path: root/drivers/acpi/apei/ghes.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * APEI Generic Hardware Error Source support
 *
 * Generic Hardware Error Source provides a way to report platform
 * hardware errors (such as that from chipset). It works in so called
 * "Firmware First" mode, that is, hardware errors are reported to
 * firmware firstly, then reported to Linux by firmware. This way,
 * some non-standard hardware error registers or non-standard hardware
 * link can be checked by firmware to produce more hardware error
 * information for Linux.
 *
 * For more information about Generic Hardware Error Source, please
 * refer to ACPI Specification version 4.0, section 17.3.2.6
 *
 * Copyright 2010,2011 Intel Corp.
 *   Author: Huang Ying <ying.huang@intel.com>
 */

#include <linux/arm_sdei.h>
#include <linux/kernel.h>
#include <linux/moduleparam.h>
#include <linux/init.h>
#include <linux/acpi.h>
#include <linux/io.h>
#include <linux/interrupt.h>
#include <linux/timer.h>
#include <linux/cper.h>
#include <linux/platform_device.h>
#include <linux/mutex.h>
#include <linux/ratelimit.h>
#include <linux/vmalloc.h>
#include <linux/irq_work.h>
#include <linux/llist.h>
#include <linux/genalloc.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/aer.h>
#include <linux/nmi.h>
#include <linux/sched/clock.h>
#include <linux/uuid.h>
#include <linux/ras.h>

#include <acpi/actbl1.h>
#include <acpi/ghes.h>
#include <acpi/apei.h>
#include <asm/fixmap.h>
#include <asm/tlbflush.h>
#include <ras/ras_event.h>

#include "apei-internal.h"

#define GHES_PFX	"GHES: "

#define GHES_ESTATUS_MAX_SIZE		65536
#define GHES_ESOURCE_PREALLOC_MAX_SIZE	65536

#define GHES_ESTATUS_POOL_MIN_ALLOC_ORDER 3

/* This is just an estimation for memory pool allocation */
#define GHES_ESTATUS_CACHE_AVG_SIZE	512

#define GHES_ESTATUS_CACHES_SIZE	4

#define GHES_ESTATUS_IN_CACHE_MAX_NSEC	10000000000ULL
/* Prevent too many caches are allocated because of RCU */
#define GHES_ESTATUS_CACHE_ALLOCED_MAX	(GHES_ESTATUS_CACHES_SIZE * 3 / 2)

#define GHES_ESTATUS_CACHE_LEN(estatus_len)			\
	(sizeof(struct ghes_estatus_cache) + (estatus_len))
#define GHES_ESTATUS_FROM_CACHE(estatus_cache)			\
	((struct acpi_hest_generic_status *)				\
	 ((struct ghes_estatus_cache *)(estatus_cache) + 1))

#define GHES_ESTATUS_NODE_LEN(estatus_len)			\
	(sizeof(struct ghes_estatus_node) + (estatus_len))
#define GHES_ESTATUS_FROM_NODE(estatus_node)			\
	((struct acpi_hest_generic_status *)				\
	 ((struct ghes_estatus_node *)(estatus_node) + 1))

/*
 *  NMI-like notifications vary by architecture, before the compiler can prune
 *  unused static functions it needs a value for these enums.
 */
#ifndef CONFIG_ARM_SDE_INTERFACE
#define FIX_APEI_GHES_SDEI_NORMAL	__end_of_fixed_addresses
#define FIX_APEI_GHES_SDEI_CRITICAL	__end_of_fixed_addresses
#endif

static inline bool is_hest_type_generic_v2(struct ghes *ghes)
{
	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
}

/*
 * 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.
 */
bool ghes_disable;
module_param_named(disable, ghes_disable, 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.
 *
 * RCU is used for these lists, so ghes_list_mutex is only used for
 * list changing, not for traversing.
 */
static LIST_HEAD(ghes_hed);
static DEFINE_MUTEX(ghes_list_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
 * the fixmap is used instead.
 *
 * This spinlock is used to prevent the fixmap entry from being used
 * simultaneously.
 */
static DEFINE_SPINLOCK(ghes_notify_lock_irq);

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 atomic_t ghes_estatus_cache_alloced;

static int ghes_panic_timeout __read_mostly = 30</