[RFC v2 6/9] khugepaged: introduce khugepaged_scan_bitmap for mTHP support

[Nico Pache <npache@redhat.com>]

khugepaged scans PMD ranges for potential collapse to a hugepage. To add
mTHP support we use this scan to instead record chunks of fully utilized
sections of the PMD.

create a bitmap to represent a PMD in order MTHP_MIN_ORDER chunks.
by default we will set this to order 3. The reasoning is that for 4K 512
PMD size this results in a 64 bit bitmap which has some optimizations.
For other arches like ARM64 64K, we can set a larger order if needed.

khugepaged_scan_bitmap uses a stack struct to recursively scan a bitmap
that represents chunks of utilized regions. We can then determine what
mTHP size fits best and in the following patch, we set this bitmap while
scanning the PMD.

max_ptes_none is used as a scale to determine how "full" an order must
be before being considered for collapse.

If a order is set to "always" lets always collapse to that order in a
greedy manner.

Signed-off-by: Nico Pache <npache@redhat.com>
---
 include/linux/khugepaged.h |  4 ++
 mm/khugepaged.c            | 89 +++++++++++++++++++++++++++++++++++---
 2 files changed, 86 insertions(+), 7 deletions(-)

diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 1f46046080f5..1fe0c4fc9d37 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -1,6 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_KHUGEPAGED_H
 #define _LINUX_KHUGEPAGED_H
+#define MIN_MTHP_ORDER	3
+#define MIN_MTHP_NR	(1<<MIN_MTHP_ORDER)
+#define MAX_MTHP_BITMAP_SIZE  (1 << (ilog2(MAX_PTRS_PER_PTE * PAGE_SIZE) - MIN_MTHP_ORDER))
+#define MTHP_BITMAP_SIZE  (1 << (HPAGE_PMD_ORDER - MIN_MTHP_ORDER))
 
 extern unsigned int khugepaged_max_ptes_none __read_mostly;
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 3776055bd477..c8048d9ec7fb 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -94,6 +94,11 @@ static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
 
 static struct kmem_cache *mm_slot_cache __ro_after_init;
 
+struct scan_bit_state {
+	u8 order;
+	u16 offset;
+};
+
 struct collapse_control {
 	bool is_khugepaged;
 
@@ -102,6 +107,15 @@ struct collapse_control {
 
 	/* nodemask for allocation fallback */
 	nodemask_t alloc_nmask;
+
+	/* bitmap used to collapse mTHP sizes. 1bit = order MIN_MTHP_ORDER mTHP */
+	DECLARE_BITMAP(mthp_bitmap, MAX_MTHP_BITMAP_SIZE);
+	DECLARE_BITMAP(mthp_bitmap_temp, MAX_MTHP_BITMAP_SIZE);
+	struct scan_bit_state mthp_bitmap_stack[MAX_MTHP_BITMAP_SIZE];
+};
+
+struct collapse_control khugepaged_collapse_control = {
+	.is_khugepaged = true,
 };
 
 /**
@@ -851,10 +865,6 @@ static void khugepaged_alloc_sleep(void)
 	remove_wait_queue(&khugepaged_wait, &wait);
 }
 
-struct collapse_control khugepaged_collapse_control = {
-	.is_khugepaged = true,
-};
-
 static bool khugepaged_scan_abort(int nid, struct collapse_control *cc)
 {
 	int i;
@@ -1112,7 +1122,8 @@ static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm,
 
 static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 			      int referenced, int unmapped,
-			      struct collapse_control *cc)
+			      struct collapse_control *cc, bool *mmap_locked,
+				  u8 order, u16 offset)
 {
 	LIST_HEAD(compound_pagelist);
 	pmd_t *pmd, _pmd;
@@ -1130,8 +1141,12 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	 * The allocation can take potentially a long time if it involves
 	 * sync compaction, and we do not need to hold the mmap_lock during
 	 * that. We will recheck the vma after taking it again in write mode.
+	 * If collapsing mTHPs we may have already released the read_lock.
 	 */
-	mmap_read_unlock(mm);
+	if (*mmap_locked) {
+		mmap_read_unlock(mm);
+		*mmap_locked = false;
+	}
 
 	result = alloc_charge_folio(&folio, mm, cc, HPAGE_PMD_ORDER);
 	if (result != SCAN_SUCCEED)
@@ -1266,12 +1281,71 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 out_up_write:
 	mmap_write_unlock(mm);
 out_nolock:
+	*mmap_locked = false;
 	if (folio)
 		folio_put(folio);
 	trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result);
 	return result;
 }
 
+// Recursive function to consume the bitmap
+static int khugepaged_scan_bitmap(struct mm_struct *mm, unsigned long address,
+			int referenced, int unmapped, struct collapse_control *cc,
+			bool *mmap_locked, unsigned long enabled_orders)
+{
+	u8 order, next_order;
+	u16 offset, mid_offset;
+	int num_chunks;
+	int bits_set, threshold_bits;
+	int top = -1;
+	int collapsed = 0;
+	int ret;
+	struct scan_bit_state state;
+
+	cc->mthp_bitmap_stack[++top] = (struct scan_bit_state)
+		{ HPAGE_PMD_ORDER - MIN_MTHP_ORDER, 0 };
+
+	while (top >= 0) {
+		state = cc->mthp_bitmap_stack[top--];
+		order = state.order + MIN_MTHP_ORDER;
+		offset = state.offset;
+		num_chunks = 1 << (state.order);
+		// Skip mTHP orders that are not enabled
+		if (!test_bit(order, &enabled_orders))
+			goto next;
+
+		// copy the relavant section to a new bitmap
+		bitmap_shift_right(cc->mthp_bitmap_temp, cc->mthp_bitmap, offset,
+				  MTHP_BITMAP_SIZE);
+
+		bits_set = bitmap_weight(cc->mthp_bitmap_temp, num_chunks);
+		threshold_bits = (HPAGE_PMD_NR - khugepaged_max_ptes_none - 1)
+				>> (HPAGE_PMD_ORDER - state.order);
+
+		//Check if the region is "almost full" based on the threshold
+		if (bits_set > threshold_bits
+			|| test_bit(order, &huge_anon_orders_always)) {
+			ret = collapse_huge_page(mm, address, referenced, unmapped, cc,
+					mmap_locked, order, offset * MIN_MTHP_NR);
+			if (ret == SCAN_SUCCEED) {
+				collapsed += (1 << order);
+				continue;
+			}
+		}
+
+next:
+		if (state.order > 0) {
+			next_order = state.order - 1;
+			mid_offset = offset + (num_chunks / 2);
+			cc->mthp_bitmap_stack[++top] = (struct scan_bit_state)
+				{ next_order, mid_offset };
+			cc->mthp_bitmap_stack[++top] = (struct scan_bit_state)
+				{ next_order, offset };
+			}
+	}
+	return collapsed;
+}
+
 static int khugepaged_scan_pmd(struct mm_struct *mm,
 				   struct vm_area_struct *vma,
 				   unsigned long address, bool *mmap_locked,
@@ -1440,7 +1514,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	pte_unmap_unlock(pte, ptl);
 	if (result == SCAN_SUCCEED) {
 		result = collapse_huge_page(mm, address, referenced,
-					    unmapped, cc);
+					    unmapped, cc, mmap_locked, HPAGE_PMD_ORDER, 0);
 		/* collapse_huge_page will return with the mmap_lock released */
 		*mmap_locked = false;
 	}
@@ -2856,6 +2930,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	mmdrop(mm);
 	kfree(cc);
 
+
 	return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0
 			: madvise_collapse_errno(last_fail);
 }
-- 
2.48.1