From: Laurent Dufour <ldufour@linux.vnet.ibm.com>
To: paulmck@linux.vnet.ibm.com, peterz@infradead.org,
akpm@linux-foundation.org, kirill@shutemov.name,
ak@linux.intel.com, mhocko@kernel.org, dave@stgolabs.net,
jack@suse.cz, Matthew Wilcox <willy@infradead.org>,
benh@kernel.crashing.org, mpe@ellerman.id.au, paulus@samba.org,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
hpa@zytor.com, Will Deacon <will.deacon@arm.com>,
Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
haren@linux.vnet.ibm.com, khandual@linux.vnet.ibm.com,
npiggin@gmail.com, bsingharora@gmail.com,
Tim Chen <tim.c.chen@linux.intel.com>,
linuxppc-dev@lists.ozlabs.org, x86@kernel.org
Subject: [PATCH v5 06/22] mm: VMA sequence count
Date: Wed, 11 Oct 2017 15:52:30 +0200 [thread overview]
Message-ID: <1507729966-10660-7-git-send-email-ldufour@linux.vnet.ibm.com> (raw)
In-Reply-To: <1507729966-10660-1-git-send-email-ldufour@linux.vnet.ibm.com>
From: Peter Zijlstra <peterz@infradead.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@infradead.org>
[Port to 4.12 kernel]
[Build depends on CONFIG_SPF]
[Introduce vm_write_* inline function depending on CONFIG_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@linux.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..1e7740170c24 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 CONFIG_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 /* CONFIG_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..3819fec89c7b 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 CONFIG_SPF
+ seqcount_t vm_sequence;
+#endif
} __randomize_layout;
struct core_thread {
diff --git a/mm/memory.c b/mm/memory.c
index 0fd72b19c730..eaa86e41124f 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..0e90b469fd97 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 CONFIG_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
next prev parent reply other threads:[~2017-10-11 14:00 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-11 13:52 [PATCH v5 00/22] Speculative page faults Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 01/22] x86/mm: Define CONFIG_SPF Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 02/22] powerpc/mm: " Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 03/22] mm: Dont assume page-table invariance during faults Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 04/22] mm: Prepare for FAULT_FLAG_SPECULATIVE Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 05/22] mm: Introduce pte_spinlock " Laurent Dufour
2017-10-11 13:52 ` Laurent Dufour [this message]
2017-10-11 13:52 ` [PATCH v5 07/22] mm: Protect VMA modifications using VMA sequence count Laurent Dufour
2017-10-26 10:18 ` Andrea Arcangeli
2017-11-02 15:16 ` Laurent Dufour
2017-11-02 17:25 ` Laurent Dufour
2017-11-02 20:08 ` Andrea Arcangeli
2017-11-06 9:47 ` Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 08/22] mm: RCU free VMAs Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 09/22] mm: Cache some VMA fields in the vm_fault structure Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 10/22] mm: Protect SPF handler against anon_vma changes Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 11/22] mm/migrate: Pass vm_fault pointer to migrate_misplaced_page() Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 12/22] mm: Introduce __lru_cache_add_active_or_unevictable Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 13/22] mm: Introduce __maybe_mkwrite() Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 14/22] mm: Introduce __vm_normal_page() Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 15/22] mm: Introduce __page_add_new_anon_rmap() Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 16/22] mm: Provide speculative fault infrastructure Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 17/22] mm: Try spin lock in speculative path Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 18/22] mm: Adding speculative page fault failure trace events Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 19/22] perf: Add a speculative page fault sw event Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 20/22] perf tools: Add support for the SPF perf event Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 21/22] x86/mm: Add speculative pagefault handling Laurent Dufour
2017-10-11 13:52 ` [PATCH v5 22/22] powerpc/mm: Add speculative page fault Laurent Dufour
2017-10-26 8:14 ` [v5,22/22] " kemi
2017-11-02 14:11 ` Laurent Dufour
2017-11-06 10:27 ` Sergey Senozhatsky
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=1507729966-10660-7-git-send-email-ldufour@linux.vnet.ibm.com \
--to=ldufour@linux.vnet.ibm.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=alexei.starovoitov@gmail.com \
--cc=benh@kernel.crashing.org \
--cc=bsingharora@gmail.com \
--cc=dave@stgolabs.net \
--cc=haren@linux.vnet.ibm.com \
--cc=hpa@zytor.com \
--cc=jack@suse.cz \
--cc=khandual@linux.vnet.ibm.com \
--cc=kirill@shutemov.name \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mhocko@kernel.org \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=npiggin@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=sergey.senozhatsky@gmail.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=will.deacon@arm.com \
--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).