x86/mm: Only do broadcast flush from reclaim if pages were unmapped

Track whether pages were unmapped from any MM (even ones with a currently
empty mm_cpumask) by the reclaim code, to figure out whether or not
broadcast TLB flush should be done when reclaim finishes.

The reason any MM must be tracked, and not only ones contributing to the
tlbbatch cpumask, is that broadcast ASIDs are expected to be kept up to
date even on CPUs where the MM is not currently active.

This change allows reclaim to avoid doing TLB flushes when only clean page
cache pages and/or slab memory were reclaimed, which is fairly common.

( This is a simpler alternative to the code that was in my INVLPGB series
  before, and it seems to capture most of the benefit due to how common
  it is to reclaim only page cache. )

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250319132520.6b10ad90@fangorn

Author: rikvanriel

arch/x86/include/asm/tlbbatch.h

@@ -10,6 +10,11 @@ struct arch_tlbflush_unmap_batch {
 	 * the PFNs being flushed..
 	 */
 	struct cpumask cpumask;
+	/*
+	 * Set if pages were unmapped from any MM, even one that does not
+	 * have active CPUs in its cpumask.
+	 */
+	bool unmapped_pages;
 };
 
 #endif /* _ARCH_X86_TLBBATCH_H */

arch/x86/include/asm/tlbflush.h

@@ -353,6 +353,7 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
 {
 	inc_mm_tlb_gen(mm);
 	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+	batch->unmapped_pages = true;
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 

arch/x86/mm/tlb.c

@@ -1633,8 +1633,9 @@ 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)) {
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch->unmapped_pages) {
 		invlpgb_flush_all_nonglobals();
+		batch->unmapped_pages = false;
 	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
 		flush_tlb_multi(&batch->cpumask, info);
 	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {