1 files changed, 195 insertions, 8 deletions

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 512067cac170..f0584ccad451 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/cleanup.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -33,6 +34,7 @@
 #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>
@@ -47,6 +49,7 @@
 #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"
@@ -170,8 +173,6 @@ 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;
@@ -673,6 +674,174 @@ 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);
+
+/* 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 bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -707,6 +876,22 @@ 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_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);
 
@@ -899,14 +1084,16 @@ 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);
 
 	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)
@@ -951,7 +1138,7 @@ 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);
@@ -1521,14 +1708,14 @@ static struct platform_driver ghes_platform_driver = {
 		.name	= "GHES",
 	},
 	.probe		= ghes_probe,
-	.remove_new	= ghes_remove,
+	.remove		= ghes_remove,
 };
 
 void __init acpi_ghes_init(void)
 {
 	int rc;
 
-	sdei_init();
+	acpi_sdei_init();
 
 	if (acpi_disabled)
 		return;