Re: [PATCH v2 4/4] powerpc/kdump: add support for high crashkernel reservation

[Hari Bathini <hbathini@linux.ibm.com>]

On 08/07/26 8:03 pm, Sourabh Jain wrote:
> With this changes included crashkernel=xxM,high will be supported on
> powerpc. This allow user to allocated crashkernel memory on higer memory
> region and keeping the low memory allocation minimal.
> 
> The low memory reservation is by default set to 64 MB and it is reserved
> below RTAS_INSTANTIATE_MAX (1G) to make sure rtas instantiation work
> properly.
> 
> powerpc uses generic crashkernel parser and reserve functions and they
> are capable of handling high crashkernel reservtion so
> arch_reserve_crashkernel() is updated call generic crashkernel praser
> and reserve function with resptive options to make
> crashkernel=XXM,high prase and make crashkernel memory get reserved on
> higher memory regions.
> 
> Note: High crashkernel is supported only on PPC 64-bit systems when
> 64-bit RTAS is instantiated and Radix MMU is enabled; otherwise, the
> crashkernel reservation falls back to the default, even if the kernel
> command includes crashkernel=XXM,high.
> 
> Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
> ---
>   arch/powerpc/include/asm/crash_reserve.h |  6 ++++
>   arch/powerpc/include/asm/kexec.h         |  1 +
>   arch/powerpc/include/asm/rtas.h          |  9 +++++
>   arch/powerpc/kexec/core.c                | 45 +++++++++++++++++-------
>   4 files changed, 49 insertions(+), 12 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/crash_reserve.h b/arch/powerpc/include/asm/crash_reserve.h
> index d1b570ddbf98..4f2096984736 100644
> --- a/arch/powerpc/include/asm/crash_reserve.h
> +++ b/arch/powerpc/include/asm/crash_reserve.h
> @@ -2,6 +2,8 @@
>   #ifndef _ASM_POWERPC_CRASH_RESERVE_H
>   #define _ASM_POWERPC_CRASH_RESERVE_H
>   
> +#include <asm/rtas.h>
> +
>   /* crash kernel regions are Page size agliged */
>   #define CRASH_ALIGN             PAGE_SIZE
>   
> @@ -12,5 +14,9 @@ static inline bool arch_add_crash_res_to_iomem(void)
>   }
>   #define arch_add_crash_res_to_iomem arch_add_crash_res_to_iomem
>   #endif
> +#define DEFAULT_CRASH_KERNEL_LOW_SIZE SZ_64M
> +
> +#define CRASH_ADDR_LOW_MAX	RTAS_INSTANTIATE_MAX
> +#define CRASH_ADDR_HIGH_MAX	memblock_end_of_DRAM()
>   
>   #endif /* _ASM_POWERPC_CRASH_RESERVE_H */
> diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
> index e02710d6a2e1..9e676bd3bf03 100644
> --- a/arch/powerpc/include/asm/kexec.h
> +++ b/arch/powerpc/include/asm/kexec.h
> @@ -118,6 +118,7 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem
>   int __init overlaps_crashkernel(unsigned long start, unsigned long size);
>   extern void arch_reserve_crashkernel(void);
>   extern void kdump_cma_reserve(void);
> +unsigned long long __init get_crash_base(unsigned long long crash_base);
>   #else
>   static inline void arch_reserve_crashkernel(void) {}
>   static inline int overlaps_crashkernel(unsigned long start, unsigned long size) { return 0; }
> diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
> index aaa4c3bc1d61..d290437d8131 100644
> --- a/arch/powerpc/include/asm/rtas.h
> +++ b/arch/powerpc/include/asm/rtas.h
> @@ -561,6 +561,14 @@ static inline int page_is_rtas_user_buf(unsigned long pfn)
>   	return 0;
>   }
>   
> +static inline bool is_rtas_high_crashkernel_capable(void)
> +{
> +	if (rtas_64)
> +		return true;
> +
> +	return false;
> +}
> +
>   /* Not the best place to put pSeries_coalesce_init, will be fixed when we
>    * move some of the rtas suspend-me stuff to pseries */
>   void pSeries_coalesce_init(void);
> @@ -569,6 +577,7 @@ void rtas_initialize(void);
>   static inline int page_is_rtas_user_buf(unsigned long pfn) { return 0;}
>   static inline void pSeries_coalesce_init(void) { }
>   static inline void rtas_initialize(void) { }

> +static inline bool is_rtas_high_crashkernel_capable(void) { return true; }

Though !CONFIG_PPC_RTAS may imply radix MMU and high crashkernel
capable, is_rtas_high_crashkernel_capable() returning true for
!CONFIG_PPC_RTAS case seems counter-intuitive. Have a single
generic (non-rtas specific) function that accounts for high
crashkernel support in different scenarios?

>   #endif
>   
>   #ifdef CONFIG_HV_PERF_CTRS
> diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
> index dc44f11be353..81fc437377c8 100644
> --- a/arch/powerpc/kexec/core.c
> +++ b/arch/powerpc/kexec/core.c
> @@ -15,6 +15,7 @@
>   #include <linux/irq.h>
>   #include <linux/ftrace.h>
>   
> +#include <asm/rtas.h>
>   #include <asm/kdump.h>
>   #include <asm/machdep.h>
>   #include <asm/pgalloc.h>
> @@ -64,7 +65,7 @@ void machine_kexec(struct kimage *image)
>   
>   static unsigned long long crashk_cma_size;
>   
> -static unsigned long long __init get_crash_base(unsigned long long crash_base)
> +unsigned long long __init get_crash_base(unsigned long long crash_base)
>   {
>   
>   #ifndef CONFIG_NONSTATIC_KERNEL
> @@ -104,35 +105,55 @@ static unsigned long long __init get_crash_base(unsigned long long crash_base)
>   #endif
>   }
>   
> +static bool high_crashkernel_supported(void)
> +{
> +#if defined(CONFIG_PPC64) && (defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV))
> +	if (early_radix_enabled() && is_rtas_high_crashkernel_capable())
> +		return true;
> +#endif
> +	return false;
> +}
> +
>   void __init arch_reserve_crashkernel(void)
>   {
> -	unsigned long long crash_size, crash_base, crash_end;
> +	unsigned long long crash_size, crash_base, crash_end, low_size = 0;
>   	unsigned long long kernel_start, kernel_size;
>   	unsigned long long total_mem_sz;
> +	bool high = false;
>   	int ret;
>   
>   	total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
>   
>   	/* use common parsing */
>   	ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size,
> -				&crash_base, NULL, &crashk_cma_size, NULL);
> +				&crash_base, &low_size, &crashk_cma_size, &high);
>   
>   	if (ret)
>   		return;
>   
> -	crash_base = get_crash_base(crash_base);
> -	crash_end = crash_base + crash_size - 1;
> +	if (high && !high_crashkernel_supported()) {
> +		high = false;
> +		low_size = 0;
> +		pr_warn("High crashkernel unsupported, using standard reservation");
> +	}
>   
> -	kernel_start = __pa(_stext);
> -	kernel_size = _end - _stext;
> +	if (high) {
> +		crash_base = 0;
> +	} else {
> +		crash_base = get_crash_base(crash_base);
> +		crash_end = crash_base + crash_size - 1;
>   
> -	/* The crash region must not overlap the current kernel */
> -	if ((kernel_start + kernel_size > crash_base) && (kernel_start <= crash_end)) {
> -		pr_warn("Crash kernel can not overlap current kernel\n");
> -		return;
> +		kernel_start = __pa(_stext);
> +		kernel_size = _end - _stext;
> +
> +		/* The crash region must not overlap the current kernel */
> +		if ((kernel_start + kernel_size > crash_base) && (kernel_start <= crash_end)) {
> +			pr_warn("Crash kernel can not overlap current kernel\n");
> +			return;
> +		}
>   	}
>   
> -	reserve_crashkernel_generic(crash_size, crash_base, 0, false);
> +	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
>   }
>   
>   void __init kdump_cma_reserve(void)

- Hari