diff options
| author | Nadav Amit <namit@vmware.com> | 2021-02-20 15:17:08 -0800 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2021-03-06 12:59:10 +0100 |
| commit | 2f4305b19fe6a2a261d76c21856c5598f7d878fe (patch) | |
| tree | 061ebf3ef8372e4da41a4c113127381207bc1d0c /arch/x86/mm | |
| parent | 4ce94eabac16b1d2c95762b40f49e5654ab288d7 (diff) | |
x86/mm/tlb: Privatize cpu_tlbstate
cpu_tlbstate is mostly private and only the variable is_lazy is shared.
This causes some false-sharing when TLB flushes are performed.
Break cpu_tlbstate intro cpu_tlbstate and cpu_tlbstate_shared, and mark
each one accordingly.
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20210220231712.2475218-6-namit@vmware.com
Diffstat (limited to 'arch/x86/mm')
| -rw-r--r-- | arch/x86/mm/init.c | 2 | ||||
| -rw-r--r-- | arch/x86/mm/tlb.c | 17 |
2 files changed, 11 insertions, 8 deletions
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index dd694fb93916..ed2e36748758 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1017,7 +1017,7 @@ void __init zone_sizes_init(void) free_area_init(max_zone_pfns); } -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { +__visible DEFINE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8db87cd92e6b..345a0aff5de4 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -300,7 +300,7 @@ void leave_mm(int cpu) return; /* Warn if we're not lazy. */ - WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy)); + WARN_ON(!this_cpu_read(cpu_tlbstate_shared.is_lazy)); switch_mm(NULL, &init_mm, NULL); } @@ -424,7 +424,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, { struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); - bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy); + bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy); unsigned cpu = smp_processor_id(); u64 next_tlb_gen; bool need_flush; @@ -469,7 +469,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, __flush_tlb_all(); } #endif - this_cpu_write(cpu_tlbstate.is_lazy, false); + this_cpu_write(cpu_tlbstate_shared.is_lazy, false); /* * The membarrier system call requires a full memory barrier and @@ -490,7 +490,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, /* * Even in lazy TLB mode, the CPU should stay set in the * mm_cpumask. The TLB shootdown code can figure out from - * cpu_tlbstate.is_lazy whether or not to send an IPI. + * cpu_tlbstate_shared.is_lazy whether or not to send an IPI. */ if (WARN_ON_ONCE(real_prev != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))) @@ -598,7 +598,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) return; - this_cpu_write(cpu_tlbstate.is_lazy, true); + this_cpu_write(cpu_tlbstate_shared.is_lazy, true); } /* @@ -690,7 +690,7 @@ static void flush_tlb_func(void *info) VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != loaded_mm->context.ctx_id); - if (this_cpu_read(cpu_tlbstate.is_lazy)) { + if (this_cpu_read(cpu_tlbstate_shared.is_lazy)) { /* * We're in lazy mode. We need to at least flush our * paging-structure cache to avoid speculatively reading @@ -790,11 +790,14 @@ done: static bool tlb_is_not_lazy(int cpu) { - return !per_cpu(cpu_tlbstate.is_lazy, cpu); + return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); } static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); +DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); +EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared); + STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, const struct flush_tlb_info *info) { |