[PATCH -next v2 0/2] support allocating crashkernel above 4G explicitly on riscv

[PATCH -next v2 0/2] support allocating crashkernel above 4G explicitly on riscv

[Chen Jiahao]

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.
Hence this patchset introduces 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". Besides, there are few rules need
to take notice:
1. "crashkernel=X,[high,low]" will be ignored if "crashkernel=size"
   is specified.
2. "crashkernel=X,low" is valid only when "crashkernel=X,high" is passed
   and there is enough memory to be allocated under 4G.
3. When allocating crashkernel above 4G and no "crashkernel=X,low" is
   specified, a 128M low memory will be allocated automatically for
   swiotlb bounce buffer.
See Documentation/admin-guide/kernel-parameters.txt for more information.

To verify loading the crashkernel, adapted kexec-tools is attached below:
https://github.com/chenjh005/kexec-tools/tree/build-test-riscv-v2

Following test cases have been performed as expected:
1) crashkernel=256M                          //low=256M
2) crashkernel=1G                            //low=1G
3) crashkernel=4G                            //high=4G, low=128M(default)
4) crashkernel=4G crashkernel=256M,high      //high=4G, low=128M(default), high is ignored
5) crashkernel=4G crashkernel=256M,low       //high=4G, low=128M(default), low is ignored
6) crashkernel=4G,high                       //high=4G, low=128M(default)
7) crashkernel=256M,low                      //low=0M, invalid
8) crashkernel=4G,high crashkernel=256M,low  //high=4G, low=256M
9) crashkernel=4G,high crashkernel=4G,low    //high=0M, low=0M, invalid
10) crashkernel=512M@0xd0000000              //low=512M
11) crashkernel=1G@0xe0000000                //high=0M, low=0M, no enough low memory, failed

Changes since [v2]:
1. Update the allocation logic to ensure the high crashkernel
   region is reserved strictly above dma32_phys_limit.
2. Clean up some minor format problems.

Chen Jiahao (2):
  riscv: kdump: Implement crashkernel=X,[high,low]
  docs: kdump: Update the crashkernel description for riscv

 .../admin-guide/kernel-parameters.txt         | 15 ++---
 arch/riscv/kernel/setup.c                     |  5 ++
 arch/riscv/mm/init.c                          | 63 +++++++++++++++++--
 3 files changed, 72 insertions(+), 11 deletions(-)

-- 
2.31.1

[PATCH -next v2 1/2] riscv: kdump: Implement crashkernel=X,[high,low]

[Chen Jiahao]

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      | 63 ++++++++++++++++++++++++++++++++++++---
 2 files changed, 64 insertions(+), 4 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..b7708cc467fa 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
  *
@@ -1163,6 +1185,7 @@ 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();
 
@@ -1182,8 +1205,30 @@ static void __init reserve_crashkernel(void)
 
 	ret = parse_crashkernel(boot_command_line, 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(boot_command_line, 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(boot_command_line, 0, &crash_low_size, &crash_base);
+		if (ret == -ENOENT)
+			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
+		else if (ret)
+			return;
+
+		search_start = dma32_phys_limit;
+	} else if (ret || !crash_size) {
+		/* Invalid argument value specified */
 		return;
+	}
 
 	crash_size = PAGE_ALIGN(crash_size);
 
@@ -1201,16 +1246,26 @@ 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, (unsigned long)dma32_phys_limit));
 	if (crash_base == 0) {
-		/* Try again without restricting region to 32bit addressible memory */
+		/* 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, (unsigned long)dma32_phys_limit),
+						       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

[PATCH -next v2 2/2] docs: kdump: Update the crashkernel description for riscv

[Chen Jiahao]

Now "crashkernel=" parameter on riscv has been updated to support
crashkernel=X,[high,low]. Through which we can reserve memory region
above/within 32bit addressible DMA zone.

Here update the parameter description accordingly.

Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
---
 Documentation/admin-guide/kernel-parameters.txt | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 9bc3813bce8f..a947d3d7c85c 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -866,7 +866,7 @@
 			memory region [offset, offset + size] for that kernel
 			image. If '@offset' is omitted, then a suitable offset
 			is selected automatically.
-			[KNL, X86-64, ARM64] Select a region under 4G first, and
+			[KNL, X86-64, ARM64, RISCV] Select a region under 4G first, and
 			fall back to reserve region above 4G when '@offset'
 			hasn't been specified.
 			See Documentation/admin-guide/kdump/kdump.rst for further details.
@@ -879,14 +879,14 @@
 			Documentation/admin-guide/kdump/kdump.rst for an example.
 
 	crashkernel=size[KMG],high
-			[KNL, X86-64, ARM64] range could be above 4G. Allow kernel
-			to allocate physical memory region from top, so could
-			be above 4G if system have more than 4G ram installed.
-			Otherwise memory region will be allocated below 4G, if
-			available.
+			[KNL, X86-64, ARM64, RISCV] range could be above 4G.
+			Allow kernel to allocate physical memory region from top,
+			so could be above 4G if system have more than 4G ram
+			installed. Otherwise memory region will be allocated
+			below 4G, if available.
 			It will be ignored if crashkernel=X is specified.
 	crashkernel=size[KMG],low
-			[KNL, X86-64, ARM64] range under 4G. When crashkernel=X,high
+			[KNL, X86-64, ARM64, RISCV] range under 4G. When crashkernel=X,high
 			is passed, kernel could allocate physical memory region
 			above 4G, that cause second kernel crash on system
 			that require some amount of low memory, e.g. swiotlb
@@ -897,6 +897,7 @@
 			size is	platform dependent.
 			  --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB)
 			  --> arm64: 128MiB
+			  --> riscv: 128MiB
 			This one lets the user specify own low range under 4G
 			for second kernel instead.
 			0: to disable low allocation.
-- 
2.31.1

Re: [PATCH -next v2 1/2] riscv: kdump: Implement crashkernel=X,[high,low]

[Baoquan He]

On 03/28/23 at 07:51pm, 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>
> ---
>  arch/riscv/kernel/setup.c |  5 ++++
>  arch/riscv/mm/init.c      | 63 ++++++++++++++++++++++++++++++++++++---
>  2 files changed, 64 insertions(+), 4 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..b7708cc467fa 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
>   *
> @@ -1163,6 +1185,7 @@ 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();
>  
> @@ -1182,8 +1205,30 @@ static void __init reserve_crashkernel(void)
>  
>  	ret = parse_crashkernel(boot_command_line, 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(boot_command_line, 0, &crash_size, &crash_base);

I would add a local variable to assign boot_command_line to it just like
arm64 does. Then these lines could be shorter. 

	char *cmdline = boot_command_line;

> +		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(boot_command_line, 0, &crash_low_size, &crash_base);
> +		if (ret == -ENOENT)
> +			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
> +		else if (ret)
> +			return;
> +
> +		search_start = dma32_phys_limit;
> +	} else if (ret || !crash_size) {
> +		/* Invalid argument value specified */
>  		return;
> +	}
>  
>  	crash_size = PAGE_ALIGN(crash_size);
>  
> @@ -1201,16 +1246,26 @@ 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, (unsigned long)dma32_phys_limit));
>  	if (crash_base == 0) {

The above conditional check isn't right. If crashkernel=size@offset
specified, the reservation failure won't trigger retry. This seems to be
originally introduced by old commit, while this need be fixed firstly.

> -		/* Try again without restricting region to 32bit addressible memory */
> +		/* 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, (unsigned long)dma32_phys_limit),
> +						       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
> 

Re: [PATCH -next v2 1/2] riscv: kdump: Implement crashkernel=X,[high,low]

[chenjiahao (C)]

On 2023/3/29 19:19, Baoquan He wrote:
> On 03/28/23 at 07:51pm, Chen Jiahao wrote:

Thanks for reviewing.

>> 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      | 63 ++++++++++++++++++++++++++++++++++++---
>>   2 files changed, 64 insertions(+), 4 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..b7708cc467fa 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
>>    *
>> @@ -1163,6 +1185,7 @@ 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();
>>   
>> @@ -1182,8 +1205,30 @@ static void __init reserve_crashkernel(void)
>>   
>>   	ret = parse_crashkernel(boot_command_line, 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(boot_command_line, 0, &crash_size, &crash_base);
> I would add a local variable to assign boot_command_line to it just like
> arm64 does. Then these lines could be shorter.
>
> 	char *cmdline = boot_command_line;
Agreed, I will clean this up later in next version.
>> +		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(boot_command_line, 0, &crash_low_size, &crash_base);
>> +		if (ret == -ENOENT)
>> +			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
>> +		else if (ret)
>> +			return;
>> +
>> +		search_start = dma32_phys_limit;
>> +	} else if (ret || !crash_size) {
>> +		/* Invalid argument value specified */
>>   		return;
>> +	}
>>   
>>   	crash_size = PAGE_ALIGN(crash_size);
>>   
>> @@ -1201,16 +1246,26 @@ 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, (unsigned long)dma32_phys_limit));
>>   	if (crash_base == 0) {
> The above conditional check isn't right. If crashkernel=size@offset
> specified, the reservation failure won't trigger retry. This seems to be
> originally introduced by old commit, while this need be fixed firstly.

Just a little curious about the rule to cope with this specific case. If 
"crashkernel=size@offset" was passed

but reserve failed, should try again to allocate in high memory, 
regardless the specified size@offset,

or just throw a warning and return? Since I noticed the current logic 
here on Arm64 is to check if !fixed_base first

before retrying.


Or have I missed anything else?

>> -		/* Try again without restricting region to 32bit addressible memory */
>> +		/* 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, (unsigned long)dma32_phys_limit),
>> +						       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
>>
BR,

Jiahao

Re: [PATCH -next v2 1/2] riscv: kdump: Implement crashkernel=X,[high,low]

[Baoquan He]

On 03/30/23 at 09:40pm, chenjiahao (C) wrote:
......
> Agreed, I will clean this up later in next version.
> > > +		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(boot_command_line, 0, &crash_low_size, &crash_base);
> > > +		if (ret == -ENOENT)
> > > +			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
> > > +		else if (ret)
> > > +			return;
> > > +
> > > +		search_start = dma32_phys_limit;
> > > +	} else if (ret || !crash_size) {
> > > +		/* Invalid argument value specified */
> > >   		return;
> > > +	}
> > >   	crash_size = PAGE_ALIGN(crash_size);
> > > @@ -1201,16 +1246,26 @@ 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, (unsigned long)dma32_phys_limit));
> > >   	if (crash_base == 0) {
> > The above conditional check isn't right. If crashkernel=size@offset
> > specified, the reservation failure won't trigger retry. This seems to be
> > originally introduced by old commit, while this need be fixed firstly.
> 
> Just a little curious about the rule to cope with this specific case. If
> "crashkernel=size@offset" was passed
> 
> but reserve failed, should try again to allocate in high memory, regardless
> the specified size@offset,
> 
> or just throw a warning and return? Since I noticed the current logic here
> on Arm64 is to check if !fixed_base first

Yeah, we need mark the "crashkernel=size@offset" case and avoid to
retry. Because you won't succeed if  memblock has already failed to
reserve an unavailable memory region, retry is meaningless. This has
been done in x86, arm64.

Re: [PATCH -next v2 1/2] riscv: kdump: Implement crashkernel=X,[high,low]

[chenjiahao (C)]

On 2023/3/31 7:32, Baoquan He wrote:
> On 03/30/23 at 09:40pm, chenjiahao (C) wrote:
> ......
>> Agreed, I will clean this up later in next version.
>>>> +		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(boot_command_line, 0, &crash_low_size, &crash_base);
>>>> +		if (ret == -ENOENT)
>>>> +			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
>>>> +		else if (ret)
>>>> +			return;
>>>> +
>>>> +		search_start = dma32_phys_limit;
>>>> +	} else if (ret || !crash_size) {
>>>> +		/* Invalid argument value specified */
>>>>    		return;
>>>> +	}
>>>>    	crash_size = PAGE_ALIGN(crash_size);
>>>> @@ -1201,16 +1246,26 @@ 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, (unsigned long)dma32_phys_limit));
>>>>    	if (crash_base == 0) {
>>> The above conditional check isn't right. If crashkernel=size@offset
>>> specified, the reservation failure won't trigger retry. This seems to be
>>> originally introduced by old commit, while this need be fixed firstly.
>> Just a little curious about the rule to cope with this specific case. If
>> "crashkernel=size@offset" was passed
>>
>> but reserve failed, should try again to allocate in high memory, regardless
>> the specified size@offset,
>>
>> or just throw a warning and return? Since I noticed the current logic here
>> on Arm64 is to check if !fixed_base first
> Yeah, we need mark the "crashkernel=size@offset" case and avoid to
> retry. Because you won't succeed if  memblock has already failed to
> reserve an unavailable memory region, retry is meaningless. This has
> been done in x86, arm64.

Make sense, thanks.

Actually, in my previous tests, the result in this case is the same
as expectation, i.e. when allocating "crashkernel=size@offset" failed
on low memory, it would retry but return on failure. Since the
search_end is assigned with offset + size, which is lower than DMA32
limit, the second allocation is definitely invalid.

But for sure, to make the code easy to read and eradicate other
possible corner cases, I will check if !fixed_base first on retry.

>