diff mbox series

[-next,v3,1/2] riscv: kdump: Implement crashkernel=X,[high,low]

Message ID 20230406220206.3067006-2-chenjiahao16@huawei.com (mailing list archive)
State Superseded
Headers show
Series support allocating crashkernel above 4G explicitly on riscv | expand

Checks

Context Check Description
conchuod/cover_letter success Series has a cover letter
conchuod/tree_selection success Guessed tree name to be for-next at HEAD d34a6b715a23
conchuod/fixes_present success Fixes tag not required for -next series
conchuod/maintainers_pattern success MAINTAINERS pattern errors before the patch: 1 and now 1
conchuod/verify_signedoff success Signed-off-by tag matches author and committer
conchuod/kdoc success Errors and warnings before: 0 this patch: 0
conchuod/build_rv64_clang_allmodconfig success Errors and warnings before: 18 this patch: 18
conchuod/module_param success Was 0 now: 0
conchuod/build_rv64_gcc_allmodconfig success Errors and warnings before: 19 this patch: 19
conchuod/build_rv32_defconfig success Build OK
conchuod/dtb_warn_rv64 success Errors and warnings before: 3 this patch: 3
conchuod/header_inline success No static functions without inline keyword in header files
conchuod/checkpatch success total: 0 errors, 0 warnings, 0 checks, 124 lines checked
conchuod/source_inline success Was 0 now: 0
conchuod/build_rv64_nommu_k210_defconfig success Build OK
conchuod/verify_fixes success No Fixes tag
conchuod/build_rv64_nommu_virt_defconfig success Build OK

Commit Message

Chen Jiahao April 6, 2023, 10:02 p.m. UTC
On riscv, the current crash kernel allocation logic is trying to
allocate within 32bit addressible memory region by default, if
failed, try to allocate without 4G restriction.

In need of saving DMA zone memory while allocating a relatively large
crash kernel region, allocating the reserved memory top down in
high memory, without overlapping the DMA zone, is a mature solution.
Here introduce the parameter option crashkernel=X,[high,low].

One can reserve the crash kernel from high memory above DMA zone range
by explicitly passing "crashkernel=X,high"; or reserve a memory range
below 4G with "crashkernel=X,low".

Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
---
 arch/riscv/kernel/setup.c |  5 +++
 arch/riscv/mm/init.c      | 74 ++++++++++++++++++++++++++++++++++++---
 2 files changed, 74 insertions(+), 5 deletions(-)

Comments

Guo Ren April 7, 2023, 9:06 a.m. UTC | #1
On Thu, Apr 6, 2023 at 10:06 PM Chen Jiahao <chenjiahao16@huawei.com> wrote:
>
> On riscv, the current crash kernel allocation logic is trying to
> allocate within 32bit addressible memory region by default, if
> failed, try to allocate without 4G restriction.
>
> In need of saving DMA zone memory while allocating a relatively large
> crash kernel region, allocating the reserved memory top down in
> high memory, without overlapping the DMA zone, is a mature solution.
> Here introduce the parameter option crashkernel=X,[high,low].
>
> One can reserve the crash kernel from high memory above DMA zone range
> by explicitly passing "crashkernel=X,high"; or reserve a memory range
> below 4G with "crashkernel=X,low".
Asked-by: Guo Ren <guoren@kernel.org>

>
> Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
> ---
>  arch/riscv/kernel/setup.c |  5 +++
>  arch/riscv/mm/init.c      | 74 ++++++++++++++++++++++++++++++++++++---
>  2 files changed, 74 insertions(+), 5 deletions(-)
>
> diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
> index 5d3184cbf518..ea84e5047c23 100644
> --- a/arch/riscv/kernel/setup.c
> +++ b/arch/riscv/kernel/setup.c
> @@ -176,6 +176,11 @@ static void __init init_resources(void)
>                 if (ret < 0)
>                         goto error;
>         }
> +       if (crashk_low_res.start != crashk_low_res.end) {
> +               ret = add_resource(&iomem_resource, &crashk_low_res);
> +               if (ret < 0)
> +                       goto error;
> +       }
>  #endif
>
>  #ifdef CONFIG_CRASH_DUMP
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index 478d6763a01a..b5b457193423 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -1152,6 +1152,28 @@ static inline void setup_vm_final(void)
>  }
>  #endif /* CONFIG_MMU */
>
> +/* Reserve 128M low memory by default for swiotlb buffer */
> +#define DEFAULT_CRASH_KERNEL_LOW_SIZE  (128UL << 20)
> +
> +static int __init reserve_crashkernel_low(unsigned long long low_size)
> +{
> +       unsigned long long low_base;
> +
> +       low_base = memblock_phys_alloc_range(low_size, PMD_SIZE, 0, dma32_phys_limit);
> +       if (!low_base) {
> +               pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size);
> +               return -ENOMEM;
> +       }
> +
> +       pr_info("crashkernel low memory reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
> +               low_base, low_base + low_size, low_size >> 20);
> +
> +       crashk_low_res.start = low_base;
> +       crashk_low_res.end = low_base + low_size - 1;
> +
> +       return 0;
> +}
> +
>  /*
>   * reserve_crashkernel() - reserves memory for crash kernel
>   *
> @@ -1163,8 +1185,12 @@ static void __init reserve_crashkernel(void)
>  {
>         unsigned long long crash_base = 0;
>         unsigned long long crash_size = 0;
> +       unsigned long long crash_low_size = 0;
>         unsigned long search_start = memblock_start_of_DRAM();
>         unsigned long search_end = memblock_end_of_DRAM();
> +       unsigned long search_low_max = (unsigned long)dma32_phys_limit;
> +       char *cmdline = boot_command_line;
> +       bool fixed_base = false;
>
>         int ret = 0;
>
> @@ -1180,14 +1206,37 @@ static void __init reserve_crashkernel(void)
>                 return;
>         }
>
> -       ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
> +       ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
>                                 &crash_size, &crash_base);
> -       if (ret || !crash_size)
> +       if (ret == -ENOENT) {
> +               /*
> +                * crashkernel=X,[high,low] can be specified or not, but
> +                * invalid value is not allowed.
> +                */
> +               ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
> +               if (ret || !crash_size)
> +                       return;
> +
> +               /*
> +                * crashkernel=Y,low is valid only when crashkernel=X,high
> +                * is passed and high memory is reserved successful.
> +                */
> +               ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
> +               if (ret == -ENOENT)
> +                       crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
> +               else if (ret)
> +                       return;
> +
> +               search_start = search_low_max;
> +       } else if (ret || !crash_size) {
> +               /* Invalid argument value specified */
>                 return;
> +       }
>
>         crash_size = PAGE_ALIGN(crash_size);
>
>         if (crash_base) {
> +               fixed_base = true;
>                 search_start = crash_base;
>                 search_end = crash_base + crash_size;
>         }
> @@ -1201,16 +1250,31 @@ static void __init reserve_crashkernel(void)
>          */
>         crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
>                                                search_start,
> -                                              min(search_end, (unsigned long) SZ_4G));
> +                                              min(search_end, search_low_max));
>         if (crash_base == 0) {
> -               /* Try again without restricting region to 32bit addressible memory */
> +               if (fixed_base) {
> +                       pr_warn("crashkernel: allocating failed with given size@offset\n");
> +                       return;
> +               }
> +
> +               /* Try again above the region of 32bit addressible memory */
>                 crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
> -                                               search_start, search_end);
> +                                                      max(search_start, search_low_max),
> +                                                      search_end);
>                 if (crash_base == 0) {
>                         pr_warn("crashkernel: couldn't allocate %lldKB\n",
>                                 crash_size >> 10);
>                         return;
>                 }
> +
> +               if (!crash_low_size)
> +                       crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
> +       }
> +
> +       if ((crash_base > dma32_phys_limit - crash_low_size) &&
> +           crash_low_size && reserve_crashkernel_low(crash_low_size)) {
> +               memblock_phys_free(crash_base, crash_size);
> +               return;
>         }
>
>         pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",
> --
> 2.31.1
>
Simon Horman April 7, 2023, 12:03 p.m. UTC | #2
On Fri, Apr 07, 2023 at 06:02:05AM +0800, Chen Jiahao wrote:
> On riscv, the current crash kernel allocation logic is trying to
> allocate within 32bit addressible memory region by default, if
> failed, try to allocate without 4G restriction.
> 
> In need of saving DMA zone memory while allocating a relatively large
> crash kernel region, allocating the reserved memory top down in
> high memory, without overlapping the DMA zone, is a mature solution.
> Here introduce the parameter option crashkernel=X,[high,low].
> 
> One can reserve the crash kernel from high memory above DMA zone range
> by explicitly passing "crashkernel=X,high"; or reserve a memory range
> below 4G with "crashkernel=X,low".
> 
> Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>

...

> @@ -1180,14 +1206,37 @@ static void __init reserve_crashkernel(void)
>  		return;
>  	}
>  
> -	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
> +	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
>  				&crash_size, &crash_base);
> -	if (ret || !crash_size)
> +	if (ret == -ENOENT) {
> +		/*
> +		 * crashkernel=X,[high,low] can be specified or not, but
> +		 * invalid value is not allowed.

nit: Perhaps something like this would be easier to correlate with the
     code that follows:

		/* Fallback to crashkernel=X,[high,low] */


> +		 */
> +		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
> +		if (ret || !crash_size)
> +			return;
> +
> +		/*
> +		 * crashkernel=Y,low is valid only when crashkernel=X,high
> +		 * is passed and high memory is reserved successful.

nit: s/successful/successfully/

> +		 */
> +		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
> +		if (ret == -ENOENT)
> +			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
> +		else if (ret)
> +			return;
> +
> +		search_start = search_low_max;
> +	} else if (ret || !crash_size) {
> +		/* Invalid argument value specified */
>  		return;
> +	}

...
Simon Horman April 7, 2023, 12:03 p.m. UTC | #3
On Fri, Apr 07, 2023 at 05:06:24PM +0800, Guo Ren wrote:
> On Thu, Apr 6, 2023 at 10:06 PM Chen Jiahao <chenjiahao16@huawei.com> wrote:
> >
> > On riscv, the current crash kernel allocation logic is trying to
> > allocate within 32bit addressible memory region by default, if
> > failed, try to allocate without 4G restriction.
> >
> > In need of saving DMA zone memory while allocating a relatively large
> > crash kernel region, allocating the reserved memory top down in
> > high memory, without overlapping the DMA zone, is a mature solution.
> > Here introduce the parameter option crashkernel=X,[high,low].
> >
> > One can reserve the crash kernel from high memory above DMA zone range
> > by explicitly passing "crashkernel=X,high"; or reserve a memory range
> > below 4G with "crashkernel=X,low".
> Asked-by: Guo Ren <guoren@kernel.org>

Perhaps 'Acked-by' :)
Leizhen (ThunderTown) April 7, 2023, 12:58 p.m. UTC | #4
On 2023/4/7 20:03, Simon Horman wrote:
> On Fri, Apr 07, 2023 at 06:02:05AM +0800, Chen Jiahao wrote:
>> On riscv, the current crash kernel allocation logic is trying to
>> allocate within 32bit addressible memory region by default, if
>> failed, try to allocate without 4G restriction.
>>
>> In need of saving DMA zone memory while allocating a relatively large
>> crash kernel region, allocating the reserved memory top down in
>> high memory, without overlapping the DMA zone, is a mature solution.
>> Here introduce the parameter option crashkernel=X,[high,low].
>>
>> One can reserve the crash kernel from high memory above DMA zone range
>> by explicitly passing "crashkernel=X,high"; or reserve a memory range
>> below 4G with "crashkernel=X,low".
>>
>> Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
> 
> ...
> 
>> @@ -1180,14 +1206,37 @@ static void __init reserve_crashkernel(void)
>>  		return;
>>  	}
>>  
>> -	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
>> +	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
>>  				&crash_size, &crash_base);
>> -	if (ret || !crash_size)
>> +	if (ret == -ENOENT) {
>> +		/*
>> +		 * crashkernel=X,[high,low] can be specified or not, but
>> +		 * invalid value is not allowed.
> 
> nit: Perhaps something like this would be easier to correlate with the
>      code that follows:
> 
> 		/* Fallback to crashkernel=X,[high,low] */

The description "crashkernel=X,[high,low] can be specified or not" is not
correct, because crashkernel=X,high must be specified when walking into this
branch. So use Simon's comments or copy arm64's comments(it's written for
parse_crashkernel_low()).

> 
> 
>> +		 */
>> +		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
>> +		if (ret || !crash_size)
>> +			return;
>> +
>> +		/*
>> +		 * crashkernel=Y,low is valid only when crashkernel=X,high
>> +		 * is passed and high memory is reserved successful.
> 
> nit: s/successful/successfully/

Seems like the whole "and high memory is reserved successful" needs to be deleted.
Only the dependency between the two boot options should be described here,
regardless of whether their memory is successfully allocated.

> 
>> +		 */
>> +		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
>> +		if (ret == -ENOENT)
>> +			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
>> +		else if (ret)
>> +			return;
>> +
>> +		search_start = search_low_max;
>> +	} else if (ret || !crash_size) {
>> +		/* Invalid argument value specified */
>>  		return;
>> +	}
> 
> ...
> .
>
Leizhen (ThunderTown) April 8, 2023, 2 a.m. UTC | #5
On 2023/4/7 20:58, Leizhen (ThunderTown) wrote:
> 
> 
> On 2023/4/7 20:03, Simon Horman wrote:
>> On Fri, Apr 07, 2023 at 06:02:05AM +0800, Chen Jiahao wrote:
>>> On riscv, the current crash kernel allocation logic is trying to
>>> allocate within 32bit addressible memory region by default, if
>>> failed, try to allocate without 4G restriction.
>>>
>>> In need of saving DMA zone memory while allocating a relatively large
>>> crash kernel region, allocating the reserved memory top down in
>>> high memory, without overlapping the DMA zone, is a mature solution.
>>> Here introduce the parameter option crashkernel=X,[high,low].
>>>
>>> One can reserve the crash kernel from high memory above DMA zone range
>>> by explicitly passing "crashkernel=X,high"; or reserve a memory range
>>> below 4G with "crashkernel=X,low".
>>>
>>> Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
>>
>> ...
>>
>>> @@ -1180,14 +1206,37 @@ static void __init reserve_crashkernel(void)
>>>  		return;
>>>  	}
>>>  
>>> -	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
>>> +	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
>>>  				&crash_size, &crash_base);
>>> -	if (ret || !crash_size)
>>> +	if (ret == -ENOENT) {
>>> +		/*
>>> +		 * crashkernel=X,[high,low] can be specified or not, but
>>> +		 * invalid value is not allowed.
>>
>> nit: Perhaps something like this would be easier to correlate with the
>>      code that follows:
>>
>> 		/* Fallback to crashkernel=X,[high,low] */
> 
> The description "crashkernel=X,[high,low] can be specified or not" is not
> correct, because crashkernel=X,high must be specified when walking into this
> branch. So use Simon's comments or copy arm64's comments(it's written for
> parse_crashkernel_low()).

I rethink it a little bit, if it's relative to crashkernel=X[@offset],
that's also true.

Reviewed-by: Zhen Lei <thunder.leizhen@huawei.com>

> 
>>
>>
>>> +		 */
>>> +		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
>>> +		if (ret || !crash_size)
>>> +			return;
>>> +
>>> +		/*
>>> +		 * crashkernel=Y,low is valid only when crashkernel=X,high
>>> +		 * is passed and high memory is reserved successful.
>>
>> nit: s/successful/successfully/
> 
> Seems like the whole "and high memory is reserved successful" needs to be deleted.
> Only the dependency between the two boot options should be described here,
> regardless of whether their memory is successfully allocated.
> 
>>
>>> +		 */
>>> +		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
>>> +		if (ret == -ENOENT)
>>> +			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
>>> +		else if (ret)
>>> +			return;
>>> +
>>> +		search_start = search_low_max;
>>> +	} else if (ret || !crash_size) {
>>> +		/* Invalid argument value specified */
>>>  		return;
>>> +	}
>>
>> ...
>> .
>>
>
Chen Jiahao April 10, 2023, 9:20 a.m. UTC | #6
On 2023/4/7 20:03, Simon Horman wrote:
> On Fri, Apr 07, 2023 at 06:02:05AM +0800, Chen Jiahao wrote:
>> On riscv, the current crash kernel allocation logic is trying to
>> allocate within 32bit addressible memory region by default, if
>> failed, try to allocate without 4G restriction.
>>
>> In need of saving DMA zone memory while allocating a relatively large
>> crash kernel region, allocating the reserved memory top down in
>> high memory, without overlapping the DMA zone, is a mature solution.
>> Here introduce the parameter option crashkernel=X,[high,low].
>>
>> One can reserve the crash kernel from high memory above DMA zone range
>> by explicitly passing "crashkernel=X,high"; or reserve a memory range
>> below 4G with "crashkernel=X,low".
>>
>> Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
> ...
>
>> @@ -1180,14 +1206,37 @@ static void __init reserve_crashkernel(void)
>>   		return;
>>   	}
>>   
>> -	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
>> +	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
>>   				&crash_size, &crash_base);
>> -	if (ret || !crash_size)
>> +	if (ret == -ENOENT) {
>> +		/*
>> +		 * crashkernel=X,[high,low] can be specified or not, but
>> +		 * invalid value is not allowed.
> nit: Perhaps something like this would be easier to correlate with the
>       code that follows:
>
> 		/* Fallback to crashkernel=X,[high,low] */
>
Agreed, this would be more concise and accurate.
>> +		 */
>> +		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
>> +		if (ret || !crash_size)
>> +			return;
>> +
>> +		/*
>> +		 * crashkernel=Y,low is valid only when crashkernel=X,high
>> +		 * is passed and high memory is reserved successful.
> nit: s/successful/successfully/

I will fix above nits and resend another version later, thanks.


>> +		 */
>> +		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
>> +		if (ret == -ENOENT)
>> +			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
>> +		else if (ret)
>> +			return;
>> +
>> +		search_start = search_low_max;
>> +	} else if (ret || !crash_size) {
>> +		/* Invalid argument value specified */
>>   		return;
>> +	}
> ...
Chen Jiahao April 10, 2023, 9:52 a.m. UTC | #7
On 2023/4/8 10:00, Leizhen (ThunderTown) wrote:
>
> On 2023/4/7 20:58, Leizhen (ThunderTown) wrote:
>>
>> On 2023/4/7 20:03, Simon Horman wrote:
>>> On Fri, Apr 07, 2023 at 06:02:05AM +0800, Chen Jiahao wrote:
>>>> On riscv, the current crash kernel allocation logic is trying to
>>>> allocate within 32bit addressible memory region by default, if
>>>> failed, try to allocate without 4G restriction.
>>>>
>>>> In need of saving DMA zone memory while allocating a relatively large
>>>> crash kernel region, allocating the reserved memory top down in
>>>> high memory, without overlapping the DMA zone, is a mature solution.
>>>> Here introduce the parameter option crashkernel=X,[high,low].
>>>>
>>>> One can reserve the crash kernel from high memory above DMA zone range
>>>> by explicitly passing "crashkernel=X,high"; or reserve a memory range
>>>> below 4G with "crashkernel=X,low".
>>>>
>>>> Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
>>> ...
>>>
>>>> @@ -1180,14 +1206,37 @@ static void __init reserve_crashkernel(void)
>>>>   		return;
>>>>   	}
>>>>   
>>>> -	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
>>>> +	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
>>>>   				&crash_size, &crash_base);
>>>> -	if (ret || !crash_size)
>>>> +	if (ret == -ENOENT) {
>>>> +		/*
>>>> +		 * crashkernel=X,[high,low] can be specified or not, but
>>>> +		 * invalid value is not allowed.
>>> nit: Perhaps something like this would be easier to correlate with the
>>>       code that follows:
>>>
>>> 		/* Fallback to crashkernel=X,[high,low] */
>> The description "crashkernel=X,[high,low] can be specified or not" is not
>> correct, because crashkernel=X,high must be specified when walking into this
>> branch. So use Simon's comments or copy arm64's comments(it's written for
>> parse_crashkernel_low()).
> I rethink it a little bit, if it's relative to crashkernel=X[@offset],
> that's also true.
>
> Reviewed-by: Zhen Lei <thunder.leizhen@huawei.com>

Sure, The commit should not be ambiguous like this, Simon's comment above is

a better option.


>>>
>>>> +		 */
>>>> +		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
>>>> +		if (ret || !crash_size)
>>>> +			return;
>>>> +
>>>> +		/*
>>>> +		 * crashkernel=Y,low is valid only when crashkernel=X,high
>>>> +		 * is passed and high memory is reserved successful.
>>> nit: s/successful/successfully/
>> Seems like the whole "and high memory is reserved successful" needs to be deleted.
>> Only the dependency between the two boot options should be described here,
>> regardless of whether their memory is successfully allocated.

The comment here is imprecise, since there is absolutely no check whether

the allocation is successful before "parse_crashkernel_low"


>>
>>>> +		 */
>>>> +		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
>>>> +		if (ret == -ENOENT)
>>>> +			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
>>>> +		else if (ret)
>>>> +			return;
>>>> +
>>>> +		search_start = search_low_max;
>>>> +	} else if (ret || !crash_size) {
>>>> +		/* Invalid argument value specified */
>>>>   		return;
>>>> +	}
>>> ...
>>> .
>>>
BR,

Jiahao
Guo Ren April 11, 2023, 1:38 a.m. UTC | #8
On Fri, Apr 7, 2023 at 8:03 PM Simon Horman <horms@kernel.org> wrote:
>
> On Fri, Apr 07, 2023 at 05:06:24PM +0800, Guo Ren wrote:
> > On Thu, Apr 6, 2023 at 10:06 PM Chen Jiahao <chenjiahao16@huawei.com> wrote:
> > >
> > > On riscv, the current crash kernel allocation logic is trying to
> > > allocate within 32bit addressible memory region by default, if
> > > failed, try to allocate without 4G restriction.
> > >
> > > In need of saving DMA zone memory while allocating a relatively large
> > > crash kernel region, allocating the reserved memory top down in
> > > high memory, without overlapping the DMA zone, is a mature solution.
> > > Here introduce the parameter option crashkernel=X,[high,low].
> > >
> > > One can reserve the crash kernel from high memory above DMA zone range
> > > by explicitly passing "crashkernel=X,high"; or reserve a memory range
> > > below 4G with "crashkernel=X,low".
> > Asked-by: Guo Ren <guoren@kernel.org>
>
> Perhaps 'Acked-by' :)
Sorry, my typo.

Acked-by: Guo Ren <guoren@kernel.org>
diff mbox series

Patch

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 5d3184cbf518..ea84e5047c23 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -176,6 +176,11 @@  static void __init init_resources(void)
 		if (ret < 0)
 			goto error;
 	}
+	if (crashk_low_res.start != crashk_low_res.end) {
+		ret = add_resource(&iomem_resource, &crashk_low_res);
+		if (ret < 0)
+			goto error;
+	}
 #endif
 
 #ifdef CONFIG_CRASH_DUMP
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 478d6763a01a..b5b457193423 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1152,6 +1152,28 @@  static inline void setup_vm_final(void)
 }
 #endif /* CONFIG_MMU */
 
+/* Reserve 128M low memory by default for swiotlb buffer */
+#define DEFAULT_CRASH_KERNEL_LOW_SIZE	(128UL << 20)
+
+static int __init reserve_crashkernel_low(unsigned long long low_size)
+{
+	unsigned long long low_base;
+
+	low_base = memblock_phys_alloc_range(low_size, PMD_SIZE, 0, dma32_phys_limit);
+	if (!low_base) {
+		pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size);
+		return -ENOMEM;
+	}
+
+	pr_info("crashkernel low memory reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
+		low_base, low_base + low_size, low_size >> 20);
+
+	crashk_low_res.start = low_base;
+	crashk_low_res.end = low_base + low_size - 1;
+
+	return 0;
+}
+
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
  *
@@ -1163,8 +1185,12 @@  static void __init reserve_crashkernel(void)
 {
 	unsigned long long crash_base = 0;
 	unsigned long long crash_size = 0;
+	unsigned long long crash_low_size = 0;
 	unsigned long search_start = memblock_start_of_DRAM();
 	unsigned long search_end = memblock_end_of_DRAM();
+	unsigned long search_low_max = (unsigned long)dma32_phys_limit;
+	char *cmdline = boot_command_line;
+	bool fixed_base = false;
 
 	int ret = 0;
 
@@ -1180,14 +1206,37 @@  static void __init reserve_crashkernel(void)
 		return;
 	}
 
-	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
 				&crash_size, &crash_base);
-	if (ret || !crash_size)
+	if (ret == -ENOENT) {
+		/*
+		 * crashkernel=X,[high,low] can be specified or not, but
+		 * invalid value is not allowed.
+		 */
+		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
+		if (ret || !crash_size)
+			return;
+
+		/*
+		 * crashkernel=Y,low is valid only when crashkernel=X,high
+		 * is passed and high memory is reserved successful.
+		 */
+		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
+		if (ret == -ENOENT)
+			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
+		else if (ret)
+			return;
+
+		search_start = search_low_max;
+	} else if (ret || !crash_size) {
+		/* Invalid argument value specified */
 		return;
+	}
 
 	crash_size = PAGE_ALIGN(crash_size);
 
 	if (crash_base) {
+		fixed_base = true;
 		search_start = crash_base;
 		search_end = crash_base + crash_size;
 	}
@@ -1201,16 +1250,31 @@  static void __init reserve_crashkernel(void)
 	 */
 	crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
 					       search_start,
-					       min(search_end, (unsigned long) SZ_4G));
+					       min(search_end, search_low_max));
 	if (crash_base == 0) {
-		/* Try again without restricting region to 32bit addressible memory */
+		if (fixed_base) {
+			pr_warn("crashkernel: allocating failed with given size@offset\n");
+			return;
+		}
+
+		/* Try again above the region of 32bit addressible memory */
 		crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
-						search_start, search_end);
+						       max(search_start, search_low_max),
+						       search_end);
 		if (crash_base == 0) {
 			pr_warn("crashkernel: couldn't allocate %lldKB\n",
 				crash_size >> 10);
 			return;
 		}
+
+		if (!crash_low_size)
+			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
+	}
+
+	if ((crash_base > dma32_phys_limit - crash_low_size) &&
+	    crash_low_size && reserve_crashkernel_low(crash_low_size)) {
+		memblock_phys_free(crash_base, crash_size);
+		return;
 	}
 
 	pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",