[RFC PATCH 08/19] mm: hugetlb: Refactor restore_reserve_on_error

From: Ackerley Tng
Date: Tue Jun 06 2023 - 15:05:29 EST


Refactor restore_reserve_on_error to allow resv_map to be passed
in. vma_resv_map() assumes the use of hugetlbfs in the way it
retrieves the resv_map from the vma and inode.

Introduce restore_reserve_on_error_vma() which retains original
functionality to simplify refactoring for now.

Signed-off-by: Ackerley Tng <ackerleytng@xxxxxxxxxx>
---
fs/hugetlbfs/inode.c | 2 +-
include/linux/hugetlb.h | 6 ++++--
mm/hugetlb.c | 37 +++++++++++++++++++++----------------
3 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 0fc49b6252e4..44e6ee9a856d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -868,7 +868,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
__folio_mark_uptodate(folio);
error = hugetlb_add_to_page_cache(folio, mapping, index);
if (unlikely(error)) {
- restore_reserve_on_error(h, &pseudo_vma, addr, folio);
+ restore_reserve_on_error_vma(h, &pseudo_vma, addr, folio);
folio_put(folio);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
goto out;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 7d49048c5a2a..02a2766d89a4 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -760,8 +760,10 @@ int hugetlb_filemap_add_folio(struct address_space *mapping, struct hstate *h,
struct folio *folio, pgoff_t idx);
int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,
pgoff_t idx);
-void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
- unsigned long address, struct folio *folio);
+void restore_reserve_on_error(struct resv_map *resv, pgoff_t resv_index,
+ bool may_share, struct folio *folio);
+void restore_reserve_on_error_vma(struct hstate *h, struct vm_area_struct *vma,
+ unsigned long address, struct folio *folio);

/* arch callback */
int __init __alloc_bootmem_huge_page(struct hstate *h, int nid);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d943f83d15a9..4675f9efeba4 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2805,15 +2805,10 @@ static long resv_map_del_reservation(struct resv_map *resv, pgoff_t resv_index,
*
* In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio.
*/
-void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
- unsigned long address, struct folio *folio)
+void restore_reserve_on_error(struct resv_map *resv, pgoff_t resv_index,
+ bool may_share, struct folio *folio)
{
- long rc;
- struct resv_map *resv = vma_resv_map(vma);
- pgoff_t resv_index = vma_hugecache_offset(h, vma, address);
- bool may_share = vma->vm_flags & VM_MAYSHARE;
-
- rc = resv_map_needs_reservation(resv, resv_index, may_share);
+ long rc = resv_map_needs_reservation(resv, resv_index, may_share);

if (folio_test_hugetlb_restore_reserve(folio)) {
if (unlikely(rc < 0))
@@ -2865,7 +2860,7 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
* For shared mappings, no entry in the map indicates
* no reservation. We are done.
*/
- if (!(vma->vm_flags & VM_MAYSHARE))
+ if (!may_share)
/*
* For private mappings, no entry indicates
* a reservation is present. Since we can
@@ -2883,6 +2878,16 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
}
}

+void restore_reserve_on_error_vma(struct hstate *h, struct vm_area_struct *vma,
+ unsigned long address, struct folio *folio)
+{
+ struct resv_map *resv = vma_resv_map(vma);
+ pgoff_t resv_index = vma_hugecache_offset(h, vma, address);
+ bool may_share = vma->vm_flags & VM_MAYSHARE;
+
+ restore_reserve_on_error(resv, resv_index, may_share, folio);
+}
+
/*
* alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve
* the old one
@@ -5109,8 +5114,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
entry = huge_ptep_get(src_pte);
if (!pte_same(src_pte_old, entry)) {
- restore_reserve_on_error(h, dst_vma, addr,
- new_folio);
+ restore_reserve_on_error_vma(h, dst_vma, addr,
+ new_folio);
folio_put(new_folio);
/* huge_ptep of dst_pte won't change as in child */
goto again;
@@ -5642,7 +5647,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
* unshare)
*/
if (new_folio != page_folio(old_page))
- restore_reserve_on_error(h, vma, haddr, new_folio);
+ restore_reserve_on_error_vma(h, vma, haddr, new_folio);
folio_put(new_folio);
out_release_old:
put_page(old_page);
@@ -5860,7 +5865,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
* to the page cache. So it's safe to call
* restore_reserve_on_error() here.
*/
- restore_reserve_on_error(h, vma, haddr, folio);
+ restore_reserve_on_error_vma(h, vma, haddr, folio);
folio_put(folio);
goto out;
}
@@ -5965,7 +5970,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
spin_unlock(ptl);
backout_unlocked:
if (new_folio && !new_pagecache_folio)
- restore_reserve_on_error(h, vma, haddr, folio);
+ restore_reserve_on_error_vma(h, vma, haddr, folio);

folio_unlock(folio);
folio_put(folio);
@@ -6232,7 +6237,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
/* Free the allocated folio which may have
* consumed a reservation.
*/
- restore_reserve_on_error(h, dst_vma, dst_addr, folio);
+ restore_reserve_on_error_vma(h, dst_vma, dst_addr, folio);
folio_put(folio);

/* Allocate a temporary folio to hold the copied
@@ -6361,7 +6366,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
folio_unlock(folio);
out_release_nounlock:
if (!folio_in_pagecache)
- restore_reserve_on_error(h, dst_vma, dst_addr, folio);
+ restore_reserve_on_error_vma(h, dst_vma, dst_addr, folio);
folio_put(folio);
goto out;
}
--
2.41.0.rc0.172.g3f132b7071-goog