[PATCH 6.12.y] mm/hugetlb: fix mremap deadlock when PMD sharing is possible

[Sasha Levin <sashal@kernel.org>]

From: Li Zhe <lizhe.67@bytedance.com>

[ Upstream commit 92daa8652f88c8cfc05f4899a8408a04b02f211e ]

move_hugetlb_page_tables() holds the mapping's i_mmap_rwsem for
write while moving hugetlb PTEs. This prevents races with truncation
and protects huge_pmd_unshare(), but the move loop must not call
helpers that can acquire the same rwsem for read.

huge_pte_alloc() can do that when the destination can use PMD
sharing: it may call huge_pmd_share(), which takes i_mmap_rwsem for
read while searching for a shareable PMD table. Calling it while the
move path already holds i_mmap_rwsem for write can deadlock.

Avoid that path for PMD-sized hugetlb mappings that can use PMD
sharing. Instead of allocating or sharing the destination page table
while moving, zap the source range and let the destination fault path
populate or share the PMD lazily.

Reuse the hugetlb unmap logic for the source-side zap by splitting
the core loop out of __unmap_hugepage_range(). The wrapper keeps the
existing tlb_start_vma(), tlb_end_vma() and huge_pmd_unshare_flush()
behavior, while move_hugetlb_page_tables() can reuse the unmap loop
with its existing mmu_gather.

Link: https://lore.kernel.org/20261022034543.51226-4-lizhe.67@bytedance.com
Fixes: 550a7d60bd5e ("mm, hugepages: add mremap() support for hugepage backed vma")
Signed-off-by: Li Zhe <lizhe.67@bytedance.com>
Co-developed-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Jose A. Perez de Azpillaga <azpijr@gmail.com>
Cc: <stable@vger.kernel.org>
[ sashal: adapted the unmap helper’s folio parameter to the existing struct page ref_page interface ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 mm/hugetlb.c | 47 +++++++++++++++++++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e6f913f227e6c..fcdb4f2e4c599 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -92,6 +92,10 @@ static int __huge_pmd_unshare(struct mmu_gather *tlb,
 		bool check_locks);
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end, bool take_locks);
+static void hugetlb_unmap_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, unsigned long start,
+				unsigned long end, struct page *ref_page,
+				zap_flags_t zap_flags);
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
 static void hugetlb_free_folio(struct folio *folio)
@@ -5540,6 +5544,8 @@ unsigned long move_hugetlb_page_tables(struct vm_area_struct *vma,
 	for (; old_addr < old_end; old_addr += sz, new_addr += sz) {
 		const unsigned long offset_to_last_entry =
 			(old_addr | last_addr_mask) - old_addr;
+		const unsigned long offset_to_last_dst_entry =
+			(new_addr | last_addr_mask) - new_addr;
 
 		src_pte = hugetlb_walk(vma, old_addr, sz);
 		if (!src_pte) {
@@ -5556,6 +5562,24 @@ unsigned long move_hugetlb_page_tables(struct vm_area_struct *vma,
 			continue;
 		}
 
+		/*
+		 * Avoid entering the destination PMD sharing path while holding
+		 * i_mmap_rwsem for write. Leave destination page table
+		 * population to the fault path, which can share the PMD lazily.
+		 */
+		if (sz == PMD_SIZE && want_pmd_share(new_vma, new_addr)) {
+			const unsigned long unmap_size =
+				min(old_end - old_addr,
+				    offset_to_last_dst_entry + sz);
+
+			hugetlb_unmap_range(&tlb, vma, old_addr,
+					    old_addr + unmap_size, NULL,
+					    ZAP_FLAG_DROP_MARKER);
+			old_addr += unmap_size - sz;
+			new_addr += unmap_size - sz;
+			continue;
+		}
+
 		dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz);
 		if (!dst_pte)
 			break;
@@ -5575,9 +5599,10 @@ unsigned long move_hugetlb_page_tables(struct vm_area_struct *vma,
 	return len + old_addr - old_end;
 }
 
-void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
-			    unsigned long start, unsigned long end,
-			    struct page *ref_page, zap_flags_t zap_flags)
+static void hugetlb_unmap_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, unsigned long start,
+				unsigned long end, struct page *ref_page,
+				zap_flags_t zap_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -5595,13 +5620,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	BUG_ON(start & ~huge_page_mask(h));
 	BUG_ON(end & ~huge_page_mask(h));
 
-	/*
-	 * This is a hugetlb vma, all the pte entries should point
-	 * to huge page.
-	 */
-	tlb_change_page_size(tlb, sz);
-	tlb_start_vma(tlb, vma);
-
 	last_addr_mask = hugetlb_mask_last_page(h);
 	address = start;
 	for (; address < end; address += sz) {
@@ -5728,6 +5746,15 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		if (ref_page)
 			break;
 	}
+}
+
+void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+			    unsigned long start, unsigned long end,
+			    struct page *ref_page, zap_flags_t zap_flags)
+{
+	tlb_change_page_size(tlb, huge_page_size(hstate_vma(vma)));
+	tlb_start_vma(tlb, vma);
+	hugetlb_unmap_range(tlb, vma, start, end, ref_page, zap_flags);
 	tlb_end_vma(tlb, vma);
 
 	huge_pmd_unshare_flush(tlb, vma);
-- 
2.53.0