[kernel,2/9] powerpc/mmu: Add real mode support for IOMMU preregistered memory

This makes mm_iommu_lookup() able to work in realmode by replacing
list_for_each_entry_rcu() (which can do debug stuff which can fail in
real mode) with list_for_each_entry_lockless().

This adds realmode version of mm_iommu_ua_to_hpa() which adds
explicit vmalloc'd-to-linear address conversion.
Unlike mm_iommu_ua_to_hpa(), mm_iommu_rm_ua_to_hpa() can fail.

This changes mm_iommu_preregistered() to receive @mm as in real mode
@current does not always have a correct pointer.

This adds realmode version of mm_iommu_lookup() which receives @mm
(for the same reason as for mm_iommu_preregistered()) and uses
lockless version of list_for_each_entry_rcu().

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/powerpc/include/asm/mmu_context.h |  6 ++++-
 arch/powerpc/mm/mmu_context_iommu.c    | 45 ++++++++++++++++++++++++++++++----
 2 files changed, 45 insertions(+), 6 deletions(-)

On Mon, Mar 07, 2016 at 02:41:10PM +1100, Alexey Kardashevskiy wrote:
> This makes mm_iommu_lookup() able to work in realmode by replacing
> list_for_each_entry_rcu() (which can do debug stuff which can fail in
> real mode) with list_for_each_entry_lockless().
> 
> This adds realmode version of mm_iommu_ua_to_hpa() which adds
> explicit vmalloc'd-to-linear address conversion.
> Unlike mm_iommu_ua_to_hpa(), mm_iommu_rm_ua_to_hpa() can fail.
> 
> This changes mm_iommu_preregistered() to receive @mm as in real mode
> @current does not always have a correct pointer.

So, I'd generally expect a parameter called @mm to be an mm_struct *,
not a mm_context_t.

> 
> This adds realmode version of mm_iommu_lookup() which receives @mm
> (for the same reason as for mm_iommu_preregistered()) and uses
> lockless version of list_for_each_entry_rcu().
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>



> ---
>  arch/powerpc/include/asm/mmu_context.h |  6 ++++-
>  arch/powerpc/mm/mmu_context_iommu.c    | 45 ++++++++++++++++++++++++++++++----
>  2 files changed, 45 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
> index 878c277..3ba652a 100644
> --- a/arch/powerpc/include/asm/mmu_context.h
> +++ b/arch/powerpc/include/asm/mmu_context.h
> @@ -18,7 +18,7 @@ extern void destroy_context(struct mm_struct *mm);
>  #ifdef CONFIG_SPAPR_TCE_IOMMU
>  struct mm_iommu_table_group_mem_t;
>  
> -extern bool mm_iommu_preregistered(void);
> +extern bool mm_iommu_preregistered(mm_context_t *mm);
>  extern long mm_iommu_get(unsigned long ua, unsigned long entries,
>  		struct mm_iommu_table_group_mem_t **pmem);
>  extern long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem);
> @@ -26,10 +26,14 @@ extern void mm_iommu_init(mm_context_t *ctx);
>  extern void mm_iommu_cleanup(mm_context_t *ctx);
>  extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
>  		unsigned long size);
> +extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(mm_context_t *mm,
> +		unsigned long ua, unsigned long size);
>  extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
>  		unsigned long entries);
>  extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
>  		unsigned long ua, unsigned long *hpa);
> +extern long mm_iommu_rm_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
> +		unsigned long ua, unsigned long *hpa);
>  extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
>  extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
>  #endif
> diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
> index da6a216..aa1565d 100644
> --- a/arch/powerpc/mm/mmu_context_iommu.c
> +++ b/arch/powerpc/mm/mmu_context_iommu.c
> @@ -63,12 +63,9 @@ static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
>  	return ret;
>  }
>  
> -bool mm_iommu_preregistered(void)
> +bool mm_iommu_preregistered(mm_context_t *mm)
>  {
> -	if (!current || !current->mm)
> -		return false;
> -
> -	return !list_empty(&current->mm->context.iommu_group_mem_list);
> +	return !list_empty(&mm->iommu_group_mem_list);
>  }
>  EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
>  
> @@ -231,6 +228,24 @@ unlock_exit:
>  }
>  EXPORT_SYMBOL_GPL(mm_iommu_put);
>  
> +struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(mm_context_t *mm,
> +		unsigned long ua, unsigned long size)
> +{
> +	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;

I think you could do with a comment here explaining why the lockless
traversal is safe.

> +	list_for_each_entry_lockless(mem, &mm->iommu_group_mem_list, next) {
> +		if ((mem->ua <= ua) &&
> +				(ua + size <= mem->ua +
> +				 (mem->entries << PAGE_SHIFT))) {
> +			ret = mem;
> +			break;
> +		}
> +	}
> +
> +	return ret;
> +}
> +EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm);
> +
>  struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
>  		unsigned long size)
>  {
> @@ -284,6 +299,26 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
>  }
>  EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
>  
> +long mm_iommu_rm_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
> +		unsigned long ua, unsigned long *hpa)
> +{
> +	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
> +	void *va = &mem->hpas[entry];
> +	unsigned long *ra;
> +
> +	if (entry >= mem->entries)
> +		return -EFAULT;
> +
> +	ra = (void *) vmalloc_to_phys(va);
> +	if (!ra)
> +		return -EFAULT;
> +
> +	*hpa = *ra | (ua & ~PAGE_MASK);
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(mm_iommu_rm_ua_to_hpa);
> +
>  long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
>  {
>  	if (atomic64_inc_not_zero(&mem->mapped))