The quilt patch titled
Subject: mm: introduce __vm_flags_mod and use it in untrack_pfn
has been removed from the -mm tree. Its filename was
mm-introduce-__vm_flags_mod-and-use-it-in-untrack_pfn.patch
This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Subject: mm: introduce __vm_flags_mod and use it in untrack_pfn
Date: Thu, 26 Jan 2023 11:37:51 -0800
There are scenarios when vm_flags can be modified without exclusive
mmap_lock, such as:
- after VMA was isolated and mmap_lock was downgraded or dropped
- in exit_mmap when there are no other mm users and locking is unnecessary
Introduce __vm_flags_mod to avoid assertions when the caller takes
responsibility for the required locking.
Pass a hint to untrack_pfn to conditionally use __vm_flags_mod for
flags modification to avoid assertion.
Link: https://lkml.kernel.org/r/20230126193752.297968-7-surenb@xxxxxxxxxx
Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Acked-by: Mike Rapoport (IBM) <rppt@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Arjun Roy <arjunroy@xxxxxxxxxx>
Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Eric Dumazet <edumazet@xxxxxxxxxx>
Cc: Greg Thelen <gthelen@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Jann Horn <jannh@xxxxxxxxxx>
Cc: Joel Fernandes <joelaf@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Kent Overstreet <kent.overstreet@xxxxxxxxx>
Cc: Laurent Dufour <ldufour@xxxxxxxxxxxxx>
Cc: Liam R. Howlett <Liam.Howlett@xxxxxxxxxx>
Cc: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxx>
Cc: Peter Oskolkov <posk@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Punit Agrawal <punit.agrawal@xxxxxxxxxxxxx>
Cc: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Cc: Sebastian Reichel <sebastian.reichel@xxxxxxxxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Soheil Hassas Yeganeh <soheil@xxxxxxxxxx>
Cc: Song Liu <songliubraving@xxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/x86/mm/pat/memtype.c | 10 +++++++---
include/linux/mm.h | 14 ++++++++++++--
include/linux/pgtable.h | 5 +++--
mm/memory.c | 13 +++++++------
mm/memremap.c | 4 ++--
mm/mmap.c | 16 ++++++++++------
6 files changed, 41 insertions(+), 21 deletions(-)
--- a/arch/x86/mm/pat/memtype.c~mm-introduce-__vm_flags_mod-and-use-it-in-untrack_pfn
+++ a/arch/x86/mm/pat/memtype.c
@@ -1046,7 +1046,7 @@ void track_pfn_insert(struct vm_area_str
* can be for the entire vma (in which case pfn, size are zero).
*/
void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
- unsigned long size)
+ unsigned long size, bool mm_wr_locked)
{
resource_size_t paddr;
unsigned long prot;
@@ -1065,8 +1065,12 @@ void untrack_pfn(struct vm_area_struct *
size = vma->vm_end - vma->vm_start;
}
free_pfn_range(paddr, size);
- if (vma)
- vm_flags_clear(vma, VM_PAT);
+ if (vma) {
+ if (mm_wr_locked)
+ vm_flags_clear(vma, VM_PAT);
+ else
+ __vm_flags_mod(vma, 0, VM_PAT);
+ }
}
/*
--- a/include/linux/mm.h~mm-introduce-__vm_flags_mod-and-use-it-in-untrack_pfn
+++ a/include/linux/mm.h
@@ -657,6 +657,16 @@ static inline void vm_flags_clear(struct
}
/*
+ * Use only if VMA is not part of the VMA tree or has no other users and
+ * therefore needs no locking.
+ */
+static inline void __vm_flags_mod(struct vm_area_struct *vma,
+ vm_flags_t set, vm_flags_t clear)
+{
+ vm_flags_init(vma, (vma->vm_flags | set) & ~clear);
+}
+
+/*
* Use only when the order of set/clear operations is unimportant, otherwise
* use vm_flags_{set|clear} explicitly.
*/
@@ -664,7 +674,7 @@ static inline void vm_flags_mod(struct v
vm_flags_t set, vm_flags_t clear)
{
mmap_assert_write_locked(vma->vm_mm);
- vm_flags_init(vma, (vma->vm_flags | set) & ~clear);
+ __vm_flags_mod(vma, set, clear);
}
static inline void vma_set_anonymous(struct vm_area_struct *vma)
@@ -2085,7 +2095,7 @@ static inline void zap_vma_pages(struct
}
void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
struct vm_area_struct *start_vma, unsigned long start,
- unsigned long end);
+ unsigned long end, bool mm_wr_locked);
struct mmu_notifier_range;
--- a/include/linux/pgtable.h~mm-introduce-__vm_flags_mod-and-use-it-in-untrack_pfn
+++ a/include/linux/pgtable.h
@@ -1185,7 +1185,8 @@ static inline int track_pfn_copy(struct
* can be for the entire vma (in which case pfn, size are zero).
*/
static inline void untrack_pfn(struct vm_area_struct *vma,
- unsigned long pfn, unsigned long size)
+ unsigned long pfn, unsigned long size,
+ bool mm_wr_locked)
{
}
@@ -1203,7 +1204,7 @@ extern void track_pfn_insert(struct vm_a
pfn_t pfn);
extern int track_pfn_copy(struct vm_area_struct *vma);
extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
- unsigned long size);
+ unsigned long size, bool mm_wr_locked);
extern void untrack_pfn_moved(struct vm_area_struct *vma);
#endif
--- a/mm/memory.c~mm-introduce-__vm_flags_mod-and-use-it-in-untrack_pfn
+++ a/mm/memory.c
@@ -1613,7 +1613,7 @@ void unmap_page_range(struct mmu_gather
static void unmap_single_vma(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr,
- struct zap_details *details)
+ struct zap_details *details, bool mm_wr_locked)
{
unsigned long start = max(vma->vm_start, start_addr);
unsigned long end;
@@ -1628,7 +1628,7 @@ static void unmap_single_vma(struct mmu_
uprobe_munmap(vma, start, end);
if (unlikely(vma->vm_flags & VM_PFNMAP))
- untrack_pfn(vma, 0, 0);
+ untrack_pfn(vma, 0, 0, mm_wr_locked);
if (start != end) {
if (unlikely(is_vm_hugetlb_page(vma))) {
@@ -1675,7 +1675,7 @@ static void unmap_single_vma(struct mmu_
*/
void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
struct vm_area_struct *vma, unsigned long start_addr,
- unsigned long end_addr)
+ unsigned long end_addr, bool mm_wr_locked)
{
struct mmu_notifier_range range;
struct zap_details details = {
@@ -1689,7 +1689,8 @@ void unmap_vmas(struct mmu_gather *tlb,
start_addr, end_addr);
mmu_notifier_invalidate_range_start(&range);
do {
- unmap_single_vma(tlb, vma, start_addr, end_addr, &details);
+ unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
+ mm_wr_locked);
} while ((vma = mas_find(&mas, end_addr - 1)) != NULL);
mmu_notifier_invalidate_range_end(&range);
}
@@ -1723,7 +1724,7 @@ void zap_page_range_single(struct vm_are
* unmap 'address-end' not 'range.start-range.end' as range
* could have been expanded for hugetlb pmd sharing.
*/
- unmap_single_vma(&tlb, vma, address, end, details);
+ unmap_single_vma(&tlb, vma, address, end, details, false);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
}
@@ -2492,7 +2493,7 @@ int remap_pfn_range(struct vm_area_struc
err = remap_pfn_range_notrack(vma, addr, pfn, size, prot);
if (err)
- untrack_pfn(vma, pfn, PAGE_ALIGN(size));
+ untrack_pfn(vma, pfn, PAGE_ALIGN(size), true);
return err;
}
EXPORT_SYMBOL(remap_pfn_range);
--- a/mm/memremap.c~mm-introduce-__vm_flags_mod-and-use-it-in-untrack_pfn
+++ a/mm/memremap.c
@@ -129,7 +129,7 @@ static void pageunmap_range(struct dev_p
}
mem_hotplug_done();
- untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
+ untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
pgmap_array_delete(range);
}
@@ -276,7 +276,7 @@ err_add_memory:
if (!is_private)
kasan_remove_zero_shadow(__va(range->start), range_len(range));
err_kasan:
- untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
+ untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
err_pfn_remap:
pgmap_array_delete(range);
return error;
--- a/mm/mmap.c~mm-introduce-__vm_flags_mod-and-use-it-in-untrack_pfn
+++ a/mm/mmap.c
@@ -78,7 +78,7 @@ core_param(ignore_rlimit_data, ignore_rl
static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
struct vm_area_struct *vma, struct vm_area_struct *prev,
struct vm_area_struct *next, unsigned long start,
- unsigned long end);
+ unsigned long end, bool mm_wr_locked);
static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
{
@@ -2133,14 +2133,14 @@ static inline void remove_mt(struct mm_s
static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
struct vm_area_struct *vma, struct vm_area_struct *prev,
struct vm_area_struct *next,
- unsigned long start, unsigned long end)
+ unsigned long start, unsigned long end, bool mm_wr_locked)
{
struct mmu_gather tlb;
lru_add_drain();
tlb_gather_mmu(&tlb, mm);
update_hiwater_rss(mm);
- unmap_vmas(&tlb, mt, vma, start, end);
+ unmap_vmas(&tlb, mt, vma, start, end, mm_wr_locked);
free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
next ? next->vm_start : USER_PGTABLES_CEILING);
tlb_finish_mmu(&tlb);
@@ -2388,7 +2388,11 @@ do_vmi_align_munmap(struct vma_iterator
mmap_write_downgrade(mm);
}
- unmap_region(mm, &mt_detach, vma, prev, next, start, end);
+ /*
+ * 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, !downgrade);
/* Statistics and freeing VMAs */
mas_set(&mas_detach, start);
remove_mt(mm, &mas_detach);
@@ -2701,7 +2705,7 @@ unmap_and_free_vma:
/* Undo any partial mapping done by a device driver. */
unmap_region(mm, &mm->mm_mt, 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);
@@ -3029,7 +3033,7 @@ 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);
+ unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX, false);
mmap_read_unlock(mm);
/*
_
Patches currently in -mm which might be from surenb@xxxxxxxxxx are
