Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 15 Feb 2018 17:04:32 +0000
From:   Mark Rutland <mark.rutland@arm.com>
To:     netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     davem@davemloft.net, willemb@google.com, edumazet@google.com
Subject: v4.16-rc1 misaligned atomics in skb__clone / __napi_alloc_skb
Message-ID: <20180215170432.e4wue4osyv3vmdla@lakrids.cambridge.arm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
User-Agent: NeoMutt/20170113 (1.7.2)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Hi,

While fuzzing arm64 v4.16-rc1 with Syzkaller, I've been hitting a
misaligned atomic in __skb_clone:

	atomic_inc(&(skb_shinfo(skb)->dataref));

.. where dataref doesn't have the required natural alignment, and the
atomic operation faults. e.g. i often see it aligned to a single byte
boundary rather than a four byte boundary.

AFAICT, the skb_shared_info is misaligned at the instant it's allocated
in __napi_alloc_skb(). With the patch at the end of this mail, the
atomic_set() (which is a WRITE_ONCE()) in __build_skb() blows up, e.g.

WARNING: CPU: 0 PID: 8457 at mm/access_once.c:12 access_once_alignment_check+0x34/0x40 mm/access_once.c:12
Kernel panic - not syncing: panic_on_warn set ...

CPU: 0 PID: 8457 Comm: syz-executor1 Not tainted 4.16.0-rc1-00002-gb03ae7b8b0de #9
Hardware name: linux,dummy-virt (DT)
Call trace:
 dump_backtrace+0x0/0x390 arch/arm64/kernel/time.c:52
 show_stack+0x20/0x30 arch/arm64/kernel/traps.c:151
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0xd0/0x130 lib/dump_stack.c:53
 panic+0x220/0x3fc kernel/panic.c:183
 __warn+0x270/0x2bc kernel/panic.c:547
 report_bug+0x1dc/0x2d0 lib/bug.c:184
 bug_handler+0x7c/0x128 arch/arm64/kernel/traps.c:758
 call_break_hook arch/arm64/kernel/debug-monitors.c:305 [inline]
 brk_handler+0x1a0/0x300 arch/arm64/kernel/debug-monitors.c:320
 do_debug_exception+0x15c/0x408 arch/arm64/mm/fault.c:808
 el1_dbg+0x18/0x78
 access_once_alignment_check+0x34/0x40 mm/access_once.c:12
 __napi_alloc_skb+0x18c/0x2b8 net/core/skbuff.c:482
 napi_alloc_skb include/linux/skbuff.h:2643 [inline]
 napi_get_frags+0x68/0x120 net/core/dev.c:5108
 tun_napi_alloc_frags drivers/net/tun.c:1477 [inline]
 tun_get_user+0x13b0/0x3fe8 drivers/net/tun.c:1820
 tun_chr_write_iter+0xa8/0x158 drivers/net/tun.c:1988
 call_write_iter include/linux/fs.h:1781 [inline]
 do_iter_readv_writev+0x2f8/0x490 fs/read_write.c:653
 do_iter_write+0x14c/0x4b0 fs/read_write.c:932
 vfs_writev+0x130/0x288 fs/read_write.c:977
 do_writev+0xe0/0x248 fs/read_write.c:1012
 SYSC_writev fs/read_write.c:1085 [inline]
 SyS_writev+0x34/0x48 fs/read_write.c:1082
 el0_svc_naked+0x30/0x34
SMP: stopping secondary CPUs
Kernel Offset: disabled
CPU features: 0x1002082
Memory Limit: none
Rebooting in 86400 seconds..

... I see these splats with both tun and virtio-net.

I have some Syzkaller logs, and can reproduce the problem locally, but
unfortunately the C reproducer it generated doesn't seem to work on its
own.

Any ideas as to how this could happen?

Thanks,
Mark.

---->8----
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index c2cc57a2f508..c06b810a3b3b 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -163,6 +163,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 
 #include <uapi/linux/types.h>
 
+void access_once_alignment_check(const volatile void *ptr, int size);
+
 #define __READ_ONCE_SIZE                                               \
 ({                                                                     \
        switch (size) {                                                 \
@@ -180,6 +182,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 static __always_inline
 void __read_once_size(const volatile void *p, void *res, int size)
 {
+       access_once_alignment_check(p, size);
        __READ_ONCE_SIZE;
 }
 
@@ -203,6 +206,8 @@ void __read_once_size_nocheck(const volatile void *p, void *res, int size)
 
 static __always_inline void __write_once_size(volatile void *p, void *res, int size)
 {
+       access_once_alignment_check(p, size);
+
        switch (size) {
        case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
        case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
diff --git a/mm/Makefile b/mm/Makefile
index e669f02c5a54..604d269d7d57 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -3,6 +3,7 @@
 # Makefile for the linux memory manager.
 #
 
+KASAN_SANITIZE_access_once.o := n
 KASAN_SANITIZE_slab_common.o := n
 KASAN_SANITIZE_slab.o := n
 KASAN_SANITIZE_slub.o := n
@@ -10,6 +11,7 @@ KASAN_SANITIZE_slub.o := n
 # These files are disabled because they produce non-interesting and/or
 # flaky coverage that is not a function of syscall inputs. E.g. slab is out of
 # free pages, or a task is migrated between nodes.
+KCOV_INSTRUMENT_access_once.o := n
 KCOV_INSTRUMENT_slab_common.o := n
 KCOV_INSTRUMENT_slob.o := n
 KCOV_INSTRUMENT_slab.o := n
@@ -39,7 +41,7 @@ obj-y                 := filemap.o mempool.o oom_kill.o \
                           mm_init.o mmu_context.o percpu.o slab_common.o \
                           compaction.o vmacache.o swap_slots.o \
                           interval_tree.o list_lru.o workingset.o \
-                          debug.o $(mmu-y)
+                          debug.o access_once.o $(mmu-y)
 
 obj-y += init-mm.o
 
diff --git a/mm/access_once.c b/mm/access_once.c
new file mode 100644
index 000000000000..42ee35d171c4
--- /dev/null
+++ b/mm/access_once.c
@@ -0,0 +1,15 @@
+#include <linux/bug.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+
+void access_once_alignment_check(const volatile void *ptr, int size)
+{
+       switch (size) {
+       case 1:
+       case 2:
+       case 4:
+       case 8:
+               WARN_ON(!IS_ALIGNED((unsigned long)ptr, size));
+       }
+}
+EXPORT_SYMBOL(access_once_alignment_check);