1 files changed, 460 insertions, 116 deletions

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0c8330ed1ffd..0dc767392a6c 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -22,10 +22,12 @@
 #include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
+#include <linux/bitfield.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
 #include <linux/timer.h>
 #include <linux/cper.h>
+#include <linux/cleanup.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -33,6 +35,7 @@
 #include <linux/irq_work.h>
 #include <linux/llist.h>
 #include <linux/genalloc.h>
+#include <linux/kfifo.h>
 #include <linux/pci.h>
 #include <linux/pfn.h>
 #include <linux/aer.h>
@@ -41,12 +44,14 @@
 #include <linux/uuid.h>
 #include <linux/ras.h>
 #include <linux/task_work.h>
+#include <linux/vmcore_info.h>
 
 #include <acpi/actbl1.h>
 #include <acpi/ghes.h>
 #include <acpi/apei.h>
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
+#include <cxl/event.h>
 #include <ras/ras_event.h>
 
 #include "apei-internal.h"
@@ -94,12 +99,28 @@
 #define FIX_APEI_GHES_SDEI_CRITICAL	__end_of_fixed_addresses
 #endif
 
+static ATOMIC_NOTIFIER_HEAD(ghes_report_chain);
+
 static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 {
 	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
 }
 
 /*
+ * A platform may describe one error source for the handling of synchronous
+ * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
+ * or External Interrupt). On x86, the HEST notifications are always
+ * asynchronous, so only SEA on ARM is delivered as a synchronous
+ * notification.
+ */
+static inline bool is_hest_sync_notify(struct ghes *ghes)
+{
+	u8 notify_type = ghes->generic->notify.type;
+
+	return notify_type == ACPI_HEST_NOTIFY_SEA;
+}
+
+/*
  * This driver isn't really modular, however for the time being,
  * continuing to use module_param is the easiest way to remain
  * compatible with existing boot arg use cases.
@@ -108,6 +129,13 @@ bool ghes_disable;
 module_param_named(disable, ghes_disable, bool, 0);
 
 /*
+ * "ghes.edac_force_enable" forcibly enables ghes_edac and skips the platform
+ * check.
+ */
+static bool ghes_edac_force_enable;
+module_param_named(edac_force_enable, ghes_edac_force_enable, bool, 0);
+
+/*
  * All error sources notified with HED (Hardware Error Device) share a
  * single notifier callback, so they need to be linked and checked one
  * by one. This holds true for NMI too.
@@ -119,6 +147,13 @@ static LIST_HEAD(ghes_hed);
 static DEFINE_MUTEX(ghes_list_mutex);
 
 /*
+ * A list of GHES devices which are given to the corresponding EDAC driver
+ * ghes_edac for further use.
+ */
+static LIST_HEAD(ghes_devs);
+static DEFINE_MUTEX(ghes_devs_mutex);
+
+/*
  * Because the memory area used to transfer hardware error information
  * from BIOS to Linux can be determined only in NMI, IRQ or timer
  * handler, but general ioremap can not be used in atomic context, so
@@ -136,13 +171,10 @@ struct ghes_vendor_record_entry {
 };
 
 static struct gen_pool *ghes_estatus_pool;
-static unsigned long ghes_estatus_pool_size_request;
 
-static struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
+static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
 static atomic_t ghes_estatus_cache_alloced;
 
-static int ghes_panic_timeout __read_mostly = 30;
-
 static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
 {
 	phys_addr_t paddr;
@@ -163,7 +195,7 @@ static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx)
 	clear_fixmap(fixmap_idx);
 }
 
-int ghes_estatus_pool_init(int num_ghes)
+int ghes_estatus_pool_init(unsigned int num_ghes)
 {
 	unsigned long addr, len;
 	int rc;
@@ -175,7 +207,6 @@ int ghes_estatus_pool_init(int num_ghes)
 	len = GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX;
 	len += (num_ghes * GHES_ESOURCE_PREALLOC_MAX_SIZE);
 
-	ghes_estatus_pool_size_request = PAGE_ALIGN(len);
 	addr = (unsigned long)vmalloc(PAGE_ALIGN(len));
 	if (!addr)
 		goto err_pool_alloc;
@@ -195,6 +226,20 @@ err_pool_alloc:
 	return -ENOMEM;
 }
 
+/**
+ * ghes_estatus_pool_region_free - free previously allocated memory
+ *				   from the ghes_estatus_pool.
+ * @addr: address of memory to free.
+ * @size: size of memory to free.
+ *
+ * Returns none.
+ */
+void ghes_estatus_pool_region_free(unsigned long addr, u32 size)
+{
+	gen_pool_free(ghes_estatus_pool, addr, size);
+}
+EXPORT_SYMBOL_GPL(ghes_estatus_pool_region_free);
+
 static int map_gen_v2(struct ghes *ghes)
 {
 	return apei_map_generic_address(&ghes->generic_v2->read_ack_register);
@@ -421,39 +466,58 @@ static void ghes_clear_estatus(struct ghes *ghes,
 		ghes_ack_error(ghes->generic_v2);
 }
 
-/*
- * Called as task_work before returning to user-space.
- * Ensure any queued work has been done before we return to the context that
- * triggered the notification.
+/**
+ * struct ghes_task_work - for synchronous RAS event
+ *
+ * @twork:                callback_head for task work
+ * @pfn:                  page frame number of corrupted page
+ * @flags:                work control flags
+ *
+ * Structure to pass task work to be handled before
+ * returning to user-space via task_work_add().
  */
-static void ghes_kick_task_work(struct callback_head *head)
+struct ghes_task_work {
+	struct callback_head twork;
+	u64 pfn;
+	int flags;
+};
+
+static void memory_failure_cb(struct callback_head *twork)
 {
-	struct acpi_hest_generic_status *estatus;
-	struct ghes_estatus_node *estatus_node;
-	u32 node_len;
+	struct ghes_task_work *twcb = container_of(twork, struct ghes_task_work, twork);
+	int ret;
 
-	estatus_node = container_of(head, struct ghes_estatus_node, task_work);
-	if (IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
-		memory_failure_queue_kick(estatus_node->task_work_cpu);
+	ret = memory_failure(twcb->pfn, twcb->flags);
+	gen_pool_free(ghes_estatus_pool, (unsigned long)twcb, sizeof(*twcb));
 
-	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-	node_len = GHES_ESTATUS_NODE_LEN(cper_estatus_len(estatus));
-	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
+	if (!ret || ret == -EHWPOISON || ret == -EOPNOTSUPP)
+		return;
+
+	pr_err("%#llx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
+			twcb->pfn, current->comm, task_pid_nr(current));
+	force_sig(SIGBUS);
 }
 
 static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 {
+	struct ghes_task_work *twcb;
 	unsigned long pfn;
 
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
 		return false;
 
 	pfn = PHYS_PFN(physical_addr);
-	if (!pfn_valid(pfn)) {
-		pr_warn_ratelimited(FW_WARN GHES_PFX
-		"Invalid address in generic error data: %#llx\n",
-		physical_addr);
-		return false;
+
+	if (flags == MF_ACTION_REQUIRED && current->mm) {
+		twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb));
+		if (!twcb)
+			return false;
+
+		twcb->pfn = pfn;
+		twcb->flags = flags;
+		init_task_work(&twcb->twork, memory_failure_cb);
+		task_work_add(current, &twcb->twork, TWA_RESUME);
+		return true;
 	}
 
 	memory_failure_queue(pfn, flags);
@@ -461,7 +525,7 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 }
 
 static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
-				       int sev)
+				       int sev, bool sync)
 {
 	int flags = -1;
 	int sec_sev = ghes_severity(gdata->error_severity);
@@ -475,7 +539,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
 		flags = MF_SOFT_OFFLINE;
 	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
-		flags = 0;
+		flags = sync ? MF_ACTION_REQUIRED : 0;
 
 	if (flags != -1)
 		return ghes_do_memory_failure(mem_err->physical_addr, flags);
@@ -483,25 +547,26 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	return false;
 }
 
-static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
+static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
+				     int sev, bool sync)
 {
 	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
+	int flags = sync ? MF_ACTION_REQUIRED : 0;
+	char error_type[120];
 	bool queued = false;
 	int sec_sev, i;
 	char *p;
 
-	log_arm_hw_error(err);
-
 	sec_sev = ghes_severity(gdata->error_severity);
+	log_arm_hw_error(err, sec_sev);
 	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
 		return false;
 
 	p = (char *)(err + 1);
 	for (i = 0; i < err->err_info_num; i++) {
 		struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
-		bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
+		bool is_cache = err_info->type & CPER_ARM_CACHE_ERROR;
 		bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
-		const char *error_type = "unknown error";
 
 		/*
 		 * The field (err_info->error_info & BIT(26)) is fixed to set to
@@ -510,17 +575,20 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s
 		 * and don't filter out 'corrected' error here.
 		 */
 		if (is_cache && has_pa) {
-			queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0);
+			queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
 			p += err_info->length;
 			continue;
 		}
 
-		if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs))
-			error_type = cper_proc_error_type_strs[err_info->type];
+		cper_bits_to_str(error_type, sizeof(error_type),
+				 FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type),
+				 cper_proc_error_type_strs,
+				 ARRAY_SIZE(cper_proc_error_type_strs));
 
 		pr_warn_ratelimited(FW_WARN GHES_PFX
-				    "Unhandled processor error type: %s\n",
-				    error_type);
+				    "Unhandled processor error type 0x%02x: %s%s\n",
+				    err_info->type, error_type,
+				    (err_info->type & ~CPER_ARM_ERR_TYPE_MASK) ? " with reserved bit(s)" : "");
 		p += err_info->length;
 	}
 
@@ -550,6 +618,7 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
 	    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
 		unsigned int devfn;
 		int aer_severity;
+		u8 *aer_info;
 
 		devfn = PCI_DEVFN(pcie_err->device_id.device,
 				  pcie_err->device_id.function);
@@ -563,11 +632,17 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
 		if (gdata->flags & CPER_SEC_RESET)
 			aer_severity = AER_FATAL;
 
+		aer_info = (void *)gen_pool_alloc(ghes_estatus_pool,
+						  sizeof(struct aer_capability_regs));
+		if (!aer_info)
+			return;
+		memcpy(aer_info, pcie_err->aer_info, sizeof(struct aer_capability_regs));
+
 		aer_recover_queue(pcie_err->device_id.segment,
 				  pcie_err->device_id.bus,
 				  devfn, aer_severity,
 				  (struct aer_capability_regs *)
-				  pcie_err->aer_info);
+				  aer_info);
 	}
 #endif
 }
@@ -622,7 +697,209 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
-static bool ghes_do_proc(struct ghes *ghes,
+/* Room for 8 entries */
+#define CXL_CPER_PROT_ERR_FIFO_DEPTH 8
+static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
+		    CXL_CPER_PROT_ERR_FIFO_DEPTH);
+
+/* Synchronize schedule_work() with cxl_cper_prot_err_work changes */
+static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock);
+struct work_struct *cxl_cper_prot_err_work;
+
+static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+				   int severity)
+{
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	struct cxl_cper_prot_err_work_data wd;
+	u8 *dvsec_start, *cap_start;
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_AGENT_ADDRESS)) {
+		pr_err_ratelimited("CXL CPER invalid agent type\n");
+		return;
+	}
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_ERROR_LOG)) {
+		pr_err_ratelimited("CXL CPER invalid protocol error log\n");
+		return;
+	}
+
+	if (prot_err->err_len != sizeof(struct cxl_ras_capability_regs)) {
+		pr_err_ratelimited("CXL CPER invalid RAS Cap size (%u)\n",
+				   prot_err->err_len);
+		return;
+	}
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
+		pr_warn(FW_WARN "CXL CPER no device serial number\n");
+
+	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
+
+	if (!cxl_cper_prot_err_work)
+		return;
+
+	switch (prot_err->agent_type) {
+	case RCD:
+	case DEVICE:
+	case LD:
+	case FMLD:
+	case RP:
+	case DSP:
+	case USP:
+		memcpy(&wd.prot_err, prot_err, sizeof(wd.prot_err));
+
+		dvsec_start = (u8 *)(prot_err + 1);
+		cap_start = dvsec_start + prot_err->dvsec_len;
+
+		memcpy(&wd.ras_cap, cap_start, sizeof(wd.ras_cap));
+		wd.severity = cper_severity_to_aer(severity);
+		break;
+	default:
+		pr_err_ratelimited("CXL CPER invalid agent type: %d\n",
+				   prot_err->agent_type);
+		return;
+	}
+
+	if (!kfifo_put(&cxl_cper_prot_err_fifo, wd)) {
+		pr_err_ratelimited("CXL CPER kfifo overflow\n");
+		return;
+	}
+
+	schedule_work(cxl_cper_prot_err_work);
+#endif
+}
+
+int cxl_cper_register_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = work;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_prot_err_work, "CXL");
+
+int cxl_cper_unregister_prot_err_work(struct work_struct *work)
+{
+	if (cxl_cper_prot_err_work != work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_prot_err_work_lock);
+	cxl_cper_prot_err_work = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_prot_err_work, "CXL");
+
+int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data *wd)
+{
+	return kfifo_get(&cxl_cper_prot_err_fifo, wd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_prot_err_kfifo_get, "CXL");
+
+/* Room for 8 entries for each of the 4 event log queues */
+#define CXL_CPER_FIFO_DEPTH 32
+DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH);
+
+/* Synchronize schedule_work() with cxl_cper_work changes */
+static DEFINE_SPINLOCK(cxl_cper_work_lock);
+struct work_struct *cxl_cper_work;
+
+static void cxl_cper_post_event(enum cxl_event_type event_type,
+				struct cxl_cper_event_rec *rec)
+{
+	struct cxl_cper_work_data wd;
+
+	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(spinlock_irqsave)(&cxl_cper_work_lock);
+
+	if (!cxl_cper_work)
+		return;
+
+	wd.event_type = event_type;
+	memcpy(&wd.rec, rec, sizeof(wd.rec));
+
+	if (!kfifo_put(&cxl_cper_fifo, wd)) {
+		pr_err_ratelimited("CXL CPER kfifo overflow\n");
+		return;
+	}
+
+	schedule_work(cxl_cper_work);
+}
+
+int cxl_cper_register_work(struct work_struct *work)
+{
+	if (cxl_cper_work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_work_lock);
+	cxl_cper_work = work;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, "CXL");
+
+int cxl_cper_unregister_work(struct work_struct *work)
+{
+	if (cxl_cper_work != work)
+		return -EINVAL;
+
+	guard(spinlock)(&cxl_cper_work_lock);
+	cxl_cper_work = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, "CXL");
+
+int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
+{
+	return kfifo_get(&cxl_cper_fifo, wd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL");
+
+static void ghes_log_hwerr(int sev, guid_t *sec_type)
+{
+	if (sev != CPER_SEV_RECOVERABLE)
+		return;
+
+	if (guid_equal(sec_type, &CPER_SEC_PROC_ARM) ||
+	    guid_equal(sec_type, &CPER_SEC_PROC_GENERIC) ||
+	    guid_equal(sec_type, &CPER_SEC_PROC_IA)) {
+		hwerr_log_error_type(HWERR_RECOV_CPU);
+		return;
+	}
+
+	if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR) ||
+	    guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID) ||
+	    guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID) ||
+	    guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) {
+		hwerr_log_error_type(HWERR_RECOV_CXL);
+		return;
+	}
+
+	if (guid_equal(sec_type, &CPER_SEC_PCIE) ||
+	    guid_equal(sec_type, &CPER_SEC_PCI_X_BUS)) {
+		hwerr_log_error_type(HWERR_RECOV_PCI);
+		return;
+	}
+
+	if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
+		hwerr_log_error_type(HWERR_RECOV_MEMORY);
+		return;
+	}
+
+	hwerr_log_error_type(HWERR_RECOV_OTHERS);
+}
+
+static void ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
 	int sev, sec_sev;
@@ -631,6 +908,7 @@ static bool ghes_do_proc(struct ghes *ghes,
 	const guid_t *fru_id = &guid_null;
 	char *fru_text = "";
 	bool queued = false;
+	bool sync = is_hest_sync_notify(ghes);
 
 	sev = ghes_severity(estatus->error_severity);
 	apei_estatus_for_each_section(estatus, gdata) {
@@ -642,19 +920,34 @@ static bool ghes_do_proc(struct ghes *ghes,
 		if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
 			fru_text = gdata->fru_text;
 
+		ghes_log_hwerr(sev, sec_type);
 		if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
 			struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
 
-			ghes_edac_report_mem_error(sev, mem_err);
+			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
-			queued = ghes_handle_memory_failure(gdata, sev);
-		}
-		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
+			queued = ghes_handle_memory_failure(gdata, sev, sync);
+		} else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			ghes_handle_aer(gdata);
-		}
-		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
-			queued = ghes_handle_arm_hw_error(gdata, sev);
+		} 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_PROT_ERR)) {
+			struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_prot_err(prot_err, gdata->error_severity);
+		} 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);
 
@@ -665,7 +958,16 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 	}
 
-	return queued;
+	/*
+	 * If no memory failure work is queued for abnormal synchronous
+	 * errors, do a force kill.
+	 */
+	if (sync && !queued) {
+		dev_err(ghes->dev,
+			HW_ERR GHES_PFX "%s:%d: synchronous unrecoverable error (SIGBUS)\n",
+			current->comm, task_pid_nr(current));
+		force_sig(SIGBUS);
+	}
 }
 
 static void __ghes_print_estatus(const char *pfx,
@@ -773,48 +1075,42 @@ static struct ghes_estatus_cache *ghes_estatus_cache_alloc(
 	return cache;
 }
 
-static void ghes_estatus_cache_free(struct ghes_estatus_cache *cache)
+static void ghes_estatus_cache_rcu_free(struct rcu_head *head)
 {
+	struct ghes_estatus_cache *cache;
 	u32 len;
 
+	cache = container_of(head, struct ghes_estatus_cache, rcu);
 	len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache));
 	len = GHES_ESTATUS_CACHE_LEN(len);
 	gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len);
 	atomic_dec(&ghes_estatus_cache_alloced);
 }
 
-static void ghes_estatus_cache_rcu_free(struct rcu_head *head)
-{
-	struct ghes_estatus_cache *cache;
-
-	cache = container_of(head, struct ghes_estatus_cache, rcu);
-	ghes_estatus_cache_free(cache);
-}
-
-static void ghes_estatus_cache_add(
-	struct acpi_hest_generic *generic,
-	struct acpi_hest_generic_status *estatus)
+static void
+ghes_estatus_cache_add(struct acpi_hest_generic *generic,
+		       struct acpi_hest_generic_status *estatus)
 {
-	int i, slot = -1, count;
 	unsigned long long now, duration, period, max_period = 0;
-	struct ghes_estatus_cache *cache, *slot_cache = NULL, *new_cache;
+	struct ghes_estatus_cache *cache, *new_cache;
+	struct ghes_estatus_cache __rcu *victim;
+	int i, slot = -1, count;
 
 	new_cache = ghes_estatus_cache_alloc(generic, estatus);
-	if (new_cache == NULL)
+	if (!new_cache)
 		return;
+
 	rcu_read_lock();
 	now = sched_clock();
 	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
 		cache = rcu_dereference(ghes_estatus_caches[i]);
 		if (cache == NULL) {
 			slot = i;
-			slot_cache = NULL;
 			break;
 		}
 		duration = now - cache->time_in;
 		if (duration >= GHES_ESTATUS_IN_CACHE_MAX_NSEC) {
 			slot = i;
-			slot_cache = cache;
 			break;
 		}
 		count = atomic_read(&cache->count);
@@ -823,32 +1119,48 @@ static void ghes_estatus_cache_add(
 		if (period > max_period) {
 			max_period = period;
 			slot = i;
-			slot_cache = cache;
 		}
 	}
-	/* new_cache must be put into array after its contents are written */
-	smp_wmb();
-	if (slot != -1 && cmpxchg(ghes_estatus_caches + slot,
-				  slot_cache, new_cache) == slot_cache) {
-		if (slot_cache)
-			call_rcu(&slot_cache->rcu, ghes_estatus_cache_rcu_free);
-	} else
-		ghes_estatus_cache_free(new_cache);
 	rcu_read_unlock();
+
+	if (slot != -1) {
+		/*
+		 * Use release semantics to ensure that ghes_estatus_cached()
+		 * running on another CPU will see the updated cache fields if
+		 * it can see the new value of the pointer.
+		 */
+		victim = xchg_release(&ghes_estatus_caches[slot],
+				      RCU_INITIALIZER(new_cache));
+
+		/*
+		 * At this point, victim may point to a cached item different
+		 * from the one based on which we selected the slot. Instead of
+		 * going to the loop again to pick another slot, let's just
+		 * drop the other item anyway: this may cause a false cache
+		 * miss later on, but that won't cause any problems.
+		 */
+		if (victim)
+			call_rcu(&unrcu_pointer(victim)->rcu,
+				 ghes_estatus_cache_rcu_free);
+	}
 }
 
 static void __ghes_panic(struct ghes *ghes,
 			 struct acpi_hest_generic_status *estatus,
 			 u64 buf_paddr, enum fixed_addresses fixmap_idx)
 {
+	const char *msg = GHES_PFX "Fatal hardware error";
+
 	__ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
+
 	ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
 
-	/* reboot to log the error! */
 	if (!panic_timeout)
-		panic_timeout = ghes_panic_timeout;
-	panic("Fatal hardware error!");
+		pr_emerg("%s but panic disabled\n", msg);
+
+	panic(msg);
 }
 
 static int ghes_proc(struct ghes *ghes)
@@ -893,7 +1205,7 @@ static void ghes_add_timer(struct ghes *ghes)
 
 static void ghes_poll_func(struct timer_list *t)
 {
-	struct ghes *ghes = from_timer(ghes, t, timer);
+	struct ghes *ghes = timer_container_of(ghes, t, timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
@@ -926,12 +1238,10 @@ static int ghes_notify_hed(struct notifier_block *this, unsigned long event,
 	int ret = NOTIFY_DONE;
 
 	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
-	rcu_read_lock();
 	list_for_each_entry_rcu(ghes, &ghes_hed, list) {
 		if (!ghes_proc(ghes))
 			ret = NOTIFY_OK;
 	}
-	rcu_read_unlock();
 	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
 
 	return ret;
@@ -961,9 +1271,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
 	struct acpi_hest_generic_status *estatus;
-	bool task_work_pending;
 	u32 len, node_len;
-	int ret;
 
 	llnode = llist_del_all(&ghes_estatus_llist);
 	/*
@@ -978,25 +1286,16 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 		len = cper_estatus_len(estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
-		task_work_pending = ghes_do_proc(estatus_node->ghes, estatus);
+
+		ghes_do_proc(estatus_node->ghes, estatus);
+
 		if (!ghes_estatus_cached(estatus)) {
 			generic = estatus_node->generic;
 			if (ghes_print_estatus(NULL, generic, estatus))
 				ghes_estatus_cache_add(generic, estatus);
 		}
-
-		if (task_work_pending && current->mm != &init_mm) {
-			estatus_node->task_work.func = ghes_kick_task_work;
-			estatus_node->task_work_cpu = smp_processor_id();
-			ret = task_work_add(current, &estatus_node->task_work,
-					    TWA_RESUME);
-			if (ret)
-				estatus_node->task_work.func = NULL;
-		}
-
-		if (!estatus_node->task_work.func)
-			gen_pool_free(ghes_estatus_pool,
-				      (unsigned long)estatus_node, node_len);
+		gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
+			      node_len);
 
 		llnode = next;
 	}
@@ -1057,7 +1356,6 @@ static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
 
 	estatus_node->ghes = ghes;
 	estatus_node->generic = ghes->generic;
-	estatus_node->task_work.func = NULL;
 	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 
 	if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {
@@ -1376,7 +1674,11 @@ static int ghes_probe(struct platform_device *ghes_dev)
 
 	platform_set_drvdata(ghes_dev, ghes);
 
-	ghes_edac_register(ghes, &ghes_dev->dev);
+	ghes->dev = &ghes_dev->dev;
+
+	mutex_lock(&ghes_devs_mutex);
+	list_add_tail(&ghes->elist, &ghes_devs);
+	mutex_unlock(&ghes_devs_mutex);
 
 	/* Handle any pending errors right away */
 	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
@@ -1393,7 +1695,7 @@ err:
 	return rc;
 }
 
-static int ghes_remove(struct platform_device *ghes_dev)
+static void ghes_remove(struct platform_device *ghes_dev)
 {
 	int rc;
 	struct ghes *ghes;
@@ -1405,7 +1707,7 @@ static int ghes_remove(struct platform_device *ghes_dev)
 	ghes->flags |= GHES_EXITING;
 	switch (generic->notify.type) {
 	case ACPI_HEST_NOTIFY_POLLED:
-		del_timer_sync(&ghes->timer);
+		timer_shutdown_sync(&ghes->timer);
 		break;
 	case ACPI_HEST_NOTIFY_EXTERNAL:
 		free_irq(ghes->irq, ghes);
@@ -1430,8 +1732,15 @@ static int ghes_remove(struct platform_device *ghes_dev)
 		break;
 	case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
 		rc = apei_sdei_unregister_ghes(ghes);
-		if (rc)
-			return rc;
+		if (rc) {
+			/*
+			 * Returning early results in a resource leak, but we're
+			 * only here if stopping the hardware failed.
+			 */
+			dev_err(&ghes_dev->dev, "Failed to unregister ghes (%pe)\n",
+				ERR_PTR(rc));
+			return;
+		}
 		break;
 	default:
 		BUG();
@@ -1440,13 +1749,11 @@ static int ghes_remove(struct platform_device *ghes_dev)
 
 	ghes_fini(ghes);
 
-	ghes_edac_unregister(ghes);
+	mutex_lock(&ghes_devs_mutex);
+	list_del(&ghes->elist);
+	mutex_unlock(&ghes_devs_mutex);
 
 	kfree(ghes);
-
-	platform_set_drvdata(ghes_dev, NULL);
-
-	return 0;
 }
 
 static struct platform_driver ghes_platform_driver = {
@@ -1457,33 +1764,35 @@ static struct platform_driver ghes_platform_driver = {
 	.remove		= ghes_remove,
 };
 
-static int __init ghes_init(void)
+void __init acpi_ghes_init(void)
 {
 	int rc;
 
+	acpi_sdei_init();
+
 	if (acpi_disabled)
-		return -ENODEV;
+		return;
 
 	switch (hest_disable) {
 	case HEST_NOT_FOUND:
-		return -ENODEV;
+		return;
 	case HEST_DISABLED:
 		pr_info(GHES_PFX "HEST is not enabled!\n");
-		return -EINVAL;
+		return;
 	default:
 		break;
 	}
 
 	if (ghes_disable) {
 		pr_info(GHES_PFX "GHES is not enabled!\n");
-		return -EINVAL;
+		return;
 	}
 
 	ghes_nmi_init_cxt();
 
 	rc = platform_driver_register(&ghes_platform_driver);
 	if (rc)
-		goto err;
+		return;
 
 	rc = apei_osc_setup();
 	if (rc == 0 && osc_sb_apei_support_acked)
@@ -1494,9 +1803,44 @@ static int __init ghes_init(void)
 		pr_info(GHES_PFX "APEI firmware first mode is enabled by APEI bit.\n");
 	else
 		pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");
+}
 
-	return 0;
-err:
-	return rc;
+/*
+ * Known x86 systems that prefer GHES error reporting:
+ */
+static struct acpi_platform_list plat_list[] = {
+	{"HPE   ", "Server  ", 0, ACPI_SIG_FADT, all_versions},
+	{ } /* End */
+};
+
+struct list_head *ghes_get_devices(void)
+{
+	int idx = -1;
+
+	if (IS_ENABLED(CONFIG_X86)) {
+		idx = acpi_match_platform_list(plat_list);
+		if (idx < 0) {
+			if (!ghes_edac_force_enable)
+				return NULL;
+
+			pr_warn_once("Force-loading ghes_edac on an unsupported platform. You're on your own!\n");
+		}
+	} else if (list_empty(&ghes_devs)) {
+		return NULL;
+	}
+
+	return &ghes_devs;
+}
+EXPORT_SYMBOL_GPL(ghes_get_devices);
+
+void ghes_register_report_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_register(&ghes_report_chain, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_register_report_chain);
+
+void ghes_unregister_report_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_unregister(&ghes_report_chain, nb);
 }
-device_initcall(ghes_init);
+EXPORT_SYMBOL_GPL(ghes_unregister_report_chain);