arm64：用 sme_active_cpus 掩码替代 mm_cpumask 采样 — 恢复 C1-Pro SME DVMSync erratum 下的 TLB 回收批量收益

@@ arch/arm64/include/asm/tlbflush.h
-static inline void sme_dvmsync_add_pending(struct arch_tlbflush_unmap_batch *batch,
-					   struct mm_struct *mm)
+static inline void sme_dvmsync_batch(void)
 {
 	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
 		return;
 
-	/*
-	 * Order the mm_cpumask() read after the hardware DVMSync.
-	 */
-	dsb(ish);
-	if (cpumask_empty(mm_cpumask(mm)))
-		return;
-
-	/*
-	 * Allocate the batch cpumask on first use. Fall back to an immediate
-	 * IPI for this mm in case of failure.
-	 */
-	if (!cpumask_available(batch->cpumask) &&
-	    !zalloc_cpumask_var(&batch->cpumask, GFP_ATOMIC)) {
-		sme_do_dvmsync(mm_cpumask(mm));
-		return;
-	}
-
-	cpumask_or(batch->cpumask, batch->cpumask, mm_cpumask(mm));
-}
-
-static inline void sme_dvmsync_batch(struct arch_tlbflush_unmap_batch *batch)
-{
-	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
-		return;
-
-	if (!cpumask_available(batch->cpumask))
-		return;
-
-	sme_do_dvmsync(batch->cpumask);
-	cpumask_clear(batch->cpumask);
+	sme_do_dvmsync(&sme_active_cpus);
 }

@@ arch/arm64/kernel/fpsimd.c
 static cpumask_t sme_dvmsync_cpus;
+cpumask_t sme_active_cpus;
 ...
 	cpumask_set_cpu(cpu, mm_cpumask(current->mm));
+	cpumask_set_cpu(cpu, &sme_active_cpus);
 	/*
 	 * A subsequent (post ERET) SME access may use a stale address
 	 * translation. On C1-Pro, a TLBI+DSB on a different CPU will wait for
-	 * the completion of cpumask_set_cpu() above as it appears in program
-	 * order before the SME access. The post-TLBI+DSB read of mm_cpumask()
-	 * will lead to the IPI being issued.
+	 * the completion of the cpumask_set_cpu() operations above as they
+	 * appear in program order before the SME access. The post-TLBI+DSB
+	 * read of mm_cpumask() or sme_active_cpus will lead to the IPI being
+	 * issued.
 	 *
 	 * https://lore.kernel.org/r/ablEXwhfKyJW1i7l@J2N7QTR9R3
 	 */
@@
 	cpumask_clear_cpu(cpu, mm_cpumask(current->mm));
+	cpumask_clear_cpu(cpu, &sme_active_cpus);