fork: use __mt_dup() to duplicate maple tree in dup_mmap()

In dup_mmap(), using __mt_dup() to duplicate the old maple tree and then
directly replacing the entries of VMAs in the new maple tree can result in
better performance.  __mt_dup() uses DFS pre-order to duplicate the maple
tree, so it is efficient.

The average time complexity of __mt_dup() is O(n), where n is the number
of VMAs.  The proof of the time complexity is provided in the commit log
that introduces __mt_dup().  After duplicating the maple tree, each
element is traversed and replaced (ignoring the cases of deletion, which
are rare).  Since it is only a replacement operation for each element,
this process is also O(n).

Analyzing the exact time complexity of the previous algorithm is
challenging because each insertion can involve appending to a node,
pushing data to adjacent nodes, or even splitting nodes.  The frequency of
each action is difficult to calculate.  The worst-case scenario for a
single insertion is when the tree undergoes splitting at every level.  If
we consider each insertion as the worst-case scenario, we can determine
that the upper bound of the time complexity is O(n*log(n)), although this
is a loose upper bound.  However, based on the test data, it appears that
the actual time complexity is likely to be O(n).

As the entire maple tree is duplicated using __mt_dup(), if dup_mmap()
fails, there will be a portion of VMAs that have not been duplicated in
the maple tree.  To handle this, we mark the failure point with
XA_ZERO_ENTRY.  In exit_mmap(), if this marker is encountered, stop
releasing VMAs that have not been duplicated after this point.

There is a "spawn" in byte-unixbench[1], which can be used to test the
performance of fork().  I modified it slightly to make it work with
different number of VMAs.

Below are the test results.  The first row shows the number of VMAs.  The
second and third rows show the number of fork() calls per ten seconds,
corresponding to next-20231006 and the this patchset, respectively.  The
test results were obtained with CPU binding to avoid scheduler load
balancing that could cause unstable results.  There are still some
fluctuations in the test results, but at least they are better than the
original performance.

21     121   221    421    821    1621   3221   6421   12821  25621  51221
112100 76261 54227  34035  20195  11112  6017   3161   1606   802    393
114558 83067 65008  45824  28751  16072  8922   4747   2436   1233   599
2.19%  8.92% 19.88% 34.64% 42.37% 44.64% 48.28% 50.17% 51.68% 53.74% 52.42%

[1] https://github.com/kdlucas/byte-unixbench/tree/master

Link: https://lkml.kernel.org/r/20231027033845.90608-11-zhangpeng.00@bytedance.com
Signed-off-by: Peng Zhang <zhangpeng.00@bytedance.com>
Suggested-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Mike Christie <michael.christie@oracle.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 52 insertions, 26 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 418d26608ece..64cd1ee4aacc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -994,6 +994,17 @@ static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi,
 	return mas_expected_entries(&vmi->mas, count);
 }
 
+static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
+			unsigned long start, unsigned long end, gfp_t gfp)
+{
+	__mas_set_range(&vmi->mas, start, end - 1);
+	mas_store_gfp(&vmi->mas, NULL, gfp);
+	if (unlikely(mas_is_err(&vmi->mas)))
+		return -ENOMEM;
+
+	return 0;
+}
+
 /* Free any unused preallocations */
 static inline void vma_iter_free(struct vma_iterator *vmi)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 10917c3e1f03..93924392a5c3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -650,7 +650,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	int retval;
 	unsigned long charge = 0;
 	LIST_HEAD(uf);
-	VMA_ITERATOR(old_vmi, oldmm, 0);
 	VMA_ITERATOR(vmi, mm, 0);
 
 	uprobe_start_dup_mmap();
@@ -678,16 +677,22 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		goto out;
 	khugepaged_fork(mm, oldmm);
 
-	retval = vma_iter_bulk_alloc(&vmi, oldmm->map_count);
-	if (retval)
+	/* Use __mt_dup() to efficiently build an identical maple tree. */
+	retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
+	if (unlikely(retval))
 		goto out;
 
 	mt_clear_in_rcu(vmi.mas.tree);
-	for_each_vma(old_vmi, mpnt) {
+	for_each_vma(vmi, mpnt) {
 		struct file *file;
 
 		vma_start_write(mpnt);
 		if (mpnt->vm_flags & VM_DONTCOPY) {
+			retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start,
+						    mpnt->vm_end, GFP_KERNEL);
+			if (retval)
+				goto loop_out;
+
 			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
 			continue;
 		}
@@ -749,9 +754,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		if (is_vm_hugetlb_page(tmp))
 			hugetlb_dup_vma_private(tmp);
 
-		/* Link the vma into the MT */
-		if (vma_iter_bulk_store(&vmi, tmp))
-			goto fail_nomem_vmi_store;
+		/*
+		 * Link the vma into the MT. After using __mt_dup(), memory
+		 * allocation is not necessary here, so it cannot fail.
+		 */
+		vma_iter_bulk_store(&vmi, tmp);
 
 		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
@@ -760,15 +767,28 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
 
-		if (retval)
+		if (retval) {
+			mpnt = vma_next(&vmi);
 			goto loop_out;
+		}
 	}
 	/* a new mm has just been created */
 	retval = arch_dup_mmap(oldmm, mm);
 loop_out:
 	vma_iter_free(&vmi);
-	if (!retval)
+	if (!retval) {
 		mt_set_in_rcu(vmi.mas.tree);
+	} else if (mpnt) {
+		/*
+		 * The entire maple tree has already been duplicated. If the
+		 * mmap duplication fails, mark the failure point with
+		 * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered,
+		 * stop releasing VMAs that have not been duplicated after this
+		 * point.
+		 */
+		mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
+		mas_store(&vmi.mas, XA_ZERO_ENTRY);
+	}
 out:
 	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
@@ -778,8 +798,6 @@ fail_uprobe_end:
 	uprobe_end_dup_mmap();
 	return retval;
 
-fail_nomem_vmi_store:
-	unlink_anon_vmas(tmp);
 fail_nomem_anon_vma_fork:
 	mpol_put(vma_policy(tmp));
 fail_nomem_policy:
diff --git a/mm/internal.h b/mm/internal.h
index b61034bd50f5..89a5a794d68f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1154,17 +1154,6 @@ static inline void vma_iter_clear(struct vma_iterator *vmi)
 	mas_store_prealloc(&vmi->mas, NULL);
 }
 
-static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
-			unsigned long start, unsigned long end, gfp_t gfp)
-{
-	__mas_set_range(&vmi->mas, start, end - 1);
-	mas_store_gfp(&vmi->mas, NULL, gfp);
-	if (unlikely(mas_is_err(&vmi->mas)))
-		return -ENOMEM;
-
-	return 0;
-}
-
 static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi)
 {
 	return mas_walk(&vmi->mas);
diff --git a/mm/memory.c b/mm/memory.c
index 5c757fba8858..a7025ed5c65b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -374,6 +374,8 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 		 * be 0.  This will underflow and is okay.
 		 */
 		next = mas_find(mas, ceiling - 1);
+		if (unlikely(xa_is_zero(next)))
+			next = NULL;
 
 		/*
 		 * Hide vma from rmap and truncate_pagecache before freeing
@@ -395,6 +397,8 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 			       && !is_vm_hugetlb_page(next)) {
 				vma = next;
 				next = mas_find(mas, ceiling - 1);
+				if (unlikely(xa_is_zero(next)))
+					next = NULL;
 				if (mm_wr_locked)
 					vma_start_write(vma);
 				unlink_anon_vmas(vma);
@@ -1744,7 +1748,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 		unmap_single_vma(tlb, vma, start, end, &details,
 				 mm_wr_locked);
 		hugetlb_zap_end(vma, &details);
-	} while ((vma = mas_find(mas, tree_end - 1)) != NULL);
+		vma = mas_find(mas, tree_end - 1);
+	} while (vma && likely(!xa_is_zero(vma)));
 	mmu_notifier_invalidate_range_end(&range);
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 1971bfffcc03..4f1cb814586d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3294,10 +3294,11 @@ void exit_mmap(struct mm_struct *mm)
 	arch_exit_mmap(mm);
 
 	vma = mas_find(&mas, ULONG_MAX);
-	if (!vma) {
+	if (!vma || unlikely(xa_is_zero(vma))) {
 		/* Can happen if dup_mmap() received an OOM */
 		mmap_read_unlock(mm);
-		return;
+		mmap_write_lock(mm);
+		goto destroy;
 	}
 
 	lru_add_drain();
@@ -3332,11 +3333,13 @@ void exit_mmap(struct mm_struct *mm)
 		remove_vma(vma, true);
 		count++;
 		cond_resched();
-	} while ((vma = mas_find(&mas, ULONG_MAX)) != NULL);
+		vma = mas_find(&mas, ULONG_MAX);
+	} while (vma && likely(!xa_is_zero(vma)));
 
 	BUG_ON(count != mm->map_count);
 
 	trace_exit_mmap(mm);
+destroy:
 	__mt_destroy(&mm->mm_mt);
 	mmap_write_unlock(mm);
 	vm_unacct_memory(nr_accounted);