diff options
| author | Nicholas Piggin <npiggin@gmail.com> | 2018-06-01 20:01:20 +1000 |
|---|---|---|
| committer | Michael Ellerman <mpe@ellerman.id.au> | 2018-06-03 20:40:36 +1000 |
| commit | 85bcfaf69cbd610fdfac3351cf385809a2f4a93b (patch) | |
| tree | 0c3ec307217742cf1857462744ca588ecca006e9 /arch/powerpc/include | |
| parent | f1cb8f9beba8699dd1b4518418191499e53f7b17 (diff) | |
powerpc/64s/radix: optimise pte_update
Implementing pte_update with pte_xchg (which uses cmpxchg) is
inefficient. A single larx/stcx. works fine, no need for the less
efficient cmpxchg sequence.
Then remove the memory barriers from the operation. There is a
requirement for TLB flushing to load mm_cpumask after the store
that reduces pte permissions, which is moved into the TLB flush
code.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/include')
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/radix.h | 25 |
1 files changed, 13 insertions, 12 deletions
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 9c567d243f61..ef9f96742ce1 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -131,20 +131,21 @@ extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr, unsigned long set) { - pte_t pte; - unsigned long old_pte, new_pte; - - do { - pte = READ_ONCE(*ptep); - old_pte = pte_val(pte); - new_pte = (old_pte | set) & ~clr; - - } while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); - - return old_pte; + __be64 old_be, tmp_be; + + __asm__ __volatile__( + "1: ldarx %0,0,%3 # pte_update\n" + " andc %1,%0,%5 \n" + " or %1,%1,%4 \n" + " stdcx. %1,0,%3 \n" + " bne- 1b" + : "=&r" (old_be), "=&r" (tmp_be), "=m" (*ptep) + : "r" (ptep), "r" (cpu_to_be64(set)), "r" (cpu_to_be64(clr)) + : "cc" ); + + return be64_to_cpu(old_be); } - static inline unsigned long radix__pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long clr, |