1 files changed, 219 insertions, 63 deletions

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index a2491905f165..0dc767392a6c 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -22,6 +22,7 @@
 #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>
@@ -43,6 +44,7 @@
 #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>
@@ -173,8 +175,6 @@ static struct gen_pool *ghes_estatus_pool;
 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;
@@ -466,39 +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) && !arch_is_platform_page(physical_addr)) {
-		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);
@@ -529,26 +548,25 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 }
 
 static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
-				       int sev, bool sync)
+				     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
@@ -562,12 +580,15 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 			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;
 	}
 
@@ -676,6 +697,105 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+/* 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);
@@ -726,7 +846,7 @@ int cxl_cper_register_work(struct work_struct *work)
 	cxl_cper_work = work;
 	return 0;
 }
-EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, CXL);
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, "CXL");
 
 int cxl_cper_unregister_work(struct work_struct *work)
 {
@@ -737,15 +857,49 @@ int cxl_cper_unregister_work(struct work_struct *work)
 	cxl_cper_work = NULL;
 	return 0;
 }
-EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, CXL);
+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);
+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;
+	}
 
-static bool ghes_do_proc(struct ghes *ghes,
+	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;
@@ -766,6 +920,7 @@ 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);
 
@@ -773,12 +928,14 @@ static bool ghes_do_proc(struct ghes *ghes,
 
 			arch_apei_report_mem_error(sev, mem_err);
 			queued = ghes_handle_memory_failure(gdata, sev, sync);
-		}
-		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
+		} else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			ghes_handle_aer(gdata);
-		}
-		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
+		} 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);
 
@@ -801,7 +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,
@@ -983,14 +1149,18 @@ 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)
@@ -1035,7 +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);
@@ -1068,12 +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;
@@ -1103,9 +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);
 	/*
@@ -1120,25 +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) {
-			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;
 	}
@@ -1199,7 +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)) {
@@ -1612,7 +1768,7 @@ void __init acpi_ghes_init(void)
 {
 	int rc;
 
-	sdei_init();
+	acpi_sdei_init();
 
 	if (acpi_disabled)
 		return;