linux/net/sched/cls_tcindex.c

644 lines
15 KiB
C
Raw Normal View History

/*
* net/sched/cls_tcindex.c Packet classifier for skb->tc_index
*
* Written 1998,1999 by Werner Almesberger, EPFL ICA
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/errno.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <net/act_api.h>
#include <net/netlink.h>
#include <net/pkt_cls.h>
/*
* Passing parameters to the root seems to be done more awkwardly than really
* necessary. At least, u32 doesn't seem to use such dirty hacks. To be
* verified. FIXME.
*/
#define PERFECT_HASH_THRESHOLD 64 /* use perfect hash if not bigger */
#define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */
struct tcindex_filter_result {
struct tcf_exts exts;
struct tcf_result res;
struct rcu_head rcu;
};
struct tcindex_filter {
u16 key;
struct tcindex_filter_result result;
struct tcindex_filter __rcu *next;
struct rcu_head rcu;
};
struct tcindex_data {
struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */
struct tcindex_filter __rcu **h; /* imperfect hash; */
struct tcf_proto *tp;
u16 mask; /* AND key with mask */
u32 shift; /* shift ANDed key to the right */
u32 hash; /* hash table size; 0 if undefined */
u32 alloc_hash; /* allocated size */
u32 fall_through; /* 0: only classify if explicit match */
struct rcu_head rcu;
};
static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
{
return tcf_exts_has_actions(&r->exts) || r->res.classid;
}
static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p,
u16 key)
{
if (p->perfect) {
struct tcindex_filter_result *f = p->perfect + key;
return tcindex_filter_is_set(f) ? f : NULL;
} else if (p->h) {
struct tcindex_filter __rcu **fp;
struct tcindex_filter *f;
fp = &p->h[key % p->hash];
for (f = rcu_dereference_bh_rtnl(*fp);
f;
fp = &f->next, f = rcu_dereference_bh_rtnl(*fp))
if (f->key == key)
return &f->result;
}
return NULL;
}
static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct tcindex_data *p = rcu_dereference_bh(tp->root);
struct tcindex_filter_result *f;
int key = (skb->tc_index & p->mask) >> p->shift;
pr_debug("tcindex_classify(skb %p,tp %p,res %p),p %p\n",
skb, tp, res, p);
f = tcindex_lookup(p, key);
if (!f) {
if (!p->fall_through)
return -1;
res->classid = TC_H_MAKE(TC_H_MAJ(tp->q->handle), key);
res->class = 0;
pr_debug("alg 0x%x\n", res->classid);
return 0;
}
*res = f->res;
pr_debug("map 0x%x\n", res->classid);
return tcf_exts_exec(skb, &f->exts, res);
}
static void *tcindex_get(struct tcf_proto *tp, u32 handle)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r;
pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle);
if (p->perfect && handle >= p->alloc_hash)
return NULL;
r = tcindex_lookup(p, handle);
return r && tcindex_filter_is_set(r) ? r : NULL;
}
static int tcindex_init(struct tcf_proto *tp)
{
struct tcindex_data *p;
pr_debug("tcindex_init(tp %p)\n", tp);
p = kzalloc(sizeof(struct tcindex_data), GFP_KERNEL);
if (!p)
return -ENOMEM;
p->mask = 0xffff;
p->hash = DEFAULT_HASH_SIZE;
p->fall_through = 1;
rcu_assign_pointer(tp->root, p);
return 0;
}
static void tcindex_destroy_rexts(struct rcu_head *head)
{
struct tcindex_filter_result *r;
r = container_of(head, struct tcindex_filter_result, rcu);
tcf_exts_destroy(&r->exts);
}
static void tcindex_destroy_fexts(struct rcu_head *head)
{
struct tcindex_filter *f = container_of(head, struct tcindex_filter,
rcu);
tcf_exts_destroy(&f->result.exts);
kfree(f);
}
static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r = arg;
struct tcindex_filter __rcu **walk;
struct tcindex_filter *f = NULL;
pr_debug("tcindex_delete(tp %p,arg %p),p %p\n", tp, arg, p);
if (p->perfect) {
if (!r->res.class)
return -ENOENT;
} else {
int i;
for (i = 0; i < p->hash; i++) {
walk = p->h + i;
for (f = rtnl_dereference(*walk); f;
walk = &f->next, f = rtnl_dereference(*walk)) {
if (&f->result == r)
goto found;
}
}
return -ENOENT;
found:
rcu_assign_pointer(*walk, rtnl_dereference(f->next));
}
tcf_unbind_filter(tp, &r->res);
/* all classifiers are required to call tcf_exts_destroy() after rcu
* grace period, since converted-to-rcu actions are relying on that
* in cleanup() callback
*/
if (f)
call_rcu(&f->rcu, tcindex_destroy_fexts);
else
call_rcu(&r->rcu, tcindex_destroy_rexts);
*last = false;
return 0;
}
static int tcindex_destroy_element(struct tcf_proto *tp,
void *arg, struct tcf_walker *walker)
{
bool last;
return tcindex_delete(tp, arg, &last);
}
static void __tcindex_destroy(struct rcu_head *head)
{
struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
kfree(p->perfect);
kfree(p->h);
kfree(p);
}
static inline int
valid_perfect_hash(struct tcindex_data *p)
{
return p->hash > (p->mask >> p->shift);
}
static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
[TCA_TCINDEX_HASH] = { .type = NLA_U32 },
[TCA_TCINDEX_MASK] = { .type = NLA_U16 },
[TCA_TCINDEX_SHIFT] = { .type = NLA_U32 },
[TCA_TCINDEX_FALL_THROUGH] = { .type = NLA_U32 },
[TCA_TCINDEX_CLASSID] = { .type = NLA_U32 },
};
static int tcindex_filter_result_init(struct tcindex_filter_result *r)
net_sched: fix an oops in tcindex filter 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>
2014-05-19 19:15:49 +00:00
{
memset(r, 0, sizeof(*r));
return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
net_sched: fix an oops in tcindex filter 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>
2014-05-19 19:15:49 +00:00
}
static void __tcindex_partial_destroy(struct rcu_head *head)
{
struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
kfree(p->perfect);
kfree(p);
}
static void tcindex_free_perfect_hash(struct tcindex_data *cp)
{
int i;
for (i = 0; i < cp->hash; i++)
tcf_exts_destroy(&cp->perfect[i].exts);
kfree(cp->perfect);
}
static int tcindex_alloc_perfect_hash(struct tcindex_data *cp)
{
int i, err = 0;
cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result),
GFP_KERNEL);
if (!cp->perfect)
return -ENOMEM;
for (i = 0; i < cp->hash; i++) {
err = tcf_exts_init(&cp->perfect[i].exts,
TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
if (err < 0)
goto errout;
}
return 0;
errout:
tcindex_free_perfect_hash(cp);
return err;
}
static int
tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
u32 handle, struct tcindex_data *p,
struct tcindex_filter_result *r, struct nlattr **tb,
struct nlattr *est, bool ovr)
{
struct tcindex_filter_result new_filter_result, *old_r = r;
struct tcindex_filter_result cr;
struct tcindex_data *cp = NULL, *oldp;
struct tcindex_filter *f = NULL; /* make gcc behave */
int err, balloc = 0;
struct tcf_exts e;
err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
if (err < 0)
return err;
err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
if (err < 0)
goto errout;
err = -ENOMEM;
/* tcindex_data attributes must look atomic to classifier/lookup so
* allocate new tcindex data and RCU assign it onto root. Keeping
* perfect hash and hash pointers from old data.
*/
cp = kzalloc(sizeof(*cp), GFP_KERNEL);
if (!cp)
goto errout;
cp->mask = p->mask;
cp->shift = p->shift;
cp->hash = p->hash;
cp->alloc_hash = p->alloc_hash;
cp->fall_through = p->fall_through;
cp->tp = tp;
if (p->perfect) {
net_sched: fix another crash in cls_tcindex This patch fixes the following crash: [ 166.670795] BUG: unable to handle kernel NULL pointer dereference at (null) [ 166.674230] IP: [<ffffffff814b739f>] __list_del_entry+0x5c/0x98 [ 166.674230] PGD d0ea5067 PUD ce7fc067 PMD 0 [ 166.674230] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [ 166.674230] CPU: 1 PID: 775 Comm: tc Not tainted 3.17.0-rc6+ #642 [ 166.674230] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 166.674230] task: ffff8800d03c4d20 ti: ffff8800cae7c000 task.ti: ffff8800cae7c000 [ 166.674230] RIP: 0010:[<ffffffff814b739f>] [<ffffffff814b739f>] __list_del_entry+0x5c/0x98 [ 166.674230] RSP: 0018:ffff8800cae7f7d0 EFLAGS: 00010207 [ 166.674230] RAX: 0000000000000000 RBX: ffff8800cba8d700 RCX: ffff8800cba8d700 [ 166.674230] RDX: 0000000000000000 RSI: dead000000200200 RDI: ffff8800cba8d700 [ 166.674230] RBP: ffff8800cae7f7d0 R08: 0000000000000001 R09: 0000000000000001 [ 166.674230] R10: 0000000000000000 R11: 000000000000859a R12: ffffffffffffffe8 [ 166.674230] R13: ffff8800cba8c5b8 R14: 0000000000000001 R15: ffff8800cba8d700 [ 166.674230] FS: 00007fdb5f04a740(0000) GS:ffff88011a800000(0000) knlGS:0000000000000000 [ 166.674230] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 166.674230] CR2: 0000000000000000 CR3: 00000000cf929000 CR4: 00000000000006e0 [ 166.674230] Stack: [ 166.674230] ffff8800cae7f7e8 ffffffff814b73e8 ffff8800cba8d6e8 ffff8800cae7f828 [ 166.674230] ffffffff817caeec 0000000000000046 ffff8800cba8c5b0 ffff8800cba8c5b8 [ 166.674230] 0000000000000000 0000000000000001 ffff8800cf8e33e8 ffff8800cae7f848 [ 166.674230] Call Trace: [ 166.674230] [<ffffffff814b73e8>] list_del+0xd/0x2b [ 166.674230] [<ffffffff817caeec>] tcf_action_destroy+0x4c/0x71 [ 166.674230] [<ffffffff817ca0ce>] tcf_exts_destroy+0x20/0x2d [ 166.674230] [<ffffffff817ec2b5>] tcindex_delete+0x196/0x1b7 struct list_head can not be simply copied and we should always init it. Cc: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-30 23:07:23 +00:00
int i;
if (tcindex_alloc_perfect_hash(cp) < 0)
goto errout;
net_sched: fix another crash in cls_tcindex This patch fixes the following crash: [ 166.670795] BUG: unable to handle kernel NULL pointer dereference at (null) [ 166.674230] IP: [<ffffffff814b739f>] __list_del_entry+0x5c/0x98 [ 166.674230] PGD d0ea5067 PUD ce7fc067 PMD 0 [ 166.674230] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [ 166.674230] CPU: 1 PID: 775 Comm: tc Not tainted 3.17.0-rc6+ #642 [ 166.674230] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 166.674230] task: ffff8800d03c4d20 ti: ffff8800cae7c000 task.ti: ffff8800cae7c000 [ 166.674230] RIP: 0010:[<ffffffff814b739f>] [<ffffffff814b739f>] __list_del_entry+0x5c/0x98 [ 166.674230] RSP: 0018:ffff8800cae7f7d0 EFLAGS: 00010207 [ 166.674230] RAX: 0000000000000000 RBX: ffff8800cba8d700 RCX: ffff8800cba8d700 [ 166.674230] RDX: 0000000000000000 RSI: dead000000200200 RDI: ffff8800cba8d700 [ 166.674230] RBP: ffff8800cae7f7d0 R08: 0000000000000001 R09: 0000000000000001 [ 166.674230] R10: 0000000000000000 R11: 000000000000859a R12: ffffffffffffffe8 [ 166.674230] R13: ffff8800cba8c5b8 R14: 0000000000000001 R15: ffff8800cba8d700 [ 166.674230] FS: 00007fdb5f04a740(0000) GS:ffff88011a800000(0000) knlGS:0000000000000000 [ 166.674230] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 166.674230] CR2: 0000000000000000 CR3: 00000000cf929000 CR4: 00000000000006e0 [ 166.674230] Stack: [ 166.674230] ffff8800cae7f7e8 ffffffff814b73e8 ffff8800cba8d6e8 ffff8800cae7f828 [ 166.674230] ffffffff817caeec 0000000000000046 ffff8800cba8c5b0 ffff8800cba8c5b8 [ 166.674230] 0000000000000000 0000000000000001 ffff8800cf8e33e8 ffff8800cae7f848 [ 166.674230] Call Trace: [ 166.674230] [<ffffffff814b73e8>] list_del+0xd/0x2b [ 166.674230] [<ffffffff817caeec>] tcf_action_destroy+0x4c/0x71 [ 166.674230] [<ffffffff817ca0ce>] tcf_exts_destroy+0x20/0x2d [ 166.674230] [<ffffffff817ec2b5>] tcindex_delete+0x196/0x1b7 struct list_head can not be simply copied and we should always init it. Cc: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-30 23:07:23 +00:00
for (i = 0; i < cp->hash; i++)
cp->perfect[i].res = p->perfect[i].res;
balloc = 1;
}
cp->h = p->h;
err = tcindex_filter_result_init(&new_filter_result);
if (err < 0)
goto errout1;
err = tcindex_filter_result_init(&cr);
if (err < 0)
goto errout1;
if (old_r)
net_sched: fix an oops in tcindex filter 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>
2014-05-19 19:15:49 +00:00
cr.res = r->res;
if (tb[TCA_TCINDEX_HASH])
cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
if (tb[TCA_TCINDEX_MASK])
cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
if (tb[TCA_TCINDEX_SHIFT])
cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
err = -EBUSY;
/* Hash already allocated, make sure that we still meet the
* requirements for the allocated hash.
*/
if (cp->perfect) {
if (!valid_perfect_hash(cp) ||
cp->hash > cp->alloc_hash)
goto errout_alloc;
} else if (cp->h && cp->hash != cp->alloc_hash) {
goto errout_alloc;
}
err = -EINVAL;
if (tb[TCA_TCINDEX_FALL_THROUGH])
cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
if (!cp->hash) {
/* Hash not specified, use perfect hash if the upper limit
* of the hashing index is below the threshold.
*/
if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
cp->hash = (cp->mask >> cp->shift) + 1;
else
cp->hash = DEFAULT_HASH_SIZE;
}
if (!cp->perfect && !cp->h)
cp->alloc_hash = cp->hash;
/* Note: this could be as restrictive as if (handle & ~(mask >> shift))
* but then, we'd fail handles that may become valid after some future
* mask change. While this is extremely unlikely to ever matter,
* the check below is safer (and also more backwards-compatible).
*/
if (cp->perfect || valid_perfect_hash(cp))
if (handle >= cp->alloc_hash)
goto errout_alloc;
err = -ENOMEM;
if (!cp->perfect && !cp->h) {
if (valid_perfect_hash(cp)) {
if (tcindex_alloc_perfect_hash(cp) < 0)
goto errout_alloc;
balloc = 1;
} else {
struct tcindex_filter __rcu **hash;
hash = kcalloc(cp->hash,
sizeof(struct tcindex_filter *),
GFP_KERNEL);
if (!hash)
goto errout_alloc;
cp->h = hash;
balloc = 2;
}
}
if (cp->perfect)
r = cp->perfect + handle;
else
r = tcindex_lookup(cp, handle) ? : &new_filter_result;
if (r == &new_filter_result) {
f = kzalloc(sizeof(*f), GFP_KERNEL);
if (!f)
goto errout_alloc;
net_sched: fix another crash in cls_tcindex This patch fixes the following crash: [ 166.670795] BUG: unable to handle kernel NULL pointer dereference at (null) [ 166.674230] IP: [<ffffffff814b739f>] __list_del_entry+0x5c/0x98 [ 166.674230] PGD d0ea5067 PUD ce7fc067 PMD 0 [ 166.674230] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [ 166.674230] CPU: 1 PID: 775 Comm: tc Not tainted 3.17.0-rc6+ #642 [ 166.674230] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 166.674230] task: ffff8800d03c4d20 ti: ffff8800cae7c000 task.ti: ffff8800cae7c000 [ 166.674230] RIP: 0010:[<ffffffff814b739f>] [<ffffffff814b739f>] __list_del_entry+0x5c/0x98 [ 166.674230] RSP: 0018:ffff8800cae7f7d0 EFLAGS: 00010207 [ 166.674230] RAX: 0000000000000000 RBX: ffff8800cba8d700 RCX: ffff8800cba8d700 [ 166.674230] RDX: 0000000000000000 RSI: dead000000200200 RDI: ffff8800cba8d700 [ 166.674230] RBP: ffff8800cae7f7d0 R08: 0000000000000001 R09: 0000000000000001 [ 166.674230] R10: 0000000000000000 R11: 000000000000859a R12: ffffffffffffffe8 [ 166.674230] R13: ffff8800cba8c5b8 R14: 0000000000000001 R15: ffff8800cba8d700 [ 166.674230] FS: 00007fdb5f04a740(0000) GS:ffff88011a800000(0000) knlGS:0000000000000000 [ 166.674230] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 166.674230] CR2: 0000000000000000 CR3: 00000000cf929000 CR4: 00000000000006e0 [ 166.674230] Stack: [ 166.674230] ffff8800cae7f7e8 ffffffff814b73e8 ffff8800cba8d6e8 ffff8800cae7f828 [ 166.674230] ffffffff817caeec 0000000000000046 ffff8800cba8c5b0 ffff8800cba8c5b8 [ 166.674230] 0000000000000000 0000000000000001 ffff8800cf8e33e8 ffff8800cae7f848 [ 166.674230] Call Trace: [ 166.674230] [<ffffffff814b73e8>] list_del+0xd/0x2b [ 166.674230] [<ffffffff817caeec>] tcf_action_destroy+0x4c/0x71 [ 166.674230] [<ffffffff817ca0ce>] tcf_exts_destroy+0x20/0x2d [ 166.674230] [<ffffffff817ec2b5>] tcindex_delete+0x196/0x1b7 struct list_head can not be simply copied and we should always init it. Cc: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-30 23:07:23 +00:00
f->key = handle;
f->next = NULL;
err = tcindex_filter_result_init(&f->result);
if (err < 0) {
kfree(f);
goto errout_alloc;
}
}
if (tb[TCA_TCINDEX_CLASSID]) {
cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
tcf_bind_filter(tp, &cr.res, base);
}
net_sched: fix an oops in tcindex filter 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>
2014-05-19 19:15:49 +00:00
if (old_r)
tcf_exts_change(&r->exts, &e);
net_sched: fix an oops in tcindex filter 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>
2014-05-19 19:15:49 +00:00
else
tcf_exts_change(&cr.exts, &e);
if (old_r && old_r != r) {
err = tcindex_filter_result_init(old_r);
if (err < 0) {
kfree(f);
goto errout_alloc;
}
}
oldp = p;
net_sched: fix an oops in tcindex filter 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>
2014-05-19 19:15:49 +00:00
r->res = cr.res;
rcu_assign_pointer(tp->root, cp);
if (r == &new_filter_result) {
struct tcindex_filter *nfp;
struct tcindex_filter __rcu **fp;
tcf_exts_change(&f->result.exts, &r->exts);
net_sched: fix a null pointer dereference in tcindex_set_parms() This patch fixes the following crash: [ 42.199159] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 [ 42.200027] IP: [<ffffffff817e3fc4>] tcindex_set_parms+0x45c/0x526 [ 42.200027] PGD d2319067 PUD d4ffe067 PMD 0 [ 42.200027] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC [ 42.200027] CPU: 0 PID: 541 Comm: tc Not tainted 3.17.0-rc4+ #603 [ 42.200027] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 42.200027] task: ffff8800d22d2670 ti: ffff8800ce790000 task.ti: ffff8800ce790000 [ 42.200027] RIP: 0010:[<ffffffff817e3fc4>] [<ffffffff817e3fc4>] tcindex_set_parms+0x45c/0x526 [ 42.200027] RSP: 0018:ffff8800ce793898 EFLAGS: 00010202 [ 42.200027] RAX: 0000000000000001 RBX: ffff8800d1786498 RCX: 0000000000000000 [ 42.200027] RDX: ffffffff82114ec8 RSI: ffffffff82114ec8 RDI: ffffffff82114ec8 [ 42.200027] RBP: ffff8800ce793958 R08: 00000000000080d0 R09: 0000000000000001 [ 42.200027] R10: ffff8800ce7939a0 R11: 0000000000000246 R12: ffff8800d017d238 [ 42.200027] R13: 0000000000000018 R14: ffff8800d017c6a0 R15: ffff8800d1786620 [ 42.200027] FS: 00007f4e24539740(0000) GS:ffff88011a600000(0000) knlGS:0000000000000000 [ 42.200027] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 42.200027] CR2: 0000000000000018 CR3: 00000000cff38000 CR4: 00000000000006f0 [ 42.200027] Stack: [ 42.200027] ffff8800ce0949f0 0000000000000000 0000000200000003 ffff880000000000 [ 42.200027] ffff8800ce7938b8 ffff8800ce7938b8 0000000600000007 0000000000000000 [ 42.200027] ffff8800ce7938d8 ffff8800ce7938d8 0000000600000007 ffff8800ce0949f0 [ 42.200027] Call Trace: [ 42.200027] [<ffffffff817e4169>] tcindex_change+0xdb/0xee [ 42.200027] [<ffffffff817c16ca>] tc_ctl_tfilter+0x44d/0x63f [ 42.200027] [<ffffffff8179d161>] rtnetlink_rcv_msg+0x181/0x194 [ 42.200027] [<ffffffff8179cf9d>] ? rtnl_lock+0x17/0x19 [ 42.200027] [<ffffffff8179cfe0>] ? __rtnl_unlock+0x17/0x17 [ 42.200027] [<ffffffff817ee296>] netlink_rcv_skb+0x49/0x8b [ 43.462494] [<ffffffff8179cfc2>] rtnetlink_rcv+0x23/0x2a [ 43.462494] [<ffffffff817ec8df>] netlink_unicast+0xc7/0x148 [ 43.462494] [<ffffffff817ed413>] netlink_sendmsg+0x5cb/0x63d [ 43.462494] [<ffffffff810ad781>] ? mark_lock+0x2e/0x224 [ 43.462494] [<ffffffff817757b8>] __sock_sendmsg_nosec+0x25/0x27 [ 43.462494] [<ffffffff81778165>] sock_sendmsg+0x57/0x71 [ 43.462494] [<ffffffff81152bbd>] ? might_fault+0x57/0xa4 [ 43.462494] [<ffffffff81152c06>] ? might_fault+0xa0/0xa4 [ 43.462494] [<ffffffff81152bbd>] ? might_fault+0x57/0xa4 [ 43.462494] [<ffffffff817838fd>] ? verify_iovec+0x69/0xb7 [ 43.462494] [<ffffffff817784f8>] ___sys_sendmsg+0x21d/0x2bb [ 43.462494] [<ffffffff81009db3>] ? native_sched_clock+0x35/0x37 [ 43.462494] [<ffffffff8109ab53>] ? sched_clock_local+0x12/0x72 [ 43.462494] [<ffffffff810ad781>] ? mark_lock+0x2e/0x224 [ 43.462494] [<ffffffff8109ada4>] ? sched_clock_cpu+0xa0/0xb9 [ 43.462494] [<ffffffff810aee37>] ? __lock_acquire+0x5fe/0xde4 [ 43.462494] [<ffffffff8119f570>] ? rcu_read_lock_held+0x36/0x38 [ 43.462494] [<ffffffff8119f75a>] ? __fcheck_files.isra.7+0x4b/0x57 [ 43.462494] [<ffffffff8119fbf2>] ? __fget_light+0x30/0x54 [ 43.462494] [<ffffffff81779012>] __sys_sendmsg+0x42/0x60 [ 43.462494] [<ffffffff81779042>] SyS_sendmsg+0x12/0x1c [ 43.462494] [<ffffffff819d24d2>] system_call_fastpath+0x16/0x1b 'p->h' could be NULL while 'cp->h' is always update to date. Fixes: commit 331b72922c5f58d48fd ("net: sched: RCU cls_tcindex") Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-By: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-15 23:43:43 +00:00
fp = cp->h + (handle % cp->hash);
for (nfp = rtnl_dereference(*fp);
nfp;
fp = &nfp->next, nfp = rtnl_dereference(*fp))
; /* nothing */
rcu_assign_pointer(*fp, f);
}
if (oldp)
call_rcu(&oldp->rcu, __tcindex_partial_destroy);
return 0;
errout_alloc:
if (balloc == 1)
tcindex_free_perfect_hash(cp);
else if (balloc == 2)
kfree(cp->h);
errout1:
tcf_exts_destroy(&cr.exts);
tcf_exts_destroy(&new_filter_result.exts);
errout:
kfree(cp);
tcf_exts_destroy(&e);
return err;
}
static int
tcindex_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca, void **arg, bool ovr)
{
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_TCINDEX_MAX + 1];
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r = *arg;
int err;
pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p,"
"p %p,r %p,*arg %p\n",
tp, handle, tca, arg, opt, p, r, arg ? *arg : NULL);
if (!opt)
return 0;
err = nla_parse_nested(tb, TCA_TCINDEX_MAX, opt, tcindex_policy, NULL);
if (err < 0)
return err;
return tcindex_set_parms(net, tp, base, handle, p, r, tb,
tca[TCA_RATE], ovr);
}
static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter *f, *next;
int i;
pr_debug("tcindex_walk(tp %p,walker %p),p %p\n", tp, walker, p);
if (p->perfect) {
for (i = 0; i < p->hash; i++) {
if (!p->perfect[i].res.class)
continue;
if (walker->count >= walker->skip) {
if (walker->fn(tp, p->perfect + i, walker) < 0) {
walker->stop = 1;
return;
}
}
walker->count++;
}
}
if (!p->h)
return;
for (i = 0; i < p->hash; i++) {
for (f = rtnl_dereference(p->h[i]); f; f = next) {
next = rtnl_dereference(f->next);
if (walker->count >= walker->skip) {
if (walker->fn(tp, &f->result, walker) < 0) {
walker->stop = 1;
return;
}
}
walker->count++;
}
}
}
static void tcindex_destroy(struct tcf_proto *tp)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcf_walker walker;
pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
walker.count = 0;
walker.skip = 0;
walker.fn = tcindex_destroy_element;
tcindex_walk(tp, &walker);
call_rcu(&p->rcu, __tcindex_destroy);
}
static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh,
struct sk_buff *skb, struct tcmsg *t)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r = fh;
struct nlattr *nest;
pr_debug("tcindex_dump(tp %p,fh %p,skb %p,t %p),p %p,r %p\n",
tp, fh, skb, t, p, r);
pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h);
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
if (!fh) {
t->tcm_handle = ~0; /* whatever ... */
if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) ||
nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) ||
nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) ||
nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through))
goto nla_put_failure;
nla_nest_end(skb, nest);
} else {
if (p->perfect) {
t->tcm_handle = r - p->perfect;
} else {
struct tcindex_filter *f;
struct tcindex_filter __rcu **fp;
int i;
t->tcm_handle = 0;
for (i = 0; !t->tcm_handle && i < p->hash; i++) {
fp = &p->h[i];
for (f = rtnl_dereference(*fp);
!t->tcm_handle && f;
fp = &f->next, f = rtnl_dereference(*fp)) {
if (&f->result == r)
t->tcm_handle = f->key;
}
}
}
pr_debug("handle = %d\n", t->tcm_handle);
if (r->res.class &&
nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid))
goto nla_put_failure;
if (tcf_exts_dump(skb, &r->exts) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
if (tcf_exts_dump_stats(skb, &r->exts) < 0)
goto nla_put_failure;
}
return skb->len;
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
}
static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl)
{
struct tcindex_filter_result *r = fh;
if (r && r->res.classid == classid)
r->res.class = cl;
}
static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
.kind = "tcindex",
.classify = tcindex_classify,
.init = tcindex_init,
.destroy = tcindex_destroy,
.get = tcindex_get,
.change = tcindex_change,
.delete = tcindex_delete,
.walk = tcindex_walk,
.dump = tcindex_dump,
.bind_class = tcindex_bind_class,
.owner = THIS_MODULE,
};
static int __init init_tcindex(void)
{
return register_tcf_proto_ops(&cls_tcindex_ops);
}
static void __exit exit_tcindex(void)
{
unregister_tcf_proto_ops(&cls_tcindex_ops);
}
module_init(init_tcindex)
module_exit(exit_tcindex)
MODULE_LICENSE("GPL");