mm: hugetlb: make the hugetlb migration strategy consistent

As discussed in previous thread [1], there is an inconsistency when
handing hugetlb migration.  When handling the migration of freed hugetlb,
it prevents fallback to other NUMA nodes in
alloc_and_dissolve_hugetlb_folio().  However, when dealing with in-use
hugetlb, it allows fallback to other NUMA nodes in
alloc_hugetlb_folio_nodemask(), which can break the per-node hugetlb pool
and might result in unexpected failures when node bound workloads doesn't
get what is asssumed available.

To make hugetlb migration strategy more clear, we should list all the scenarios
of hugetlb migration and analyze whether allocation fallback is permitted:

1) Memory offline: will call dissolve_free_huge_pages() to free the
   freed hugetlb, and call do_migrate_range() to migrate the in-use
   hugetlb.  Both can break the per-node hugetlb pool, but as this is an
   explicit offlining operation, no better choice.  So should allow the
   hugetlb allocation fallback.

2) Memory failure: same as memory offline.  Should allow fallback to a
   different node might be the only option to handle it, otherwise the
   impact of poisoned memory can be amplified.

3) Longterm pinning: will call migrate_longterm_unpinnable_pages() to
   migrate in-use and not-longterm-pinnable hugetlb, which can break the
   per-node pool.  But we should fail to longterm pinning if can not
   allocate on current node to avoid breaking the per-node pool.

4) Syscalls (mbind, migrate_pages, move_pages): these are explicit
   users operation to move pages to other nodes, so fallback to other
   nodes should not be prohibited.

5) alloc_contig_range: used by CMA allocation and virtio-mem
   fake-offline to allocate given range of pages.  Now the freed hugetlb
   migration is not allowed to fallback, to keep consistency, the in-use
   hugetlb migration should be also not allowed to fallback.

6) alloc_contig_pages: used by kfence, pgtable_debug etc.  The strategy
   should be consistent with that of alloc_contig_range().

Based on the analysis of the various scenarios above, introducing a new
helper to determine whether fallback is permitted according to the
migration reason..

[1] https://lore.kernel.org/all/6f26ce22d2fcd523418a085f2c588fe0776d46e7.1706794035.git.baolin.wang@linux.alibaba.com/
Link: https://lkml.kernel.org/r/3519fcd41522817307a05b40fb551e2e17e68101.1709719720.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

4 files changed, 49 insertions, 6 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 300de33c6fde..d748628efc5e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -723,7 +723,8 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
 struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
-				nodemask_t *nmask, gfp_t gfp_mask);
+				nodemask_t *nmask, gfp_t gfp_mask,
+				bool allow_alloc_fallback);
 int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,
 			pgoff_t idx);
 void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
@@ -946,6 +947,30 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
 	return modified_mask;
 }
 
+static inline bool htlb_allow_alloc_fallback(int reason)
+{
+	bool allowed_fallback = false;
+
+	/*
+	 * Note: the memory offline, memory failure and migration syscalls will
+	 * be allowed to fallback to other nodes due to lack of a better chioce,
+	 * that might break the per-node hugetlb pool. While other cases will
+	 * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool.
+	 */
+	switch (reason) {
+	case MR_MEMORY_HOTPLUG:
+	case MR_MEMORY_FAILURE:
+	case MR_SYSCALL:
+	case MR_MEMPOLICY_MBIND:
+		allowed_fallback = true;
+		break;
+	default:
+		break;
+	}
+
+	return allowed_fallback;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
@@ -1041,7 +1066,8 @@ static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 
 static inline struct folio *
 alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
-			nodemask_t *nmask, gfp_t gfp_mask)
+			nodemask_t *nmask, gfp_t gfp_mask,
+			bool allow_alloc_fallback)
 {
 	return NULL;
 }
@@ -1157,6 +1183,11 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
 	return 0;
 }
 
+static inline bool htlb_allow_alloc_fallback(int reason)
+{
+	return false;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e4dd0c802489..2e984554ec63 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2598,7 +2598,7 @@ struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h,
 
 /* folio migration callback function */
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
-		nodemask_t *nmask, gfp_t gfp_mask)
+		nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback)
 {
 	spin_lock_irq(&hugetlb_lock);
 	if (available_huge_pages(h)) {
@@ -2613,6 +2613,10 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
 	}
 	spin_unlock_irq(&hugetlb_lock);
 
+	/* We cannot fallback to other nodes, as we could break the per-node pool. */
+	if (!allow_alloc_fallback)
+		gfp_mask |= __GFP_THISNODE;
+
 	return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask);
 }
 
@@ -6636,7 +6640,13 @@ static struct folio *alloc_hugetlb_folio_vma(struct hstate *h,
 
 	gfp_mask = htlb_alloc_mask(h);
 	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask);
+	/*
+	 * This is used to allocate a temporary hugetlb to hold the copied
+	 * content, which will then be copied again to the final hugetlb
+	 * consuming a reservation. Set the alloc_fallback to false to indicate
+	 * that breaking the per-node hugetlb pool is not allowed in this case.
+	 */
+	folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask, false);
 	mpol_cond_put(mpol);
 
 	return folio;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e128e6b7bbcb..72626b2cefa9 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1228,7 +1228,8 @@ static struct folio *alloc_migration_target_by_mpol(struct folio *src,
 		h = folio_hstate(src);
 		gfp = htlb_alloc_mask(h);
 		nodemask = policy_nodemask(gfp, pol, ilx, &nid);
-		return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp);
+		return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp,
+				htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND));
 	}
 
 	if (folio_test_large(src))
diff --git a/mm/migrate.c b/mm/migrate.c
index bde63010a3cf..ab9856f5931b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2022,7 +2022,8 @@ struct folio *alloc_migration_target(struct folio *src, unsigned long private)
 
 		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
 		return alloc_hugetlb_folio_nodemask(h, nid,
-						mtc->nmask, gfp_mask);
+						mtc->nmask, gfp_mask,
+						htlb_allow_alloc_fallback(mtc->reason));
 	}
 
 	if (folio_test_large(src)) {