Re: [PATCH 1/2 v6] x86/kdump: always reserve the low 1MiB when the crashkernel option is specified

[Dave Young]

On 10/28/19 at 10:45am, Lianbo Jiang wrote:
> Kdump kernel will reuse the first 640k region because the real mode
> trampoline has to work in this area. When the vmcore is dumped, the
> old memory in this area may be accessed, therefore, kernel has to
> copy the contents of the first 640k area to a backup region so that
> kdump kernel can read the old memory from the backup area of the
> first 640k area, which is done in the purgatory().
> 
> But, the current handling of copying the first 640k area runs into
> problems when SME is enabled, kernel does not properly copy these
> old memory to the backup area in the purgatory(), thereby, kdump
> kernel reads out the encrypted contents, because the kdump kernel
> must access the first kernel's memory with the encryption bit set
> when SME is enabled in the first kernel. Please refer to this link:
> 
> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204793
> 
> Finally, it causes the following errors, and the crash tool gets
> invalid pointers when parsing the vmcore.
> 
> crash> kmem -s|grep -i invalid
> kmem: dma-kmalloc-512: slab:ffffd77680001c00 invalid freepointer:a6086ac099f0c5a4
> kmem: dma-kmalloc-512: slab:ffffd77680001c00 invalid freepointer:a6086ac099f0c5a4
> crash>
> 
> To avoid the above errors, when the crashkernel option is specified,
> lets reserve the remaining low 1MiB memory(after reserving real mode
> memory) so that the allocated memory does not fall into the low 1MiB
> area, which makes us not to copy the first 640k content to a backup
> region in purgatory(). This indicates that it does not need to be
> included in crash dumps or used for anything except the processor
> trampolines that must live in the low 1MiB.
> 
> Signed-off-by: Lianbo Jiang <lijiang@xxxxxxxxxx>
> ---
> BTW:I also tried to fix the above problem in purgatory(), but there
> are too many restricts in purgatory() context, for example: i can't
> allocate new memory to create the identity mapping page table for
> SME situation.
> 
> Currently, there are two places where the first 640k area is needed,
> the first one is in the find_trampoline_placement(), another one is
> in the reserve_real_mode(), and their content doesn't matter.
> 
> In addition, also need to clean all the code related to the backup
> region later.
> 
>  arch/x86/kernel/machine_kexec_64.c | 15 +++++++++++++++
>  arch/x86/realmode/init.c           |  2 ++
>  include/linux/kexec.h              |  2 ++
>  kernel/kexec_core.c                |  3 +++
>  4 files changed, 22 insertions(+)
> 
> diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
> index 5dcd438ad8f2..42d7c15c45f1 100644
> --- a/arch/x86/kernel/machine_kexec_64.c
> +++ b/arch/x86/kernel/machine_kexec_64.c
> @@ -17,6 +17,7 @@
>  #include <linux/suspend.h>
>  #include <linux/vmalloc.h>
>  #include <linux/efi.h>
> +#include <linux/memblock.h>
>  
>  #include <asm/init.h>
>  #include <asm/pgtable.h>
> @@ -27,6 +28,7 @@
>  #include <asm/kexec-bzimage64.h>
>  #include <asm/setup.h>
>  #include <asm/set_memory.h>
> +#include <asm/cmdline.h>
>  
>  #ifdef CONFIG_ACPI
>  /*
> @@ -687,3 +689,16 @@ void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages)
>  	 */
>  	set_memory_encrypted((unsigned long)vaddr, pages);
>  }
> +
> +/*
> + * When the crashkernel option is specified, only use the low
> + * 1MiB for the real mode trampoline.
> + */
> +void __init kexec_reserve_low_1MiB(void)
> +{
> +	if (cmdline_find_option(boot_command_line, "crashkernel",
> +				NULL, 0) > 0) {
> +		memblock_reserve(0, 1<<20);
> +		pr_info("Reserving the low 1MiB of memory for crashkernel\n");
> +	}
> +}
> diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
> index 7dce39c8c034..064cc79a015d 100644
> --- a/arch/x86/realmode/init.c
> +++ b/arch/x86/realmode/init.c
> @@ -3,6 +3,7 @@
>  #include <linux/slab.h>
>  #include <linux/memblock.h>
>  #include <linux/mem_encrypt.h>
> +#include <linux/kexec.h>
>  
>  #include <asm/set_memory.h>
>  #include <asm/pgtable.h>
> @@ -34,6 +35,7 @@ void __init reserve_real_mode(void)
>  
>  	memblock_reserve(mem, size);
>  	set_real_mode_mem(mem);
> +	kexec_reserve_low_1MiB();
>  }
>  
>  static void __init setup_real_mode(void)
> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> index 1776eb2e43a4..988bf2de51a7 100644
> --- a/include/linux/kexec.h
> +++ b/include/linux/kexec.h
> @@ -306,6 +306,7 @@ extern void __crash_kexec(struct pt_regs *);
>  extern void crash_kexec(struct pt_regs *);
>  int kexec_should_crash(struct task_struct *);
>  int kexec_crash_loaded(void);
> +void __init kexec_reserve_low_1MiB(void);
>  void crash_save_cpu(struct pt_regs *regs, int cpu);
>  extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
>  
> @@ -397,6 +398,7 @@ static inline void __crash_kexec(struct pt_regs *regs) { }
>  static inline void crash_kexec(struct pt_regs *regs) { }
>  static inline int kexec_should_crash(struct task_struct *p) { return 0; }
>  static inline int kexec_crash_loaded(void) { return 0; }
> +static inline void __init kexec_reserve_low_1MiB(void) { }
>  #define kexec_in_progress false
>  #endif /* CONFIG_KEXEC_CORE */
>  
> diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
> index 15d70a90b50d..8856047bcdc8 100644
> --- a/kernel/kexec_core.c
> +++ b/kernel/kexec_core.c
> @@ -1213,3 +1213,6 @@ void __weak arch_kexec_protect_crashkres(void)
>  
>  void __weak arch_kexec_unprotect_crashkres(void)
>  {}
> +
> +void __init __weak kexec_reserve_low_1MiB(void)
> +{}

Hi Lianbo,

Since this is x86 only, add a weak function sounds not necessary.
For example can just move it to  arch/x86/include/asm/kexec.h
Or maybe even better to limit it to kdump only, move it to 
arch/x86/include/asm/crash.h
and arch/x86/kernel/crash.c

Thanks
Dave