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
  ...

Documentation/ABI/testing/sysfs-bus-cxl

@@ -28,6 +28,23 @@ Description:
 		Payload in the CXL-2.0 specification.
 
 
+What:		/sys/bus/cxl/devices/memX/ram/qos_class
+Date:		May, 2023
+KernelVersion:	v6.8
+Contact:	[email protected]
+Description:
+		(RO) For CXL host platforms that support "QoS Telemmetry"
+		this attribute conveys a comma delimited list of platform
+		specific cookies that identifies a QoS performance class
+		for the volatile partition of the CXL mem device. These
+		class-ids can be compared against a similar "qos_class"
+		published for a root decoder. While it is not required
+		that the endpoints map their local memory-class to a
+		matching platform class, mismatches are not recommended
+		and there are platform specific performance related
+		side-effects that may result. First class-id is displayed.
+
+
 What:		/sys/bus/cxl/devices/memX/pmem/size
 Date:		December, 2020
 KernelVersion:	v5.12
@@ -38,6 +55,23 @@ Description:
 		Payload in the CXL-2.0 specification.
 
 
+What:		/sys/bus/cxl/devices/memX/pmem/qos_class
+Date:		May, 2023
+KernelVersion:	v6.8
+Contact:	[email protected]
+Description:
+		(RO) For CXL host platforms that support "QoS Telemmetry"
+		this attribute conveys a comma delimited list of platform
+		specific cookies that identifies a QoS performance class
+		for the persistent partition of the CXL mem device. These
+		class-ids can be compared against a similar "qos_class"
+		published for a root decoder. While it is not required
+		that the endpoints map their local memory-class to a
+		matching platform class, mismatches are not recommended
+		and there are platform specific performance related
+		side-effects that may result. First class-id is displayed.
+
+
 What:		/sys/bus/cxl/devices/memX/serial
 Date:		January, 2022
 KernelVersion:	v5.18

MAINTAINERS

@@ -5280,6 +5280,7 @@ M:	Dan Williams <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/cxl/
+F:	include/linux/cxl-event.h
 F:	include/uapi/linux/cxl_mem.h
 F:	tools/testing/cxl/
 

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);