diff mbox series

[06/15] arm64: Add KHO support

Message ID 20231213000452.88295-7-graf@amazon.com (mailing list archive)
State New
Headers show
Series kexec: Allow preservation of ftrace buffers | expand

Commit Message

Alexander Graf Dec. 13, 2023, 12:04 a.m. UTC
We now have all bits in place to support KHO kexecs. This patch adds
awareness of KHO in the kexec file as well as boot path for arm64 and
adds the respective kconfig option to the architecture so that it can
use KHO successfully.

Signed-off-by: Alexander Graf <graf@amazon.com>
---
 arch/arm64/Kconfig        | 12 ++++++++++++
 arch/arm64/kernel/setup.c |  2 ++
 arch/arm64/mm/init.c      |  8 ++++++++
 drivers/of/fdt.c          | 41 +++++++++++++++++++++++++++++++++++++++
 drivers/of/kexec.c        | 36 ++++++++++++++++++++++++++++++++++
 5 files changed, 99 insertions(+)

Comments

kernel test robot Dec. 13, 2023, 11:22 a.m. UTC | #1
Hi Alexander,

kernel test robot noticed the following build warnings:

[auto build test WARNING on tip/x86/core]
[also build test WARNING on arm64/for-next/core akpm-mm/mm-everything linus/master v6.7-rc5 next-20231213]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Alexander-Graf/mm-memblock-Add-support-for-scratch-memory/20231213-080941
base:   tip/x86/core
patch link:    https://lore.kernel.org/r/20231213000452.88295-7-graf%40amazon.com
patch subject: [PATCH 06/15] arm64: Add KHO support
config: i386-buildonly-randconfig-001-20231213 (https://download.01.org/0day-ci/archive/20231213/202312131958.BJ7skdaN-lkp@intel.com/config)
compiler: clang version 16.0.4 (https://github.com/llvm/llvm-project.git ae42196bc493ffe877a7e3dff8be32035dea4d07)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20231213/202312131958.BJ7skdaN-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202312131958.BJ7skdaN-lkp@intel.com/

All warnings (new ones prefixed by >>):

>> drivers/of/fdt.c:1012:13: warning: no previous prototype for function 'early_init_dt_check_kho' [-Wmissing-prototypes]
   void __init early_init_dt_check_kho(void)
               ^
   drivers/of/fdt.c:1012:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
   void __init early_init_dt_check_kho(void)
   ^
   static 
   1 warning generated.


vim +/early_init_dt_check_kho +1012 drivers/of/fdt.c

  1008	
  1009	/**
  1010	 * early_init_dt_check_kho - Decode info required for kexec handover from DT
  1011	 */
> 1012	void __init early_init_dt_check_kho(void)
  1013	{
  1014	#ifdef CONFIG_KEXEC_KHO
  1015		unsigned long node = chosen_node_offset;
  1016		u64 kho_start, scratch_start, scratch_size, mem_start, mem_size;
  1017		const __be32 *p;
  1018		int l;
  1019	
  1020		if ((long)node < 0)
  1021			return;
  1022	
  1023		p = of_get_flat_dt_prop(node, "linux,kho-dt", &l);
  1024		if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
  1025			return;
  1026	
  1027		kho_start = dt_mem_next_cell(dt_root_addr_cells, &p);
  1028	
  1029		p = of_get_flat_dt_prop(node, "linux,kho-scratch", &l);
  1030		if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
  1031			return;
  1032	
  1033		scratch_start = dt_mem_next_cell(dt_root_addr_cells, &p);
  1034		scratch_size = dt_mem_next_cell(dt_root_addr_cells, &p);
  1035	
  1036		p = of_get_flat_dt_prop(node, "linux,kho-mem", &l);
  1037		if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
  1038			return;
  1039	
  1040		mem_start = dt_mem_next_cell(dt_root_addr_cells, &p);
  1041		mem_size = dt_mem_next_cell(dt_root_addr_cells, &p);
  1042	
  1043		kho_populate(kho_start, scratch_start, scratch_size, mem_start, mem_size);
  1044	#endif
  1045	}
  1046
kernel test robot Dec. 13, 2023, 1:41 p.m. UTC | #2
Hi Alexander,

kernel test robot noticed the following build warnings:

[auto build test WARNING on tip/x86/core]
[also build test WARNING on arm64/for-next/core akpm-mm/mm-everything linus/master v6.7-rc5 next-20231213]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Alexander-Graf/mm-memblock-Add-support-for-scratch-memory/20231213-080941
base:   tip/x86/core
patch link:    https://lore.kernel.org/r/20231213000452.88295-7-graf%40amazon.com
patch subject: [PATCH 06/15] arm64: Add KHO support
config: microblaze-randconfig-r133-20231213 (https://download.01.org/0day-ci/archive/20231213/202312132139.g2NKV67G-lkp@intel.com/config)
compiler: microblaze-linux-gcc (GCC) 13.2.0
reproduce: (https://download.01.org/0day-ci/archive/20231213/202312132139.g2NKV67G-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202312132139.g2NKV67G-lkp@intel.com/

sparse warnings: (new ones prefixed by >>)
>> drivers/of/fdt.c:1012:13: sparse: sparse: symbol 'early_init_dt_check_kho' was not declared. Should it be static?

vim +/early_init_dt_check_kho +1012 drivers/of/fdt.c

  1008	
  1009	/**
  1010	 * early_init_dt_check_kho - Decode info required for kexec handover from DT
  1011	 */
> 1012	void __init early_init_dt_check_kho(void)
  1013	{
  1014	#ifdef CONFIG_KEXEC_KHO
  1015		unsigned long node = chosen_node_offset;
  1016		u64 kho_start, scratch_start, scratch_size, mem_start, mem_size;
  1017		const __be32 *p;
  1018		int l;
  1019	
  1020		if ((long)node < 0)
  1021			return;
  1022	
  1023		p = of_get_flat_dt_prop(node, "linux,kho-dt", &l);
  1024		if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
  1025			return;
  1026	
  1027		kho_start = dt_mem_next_cell(dt_root_addr_cells, &p);
  1028	
  1029		p = of_get_flat_dt_prop(node, "linux,kho-scratch", &l);
  1030		if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
  1031			return;
  1032	
  1033		scratch_start = dt_mem_next_cell(dt_root_addr_cells, &p);
  1034		scratch_size = dt_mem_next_cell(dt_root_addr_cells, &p);
  1035	
  1036		p = of_get_flat_dt_prop(node, "linux,kho-mem", &l);
  1037		if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
  1038			return;
  1039	
  1040		mem_start = dt_mem_next_cell(dt_root_addr_cells, &p);
  1041		mem_size = dt_mem_next_cell(dt_root_addr_cells, &p);
  1042	
  1043		kho_populate(kho_start, scratch_start, scratch_size, mem_start, mem_size);
  1044	#endif
  1045	}
  1046
Rob Herring (Arm) Dec. 14, 2023, 10:36 p.m. UTC | #3
On Wed, Dec 13, 2023 at 12:04:43AM +0000, Alexander Graf wrote:
> We now have all bits in place to support KHO kexecs. This patch adds
> awareness of KHO in the kexec file as well as boot path for arm64 and
> adds the respective kconfig option to the architecture so that it can
> use KHO successfully.
> 
> Signed-off-by: Alexander Graf <graf@amazon.com>
> ---
>  arch/arm64/Kconfig        | 12 ++++++++++++
>  arch/arm64/kernel/setup.c |  2 ++
>  arch/arm64/mm/init.c      |  8 ++++++++
>  drivers/of/fdt.c          | 41 +++++++++++++++++++++++++++++++++++++++
>  drivers/of/kexec.c        | 36 ++++++++++++++++++++++++++++++++++
>  5 files changed, 99 insertions(+)
> 
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 7b071a00425d..1ba338ce7598 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -1501,6 +1501,18 @@ config ARCH_SUPPORTS_CRASH_DUMP
>  config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
>  	def_bool CRASH_CORE
>  
> +config KEXEC_KHO
> +	bool "kexec handover"
> +	depends on KEXEC
> +	select MEMBLOCK_SCRATCH
> +	select LIBFDT
> +	select CMA
> +	help
> +	  Allow kexec to hand over state across kernels by generating and
> +	  passing additional metadata to the target kernel. This is useful
> +	  to keep data or state alive across the kexec. For this to work,
> +	  both source and target kernels need to have this option enabled.

Why do we have the same kconfig entry twice? Here and x86.

> +
>  config TRANS_TABLE
>  	def_bool y
>  	depends on HIBERNATION || KEXEC_CORE
> diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
> index 417a8a86b2db..8035b673d96d 100644
> --- a/arch/arm64/kernel/setup.c
> +++ b/arch/arm64/kernel/setup.c
> @@ -346,6 +346,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
>  
>  	paging_init();
>  
> +	kho_reserve_mem();
> +
>  	acpi_table_upgrade();
>  
>  	/* Parse the ACPI tables for possible boot-time configuration */
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index 74c1db8ce271..254d82f3383a 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -358,6 +358,8 @@ void __init bootmem_init(void)
>  	 */
>  	arch_reserve_crashkernel();
>  
> +	kho_reserve();
> +

reserve what? It is not obvious what the difference between 
kho_reserve_mem() and kho_reserve() are.

>  	memblock_dump_all();
>  }
>  
> @@ -386,6 +388,12 @@ void __init mem_init(void)
>  	/* this will put all unused low memory onto the freelists */
>  	memblock_free_all();
>  
> +	/*
> +	 * Now that all KHO pages are marked as reserved, let's flip them back
> +	 * to normal pages with accurate refcount.
> +	 */
> +	kho_populate_refcount();
> +
>  	/*
>  	 * Check boundaries twice: Some fundamental inconsistencies can be
>  	 * detected at build time already.
> diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
> index bf502ba8da95..af95139351ed 100644
> --- a/drivers/of/fdt.c
> +++ b/drivers/of/fdt.c
> @@ -1006,6 +1006,44 @@ void __init early_init_dt_check_for_usable_mem_range(void)
>  		memblock_add(rgn[i].base, rgn[i].size);
>  }
>  
> +/**
> + * early_init_dt_check_kho - Decode info required for kexec handover from DT
> + */
> +void __init early_init_dt_check_kho(void)
> +{
> +#ifdef CONFIG_KEXEC_KHO

if (!IS_ENABLED(CONFIG_KEXEC_KHO))
  return;

You'll need a kho_populate() stub.

> +	unsigned long node = chosen_node_offset;
> +	u64 kho_start, scratch_start, scratch_size, mem_start, mem_size;
> +	const __be32 *p;
> +	int l;
> +
> +	if ((long)node < 0)
> +		return;
> +
> +	p = of_get_flat_dt_prop(node, "linux,kho-dt", &l);
> +	if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
> +		return;
> +
> +	kho_start = dt_mem_next_cell(dt_root_addr_cells, &p);
> +
> +	p = of_get_flat_dt_prop(node, "linux,kho-scratch", &l);
> +	if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
> +		return;
> +
> +	scratch_start = dt_mem_next_cell(dt_root_addr_cells, &p);
> +	scratch_size = dt_mem_next_cell(dt_root_addr_cells, &p);
> +
> +	p = of_get_flat_dt_prop(node, "linux,kho-mem", &l);
> +	if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
> +		return;
> +
> +	mem_start = dt_mem_next_cell(dt_root_addr_cells, &p);
> +	mem_size = dt_mem_next_cell(dt_root_addr_cells, &p);
> +
> +	kho_populate(kho_start, scratch_start, scratch_size, mem_start, mem_size);
> +#endif
> +}
> +
>  #ifdef CONFIG_SERIAL_EARLYCON
>  
>  int __init early_init_dt_scan_chosen_stdout(void)
> @@ -1304,6 +1342,9 @@ void __init early_init_dt_scan_nodes(void)
>  
>  	/* Handle linux,usable-memory-range property */
>  	early_init_dt_check_for_usable_mem_range();
> +
> +	/* Handle kexec handover */
> +	early_init_dt_check_kho();
>  }
>  
>  bool __init early_init_dt_scan(void *params)
> diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c
> index 68278340cecf..a612e6bb8c75 100644
> --- a/drivers/of/kexec.c
> +++ b/drivers/of/kexec.c
> @@ -264,6 +264,37 @@ static inline int setup_ima_buffer(const struct kimage *image, void *fdt,
>  }
>  #endif /* CONFIG_IMA_KEXEC */
>  
> +static int kho_add_chosen(const struct kimage *image, void *fdt, int chosen_node)
> +{
> +	int ret = 0;
> +
> +#ifdef CONFIG_KEXEC_KHO

ditto

Though perhaps image->kho is not defined?


> +	if (!image->kho.dt.buffer || !image->kho.mem_cache.buffer)
> +		goto out;
> +
> +	pr_debug("Adding kho metadata to DT");
> +
> +	ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, "linux,kho-dt",
> +				       image->kho.dt.mem, image->kho.dt.memsz);
> +	if (ret)
> +		goto out;
> +
> +	ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, "linux,kho-scratch",
> +				       kho_scratch_phys, kho_scratch_len);
> +	if (ret)
> +		goto out;
> +
> +	ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, "linux,kho-mem",
> +				       image->kho.mem_cache.mem,
> +				       image->kho.mem_cache.bufsz);
> +	if (ret)
> +		goto out;
> +
> +out:
> +#endif
> +	return ret;
> +}
> +
>  /*
>   * of_kexec_alloc_and_setup_fdt - Alloc and setup a new Flattened Device Tree
>   *
> @@ -412,6 +443,11 @@ void *of_kexec_alloc_and_setup_fdt(const struct kimage *image,
>  		}
>  	}
>  
> +	/* Add kho metadata if this is a KHO image */
> +	ret = kho_add_chosen(image, fdt, chosen_node);
> +	if (ret)
> +		goto out;
> +
>  	/* add bootargs */
>  	if (cmdline) {
>  		ret = fdt_setprop_string(fdt, chosen_node, "bootargs", cmdline);
> -- 
> 2.40.1
> 
> 
> 
> 
> Amazon Development Center Germany GmbH
> Krausenstr. 38
> 10117 Berlin
> Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss
> Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B
> Sitz: Berlin
> Ust-ID: DE 289 237 879
> 
> 
>
Alexander Graf Dec. 18, 2023, 11:01 p.m. UTC | #4
Hey Rob!

On 14.12.23 23:36, Rob Herring wrote:
> On Wed, Dec 13, 2023 at 12:04:43AM +0000, Alexander Graf wrote:
>> We now have all bits in place to support KHO kexecs. This patch adds
>> awareness of KHO in the kexec file as well as boot path for arm64 and
>> adds the respective kconfig option to the architecture so that it can
>> use KHO successfully.
>>
>> Signed-off-by: Alexander Graf <graf@amazon.com>
>> ---
>>   arch/arm64/Kconfig        | 12 ++++++++++++
>>   arch/arm64/kernel/setup.c |  2 ++
>>   arch/arm64/mm/init.c      |  8 ++++++++
>>   drivers/of/fdt.c          | 41 +++++++++++++++++++++++++++++++++++++++
>>   drivers/of/kexec.c        | 36 ++++++++++++++++++++++++++++++++++
>>   5 files changed, 99 insertions(+)
>>
>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>> index 7b071a00425d..1ba338ce7598 100644
>> --- a/arch/arm64/Kconfig
>> +++ b/arch/arm64/Kconfig
>> @@ -1501,6 +1501,18 @@ config ARCH_SUPPORTS_CRASH_DUMP
>>   config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
>>        def_bool CRASH_CORE
>>
>> +config KEXEC_KHO
>> +     bool "kexec handover"
>> +     depends on KEXEC
>> +     select MEMBLOCK_SCRATCH
>> +     select LIBFDT
>> +     select CMA
>> +     help
>> +       Allow kexec to hand over state across kernels by generating and
>> +       passing additional metadata to the target kernel. This is useful
>> +       to keep data or state alive across the kexec. For this to work,
>> +       both source and target kernels need to have this option enabled.
> Why do we have the same kconfig entry twice? Here and x86.


This was how the kexec config options were done when I wrote the patches 
originally. Since then, looks like Eric DeVolder has cleaned up things 
quite nicely. I'll adapt the new way.


>
>> +
>>   config TRANS_TABLE
>>        def_bool y
>>        depends on HIBERNATION || KEXEC_CORE
>> diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
>> index 417a8a86b2db..8035b673d96d 100644
>> --- a/arch/arm64/kernel/setup.c
>> +++ b/arch/arm64/kernel/setup.c
>> @@ -346,6 +346,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
>>
>>        paging_init();
>>
>> +     kho_reserve_mem();
>> +
>>        acpi_table_upgrade();
>>
>>        /* Parse the ACPI tables for possible boot-time configuration */
>> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
>> index 74c1db8ce271..254d82f3383a 100644
>> --- a/arch/arm64/mm/init.c
>> +++ b/arch/arm64/mm/init.c
>> @@ -358,6 +358,8 @@ void __init bootmem_init(void)
>>         */
>>        arch_reserve_crashkernel();
>>
>> +     kho_reserve();
>> +
> reserve what? It is not obvious what the difference between
> kho_reserve_mem() and kho_reserve() are.


Yeah, I agree. I was struggling to find good names for them. What they 
do is:

kho_reserve() - Reserve CMA memory for later kexec. We use this memory 
region as scratch memory later.
kho_reserve_mem() - Post-KHO. Creates memory reservations inside 
memblocks for pre-KHO handed over memory.

For v2, I'll change them to kho_reserve_scratch() and 
kho_reserve_previous_mem() unless you have better ideas :)


>
>>        memblock_dump_all();
>>   }
>>
>> @@ -386,6 +388,12 @@ void __init mem_init(void)
>>        /* this will put all unused low memory onto the freelists */
>>        memblock_free_all();
>>
>> +     /*
>> +      * Now that all KHO pages are marked as reserved, let's flip them back
>> +      * to normal pages with accurate refcount.
>> +      */
>> +     kho_populate_refcount();
>> +
>>        /*
>>         * Check boundaries twice: Some fundamental inconsistencies can be
>>         * detected at build time already.
>> diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
>> index bf502ba8da95..af95139351ed 100644
>> --- a/drivers/of/fdt.c
>> +++ b/drivers/of/fdt.c
>> @@ -1006,6 +1006,44 @@ void __init early_init_dt_check_for_usable_mem_range(void)
>>                memblock_add(rgn[i].base, rgn[i].size);
>>   }
>>
>> +/**
>> + * early_init_dt_check_kho - Decode info required for kexec handover from DT
>> + */
>> +void __init early_init_dt_check_kho(void)
>> +{
>> +#ifdef CONFIG_KEXEC_KHO
> if (!IS_ENABLED(CONFIG_KEXEC_KHO))
>    return;
>
> You'll need a kho_populate() stub.


Always happy to remove #ifdefs :)


>
>> +     unsigned long node = chosen_node_offset;
>> +     u64 kho_start, scratch_start, scratch_size, mem_start, mem_size;
>> +     const __be32 *p;
>> +     int l;
>> +
>> +     if ((long)node < 0)
>> +             return;
>> +
>> +     p = of_get_flat_dt_prop(node, "linux,kho-dt", &l);
>> +     if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
>> +             return;
>> +
>> +     kho_start = dt_mem_next_cell(dt_root_addr_cells, &p);
>> +
>> +     p = of_get_flat_dt_prop(node, "linux,kho-scratch", &l);
>> +     if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
>> +             return;
>> +
>> +     scratch_start = dt_mem_next_cell(dt_root_addr_cells, &p);
>> +     scratch_size = dt_mem_next_cell(dt_root_addr_cells, &p);
>> +
>> +     p = of_get_flat_dt_prop(node, "linux,kho-mem", &l);
>> +     if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
>> +             return;
>> +
>> +     mem_start = dt_mem_next_cell(dt_root_addr_cells, &p);
>> +     mem_size = dt_mem_next_cell(dt_root_addr_cells, &p);
>> +
>> +     kho_populate(kho_start, scratch_start, scratch_size, mem_start, mem_size);
>> +#endif
>> +}
>> +
>>   #ifdef CONFIG_SERIAL_EARLYCON
>>
>>   int __init early_init_dt_scan_chosen_stdout(void)
>> @@ -1304,6 +1342,9 @@ void __init early_init_dt_scan_nodes(void)
>>
>>        /* Handle linux,usable-memory-range property */
>>        early_init_dt_check_for_usable_mem_range();
>> +
>> +     /* Handle kexec handover */
>> +     early_init_dt_check_kho();
>>   }
>>
>>   bool __init early_init_dt_scan(void *params)
>> diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c
>> index 68278340cecf..a612e6bb8c75 100644
>> --- a/drivers/of/kexec.c
>> +++ b/drivers/of/kexec.c
>> @@ -264,6 +264,37 @@ static inline int setup_ima_buffer(const struct kimage *image, void *fdt,
>>   }
>>   #endif /* CONFIG_IMA_KEXEC */
>>
>> +static int kho_add_chosen(const struct kimage *image, void *fdt, int chosen_node)
>> +{
>> +     int ret = 0;
>> +
>> +#ifdef CONFIG_KEXEC_KHO
> ditto
>
> Though perhaps image->kho is not defined?


Correct, it is not. But I'm happy to have a few local variables that I 
stash the image->kho contents inside an ifdef into so we can at least 
compile check all libfdt invocations.


Alex




Amazon Development Center Germany GmbH
Krausenstr. 38
10117 Berlin
Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss
Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B
Sitz: Berlin
Ust-ID: DE 289 237 879
diff mbox series

Patch

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7b071a00425d..1ba338ce7598 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1501,6 +1501,18 @@  config ARCH_SUPPORTS_CRASH_DUMP
 config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
 	def_bool CRASH_CORE
 
+config KEXEC_KHO
+	bool "kexec handover"
+	depends on KEXEC
+	select MEMBLOCK_SCRATCH
+	select LIBFDT
+	select CMA
+	help
+	  Allow kexec to hand over state across kernels by generating and
+	  passing additional metadata to the target kernel. This is useful
+	  to keep data or state alive across the kexec. For this to work,
+	  both source and target kernels need to have this option enabled.
+
 config TRANS_TABLE
 	def_bool y
 	depends on HIBERNATION || KEXEC_CORE
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 417a8a86b2db..8035b673d96d 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -346,6 +346,8 @@  void __init __no_sanitize_address setup_arch(char **cmdline_p)
 
 	paging_init();
 
+	kho_reserve_mem();
+
 	acpi_table_upgrade();
 
 	/* Parse the ACPI tables for possible boot-time configuration */
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 74c1db8ce271..254d82f3383a 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -358,6 +358,8 @@  void __init bootmem_init(void)
 	 */
 	arch_reserve_crashkernel();
 
+	kho_reserve();
+
 	memblock_dump_all();
 }
 
@@ -386,6 +388,12 @@  void __init mem_init(void)
 	/* this will put all unused low memory onto the freelists */
 	memblock_free_all();
 
+	/*
+	 * Now that all KHO pages are marked as reserved, let's flip them back
+	 * to normal pages with accurate refcount.
+	 */
+	kho_populate_refcount();
+
 	/*
 	 * Check boundaries twice: Some fundamental inconsistencies can be
 	 * detected at build time already.
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index bf502ba8da95..af95139351ed 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1006,6 +1006,44 @@  void __init early_init_dt_check_for_usable_mem_range(void)
 		memblock_add(rgn[i].base, rgn[i].size);
 }
 
+/**
+ * early_init_dt_check_kho - Decode info required for kexec handover from DT
+ */
+void __init early_init_dt_check_kho(void)
+{
+#ifdef CONFIG_KEXEC_KHO
+	unsigned long node = chosen_node_offset;
+	u64 kho_start, scratch_start, scratch_size, mem_start, mem_size;
+	const __be32 *p;
+	int l;
+
+	if ((long)node < 0)
+		return;
+
+	p = of_get_flat_dt_prop(node, "linux,kho-dt", &l);
+	if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
+		return;
+
+	kho_start = dt_mem_next_cell(dt_root_addr_cells, &p);
+
+	p = of_get_flat_dt_prop(node, "linux,kho-scratch", &l);
+	if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
+		return;
+
+	scratch_start = dt_mem_next_cell(dt_root_addr_cells, &p);
+	scratch_size = dt_mem_next_cell(dt_root_addr_cells, &p);
+
+	p = of_get_flat_dt_prop(node, "linux,kho-mem", &l);
+	if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32))
+		return;
+
+	mem_start = dt_mem_next_cell(dt_root_addr_cells, &p);
+	mem_size = dt_mem_next_cell(dt_root_addr_cells, &p);
+
+	kho_populate(kho_start, scratch_start, scratch_size, mem_start, mem_size);
+#endif
+}
+
 #ifdef CONFIG_SERIAL_EARLYCON
 
 int __init early_init_dt_scan_chosen_stdout(void)
@@ -1304,6 +1342,9 @@  void __init early_init_dt_scan_nodes(void)
 
 	/* Handle linux,usable-memory-range property */
 	early_init_dt_check_for_usable_mem_range();
+
+	/* Handle kexec handover */
+	early_init_dt_check_kho();
 }
 
 bool __init early_init_dt_scan(void *params)
diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c
index 68278340cecf..a612e6bb8c75 100644
--- a/drivers/of/kexec.c
+++ b/drivers/of/kexec.c
@@ -264,6 +264,37 @@  static inline int setup_ima_buffer(const struct kimage *image, void *fdt,
 }
 #endif /* CONFIG_IMA_KEXEC */
 
+static int kho_add_chosen(const struct kimage *image, void *fdt, int chosen_node)
+{
+	int ret = 0;
+
+#ifdef CONFIG_KEXEC_KHO
+	if (!image->kho.dt.buffer || !image->kho.mem_cache.buffer)
+		goto out;
+
+	pr_debug("Adding kho metadata to DT");
+
+	ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, "linux,kho-dt",
+				       image->kho.dt.mem, image->kho.dt.memsz);
+	if (ret)
+		goto out;
+
+	ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, "linux,kho-scratch",
+				       kho_scratch_phys, kho_scratch_len);
+	if (ret)
+		goto out;
+
+	ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, "linux,kho-mem",
+				       image->kho.mem_cache.mem,
+				       image->kho.mem_cache.bufsz);
+	if (ret)
+		goto out;
+
+out:
+#endif
+	return ret;
+}
+
 /*
  * of_kexec_alloc_and_setup_fdt - Alloc and setup a new Flattened Device Tree
  *
@@ -412,6 +443,11 @@  void *of_kexec_alloc_and_setup_fdt(const struct kimage *image,
 		}
 	}
 
+	/* Add kho metadata if this is a KHO image */
+	ret = kho_add_chosen(image, fdt, chosen_node);
+	if (ret)
+		goto out;
+
 	/* add bootargs */
 	if (cmdline) {
 		ret = fdt_setprop_string(fdt, chosen_node, "bootargs", cmdline);