The patch titled
Subject: mm: set up vma iterator for vma_iter_prealloc() calls
has been added to the -mm mm-unstable branch. Its filename is
mm-set-up-vma-iterator-for-vma_iter_prealloc-calls.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-set-up-vma-iterator-for-vma_iter_prealloc-calls.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: "Liam R. Howlett" <Liam.Howlett@xxxxxxxxxx>
Subject: mm: set up vma iterator for vma_iter_prealloc() calls
Date: Mon, 12 Jun 2023 16:39:48 -0400
Set the correct limits for vma_iter_prealloc() calls so that the maple
tree can be smarter about how many nodes are needed.
Link: https://lkml.kernel.org/r/20230612203953.2093911-12-Liam.Howlett@xxxxxxxxxx
Signed-off-by: Liam R. Howlett <Liam.Howlett@xxxxxxxxxx>
Cc: Peng Zhang <zhangpeng.00@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/exec.c | 1
mm/internal.h | 18 ++++------
mm/mmap.c | 81 +++++++++++++++++++++++++++++-------------------
mm/nommu.c | 33 ++++++++-----------
4 files changed, 72 insertions(+), 61 deletions(-)
--- a/fs/exec.c~mm-set-up-vma-iterator-for-vma_iter_prealloc-calls
+++ a/fs/exec.c
@@ -697,6 +697,7 @@ static int shift_arg_pages(struct vm_are
if (vma != vma_next(&vmi))
return -EFAULT;
+ vma_iter_prev_range(&vmi);
/*
* cover the whole range: [new_start, old_end)
*/
--- a/mm/internal.h~mm-set-up-vma-iterator-for-vma_iter_prealloc-calls
+++ a/mm/internal.h
@@ -1041,23 +1041,21 @@ static inline void vma_iter_config(struc
/*
* VMA Iterator functions shared between nommu and mmap
*/
-static inline int vma_iter_prealloc(struct vma_iterator *vmi)
+static inline int vma_iter_prealloc(struct vma_iterator *vmi,
+ struct vm_area_struct *vma)
{
- return mas_preallocate(&vmi->mas, NULL, GFP_KERNEL);
+ return mas_preallocate(&vmi->mas, vma, GFP_KERNEL);
}
-static inline void vma_iter_clear(struct vma_iterator *vmi,
- unsigned long start, unsigned long end)
+static inline void vma_iter_clear(struct vma_iterator *vmi)
{
- mas_set_range(&vmi->mas, start, end - 1);
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)
{
- vmi->mas.index = start;
- vmi->mas.last = end - 1;
+ __mas_set_range(&vmi->mas, start, end - 1);
mas_store_gfp(&vmi->mas, NULL, gfp);
if (unlikely(mas_is_err(&vmi->mas)))
return -ENOMEM;
@@ -1094,8 +1092,7 @@ static inline void vma_iter_store(struct
((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
vma_iter_invalidate(vmi);
- vmi->mas.index = vma->vm_start;
- vmi->mas.last = vma->vm_end - 1;
+ __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1);
mas_store_prealloc(&vmi->mas, vma);
}
@@ -1106,8 +1103,7 @@ static inline int vma_iter_store_gfp(str
((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
vma_iter_invalidate(vmi);
- vmi->mas.index = vma->vm_start;
- vmi->mas.last = vma->vm_end - 1;
+ __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1);
mas_store_gfp(&vmi->mas, vma, gfp);
if (unlikely(mas_is_err(&vmi->mas)))
return -ENOMEM;
--- a/mm/mmap.c~mm-set-up-vma-iterator-for-vma_iter_prealloc-calls
+++ a/mm/mmap.c
@@ -408,7 +408,8 @@ static int vma_link(struct mm_struct *mm
VMA_ITERATOR(vmi, mm, 0);
struct address_space *mapping = NULL;
- if (vma_iter_prealloc(&vmi))
+ vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
+ if (vma_iter_prealloc(&vmi, vma))
return -ENOMEM;
if (vma->vm_file) {
@@ -661,19 +662,16 @@ int vma_expand(struct vma_iterator *vmi,
/* Only handles expanding */
VM_WARN_ON(vma->vm_start < start || vma->vm_end > end);
- if (vma_iter_prealloc(vmi))
+ /* Note: vma iterator must be pointing to 'start' */
+ vma_iter_config(vmi, start, end);
+ if (vma_iter_prealloc(vmi, vma))
goto nomem;
vma_prepare(&vp);
vma_adjust_trans_huge(vma, start, end, 0);
- /* VMA iterator points to previous, so set to start if necessary */
- if (vma_iter_addr(vmi) != start)
- vma_iter_set(vmi, start);
-
vma->vm_start = start;
vma->vm_end = end;
vma->vm_pgoff = pgoff;
- /* Note: mas must be pointing to the expanding VMA */
vma_iter_store(vmi, vma);
vma_complete(&vp, vmi, vma->vm_mm);
@@ -700,19 +698,19 @@ int vma_shrink(struct vma_iterator *vmi,
WARN_ON((vma->vm_start != start) && (vma->vm_end != end));
- if (vma_iter_prealloc(vmi))
+ if (vma->vm_start < start)
+ vma_iter_config(vmi, vma->vm_start, start);
+ else
+ vma_iter_config(vmi, end, vma->vm_end);
+
+ if (vma_iter_prealloc(vmi, NULL))
return -ENOMEM;
init_vma_prep(&vp, vma);
vma_prepare(&vp);
vma_adjust_trans_huge(vma, start, end, 0);
- if (vma->vm_start < start)
- vma_iter_clear(vmi, vma->vm_start, start);
-
- if (vma->vm_end > end)
- vma_iter_clear(vmi, end, vma->vm_end);
-
+ vma_iter_clear(vmi);
vma->vm_start = start;
vma->vm_end = end;
vma->vm_pgoff = pgoff;
@@ -988,7 +986,17 @@ struct vm_area_struct *vma_merge(struct
if (err)
return NULL;
- if (vma_iter_prealloc(vmi))
+ if (vma_start < vma->vm_start || vma_end > vma->vm_end)
+ vma_expanded = true;
+
+ if (vma_expanded) {
+ vma_iter_config(vmi, vma_start, vma_end);
+ } else {
+ vma_iter_config(vmi, adjust->vm_start + adj_start,
+ adjust->vm_end);
+ }
+
+ if (vma_iter_prealloc(vmi, vma))
return NULL;
init_multi_vma_prep(&vp, vma, adjust, remove, remove2);
@@ -997,8 +1005,6 @@ struct vm_area_struct *vma_merge(struct
vma_prepare(&vp);
vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start);
- if (vma_start < vma->vm_start || vma_end > vma->vm_end)
- vma_expanded = true;
vma->vm_start = vma_start;
vma->vm_end = vma_end;
@@ -1942,7 +1948,7 @@ int expand_upwards(struct vm_area_struct
struct vm_area_struct *next;
unsigned long gap_addr;
int error = 0;
- MA_STATE(mas, &mm->mm_mt, 0, 0);
+ MA_STATE(mas, &mm->mm_mt, vma->vm_start, address);
if (!(vma->vm_flags & VM_GROWSUP))
return -EFAULT;
@@ -1967,6 +1973,10 @@ int expand_upwards(struct vm_area_struct
/* Check that both stack segments have the same anon_vma? */
}
+ if (next)
+ mas_prev_range(&mas, address);
+
+ __mas_set_range(&mas, vma->vm_start, address - 1);
if (mas_preallocate(&mas, vma, GFP_KERNEL))
return -ENOMEM;
@@ -2010,7 +2020,6 @@ int expand_upwards(struct vm_area_struct
anon_vma_interval_tree_pre_update_vma(vma);
vma->vm_end = address;
/* Overwrite old entry in mtree. */
- mas_set_range(&mas, vma->vm_start, address - 1);
mas_store_prealloc(&mas, vma);
anon_vma_interval_tree_post_update_vma(vma);
spin_unlock(&mm->page_table_lock);
@@ -2049,6 +2058,10 @@ int expand_downwards(struct vm_area_stru
return -ENOMEM;
}
+ if (prev)
+ mas_next_range(&mas, vma->vm_start);
+
+ __mas_set_range(&mas, address, vma->vm_end - 1);
if (mas_preallocate(&mas, vma, GFP_KERNEL))
return -ENOMEM;
@@ -2093,7 +2106,6 @@ int expand_downwards(struct vm_area_stru
vma->vm_start = address;
vma->vm_pgoff -= grow;
/* Overwrite old entry in mtree. */
- mas_set_range(&mas, address, vma->vm_end - 1);
mas_store_prealloc(&mas, vma);
anon_vma_interval_tree_post_update_vma(vma);
spin_unlock(&mm->page_table_lock);
@@ -2252,10 +2264,6 @@ int __split_vma(struct vma_iterator *vmi
if (!new)
return -ENOMEM;
- err = -ENOMEM;
- if (vma_iter_prealloc(vmi))
- goto out_free_vma;
-
if (new_below) {
new->vm_end = addr;
} else {
@@ -2263,6 +2271,11 @@ int __split_vma(struct vma_iterator *vmi
new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
}
+ err = -ENOMEM;
+ vma_iter_config(vmi, new->vm_start, new->vm_end);
+ if (vma_iter_prealloc(vmi, new))
+ goto out_free_vma;
+
err = vma_dup_policy(vma, new);
if (err)
goto out_free_vmi;
@@ -2598,8 +2611,12 @@ unsigned long mmap_region(struct file *f
next = vma_next(&vmi);
prev = vma_prev(&vmi);
- if (vm_flags & VM_SPECIAL)
+ if (vm_flags & VM_SPECIAL) {
+ if (prev)
+ vma_iter_next_range(&vmi);
+
goto cannot_expand;
+ }
/* Attempt to expand an old mapping */
/* Check next */
@@ -2609,6 +2626,7 @@ unsigned long mmap_region(struct file *f
merge_end = next->vm_end;
vma = next;
vm_pgoff = next->vm_pgoff - pglen;
+
}
/* Check prev */
@@ -2620,9 +2638,10 @@ unsigned long mmap_region(struct file *f
merge_start = prev->vm_start;
vma = prev;
vm_pgoff = prev->vm_pgoff;
+ } else if (prev) {
+ vma_iter_next_range(&vmi);
}
-
/* Actually expand, if possible */
if (vma &&
!vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) {
@@ -2631,9 +2650,6 @@ unsigned long mmap_region(struct file *f
}
cannot_expand:
- if (prev)
- vma_iter_next_range(&vmi);
-
/*
* Determine the object being mapped and call the appropriate
* specific mapper. the address has already been validated, but
@@ -2719,7 +2735,7 @@ cannot_expand:
goto close_and_free_vma;
error = -ENOMEM;
- if (vma_iter_prealloc(&vmi))
+ if (vma_iter_prealloc(&vmi, vma))
goto close_and_free_vma;
if (vma->vm_file)
@@ -2992,7 +3008,8 @@ static int do_brk_flags(struct vma_itera
if (vma && vma->vm_end == addr && !vma_policy(vma) &&
can_vma_merge_after(vma, flags, NULL, NULL,
addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) {
- if (vma_iter_prealloc(vmi))
+ vma_iter_config(vmi, vma->vm_start, addr + len);
+ if (vma_iter_prealloc(vmi, vma))
goto unacct_fail;
init_vma_prep(&vp, vma);
@@ -3007,6 +3024,8 @@ static int do_brk_flags(struct vma_itera
goto out;
}
+ if (vma)
+ vma_iter_next_range(vmi);
/* create a vma struct for an anonymous mapping */
vma = vm_area_alloc(mm);
if (!vma)
--- a/mm/nommu.c~mm-set-up-vma-iterator-for-vma_iter_prealloc-calls
+++ a/mm/nommu.c
@@ -583,7 +583,8 @@ static int delete_vma_from_mm(struct vm_
{
VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_start);
- if (vma_iter_prealloc(&vmi)) {
+ vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
+ if (vma_iter_prealloc(&vmi, vma)) {
pr_warn("Allocation of vma tree for process %d failed\n",
current->pid);
return -ENOMEM;
@@ -591,7 +592,7 @@ static int delete_vma_from_mm(struct vm_
cleanup_vma_from_mm(vma);
/* remove from the MM's tree and list */
- vma_iter_clear(&vmi, vma->vm_start, vma->vm_end);
+ vma_iter_clear(&vmi);
return 0;
}
/*
@@ -1041,9 +1042,6 @@ unsigned long do_mmap(struct file *file,
if (!vma)
goto error_getting_vma;
- if (vma_iter_prealloc(&vmi))
- goto error_vma_iter_prealloc;
-
region->vm_usage = 1;
region->vm_flags = vm_flags;
region->vm_pgoff = pgoff;
@@ -1185,6 +1183,10 @@ unsigned long do_mmap(struct file *file,
share:
BUG_ON(!vma->vm_region);
+ vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
+ if (vma_iter_prealloc(&vmi, vma))
+ goto error_just_free;
+
setup_vma_to_mm(vma, current->mm);
current->mm->map_count++;
/* add the VMA to the tree */
@@ -1231,14 +1233,6 @@ error_getting_region:
len, current->pid);
show_free_areas(0, NULL);
return -ENOMEM;
-
-error_vma_iter_prealloc:
- kmem_cache_free(vm_region_jar, region);
- vm_area_free(vma);
- pr_warn("Allocation of vma tree for process %d failed\n", current->pid);
- show_free_areas(0, NULL);
- return -ENOMEM;
-
}
unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
@@ -1323,12 +1317,6 @@ int split_vma(struct vma_iterator *vmi,
if (!new)
goto err_vma_dup;
- if (vma_iter_prealloc(vmi)) {
- pr_warn("Allocation of vma tree for process %d failed\n",
- current->pid);
- goto err_vmi_preallocate;
- }
-
/* most fields are the same, copy all, and then fixup */
*region = *vma->vm_region;
new->vm_region = region;
@@ -1342,6 +1330,13 @@ int split_vma(struct vma_iterator *vmi,
region->vm_pgoff = new->vm_pgoff += npages;
}
+ vma_iter_config(vmi, new->vm_start, new->vm_end);
+ if (vma_iter_prealloc(vmi, vma)) {
+ pr_warn("Allocation of vma tree for process %d failed\n",
+ current->pid);
+ goto err_vmi_preallocate;
+ }
+
if (new->vm_ops && new->vm_ops->open)
new->vm_ops->open(new);
_
Patches currently in -mm which might be from Liam.Howlett@xxxxxxxxxx are
mm-mprotect-fix-do_mprotect_pkey-limit-check.patch
maple_tree-add-benchmarking-for-mas_for_each.patch
maple_tree-add-benchmarking-for-mas_prev.patch
mm-move-unmap_vmas-declaration-to-internal-header.patch
mm-change-do_vmi_align_munmap-side-tree-index.patch
mm-remove-prev-check-from-do_vmi_align_munmap.patch
maple_tree-introduce-__mas_set_range.patch
mm-remove-re-walk-from-mmap_region.patch
maple_tree-adjust-node-allocation-on-mas_rebalance.patch
maple_tree-re-introduce-entry-to-mas_preallocate-arguments.patch
mm-use-vma_iter_clear_gfp-in-nommu.patch
mm-set-up-vma-iterator-for-vma_iter_prealloc-calls.patch
maple_tree-move-mas_wr_end_piv-below-mas_wr_extend_null.patch
maple_tree-update-mas_preallocate-testing.patch
maple_tree-refine-mas_preallocate-node-calculations.patch
maple_tree-reduce-resets-during-store-setup.patch
mm-mmap-change-vma-iteration-order-in-do_vmi_align_munmap.patch
userfaultfd-fix-regression-in-userfaultfd_unmap_prep.patch
