cxl/region: Provide region info to the cxl_poison trace event

User space may need to know which region, if any, maps the poison
address(es) logged in a cxl_poison trace event. Since the mapping
of DPAs (device physical addresses) to a region can change, the
kernel must provide this information at the time the poison list
is read. The event informs user space that at event <timestamp>
this <region> mapped to this <DPA>, which is poisoned.

The cxl_poison trace event is already wired up to log the region
name and uuid if it receives param 'struct cxl_region'.

In order to provide that cxl_region, add another method for gathering
poison - by committed endpoint decoder mappings. This method is only
available with CONFIG_CXL_REGION and is only used if a region actually
maps the memdev where poison is being read. After the region driver
reads the poison list for all the mapped resources, poison is read for
any remaining unmapped resources.

The default method remains: read the poison by memdev resource.
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/438b01ccaa70592539e8eda4eb2b1d617ba03160.1681838292.git.alison.schofield@intel.comTested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

drivers/cxl/core/core.h

@@ -25,7 +25,12 @@ void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled);
 #define CXL_DAX_REGION_TYPE(x) (&cxl_dax_region_type)
 int cxl_region_init(void);
 void cxl_region_exit(void);
+int cxl_get_poison_by_endpoint(struct cxl_port *port);
 #else
+static inline int cxl_get_poison_by_endpoint(struct cxl_port *port)
+{
+	return 0;
+}
 static inline void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled)
 {
 }

drivers/cxl/core/memdev.c

@@ -136,13 +136,24 @@ static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd)
 
 int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
 {
+	struct cxl_port *port;
 	int rc;
 
+	port = dev_get_drvdata(&cxlmd->dev);
+	if (!port || !is_cxl_endpoint(port))
+		return -EINVAL;
+
 	rc = down_read_interruptible(&cxl_dpa_rwsem);
 	if (rc)
 		return rc;
 
-	rc = cxl_get_poison_by_memdev(cxlmd);
+	if (port->commit_end == -1) {
+		/* No regions mapped to this memdev */
+		rc = cxl_get_poison_by_memdev(cxlmd);
+	} else {
+		/* Regions mapped, collect poison by endpoint */
+		rc =  cxl_get_poison_by_endpoint(port);
+	}
 	up_read(&cxl_dpa_rwsem);
 
 	return rc;

drivers/cxl/core/region.c

@@ -2238,6 +2238,130 @@ struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev)
 }
 EXPORT_SYMBOL_NS_GPL(to_cxl_pmem_region, CXL);
 
+struct cxl_poison_context {
+	struct cxl_port *port;
+	enum cxl_decoder_mode mode;
+	u64 offset;
+};
+
+static int cxl_get_poison_unmapped(struct cxl_memdev *cxlmd,
+				   struct cxl_poison_context *ctx)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	u64 offset, length;
+	int rc = 0;
+
+	/*
+	 * Collect poison for the remaining unmapped resources
+	 * after poison is collected by committed endpoints.
+	 *
+	 * Knowing that PMEM must always follow RAM, get poison
+	 * for unmapped resources based on the last decoder's mode:
+	 *	ram: scan remains of ram range, then any pmem range
+	 *	pmem: scan remains of pmem range
+	 */
+
+	if (ctx->mode == CXL_DECODER_RAM) {
+		offset = ctx->offset;
+		length = resource_size(&cxlds->ram_res) - offset;
+		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
+		if (rc == -EFAULT)
+			rc = 0;
+		if (rc)
+			return rc;
+	}
+	if (ctx->mode == CXL_DECODER_PMEM) {
+		offset = ctx->offset;
+		length = resource_size(&cxlds->dpa_res) - offset;
+		if (!length)
+			return 0;
+	} else if (resource_size(&cxlds->pmem_res)) {
+		offset = cxlds->pmem_res.start;
+		length = resource_size(&cxlds->pmem_res);
+	} else {
+		return 0;
+	}
+
+	return cxl_mem_get_poison(cxlmd, offset, length, NULL);
+}
+
+static int poison_by_decoder(struct device *dev, void *arg)
+{
+	struct cxl_poison_context *ctx = arg;
+	struct cxl_endpoint_decoder *cxled;
+	struct cxl_memdev *cxlmd;
+	u64 offset, length;
+	int rc = 0;
+
+	if (!is_endpoint_decoder(dev))
+		return rc;
+
+	cxled = to_cxl_endpoint_decoder(dev);
+	if (!cxled->dpa_res || !resource_size(cxled->dpa_res))
+		return rc;
+
+	/*
+	 * Regions are only created with single mode decoders: pmem or ram.
+	 * Linux does not support mixed mode decoders. This means that
+	 * reading poison per endpoint decoder adheres to the requirement
+	 * that poison reads of pmem and ram must be separated.
+	 * CXL 3.0 Spec 8.2.9.8.4.1
+	 */
+	if (cxled->mode == CXL_DECODER_MIXED) {
+		dev_dbg(dev, "poison list read unsupported in mixed mode\n");
+		return rc;
+	}
+
+	cxlmd = cxled_to_memdev(cxled);
+	if (cxled->skip) {
+		offset = cxled->dpa_res->start - cxled->skip;
+		length = cxled->skip;
+		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
+		if (rc == -EFAULT && cxled->mode == CXL_DECODER_RAM)
+			rc = 0;
+		if (rc)
+			return rc;
+	}
+
+	offset = cxled->dpa_res->start;
+	length = cxled->dpa_res->end - offset + 1;
+	rc = cxl_mem_get_poison(cxlmd, offset, length, cxled->cxld.region);
+	if (rc == -EFAULT && cxled->mode == CXL_DECODER_RAM)
+		rc = 0;
+	if (rc)
+		return rc;
+
+	/* Iterate until commit_end is reached */
+	if (cxled->cxld.id == ctx->port->commit_end) {
+		ctx->offset = cxled->dpa_res->end + 1;
+		ctx->mode = cxled->mode;
+		return 1;
+	}
+
+	return 0;
+}
+
+int cxl_get_poison_by_endpoint(struct cxl_port *port)
+{
+	struct cxl_poison_context ctx;
+	int rc = 0;
+
+	rc = down_read_interruptible(&cxl_region_rwsem);
+	if (rc)
+		return rc;
+
+	ctx = (struct cxl_poison_context) {
+		.port = port
+	};
+
+	rc = device_for_each_child(&port->dev, &ctx, poison_by_decoder);
+	if (rc == 1)
+		rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport), &ctx);
+
+	up_read(&cxl_region_rwsem);
+	return rc;
+}
+
 static struct lock_class_key cxl_pmem_region_key;
 
 static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr)