[PATCH 1/1] Fixup write permission of TLB on powerpc e500 core

[Peter Zijlstra]

On Fri, 2011-07-15 at 16:07 +0800, Shan Hai wrote:
> The kernel has no write permission on COW pages by default on e500 core, this
> will cause endless loop in futex_lock_pi, because futex code assumes the kernel
> has write permission on COW pages. Grant write permission to the kernel on COW
> pages when access violation page fault occurs.
> 
> Signed-off-by: Shan Hai <haishan.bai at gmail.com>
> ---
>  arch/powerpc/include/asm/futex.h |   11 ++++++++++-
>  arch/powerpc/include/asm/tlb.h   |   25 +++++++++++++++++++++++++
>  2 files changed, 35 insertions(+), 1 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
> index c94e4a3..54c3e74 100644
> --- a/arch/powerpc/include/asm/futex.h
> +++ b/arch/powerpc/include/asm/futex.h
> @@ -8,6 +8,7 @@
>  #include <asm/errno.h>
>  #include <asm/synch.h>
>  #include <asm/asm-compat.h>
> +#include <asm/tlb.h>
>  
>  #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \
>    __asm__ __volatile ( \
> @@ -113,7 +114,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
>          : "cc", "memory");
>  
>  	*uval = prev;
> -        return ret;
> +
> +	/* Futex assumes the kernel has permission to write to
> +	 * COW pages, grant the kernel write permission on COW
> +	 * pages because it has none by default.
> +	 */
> +	if (ret == -EFAULT)
> +		__tlb_fixup_write_permission(current->mm, (unsigned long)uaddr);
> +
> +	return ret;
>  }
>  
>  #endif /* __KERNEL__ */
> diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
> index e2b428b..3863c6a 100644
> --- a/arch/powerpc/include/asm/tlb.h
> +++ b/arch/powerpc/include/asm/tlb.h
> @@ -45,5 +45,30 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
>  #endif
>  }
>  
> +/* Grant write permission to the kernel on a page. */
> +static inline void __tlb_fixup_write_permission(struct mm_struct *mm,
> +						unsigned long address)
> +{
> +#if defined(CONFIG_FSL_BOOKE)
> +	/* Grant write permission to the kernel on a page by setting TLB.SW
> +	 * bit, the bit setting operation is tricky here, calling
> +	 * handle_mm_fault with FAULT_FLAG_WRITE causes _PAGE_DIRTY bit of
> +	 * the pte to be set, the _PAGE_DIRTY of the pte is translated into
> +	 * TLB.SW on Powerpc e500 core.
> +	 */
> +
> +	struct vm_area_struct *vma;
> +
> +	vma = find_vma(mm, address);

Uhm, find_vma() needs mmap_sem, and futex_atomic_cmpxchg_inatomic() is
most certainly not called with that lock held.

> +	if (likely(vma)) {
> +		/* only fixup present page */
> +		if (follow_page(vma, address, FOLL_WRITE)) {
> +			handle_mm_fault(mm, vma, address, FAULT_FLAG_WRITE);

So how can this toggle your sw dirty/young tracking, that's pretty much
what gup(.write=1) does too!

> +			flush_tlb_page(vma, address);
> +		}
> +	}
> +#endif
> +}
> +
>  #endif /* __KERNEL__ */
>  #endif /* __ASM_POWERPC_TLB_H */