Merge tag 'cxl-for-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull CXL (Compute Express Link) updates from Dan Williams:
 "The bulk of this update is support for enumerating the performance
  capabilities of CXL memory targets and connecting that to a platform
  CXL memory QoS class. Some follow-on work remains to hook up this data
  into core-mm policy, but that is saved for v6.9.

  The next significant update is unifying how CXL event records (things
  like background scrub errors) are processed between so called
  "firmware first" and native error record retrieval. The CXL driver
  handler that processes the record retrieved from the device mailbox is
  now the handler for that same record format coming from an EFI/ACPI
  notification source.

  This also contains miscellaneous feature updates, like Get Timestamp,
  and other fixups.

  Summary:

   - Add support for parsing the Coherent Device Attribute Table (CDAT)

   - Add support for calculating a platform CXL QoS class from CDAT data

   - Unify the tracing of EFI CXL Events with native CXL Events.

   - Add Get Timestamp support

   - Miscellaneous cleanups and fixups"

* tag 'cxl-for-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (41 commits)
  cxl/core: use sysfs_emit() for attr's _show()
  cxl/pci: Register for and process CPER events
  PCI: Introduce cleanup helpers for device reference counts and locks
  acpi/ghes: Process CXL Component Events
  cxl/events: Create a CXL event union
  cxl/events: Separate UUID from event structures
  cxl/events: Remove passing a UUID to known event traces
  cxl/events: Create common event UUID defines
  cxl/events: Promote CXL event structures to a core header
  cxl: Refactor to use __free() for cxl_root allocation in cxl_endpoint_port_probe()
  cxl: Refactor to use __free() for cxl_root allocation in cxl_find_nvdimm_bridge()
  cxl: Fix device reference leak in cxl_port_perf_data_calculate()
  cxl: Convert find_cxl_root() to return a 'struct cxl_root *'
  cxl: Introduce put_cxl_root() helper
  cxl/port: Fix missing target list lock
  cxl/port: Fix decoder initialization when nr_targets > interleave_ways
  cxl/region: fix x9 interleave typo
  cxl/trace: Pass UUID explicitly to event traces
  cxl/region: use %pap format to print resource_size_t
  cxl/region: Add dev_dbg() detail on failure to allocate HPA space
  ...

3 files changed, 256 insertions, 31 deletions

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index ab2a82cb1b0b..7b7c605166e0 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/timer.h>
 #include <linux/cper.h>
+#include <linux/cxl-event.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -673,6 +674,78 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+/*
+ * Only a single callback can be registered for CXL CPER events.
+ */
+static DECLARE_RWSEM(cxl_cper_rw_sem);
+static cxl_cper_callback cper_callback;
+
+/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
+
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
+	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
+		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
+
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CPER_SEC_CXL_DRAM_GUID						\
+	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
+		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CPER_SEC_CXL_MEM_MODULE_GUID					\
+	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
+
+static void cxl_cper_post_event(enum cxl_event_type event_type,
+				struct cxl_cper_event_rec *rec)
+{
+	if (rec->hdr.length <= sizeof(rec->hdr) ||
+	    rec->hdr.length > sizeof(*rec)) {
+		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
+		       rec->hdr.length);
+		return;
+	}
+
+	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
+		pr_err(FW_WARN "CXL CPER invalid event\n");
+		return;
+	}
+
+	guard(rwsem_read)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		cper_callback(event_type, rec);
+}
+
+int cxl_cper_register_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		return -EINVAL;
+	cper_callback = callback;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_callback, CXL);
+
+int cxl_cper_unregister_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (callback != cper_callback)
+		return -EINVAL;
+	cper_callback = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_callback, CXL);
+
 static bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -707,6 +780,22 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			queued = ghes_handle_arm_hw_error(gdata, sev, sync);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
+		} else if (guid_equal(sec_type,
+				      &CPER_SEC_CXL_MEM_MODULE_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 9ef5f1bdcfdb..d6b85f0f6082 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -58,14 +58,22 @@ struct target_cache {
 	struct node_cache_attrs cache_attrs;
 };
 
+enum {
+	NODE_ACCESS_CLASS_0 = 0,
+	NODE_ACCESS_CLASS_1,
+	NODE_ACCESS_CLASS_GENPORT_SINK,
+	NODE_ACCESS_CLASS_MAX,
+};
+
 struct memory_target {
 	struct list_head node;
 	unsigned int memory_pxm;
 	unsigned int processor_pxm;
 	struct resource memregions;
-	struct node_hmem_attrs hmem_attrs[2];
+	struct access_coordinate coord[NODE_ACCESS_CLASS_MAX];
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
+	u8 gen_port_device_handle[ACPI_SRAT_DEVICE_HANDLE_SIZE];
 	bool registered;
 };
 
@@ -100,6 +108,47 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm)
 	return NULL;
 }
 
+static struct memory_target *acpi_find_genport_target(u32 uid)
+{
+	struct memory_target *target;
+	u32 target_uid;
+	u8 *uid_ptr;
+
+	list_for_each_entry(target, &targets, node) {
+		uid_ptr = target->gen_port_device_handle + 8;
+		target_uid = *(u32 *)uid_ptr;
+		if (uid == target_uid)
+			return target;
+	}
+
+	return NULL;
+}
+
+/**
+ * acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port
+ * @uid: ACPI unique id
+ * @coord: The access coordinates written back out for the generic port
+ *
+ * Return: 0 on success. Errno on failure.
+ *
+ * Only supports device handles that are ACPI. Assume ACPI0016 HID for CXL.
+ */
+int acpi_get_genport_coordinates(u32 uid,
+				 struct access_coordinate *coord)
+{
+	struct memory_target *target;
+
+	guard(mutex)(&target_lock);
+	target = acpi_find_genport_target(uid);
+	if (!target)
+		return -ENOENT;
+
+	*coord = target->coord[NODE_ACCESS_CLASS_GENPORT_SINK];
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(acpi_get_genport_coordinates, CXL);
+
 static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 {
 	struct memory_initiator *initiator;
@@ -120,8 +169,7 @@ static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 	list_add_tail(&initiator->node, &initiators);
 }
 
-static __init void alloc_memory_target(unsigned int mem_pxm,
-		resource_size_t start, resource_size_t len)
+static __init struct memory_target *alloc_target(unsigned int mem_pxm)
 {
 	struct memory_target *target;
 
@@ -129,7 +177,7 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 	if (!target) {
 		target = kzalloc(sizeof(*target), GFP_KERNEL);
 		if (!target)
-			return;
+			return NULL;
 		target->memory_pxm = mem_pxm;
 		target->processor_pxm = PXM_INVAL;
 		target->memregions = (struct resource) {
@@ -142,6 +190,19 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 		INIT_LIST_HEAD(&target->caches);
 	}
 
+	return target;
+}
+
+static __init void alloc_memory_target(unsigned int mem_pxm,
+				       resource_size_t start,
+				       resource_size_t len)
+{
+	struct memory_target *target;
+
+	target = alloc_target(mem_pxm);
+	if (!target)
+		return;
+
 	/*
 	 * There are potentially multiple ranges per PXM, so record each
 	 * in the per-target memregions resource tree.
@@ -152,6 +213,18 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 				start, start + len, mem_pxm);
 }
 
+static __init void alloc_genport_target(unsigned int mem_pxm, u8 *handle)
+{
+	struct memory_target *target;
+
+	target = alloc_target(mem_pxm);
+	if (!target)
+		return;
+
+	memcpy(target->gen_port_device_handle, handle,
+	       ACPI_SRAT_DEVICE_HANDLE_SIZE);
+}
+
 static __init const char *hmat_data_type(u8 type)
 {
 	switch (type) {
@@ -228,24 +301,24 @@ static void hmat_update_target_access(struct memory_target *target,
 {
 	switch (type) {
 	case ACPI_HMAT_ACCESS_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].read_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_READ_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
+		target->coord[access].read_latency = value;
 		break;
 	case ACPI_HMAT_WRITE_LATENCY:
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_ACCESS_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	case ACPI_HMAT_READ_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
 		break;
 	case ACPI_HMAT_WRITE_BANDWIDTH:
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	default:
 		break;
@@ -291,11 +364,28 @@ static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc)
 	}
 }
 
+static __init void hmat_update_target(unsigned int tgt_pxm, unsigned int init_pxm,
+				      u8 mem_hier, u8 type, u32 value)
+{
+	struct memory_target *target = find_mem_target(tgt_pxm);
+
+	if (mem_hier != ACPI_HMAT_MEMORY)
+		return;
+
+	if (target && target->processor_pxm == init_pxm) {
+		hmat_update_target_access(target, type, value,
+					  NODE_ACCESS_CLASS_0);
+		/* If the node has a CPU, update access 1 */
+		if (node_state(pxm_to_node(init_pxm), N_CPU))
+			hmat_update_target_access(target, type, value,
+						  NODE_ACCESS_CLASS_1);
+	}
+}
+
 static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 				      const unsigned long end)
 {
 	struct acpi_hmat_locality *hmat_loc = (void *)header;
-	struct memory_target *target;
 	unsigned int init, targ, total_size, ipds, tpds;
 	u32 *inits, *targs, value;
 	u16 *entries;
@@ -336,15 +426,8 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 				inits[init], targs[targ], value,
 				hmat_data_type_suffix(type));
 
-			if (mem_hier == ACPI_HMAT_MEMORY) {
-				target = find_mem_target(targs[targ]);
-				if (target && target->processor_pxm == inits[init]) {
-					hmat_update_target_access(target, type, value, 0);
-					/* If the node has a CPU, update access 1 */
-					if (node_state(pxm_to_node(inits[init]), N_CPU))
-						hmat_update_target_access(target, type, value, 1);
-				}
-			}
+			hmat_update_target(targs[targ], inits[init],
+					   mem_hier, type, value);
 		}
 	}
 
@@ -491,6 +574,27 @@ static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header,
 	return 0;
 }
 
+static __init int srat_parse_genport_affinity(union acpi_subtable_headers *header,
+					      const unsigned long end)
+{
+	struct acpi_srat_generic_affinity *ga = (void *)header;
+
+	if (!ga)
+		return -EINVAL;
+
+	if (!(ga->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED))
+		return 0;
+
+	/* Skip PCI device_handle for now */
+	if (ga->device_handle_type != 0)
+		return 0;
+
+	alloc_genport_target(ga->proximity_domain,
+			     (u8 *)ga->device_handle);
+
+	return 0;
+}
+
 static u32 hmat_initiator_perf(struct memory_target *target,
 			       struct memory_initiator *initiator,
 			       struct acpi_hmat_locality *hmat_loc)
@@ -592,6 +696,11 @@ static void hmat_update_target_attrs(struct memory_target *target,
 	u32 best = 0;
 	int i;
 
+	/* Don't update for generic port if there's no device handle */
+	if (access == NODE_ACCESS_CLASS_GENPORT_SINK &&
+	    !(*(u16 *)target->gen_port_device_handle))
+		return;
+
 	bitmap_zero(p_nodes, MAX_NUMNODES);
 	/*
 	 * If the Address Range Structure provides a local processor pxm, set
@@ -661,6 +770,14 @@ static void __hmat_register_target_initiators(struct memory_target *target,
 	}
 }
 
+static void hmat_register_generic_target_initiators(struct memory_target *target)
+{
+	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
+
+	__hmat_register_target_initiators(target, p_nodes,
+					  NODE_ACCESS_CLASS_GENPORT_SINK);
+}
+
 static void hmat_register_target_initiators(struct memory_target *target)
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
@@ -681,7 +798,7 @@ static void hmat_register_target_cache(struct memory_target *target)
 static void hmat_register_target_perf(struct memory_target *target, int access)
 {
 	unsigned mem_nid = pxm_to_node(target->memory_pxm);
-	node_set_perf_attrs(mem_nid, &target->hmem_attrs[access], access);
+	node_set_perf_attrs(mem_nid, &target->coord[access], access);
 }
 
 static void hmat_register_target_devices(struct memory_target *target)
@@ -713,6 +830,17 @@ static void hmat_register_target(struct memory_target *target)
 	hmat_register_target_devices(target);
 
 	/*
+	 * Register generic port perf numbers. The nid may not be
+	 * initialized and is still NUMA_NO_NODE.
+	 */
+	mutex_lock(&target_lock);
+	if (*(u16 *)target->gen_port_device_handle) {
+		hmat_register_generic_target_initiators(target);
+		target->registered = true;
+	}
+	mutex_unlock(&target_lock);
+
+	/*
 	 * Skip offline nodes. This can happen when memory
 	 * marked EFI_MEMORY_SP, "specific purpose", is applied
 	 * to all the memory in a proximity domain leading to
@@ -726,8 +854,8 @@ static void hmat_register_target(struct memory_target *target)
 	if (!target->registered) {
 		hmat_register_target_initiators(target);
 		hmat_register_target_cache(target);
-		hmat_register_target_perf(target, 0);
-		hmat_register_target_perf(target, 1);
+		hmat_register_target_perf(target, NODE_ACCESS_CLASS_0);
+		hmat_register_target_perf(target, NODE_ACCESS_CLASS_1);
 		target->registered = true;
 	}
 	mutex_unlock(&target_lock);
@@ -765,7 +893,7 @@ static int hmat_set_default_dram_perf(void)
 	int rc;
 	int nid, pxm;
 	struct memory_target *target;
-	struct node_hmem_attrs *attrs;
+	struct access_coordinate *attrs;
 
 	if (!default_dram_type)
 		return -EIO;
@@ -775,7 +903,7 @@ static int hmat_set_default_dram_perf(void)
 		target = find_mem_target(pxm);
 		if (!target)
 			continue;
-		attrs = &target->hmem_attrs[1];
+		attrs = &target->coord[1];
 		rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT");
 		if (rc)
 			return rc;
@@ -789,7 +917,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
 	struct memory_target *target;
-	struct node_hmem_attrs *perf;
+	struct access_coordinate *perf;
 	int *adist = data;
 	int pxm;
 
@@ -802,7 +930,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 	hmat_update_target_attrs(target, p_nodes, 1);
 	mutex_unlock(&target_lock);
 
-	perf = &target->hmem_attrs[1];
+	perf = &target->coord[1];
 
 	if (mt_perf_to_adistance(perf, adist))
 		return NOTIFY_OK;
@@ -870,6 +998,13 @@ static __init int hmat_init(void)
 				ACPI_SRAT_TYPE_MEMORY_AFFINITY,
 				srat_parse_mem_affinity, 0) < 0)
 		goto out_put;
+
+	if (acpi_table_parse_entries(ACPI_SIG_SRAT,
+				     sizeof(struct acpi_table_srat),
+				     ACPI_SRAT_TYPE_GENERIC_PORT_AFFINITY,
+				     srat_parse_genport_affinity, 0) < 0)
+		goto out_put;
+
 	acpi_put_table(tbl);
 
 	status = acpi_get_table(ACPI_SIG_HMAT, 0, &tbl);
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index c1516337f668..b07f7d091d13 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -251,8 +251,9 @@ int __init_or_acpilib acpi_table_parse_entries_array(
 		return -ENODEV;
 	}
 
-	count = acpi_parse_entries_array(id, table_size, table_header,
-			proc, proc_num, max_entries);
+	count = acpi_parse_entries_array(id, table_size,
+					 (union fw_table_header *)table_header,
+					 proc, proc_num, max_entries);
 
 	acpi_put_table(table_header);
 	return count;