[RFC,v1,01/10] book3s64/hash: Remove kfence support temporarily

Kfence on book3s Hash on pseries is anyways broken. It fails to boot
due to RMA size limitation. That is because, kfence with Hash uses
debug_pagealloc infrastructure. debug_pagealloc allocates linear map
for entire dram size instead of just kfence relevant objects.
This means for 16TB of DRAM it will require (16TB >> PAGE_SHIFT)
which is 256MB which is half of RMA region on P8.
crash kernel reserves 256MB and we also need 2048 * 16KB * 3 for
emergency stack and some more for paca allocations.
That means there is not enough memory for reserving the full linear map
in the RMA region, if the DRAM size is too big (>=16TB)
(The issue is seen above 8TB with crash kernel 256 MB reservation).

Now Kfence does not require linear memory map for entire DRAM.
It only needs for kfence objects. So this patch temporarily removes the
kfence functionality since debug_pagealloc code needs some refactoring.
We will bring in kfence on Hash support in later patches.

Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
---
 arch/powerpc/include/asm/kfence.h     |  5 +++++
 arch/powerpc/mm/book3s64/hash_utils.c | 16 +++++++++++-----
 2 files changed, 16 insertions(+), 5 deletions(-)

Le 31/07/2024 à 09:56, Ritesh Harjani (IBM) a écrit :
> [Vous ne recevez pas souvent de courriers de ritesh.list@gmail.com. Découvrez pourquoi ceci est important à https://aka.ms/LearnAboutSenderIdentification ]
> 
> Kfence on book3s Hash on pseries is anyways broken. It fails to boot
> due to RMA size limitation. That is because, kfence with Hash uses
> debug_pagealloc infrastructure. debug_pagealloc allocates linear map
> for entire dram size instead of just kfence relevant objects.
> This means for 16TB of DRAM it will require (16TB >> PAGE_SHIFT)
> which is 256MB which is half of RMA region on P8.
> crash kernel reserves 256MB and we also need 2048 * 16KB * 3 for
> emergency stack and some more for paca allocations.
> That means there is not enough memory for reserving the full linear map
> in the RMA region, if the DRAM size is too big (>=16TB)
> (The issue is seen above 8TB with crash kernel 256 MB reservation).
> 
> Now Kfence does not require linear memory map for entire DRAM.
> It only needs for kfence objects. So this patch temporarily removes the
> kfence functionality since debug_pagealloc code needs some refactoring.
> We will bring in kfence on Hash support in later patches.
> 
> Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
> ---
>   arch/powerpc/include/asm/kfence.h     |  5 +++++
>   arch/powerpc/mm/book3s64/hash_utils.c | 16 +++++++++++-----
>   2 files changed, 16 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/kfence.h b/arch/powerpc/include/asm/kfence.h
> index fab124ada1c7..f3a9476a71b3 100644
> --- a/arch/powerpc/include/asm/kfence.h
> +++ b/arch/powerpc/include/asm/kfence.h
> @@ -10,6 +10,7 @@
> 
>   #include <linux/mm.h>
>   #include <asm/pgtable.h>
> +#include <asm/mmu.h>
> 
>   #ifdef CONFIG_PPC64_ELF_ABI_V1
>   #define ARCH_FUNC_PREFIX "."
> @@ -25,6 +26,10 @@ static inline void disable_kfence(void)
> 
>   static inline bool arch_kfence_init_pool(void)
>   {
> +#ifdef CONFIG_PPC64
> +       if (!radix_enabled())
> +               return false;
> +#endif

Avoid #ifdefs whenever possible. Here you can do:

	if (IS_ENABLED(CONFIG_PPC64) && !radix_enabled())
		return false;

>          return !kfence_disabled;
>   }
>   #endif
> diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
> index 01c3b4b65241..1a1b50735fa0 100644
> --- a/arch/powerpc/mm/book3s64/hash_utils.c
> +++ b/arch/powerpc/mm/book3s64/hash_utils.c
> @@ -431,7 +431,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
>                          break;
> 
>                  cond_resched();
> -               if (debug_pagealloc_enabled_or_kfence() &&
> +               if (debug_pagealloc_enabled() &&
>                          (paddr >> PAGE_SHIFT) < linear_map_hash_count)
>                          linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80;
>          }
> @@ -814,7 +814,7 @@ static void __init htab_init_page_sizes(void)
>          bool aligned = true;
>          init_hpte_page_sizes();
> 
> -       if (!debug_pagealloc_enabled_or_kfence()) {
> +       if (!debug_pagealloc_enabled()) {
>                  /*
>                   * Pick a size for the linear mapping. Currently, we only
>                   * support 16M, 1M and 4K which is the default
> @@ -1134,7 +1134,7 @@ static void __init htab_initialize(void)
> 
>          prot = pgprot_val(PAGE_KERNEL);
> 
> -       if (debug_pagealloc_enabled_or_kfence()) {
> +       if (debug_pagealloc_enabled()) {
>                  linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
>                  linear_map_hash_slots = memblock_alloc_try_nid(
>                                  linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT,
> @@ -2117,7 +2117,7 @@ void hpt_do_stress(unsigned long ea, unsigned long hpte_group)
>          }
>   }
> 
> -#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
> +#if defined(CONFIG_DEBUG_PAGEALLOC)

Use #ifdef

>   static DEFINE_RAW_SPINLOCK(linear_map_hash_lock);
> 
>   static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
> @@ -2191,7 +2191,13 @@ int hash__kernel_map_pages(struct page *page, int numpages, int enable)
>          local_irq_restore(flags);
>          return 0;
>   }
> -#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_KFENCE */
> +#else /* CONFIG_DEBUG_PAGEALLOC */
> +int hash__kernel_map_pages(struct page *page, int numpages,
> +                                        int enable)
> +{
> +       return 0;
> +}
> +#endif /* CONFIG_DEBUG_PAGEALLOC */
> 
>   void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
>                                  phys_addr_t first_memblock_size)
> --
> 2.45.2
>

Sorry for the delayed response. Was pulled into something else.

Christophe Leroy <christophe.leroy@csgroup.eu> writes:

> Le 31/07/2024 à 09:56, Ritesh Harjani (IBM) a écrit :
>> [Vous ne recevez pas souvent de courriers de ritesh.list@gmail.com. Découvrez pourquoi ceci est important à https://aka.ms/LearnAboutSenderIdentification ]
>> 
>> Kfence on book3s Hash on pseries is anyways broken. It fails to boot
>> due to RMA size limitation. That is because, kfence with Hash uses
>> debug_pagealloc infrastructure. debug_pagealloc allocates linear map
>> for entire dram size instead of just kfence relevant objects.
>> This means for 16TB of DRAM it will require (16TB >> PAGE_SHIFT)
>> which is 256MB which is half of RMA region on P8.
>> crash kernel reserves 256MB and we also need 2048 * 16KB * 3 for
>> emergency stack and some more for paca allocations.
>> That means there is not enough memory for reserving the full linear map
>> in the RMA region, if the DRAM size is too big (>=16TB)
>> (The issue is seen above 8TB with crash kernel 256 MB reservation).
>> 
>> Now Kfence does not require linear memory map for entire DRAM.
>> It only needs for kfence objects. So this patch temporarily removes the
>> kfence functionality since debug_pagealloc code needs some refactoring.
>> We will bring in kfence on Hash support in later patches.
>> 
>> Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
>> ---
>>   arch/powerpc/include/asm/kfence.h     |  5 +++++
>>   arch/powerpc/mm/book3s64/hash_utils.c | 16 +++++++++++-----
>>   2 files changed, 16 insertions(+), 5 deletions(-)
>> 
>> diff --git a/arch/powerpc/include/asm/kfence.h b/arch/powerpc/include/asm/kfence.h
>> index fab124ada1c7..f3a9476a71b3 100644
>> --- a/arch/powerpc/include/asm/kfence.h
>> +++ b/arch/powerpc/include/asm/kfence.h
>> @@ -10,6 +10,7 @@
>> 
>>   #include <linux/mm.h>
>>   #include <asm/pgtable.h>
>> +#include <asm/mmu.h>
>> 
>>   #ifdef CONFIG_PPC64_ELF_ABI_V1
>>   #define ARCH_FUNC_PREFIX "."
>> @@ -25,6 +26,10 @@ static inline void disable_kfence(void)
>> 
>>   static inline bool arch_kfence_init_pool(void)
>>   {
>> +#ifdef CONFIG_PPC64
>> +       if (!radix_enabled())
>> +               return false;
>> +#endif
>
> Avoid #ifdefs whenever possible. Here you can do:
>
> 	if (IS_ENABLED(CONFIG_PPC64) && !radix_enabled())
> 		return false;
>

Sure. I will change it.

>>          return !kfence_disabled;
>>   }
>>   #endif
>> diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
>> index 01c3b4b65241..1a1b50735fa0 100644
>> --- a/arch/powerpc/mm/book3s64/hash_utils.c
>> +++ b/arch/powerpc/mm/book3s64/hash_utils.c
>> @@ -431,7 +431,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
>>                          break;
>> 
>>                  cond_resched();
>> -               if (debug_pagealloc_enabled_or_kfence() &&
>> +               if (debug_pagealloc_enabled() &&
>>                          (paddr >> PAGE_SHIFT) < linear_map_hash_count)
>>                          linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80;
>>          }
>> @@ -814,7 +814,7 @@ static void __init htab_init_page_sizes(void)
>>          bool aligned = true;
>>          init_hpte_page_sizes();
>> 
>> -       if (!debug_pagealloc_enabled_or_kfence()) {
>> +       if (!debug_pagealloc_enabled()) {
>>                  /*
>>                   * Pick a size for the linear mapping. Currently, we only
>>                   * support 16M, 1M and 4K which is the default
>> @@ -1134,7 +1134,7 @@ static void __init htab_initialize(void)
>> 
>>          prot = pgprot_val(PAGE_KERNEL);
>> 
>> -       if (debug_pagealloc_enabled_or_kfence()) {
>> +       if (debug_pagealloc_enabled()) {
>>                  linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
>>                  linear_map_hash_slots = memblock_alloc_try_nid(
>>                                  linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT,
>> @@ -2117,7 +2117,7 @@ void hpt_do_stress(unsigned long ea, unsigned long hpte_group)
>>          }
>>   }
>> 
>> -#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
>> +#if defined(CONFIG_DEBUG_PAGEALLOC)
>
> Use #ifdef
>

Sure. Thanks!

-ritesh