On 25 April 2018 at 11:06, AKASHI Takahiro <takahiro.aka...@linaro.org> wrote:
> Ard,
>
> On Wed, Apr 25, 2018 at 10:09:26AM +0200, Ard Biesheuvel wrote:
>> On 25 April 2018 at 08:35, AKASHI Takahiro <takahiro.aka...@linaro.org>
>> wrote:
>> > 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 f56ab9a5b73c ("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 a memory attribute
>> > provided by the firmware (efi). Hence retaining cacheability in said cases
>> > allows the kernel safe access to ACPI tables.
>> >
>> > Please note that arm_enable_runtime_services(), which is renamed to
>> > efi_enter_virtual_mode() due to the similarity to x86's, is now called
>> > earlier before acpi_early_init() since efi_mem_attributes() relies on
>> > efi.memmap being mapped.
>> >
>> > Signed-off-by: AKASHI Takahiro <takahiro.aka...@linaro.org>
>> > Suggested-by: James Morse <james.mo...@arm.com>
>> > Suggested-by: Ard Biesheuvel <ard.biesheu...@linaro.org>
>> > Reported-by and Tested-by: Bhupesh Sharma <bhsha...@redhat.com>
>> > ---
>> > arch/arm64/include/asm/acpi.h | 23 ++++++++++++++++-------
>> > arch/arm64/kernel/acpi.c | 11 +++--------
>> > drivers/firmware/efi/arm-runtime.c | 15 ++++++---------
>> > init/main.c | 3 +++
>> > 4 files changed, 28 insertions(+), 24 deletions(-)
>> >
>> > diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
>> > index 32f465a80e4e..d53c95f4e1a9 100644
>> > --- a/arch/arm64/include/asm/acpi.h
>> > +++ b/arch/arm64/include/asm/acpi.h
>> > @@ -12,10 +12,12 @@
>> > #ifndef _ASM_ACPI_H
>> > #define _ASM_ACPI_H
>> >
>> > +#include <linux/efi.h>
>> > #include <linux/memblock.h>
>> > #include <linux/psci.h>
>> >
>> > #include <asm/cputype.h>
>> > +#include <asm/io.h>
>> > #include <asm/smp_plat.h>
>> > #include <asm/tlbflush.h>
>> >
>> > @@ -29,18 +31,22 @@
>> >
>> > /* Basic configuration for ACPI */
>> > #ifdef CONFIG_ACPI
>> > +pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
>> > +
>> > /* ACPI table mapping after acpi_permanent_mmap is set */
>> > static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
>> > acpi_size size)
>> > {
>> > + /* For normal memory we already have a cacheable mapping. */
>> > + if (memblock_is_map_memory(phys))
>> > + return (void __iomem *)__phys_to_virt(phys);
>> > +
>> > /*
>> > - * EFI's reserve_regions() call adds memory with the WB attribute
>> > - * to memblock via early_init_dt_add_memory_arch().
>> > + * We should still honor the memory's attribute here because
>> > + * crash dump kernel possibly excludes some ACPI (reclaim)
>> > + * regions from memblock list.
>> > */
>> > - if (!memblock_is_memory(phys))
>> > - return ioremap(phys, size);
>> > -
>> > - return ioremap_cache(phys, size);
>> > + return __ioremap(phys, size, __acpi_get_mem_attribute(phys));
>> > }
>> > #define acpi_os_ioremap acpi_os_ioremap
>> >
>> > @@ -125,7 +131,10 @@ static inline const char *acpi_get_enable_method(int
>> > cpu)
>> > * for compatibility.
>> > */
>> > #define acpi_disable_cmcff 1
>> > -pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
>> > +static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
>> > +{
>> > + return __acpi_get_mem_attribute(addr);
>> > +}
>> > #endif /* CONFIG_ACPI_APEI */
>> >
>> > #ifdef CONFIG_ACPI_NUMA
>> > diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
>> > index 7b09487ff8fb..7880076c1cf0 100644
>> > --- a/arch/arm64/kernel/acpi.c
>> > +++ b/arch/arm64/kernel/acpi.c
>> > @@ -18,6 +18,7 @@
>> > #include <linux/acpi.h>
>> > #include <linux/bootmem.h>
>> > #include <linux/cpumask.h>
>> > +# include <linux/efi.h>
>>
>> Please drop the space after #
>
> Oops, will fix.
>
>> > #include <linux/efi-bgrt.h>
>> > #include <linux/init.h>
>> > #include <linux/irq.h>
>> > @@ -29,12 +30,8 @@
>> >
>> > #include <asm/cputype.h>
>> > #include <asm/cpu_ops.h>
>> > -#include <asm/smp_plat.h>
>> > -
>> > -#ifdef CONFIG_ACPI_APEI
>> > -# include <linux/efi.h>
>> > # include <asm/pgtable.h>
>>
>> And here
>
> Yes, but it's not my change ...
>
The space is there because of the #ifdef, which you remove ...
>> > -#endif
>> > +#include <asm/smp_plat.h>
>> >
>> > int acpi_noirq = 1; /* skip ACPI IRQ initialization */
>> > int acpi_disabled = 1;
>> > @@ -239,8 +236,7 @@ void __init acpi_boot_table_init(void)
>> > }
>> > }
>> >
>> > -#ifdef CONFIG_ACPI_APEI
>> > -pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
>> > +pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
>> > {
>> > /*
>> > * According to "Table 8 Map: EFI memory types to AArch64 memory
>> > @@ -261,4 +257,3 @@ pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
>> > return __pgprot(PROT_NORMAL_NC);
>> > return __pgprot(PROT_DEVICE_nGnRnE);
>> > }
>> > -#endif
>> > diff --git a/drivers/firmware/efi/arm-runtime.c
>> > b/drivers/firmware/efi/arm-runtime.c
>> > index 5889cbea60b8..1148ea5a0faa 100644
>> > --- a/drivers/firmware/efi/arm-runtime.c
>> > +++ b/drivers/firmware/efi/arm-runtime.c
>> > @@ -106,23 +106,23 @@ static bool __init efi_virtmap_init(void)
>> > * non-early mapping of the UEFI system table and virtual mappings for all
>> > * EFI_MEMORY_RUNTIME regions.
>> > */
>> > -static int __init arm_enable_runtime_services(void)
>> > +void __init efi_enter_virtual_mode(void)
>> > {
>> > u64 mapsize;
>> >
>> > if (!efi_enabled(EFI_BOOT)) {
>> > pr_info("EFI services will not be available.\n");
>> > - return 0;
>> > + return;
>> > }
>> >
>> > if (efi_runtime_disabled()) {
>> > pr_info("EFI runtime services will be disabled.\n");
>> > - return 0;
>> > + return;
>> > }
>> >
>>
>> This is a problem. If you are booting using efi=noruntime, the routine
>> exits early and never sets up the mapping for the EFI memory map.
>> So the efi_memmap_init_late() call should be moved before the
>> efi_runtime_disabled() check, everything else can stay as is afaict
>>
>> Could you please move the changes to this file and init/main.c into a
>> separate patch?
>
> Okay.
>
> Thank you for your reviewing.
>
> -Takahiro AKASHI
>
>
>> > if (efi_enabled(EFI_RUNTIME_SERVICES)) {
>> > pr_info("EFI runtime services access via paravirt.\n");
>> > - return 0;
>> > + return;
>> > }
>> >
>> > pr_info("Remapping and enabling EFI services.\n");
>> > @@ -131,21 +131,18 @@ static int __init arm_enable_runtime_services(void)
>> >
>> > if (efi_memmap_init_late(efi.memmap.phys_map, mapsize)) {
>> > pr_err("Failed to remap EFI memory map\n");
>> > - return -ENOMEM;
>> > + return;
>> > }
>> >
>> > if (!efi_virtmap_init()) {
>> > pr_err("UEFI virtual mapping missing or invalid -- runtime
>> > services will not be available\n");
>> > - return -ENOMEM;
>> > + return;
>> > }
>> >
>> > /* Set up runtime services function pointers */
>> > efi_native_runtime_setup();
>> > set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
>> > -
>> > - return 0;
>> > }
>> > -early_initcall(arm_enable_runtime_services);
>> >
>> > void efi_virtmap_load(void)
>> > {
>> > diff --git a/init/main.c b/init/main.c
>> > index b795aa341a3a..40d05b63960f 100644
>> > --- a/init/main.c
>> > +++ b/init/main.c
>> > @@ -693,6 +693,9 @@ asmlinkage __visible void __init start_kernel(void)
>> > debug_objects_mem_init();
>> > setup_per_cpu_pageset();
>> > numa_policy_init();
>> > + if (IS_ENABLED(CONFIG_EFI) &&
>> > + (IS_ENABLED(CONFIG_ARM64) || IS_ENABLED(CONFIG_ARM)))
>> > + efi_enter_virtual_mode();
>> > acpi_early_init();
>> > if (late_time_init)
>> > late_time_init();
>> > --
>> > 2.17.0
>> >
