[PATCH 2/4] mm: speed up mremap by 500x on large regions (v2)

["Joel Fernandes (Google)" <joel@joelfernandes.org>]

Android needs to mremap large regions of memory during memory management
related operations. The mremap system call can be really slow if THP is
not enabled. The bottleneck is move_page_tables, which is copying each
pte at a time, and can be really slow across a large map. Turning on THP
may not be a viable option, and is not for us. This patch speeds up the
performance for non-THP system by copying at the PMD level when possible.

The speed up is three orders of magnitude. On a 1GB mremap, the mremap
completion times drops from 160-250 millesconds to 380-400 microseconds.

Before:
Total mremap time for 1GB data: 242321014 nanoseconds.
Total mremap time for 1GB data: 196842467 nanoseconds.
Total mremap time for 1GB data: 167051162 nanoseconds.

After:
Total mremap time for 1GB data: 385781 nanoseconds.
Total mremap time for 1GB data: 388959 nanoseconds.
Total mremap time for 1GB data: 402813 nanoseconds.

Incase THP is enabled, the optimization is skipped. I also flush the
tlb every time we do this optimization since I couldn't find a way to
determine if the low-level PTEs are dirty. It is seen that the cost of
doing so is not much compared the improvement, on both x86-64 and arm64.

Cc: minchan@kernel.org
Cc: pantin@google.com
Cc: hughd@google.com
Cc: lokeshgidra@google.com
Cc: dancol@google.com
Cc: mhocko@kernel.org
Cc: kirill@shutemov.name
Cc: akpm@linux-foundation.org
Cc: kernel-team@android.com
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
 arch/Kconfig |  5 ++++
 mm/mremap.c  | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

diff --git a/arch/Kconfig b/arch/Kconfig
index 6801123932a5..9724fe39884f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -518,6 +518,11 @@ config HAVE_IRQ_TIME_ACCOUNTING
 	  Archs need to ensure they use a high enough resolution clock to
 	  support irq time accounting and then call enable_sched_clock_irqtime().
 
+config HAVE_MOVE_PMD
+	bool
+	help
+	  Archs that select this are able to move page tables at the PMD level.
+
 config HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	bool
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 9e68a02a52b1..2fd163cff406 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -191,6 +191,54 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		drop_rmap_locks(vma);
 }
 
+static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
+		  unsigned long new_addr, unsigned long old_end,
+		  pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
+{
+	spinlock_t *old_ptl, *new_ptl;
+	struct mm_struct *mm = vma->vm_mm;
+
+	if ((old_addr & ~PMD_MASK) || (new_addr & ~PMD_MASK)
+	    || old_end - old_addr < PMD_SIZE)
+		return false;
+
+	/*
+	 * The destination pmd shouldn't be established, free_pgtables()
+	 * should have release it.
+	 */
+	if (WARN_ON(!pmd_none(*new_pmd)))
+		return false;
+
+	/*
+	 * We don't have to worry about the ordering of src and dst
+	 * ptlocks because exclusive mmap_sem prevents deadlock.
+	 */
+	old_ptl = pmd_lock(vma->vm_mm, old_pmd);
+	if (old_ptl) {
+		pmd_t pmd;
+
+		new_ptl = pmd_lockptr(mm, new_pmd);
+		if (new_ptl != old_ptl)
+			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+
+		/* Clear the pmd */
+		pmd = *old_pmd;
+		pmd_clear(old_pmd);
+
+		VM_BUG_ON(!pmd_none(*new_pmd));
+
+		/* Set the new pmd */
+		set_pmd_at(mm, new_addr, new_pmd, pmd);
+		if (new_ptl != old_ptl)
+			spin_unlock(new_ptl);
+		spin_unlock(old_ptl);
+
+		*need_flush = true;
+		return true;
+	}
+	return false;
+}
+
 unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len,
@@ -239,7 +287,24 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			split_huge_pmd(vma, old_pmd, old_addr);
 			if (pmd_trans_unstable(old_pmd))
 				continue;
+		} else if (extent == PMD_SIZE && IS_ENABLED(CONFIG_HAVE_MOVE_PMD)) {
+			/*
+			 * If the extent is PMD-sized, try to speed the move by
+			 * moving at the PMD level if possible.
+			 */
+			bool moved;
+
+			if (need_rmap_locks)
+				take_rmap_locks(vma);
+			moved = move_normal_pmd(vma, old_addr, new_addr,
+					old_end, old_pmd, new_pmd,
+					&need_flush);
+			if (need_rmap_locks)
+				drop_rmap_locks(vma);
+			if (moved)
+				continue;
 		}
+
 		if (pte_alloc(new_vma->vm_mm, new_pmd))
 			break;
 		next = (new_addr + PMD_SIZE) & PMD_MASK;
-- 
2.19.0.605.g01d371f741-goog