cxl: Add a cached copy of target_map to cxl_decoder

Add a cached copy of the hardware port-id list that is available at init
before all @DPORT objects have been instantiated. Change is in preparation
of delayed dport instantiation.

Reviewed-by: Robert Richter <rrichter@amd.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Tested-by: Robert Richter <rrichter@amd.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>

Author: davejiang

drivers/cxl/acpi.c

@@ -398,7 +398,6 @@ DEFINE_FREE(del_cxl_resource, struct resource *, if (_T) del_cxl_resource(_T))
 static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 			     struct cxl_cfmws_context *ctx)
 {
-	int target_map[CXL_DECODER_MAX_INTERLEAVE];
 	struct cxl_port *root_port = ctx->root_port;
 	struct cxl_cxims_context cxims_ctx;
 	struct device *dev = ctx->dev;
@@ -416,8 +415,6 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 	rc = eig_to_granularity(cfmws->granularity, &ig);
 	if (rc)
 		return rc;
-	for (i = 0; i < ways; i++)
-		target_map[i] = cfmws->interleave_targets[i];
 
 	struct resource *res __free(del_cxl_resource) = alloc_cxl_resource(
 		cfmws->base_hpa, cfmws->window_size, ctx->id++);
@@ -443,6 +440,8 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 		.end = cfmws->base_hpa + cfmws->window_size - 1,
 	};
 	cxld->interleave_ways = ways;
+	for (i = 0; i < ways; i++)
+		cxld->target_map[i] = cfmws->interleave_targets[i];
 	/*
 	 * Minimize the x1 granularity to advertise support for any
 	 * valid region granularity
@@ -475,7 +474,7 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 	if (cfmws->interleave_arithmetic == ACPI_CEDT_CFMWS_ARITHMETIC_XOR)
 		cxlrd->hpa_to_spa = cxl_xor_hpa_to_spa;
 
-	rc = cxl_decoder_add(cxld, target_map);
+	rc = cxl_decoder_add(cxld);
 	if (rc)
 		return rc;
 

drivers/cxl/core/hdm.c

@@ -21,12 +21,11 @@ struct cxl_rwsem cxl_rwsem = {
 	.dpa = __RWSEM_INITIALIZER(cxl_rwsem.dpa),
 };
 
-static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
-			   int *target_map)
+static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld)
 {
 	int rc;
 
-	rc = cxl_decoder_add_locked(cxld, target_map);
+	rc = cxl_decoder_add_locked(cxld);
 	if (rc) {
 		put_device(&cxld->dev);
 		dev_err(&port->dev, "Failed to add decoder\n");
@@ -54,7 +53,6 @@ int devm_cxl_add_passthrough_decoder(struct cxl_port *port)
 {
 	struct cxl_switch_decoder *cxlsd;
 	struct cxl_dport *dport = NULL;
-	int single_port_map[1];
 	unsigned long index;
 	struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev);
 
@@ -73,9 +71,9 @@ int devm_cxl_add_passthrough_decoder(struct cxl_port *port)
 
 	xa_for_each(&port->dports, index, dport)
 		break;
-	single_port_map[0] = dport->port_id;
+	cxlsd->cxld.target_map[0] = dport->port_id;
 
-	return add_hdm_decoder(port, &cxlsd->cxld, single_port_map);
+	return add_hdm_decoder(port, &cxlsd->cxld);
 }
 EXPORT_SYMBOL_NS_GPL(devm_cxl_add_passthrough_decoder, "CXL");
 
@@ -984,7 +982,7 @@ static int cxl_setup_hdm_decoder_from_dvsec(
 }
 
 static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
-			    int *target_map, void __iomem *hdm, int which,
+			    void __iomem *hdm, int which,
 			    u64 *dpa_base, struct cxl_endpoint_dvsec_info *info)
 {
 	struct cxl_endpoint_decoder *cxled = NULL;
@@ -1103,7 +1101,7 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 		hi = readl(hdm + CXL_HDM_DECODER0_TL_HIGH(which));
 		target_list.value = (hi << 32) + lo;
 		for (i = 0; i < cxld->interleave_ways; i++)
-			target_map[i] = target_list.target_id[i];
+			cxld->target_map[i] = target_list.target_id[i];
 
 		return 0;
 	}
@@ -1179,7 +1177,6 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
 	cxl_settle_decoders(cxlhdm);
 
 	for (i = 0; i < cxlhdm->decoder_count; i++) {
-		int target_map[CXL_DECODER_MAX_INTERLEAVE] = { 0 };
 		int rc, target_count = cxlhdm->target_count;
 		struct cxl_decoder *cxld;
 
@@ -1207,16 +1204,15 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
 			cxld = &cxlsd->cxld;
 		}
 
-		rc = init_hdm_decoder(port, cxld, target_map, hdm, i,
-				      &dpa_base, info);
+		rc = init_hdm_decoder(port, cxld, hdm, i, &dpa_base, info);
 		if (rc) {
 			dev_warn(&port->dev,
 				 "Failed to initialize decoder%d.%d\n",
 				 port->id, i);
 			put_device(&cxld->dev);
 			return rc;
 		}
-		rc = add_hdm_decoder(port, cxld, target_map);
+		rc = add_hdm_decoder(port, cxld);
 		if (rc) {
 			dev_warn(&port->dev,
 				 "Failed to add decoder%d.%d\n", port->id, i);

drivers/cxl/core/port.c

@@ -1715,21 +1715,19 @@ struct cxl_port *cxl_mem_find_port(struct cxl_memdev *cxlmd,
 EXPORT_SYMBOL_NS_GPL(cxl_mem_find_port, "CXL");
 
 static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
-				    struct cxl_port *port, int *target_map)
+				    struct cxl_port *port)
 {
+	struct cxl_decoder *cxld = &cxlsd->cxld;
 	int i;
 
-	if (!target_map)
-		return 0;
-
 	device_lock_assert(&port->dev);
 
 	if (xa_empty(&port->dports))
 		return -EINVAL;
 
 	guard(rwsem_write)(&cxl_rwsem.region);
 	for (i = 0; i < cxlsd->cxld.interleave_ways; i++) {
-		struct cxl_dport *dport = find_dport(port, target_map[i]);
+		struct cxl_dport *dport = find_dport(port, cxld->target_map[i]);
 
 		if (!dport)
 			return -ENXIO;
@@ -1921,9 +1919,6 @@ EXPORT_SYMBOL_NS_GPL(cxl_endpoint_decoder_alloc, "CXL");
 /**
  * cxl_decoder_add_locked - Add a decoder with targets
  * @cxld: The cxl decoder allocated by cxl_<type>_decoder_alloc()
- * @target_map: A list of downstream ports that this decoder can direct memory
- *              traffic to. These numbers should correspond with the port number
- *              in the PCIe Link Capabilities structure.
  *
  * Certain types of decoders may not have any targets. The main example of this
  * is an endpoint device. A more awkward example is a hostbridge whose root
@@ -1937,7 +1932,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_endpoint_decoder_alloc, "CXL");
  * Return: Negative error code if the decoder wasn't properly configured; else
  *	   returns 0.
  */
-int cxl_decoder_add_locked(struct cxl_decoder *cxld, int *target_map)
+int cxl_decoder_add_locked(struct cxl_decoder *cxld)
 {
 	struct cxl_port *port;
 	struct device *dev;
@@ -1958,7 +1953,7 @@ int cxl_decoder_add_locked(struct cxl_decoder *cxld, int *target_map)
 	if (!is_endpoint_decoder(dev)) {
 		struct cxl_switch_decoder *cxlsd = to_cxl_switch_decoder(dev);
 
-		rc = decoder_populate_targets(cxlsd, port, target_map);
+		rc = decoder_populate_targets(cxlsd, port);
 		if (rc && (cxld->flags & CXL_DECODER_F_ENABLE)) {
 			dev_err(&port->dev,
 				"Failed to populate active decoder targets\n");
@@ -1977,17 +1972,14 @@ EXPORT_SYMBOL_NS_GPL(cxl_decoder_add_locked, "CXL");
 /**
  * cxl_decoder_add - Add a decoder with targets
  * @cxld: The cxl decoder allocated by cxl_<type>_decoder_alloc()
- * @target_map: A list of downstream ports that this decoder can direct memory
- *              traffic to. These numbers should correspond with the port number
- *              in the PCIe Link Capabilities structure.
  *
  * This is the unlocked variant of cxl_decoder_add_locked().
  * See cxl_decoder_add_locked().
  *
  * Context: Process context. Takes and releases the device lock of the port that
  *	    owns the @cxld.
  */
-int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map)
+int cxl_decoder_add(struct cxl_decoder *cxld)
 {
 	struct cxl_port *port;
 
@@ -2000,7 +1992,7 @@ int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map)
 	port = to_cxl_port(cxld->dev.parent);
 
 	guard(device)(&port->dev);
-	return cxl_decoder_add_locked(cxld, target_map);
+	return cxl_decoder_add_locked(cxld);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_decoder_add, "CXL");
 

drivers/cxl/core/region.c

@@ -1510,8 +1510,10 @@ static int cxl_port_setup_targets(struct cxl_port *port,
 				cxl_rr->nr_targets_set);
 			return -ENXIO;
 		}
-	} else
+	} else {
 		cxlsd->target[cxl_rr->nr_targets_set] = ep->dport;
+		cxlsd->cxld.target_map[cxl_rr->nr_targets_set] = ep->dport->port_id;
+	}
 	inc = 1;
 out_target_set:
 	cxl_rr->nr_targets_set += inc;

drivers/cxl/cxl.h

@@ -357,6 +357,9 @@ enum cxl_decoder_type {
  * @target_type: accelerator vs expander (type2 vs type3) selector
  * @region: currently assigned region for this decoder
  * @flags: memory type capabilities and locking
+ * @target_map: cached copy of hardware port-id list, available at init
+ *              before all @dport objects have been instantiated. While
+ *              dport id is 8bit, CFMWS interleave targets are 32bits.
  * @commit: device/decoder-type specific callback to commit settings to hw
  * @reset: device/decoder-type specific callback to reset hw settings
 */
@@ -369,6 +372,7 @@ struct cxl_decoder {
 	enum cxl_decoder_type target_type;
 	struct cxl_region *region;
 	unsigned long flags;
+	u32 target_map[CXL_DECODER_MAX_INTERLEAVE];
 	int (*commit)(struct cxl_decoder *cxld);
 	void (*reset)(struct cxl_decoder *cxld);
 };
@@ -781,9 +785,9 @@ struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
 						unsigned int nr_targets);
 struct cxl_switch_decoder *cxl_switch_decoder_alloc(struct cxl_port *port,
 						    unsigned int nr_targets);
-int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map);
+int cxl_decoder_add(struct cxl_decoder *cxld);
 struct cxl_endpoint_decoder *cxl_endpoint_decoder_alloc(struct cxl_port *port);
-int cxl_decoder_add_locked(struct cxl_decoder *cxld, int *target_map);
+int cxl_decoder_add_locked(struct cxl_decoder *cxld);
 int cxl_decoder_autoremove(struct device *host, struct cxl_decoder *cxld);
 static inline int cxl_root_decoder_autoremove(struct device *host,
 					      struct cxl_root_decoder *cxlrd)

tools/testing/cxl/test/cxl.c

@@ -651,7 +651,7 @@ static int mock_cxl_add_passthrough_decoder(struct cxl_port *port)
 
 
 struct target_map_ctx {
-	int *target_map;
+	u32 *target_map;
 	int index;
 	int target_count;
 };
@@ -863,9 +863,7 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
 		target_count = NR_CXL_SWITCH_PORTS;
 
 	for (i = 0; i < NR_CXL_PORT_DECODERS; i++) {
-		int target_map[CXL_DECODER_MAX_INTERLEAVE] = { 0 };
 		struct target_map_ctx ctx = {
-			.target_map = target_map,
 			.target_count = target_count,
 		};
 		struct cxl_decoder *cxld;
@@ -894,6 +892,8 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
 			cxld = &cxled->cxld;
 		}
 
+		ctx.target_map = cxld->target_map;
+
 		mock_init_hdm_decoder(cxld);
 
 		if (target_count) {
@@ -905,7 +905,7 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
 			}
 		}
 
-		rc = cxl_decoder_add_locked(cxld, target_map);
+		rc = cxl_decoder_add_locked(cxld);
 		if (rc) {
 			put_device(&cxld->dev);
 			dev_err(&port->dev, "Failed to add decoder\n");