Merge tag 'cxl-for-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull Compute Express Link (CXL) updates from Dan Williams:
 "To date Linux has been dependent on platform-firmware to map CXL RAM
  regions and handle events / errors from devices. With this update we
  can now parse / update the CXL memory layout, and report events /
  errors from devices. This is a precursor for the CXL subsystem to
  handle the end-to-end "RAS" flow for CXL memory. i.e. the flow that
  for DDR-attached-DRAM is handled by the EDAC driver where it maps
  system physical address events to a field-replaceable-unit (FRU /
  endpoint device). In general, CXL has the potential to standardize
  what has historically been a pile of memory-controller-specific error
  handling logic.

  Another change of note is the default policy for handling RAM-backed
  device-dax instances. Previously the default access mode was "device",
  mmap(2) a device special file to access memory. The new default is
  "kmem" where the address range is assigned to the core-mm via
  add_memory_driver_managed(). This saves typical users from wondering
  why their platform memory is not visible via free(1) and stuck behind
  a device-file. At the same time it allows expert users to deploy
  policy to, for example, get dedicated access to high performance
  memory, or hide low performance memory from general purpose kernel
  allocations. This affects not only CXL, but also systems with
  high-bandwidth-memory that platform-firmware tags with the
  EFI_MEMORY_SP (special purpose) designation.

  Summary:

   - CXL RAM region enumeration: instantiate 'struct cxl_region' objects
     for platform firmware created memory regions

   - CXL RAM region provisioning: complement the existing PMEM region
     creation support with RAM region support

   - "Soft Reservation" policy change: Online (memory hot-add)
     soft-reserved memory (EFI_MEMORY_SP) by default, but still allow
     for setting aside such memory for dedicated access via device-dax.

   - CXL Events and Interrupts: Takeover CXL event handling from
     platform-firmware (ACPI calls this CXL Memory Error Reporting) and
     export CXL Events via Linux Trace Events.

   - Convey CXL _OSC results to drivers: Similar to PCI, let the CXL
     subsystem interrogate the result of CXL _OSC negotiation.

   - Emulate CXL DVSEC Range Registers as "decoders": Allow for
     first-generation devices that pre-date the definition of the CXL
     HDM Decoder Capability to translate the CXL DVSEC Range Registers
     into 'struct cxl_decoder' objects.

   - Set timestamp: Per spec, set the device timestamp in case of
     hotplug, or if platform-firwmare failed to set it.

   - General fixups: linux-next build issues, non-urgent fixes for
     pre-production hardware, unit test fixes, spelling and debug
     message improvements"

* tag 'cxl-for-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (66 commits)
  dax/kmem: Fix leak of memory-hotplug resources
  cxl/mem: Add kdoc param for event log driver state
  cxl/trace: Add serial number to trace points
  cxl/trace: Add host output to trace points
  cxl/trace: Standardize device information output
  cxl/pci: Remove locked check for dvsec_range_allowed()
  cxl/hdm: Add emulation when HDM decoders are not committed
  cxl/hdm: Create emulated cxl_hdm for devices that do not have HDM decoders
  cxl/hdm: Emulate HDM decoder from DVSEC range registers
  cxl/pci: Refactor cxl_hdm_decode_init()
  cxl/port: Export cxl_dvsec_rr_decode() to cxl_port
  cxl/pci: Break out range register decoding from cxl_hdm_decode_init()
  cxl: add RAS status unmasking for CXL
  cxl: remove unnecessary calling of pci_enable_pcie_error_reporting()
  dax/hmem: build hmem device support as module if possible
  dax: cxl: add CXL_REGION dependency
  cxl: avoid returning uninitialized error code
  cxl/pmem: Fix nvdimm registration races
  cxl/mem: Fix UAPI command comment
  cxl/uapi: Tag commands from cxl_query_cmd()
  ...

35 files changed, 3089 insertions, 552 deletions

diff --git a/drivers/Makefile b/drivers/Makefile
index b1a714686050..7d01fa2b2b7e 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -71,7 +71,7 @@ obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
 obj-$(CONFIG_PARPORT)		+= parport/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
-obj-$(CONFIG_DAX)		+= dax/
+obj-y				+= dax/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= cxl/
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 605a0c7053be..bba268ecd802 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -718,7 +718,7 @@ static void hmat_register_target_devices(struct memory_target *target)
 	for (res = target->memregions.child; res; res = res->sibling) {
 		int target_nid = pxm_to_node(target->memory_pxm);
 
-		hmem_register_device(target_nid, res);
+		hmem_register_resource(target_nid, res);
 	}
 }
 
@@ -869,4 +869,4 @@ out_put:
 	acpi_put_table(tbl);
 	return 0;
 }
-device_initcall(hmat_init);
+subsys_initcall(hmat_init);
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index b3c202d2a433..84030804a763 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -1047,6 +1047,9 @@ struct pci_bus *acpi_pci_root_create(struct acpi_pci_root *root,
 	if (!(root->osc_control_set & OSC_PCI_EXPRESS_DPC_CONTROL))
 		host_bridge->native_dpc = 0;
 
+	if (!(root->osc_ext_control_set & OSC_CXL_ERROR_REPORTING_CONTROL))
+		host_bridge->native_cxl_error = 0;
+
 	/*
 	 * Evaluate the "PCI Boot Configuration" _DSM Function.  If it
 	 * exists and returns 0, we must preserve any PCI resource
diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index 0ac53c422c31..ff4e78117b31 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -104,19 +104,29 @@ config CXL_SUSPEND
 	depends on SUSPEND && CXL_MEM
 
 config CXL_REGION
-	bool
+	bool "CXL: Region Support"
 	default CXL_BUS
 	# For MAX_PHYSMEM_BITS
 	depends on SPARSEMEM
 	select MEMREGION
 	select GET_FREE_REGION
+	help
+	  Enable the CXL core to enumerate and provision CXL regions. A CXL
+	  region is defined by one or more CXL expanders that decode a given
+	  system-physical address range. For CXL regions established by
+	  platform-firmware this option enables memory error handling to
+	  identify the devices participating in a given interleaved memory
+	  range. Otherwise, platform-firmware managed CXL is enabled by being
+	  placed in the system address map and does not need a driver.
+
+	  If unsure say 'y'
 
 config CXL_REGION_INVALIDATION_TEST
 	bool "CXL: Region Cache Management Bypass (TEST)"
 	depends on CXL_REGION
 	help
 	  CXL Region management and security operations potentially invalidate
-	  the content of CPU caches without notifiying those caches to
+	  the content of CPU caches without notifying those caches to
 	  invalidate the affected cachelines. The CXL Region driver attempts
 	  to invalidate caches when those events occur.  If that invalidation
 	  fails the region will fail to enable.  Reasons for cache
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index 13cde44c6086..7e1765b09e04 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -19,7 +19,7 @@ struct cxl_cxims_data {
 
 /*
  * Find a targets entry (n) in the host bridge interleave list.
- * CXL Specfication 3.0 Table 9-22
+ * CXL Specification 3.0 Table 9-22
  */
 static int cxl_xor_calc_n(u64 hpa, struct cxl_cxims_data *cximsd, int iw,
 			  int ig)
@@ -731,7 +731,8 @@ static void __exit cxl_acpi_exit(void)
 	cxl_bus_drain();
 }
 
-module_init(cxl_acpi_init);
+/* load before dax_hmem sees 'Soft Reserved' CXL ranges */
+subsys_initcall(cxl_acpi_init);
 module_exit(cxl_acpi_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 79c7257f4107..ca4ae31d8f57 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -3,6 +3,8 @@ obj-$(CONFIG_CXL_BUS) += cxl_core.o
 obj-$(CONFIG_CXL_SUSPEND) += suspend.o
 
 ccflags-y += -I$(srctree)/drivers/cxl
+CFLAGS_trace.o = -DTRACE_INCLUDE_PATH=. -I$(src)
+
 cxl_core-y := port.o
 cxl_core-y += pmem.o
 cxl_core-y += regs.o
@@ -10,4 +12,5 @@ cxl_core-y += memdev.o
 cxl_core-y += mbox.o
 cxl_core-y += pci.o
 cxl_core-y += hdm.o
+cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 8c04672dca56..cde475e13216 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -11,15 +11,18 @@ extern struct attribute_group cxl_base_attribute_group;
 
 #ifdef CONFIG_CXL_REGION
 extern struct device_attribute dev_attr_create_pmem_region;
+extern struct device_attribute dev_attr_create_ram_region;
 extern struct device_attribute dev_attr_delete_region;
 extern struct device_attribute dev_attr_region;
 extern const struct device_type cxl_pmem_region_type;
+extern const struct device_type cxl_dax_region_type;
 extern const struct device_type cxl_region_type;
 void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled);
 #define CXL_REGION_ATTR(x) (&dev_attr_##x.attr)
 #define CXL_REGION_TYPE(x) (&cxl_region_type)
 #define SET_CXL_REGION_ATTR(x) (&dev_attr_##x.attr),
 #define CXL_PMEM_REGION_TYPE(x) (&cxl_pmem_region_type)
+#define CXL_DAX_REGION_TYPE(x) (&cxl_dax_region_type)
 int cxl_region_init(void);
 void cxl_region_exit(void);
 #else
@@ -37,6 +40,7 @@ static inline void cxl_region_exit(void)
 #define CXL_REGION_TYPE(x) NULL
 #define SET_CXL_REGION_ATTR(x)
 #define CXL_PMEM_REGION_TYPE(x) NULL
+#define CXL_DAX_REGION_TYPE(x) NULL
 #endif
 
 struct cxl_send_command;
@@ -56,9 +60,6 @@ resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled);
 resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled);
 extern struct rw_semaphore cxl_dpa_rwsem;
 
-bool is_switch_decoder(struct device *dev);
-struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
-
 int cxl_memdev_init(void);
 void cxl_memdev_exit(void);
 void cxl_mbox_init(void);
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index dcc16d7cb8f3..45deda18ed32 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -101,11 +101,34 @@ static int map_hdm_decoder_regs(struct cxl_port *port, void __iomem *crb,
 				      BIT(CXL_CM_CAP_CAP_ID_HDM));
 }
 
+static struct cxl_hdm *devm_cxl_setup_emulated_hdm(struct cxl_port *port,
+						   struct cxl_endpoint_dvsec_info *info)
+{
+	struct device *dev = &port->dev;
+	struct cxl_hdm *cxlhdm;
+
+	if (!info->mem_enabled)
+		return ERR_PTR(-ENODEV);
+
+	cxlhdm = devm_kzalloc(dev, sizeof(*cxlhdm), GFP_KERNEL);
+	if (!cxlhdm)
+		return ERR_PTR(-ENOMEM);
+
+	cxlhdm->port = port;
+	cxlhdm->decoder_count = info->ranges;
+	cxlhdm->target_count = info->ranges;
+	dev_set_drvdata(&port->dev, cxlhdm);
+
+	return cxlhdm;
+}
+
 /**
  * devm_cxl_setup_hdm - map HDM decoder component registers
  * @port: cxl_port to map
+ * @info: cached DVSEC range register info
  */
-struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port)
+struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port,
+				   struct cxl_endpoint_dvsec_info *info)
 {
 	struct device *dev = &port->dev;
 	struct cxl_hdm *cxlhdm;
@@ -119,6 +142,9 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port)
 	cxlhdm->port = port;
 	crb = ioremap(port->component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE);
 	if (!crb) {
+		if (info && info->mem_enabled)
+			return devm_cxl_setup_emulated_hdm(port, info);
+
 		dev_err(dev, "No component registers mapped\n");
 		return ERR_PTR(-ENXIO);
 	}
@@ -279,7 +305,7 @@ success:
 	return 0;
 }
 
-static int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
+int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 				resource_size_t base, resource_size_t len,
 				resource_size_t skipped)
 {
@@ -295,6 +321,7 @@ static int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 
 	return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled);
 }
+EXPORT_SYMBOL_NS_GPL(devm_cxl_dpa_reserve, CXL);
 
 resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled)
 {
@@ -676,12 +703,71 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld)
 	port->commit_end--;
 	cxld->flags &= ~CXL_DECODER_F_ENABLE;
 
+	/* Userspace is now responsible for reconfiguring this decoder */
+	if (is_endpoint_decoder(&cxld->dev)) {
+		struct cxl_endpoint_decoder *cxled;
+
+		cxled = to_cxl_endpoint_decoder(&cxld->dev);
+		cxled->state = CXL_DECODER_STATE_MANUAL;
+	}
+
+	return 0;
+}
+
+static int cxl_setup_hdm_decoder_from_dvsec(struct cxl_port *port,
+					    struct cxl_decoder *cxld, int which,
+					    struct cxl_endpoint_dvsec_info *info)
+{
+	if (!is_cxl_endpoint(port))
+		return -EOPNOTSUPP;
+
+	if (!range_len(&info->dvsec_range[which]))
+		return -ENOENT;
+
+	cxld->target_type = CXL_DECODER_EXPANDER;
+	cxld->commit = NULL;
+	cxld->reset = NULL;
+	cxld->hpa_range = info->dvsec_range[which];
+
+	/*
+	 * Set the emulated decoder as locked pending additional support to
+	 * change the range registers at run time.
+	 */
+	cxld->flags |= CXL_DECODER_F_ENABLE | CXL_DECODER_F_LOCK;
+	port->commit_end = cxld->id;
+
 	return 0;
 }
 
+static bool should_emulate_decoders(struct cxl_port *port)
+{
+	struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev);
+	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
+	u32 ctrl;
+	int i;
+
+	if (!is_cxl_endpoint(cxlhdm->port))
+		return false;
+
+	if (!hdm)
+		return true;
+
+	/*
+	 * If any decoders are committed already, there should not be any
+	 * emulated DVSEC decoders.
+	 */
+	for (i = 0; i < cxlhdm->decoder_count; i++) {
+		ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i));
+		if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl))
+			return false;
+	}
+
+	return true;
+}
+
 static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 			    int *target_map, void __iomem *hdm, int which,
-			    u64 *dpa_base)
+			    u64 *dpa_base, struct cxl_endpoint_dvsec_info *info)
 {
 	struct cxl_endpoint_decoder *cxled = NULL;
 	u64 size, base, skip, dpa_size;
@@ -694,6 +780,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 		unsigned char target_id[8];
 	} target_list;
 
+	if (should_emulate_decoders(port))
+		return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info);
+
 	if (is_endpoint_decoder(&cxld->dev))
 		cxled = to_cxl_endpoint_decoder(&cxld->dev);
 
@@ -717,6 +806,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 		.end = base + size - 1,
 	};
 
+	if (cxled && !committed && range_len(&info->dvsec_range[which]))
+		return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info);
+
 	/* decoders are enabled if committed */
 	if (committed) {
 		cxld->flags |= CXL_DECODER_F_ENABLE;
@@ -783,21 +875,21 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 		return rc;
 	}
 	*dpa_base += dpa_size + skip;
+
+	cxled->state = CXL_DECODER_STATE_AUTO;
+
 	return 0;
 }
 
-/**
- * devm_cxl_enumerate_decoders - add decoder objects per HDM register set
- * @cxlhdm: Structure to populate with HDM capabilities
- */
-int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
+static void cxl_settle_decoders(struct cxl_hdm *cxlhdm)
 {
 	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
-	struct cxl_port *port = cxlhdm->port;
-	int i, committed;
-	u64 dpa_base = 0;
+	int committed, i;
 	u32 ctrl;
 
+	if (!hdm)
+		return;
+
 	/*
 	 * Since the register resource was recently claimed via request_region()
 	 * be careful about trusting the "not-committed" status until the commit
@@ -814,6 +906,22 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
 	/* ensure that future checks of committed can be trusted */
 	if (committed != cxlhdm->decoder_count)
 		msleep(20);
+}
+
+/**
+ * devm_cxl_enumerate_decoders - add decoder objects per HDM register set
+ * @cxlhdm: Structure to populate with HDM capabilities
+ * @info: cached DVSEC range register info
+ */
+int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
+				struct cxl_endpoint_dvsec_info *info)
+{
+	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
+	struct cxl_port *port = cxlhdm->port;
+	int i;
+	u64 dpa_base = 0;
+
+	cxl_settle_decoders(cxlhdm);
 
 	for (i = 0; i < cxlhdm->decoder_count; i++) {
 		int target_map[CXL_DECODER_MAX_INTERLEAVE] = { 0 };
@@ -826,7 +934,8 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
 			cxled = cxl_endpoint_decoder_alloc(port);
 			if (IS_ERR(cxled)) {
 				dev_warn(&port->dev,
-					 "Failed to allocate the decoder\n");
+					 "Failed to allocate decoder%d.%d\n",
+					 port->id, i);
 				return PTR_ERR(cxled);
 			}
 			cxld = &cxled->cxld;
@@ -836,21 +945,26 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
 			cxlsd = cxl_switch_decoder_alloc(port, target_count);
 			if (IS_ERR(cxlsd)) {
 				dev_warn(&port->dev,
-					 "Failed to allocate the decoder\n");
+					 "Failed to allocate decoder%d.%d\n",
+					 port->id, i);
 				return PTR_ERR(cxlsd);
 			}
 			cxld = &cxlsd->cxld;
 		}
 
-		rc = init_hdm_decoder(port, cxld, target_map, hdm, i, &dpa_base);
+		rc = init_hdm_decoder(port, cxld, target_map, 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);
 		if (rc) {
 			dev_warn(&port->dev,
-				 "Failed to add decoder to port\n");
+				 "Failed to add decoder%d.%d\n", port->id, i);
 			return rc;
 		}
 	}
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index b03fba212799..f2addb457172 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -3,11 +3,13 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/security.h>
 #include <linux/debugfs.h>
+#include <linux/ktime.h>
 #include <linux/mutex.h>
 #include <cxlmem.h>
 #include <cxl.h>
 
 #include "core.h"
+#include "trace.h"
 
 static bool cxl_raw_allow_all;
 
@@ -170,6 +172,12 @@ int cxl_internal_send_cmd(struct cxl_dev_state *cxlds,
 	out_size = mbox_cmd->size_out;
 	min_out = mbox_cmd->min_out;
 	rc = cxlds->mbox_send(cxlds, mbox_cmd);
+	/*
+	 * EIO is reserved for a payload size mismatch and mbox_send()
+	 * may not return this error.
+	 */
+	if (WARN_ONCE(rc == -EIO, "Bad return code: -EIO"))
+		return -ENXIO;
 	if (rc)
 		return rc;
 
@@ -445,9 +453,14 @@ int cxl_query_cmd(struct cxl_memdev *cxlmd,
 	 * structures.
 	 */
 	cxl_for_each_cmd(cmd) {
-		const struct cxl_command_info *info = &cmd->info;
+		struct cxl_command_info info = cmd->info;
 
-		if (copy_to_user(&q->commands[j++], info, sizeof(*info)))
+		if (test_bit(info.id, cxlmd->cxlds->enabled_cmds))
+			info.flags |= CXL_MEM_COMMAND_FLAG_ENABLED;
+		if (test_bit(info.id, cxlmd->cxlds->exclusive_cmds))
+			info.flags |= CXL_MEM_COMMAND_FLAG_EXCLUSIVE;
+
+		if (copy_to_user(&q->commands[j++], &info, sizeof(info)))
 			return -EFAULT;
 
 		if (j == n_commands)
@@ -550,9 +563,9 @@ int cxl_send_cmd(struct cxl_memdev *cxlmd, struct cxl_send_command __user *s)
 	return 0;
 }
 
-static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 size, u8 *out)
+static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 *size, u8 *out)
 {
-	u32 remaining = size;
+	u32 remaining = *size;
 	u32 offset = 0;
 
 	while (remaining) {
@@ -576,6 +589,17 @@ static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 size, u8
 		};
 
 		rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+
+		/*
+		 * The output payload length that indicates the number
+		 * of valid bytes can be smaller than the Log buffer
+		 * size.
+		 */
+		if (rc == -EIO && mbox_cmd.size_out < xfer_size) {
+			offset += mbox_cmd.size_out;
+			break;
+		}
+
 		if (rc < 0)
 			return rc;
 
@@ -584,6 +608,8 @@ static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 size, u8
 		offset += xfer_size;
 	}
 
+	*size = offset;
+
 	return 0;
 }
 
@@ -610,11 +636,12 @@ static void cxl_walk_cel(struct cxl_dev_state *cxlds, size_t size, u8 *cel)
 
 		if (!cmd) {
 			dev_dbg(cxlds->dev,
-				"Opcode 0x%04x unsupported by driver", opcode);
+				"Opcode 0x%04x unsupported by driver\n", opcode);
 			continue;
 		}
 
 		set_bit(cmd->info.id, cxlds->enabled_cmds);
+		dev_dbg(cxlds->dev, "Opcode 0x%04x enabled\n", opcode);
 	}
 }
 
@@ -694,7 +721,7 @@ int cxl_enumerate_cmds(struct cxl_dev_state *cxlds)
 			goto out;
 		}
 
-		rc = cxl_xfer_log(cxlds, &uuid, size, log);
+		rc = cxl_xfer_log(cxlds, &uuid, &size, log);
 		if (rc) {
 			kvfree(log);
 			goto out;
@@ -717,6 +744,203 @@ out:
 }
 EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL);
 
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+static const uuid_t gen_media_event_uuid =
+	UUID_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
+ */
+static const uuid_t dram_event_uuid =
+	UUID_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
+ */
+static const uuid_t mem_mod_event_uuid =
+	UUID_INIT(0xfe927475, 0xdd59, 0x4339,
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74);
+
+static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+				   enum cxl_event_log_type type,
+				   struct cxl_event_record_raw *record)
+{
+	uuid_t *id = &record->hdr.id;
+
+	if (uuid_equal(id, &gen_media_event_uuid)) {
+		struct cxl_event_gen_media *rec =
+				(struct cxl_event_gen_media *)record;
+
+		trace_cxl_general_media(cxlmd, type, rec);
+	} else if (uuid_equal(id, &dram_event_uuid)) {
+		struct cxl_event_dram *rec = (struct cxl_event_dram *)record;
+
+		trace_cxl_dram(cxlmd, type, rec);
+	} else if (uuid_equal(id, &mem_mod_event_uuid)) {
+		struct cxl_event_mem_module *rec =
+				(struct cxl_event_mem_module *)record;
+
+		trace_cxl_memory_module(cxlmd, type, rec);
+	} else {
+		/* For unknown record types print just the header */
+		trace_cxl_generic_event(cxlmd, type, record);
+	}
+}
+
+static int cxl_clear_event_record(struct cxl_dev_state *cxlds,
+				  enum cxl_event_log_type log,
+				  struct cxl_get_event_payload *get_pl)
+{
+	struct cxl_mbox_clear_event_payload *payload;
+	u16 total = le16_to_cpu(get_pl->record_count);
+	u8 max_handles = CXL_CLEAR_EVENT_MAX_HANDLES;
+	size_t pl_size = struct_size(payload, handles, max_handles);
+	struct cxl_mbox_cmd mbox_cmd;
+	u16 cnt;
+	int rc = 0;
+	int i;
+
+	/* Payload size may limit the max handles */
+	if (pl_size > cxlds->payload_size) {
+		max_handles = (cxlds->payload_size - sizeof(*payload)) /
+				sizeof(__le16);
+		pl_size = struct_size(payload, handles, max_handles);
+	}
+
+	payload = kvzalloc(pl_size, GFP_KERNEL);
+	if (!payload)
+		return -ENOMEM;
+
+	*payload = (struct cxl_mbox_clear_event_payload) {
+		.event_log = log,
+	};
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_CLEAR_EVENT_RECORD,
+		.payload_in = payload,
+		.size_in = pl_size,
+	};
+
+	/*
+	 * Clear Event Records uses u8 for the handle cnt while Get Event
+	 * Record can return up to 0xffff records.
+	 */
+	i = 0;
+	for (cnt = 0; cnt < total; cnt++) {
+		payload->handles[i++] = get_pl->records[cnt].hdr.handle;
+		dev_dbg(cxlds->dev, "Event log '%d': Clearing %u\n",
+			log, le16_to_cpu(payload->handles[i]));
+
+		if (i == max_handles) {
+			payload->nr_recs = i;
+			rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+			if (rc)
+				goto free_pl;
+			i = 0;
+		}
+	}
+
+	/* Clear what is left if any */
+	if (i) {
+		payload->nr_recs = i;
+		mbox_cmd.size_in = struct_size(payload, handles, i);
+		rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+		if (rc)
+			goto free_pl;
+	}
+
+free_pl:
+	kvfree(payload);
+	return rc;
+}
+
+static void cxl_mem_get_records_log(struct cxl_dev_state *cxlds,
+				    enum cxl_event_log_type type)
+{
+	struct cxl_get_event_payload *payload;
+	struct cxl_mbox_cmd mbox_cmd;
+	u8 log_type = type;
+	u16 nr_rec;
+
+	mutex_lock(&cxlds->event.log_lock);
+	payload = cxlds->event.buf;
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_GET_EVENT_RECORD,
+		.payload_in = &log_type,
+		.size_in = sizeof(log_type),
+		.payload_out = payload,
+		.size_out = cxlds->payload_size,
+		.min_out = struct_size(payload, records, 0),
+	};
+
+	do {
+		int rc, i;
+
+		rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+		if (rc) {
+			dev_err_ratelimited(cxlds->dev,
+				"Event log '%d': Failed to query event records : %d",
+				type, rc);
+			break;
+		}
+
+		nr_rec = le16_to_cpu(payload->record_count);
+		if (!nr_rec)
+			break;
+
+		for (i = 0; i < nr_rec; i++)
+			cxl_event_trace_record(cxlds->cxlmd, type,
+					       &payload->records[i]);
+
+		if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW)
+			trace_cxl_overflow(cxlds->cxlmd, type, payl