diff options
| -rw-r--r-- | arch/x86/include/asm/tlbbatch.h | 16 | ||||
| -rw-r--r-- | arch/x86/include/asm/tlbflush.h | 8 | ||||
| -rw-r--r-- | arch/x86/mm/tlb.c | 17 | ||||
| -rw-r--r-- | include/linux/mm_types_task.h | 15 | ||||
| -rw-r--r-- | mm/rmap.c | 16 |
5 files changed, 54 insertions, 18 deletions
diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h new file mode 100644 index 000000000000..01a6de16fb96 --- /dev/null +++ b/arch/x86/include/asm/tlbbatch.h @@ -0,0 +1,16 @@ +#ifndef _ARCH_X86_TLBBATCH_H +#define _ARCH_X86_TLBBATCH_H + +#include <linux/cpumask.h> + +#ifdef CONFIG_SMP +struct arch_tlbflush_unmap_batch { + /* + * Each bit set is a CPU that potentially has a TLB entry for one of + * the PFNs being flushed.. + */ + struct cpumask cpumask; +}; +#endif + +#endif /* _ARCH_X86_TLBBATCH_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index b9db0f8fef55..8f6e2f87511b 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -329,6 +329,14 @@ static inline void reset_lazy_tlbstate(void) this_cpu_write(cpu_tlbstate.active_mm, &init_mm); } +static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm) +{ + cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); +} + +extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); + #endif /* SMP */ #ifndef CONFIG_PARAVIRT diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 4d303864b310..743e4c6b4529 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -395,6 +395,23 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) } } +void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + int cpu = get_cpu(); + + if (cpumask_test_cpu(cpu, &batch->cpumask)) { + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); + } + + if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) + flush_tlb_others(&batch->cpumask, NULL, 0, TLB_FLUSH_ALL); + cpumask_clear(&batch->cpumask); + + put_cpu(); +} + static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 136dfdf63ba1..fc412fbd80bd 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -14,6 +14,10 @@ #include <asm/page.h> +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH +#include <asm/tlbbatch.h> +#endif + #define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) #define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) @@ -67,12 +71,15 @@ struct page_frag { struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* - * Each bit set is a CPU that potentially has a TLB entry for one of - * the PFNs being flushed. See set_tlb_ubc_flush_pending(). + * 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 + * will be flushed on all CPUs by the time that arch_tlbbatch_flush() + * returns. */ - struct cpumask cpumask; + struct arch_tlbflush_unmap_batch arch; - /* True if any bit in cpumask is set */ + /* True if a flush is needed. */ bool flush_required; /* diff --git a/mm/rmap.c b/mm/rmap.c index d405f0e0ee96..130c238fe384 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -579,25 +579,13 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma) void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; - int cpu; if (!tlb_ubc->flush_required) return; - cpu = get_cpu(); - - if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - local_flush_tlb(); - trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); - } - - if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) - flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL); - cpumask_clear(&tlb_ubc->cpumask); + arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; - put_cpu(); } /* Flush iff there are potentially writable TLB entries that can race with IO */ @@ -613,7 +601,7 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; - cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm)); + arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; /* |