[PATCH v6 0/5] Make alloc_contig_range handle Hugetlb pages

[PATCH v6 0/5] Make alloc_contig_range handle Hugetlb pages

[Oscar Salvador]

v5 -> v6:
 - Collect Acked-by from Michal
 - Adressed feedback for patch#2 (expand the comment about migrate_pfn and
   change return values)
 - Complete pathc#3's changelog (per Michal)
 - Place retry lock inside of alloc_and_dissolve_huge_page()

v4 -> v5:
 - Collect Acked-by and Reviewed-by from David and Vlastimil
 - Drop racy checks in pfn_range_valid_contig (David)
 - Rebased on top of 5.12-rc3

v3 -> v4:
 - Addressed some feedback from David and Michal
 - Make more clear what hugetlb_lock protects in isolate_or_dissolve_huge_page
 - Start reporting proper error codes from isolate_migratepages_{range,block}
 - Bail out earlier in __alloc_contig_migrate_range on -ENOMEM
 - Addressed internal feedback from Vastlimil wrt. compaction code changes

v2 -> v3:
 - Drop usage of high-level generic helpers in favour of
   low-level approach (per Michal)
 - Check for the page to be marked as PageHugeFreed
 - Add a one-time retry in case someone grabbed the free huge page
   from under us

v1 -> v2:
 - Adressed feedback by Michal
 - Restrict the allocation to a node with __GFP_THISNODE
 - Drop PageHuge check in alloc_and_dissolve_huge_page
 - Re-order comments in isolate_or_dissolve_huge_page
 - Extend comment in isolate_migratepages_block
 - Place put_page right after we got the page, otherwise
   dissolve_free_huge_page will fail

 RFC -> v1:
 - Drop RFC
 - Addressed feedback from David and Mike
 - Fence off gigantic pages as there is a cyclic dependency between
   them and alloc_contig_range
 - Re-organize the code to make race-window smaller and to put
   all details in hugetlb code
 - Drop nodemask initialization. First a node will be tried and then we
   will back to other nodes containing memory (N_MEMORY). Details in
   patch#1's changelog
 - Count new page as surplus in case we failed to dissolve the old page
   and the new one. Details in patch#1.

Cover letter:

 alloc_contig_range lacks the hability for handling HugeTLB pages.
 This can be problematic for some users, e.g: CMA and virtio-mem, where those
 users will fail the call if alloc_contig_range ever sees a HugeTLB page, even
 when those pages lay in ZONE_MOVABLE and are free.
 That problem can be easily solved by replacing the page in the free hugepage
 pool.

 In-use HugeTLB are no exception though, as those can be isolated and migrated
 as any other LRU or Movable page.

 This patchset aims for improving alloc_contig_range->isolate_migratepages_block,
 so HugeTLB pages can be recognized and handled.

 Since we also need to start reporting errors down the chain (e.g: -ENOMEM due to
 not be able to allocate a new hugetlb page), isolate_migratepages_{range,block}
 interfaces  need to change to start reporting error codes instead of the pfn == 0
 vs pfn != 0 scheme it is using right now.
 From now on, isolate_migratepages_block will not return the next pfn to be scanned
 anymore, but -EINTR, -ENOMEM or 0, so we the next pfn to be scanned will be recorded
 in cc->migrate_pfn field (as it is already done in isolate_migratepages_range()).

 Below is an insight from David (thanks), where the problem can clearly be seen:

 "Start a VM with 4G. Hotplug 1G via virtio-mem and online it to
  ZONE_MOVABLE. Allocate 512 huge pages.

  [root@localhost ~]# cat /proc/meminfo
  MemTotal:        5061512 kB
  MemFree:         3319396 kB
  MemAvailable:    3457144 kB
  ...
  HugePages_Total:     512
  HugePages_Free:      512
  HugePages_Rsvd:        0
  HugePages_Surp:        0
  Hugepagesize:       2048 kB

  The huge pages get partially allocate from ZONE_MOVABLE. Try unplugging
  1G via virtio-mem (remember, all ZONE_MOVABLE). Inside the guest:

  [  180.058992] alloc_contig_range: [1b8000, 1c0000) PFNs busy
  [  180.060531] alloc_contig_range: [1b8000, 1c0000) PFNs busy
  [  180.061972] alloc_contig_range: [1b8000, 1c0000) PFNs busy
  [  180.063413] alloc_contig_range: [1b8000, 1c0000) PFNs busy
  [  180.064838] alloc_contig_range: [1b8000, 1c0000) PFNs busy
  [  180.065848] alloc_contig_range: [1bfc00, 1c0000) PFNs busy
  [  180.066794] alloc_contig_range: [1bfc00, 1c0000) PFNs busy
  [  180.067738] alloc_contig_range: [1bfc00, 1c0000) PFNs busy
  [  180.068669] alloc_contig_range: [1bfc00, 1c0000) PFNs busy
  [  180.069598] alloc_contig_range: [1bfc00, 1c0000) PFNs busy"

 And then with this patchset running:

 "Same experiment with ZONE_MOVABLE:

  a) Free huge pages: all memory can get unplugged again.

  b) Allocated/populated but idle huge pages: all memory can get unplugged
     again.

  c) Allocated/populated but all 512 huge pages are read/written in a
     loop: all memory can get unplugged again, but I get a single

  [  121.192345] alloc_contig_range: [180000, 188000) PFNs busy

  Most probably because it happened to try migrating a huge page while it
  was busy. As virtio-mem retries on ZONE_MOVABLE a couple of times, it
  can deal with this temporary failure.

  Last but not least, I did something extreme:

  # cat /proc/meminfo
  MemTotal:        5061568 kB
  MemFree:          186560 kB
  MemAvailable:     354524 kB
  ...
  HugePages_Total:    2048
  HugePages_Free:     2048
  HugePages_Rsvd:        0
  HugePages_Surp:        0

  Triggering unplug would require to dissolve+alloc - which now fails when
  trying to allocate an additional ~512 huge pages (1G).

  As expected, I can properly see memory unplug not fully succeeding. + I
  get a fairly continuous stream of

  [  226.611584] alloc_contig_range: [19f400, 19f800) PFNs busy
  ...

  But more importantly, the hugepage count remains stable, as configured
  by the admin (me):

  HugePages_Total:    2048
  HugePages_Free:     2048
  HugePages_Rsvd:        0
  HugePages_Surp:        0"

Oscar Salvador (5):
  mm,page_alloc: Bail out earlier on -ENOMEM in
    alloc_contig_migrate_range
  mm,compaction: Let isolate_migratepages_{range,block} return error
    codes
  mm: Make alloc_contig_range handle free hugetlb pages
  mm: Make alloc_contig_range handle in-use hugetlb pages
  mm,page_alloc: Drop unnecessary checks from pfn_range_valid_contig

 include/linux/hugetlb.h |   7 +++
 mm/compaction.c         |  94 +++++++++++++++++++++++++++-----------
 mm/hugetlb.c            | 119 +++++++++++++++++++++++++++++++++++++++++++++++-
 mm/internal.h           |  10 +++-
 mm/page_alloc.c         |  21 ++++-----
 mm/vmscan.c             |   5 +-
 6 files changed, 212 insertions(+), 44 deletions(-)

-- 
2.16.3

[PATCH v6 1/5] mm,page_alloc: Bail out earlier on -ENOMEM in alloc_contig_migrate_range

[Oscar Salvador]

Currently, __alloc_contig_migrate_range can generate -EINTR, -ENOMEM or -EBUSY,
and report them down the chain.
The problem is that when migrate_pages() reports -ENOMEM, we keep going till we
exhaust all the try-attempts (5 at the moment) instead of bailing out.

migrate_pages() bails out right away on -ENOMEM because it is considered a fatal
error. Do the same here instead of keep going and retrying.
Note that this is not fixing a real issue, just a cosmetic change. Although we
can save some cycles by backing off ealier

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
---
 mm/page_alloc.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index cfc72873961d..a4f67063b85f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8481,7 +8481,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 			}
 			tries = 0;
 		} else if (++tries == 5) {
-			ret = ret < 0 ? ret : -EBUSY;
+			ret = -EBUSY;
 			break;
 		}
 
@@ -8491,6 +8491,12 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 
 		ret = migrate_pages(&cc->migratepages, alloc_migration_target,
 				NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE);
+		/*
+		 * On -ENOMEM, migrate_pages() bails out right away. It is pointless
+		 * to retry again over this error, so do the same here.
+		 */
+		if (ret == -ENOMEM)
+			break;
 	}
 	if (ret < 0) {
 		putback_movable_pages(&cc->migratepages);
-- 
2.16.3

[PATCH v6 2/5] mm,compaction: Let isolate_migratepages_{range,block} return error codes

[Oscar Salvador]

Currently, isolate_migratepages_{range,block} and their callers use
a pfn == 0 vs pfn != 0 scheme to let the caller know whether there was
any error during isolation.
This does not work as soon as we need to start reporting different error
codes and make sure we pass them down the chain, so they are properly
interpreted by functions like e.g: alloc_contig_range.

Let us rework isolate_migratepages_{range,block} so we can report error
codes.
Since isolate_migratepages_block will stop returning the next pfn to be
scanned, we reuse the cc->migrate_pfn field to keep track of that.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/compaction.c | 53 ++++++++++++++++++++++++++---------------------------
 mm/internal.h   | 10 ++++++++--
 mm/page_alloc.c |  7 +++----
 3 files changed, 37 insertions(+), 33 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index e04f4476e68e..cd090a675321 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -787,15 +787,15 @@ static bool too_many_isolated(pg_data_t *pgdat)
  *
  * Isolate all pages that can be migrated from the range specified by
  * [low_pfn, end_pfn). The range is expected to be within same pageblock.
- * Returns zero if there is a fatal signal pending, otherwise PFN of the
- * first page that was not scanned (which may be both less, equal to or more
- * than end_pfn).
+ * Returns errno, like -EAGAIN or -EINTR in case e.g signal pending or congestion,
+ * or 0.
+ * cc->migrate_pfn will contain the next pfn to scan (which may be both less,
+ * equal to or more that end_pfn).
  *
  * The pages are isolated on cc->migratepages list (not required to be empty),
- * and cc->nr_migratepages is updated accordingly. The cc->migrate_pfn field
- * is neither read nor updated.
- */
-static unsigned long
+ * and cc->nr_migratepages is updated accordingly.
+*/
+static int
 isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			unsigned long end_pfn, isolate_mode_t isolate_mode)
 {
@@ -810,6 +810,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	unsigned long next_skip_pfn = 0;
 	bool skip_updated = false;
 
+	cc->migrate_pfn = low_pfn;
+
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
 	 * list by either parallel reclaimers or compaction. If there are,
@@ -818,16 +820,16 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	while (unlikely(too_many_isolated(pgdat))) {
 		/* stop isolation if there are still pages not migrated */
 		if (cc->nr_migratepages)
-			return 0;
+			return -EAGAIN;
 
 		/* async migration should just abort */
 		if (cc->mode == MIGRATE_ASYNC)
-			return 0;
+			return -EAGAIN;
 
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		if (fatal_signal_pending(current))
-			return 0;
+			return -EINTR;
 	}
 
 	cond_resched();
@@ -1130,7 +1132,9 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	if (nr_isolated)
 		count_compact_events(COMPACTISOLATED, nr_isolated);
 
-	return low_pfn;
+	cc->migrate_pfn = low_pfn;
+
+	return 0;
 }
 
 /**
@@ -1139,15 +1143,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
  * @start_pfn: The first PFN to start isolating.
  * @end_pfn:   The one-past-last PFN.
  *
- * Returns zero if isolation fails fatally due to e.g. pending signal.
- * Otherwise, function returns one-past-the-last PFN of isolated page
- * (which may be greater than end_pfn if end fell in a middle of a THP page).
+ * Returns errno, like -EAGAIN or -EINTR in case e.g signal pending or congestion,
+ * or 0.
  */
-unsigned long
+int
 isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 							unsigned long end_pfn)
 {
 	unsigned long pfn, block_start_pfn, block_end_pfn;
+	int ret = 0;
 
 	/* Scan block by block. First and last block may be incomplete */
 	pfn = start_pfn;
@@ -1166,17 +1170,17 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 					block_end_pfn, cc->zone))
 			continue;
 
-		pfn = isolate_migratepages_block(cc, pfn, block_end_pfn,
-							ISOLATE_UNEVICTABLE);
+		ret = isolate_migratepages_block(cc, pfn, block_end_pfn,
+						 ISOLATE_UNEVICTABLE);
 
-		if (!pfn)
+		if (ret)
 			break;
 
 		if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX)
 			break;
 	}
 
-	return pfn;
+	return ret;
 }
 
 #endif /* CONFIG_COMPACTION || CONFIG_CMA */
@@ -1847,7 +1851,7 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 	 */
 	for (; block_end_pfn <= cc->free_pfn;
 			fast_find_block = false,
-			low_pfn = block_end_pfn,
+			cc->migrate_pfn = low_pfn = block_end_pfn,
 			block_start_pfn = block_end_pfn,
 			block_end_pfn += pageblock_nr_pages) {
 
@@ -1889,10 +1893,8 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 		}
 
 		/* Perform the isolation */
-		low_pfn = isolate_migratepages_block(cc, low_pfn,
-						block_end_pfn, isolate_mode);
-
-		if (!low_pfn)
+		if (isolate_migratepages_block(cc, low_pfn, block_end_pfn,
+						isolate_mode))
 			return ISOLATE_ABORT;
 
 		/*
@@ -1903,9 +1905,6 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 		break;
 	}
 
-	/* Record where migration scanner will be restarted. */
-	cc->migrate_pfn = low_pfn;
-
 	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index 1432feec62df..aedb9120ac16 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -225,7 +225,13 @@ struct compact_control {
 	unsigned int nr_freepages;	/* Number of isolated free pages */
 	unsigned int nr_migratepages;	/* Number of pages to migrate */
 	unsigned long free_pfn;		/* isolate_freepages search base */
-	unsigned long migrate_pfn;	/* isolate_migratepages search base */
+	/*
+	 * Acts as an in/out parameter to page isolation for migration.
+	 * isolate_migratepages uses it as a search base.
+	 * isolate_migratepages_block will update the value to the next pfn
+	 * after the last isolated one.
+	 */
+	unsigned long migrate_pfn;
 	unsigned long fast_start_pfn;	/* a pfn to start linear scan from */
 	struct zone *zone;
 	unsigned long total_migrate_scanned;
@@ -261,7 +267,7 @@ struct capture_control {
 unsigned long
 isolate_freepages_range(struct compact_control *cc,
 			unsigned long start_pfn, unsigned long end_pfn);
-unsigned long
+int
 isolate_migratepages_range(struct compact_control *cc,
 			   unsigned long low_pfn, unsigned long end_pfn);
 int find_suitable_fallback(struct free_area *area, unsigned int order,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a4f67063b85f..ce6a14a446a4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8474,11 +8474,10 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 
 		if (list_empty(&cc->migratepages)) {
 			cc->nr_migratepages = 0;
-			pfn = isolate_migratepages_range(cc, pfn, end);
-			if (!pfn) {
-				ret = -EINTR;
+			ret = isolate_migratepages_range(cc, pfn, end);
+			if (ret && ret != -EAGAIN)
 				break;
-			}
+			pfn = cc->migrate_pfn;
 			tries = 0;
 		} else if (++tries == 5) {
 			ret = -EBUSY;
-- 
2.16.3

Re: [PATCH v6 2/5] mm,compaction: Let isolate_migratepages_{range,block} return error codes

[Oscar Salvador]

On Fri, Mar 19, 2021 at 02:20:01PM +0100, Oscar Salvador wrote:
> Currently, isolate_migratepages_{range,block} and their callers use
> a pfn == 0 vs pfn != 0 scheme to let the caller know whether there was
> any error during isolation.
> This does not work as soon as we need to start reporting different error
> codes and make sure we pass them down the chain, so they are properly
> interpreted by functions like e.g: alloc_contig_range.
> 
> Let us rework isolate_migratepages_{range,block} so we can report error
> codes.
> Since isolate_migratepages_block will stop returning the next pfn to be
> scanned, we reuse the cc->migrate_pfn field to keep track of that.
> 
> Signed-off-by: Oscar Salvador <osalvador@suse.de>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>

Hi Andrew,

I realized a missed place wrt. error handling.
could you squash this on top?

diff --git a/mm/compaction.c b/mm/compaction.c
index cd090a675321..9b989fc3168d 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -809,6 +809,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	bool skip_on_failure = false;
 	unsigned long next_skip_pfn = 0;
 	bool skip_updated = false;
+	int ret = 0;
 
 	cc->migrate_pfn = low_pfn;
 
@@ -877,8 +878,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 			if (fatal_signal_pending(current)) {
 				cc->contended = true;
+				ret = -EINTR;
 
-				low_pfn = 0;
 				goto fatal_pending;
 			}
 
@@ -1134,7 +1135,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 	cc->migrate_pfn = low_pfn;
 
-	return 0;
+	return ret;
 }


Thanks a lot

-- 
Oscar Salvador
SUSE L3

[PATCH v6 3/5] mm: Make alloc_contig_range handle free hugetlb pages

[Oscar Salvador]

alloc_contig_range will fail if it ever sees a HugeTLB page within the
range we are trying to allocate, even when that page is free and can be
easily reallocated.
This has proved to be problematic for some users of alloc_contic_range,
e.g: CMA and virtio-mem, where those would fail the call even when those
pages lay in ZONE_MOVABLE and are free.

We can do better by trying to replace such page.

Free hugepages are tricky to handle so as to no userspace application
notices disruption, we need to replace the current free hugepage with
a new one.

In order to do that, a new function called alloc_and_dissolve_huge_page
is introduced.
This function will first try to get a new fresh hugepage, and if it
succeeds, it will replace the old one in the free hugepage pool.

The free page replacement is done under hugetlb_lock, so no external
user of hugetlb will notice the change. There is one tricky case when
page's refcount is 0 because it is in the process of being released.
A missing PageHugeFreed bit will tell us that freeing is in flight so
we retry after dropping the hugetlb_lock. The race window should be
small and the next retry should make a forward progress.

E.g:

CPU0				CPU1
__free_huge_page()		isolate_or_dissolve_huge_page
				  PageHuge() == T
				  alloc_and_dissolve_huge_page
				    alloc_fresh_huge_page()
				    spin_lock(hugetlb_lock)
				    // PageHuge() && !PageHugeFreed &&
				    // !PageCount()
				    spin_unlock(hugetlb_lock)
  spin_lock(hugetlb_lock)
  1) update_and_free_page
       PageHuge() == F
       __free_pages()
  2) enqueue_huge_page
       SetPageHugeFreed()
  spin_unlock(&hugetlb_lock)
				  spin_lock(hugetlb_lock)
                                   1) PageHuge() == F (freed by case#1 from CPU0)
				   2) PageHuge() == T
                                       PageHugeFreed() == T
                                       - proceed with replacing the page

In the case above we retry as the window race is quite small and we have high
chances to succeed next time.

With regard to the allocation, we restrict it to the node the page belongs
to with __GFP_THISNODE, meaning we do not fallback on other node's zones.

Note that gigantic hugetlb pages are fenced off since there is a cyclic
dependency between them and alloc_contig_range.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
---
 include/linux/hugetlb.h |   6 +++
 mm/compaction.c         |  37 ++++++++++++++--
 mm/hugetlb.c            | 109 +++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 147 insertions(+), 5 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index cccd1aab69dd..bcff86ca616f 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -583,6 +583,7 @@ struct huge_bootmem_page {
 	struct hstate *hstate;
 };
 
+int isolate_or_dissolve_huge_page(struct page *page);
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
@@ -865,6 +866,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
+static inline int isolate_or_dissolve_huge_page(struct page *page)
+{
+	return -ENOMEM;
+}
+
 static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
 					   unsigned long addr,
 					   int avoid_reserve)
diff --git a/mm/compaction.c b/mm/compaction.c
index cd090a675321..3b26c5c6c931 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -788,7 +788,7 @@ static bool too_many_isolated(pg_data_t *pgdat)
  * Isolate all pages that can be migrated from the range specified by
  * [low_pfn, end_pfn). The range is expected to be within same pageblock.
  * Returns errno, like -EAGAIN or -EINTR in case e.g signal pending or congestion,
- * or 0.
+ * -ENOMEM in case we could not allocate a page, or 0.
  * cc->migrate_pfn will contain the next pfn to scan (which may be both less,
  * equal to or more that end_pfn).
  *
@@ -809,6 +809,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	bool skip_on_failure = false;
 	unsigned long next_skip_pfn = 0;
 	bool skip_updated = false;
+	bool fatal_error = false;
+	int ret = 0;
 
 	cc->migrate_pfn = low_pfn;
 
@@ -906,6 +908,32 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			valid_page = page;
 		}
 
+		if (PageHuge(page) && cc->alloc_contig) {
+			ret = isolate_or_dissolve_huge_page(page);
+
+			/*
+			 * Fail isolation in case isolate_or_dissolve_huge_page
+			 * reports an error. In case of -ENOMEM, abort right away.
+			 */
+			if (ret < 0) {
+				/*
+				 * Do not report -EBUSY down the chain.
+				 */
+				if (ret == -ENOMEM)
+					fatal_error = true;
+				else
+					ret = 0;
+				goto isolate_fail;
+			}
+
+			/*
+			 * Ok, the hugepage was dissolved. Now these pages are
+			 * Buddy and cannot be re-allocated because they are
+			 * isolated. Fall-through as the check below handles
+			 * Buddy pages.
+			 */
+		}
+
 		/*
 		 * Skip if free. We read page order here without zone lock
 		 * which is generally unsafe, but the race window is small and
@@ -1091,6 +1119,9 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			 */
 			next_skip_pfn += 1UL << cc->order;
 		}
+
+		if (fatal_error)
+			break;
 	}
 
 	/*
@@ -1134,7 +1165,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 	cc->migrate_pfn = low_pfn;
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -1144,7 +1175,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
  * @end_pfn:   The one-past-last PFN.
  *
  * Returns errno, like -EAGAIN or -EINTR in case e.g signal pending or congestion,
- * or 0.
+ * -ENOMEM in case we could not allocate a page, or 0.
  */
 int
 isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5b1ab1f427c5..3194c1bd9e32 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1035,13 +1035,18 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg)
 	return false;
 }
 
+static void __enqueue_huge_page(struct list_head *list, struct page *page)
+{
+	list_move(&page->lru, list);
+	SetHPageFreed(page);
+}
+
 static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
 	int nid = page_to_nid(page);
-	list_move(&page->lru, &h->hugepage_freelists[nid]);
+	__enqueue_huge_page(&h->hugepage_freelists[nid], page);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
-	SetHPageFreed(page);
 }
 
 static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
@@ -2245,6 +2250,106 @@ static void restore_reserve_on_error(struct hstate *h,
 	}
 }
 
+/*
+ * alloc_and_dissolve_huge_page - Allocate a new page and dissolve the old one
+ * @h: struct hstate old page belongs to
+ * @old_page: Old page to dissolve
+ * Returns 0 on success, otherwise negated error.
+ */
+
+static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page)
+{
+	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
+	int nid = page_to_nid(old_page);
+	struct page *new_page;
+	int ret = 0;
+
+	/*
+	 * Before dissolving the page, we need to allocate a new one,
+	 * so the pool remains stable.
+	 */
+	new_page = alloc_fresh_huge_page(h, gfp_mask, nid, NULL, NULL);
+	if (!new_page)
+		return -ENOMEM;
+
+	/*
+	 * Pages got from Buddy are self-refcounted, but free hugepages
+	 * need to have a refcount of 0.
+	 */
+	page_ref_dec(new_page);
+retry:
+	spin_lock(&hugetlb_lock);
+	if (!PageHuge(old_page)) {
+		/*
+		 * Freed from under us. Drop new_page too.
+		 */
+		update_and_free_page(h, new_page);
+		goto unlock;
+	} else if (page_count(old_page)) {
+		/*
+		 * Someone has grabbed the page, fail for now.
+		 */
+		ret = -EBUSY;
+		update_and_free_page(h, new_page);
+		goto unlock;
+	} else if (!HPageFreed(old_page)) {
+		/*
+		 * Page's refcount is 0 but it has not been enqueued in the
+		 * freelist yet. Race window is small, so we can succed here if
+		 * we retry.
+		 */
+		spin_unlock(&hugetlb_lock);
+		cond_resched();
+		goto retry;
+	} else {
+		/*
+		 * Ok, old_page is still a genuine free hugepage. Replace it
+		 * with the new one.
+		 */
+		list_del(&old_page->lru);
+		update_and_free_page(h, old_page);
+		/*
+		 * h->free_huge_pages{_node} counters do not need to be updated.
+		 */
+		__enqueue_huge_page(&h->hugepage_freelists[nid], new_page);
+	}
+unlock:
+	spin_unlock(&hugetlb_lock);
+
+	return ret;
+}
+
+int isolate_or_dissolve_huge_page(struct page *page)
+{
+	struct hstate *h;
+	struct page *head;
+
+	/*
+	 * The page might have been dissolved from under our feet, so make sure
+	 * to carefully check the state under the lock.
+	 * Return success when racing as if we dissolved the page ourselves.
+	 */
+	spin_lock(&hugetlb_lock);
+	if (PageHuge(page)) {
+		head = compound_head(page);
+		h = page_hstate(head);
+	} else {
+		spin_unlock(&hugetlb_lock);
+		return 0;
+	}
+	spin_unlock(&hugetlb_lock);
+
+	/*
+	 * Fence off gigantic pages as there is a cyclic dependency between
+	 * alloc_contig_range and them. Return -ENOME as this has the effect
+	 * of bailing out right away without further retrying.
+	 */
+	if (hstate_is_gigantic(h))
+		return -ENOMEM;
+
+	return alloc_and_dissolve_huge_page(h, head);
+}
+
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				    unsigned long addr, int avoid_reserve)
 {
-- 
2.16.3

[PATCH v6 4/5] mm: Make alloc_contig_range handle in-use hugetlb pages

[Oscar Salvador]

alloc_contig_range() will fail if it finds a HugeTLB page within the range,
without a chance to handle them. Since HugeTLB pages can be migrated as any
LRU or Movable page, it does not make sense to bail out without trying.
Enable the interface to recognize in-use HugeTLB pages so we can migrate
them, and have much better chances to succeed the call.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
---
 include/linux/hugetlb.h |  5 +++--
 mm/compaction.c         | 12 +++++++++++-
 mm/hugetlb.c            | 22 ++++++++++++++++------
 mm/vmscan.c             |  5 +++--
 4 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index bcff86ca616f..a37b4ce86e58 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -583,7 +583,7 @@ struct huge_bootmem_page {
 	struct hstate *hstate;
 };
 
-int isolate_or_dissolve_huge_page(struct page *page);
+int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
@@ -866,7 +866,8 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
-static inline int isolate_or_dissolve_huge_page(struct page *page)
+static inline int isolate_or_dissolve_huge_page(struct page *page,
+						struct list_head *list)
 {
 	return -ENOMEM;
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index 3b26c5c6c931..4143d1984a21 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -909,7 +909,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		}
 
 		if (PageHuge(page) && cc->alloc_contig) {
-			ret = isolate_or_dissolve_huge_page(page);
+			ret = isolate_or_dissolve_huge_page(page, &cc->migratepages);
 
 			/*
 			 * Fail isolation in case isolate_or_dissolve_huge_page
@@ -926,6 +926,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 				goto isolate_fail;
 			}
 
+			if (PageHuge(page)) {
+				/*
+				 * Hugepage was successfully isolated and placed
+				 * on the cc->migratepages list.
+				 */
+				low_pfn += compound_nr(page) - 1;
+				goto isolate_success_no_list;
+			}
+
 			/*
 			 * Ok, the hugepage was dissolved. Now these pages are
 			 * Buddy and cannot be re-allocated because they are
@@ -1067,6 +1076,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 isolate_success:
 		list_add(&page->lru, &cc->migratepages);
+isolate_success_no_list:
 		cc->nr_migratepages += compound_nr(page);
 		nr_isolated += compound_nr(page);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3194c1bd9e32..85e4bedbd5ac 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2257,7 +2257,8 @@ static void restore_reserve_on_error(struct hstate *h,
  * Returns 0 on success, otherwise negated error.
  */
 
-static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page)
+static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page,
+					struct list_head *list)
 {
 	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 	int nid = page_to_nid(old_page);
@@ -2287,11 +2288,14 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page)
 		goto unlock;
 	} else if (page_count(old_page)) {
 		/*
-		 * Someone has grabbed the page, fail for now.
+		 * Someone has grabbed the page, try to isolate it here.
+		 * Fail with -EBUSY if not possible.
 		 */
-		ret = -EBUSY;
 		update_and_free_page(h, new_page);
-		goto unlock;
+		spin_unlock(&hugetlb_lock);
+		if (!isolate_huge_page(old_page, list))
+			ret = -EBUSY;
+		return ret;
 	} else if (!HPageFreed(old_page)) {
 		/*
 		 * Page's refcount is 0 but it has not been enqueued in the
@@ -2319,10 +2323,11 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page)
 	return ret;
 }
 
-int isolate_or_dissolve_huge_page(struct page *page)
+int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
 {
 	struct hstate *h;
 	struct page *head;
+	int ret = -EBUSY;
 
 	/*
 	 * The page might have been dissolved from under our feet, so make sure
@@ -2347,7 +2352,12 @@ int isolate_or_dissolve_huge_page(struct page *page)
 	if (hstate_is_gigantic(h))
 		return -ENOMEM;
 
-	return alloc_and_dissolve_huge_page(h, head);
+	if (page_count(head) && isolate_huge_page(head, list))
+		ret = 0;
+	else if (!page_count(head))
+		ret = alloc_and_dissolve_huge_page(h, head, list);
+
+	return ret;
 }
 
 struct page *alloc_huge_page(struct vm_area_struct *vma,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 562e87cbd7a1..42aaef30633e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1507,8 +1507,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 	LIST_HEAD(clean_pages);
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
-		if (page_is_file_lru(page) && !PageDirty(page) &&
-		    !__PageMovable(page) && !PageUnevictable(page)) {
+		if (!PageHuge(page) && page_is_file_lru(page) &&
+		    !PageDirty(page) && !__PageMovable(page) &&
+		    !PageUnevictable(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
-- 
2.16.3

[PATCH v6 5/5] mm,page_alloc: Drop unnecessary checks from pfn_range_valid_contig

[Oscar Salvador]

pfn_range_valid_contig() bails out when it finds an in-use page or a
hugetlb page, among other things.
We can drop the in-use page check since __alloc_contig_pages can migrate
away those pages, and the hugetlb page check can go too since
isolate_migratepages_range is now capable of dealing with hugetlb pages.
Either way, those checks are racy so let the end function handle it
when the time comes.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Suggested-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
 mm/page_alloc.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ce6a14a446a4..516302b280de 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8685,12 +8685,6 @@ static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn,
 
 		if (PageReserved(page))
 			return false;
-
-		if (page_count(page) > 0)
-			return false;
-
-		if (PageHuge(page))
-			return false;
 	}
 	return true;
 }
-- 
2.16.3

Re: [PATCH v6 5/5] mm,page_alloc: Drop unnecessary checks from pfn_range_valid_contig

[Michal Hocko]

On Fri 19-03-21 14:20:04, Oscar Salvador wrote:
> pfn_range_valid_contig() bails out when it finds an in-use page or a
> hugetlb page, among other things.
> We can drop the in-use page check since __alloc_contig_pages can migrate
> away those pages, and the hugetlb page check can go too since
> isolate_migratepages_range is now capable of dealing with hugetlb pages.
> Either way, those checks are racy so let the end function handle it
> when the time comes.
> 
> Signed-off-by: Oscar Salvador <osalvador@suse.de>
> Suggested-by: David Hildenbrand <david@redhat.com>
> Reviewed-by: David Hildenbrand <david@redhat.com>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
>  mm/page_alloc.c | 6 ------
>  1 file changed, 6 deletions(-)
> 
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index ce6a14a446a4..516302b280de 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -8685,12 +8685,6 @@ static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn,
>  
>  		if (PageReserved(page))
>  			return false;
> -
> -		if (page_count(page) > 0)
> -			return false;
> -
> -		if (PageHuge(page))
> -			return false;
>  	}
>  	return true;
>  }
> -- 
> 2.16.3

-- 
Michal Hocko
SUSE Labs