[v12,12/16] x86/mm: enable broadcast TLB invalidation for multi-threaded processes

Commit Message

Rik van Riel Feb. 21, 2025, 12:53 a.m. UTC

Use broadcast TLB invalidation, using the INVPLGB instruction.

There is not enough room in the 12-bit ASID address space to hand
out broadcast ASIDs to every process. Only hand out broadcast ASIDs
to processes when they are observed to be simultaneously running
on 4 or more CPUs.

This also allows single threaded process to continue using the
cheaper, local TLB invalidation instructions like INVLPGB.

Signed-off-by: Rik van Riel <[e-mail]>
Reviewed-by: Nadav Amit <[e-mail]>
Tested-by: Manali Shukla <[e-mail]>
Tested-by: Brendan Jackman <[e-mail]>
Tested-by: Michael Kelley <[e-mail]>
---
 arch/x86/mm/tlb.c | 107 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 106 insertions(+), 1 deletion(-)

Patch

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index d8a04e398615..01a5edb51ebe 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -420,6 +420,108 @@  static bool needs_global_asid_reload(struct mm_struct *next, u16 prev_asid)
 	return false;
 }
 
+/*
+ * x86 has 4k ASIDs (2k when compiled with KPTI), but the largest
+ * x86 systems have over 8k CPUs. Because of this potential ASID
+ * shortage, global ASIDs are handed out to processes that have
+ * frequent TLB flushes and are active on 4 or more CPUs simultaneously.
+ */
+static void consider_global_asid(struct mm_struct *mm)
+{
+	if (!static_cpu_has(X86_FEATURE_INVLPGB))
+		return;
+
+	/* Check every once in a while. */
+	if ((current->pid & 0x1f) != (jiffies & 0x1f))
+		return;
+
+	if (!READ_ONCE(global_asid_available))
+		return;
+
+	/*
+	 * Assign a global ASID if the process is active on
+	 * 4 or more CPUs simultaneously.
+	 */
+	if (mm_active_cpus_exceeds(mm, 3))
+		use_global_asid(mm);
+}
+
+static void finish_asid_transition(struct flush_tlb_info *info)
+{
+	struct mm_struct *mm = info->mm;
+	int bc_asid = mm_global_asid(mm);
+	int cpu;
+
+	if (!READ_ONCE(mm->context.asid_transition))
+		return;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/*
+		 * The remote CPU is context switching. Wait for that to
+		 * finish, to catch the unlikely case of it switching to
+		 * the target mm with an out of date ASID.
+		 */
+		while (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) == LOADED_MM_SWITCHING)
+			cpu_relax();
+
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) != mm)
+			continue;
+
+		/*
+		 * If at least one CPU is not using the global ASID yet,
+		 * send a TLB flush IPI. The IPI should cause stragglers
+		 * to transition soon.
+		 *
+		 * This can race with the CPU switching to another task;
+		 * that results in a (harmless) extra IPI.
+		 */
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm_asid, cpu)) != bc_asid) {
+			flush_tlb_multi(mm_cpumask(info->mm), info);
+			return;
+		}
+	}
+
+	/* All the CPUs running this process are using the global ASID. */
+	WRITE_ONCE(mm->context.asid_transition, false);
+}
+
+static void broadcast_tlb_flush(struct flush_tlb_info *info)
+{
+	bool pmd = info->stride_shift == PMD_SHIFT;
+	unsigned long asid = info->mm->context.global_asid;
+	unsigned long addr = info->start;
+
+	/*
+	 * TLB flushes with INVLPGB are kicked off asynchronously.
+	 * The inc_mm_tlb_gen() guarantees page table updates are done
+	 * before these TLB flushes happen.
+	 */
+	if (info->end == TLB_FLUSH_ALL) {
+		invlpgb_flush_single_pcid_nosync(kern_pcid(asid));
+		/* Do any CPUs supporting INVLPGB need PTI? */
+		if (static_cpu_has(X86_FEATURE_PTI))
+			invlpgb_flush_single_pcid_nosync(user_pcid(asid));
+	} else do {
+		unsigned long nr = 1;
+
+		if (info->stride_shift <= PMD_SHIFT) {
+			nr = (info->end - addr) >> info->stride_shift;
+			nr = clamp_val(nr, 1, invlpgb_count_max);
+		}
+
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd);
+		if (static_cpu_has(X86_FEATURE_PTI))
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd);
+
+		addr += nr << info->stride_shift;
+	} while (addr < info->end);
+
+	finish_asid_transition(info);
+
+	/* Wait for the INVLPGBs kicked off above to finish. */
+	__tlbsync();
+}
+
 /*
  * Given an ASID, flush the corresponding user ASID.  We can delay this
  * until the next time we switch to it.
@@ -1250,9 +1352,12 @@  void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+	if (mm_global_asid(mm)) {
+		broadcast_tlb_flush(info);
+	} else if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
 		info->trim_cpumask = should_trim_cpumask(mm);
 		flush_tlb_multi(mm_cpumask(mm), info);
+		consider_global_asid(mm);
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();