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

/*
 * 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>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version
 * 2 as published by the Free Software Foundation;
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 */

#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/kdebug.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/aer.h>
#include <linux/nmi.h>

#include <acpi/ghes.h>
#include <acpi/apei.h>
#include <asm/tlbflush.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))

/*
 * 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 SCI shares one notifier function,
 * so they need to be linked and checked one by one.  This is applied
 * to 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_sci);
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
 * a special version of atomic ioremap is implemented for that.
 */

/*
 * Two virtual pages are used, one for IRQ/PROCESS context, the other for
 * NMI context (optionally).
 */
#ifdef CONFIG_HAVE_ACPI_APEI_NMI
#define GHES_IOREMAP_PAGES           2
#else
#define GHES_IOREMAP_PAGES           1
#endif
#define GHES_IOREMAP_IRQ_PAGE(base)	(base)
#define GHES_IOREMAP_NMI_PAGE(base)	((base) + PAGE_SIZE)

/* virtual memory area for atomic ioremap */
static struct vm_struct *ghes_ioremap_area;
/*
 * These 2 spinlock is used to prevent atomic ioremap virtual memory
 * area from being mapped simultaneously.
 */
static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi);
static DEFINE_SPINLOCK(ghes_ioremap_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_ioremap_init(void)
{
	ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES,
		VM_IOREMAP, VMALLOC_START, VMALLOC_END);
	if (!ghes_ioremap_area) {
		pr_err(GHES_PFX "Failed to allocate virtual memory area for atomic ioremap.\n");
		return -ENOMEM;
	}

	return 0;
}

static void ghes_ioremap_exit(void)
{
	free_vm_area(ghes_ioremap_area);
}

static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn)
{
	unsigned long vaddr;

	vaddr = (unsigned long)GHES_IOREMAP_NMI_PAGE(ghes_ioremap_area->addr);
	ioremap_page_range(vaddr, vaddr + PAGE_SIZE,
			   pfn << PAGE_SHIFT, PAGE_KERNEL);

	return (void __iomem *)vaddr;
}

static void __iomem *ghes_ioremap_pfn_irq(u64 pfn)
{
	unsigned long vaddr, paddr;
	pgprot_t prot;

	vaddr = (unsigned long)GHES_IOREMAP_IRQ_PAGE(ghes_ioremap_area->addr);

	paddr = pfn << PAGE_SHIFT;
	prot = arch_apei_get_mem_attribute(paddr);

	ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot);

	return (void __iomem *)vaddr;
}

static void ghes_iounmap_nmi(void __iomem *vaddr_ptr)
{
	unsigned long vaddr = (unsigned long __force)vaddr_ptr;
	void *base = ghes_ioremap_area->addr;

	BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_NMI_PAGE(base));
	unmap_kernel_range_noflush(vaddr, PAGE_SIZE);
	arch_apei_flush_tlb_one(vaddr);
}

static void ghes_iounmap_irq(void __iomem *vaddr_ptr)
{
	unsigned long vaddr = (unsigned long __force)vaddr_ptr;
	void *base = ghes_ioremap_area->addr