mm: change do_vmi_align_munmap() tracking of VMAs to remove

The majority of the calls to munmap a vm range is within a single vma.
The maple tree is able to store a single entry at 0, with a size of 1 as
a pointer and avoid any allocations.  Change do_vmi_align_munmap() to
store the VMAs being munmap()'ed into a tree indexed by the count.  This
will leverage the ability to store the first entry without a node
allocation.

Storing the entries into a tree by the count and not the vma start and
end means changing the functions which iterate over the entries.  Update
unmap_vmas() and free_pgtables() to take a maple state and a tree end
address to support this functionality.

Passing through the same maple state to unmap_vmas() and free_pgtables()
means the state needs to be reset between calls.  This happens in the
static unmap_region() and exit_mmap().

Link: https://lkml.kernel.org/r/20230724183157.3939892-4-Liam.Howlett@oracle.comSigned-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Peng Zhang <zhangpeng.00@bytedance.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/mm.h

@@ -2287,9 +2287,9 @@ static inline void zap_vma_pages(struct vm_area_struct *vma)
 	zap_page_range_single(vma, vma->vm_start,
 			      vma->vm_end - vma->vm_start, NULL);
 }
-void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
+void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 		struct vm_area_struct *start_vma, unsigned long start,
-		unsigned long end, bool mm_wr_locked);
+		unsigned long end, unsigned long tree_end, bool mm_wr_locked);
 
 struct mmu_notifier_range;
 

mm/internal.h

@@ -109,7 +109,7 @@ bool __folio_end_writeback(struct folio *folio);
 void deactivate_file_folio(struct folio *folio);
 void folio_activate(struct folio *folio);
 
-void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
+void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 		   struct vm_area_struct *start_vma, unsigned long floor,
 		   unsigned long ceiling, bool mm_wr_locked);
 void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);

mm/memory.c

@@ -361,12 +361,10 @@ void free_pgd_range(struct mmu_gather *tlb,
 	} while (pgd++, addr = next, addr != end);
 }
 
-void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
+void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 		   struct vm_area_struct *vma, unsigned long floor,
 		   unsigned long ceiling, bool mm_wr_locked)
 {
-	MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
-
 	do {
 		unsigned long addr = vma->vm_start;
 		struct vm_area_struct *next;
@@ -375,7 +373,7 @@ void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
 		 * Note: USER_PGTABLES_CEILING may be passed as ceiling and may
 		 * be 0.  This will underflow and is okay.
 		 */
-		next = mas_find(&mas, ceiling - 1);
+		next = mas_find(mas, ceiling - 1);
 
 		/*
 		 * Hide vma from rmap and truncate_pagecache before freeing
@@ -396,7 +394,7 @@ void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
 			while (next && next->vm_start <= vma->vm_end + PMD_SIZE
 			       && !is_vm_hugetlb_page(next)) {
 				vma = next;
-				next = mas_find(&mas, ceiling - 1);
+				next = mas_find(mas, ceiling - 1);
 				if (mm_wr_locked)
 					vma_start_write(vma);
 				unlink_anon_vmas(vma);
@@ -1713,9 +1711,10 @@ 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 maple_tree *mt,
+void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 		struct vm_area_struct *vma, unsigned long start_addr,
-		unsigned long end_addr, bool mm_wr_locked)
+		unsigned long end_addr, unsigned long tree_end,
+		bool mm_wr_locked)
 {
 	struct mmu_notifier_range range;
 	struct zap_details details = {
@@ -1723,7 +1722,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 		/* Careful - we need to zap private pages too! */
 		.even_cows = true,
 	};
-	MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm,
 				start_addr, end_addr);
@@ -1731,7 +1729,7 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 	do {
 		unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
 				 mm_wr_locked);
-	} while ((vma = mas_find(&mas, end_addr - 1)) != NULL);
+	} while ((vma = mas_find(mas, tree_end - 1)) != NULL);
 	mmu_notifier_invalidate_range_end(&range);
 }
 

mm/mmap.c

@@ -76,10 +76,10 @@ int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
 static bool ignore_rlimit_data;
 core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
 
-static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
+static void unmap_region(struct mm_struct *mm, struct ma_state *mas,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
 		struct vm_area_struct *next, unsigned long start,
-		unsigned long end, bool mm_wr_locked);
+		unsigned long end, unsigned long tree_end, bool mm_wr_locked);
 
 static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
 {
@@ -2293,18 +2293,20 @@ static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas)
  *
  * Called with the mm semaphore held.
  */
-static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
+static void unmap_region(struct mm_struct *mm, struct ma_state *mas,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
-		struct vm_area_struct *next,
-		unsigned long start, unsigned long end, bool mm_wr_locked)
+		struct vm_area_struct *next, unsigned long start,
+		unsigned long end, unsigned long tree_end, bool mm_wr_locked)
 {
 	struct mmu_gather tlb;
+	unsigned long mt_start = mas->index;
 
 	lru_add_drain();
 	tlb_gather_mmu(&tlb, mm);
 	update_hiwater_rss(mm);
-	unmap_vmas(&tlb, mt, vma, start, end, mm_wr_locked);
-	free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
+	unmap_vmas(&tlb, mas, vma, start, end, tree_end, mm_wr_locked);
+	mas_set(mas, mt_start);
+	free_pgtables(&tlb, mas, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
 				 next ? next->vm_start : USER_PGTABLES_CEILING,
 				 mm_wr_locked);
 	tlb_finish_mmu(&tlb);
@@ -2472,7 +2474,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
 				goto end_split_failed;
 		}
 		vma_start_write(next);
-		mas_set_range(&mas_detach, next->vm_start, next->vm_end - 1);
+		mas_set(&mas_detach, count);
 		error = mas_store_gfp(&mas_detach, next, GFP_KERNEL);
 		if (error)
 			goto munmap_gather_failed;
@@ -2511,17 +2513,17 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
 #if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
 	/* Make sure no VMAs are about to be lost. */
 	{
-		MA_STATE(test, &mt_detach, start, end - 1);
+		MA_STATE(test, &mt_detach, 0, 0);
 		struct vm_area_struct *vma_mas, *vma_test;
 		int test_count = 0;
 
 		vma_iter_set(vmi, start);
 		rcu_read_lock();
-		vma_test = mas_find(&test, end - 1);
+		vma_test = mas_find(&test, count - 1);
 		for_each_vma_range(*vmi, vma_mas, end) {
 			BUG_ON(vma_mas != vma_test);
 			test_count++;
-			vma_test = mas_next(&test, end - 1);
+			vma_test = mas_next(&test, count - 1);
 		}
 		rcu_read_unlock();
 		BUG_ON(count != test_count);
@@ -2542,9 +2544,11 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	 * We can free page tables without write-locking mmap_lock because VMAs
 	 * were isolated before we downgraded mmap_lock.
 	 */
-	unmap_region(mm, &mt_detach, vma, prev, next, start, end, !unlock);
+	mas_set(&mas_detach, 1);
+	unmap_region(mm, &mas_detach, vma, prev, next, start, end, count,
+		     !unlock);
 	/* Statistics and freeing VMAs */
-	mas_set(&mas_detach, start);
+	mas_set(&mas_detach, 0);
 	remove_mt(mm, &mas_detach);
 	validate_mm(mm);
 	if (unlock)
@@ -2864,9 +2868,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		fput(vma->vm_file);
 		vma->vm_file = NULL;
 
+		vma_iter_set(&vmi, vma->vm_end);
 		/* Undo any partial mapping done by a device driver. */
-		unmap_region(mm, &mm->mm_mt, vma, prev, next, vma->vm_start,
-			     vma->vm_end, true);
+		unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start,
+			     vma->vm_end, vma->vm_end, true);
 	}
 	if (file && (vm_flags & VM_SHARED))
 		mapping_unmap_writable(file->f_mapping);
@@ -3185,7 +3190,7 @@ void exit_mmap(struct mm_struct *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, &mm->mm_mt, vma, 0, ULONG_MAX, false);
+	unmap_vmas(&tlb, &mas, vma, 0, ULONG_MAX, ULONG_MAX, false);
 	mmap_read_unlock(mm);
 
 	/*
@@ -3195,7 +3200,8 @@ void exit_mmap(struct mm_struct *mm)
 	set_bit(MMF_OOM_SKIP, &mm->flags);
 	mmap_write_lock(mm);
 	mt_clear_in_rcu(&mm->mm_mt);
-	free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS,
+	mas_set(&mas, vma->vm_end);
+	free_pgtables(&tlb, &mas, vma, FIRST_USER_ADDRESS,
 		      USER_PGTABLES_CEILING, true);
 	tlb_finish_mmu(&tlb);
 
@@ -3204,6 +3210,7 @@ void exit_mmap(struct mm_struct *mm)
 	 * enabled, without holding any MM locks besides the unreachable
 	 * mmap_write_lock.
 	 */
+	mas_set(&mas, vma->vm_end);
 	do {
 		if (vma->vm_flags & VM_ACCOUNT)
 			nr_accounted += vma_pages(vma);