *hdm_decoder = portdata->regs.hdm_decoder;
+		enum cxl_decoder_type type = CXL_DECODER_EXPANDER;
+		struct resource res = DEFINE_RES_MEM(0, 0);
+		struct cxl_decoder *cxld;
+		int *target_map = NULL;
+		u64 size;
+
+		if (is_endpoint_port(port))
+			target_count = 0;
+
+		cxld = cxl_decoder_alloc(port, target_count);
+		if (IS_ERR(cxld)) {
+			dev_warn(&port->dev,
+				 "Failed to allocate the decoder\n");
+			return PTR_ERR(cxld);
+		}
+
+		size = get_decoder_size(hdm_decoder, i);
+		if (size != 0) {
+			int temp[CXL_DECODER_MAX_INTERLEAVE];
+			u64 target_list, base;
+			u32 ctrl;
+			int j;
+
+			target_map = temp;
+			ctrl = readl(hdm_decoder + CXL_HDM_DECODER0_CTRL_OFFSET(i));
+			base = ioread64_hi_lo(hdm_decoder + CXL_HDM_DECODER0_BASE_LOW_OFFSET(i));
+			res = (struct resource)DEFINE_RES_MEM(base, size);
+
+			cxld->flags = CXL_DECODER_F_EN;
+			iw = cxl_hdm_decoder_iw(ctrl);
+			ig = cxl_hdm_decoder_ig(ctrl);
+
+			if (FIELD_GET(CXL_HDM_DECODER0_CTRL_TYPE, ctrl) == 0)
+				type = CXL_DECODER_ACCELERATOR;
+
+			target_list = ioread64_hi_lo(hdm_decoder + CXL_HDM_DECODER0_TL_LOW(i));
+			for (j = 0; j < iw; j++)
+				target_map[j] = (target_list >> (j * 8)) & 0xff;
+		}
+
+		cxld->target_type = type;
+		cxld->res = res;
+		cxld->interleave_ways = iw;
+		cxld->interleave_granularity = ig;
+
+		rc = cxl_decoder_add_locked(cxld, target_map);
+		if (rc)
+			put_device(&cxld->dev);
+		else
+			rc = cxl_decoder_autoremove(port->uport->parent, cxld);
+		if (rc)
+			dev_err(&port->dev, "Failed to add decoder\n");
+	}
+
+	return 0;
+}
+
+static int cxl_port_probe(struct device *dev)
+{
+	struct cxl_port *port = to_cxl_port(dev);
+	struct cxl_port_data *portdata;
+	void __iomem *crb;
+	u32 ctrl;
+	int rc;
+
+	if (port->component_reg_phys == CXL_RESOURCE_NONE)
+		return 0;
+
+	portdata = devm_kzalloc(dev, sizeof(*portdata), GFP_KERNEL);
+	if (!portdata)
+		return -ENOMEM;
+
+	crb = devm_cxl_iomap_block(&port->dev, port->component_reg_phys,
+				   CXL_COMPONENT_REG_BLOCK_SIZE);
+	if (IS_ERR_OR_NULL(crb)) {
+		dev_err(&port->dev, "No component registers mapped\n");
+		return -ENXIO;
+	}
+
+	rc = map_regs(port, crb, portdata);
+	if (rc)
+		return rc;
+
+	get_caps(port, portdata);
+	if (portdata->caps.count == 0) {
+		dev_err(&port->dev, "Spec violation. Caps invalid\n");
+		return -ENXIO;
+	}
+
+	/*
+	 * Enable HDM decoders for this port.
+	 *
+	 * FIXME: If the component was using DVSEC range registers for decode,
+	 * this will destroy that.
+	 */
+	ctrl = readl(portdata->regs.hdm_decoder + CXL_HDM_DECODER_CTRL_OFFSET);
+	ctrl |= CXL_HDM_DECODER_ENABLE;
+	writel(ctrl, portdata->regs.hdm_decoder + CXL_HDM_DECODER_CTRL_OFFSET);
+
+	rc = enumerate_hdm_decoders(port, portdata);
+	if (rc) {
+		dev_err(&port->dev, "Couldn't enumerate decoders (%d)\n", rc);
+		return rc;
+	}
+
+	dev_set_drvdata(dev, portdata);
+	return 0;
+}
+
+static struct cxl_driver cxl_port_driver = {
+	.name = "cxl_port",
+	.probe = cxl_port_probe,
+	.id = CXL_DEVICE_PORT,
+};
+module_cxl_driver(cxl_port_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(CXL);
+MODULE_ALIAS_CXL(CXL_DEVICE_PORT);
-- 
2.33.1