mm/vma: change munmap to use vma_munmap_struct() for accounting and surrounding vmas

Clean up the code by changing the munmap operation to use a structure for
the accounting and munmap variables.

Since remove_mt() is only called in one location and the contents will be
reduced to almost nothing.  The remains of the function can be added to
vms_complete_munmap_vmas().

Link: https://lkml.kernel.org/r/20240830040101.822209-7-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Bert Karwatzki <spasswolf@web.de>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Jiri Olsa <olsajiri@gmail.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/vma.c

@@ -103,7 +103,8 @@ static inline void init_vma_munmap(struct vma_munmap_struct *vms,
 	vms->unlock = unlock;
 	vms->uf = uf;
 	vms->vma_count = 0;
-	vms->nr_pages = vms->locked_vm = 0;
+	vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0;
+	vms->exec_vm = vms->stack_vm = vms->data_vm = 0;
 }
 
 /*
@@ -299,30 +300,6 @@ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	return __split_vma(vmi, vma, addr, new_below);
 }
 
-/*
- * Ok - we have the memory areas we should free on a maple tree so release them,
- * and do the vma updates.
- *
- * Called with the mm semaphore held.
- */
-static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas)
-{
-	unsigned long nr_accounted = 0;
-	struct vm_area_struct *vma;
-
-	/* Update high watermark before we lower total_vm */
-	update_hiwater_vm(mm);
-	mas_for_each(mas, vma, ULONG_MAX) {
-		long nrpages = vma_pages(vma);
-
-		if (vma->vm_flags & VM_ACCOUNT)
-			nr_accounted += nrpages;
-		vm_stat_account(mm, vma->vm_flags, -nrpages);
-		remove_vma(vma, false);
-	}
-	vm_unacct_memory(nr_accounted);
-}
-
 /*
  * init_vma_prep() - Initializer wrapper for vma_prepare struct
  * @vp: The vma_prepare struct
@@ -722,7 +699,7 @@ static inline void abort_munmap_vmas(struct ma_state *mas_detach)
 static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms,
 		struct ma_state *mas_detach)
 {
-	struct vm_area_struct *prev, *next;
+	struct vm_area_struct *vma;
 	struct mm_struct *mm;
 
 	mm = vms->mm;
@@ -731,21 +708,31 @@ static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms,
 	if (vms->unlock)
 		mmap_write_downgrade(mm);
 
-	prev = vma_iter_prev_range(vms->vmi);
-	next = vma_next(vms->vmi);
-	if (next)
-		vma_iter_prev_range(vms->vmi);
-
 	/*
 	 * We can free page tables without write-locking mmap_lock because VMAs
 	 * were isolated before we downgraded mmap_lock.
 	 */
 	mas_set(mas_detach, 1);
-	unmap_region(mm, mas_detach, vms->vma, prev, next, vms->start, vms->end,
+	unmap_region(mm, mas_detach, vms->vma, vms->prev, vms->next,
-		     vms->vma_count, !vms->unlock);
+		     vms->start, vms->end, vms->vma_count, !vms->unlock);
-	/* Statistics and freeing VMAs */
+	/* Update high watermark before we lower total_vm */
+	update_hiwater_vm(mm);
+	/* Stat accounting */
+	WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm) - vms->nr_pages);
+	/* Paranoid bookkeeping */
+	VM_WARN_ON(vms->exec_vm > mm->exec_vm);
+	VM_WARN_ON(vms->stack_vm > mm->stack_vm);
+	VM_WARN_ON(vms->data_vm > mm->data_vm);
+	mm->exec_vm -= vms->exec_vm;
+	mm->stack_vm -= vms->stack_vm;
+	mm->data_vm -= vms->data_vm;
+
+	/* Remove and clean up vmas */
 	mas_set(mas_detach, 0);
-	remove_mt(mm, mas_detach);
+	mas_for_each(mas_detach, vma, ULONG_MAX)
+		remove_vma(vma, false);
+
+	vm_unacct_memory(vms->nr_accounted);
 	validate_mm(mm);
 	if (vms->unlock)
 		mmap_read_unlock(mm);
@@ -798,18 +785,19 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
 		if (__split_vma(vms->vmi, vms->vma, vms->start, 1))
 			goto start_split_failed;
 	}
+	vms->prev = vma_prev(vms->vmi);
 
 	/*
 	 * Detach a range of VMAs from the mm. Using next as a temp variable as
 	 * it is always overwritten.
 	 */
-	next = vms->vma;
+	for_each_vma_range(*(vms->vmi), next, vms->end) {
-	do {
+		long nrpages;
+
 		if (!can_modify_vma(next)) {
 			error = -EPERM;
 			goto modify_vma_failed;
 		}
-
 		/* Does it split the end? */
 		if (next->vm_end > vms->end) {
 			if (__split_vma(vms->vmi, next, vms->end, 0))
@@ -821,8 +809,21 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
 			goto munmap_gather_failed;
 
 		vma_mark_detached(next, true);
+		nrpages = vma_pages(next);
+
+		vms->nr_pages += nrpages;
 		if (next->vm_flags & VM_LOCKED)
-			vms->locked_vm += vma_pages(next);
+			vms->locked_vm += nrpages;
+
+		if (next->vm_flags & VM_ACCOUNT)
+			vms->nr_accounted += nrpages;
+
+		if (is_exec_mapping(next->vm_flags))
+			vms->exec_vm += nrpages;
+		else if (is_stack_mapping(next->vm_flags))
+			vms->stack_vm += nrpages;
+		else if (is_data_mapping(next->vm_flags))
+			vms->data_vm += nrpages;
 
 		if (unlikely(vms->uf)) {
 			/*
@@ -842,7 +843,9 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
 		BUG_ON(next->vm_start < vms->start);
 		BUG_ON(next->vm_start > vms->end);
 #endif
-	} for_each_vma_range(*(vms->vmi), next, vms->end);
+	}
+
+	vms->next = vma_next(vms->vmi);
 
 #if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
 	/* Make sure no VMAs are about to be lost. */

mm/vma.h

@@ -33,12 +33,18 @@ struct vma_munmap_struct {
 	struct vma_iterator *vmi;
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;     /* The first vma to munmap */
+	struct vm_area_struct *prev;    /* vma before the munmap area */
+	struct vm_area_struct *next;    /* vma after the munmap area */
 	struct list_head *uf;           /* Userfaultfd list_head */
 	unsigned long start;            /* Aligned start addr (inclusive) */
 	unsigned long end;              /* Aligned end addr (exclusive) */
 	int vma_count;                  /* Number of vmas that will be removed */
 	unsigned long nr_pages;         /* Number of pages being removed */
 	unsigned long locked_vm;        /* Number of locked pages */
+	unsigned long nr_accounted;     /* Number of VM_ACCOUNT pages */
+	unsigned long exec_vm;
+	unsigned long stack_vm;
+	unsigned long data_vm;
 	bool unlock;                    /* Unlock after the munmap */
 };