[Crash-utility] RISCV64: Use va_kernel_pa_offset in VTOP()

[Alexandre Ghiti]

Hi Song,


On 24/07/2023 06:06, Song Shuai wrote:
> Since RISC-V Linux v6.4, the commit 3335068f8721 ("riscv: Use
> PUD/P4D/PGD pages for the linear mapping") changes the
> phys_ram_base from the kernel_map.phys_addr to the start of DRAM.


Maybe we could be more explicit here, kernel_map.phys_addr actually 
points to the physical start of the kernel so maybe something like that:

"changes phys_ram_base from the physical start of the kernel to the 
actual start of the DRAM."


>
> The Crash's VTOP() still uses phys_ram_base and kernel_map.virt_addr
> to translate kernel virtual address, that made Crash boot failed with
> Linux v6.4 and later version.
>
> Let Linux export kernel_map.va_kernel_pa_offset in v6.5 and Crash can
> use "va_kernel_pa_offset" to translate the kernel virtual address in
> VTOP() correctly.
>
> Signed-off-by: Song Shuai <suagrfillet at gmail.com>
> ---
> You can check/test the Linux changes from this link:
> https://github.com/sugarfillet/linux/commits/6.5-rc3-crash
>
> And I'll send the Linux changes to riscv/for-next If you're ok with this patch.
> ---
>   defs.h    |  4 ++--
>   riscv64.c | 22 ++++++++++++++++++++++
>   2 files changed, 24 insertions(+), 2 deletions(-)
>
> diff --git a/defs.h b/defs.h
> index 358f365..46b9857 100644
> --- a/defs.h
> +++ b/defs.h
> @@ -3662,8 +3662,7 @@ typedef signed int s32;
>   	ulong _X = X;									\
>   	(THIS_KERNEL_VERSION >= LINUX(5,13,0) &&					\
>   		(_X) >= machdep->machspec->kernel_link_addr) ?				\
> -		(((unsigned long)(_X)-(machdep->machspec->kernel_link_addr)) +		\
> -		 machdep->machspec->phys_base):						\
> +		((unsigned long)(_X)-(machdep->machspec->va_kernel_pa_offset)): 	\
>   		(((unsigned long)(_X)-(machdep->kvbase)) +				\
>   		 machdep->machspec->phys_base);						\
>   	})
> @@ -7021,6 +7020,7 @@ struct machine_specific {
>   	ulong modules_vaddr;
>   	ulong modules_end;
>   	ulong kernel_link_addr;
> +	ulong va_kernel_pa_offset;
>   
>   	ulong _page_present;
>   	ulong _page_read;
> diff --git a/riscv64.c b/riscv64.c
> index 6b9a688..b9e50b4 100644
> --- a/riscv64.c
> +++ b/riscv64.c
> @@ -418,6 +418,27 @@ error:
>   	error(FATAL, "cannot get vm layout\n");
>   }
>   
> +static void
> +riscv64_get_va_kernel_pa_offset(struct machine_specific *ms)
> +{
> +	unsigned long kernel_version = riscv64_get_kernel_version();
> +
> +	/*
> +	 * va_kernel_pa_offset is defined in Linux kernel since 6.5.
> +	 */
> +	if (kernel_version >= LINUX(6,5,0)) {
> +		char *string;
> +		if ((string = pc->read_vmcoreinfo("NUMBER(va_kernel_pa_offset)"))) {
> +			ms->va_kernel_pa_offset = htol(string, QUIET, NULL);
> +			free(string);
> +		} else
> +			error(FATAL, "cannot read va_kernel_pa_offset\n");
> +	} else if (kernel_version >= LINUX(6,4,0))
> +		error(FATAL, "cannot determine va_kernel_pa_offset since Linux 6.4\n");
> +	else
> +		ms->va_kernel_pa_offset = ms->kernel_link_addr - ms->phys_base;
> +}
> +
>   static int
>   riscv64_is_kvaddr(ulong vaddr)
>   {
> @@ -1352,6 +1373,7 @@ riscv64_init(int when)
>   		riscv64_get_struct_page_size(machdep->machspec);
>   		riscv64_get_va_bits(machdep->machspec);
>   		riscv64_get_va_range(machdep->machspec);
> +		riscv64_get_va_kernel_pa_offset(machdep->machspec);
>   
>   		pt_level_alloc(&machdep->pgd, "cannot malloc pgd space.");
>   		pt_level_alloc(&machdep->machspec->p4d, "cannot malloc p4d space.");


Would you mind giving me the instructions on how to reproduce the issue 
please? So that I can add that to our internal CI and avoid this type of 
breakage in the future.

Thanks,

Alex