summaryrefslogtreecommitdiffstats
path: root/patches/cve/CVE-2018-17182-mm-get-rid-of-vmacache_flush_all-entirely.patch
blob: 6d6c2ca8c11b383d88ff9e6adc49bd1514584234 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
From 84580567f1f856d2c7a610273315852e345bc3ac Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 12 Sep 2018 23:57:48 -1000
Subject: [PATCH] mm: get rid of vmacache_flush_all() entirely

commit 7a9cdebdcc17e426fb5287e4a82db1dfe86339b2 upstream.

Jann Horn points out that the vmacache_flush_all() function is not only
potentially expensive, it's buggy too.  It also happens to be entirely
unnecessary, because the sequence number overflow case can be avoided by
simply making the sequence number be 64-bit.  That doesn't even grow the
data structures in question, because the other adjacent fields are
already 64-bit.

So simplify the whole thing by just making the sequence number overflow
case go away entirely, which gets rid of all the complications and makes
the code faster too.  Win-win.

[ Oleg Nesterov points out that the VMACACHE_FULL_FLUSHES statistics
  also just goes away entirely with this ]

CVE: CVE-2018-17182
Upstream-Status: Backport [https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=linux-4.9.y&id=84580567f1f856d2c7a610273315852e345bc3ac]

Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Will Deacon <will.deacon@arm.com>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andreas Wellving <andreas.wellving@enea.com>
---
 include/linux/mm_types.h      |  2 +-
 include/linux/sched.h         |  2 +-
 include/linux/vm_event_item.h |  1 -
 include/linux/vmacache.h      |  5 -----
 mm/debug.c                    |  4 ++--
 mm/vmacache.c                 | 38 -----------------------------------
 6 files changed, 4 insertions(+), 48 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e8471c2ca83a..8d6decd50220 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -396,7 +396,7 @@ struct kioctx_table;
 struct mm_struct {
 	struct vm_area_struct *mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
-	u32 vmacache_seqnum;                   /* per-thread vmacache */
+	u64 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
 	unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1cc5723a7821..f4a551a5482c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1559,7 +1559,7 @@ struct task_struct {
 
 	struct mm_struct *mm, *active_mm;
 	/* per-thread vma caching */
-	u32 vmacache_seqnum;
+	u64 vmacache_seqnum;
 	struct vm_area_struct *vmacache[VMACACHE_SIZE];
 #if defined(SPLIT_RSS_COUNTING)
 	struct task_rss_stat	rss_stat;
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 2edb150f1a4d..544cd50fbbd0 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -97,7 +97,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_DEBUG_VM_VMACACHE
 		VMACACHE_FIND_CALLS,
 		VMACACHE_FIND_HITS,
-		VMACACHE_FULL_FLUSHES,
 #endif
 		NR_VM_EVENT_ITEMS
 };
diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h
index c3fa0fd43949..4f58ff2dacd6 100644
--- a/include/linux/vmacache.h
+++ b/include/linux/vmacache.h
@@ -15,7 +15,6 @@ static inline void vmacache_flush(struct task_struct *tsk)
 	memset(tsk->vmacache, 0, sizeof(tsk->vmacache));
 }
 
-extern void vmacache_flush_all(struct mm_struct *mm);
 extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma);
 extern struct vm_area_struct *vmacache_find(struct mm_struct *mm,
 						    unsigned long addr);
@@ -29,10 +28,6 @@ extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
 static inline void vmacache_invalidate(struct mm_struct *mm)
 {
 	mm->vmacache_seqnum++;
-
-	/* deal with overflows */
-	if (unlikely(mm->vmacache_seqnum == 0))
-		vmacache_flush_all(mm);
 }
 
 #endif /* __LINUX_VMACACHE_H */
diff --git a/mm/debug.c b/mm/debug.c
index 9feb699c5d25..bebe48aece6d 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -95,7 +95,7 @@ EXPORT_SYMBOL(dump_vma);
 
 void dump_mm(const struct mm_struct *mm)
 {
-	pr_emerg("mm %p mmap %p seqnum %d task_size %lu\n"
+	pr_emerg("mm %p mmap %p seqnum %llu task_size %lu\n"
 #ifdef CONFIG_MMU
 		"get_unmapped_area %p\n"
 #endif
@@ -125,7 +125,7 @@ void dump_mm(const struct mm_struct *mm)
 #endif
 		"def_flags: %#lx(%pGv)\n",
 
-		mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
+		mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size,
 #ifdef CONFIG_MMU
 		mm->get_unmapped_area,
 #endif
diff --git a/mm/vmacache.c b/mm/vmacache.c
index 035fdeb35b43..c9ca3dd46b97 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -5,44 +5,6 @@
 #include <linux/mm.h>
 #include <linux/vmacache.h>
 
-/*
- * Flush vma caches for threads that share a given mm.
- *
- * The operation is safe because the caller holds the mmap_sem
- * exclusively and other threads accessing the vma cache will
- * have mmap_sem held at least for read, so no extra locking
- * is required to maintain the vma cache.
- */
-void vmacache_flush_all(struct mm_struct *mm)
-{
-	struct task_struct *g, *p;
-
-	count_vm_vmacache_event(VMACACHE_FULL_FLUSHES);
-
-	/*
-	 * Single threaded tasks need not iterate the entire
-	 * list of process. We can avoid the flushing as well
-	 * since the mm's seqnum was increased and don't have
-	 * to worry about other threads' seqnum. Current's
-	 * flush will occur upon the next lookup.
-	 */
-	if (atomic_read(&mm->mm_users) == 1)
-		return;
-
-	rcu_read_lock();
-	for_each_process_thread(g, p) {
-		/*
-		 * Only flush the vmacache pointers as the
-		 * mm seqnum is already set and curr's will
-		 * be set upon invalidation when the next
-		 * lookup is done.
-		 */
-		if (mm == p->mm)
-			vmacache_flush(p);
-	}
-	rcu_read_unlock();
-}
-
 /*
  * This task may be accessing a foreign mm via (for example)
  * get_user_pages()->find_vma().  The vmacache is task-local and this