On 16/01/2025 4:30, Rik van Riel wrote:
Instead of doing a system-wide TLB flush from arch_tlbbatch_flush,
queue up asynchronous, targeted flushes from arch_tlbbatch_add_pending.
[snip]
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1659,9 +1659,7 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
* a local TLB flush is needed. Optimize this use-case by calling
* flush_tlb_func_local() directly in this case.
*/
- if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
- invlpgb_flush_all_nonglobals();
- } else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+ if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
flush_tlb_multi(&batch->cpumask, info);
} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
lockdep_assert_irqs_enabled();
@@ -1670,12 +1668,62 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
local_irq_enable();
}
+ /*
+ * If we issued (asynchronous) INVLPGB flushes, wait for them here.
+ * The cpumask above contains only CPUs that were running tasks
+ * not using broadcast TLB flushing.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch->used_invlpgb) {
+ tlbsync();
+ migrate_enable();
Maybe someone mentioned it before, but I would emphasize that I do not
think that preventing migration for potentially long time is that great.
One alternative solution would be to set a bit on cpu_tlbstate, that
when set, you'd issue a tlbsync on context switch.
(I can think about other solutions, but I think the one I just mentioned
is the cleanest one).
+ batch->used_invlpgb = false;
+ }
+
cpumask_clear(&batch->cpumask);
put_flush_tlb_info();
put_cpu();
}
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+ struct mm_struct *mm,
+ unsigned long uaddr)
+{
+ if (static_cpu_has(X86_FEATURE_INVLPGB) && mm_global_asid(mm)) {
+ u16 asid = mm_global_asid(mm);
+ /*
+ * Queue up an asynchronous invalidation. The corresponding
+ * TLBSYNC is done in arch_tlbbatch_flush(), and must be done
+ * on the same CPU.
+ */
+ if (!batch->used_invlpgb) {
+ batch->used_invlpgb = true;
+ migrate_disable();
See my comment above...
+ }
+ invlpgb_flush_user_nr_nosync(kern_pcid(asid), uaddr, 1, false);
+ /* Do any CPUs supporting INVLPGB need PTI? */
+ if (static_cpu_has(X86_FEATURE_PTI))
+ invlpgb_flush_user_nr_nosync(user_pcid(asid), uaddr, 1, false);
+
+ /*
+ * Some CPUs might still be using a local ASID for this
+ * process, and require IPIs, while others are using the
+ * global ASID.
+ *
+ * In this corner case we need to do both the broadcast
+ * TLB invalidation, and send IPIs. The IPIs will help
+ * stragglers transition to the broadcast ASID.
+ */
+ if (READ_ONCE(mm->context.asid_transition))
+ goto also_send_ipi;
+ } else {
+also_send_ipi:
I really think you should avoid such goto's. A simple bool variable of
"need_ipi" would suffice.
+ inc_mm_tlb_gen(mm);
+ cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+ }
+ mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
+}
+
/*
* Blindly accessing user memory from NMI context can be dangerous
* if we're in the middle of switching the current user task or
