| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1507543672-25821-5-git-send-email-ldufour@linux.vnet.ibm.com>
Date: Mon, 9 Oct 2017 12:07:36 +0200
From: Laurent Dufour <ldufour@...ux.vnet.ibm.com>
To: paulmck@...ux.vnet.ibm.com, peterz@...radead.org,
akpm@...ux-foundation.org, kirill@...temov.name,
ak@...ux.intel.com, mhocko@...nel.org, dave@...olabs.net,
jack@...e.cz, Matthew Wilcox <willy@...radead.org>,
benh@...nel.crashing.org, mpe@...erman.id.au, paulus@...ba.org,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, hpa@...or.com,
Will Deacon <will.deacon@....com>,
Sergey Senozhatsky <sergey.senozhatsky@...il.com>,
Andrea Arcangeli <aarcange@...hat.com>,
Alexei Starovoitov <alexei.starovoitov@...il.com>
Cc: linux-kernel@...r.kernel.org, linux-mm@...ck.org,
haren@...ux.vnet.ibm.com, khandual@...ux.vnet.ibm.com,
npiggin@...il.com, bsingharora@...il.com,
Tim Chen <tim.c.chen@...ux.intel.com>,
linuxppc-dev@...ts.ozlabs.org, x86@...nel.org
Subject: [PATCH v4 04/20] mm: VMA sequence count
From: Peter Zijlstra <peterz@...radead.org>
Wrap the VMA modifications (vma_adjust/unmap_page_range) with sequence
counts such that we can easily test if a VMA is changed.
The unmap_page_range() one allows us to make assumptions about
page-tables; when we find the seqcount hasn't changed we can assume
page-tables are still valid.
The flip side is that we cannot distinguish between a vma_adjust() and
the unmap_page_range() -- where with the former we could have
re-checked the vma bounds against the address.
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
[Port to 4.12 kernel]
[Build depends on __HAVE_ARCH_CALL_SPF]
[Introduce vm_write_* inline function depending on __HAVE_ARCH_CALL_SPF]
[Fix lock dependency between mapping->i_mmap_rwsem and vma->vm_sequence by
using vm_raw_write* functions]
Signed-off-by: Laurent Dufour <ldufour@...ux.vnet.ibm.com>
Fix locked by raw function
undo lockdep fix as raw services are now used
---
include/linux/mm.h | 41 +++++++++++++++++++++++++++++++++++++++++
include/linux/mm_types.h | 3 +++
mm/memory.c | 2 ++
mm/mmap.c | 40 +++++++++++++++++++++++++++++++++++++---
4 files changed, 83 insertions(+), 3 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index fb3477f7f742..aa06332fc01e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1349,6 +1349,47 @@ static inline int fixup_user_fault(struct task_struct *tsk,
}
#endif
+#ifdef __HAVE_ARCH_CALL_SPF
+static inline void vm_write_begin(struct vm_area_struct *vma)
+{
+ write_seqcount_begin(&vma->vm_sequence);
+}
+static inline void vm_write_begin_nested(struct vm_area_struct *vma,
+ int subclass)
+{
+ write_seqcount_begin_nested(&vma->vm_sequence, subclass);
+}
+static inline void vm_write_end(struct vm_area_struct *vma)
+{
+ write_seqcount_end(&vma->vm_sequence);
+}
+static inline void vm_raw_write_begin(struct vm_area_struct *vma)
+{
+ raw_write_seqcount_begin(&vma->vm_sequence);
+}
+static inline void vm_raw_write_end(struct vm_area_struct *vma)
+{
+ raw_write_seqcount_end(&vma->vm_sequence);
+}
+#else
+static inline void vm_write_begin(struct vm_area_struct *vma)
+{
+}
+static inline void vm_write_begin_nested(struct vm_area_struct *vma,
+ int subclass)
+{
+}
+static inline void vm_write_end(struct vm_area_struct *vma)
+{
+}
+static inline void vm_raw_write_begin(struct vm_area_struct *vma)
+{
+}
+static inline void vm_raw_write_end(struct vm_area_struct *vma)
+{
+}
+#endif /* __HAVE_ARCH_CALL_SPF */
+
extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len,
unsigned int gup_flags);
extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d1e5062b0c00..6736feb8cb28 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -346,6 +346,9 @@ struct vm_area_struct {
struct mempolicy *vm_policy; /* NUMA policy for the VMA */
#endif
struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
+#ifdef __HAVE_ARCH_CALL_SPF
+ seqcount_t vm_sequence;
+#endif
} __randomize_layout;
struct core_thread {
diff --git a/mm/memory.c b/mm/memory.c
index 27f626c229f7..ac6822356a37 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1504,6 +1504,7 @@ void unmap_page_range(struct mmu_gather *tlb,
unsigned long next;
BUG_ON(addr >= end);
+ vm_write_begin(vma);
tlb_start_vma(tlb, vma);
pgd = pgd_offset(vma->vm_mm, addr);
do {
@@ -1513,6 +1514,7 @@ void unmap_page_range(struct mmu_gather *tlb,
next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
} while (pgd++, addr = next, addr != end);
tlb_end_vma(tlb, vma);
+ vm_write_end(vma);
}
diff --git a/mm/mmap.c b/mm/mmap.c
index 2f3971a051c6..ec896358fc5a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -558,6 +558,10 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
else
mm->highest_vm_end = vm_end_gap(vma);
+#ifdef __HAVE_ARCH_CALL_SPF
+ seqcount_init(&vma->vm_sequence);
+#endif
+
/*
* vma->vm_prev wasn't known when we followed the rbtree to find the
* correct insertion point for that vma. As a result, we could not
@@ -692,6 +696,30 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
long adjust_next = 0;
int remove_next = 0;
+ /*
+ * Why using vm_raw_write*() functions here to avoid lockdep's warning ?
+ *
+ * Locked is complaining about a theoretical lock dependency, involving
+ * 3 locks:
+ * mapping->i_mmap_rwsem --> vma->vm_sequence --> fs_reclaim
+ *
+ * Here are the major path leading to this dependency :
+ * 1. __vma_adjust() mmap_sem -> vm_sequence -> i_mmap_rwsem
+ * 2. move_vmap() mmap_sem -> vm_sequence -> fs_reclaim
+ * 3. __alloc_pages_nodemask() fs_reclaim -> i_mmap_rwsem
+ * 4. unmap_mapping_range() i_mmap_rwsem -> vm_sequence
+ *
+ * So there is no way to solve this easily, especially because in
+ * unmap_mapping_range() the i_mmap_rwsem is grab while the impacted
+ * VMAs are not yet known.
+ * However, the way the vm_seq is used is guarantying that we will
+ * never block on it since we just check for its value and never wait
+ * for it to move, see vma_has_changed() and handle_speculative_fault().
+ */
+ vm_raw_write_begin(vma);
+ if (next)
+ vm_raw_write_begin(next);
+
if (next && !insert) {
struct vm_area_struct *exporter = NULL, *importer = NULL;
@@ -903,6 +931,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
mm->map_count--;
mpol_put(vma_policy(next));
kmem_cache_free(vm_area_cachep, next);
+ vm_raw_write_end(next);
/*
* In mprotect's case 6 (see comments on vma_merge),
* we must remove another next too. It would clutter
@@ -916,6 +945,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
* "vma->vm_next" gap must be updated.
*/
next = vma->vm_next;
+ if (next)
+ vm_raw_write_begin(next);
} else {
/*
* For the scope of the comment "next" and
@@ -933,10 +964,9 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
remove_next = 1;
end = next->vm_end;
goto again;
- }
- else if (next)
+ } else if (next) {
vma_gap_update(next);
- else {
+ } else {
/*
* If remove_next == 2 we obviously can't
* reach this path.
@@ -962,6 +992,10 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
if (insert && file)
uprobe_mmap(insert);
+ if (next && next != vma)
+ vm_raw_write_end(next);
+ vm_raw_write_end(vma);
+
validate_mm(mm);
return 0;
--
2.7.4
Powered by blists - more mailing lists