[RFC PATCH v12 09/26] mm: introduce API to perform tlb shootdown on exit from page allocator

[Byungchul Park <byungchul@sk.com>]

Functionally, no change.  This is a preparation for luf mechanism that
performs tlb shootdown required on exit from page allocator.

This patch introduced a new API rather than making use of existing
try_to_unmap_flush() to avoid repeated and redundant tlb shootdown due
to frequent page allocations during a session of batched unmap flush.

Signed-off-by: Byungchul Park <byungchul@sk.com>
---
 include/linux/sched.h |  1 +
 mm/internal.h         |  4 ++++
 mm/rmap.c             | 20 ++++++++++++++++++++
 3 files changed, 25 insertions(+)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index bb343136ddd05..8e6e7a83332cf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1375,6 +1375,7 @@ struct task_struct {
 #endif
 
 	struct tlbflush_unmap_batch	tlb_ubc;
+	struct tlbflush_unmap_batch	tlb_ubc_takeoff;
 
 	/* Cache last used pipe for splice(): */
 	struct pipe_inode_info		*splice_pipe;
diff --git a/mm/internal.h b/mm/internal.h
index b38a9ae9d6993..cbdebf8a02437 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1239,6 +1239,7 @@ extern struct workqueue_struct *mm_percpu_wq;
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 void try_to_unmap_flush(void);
 void try_to_unmap_flush_dirty(void);
+void try_to_unmap_flush_takeoff(void);
 void flush_tlb_batched_pending(struct mm_struct *mm);
 void fold_batch(struct tlbflush_unmap_batch *dst, struct tlbflush_unmap_batch *src, bool reset);
 void fold_luf_batch(struct luf_batch *dst, struct luf_batch *src);
@@ -1249,6 +1250,9 @@ static inline void try_to_unmap_flush(void)
 static inline void try_to_unmap_flush_dirty(void)
 {
 }
+static inline void try_to_unmap_flush_takeoff(void)
+{
+}
 static inline void flush_tlb_batched_pending(struct mm_struct *mm)
 {
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 74fbf6c2fb3a7..72c5e665e59a4 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -772,6 +772,26 @@ void fold_luf_batch(struct luf_batch *dst, struct luf_batch *src)
 	read_unlock_irqrestore(&src->lock, flags);
 }
 
+void try_to_unmap_flush_takeoff(void)
+{
+	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
+	struct tlbflush_unmap_batch *tlb_ubc_takeoff = &current->tlb_ubc_takeoff;
+
+	if (!tlb_ubc_takeoff->flush_required)
+		return;
+
+	arch_tlbbatch_flush(&tlb_ubc_takeoff->arch);
+
+	/*
+	 * Now that tlb shootdown of tlb_ubc_takeoff has been performed,
+	 * it's good chance to shrink tlb_ubc if possible.
+	 */
+	if (arch_tlbbatch_done(&tlb_ubc->arch, &tlb_ubc_takeoff->arch))
+		reset_batch(tlb_ubc);
+
+	reset_batch(tlb_ubc_takeoff);
+}
+
 /*
  * Flush TLB entries for recently unmapped pages from remote CPUs. It is
  * important if a PTE was dirty when it was unmapped that it's flushed
-- 
2.17.1