@@ -5,6 +5,7 @@
#include <linux/mm_types.h>
#include <linux/mmu_notifier.h>
#include <linux/sched.h>
+#include <linux/cpumask.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
@@ -293,6 +294,23 @@ static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
+static inline void arch_tlbbatch_clear(struct arch_tlbflush_unmap_batch *batch)
+{
+ cpumask_clear(&batch->cpumask);
+}
+
+static inline void arch_tlbbatch_fold(struct arch_tlbflush_unmap_batch *bdst,
+ struct arch_tlbflush_unmap_batch *bsrc)
+{
+ cpumask_or(&bdst->cpumask, &bdst->cpumask, &bsrc->cpumask);
+}
+
+static inline bool arch_tlbbatch_done(struct arch_tlbflush_unmap_batch *bdst,
+ struct arch_tlbflush_unmap_batch *bsrc)
+{
+ return !cpumask_andnot(&bdst->cpumask, &bdst->cpumask, &bsrc->cpumask);
+}
+
static inline bool pte_flags_need_flush(unsigned long oldflags,
unsigned long newflags,
bool ignore_access)
A new mechanism, LUF(Lazy Unmap Flush), defers tlb flush until folios that have been unmapped and freed, eventually get allocated again. It's safe for folios that had been mapped read-only and were unmapped, since the contents of the folios wouldn't change while staying in pcp or buddy so we can still read the data through the stale tlb entries. This is a preparation for the mechanism that needs to recognize read-only tlb entries by separating tlb batch arch data into two, one is for read-only entries and the other is for writable ones, and merging those two when needed. It also optimizes tlb shootdown by skipping CPUs that have already performed tlb flush needed since. To support it, added APIs manipulating arch data for x86. Signed-off-by: Byungchul Park <byungchul@sk.com> --- arch/x86/include/asm/tlbflush.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)