forked from Minki/linux
09ffcb0d71
This is a fix against the issue that crash dump kernel may hang up
during booting, which can happen on any ACPI-based system with "ACPI
Reclaim Memory."
(kernel messages after panic kicked off kdump)
(snip...)
Bye!
(snip...)
ACPI: Core revision 20170728
pud=000000002e7d0003, *pmd=000000002e7c0003, *pte=00e8000039710707
Internal error: Oops: 96000021 [#1] SMP
Modules linked in:
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.14.0-rc6 #1
task: ffff000008d05180 task.stack: ffff000008cc0000
PC is at acpi_ns_lookup+0x25c/0x3c0
LR is at acpi_ds_load1_begin_op+0xa4/0x294
(snip...)
Process swapper/0 (pid: 0, stack limit = 0xffff000008cc0000)
Call trace:
(snip...)
[<ffff0000084a6764>] acpi_ns_lookup+0x25c/0x3c0
[<ffff00000849b4f8>] acpi_ds_load1_begin_op+0xa4/0x294
[<ffff0000084ad4ac>] acpi_ps_build_named_op+0xc4/0x198
[<ffff0000084ad6cc>] acpi_ps_create_op+0x14c/0x270
[<ffff0000084acfa8>] acpi_ps_parse_loop+0x188/0x5c8
[<ffff0000084ae048>] acpi_ps_parse_aml+0xb0/0x2b8
[<ffff0000084a8e10>] acpi_ns_one_complete_parse+0x144/0x184
[<ffff0000084a8e98>] acpi_ns_parse_table+0x48/0x68
[<ffff0000084a82cc>] acpi_ns_load_table+0x4c/0xdc
[<ffff0000084b32f8>] acpi_tb_load_namespace+0xe4/0x264
[<ffff000008baf9b4>] acpi_load_tables+0x48/0xc0
[<ffff000008badc20>] acpi_early_init+0x9c/0xd0
[<ffff000008b70d50>] start_kernel+0x3b4/0x43c
Code: b9008fb9 2a000318 36380054 32190318 (b94002c0)
---[ end trace c46ed37f9651c58e ]---
Kernel panic - not syncing: Fatal exception
Rebooting in 10 seconds..
(diagnosis)
* This fault is a data abort, alignment fault (ESR=0x96000021)
during reading out ACPI table.
* Initial ACPI tables are normally stored in system ram and marked as
"ACPI Reclaim memory" by the firmware.
* After the commit f56ab9a5b7
("efi/arm: Don't mark ACPI reclaim
memory as MEMBLOCK_NOMAP"), those regions are differently handled
as they are "memblock-reserved", without NOMAP bit.
* So they are now excluded from device tree's "usable-memory-range"
which kexec-tools determines based on a current view of /proc/iomem.
* When crash dump kernel boots up, it tries to accesses ACPI tables by
mapping them with ioremap(), not ioremap_cache(), in acpi_os_ioremap()
since they are no longer part of mapped system ram.
* Given that ACPI accessor/helper functions are compiled in without
unaligned access support (ACPI_MISALIGNMENT_NOT_SUPPORTED),
any unaligned access to ACPI tables can cause a fatal panic.
With this patch, acpi_os_ioremap() always honors memory attribute
information provided by the firmware (EFI) and retaining cacheability
allows the kernel safe access to ACPI tables.
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reported-by and Tested-by: Bhupesh Sharma <bhsharma@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
260 lines
6.9 KiB
C
260 lines
6.9 KiB
C
/*
|
|
* ARM64 Specific Low-Level ACPI Boot Support
|
|
*
|
|
* Copyright (C) 2013-2014, Linaro Ltd.
|
|
* Author: Al Stone <al.stone@linaro.org>
|
|
* Author: Graeme Gregory <graeme.gregory@linaro.org>
|
|
* Author: Hanjun Guo <hanjun.guo@linaro.org>
|
|
* Author: Tomasz Nowicki <tomasz.nowicki@linaro.org>
|
|
* Author: Naresh Bhat <naresh.bhat@linaro.org>
|
|
*
|
|
* 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.
|
|
*/
|
|
|
|
#define pr_fmt(fmt) "ACPI: " fmt
|
|
|
|
#include <linux/acpi.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/efi.h>
|
|
#include <linux/efi-bgrt.h>
|
|
#include <linux/init.h>
|
|
#include <linux/irq.h>
|
|
#include <linux/irqdomain.h>
|
|
#include <linux/memblock.h>
|
|
#include <linux/of_fdt.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/serial_core.h>
|
|
|
|
#include <asm/cputype.h>
|
|
#include <asm/cpu_ops.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/smp_plat.h>
|
|
|
|
int acpi_noirq = 1; /* skip ACPI IRQ initialization */
|
|
int acpi_disabled = 1;
|
|
EXPORT_SYMBOL(acpi_disabled);
|
|
|
|
int acpi_pci_disabled = 1; /* skip ACPI PCI scan and IRQ initialization */
|
|
EXPORT_SYMBOL(acpi_pci_disabled);
|
|
|
|
static bool param_acpi_off __initdata;
|
|
static bool param_acpi_on __initdata;
|
|
static bool param_acpi_force __initdata;
|
|
|
|
static int __init parse_acpi(char *arg)
|
|
{
|
|
if (!arg)
|
|
return -EINVAL;
|
|
|
|
/* "acpi=off" disables both ACPI table parsing and interpreter */
|
|
if (strcmp(arg, "off") == 0)
|
|
param_acpi_off = true;
|
|
else if (strcmp(arg, "on") == 0) /* prefer ACPI over DT */
|
|
param_acpi_on = true;
|
|
else if (strcmp(arg, "force") == 0) /* force ACPI to be enabled */
|
|
param_acpi_force = true;
|
|
else
|
|
return -EINVAL; /* Core will print when we return error */
|
|
|
|
return 0;
|
|
}
|
|
early_param("acpi", parse_acpi);
|
|
|
|
static int __init dt_scan_depth1_nodes(unsigned long node,
|
|
const char *uname, int depth,
|
|
void *data)
|
|
{
|
|
/*
|
|
* Ignore anything not directly under the root node; we'll
|
|
* catch its parent instead.
|
|
*/
|
|
if (depth != 1)
|
|
return 0;
|
|
|
|
if (strcmp(uname, "chosen") == 0)
|
|
return 0;
|
|
|
|
if (strcmp(uname, "hypervisor") == 0 &&
|
|
of_flat_dt_is_compatible(node, "xen,xen"))
|
|
return 0;
|
|
|
|
/*
|
|
* This node at depth 1 is neither a chosen node nor a xen node,
|
|
* which we do not expect.
|
|
*/
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* __acpi_map_table() will be called before page_init(), so early_ioremap()
|
|
* or early_memremap() should be called here to for ACPI table mapping.
|
|
*/
|
|
void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size)
|
|
{
|
|
if (!size)
|
|
return NULL;
|
|
|
|
return early_memremap(phys, size);
|
|
}
|
|
|
|
void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
|
|
{
|
|
if (!map || !size)
|
|
return;
|
|
|
|
early_memunmap(map, size);
|
|
}
|
|
|
|
bool __init acpi_psci_present(void)
|
|
{
|
|
return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT;
|
|
}
|
|
|
|
/* Whether HVC must be used instead of SMC as the PSCI conduit */
|
|
bool acpi_psci_use_hvc(void)
|
|
{
|
|
return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC;
|
|
}
|
|
|
|
/*
|
|
* acpi_fadt_sanity_check() - Check FADT presence and carry out sanity
|
|
* checks on it
|
|
*
|
|
* Return 0 on success, <0 on failure
|
|
*/
|
|
static int __init acpi_fadt_sanity_check(void)
|
|
{
|
|
struct acpi_table_header *table;
|
|
struct acpi_table_fadt *fadt;
|
|
acpi_status status;
|
|
int ret = 0;
|
|
|
|
/*
|
|
* FADT is required on arm64; retrieve it to check its presence
|
|
* and carry out revision and ACPI HW reduced compliancy tests
|
|
*/
|
|
status = acpi_get_table(ACPI_SIG_FADT, 0, &table);
|
|
if (ACPI_FAILURE(status)) {
|
|
const char *msg = acpi_format_exception(status);
|
|
|
|
pr_err("Failed to get FADT table, %s\n", msg);
|
|
return -ENODEV;
|
|
}
|
|
|
|
fadt = (struct acpi_table_fadt *)table;
|
|
|
|
/*
|
|
* Revision in table header is the FADT Major revision, and there
|
|
* is a minor revision of FADT which was introduced by ACPI 5.1,
|
|
* we only deal with ACPI 5.1 or newer revision to get GIC and SMP
|
|
* boot protocol configuration data.
|
|
*/
|
|
if (table->revision < 5 ||
|
|
(table->revision == 5 && fadt->minor_revision < 1)) {
|
|
pr_err("Unsupported FADT revision %d.%d, should be 5.1+\n",
|
|
table->revision, fadt->minor_revision);
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) {
|
|
pr_err("FADT not ACPI hardware reduced compliant\n");
|
|
ret = -EINVAL;
|
|
}
|
|
|
|
out:
|
|
/*
|
|
* acpi_get_table() creates FADT table mapping that
|
|
* should be released after parsing and before resuming boot
|
|
*/
|
|
acpi_put_table(table);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* acpi_boot_table_init() called from setup_arch(), always.
|
|
* 1. find RSDP and get its address, and then find XSDT
|
|
* 2. extract all tables and checksums them all
|
|
* 3. check ACPI FADT revision
|
|
* 4. check ACPI FADT HW reduced flag
|
|
*
|
|
* We can parse ACPI boot-time tables such as MADT after
|
|
* this function is called.
|
|
*
|
|
* On return ACPI is enabled if either:
|
|
*
|
|
* - ACPI tables are initialized and sanity checks passed
|
|
* - acpi=force was passed in the command line and ACPI was not disabled
|
|
* explicitly through acpi=off command line parameter
|
|
*
|
|
* ACPI is disabled on function return otherwise
|
|
*/
|
|
void __init acpi_boot_table_init(void)
|
|
{
|
|
/*
|
|
* Enable ACPI instead of device tree unless
|
|
* - ACPI has been disabled explicitly (acpi=off), or
|
|
* - the device tree is not empty (it has more than just a /chosen node,
|
|
* and a /hypervisor node when running on Xen)
|
|
* and ACPI has not been [force] enabled (acpi=on|force)
|
|
*/
|
|
if (param_acpi_off ||
|
|
(!param_acpi_on && !param_acpi_force &&
|
|
of_scan_flat_dt(dt_scan_depth1_nodes, NULL)))
|
|
goto done;
|
|
|
|
/*
|
|
* ACPI is disabled at this point. Enable it in order to parse
|
|
* the ACPI tables and carry out sanity checks
|
|
*/
|
|
enable_acpi();
|
|
|
|
/*
|
|
* If ACPI tables are initialized and FADT sanity checks passed,
|
|
* leave ACPI enabled and carry on booting; otherwise disable ACPI
|
|
* on initialization error.
|
|
* If acpi=force was passed on the command line it forces ACPI
|
|
* to be enabled even if its initialization failed.
|
|
*/
|
|
if (acpi_table_init() || acpi_fadt_sanity_check()) {
|
|
pr_err("Failed to init ACPI tables\n");
|
|
if (!param_acpi_force)
|
|
disable_acpi();
|
|
}
|
|
|
|
done:
|
|
if (acpi_disabled) {
|
|
if (earlycon_acpi_spcr_enable)
|
|
early_init_dt_scan_chosen_stdout();
|
|
} else {
|
|
acpi_parse_spcr(earlycon_acpi_spcr_enable, true);
|
|
if (IS_ENABLED(CONFIG_ACPI_BGRT))
|
|
acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
|
|
}
|
|
}
|
|
|
|
pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
|
|
{
|
|
/*
|
|
* According to "Table 8 Map: EFI memory types to AArch64 memory
|
|
* types" of UEFI 2.5 section 2.3.6.1, each EFI memory type is
|
|
* mapped to a corresponding MAIR attribute encoding.
|
|
* The EFI memory attribute advises all possible capabilities
|
|
* of a memory region. We use the most efficient capability.
|
|
*/
|
|
|
|
u64 attr;
|
|
|
|
attr = efi_mem_attributes(addr);
|
|
if (attr & EFI_MEMORY_WB)
|
|
return PAGE_KERNEL;
|
|
if (attr & EFI_MEMORY_WT)
|
|
return __pgprot(PROT_NORMAL_WT);
|
|
if (attr & EFI_MEMORY_WC)
|
|
return __pgprot(PROT_NORMAL_NC);
|
|
return __pgprot(PROT_DEVICE_nGnRnE);
|
|
}
|