mm/vma: use unmap_desc in exit_mmap() and vms_clear_ptes()

Convert vms_clear_ptes() to use unmap_desc to call unmap_vmas() instead of
the large argument list.  The UNMAP_STATE() cannot be used because the vma
iterator in the vms does not point to the correct maple state
(mas_detach), and the tree_end will be set incorrectly.  Setting up the
arguments manually avoids setting the struct up incorrectly and doing
extra work to get the correct pagetable range.

exit_mmap() also calls unmap_vmas() with many arguments.  Using the
unmap_all_init() function to set the unmap descriptor for all vmas makes
this a bit easier to read.

Update to the vma test code is necessary to ensure testing continues to
function.

No functional changes intended.

Link: https://lkml.kernel.org/r/20260121164946.2093480-10-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Chris Li <chrisl@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: SeongJae Park <sj@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 50 insertions, 18 deletions

diff --git a/mm/internal.h b/mm/internal.h
index 2a0e42e36b48..0f3ad8665d95 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -197,6 +197,9 @@ static inline void vma_close(struct vm_area_struct *vma)
 	}
 }
 
+/* unmap_vmas is in mm/memory.c */
+void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap);
+
 #ifdef CONFIG_MMU
 
 static inline void get_anon_vma(struct anon_vma *anon_vma)
diff --git a/mm/memory.c b/mm/memory.c
index 6033cf6c93de..d68f8f082b1c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2144,11 +2144,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 /**
  * unmap_vmas - unmap a range of memory covered by a list of vma's
  * @tlb: address of the caller's struct mmu_gather
- * @mas: the maple state
- * @vma: the starting vma
- * @start_addr: virtual address at which to start unmapping
- * @end_addr: virtual address at which to end unmapping
- * @tree_end: The maximum index to check
+ * @unmap: The unmap_desc
  *
  * Unmap all pages in the vma list.
  *
@@ -2161,10 +2157,9 @@ static void unmap_single_vma(struct mmu_gather *tlb,
  * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
  * drops the lock and schedules.
  */
-void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
-		struct vm_area_struct *vma, unsigned long start_addr,
-		unsigned long end_addr, unsigned long tree_end)
+void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap)
 {
+	struct vm_area_struct *vma;
 	struct mmu_notifier_range range;
 	struct zap_details details = {
 		.zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP,
@@ -2172,16 +2167,17 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 		.even_cows = true,
 	};
 
+	vma = unmap->first;
 	mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm,
-				start_addr, end_addr);
+				unmap->vma_start, unmap->vma_end);
 	mmu_notifier_invalidate_range_start(&range);
 	do {
-		unsigned long start = start_addr;
-		unsigned long end = end_addr;
+		unsigned long start = unmap->vma_start;
+		unsigned long end = unmap->vma_end;
 		hugetlb_zap_begin(vma, &start, &end);
 		unmap_single_vma(tlb, vma, start, end, &details);
 		hugetlb_zap_end(vma, &details);
-		vma = mas_find(mas, tree_end - 1);
+		vma = mas_find(unmap->mas, unmap->tree_end - 1);
 	} while (vma);
 	mmu_notifier_invalidate_range_end(&range);
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 4500e61a0d5e..042b6b4b6ab8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1277,6 +1277,7 @@ void exit_mmap(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	unsigned long nr_accounted = 0;
 	VMA_ITERATOR(vmi, mm, 0);
+	struct unmap_desc unmap;
 
 	/* mm's last user has gone, and its about to be pulled down */
 	mmu_notifier_release(mm);
@@ -1292,11 +1293,12 @@ void exit_mmap(struct mm_struct *mm)
 		goto destroy;
 	}
 
+	unmap_all_init(&unmap, &vmi, vma);
 	flush_cache_mm(mm);
 	tlb_gather_mmu_fullmm(&tlb, mm);
 	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */
-	unmap_vmas(&tlb, &vmi.mas, vma, 0, ULONG_MAX, ULONG_MAX);
+	unmap_vmas(&tlb, &unmap);
 	mmap_read_unlock(mm);
 
 	/*
diff --git a/mm/vma.c b/mm/vma.c
index 75c68c74c062..b46c869d4bb0 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -480,8 +480,7 @@ void unmap_region(struct unmap_desc *unmap)
 
 	tlb_gather_mmu(&tlb, mm);
 	update_hiwater_rss(mm);
-	unmap_vmas(&tlb, mas, unmap->first, unmap->vma_start, unmap->vma_end,
-		   unmap->vma_end);
+	unmap_vmas(&tlb, unmap);
 	mas_set(mas, unmap->tree_reset);
 	free_pgtables(&tlb, mas, unmap->first, unmap->pg_start, unmap->pg_end,
 		      unmap->tree_end, unmap->mm_wr_locked);
@@ -1257,6 +1256,26 @@ static inline void vms_clear_ptes(struct vma_munmap_struct *vms,
 		    struct ma_state *mas_detach, bool mm_wr_locked)
 {
 	struct mmu_gather tlb;
+	struct unmap_desc unmap = {
+		.mas = mas_detach,
+		.first = vms->vma,
+		/* start and end may be different if there is no prev or next vma. */
+		.pg_start = vms->unmap_start,
+		.pg_end = vms->unmap_end,
+		.vma_start = vms->start,
+		.vma_end = vms->end,
+		/*
+		 * The tree limits and reset differ from the normal case since it's a
+		 * side-tree
+		 */
+		.tree_reset = 1,
+		.tree_end = vms->vma_count,
+		/*
+		 * We can free page tables without write-locking mmap_lock because VMAs
+		 * were isolated before we downgraded mmap_lock.
+		 */
+		.mm_wr_locked = mm_wr_locked,
+	};
 
 	if (!vms->clear_ptes) /* Nothing to do */
 		return;
@@ -1268,9 +1287,7 @@ static inline void vms_clear_ptes(struct vma_munmap_struct *vms,
 	mas_set(mas_detach, 1);
 	tlb_gather_mmu(&tlb, vms->vma->vm_mm);
 	update_hiwater_rss(vms->vma->vm_mm);
-	unmap_vmas(&tlb, mas_detach, vms->vma, vms->start, vms->end,
-		   vms->vma_count);
-
+	unmap_vmas(&tlb, &unmap);
 	mas_set(mas_detach, 1);
 	/* start and end may be different if there is no prev or next vma. */
 	free_pgtables(&tlb, mas_detach, vms->vma, vms->unmap_start,
diff --git a/mm/vma.h b/mm/vma.h
index cca7553c7d64..bb7fa5d2bde2 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -167,6 +167,20 @@ struct unmap_desc {
 	bool mm_wr_locked;            /* If the mmap write lock is held */
 };
 
+static inline void unmap_all_init(struct unmap_desc *unmap,
+		struct vma_iterator *vmi, struct vm_area_struct *vma)
+{
+	unmap->mas = &vmi->mas;
+	unmap->first = vma;
+	unmap->pg_start = FIRST_USER_ADDRESS;
+	unmap->pg_end = USER_PGTABLES_CEILING;
+	unmap->vma_start = 0;
+	unmap->vma_end = ULONG_MAX;
+	unmap->tree_end = ULONG_MAX;
+	unmap->tree_reset = vma->vm_end;
+	unmap->mm_wr_locked = false;
+}
+
 #define UNMAP_STATE(name, _vmi, _vma, _vma_start, _vma_end, _prev, _next)      \
 	struct unmap_desc name = {                                             \
 		.mas = &(_vmi)->mas,                                           \