[PATCH 3.14 137/140] net_sched: fix an oops in tcindex filter

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

3.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Cong Wang <xiyou.wangcong@gmail.com>

[ Upstream commit bf63ac73b3e132e6bf0c8798aba7b277c3316e19 ]

Kelly reported the following crash:

        IP: [<ffffffff817a993d>] tcf_action_exec+0x46/0x90
        PGD 3009067 PUD 300c067 PMD 11ff30067 PTE 800000011634b060
        Oops: 0000 [#1] SMP DEBUG_PAGEALLOC
        CPU: 1 PID: 639 Comm: dhclient Not tainted 3.15.0-rc4+ #342
        Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
        task: ffff8801169ecd00 ti: ffff8800d21b8000 task.ti: ffff8800d21b8000
        RIP: 0010:[<ffffffff817a993d>]  [<ffffffff817a993d>] tcf_action_exec+0x46/0x90
        RSP: 0018:ffff8800d21b9b90  EFLAGS: 00010283
        RAX: 00000000ffffffff RBX: ffff88011634b8e8 RCX: ffff8800cf7133d8
        RDX: ffff88011634b900 RSI: ffff8800cf7133e0 RDI: ffff8800d210f840
        RBP: ffff8800d21b9bb0 R08: ffffffff8287bf60 R09: 0000000000000001
        R10: ffff8800d2b22b24 R11: 0000000000000001 R12: ffff8800d210f840
        R13: ffff8800d21b9c50 R14: ffff8800cf7133e0 R15: ffff8800cad433d8
        FS:  00007f49723e1840(0000) GS:ffff88011a800000(0000) knlGS:0000000000000000
        CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
        CR2: ffff88011634b8f0 CR3: 00000000ce469000 CR4: 00000000000006e0
        Stack:
         ffff8800d2170188 ffff8800d210f840 ffff8800d2171b90 0000000000000000
         ffff8800d21b9be8 ffffffff817c55bb ffff8800d21b9c50 ffff8800d2171b90
         ffff8800d210f840 ffff8800d21b0300 ffff8800d21b9c50 ffff8800d21b9c18
        Call Trace:
         [<ffffffff817c55bb>] tcindex_classify+0x88/0x9b
         [<ffffffff817a7f7d>] tc_classify_compat+0x3e/0x7b
         [<ffffffff817a7fdf>] tc_classify+0x25/0x9f
         [<ffffffff817b0e68>] htb_enqueue+0x55/0x27a
         [<ffffffff817b6c2e>] dsmark_enqueue+0x165/0x1a4
         [<ffffffff81775642>] __dev_queue_xmit+0x35e/0x536
         [<ffffffff8177582a>] dev_queue_xmit+0x10/0x12
         [<ffffffff818f8ecd>] packet_sendmsg+0xb26/0xb9a
         [<ffffffff810b1507>] ? __lock_acquire+0x3ae/0xdf3
         [<ffffffff8175cf08>] __sock_sendmsg_nosec+0x25/0x27
         [<ffffffff8175d916>] sock_aio_write+0xd0/0xe7
         [<ffffffff8117d6b8>] do_sync_write+0x59/0x78
         [<ffffffff8117d84d>] vfs_write+0xb5/0x10a
         [<ffffffff8117d96a>] SyS_write+0x49/0x7f
         [<ffffffff8198e212>] system_call_fastpath+0x16/0x1b

This is because we memcpy struct tcindex_filter_result which contains
struct tcf_exts, obviously struct list_head can not be simply copied.
This is a regression introduced by commit 33be627159913b094bb578
(net_sched: act: use standard struct list_head).

It's not very easy to fix it as the code is a mess:

       if (old_r)
               memcpy(&cr, r, sizeof(cr));
       else {
               memset(&cr, 0, sizeof(cr));
               tcf_exts_init(&cr.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
       }
       ...
       tcf_exts_change(tp, &cr.exts, &e);
       ...
       memcpy(r, &cr, sizeof(cr));

the above code should equal to:

        tcindex_filter_result_init(&cr);
        if (old_r)
               cr.res = r->res;
        ...
        if (old_r)
               tcf_exts_change(tp, &r->exts, &e);
        else
               tcf_exts_change(tp, &cr.exts, &e);
        ...
        r->res = cr.res;

after this change, since there is no need to copy struct tcf_exts.

And it also fixes other places zero'ing struct's contains struct tcf_exts.

Fixes: commit 33be627159913b0 (net_sched: act: use standard struct list_head)
Reported-by: Kelly Anderson <kelly@xilka.com>
Tested-by: Kelly Anderson <kelly@xilka.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/sched/cls_tcindex.c |   30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -188,6 +188,12 @@ static const struct nla_policy tcindex_p
 	[TCA_TCINDEX_CLASSID]		= { .type = NLA_U32 },
 };
 
+static void tcindex_filter_result_init(struct tcindex_filter_result *r)
+{
+	memset(r, 0, sizeof(*r));
+	tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+}
+
 static int
 tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		  u32 handle, struct tcindex_data *p,
@@ -207,15 +213,11 @@ tcindex_set_parms(struct net *net, struc
 		return err;
 
 	memcpy(&cp, p, sizeof(cp));
-	memset(&new_filter_result, 0, sizeof(new_filter_result));
-	tcf_exts_init(&new_filter_result.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+	tcindex_filter_result_init(&new_filter_result);
 
+	tcindex_filter_result_init(&cr);
 	if (old_r)
-		memcpy(&cr, r, sizeof(cr));
-	else {
-		memset(&cr, 0, sizeof(cr));
-		tcf_exts_init(&cr.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
-	}
+		cr.res = r->res;
 
 	if (tb[TCA_TCINDEX_HASH])
 		cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -267,9 +269,14 @@ tcindex_set_parms(struct net *net, struc
 	err = -ENOMEM;
 	if (!cp.perfect && !cp.h) {
 		if (valid_perfect_hash(&cp)) {
+			int i;
+
 			cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL);
 			if (!cp.perfect)
 				goto errout;
+			for (i = 0; i < cp.hash; i++)
+				tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT,
+					      TCA_TCINDEX_POLICE);
 			balloc = 1;
 		} else {
 			cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL);
@@ -295,14 +302,17 @@ tcindex_set_parms(struct net *net, struc
 		tcf_bind_filter(tp, &cr.res, base);
 	}
 
-	tcf_exts_change(tp, &cr.exts, &e);
+	if (old_r)
+		tcf_exts_change(tp, &r->exts, &e);
+	else
+		tcf_exts_change(tp, &cr.exts, &e);
 
 	tcf_tree_lock(tp);
 	if (old_r && old_r != r)
-		memset(old_r, 0, sizeof(*old_r));
+		tcindex_filter_result_init(old_r);
 
 	memcpy(p, &cp, sizeof(cp));
-	memcpy(r, &cr, sizeof(cr));
+	r->res = cr.res;
 
 	if (r == &new_filter_result) {
 		struct tcindex_filter **fp;