From: Suren Baghdasaryan <surenb@google.com>
To: akpm@linux-foundation.org
Cc: michel@lespinasse.org, jglisse@google.com, mhocko@suse.com,
vbabka@suse.cz, hannes@cmpxchg.org, mgorman@techsingularity.net,
dave@stgolabs.net, willy@infradead.org, liam.howlett@oracle.com,
peterz@infradead.org, ldufour@linux.ibm.com, paulmck@kernel.org,
mingo@redhat.com, will@kernel.org, luto@kernel.org,
songliubraving@fb.com, peterx@redhat.com, david@redhat.com,
dhowells@redhat.com, hughd@google.com, bigeasy@linutronix.de,
kent.overstreet@linux.dev, punit.agrawal@bytedance.com,
lstoakes@gmail.com, peterjung1337@gmail.com,
rientjes@google.com, axelrasmussen@google.com,
joelaf@google.com, minchan@google.com, rppt@kernel.org,
jannh@google.com, shakeelb@google.com, tatashin@google.com,
edumazet@google.com, gthelen@google.com, gurua@google.com,
arjunroy@google.com, soheil@google.com, leewalsh@google.com,
posk@google.com, linux-mm@kvack.org,
linux-arm-kernel@lists.infradead.org,
linuxppc-dev@lists.ozlabs.org, x86@kernel.org,
linux-kernel@vger.kernel.org, kernel-team@android.com,
surenb@google.com
Subject: [PATCH v4 6/7] mm: introduce __vm_flags_mod and use it in untrack_pfn
Date: Thu, 26 Jan 2023 11:37:51 -0800 [thread overview]
Message-ID: <20230126193752.297968-7-surenb@google.com> (raw)
In-Reply-To: <20230126193752.297968-1-surenb@google.com>
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.
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
---
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(-)
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 6ca51b1aa5d9..691bf8934b6f 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -1046,7 +1046,7 @@ void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
* 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 *vma, unsigned long pfn,
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);
+ }
}
/*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3c7fc3ecaece..a00fdeb4492d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -656,6 +656,16 @@ static inline void vm_flags_clear(struct vm_area_struct *vma,
ACCESS_PRIVATE(vma, __vm_flags) &= ~flags;
}
+/*
+ * 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 vm_area_struct *vma,
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)
@@ -2102,7 +2112,7 @@ static inline void zap_vma_pages(struct vm_area_struct *vma)
}
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;
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 5fd45454c073..c63cd44777ec 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1185,7 +1185,8 @@ static inline int track_pfn_copy(struct vm_area_struct *vma)
* 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_area_struct *vma, pgprot_t *prot,
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
diff --git a/mm/memory.c b/mm/memory.c
index a6316cda0e87..7a04a1130ec1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1613,7 +1613,7 @@ void unmap_page_range(struct mmu_gather *tlb,
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_gather *tlb,
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_gather *tlb,
*/
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, struct maple_tree *mt,
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_area_struct *vma, unsigned long address,
* 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_struct *vma, unsigned long addr,
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);
diff --git a/mm/memremap.c b/mm/memremap.c
index 08cbf54fe037..2f88f43d4a01 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -129,7 +129,7 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
}
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 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
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;
diff --git a/mm/mmap.c b/mm/mmap.c
index 3d9b14d5f933..429e42c8fccc 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -78,7 +78,7 @@ core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
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)
{
@@ -2136,14 +2136,14 @@ static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas)
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);
@@ -2391,7 +2391,11 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
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);
@@ -2704,7 +2708,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
/* 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);
@@ -3031,7 +3035,7 @@ 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);
/*
--
2.39.1
next prev parent reply other threads:[~2023-01-26 19:45 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-26 19:37 [PATCH v4 0/7] introduce vm_flags modifier functions Suren Baghdasaryan
2023-01-26 19:37 ` [PATCH v4 1/7] kernel/fork: convert vma assignment to a memcpy Suren Baghdasaryan
2023-01-26 19:40 ` Mike Rapoport
2023-01-26 19:37 ` [PATCH v4 2/7] mm: introduce vma->vm_flags wrapper functions Suren Baghdasaryan
2023-01-26 19:42 ` Mike Rapoport
2023-02-08 1:48 ` Hyeonggon Yoo
2023-01-26 19:37 ` [PATCH v4 3/7] mm: replace VM_LOCKED_CLEAR_MASK with VM_LOCKED_MASK Suren Baghdasaryan
2023-01-27 17:45 ` Davidlohr Bueso
2023-01-27 20:56 ` Suren Baghdasaryan
2023-01-26 19:37 ` [PATCH v4 4/7] mm: replace vma->vm_flags direct modifications with modifier calls Suren Baghdasaryan
2023-01-27 14:23 ` Liam R. Howlett
2023-01-31 8:32 ` Hyeonggon Yoo
2023-01-31 18:54 ` Suren Baghdasaryan
2023-01-31 20:53 ` Andrew Morton
2023-01-31 21:08 ` Suren Baghdasaryan
2023-01-31 23:12 ` Andrew Morton
2023-02-01 0:03 ` Suren Baghdasaryan
2023-02-01 12:23 ` Hyeonggon Yoo
2023-01-26 19:37 ` [PATCH v4 5/7] mm: replace vma->vm_flags indirect modification in ksm_madvise Suren Baghdasaryan
2023-01-26 22:45 ` Michael Ellerman
2023-02-08 1:54 ` Hyeonggon Yoo
2023-01-26 19:37 ` Suren Baghdasaryan [this message]
2023-01-26 19:44 ` [PATCH v4 6/7] mm: introduce __vm_flags_mod and use it in untrack_pfn Mike Rapoport
2023-01-26 19:37 ` [PATCH v4 7/7] mm: export dump_mm() Suren Baghdasaryan
2023-03-14 20:11 ` [PATCH v4 0/7] introduce vm_flags modifier functions Alex Williamson
2023-03-17 19:08 ` Suren Baghdasaryan
2023-03-17 22:40 ` Alex Williamson
2023-03-17 23:04 ` Suren Baghdasaryan
2023-03-22 13:48 ` Jason Gunthorpe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230126193752.297968-7-surenb@google.com \
--to=surenb@google.com \
--cc=akpm@linux-foundation.org \
--cc=arjunroy@google.com \
--cc=axelrasmussen@google.com \
--cc=bigeasy@linutronix.de \
--cc=dave@stgolabs.net \
--cc=david@redhat.com \
--cc=dhowells@redhat.com \
--cc=edumazet@google.com \
--cc=gthelen@google.com \
--cc=gurua@google.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jannh@google.com \
--cc=jglisse@google.com \
--cc=joelaf@google.com \
--cc=kent.overstreet@linux.dev \
--cc=kernel-team@android.com \
--cc=ldufour@linux.ibm.com \
--cc=leewalsh@google.com \
--cc=liam.howlett@oracle.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=lstoakes@gmail.com \
--cc=luto@kernel.org \
--cc=mgorman@techsingularity.net \
--cc=mhocko@suse.com \
--cc=michel@lespinasse.org \
--cc=minchan@google.com \
--cc=mingo@redhat.com \
--cc=paulmck@kernel.org \
--cc=peterjung1337@gmail.com \
--cc=peterx@redhat.com \
--cc=peterz@infradead.org \
--cc=posk@google.com \
--cc=punit.agrawal@bytedance.com \
--cc=rientjes@google.com \
--cc=rppt@kernel.org \
--cc=shakeelb@google.com \
--cc=soheil@google.com \
--cc=songliubraving@fb.com \
--cc=tatashin@google.com \
--cc=vbabka@suse.cz \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).