From aefa5688c070727b8729de1aef85cad7b9933fc7 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 4 Dec 2014 11:00:14 +0530 Subject: powerpc/mm: don't do tlbie for updatepp request with NO HPTE fault upatepp can get called for a nohpte fault when we find from the linux page table that the translation was hashed before. In that case we are sure that there is no existing translation, hence we could avoid doing tlbie. We could possibly race with a parallel fault filling the TLB. But that should be ok because updatepp is only ever relaxing permissions. We also look at linux pte permission bits when filling hash pte permission bits. We also hold the linux pte busy bits while inserting/updating a hashpte entry, hence a paralle update of linux pte is not possible. On the other hand mprotect involves ptep_modify_prot_start which cause a hpte invalidate and not updatepp. Performance number: We use randbox_access_bench written by Anton. Kernel with THP disabled and smaller hash page table size. 86.60% random_access_b [kernel.kallsyms] [k] .native_hpte_updatepp 2.10% random_access_b random_access_bench [.] doit 1.99% random_access_b [kernel.kallsyms] [k] .do_raw_spin_lock 1.85% random_access_b [kernel.kallsyms] [k] .native_hpte_insert 1.26% random_access_b [kernel.kallsyms] [k] .native_flush_hash_range 1.18% random_access_b [kernel.kallsyms] [k] .__delay 0.69% random_access_b [kernel.kallsyms] [k] .native_hpte_remove 0.37% random_access_b [kernel.kallsyms] [k] .clear_user_page 0.34% random_access_b [kernel.kallsyms] [k] .__hash_page_64K 0.32% random_access_b [kernel.kallsyms] [k] fast_exception_return 0.30% random_access_b [kernel.kallsyms] [k] .hash_page_mm With Fix: 27.54% random_access_b random_access_bench [.] doit 22.90% random_access_b [kernel.kallsyms] [k] .native_hpte_insert 5.76% random_access_b [kernel.kallsyms] [k] .native_hpte_remove 5.20% random_access_b [kernel.kallsyms] [k] fast_exception_return 5.12% random_access_b [kernel.kallsyms] [k] .__hash_page_64K 4.80% random_access_b [kernel.kallsyms] [k] .hash_page_mm 3.31% random_access_b [kernel.kallsyms] [k] data_access_common 1.84% random_access_b [kernel.kallsyms] [k] .trace_hardirqs_on_caller Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/machdep.h | 2 +- arch/powerpc/include/asm/mmu-hash64.h | 22 ++++++++++++++-------- arch/powerpc/include/asm/tlbflush.h | 4 ++-- 3 files changed, 17 insertions(+), 11 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index e5c0919acca..c8175a3fe56 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -42,7 +42,7 @@ struct machdep_calls { unsigned long newpp, unsigned long vpn, int bpsize, int apsize, - int ssize, int local); + int ssize, unsigned long flags); void (*hpte_updateboltedpp)(unsigned long newpp, unsigned long ea, int psize, int ssize); diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index aeebc94b2bc..4f13c3ed7ac 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -316,27 +316,33 @@ static inline unsigned long hpt_hash(unsigned long vpn, return hash & 0x7fffffffffUL; } +#define HPTE_LOCAL_UPDATE 0x1 +#define HPTE_NOHPTE_UPDATE 0x2 + extern int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, - unsigned int local, int ssize, int subpage_prot); + unsigned long flags, int ssize, int subpage_prot); extern int __hash_page_64K(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, - unsigned int local, int ssize); + unsigned long flags, int ssize); struct mm_struct; unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap); -extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap); -extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap); +extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, + unsigned long access, unsigned long trap, + unsigned long flags); +extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap, + unsigned long dsisr); int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, - pte_t *ptep, unsigned long trap, int local, int ssize, - unsigned int shift, unsigned int mmu_psize); + pte_t *ptep, unsigned long trap, unsigned long flags, + int ssize, unsigned int shift, unsigned int mmu_psize); #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, pmd_t *pmdp, unsigned long trap, - int local, int ssize, unsigned int psize); + unsigned long flags, int ssize, unsigned int psize); #else static inline int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, pmd_t *pmdp, - unsigned long trap, int local, + unsigned long trap, unsigned long flags, int ssize, unsigned int psize) { BUG(); diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 4d3ecd8d892..23d351ca030 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -125,11 +125,11 @@ static inline void arch_leave_lazy_mmu_mode(void) extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, - int ssize, int local); + int ssize, unsigned long flags); extern void flush_hash_range(unsigned long number, int local); extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr, pmd_t *pmdp, unsigned int psize, int ssize, - int local); + unsigned long flags); static inline void local_flush_tlb_mm(struct mm_struct *mm) { -- cgit v1.2.3-70-g09d2