diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt index 30f75a79ce014a12b0fd53a18979cfff557f7f2f..1ccf586c7810841593aec987e339b625a82c6745 100644 --- a/Documentation/features/vm/TLB/arch-support.txt +++ b/Documentation/features/vm/TLB/arch-support.txt @@ -9,7 +9,7 @@ | alpha: | TODO | | arc: | TODO | | arm: | TODO | - | arm64: | TODO | + | arm64: | ok | | c6x: | .. | | csky: | TODO | | h8300: | .. | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 16620146c49a9f1cedd208e3f74abc99b2ab5673..139d98a7a12d0391e824ff1520cfbae7ee08a293 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -78,6 +78,7 @@ config ARM64 select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG) select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT diff --git a/arch/arm64/include/asm/tlbbatch.h b/arch/arm64/include/asm/tlbbatch.h new file mode 100644 index 0000000000000000000000000000000000000000..fedb0b87b8db45dbb5228f41c587efbcff9ef004 --- /dev/null +++ b/arch/arm64/include/asm/tlbbatch.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARCH_ARM64_TLBBATCH_H +#define _ARCH_ARM64_TLBBATCH_H + +struct arch_tlbflush_unmap_batch { + /* + * For arm64, HW can do tlb shootdown, so we don't + * need to record cpumask for sending IPI + */ +}; + +#endif /* _ARCH_ARM64_TLBBATCH_H */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 36f02892e1df809085551f9a753a32ae91366a5f..4c28c6c4acba9b3a53cb8ddb2faf8cb2be529bd3 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -254,17 +254,23 @@ static inline void flush_tlb_mm(struct mm_struct *mm) dsb(ish); } -static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, - unsigned long uaddr) +static inline void __flush_tlb_page_nosync(struct mm_struct *mm, + unsigned long uaddr) { unsigned long addr; dsb(ishst); - addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm)); + addr = __TLBI_VADDR(uaddr, ASID(mm)); __tlbi(vale1is, addr); __tlbi_user(vale1is, addr); } +static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, + unsigned long uaddr) +{ + return __flush_tlb_page_nosync(vma->vm_mm, uaddr); +} + static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) { @@ -272,6 +278,38 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, dsb(ish); } +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) +{ +#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI + /* + * TLB flush deferral is not required on systems which are affected by + * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation + * will have two consecutive TLBI instructions with a dsb(ish) in between + * defeating the purpose (i.e save overall 'dsb ish' cost). + */ + if (unlikely(cpus_have_const_cap(ARM64_WORKAROUND_REPEAT_TLBI))) + return false; +#endif + return true; +} + +static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm, + unsigned long uaddr) +{ + __flush_tlb_page_nosync(mm, uaddr); +} + +static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm) +{ + dsb(ish); +} + +static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + dsb(ish); +} + /* * This is meant to avoid soft lock-ups on large TLB flushing ranges and not * necessarily a performance improvement. diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index fa952eadbc2eb72e6b072d26c1c6b1b8dd1412f6..1f1e5add0b974810f0c5e98b537b8c488b832d3a 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -239,6 +239,18 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false); } +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) +{ + bool should_defer = false; + + /* If remote CPUs need to be flushed then defer batch the flush */ + if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) + should_defer = true; + put_cpu(); + + return should_defer; +} + static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) { /* @@ -250,13 +262,19 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) return atomic64_inc_return(&mm->context.tlb_gen); } -static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm) +static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm, + unsigned long uaddr) { inc_mm_tlb_gen(mm); cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); } +static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm) +{ + flush_tlb_mm(mm); +} + extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); #endif /* !MODULE */ diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index c1bc6731125cbbeb99b2bbe0d4757fad6bf5031f..78bbded3b13fd72c3c30556628cf01872ff2d7e4 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -77,8 +77,8 @@ struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * The arch code makes the following promise: generic code can modify a - * PTE, then call arch_tlbbatch_add_mm() (which internally provides all - * needed barriers), then call arch_tlbbatch_flush(), and the entries + * PTE, then call arch_tlbbatch_add_pending() (which internally provides + * all needed barriers), then call arch_tlbbatch_flush(), and the entries * will be flushed on all CPUs by the time that arch_tlbbatch_flush() * returns. */ diff --git a/mm/rmap.c b/mm/rmap.c index 3e12d26d8c55e6e0ec0c8a784b4e3758a161af7a..4d9304c751d576d5bccd6cea6260510ca3eb0719 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -623,11 +623,12 @@ void try_to_unmap_flush_dirty(void) try_to_unmap_flush(); } -static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable, + unsigned long uaddr) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; - arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); + arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, uaddr); tlb_ubc->flush_required = true; /* @@ -652,17 +653,10 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { - bool should_defer = false; - if (!(flags & TTU_BATCH_FLUSH)) return false; - /* If remote CPUs need to be flushed then defer batch the flush */ - if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) - should_defer = true; - put_cpu(); - - return should_defer; + return arch_tlbbatch_should_defer(mm); } /* @@ -683,7 +677,7 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) void flush_tlb_batched_pending(struct mm_struct *mm) { if (data_race(mm->tlb_flush_batched)) { - flush_tlb_mm(mm); + arch_flush_tlb_batched_pending(mm); /* * Do not allow the compiler to re-order the clearing of @@ -694,7 +688,8 @@ void flush_tlb_batched_pending(struct mm_struct *mm) } } #else -static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable, + unsigned long uaddr) { } @@ -1573,7 +1568,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); - set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); + set_tlb_ubc_flush_pending(mm, pte_dirty(pteval), address); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); }