+ mm-mmap-free-vm_area_struct-without-call_rcu-in-exit_mmap.patch added to mm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: mm/mmap: free vm_area_struct without call_rcu in exit_mmap
has been added to the -mm mm-unstable branch.  Its filename is
     mm-mmap-free-vm_area_struct-without-call_rcu-in-exit_mmap.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-mmap-free-vm_area_struct-without-call_rcu-in-exit_mmap.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Suren Baghdasaryan <surenb@google.com>
Subject: mm/mmap: free vm_area_struct without call_rcu in exit_mmap
Date: Mon, 27 Feb 2023 09:36:31 -0800

call_rcu() can take a long time when callback offloading is enabled.  Its
use in the vm_area_free can cause regressions in the exit path when
multiple VMAs are being freed.

Because exit_mmap() is called only after the last mm user drops its
refcount, the page fault handlers can't be racing with it.  Any other
possible user like oom-reaper or process_mrelease are already synchronized
using mmap_lock.  Therefore exit_mmap() can free VMAs directly, without
the use of call_rcu().

Expose __vm_area_free() and use it from exit_mmap() to avoid possible
call_rcu() floods and performance regressions caused by it.

Link: https://lkml.kernel.org/r/20230227173632.3292573-33-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---


--- a/include/linux/mm.h~mm-mmap-free-vm_area_struct-without-call_rcu-in-exit_mmap
+++ a/include/linux/mm.h
@@ -256,6 +256,8 @@ void setup_initial_init_mm(void *start_c
 struct vm_area_struct *vm_area_alloc(struct mm_struct *);
 struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
 void vm_area_free(struct vm_area_struct *);
+/* Use only if VMA has no other users */
+void __vm_area_free(struct vm_area_struct *vma);
 
 #ifndef CONFIG_MMU
 extern struct rb_root nommu_region_tree;
--- a/kernel/fork.c~mm-mmap-free-vm_area_struct-without-call_rcu-in-exit_mmap
+++ a/kernel/fork.c
@@ -480,7 +480,7 @@ struct vm_area_struct *vm_area_dup(struc
 	return new;
 }
 
-static void __vm_area_free(struct vm_area_struct *vma)
+void __vm_area_free(struct vm_area_struct *vma)
 {
 	free_anon_vma_name(vma);
 	kmem_cache_free(vm_area_cachep, vma);
--- a/mm/mmap.c~mm-mmap-free-vm_area_struct-without-call_rcu-in-exit_mmap
+++ a/mm/mmap.c
@@ -133,7 +133,7 @@ void unlink_file_vma(struct vm_area_stru
 /*
  * Close a vm structure and free it.
  */
-static void remove_vma(struct vm_area_struct *vma)
+static void remove_vma(struct vm_area_struct *vma, bool unreachable)
 {
 	might_sleep();
 	if (vma->vm_ops && vma->vm_ops->close)
@@ -141,7 +141,10 @@ static void remove_vma(struct vm_area_st
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	mpol_put(vma_policy(vma));
-	vm_area_free(vma);
+	if (unreachable)
+		__vm_area_free(vma);
+	else
+		vm_area_free(vma);
 }
 
 static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi,
@@ -2130,7 +2133,7 @@ static inline void remove_mt(struct mm_s
 		if (vma->vm_flags & VM_ACCOUNT)
 			nr_accounted += nrpages;
 		vm_stat_account(mm, vma->vm_flags, -nrpages);
-		remove_vma(vma);
+		remove_vma(vma, false);
 	}
 	vm_unacct_memory(nr_accounted);
 	validate_mm(mm);
@@ -3070,7 +3073,7 @@ void exit_mmap(struct mm_struct *mm)
 	do {
 		if (vma->vm_flags & VM_ACCOUNT)
 			nr_accounted += vma_pages(vma);
-		remove_vma(vma);
+		remove_vma(vma, true);
 		count++;
 		cond_resched();
 	} while ((vma = mas_find(&mas, ULONG_MAX)) != NULL);
_

Patches currently in -mm which might be from surenb@google.com are

mm-introduce-config_per_vma_lock.patch
mm-move-mmap_lock-assert-function-definitions.patch
mm-add-per-vma-lock-and-helper-functions-to-control-it.patch
mm-mark-vma-as-being-written-when-changing-vm_flags.patch
mm-mmap-move-vma_prepare-before-vma_adjust_trans_huge.patch
mm-khugepaged-write-lock-vma-while-collapsing-a-huge-page.patch
mm-mmap-write-lock-vmas-in-vma_prepare-before-modifying-them.patch
mm-mremap-write-lock-vma-while-remapping-it-to-a-new-address-range.patch
mm-write-lock-vmas-before-removing-them-from-vma-tree.patch
mm-conditionally-write-lock-vma-in-free_pgtables.patch
kernel-fork-assert-no-vma-readers-during-its-destruction.patch
mm-mmap-prevent-pagefault-handler-from-racing-with-mmu_notifier-registration.patch
mm-introduce-vma-detached-flag.patch
mm-introduce-lock_vma_under_rcu-to-be-used-from-arch-specific-code.patch
mm-fall-back-to-mmap_lock-if-vma-anon_vma-is-not-yet-set.patch
mm-add-fault_flag_vma_lock-flag.patch
mm-prevent-do_swap_page-from-handling-page-faults-under-vma-lock.patch
mm-prevent-userfaults-to-be-handled-under-per-vma-lock.patch
mm-introduce-per-vma-lock-statistics.patch
x86-mm-try-vma-lock-based-page-fault-handling-first.patch
arm64-mm-try-vma-lock-based-page-fault-handling-first.patch
mm-mmap-free-vm_area_struct-without-call_rcu-in-exit_mmap.patch
mm-separate-vma-lock-from-vm_area_struct.patch
per-vma-locks.patch