linux/net/sched/sch_dsmark.c

525 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/* net/sched/sch_dsmark.c - Differentiated Services field marker */
/* Written 1998-2000 by Werner Almesberger, EPFL ICA */
#include <linux/module.h>
#include <linux/init.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 <linux/types.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/bitops.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <asm/byteorder.h>
/*
* classid class marking
* ------- ----- -------
* n/a 0 n/a
* x:0 1 use entry [0]
* ... ... ...
* x:y y>0 y+1 use entry [y]
* ... ... ...
* x:indices-1 indices use entry [indices-1]
* ... ... ...
* x:y y+1 use entry [y & (indices-1)]
* ... ... ...
* 0xffff 0x10000 use entry [indices-1]
*/
#define NO_DEFAULT_INDEX (1 << 16)
struct mask_value {
u8 mask;
u8 value;
};
struct dsmark_qdisc_data {
struct Qdisc *q;
struct tcf_proto __rcu *filter_list;
struct tcf_block *block;
struct mask_value *mv;
u16 indices;
u8 set_tc_index;
u32 default_index; /* index range is 0...0xffff */
#define DSMARK_EMBEDDED_SZ 16
struct mask_value embedded[DSMARK_EMBEDDED_SZ];
};
static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index)
{
return index <= p->indices && index > 0;
}
/* ------------------------- Class/flow operations ------------------------- */
static int dsmark_graft(struct Qdisc *sch, unsigned long arg,
struct Qdisc *new, struct Qdisc **old,
struct netlink_ext_ack *extack)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n",
__func__, sch, p, new, old);
if (new == NULL) {
new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
sch->handle, NULL);
if (new == NULL)
new = &noop_qdisc;
}
*old = qdisc_replace(sch, new, &p->q);
return 0;
}
static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
return p->q;
}
static unsigned long dsmark_find(struct Qdisc *sch, u32 classid)
{
return TC_H_MIN(classid) + 1;
}
static unsigned long dsmark_bind_filter(struct Qdisc *sch,
unsigned long parent, u32 classid)
{
pr_debug("%s(sch %p,[qdisc %p],classid %x)\n",
__func__, sch, qdisc_priv(sch), classid);
return dsmark_find(sch, classid);
}
static void dsmark_unbind_filter(struct Qdisc *sch, unsigned long cl)
{
}
static const struct nla_policy dsmark_policy[TCA_DSMARK_MAX + 1] = {
[TCA_DSMARK_INDICES] = { .type = NLA_U16 },
[TCA_DSMARK_DEFAULT_INDEX] = { .type = NLA_U16 },
[TCA_DSMARK_SET_TC_INDEX] = { .type = NLA_FLAG },
[TCA_DSMARK_MASK] = { .type = NLA_U8 },
[TCA_DSMARK_VALUE] = { .type = NLA_U8 },
};
static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent,
struct nlattr **tca, unsigned long *arg,
struct netlink_ext_ack *extack)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_DSMARK_MAX + 1];
int err = -EINVAL;
pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n",
__func__, sch, p, classid, parent, *arg);
if (!dsmark_valid_index(p, *arg)) {
err = -ENOENT;
goto errout;
}
if (!opt)
goto errout;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt,
dsmark_policy, NULL);
if (err < 0)
goto errout;
if (tb[TCA_DSMARK_VALUE])
p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]);
if (tb[TCA_DSMARK_MASK])
p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]);
err = 0;
errout:
return err;
}
static int dsmark_delete(struct Qdisc *sch, unsigned long arg,
struct netlink_ext_ack *extack)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
if (!dsmark_valid_index(p, arg))
return -EINVAL;
p->mv[arg - 1].mask = 0xff;
p->mv[arg - 1].value = 0;
return 0;
}
static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
int i;
pr_debug("%s(sch %p,[qdisc %p],walker %p)\n",
__func__, sch, p, walker);
if (walker->stop)
return;
for (i = 0; i < p->indices; i++) {
if (p->mv[i].mask == 0xff && !p->mv[i].value)
goto ignore;
if (walker->count >= walker->skip) {
if (walker->fn(sch, i + 1, walker) < 0) {
walker->stop = 1;
break;
}
}
ignore:
walker->count++;
}
}
static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl,
struct netlink_ext_ack *extack)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
return p->block;
}
/* --------------------------- Qdisc operations ---------------------------- */
static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
unsigned int len = qdisc_pkt_len(skb);
struct dsmark_qdisc_data *p = qdisc_priv(sch);
int err;
pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p);
if (p->set_tc_index) {
int wlen = skb_network_offset(skb);
sched: consistently handle layer3 header accesses in the presence of VLANs There are a couple of places in net/sched/ that check skb->protocol and act on the value there. However, in the presence of VLAN tags, the value stored in skb->protocol can be inconsistent based on whether VLAN acceleration is enabled. The commit quoted in the Fixes tag below fixed the users of skb->protocol to use a helper that will always see the VLAN ethertype. However, most of the callers don't actually handle the VLAN ethertype, but expect to find the IP header type in the protocol field. This means that things like changing the ECN field, or parsing diffserv values, stops working if there's a VLAN tag, or if there are multiple nested VLAN tags (QinQ). To fix this, change the helper to take an argument that indicates whether the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we make sure to skip all of them, so behaviour is consistent even in QinQ mode. To make the helper usable from the ECN code, move it to if_vlan.h instead of pkt_sched.h. v3: - Remove empty lines - Move vlan variable definitions inside loop in skb_protocol() - Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and bpf_skb_ecn_set_ce() v2: - Use eth_type_vlan() helper in skb_protocol() - Also fix code that reads skb->protocol directly - Change a couple of 'if/else if' statements to switch constructs to avoid calling the helper twice Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com> Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path") Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-03 20:26:43 +00:00
switch (skb_protocol(skb, true)) {
case htons(ETH_P_IP):
wlen += sizeof(struct iphdr);
if (!pskb_may_pull(skb, wlen) ||
skb_try_make_writable(skb, wlen))
goto drop;
skb->tc_index = ipv4_get_dsfield(ip_hdr(skb))
& ~INET_ECN_MASK;
break;
case htons(ETH_P_IPV6):
wlen += sizeof(struct ipv6hdr);
if (!pskb_may_pull(skb, wlen) ||
skb_try_make_writable(skb, wlen))
goto drop;
skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb))
& ~INET_ECN_MASK;
break;
default:
skb->tc_index = 0;
break;
}
}
if (TC_H_MAJ(skb->priority) == sch->handle)
skb->tc_index = TC_H_MIN(skb->priority);
else {
struct tcf_result res;
struct tcf_proto *fl = rcu_dereference_bh(p->filter_list);
int result = tcf_classify(skb, NULL, fl, &res, false);
pr_debug("result %d class 0x%04x\n", result, res.classid);
switch (result) {
#ifdef CONFIG_NET_CLS_ACT
case TC_ACT_QUEUED:
case TC_ACT_STOLEN:
case TC_ACT_TRAP:
__qdisc_drop(skb, to_free);
return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
case TC_ACT_SHOT:
goto drop;
#endif
case TC_ACT_OK:
skb->tc_index = TC_H_MIN(res.classid);
break;
default:
if (p->default_index != NO_DEFAULT_INDEX)
skb->tc_index = p->default_index;
break;
}
}
err = qdisc_enqueue(skb, p->q, to_free);
if (err != NET_XMIT_SUCCESS) {
if (net_xmit_drop_count(err))
qdisc_qstats_drop(sch);
return err;
}
sch->qstats.backlog += len;
sch->q.qlen++;
return NET_XMIT_SUCCESS;
drop:
qdisc_drop(skb, sch, to_free);
return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
}
static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
struct sk_buff *skb;
u32 index;
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
skb = qdisc_dequeue_peeked(p->q);
if (skb == NULL)
return NULL;
qdisc_bstats_update(sch, skb);
qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
index = skb->tc_index & (p->indices - 1);
pr_debug("index %d->%d\n", skb->tc_index, index);
sched: consistently handle layer3 header accesses in the presence of VLANs There are a couple of places in net/sched/ that check skb->protocol and act on the value there. However, in the presence of VLAN tags, the value stored in skb->protocol can be inconsistent based on whether VLAN acceleration is enabled. The commit quoted in the Fixes tag below fixed the users of skb->protocol to use a helper that will always see the VLAN ethertype. However, most of the callers don't actually handle the VLAN ethertype, but expect to find the IP header type in the protocol field. This means that things like changing the ECN field, or parsing diffserv values, stops working if there's a VLAN tag, or if there are multiple nested VLAN tags (QinQ). To fix this, change the helper to take an argument that indicates whether the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we make sure to skip all of them, so behaviour is consistent even in QinQ mode. To make the helper usable from the ECN code, move it to if_vlan.h instead of pkt_sched.h. v3: - Remove empty lines - Move vlan variable definitions inside loop in skb_protocol() - Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and bpf_skb_ecn_set_ce() v2: - Use eth_type_vlan() helper in skb_protocol() - Also fix code that reads skb->protocol directly - Change a couple of 'if/else if' statements to switch constructs to avoid calling the helper twice Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com> Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path") Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-03 20:26:43 +00:00
switch (skb_protocol(skb, true)) {
case htons(ETH_P_IP):
ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask,
p->mv[index].value);
break;
case htons(ETH_P_IPV6):
ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask,
p->mv[index].value);
break;
default:
/*
* Only complain if a change was actually attempted.
* This way, we can send non-IP traffic through dsmark
* and don't need yet another qdisc as a bypass.
*/
if (p->mv[index].mask != 0xff || p->mv[index].value)
pr_warn("%s: unsupported protocol %d\n",
sched: consistently handle layer3 header accesses in the presence of VLANs There are a couple of places in net/sched/ that check skb->protocol and act on the value there. However, in the presence of VLAN tags, the value stored in skb->protocol can be inconsistent based on whether VLAN acceleration is enabled. The commit quoted in the Fixes tag below fixed the users of skb->protocol to use a helper that will always see the VLAN ethertype. However, most of the callers don't actually handle the VLAN ethertype, but expect to find the IP header type in the protocol field. This means that things like changing the ECN field, or parsing diffserv values, stops working if there's a VLAN tag, or if there are multiple nested VLAN tags (QinQ). To fix this, change the helper to take an argument that indicates whether the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we make sure to skip all of them, so behaviour is consistent even in QinQ mode. To make the helper usable from the ECN code, move it to if_vlan.h instead of pkt_sched.h. v3: - Remove empty lines - Move vlan variable definitions inside loop in skb_protocol() - Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and bpf_skb_ecn_set_ce() v2: - Use eth_type_vlan() helper in skb_protocol() - Also fix code that reads skb->protocol directly - Change a couple of 'if/else if' statements to switch constructs to avoid calling the helper twice Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com> Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path") Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-03 20:26:43 +00:00
__func__, ntohs(skb_protocol(skb, true)));
break;
}
return skb;
}
static struct sk_buff *dsmark_peek(struct Qdisc *sch)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
return p->q->ops->peek(p->q);
}
static int dsmark_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
struct nlattr *tb[TCA_DSMARK_MAX + 1];
int err = -EINVAL;
u32 default_index = NO_DEFAULT_INDEX;
u16 indices;
int i;
pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt);
if (!opt)
goto errout;
err = tcf_block_get(&p->block, &p->filter_list, sch, extack);
if (err)
return err;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt,
dsmark_policy, NULL);
if (err < 0)
goto errout;
err = -EINVAL;
sch_dsmark: fix potential NULL deref in dsmark_init() Make sure TCA_DSMARK_INDICES was provided by the user. syzbot reported : kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 8799 Comm: syz-executor235 Not tainted 5.3.0+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:nla_get_u16 include/net/netlink.h:1501 [inline] RIP: 0010:dsmark_init net/sched/sch_dsmark.c:364 [inline] RIP: 0010:dsmark_init+0x193/0x640 net/sched/sch_dsmark.c:339 Code: 85 db 58 0f 88 7d 03 00 00 e8 e9 1a ac fb 48 8b 9d 70 ff ff ff 48 b8 00 00 00 00 00 fc ff df 48 8d 7b 04 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 01 38 d0 7c 08 84 d2 0f 85 ca RSP: 0018:ffff88809426f3b8 EFLAGS: 00010247 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff85c6eb09 RDX: 0000000000000000 RSI: ffffffff85c6eb17 RDI: 0000000000000004 RBP: ffff88809426f4b0 R08: ffff88808c4085c0 R09: ffffed1015d26159 R10: ffffed1015d26158 R11: ffff8880ae930ac7 R12: ffff8880a7e96940 R13: dffffc0000000000 R14: ffff88809426f8c0 R15: 0000000000000000 FS: 0000000001292880(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000080 CR3: 000000008ca1b000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: qdisc_create+0x4ee/0x1210 net/sched/sch_api.c:1237 tc_modify_qdisc+0x524/0x1c50 net/sched/sch_api.c:1653 rtnetlink_rcv_msg+0x463/0xb00 net/core/rtnetlink.c:5223 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5241 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline] netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328 netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:657 ___sys_sendmsg+0x803/0x920 net/socket.c:2311 __sys_sendmsg+0x105/0x1d0 net/socket.c:2356 __do_sys_sendmsg net/socket.c:2365 [inline] __se_sys_sendmsg net/socket.c:2363 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2363 do_syscall_64+0xfa/0x760 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x440369 Fixes: 758cc43c6d73 ("[PKT_SCHED]: Fix dsmark to apply changes consistent") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-04 17:34:45 +00:00
if (!tb[TCA_DSMARK_INDICES])
goto errout;
indices = nla_get_u16(tb[TCA_DSMARK_INDICES]);
if (hweight32(indices) != 1)
goto errout;
if (tb[TCA_DSMARK_DEFAULT_INDEX])
default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]);
if (indices <= DSMARK_EMBEDDED_SZ)
p->mv = p->embedded;
else
p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL);
if (!p->mv) {
err = -ENOMEM;
goto errout;
}
for (i = 0; i < indices; i++) {
p->mv[i].mask = 0xff;
p->mv[i].value = 0;
}
p->indices = indices;
p->default_index = default_index;
p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]);
p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle,
NULL);
if (p->q == NULL)
p->q = &noop_qdisc;
else
qdisc_hash_add(p->q, true);
pr_debug("%s: qdisc %p\n", __func__, p->q);
err = 0;
errout:
return err;
}
static void dsmark_reset(struct Qdisc *sch)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
sch_dsmark: fix a NULL deref in qdisc_reset() If Qdisc_ops->init() is failed, Qdisc_ops->reset() would be called. When dsmark_init(Qdisc_ops->init()) is failed, it possibly doesn't initialize dsmark_qdisc_data->q. But dsmark_reset(Qdisc_ops->reset()) uses dsmark_qdisc_data->q pointer wihtout any null checking. So, panic would occur. Test commands: sysctl net.core.default_qdisc=dsmark -w ip link add dummy0 type dummy ip link add vw0 link dummy0 type virt_wifi ip link set vw0 up Splat looks like: KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] CPU: 3 PID: 684 Comm: ip Not tainted 5.12.0+ #910 RIP: 0010:qdisc_reset+0x2b/0x680 Code: 1f 44 00 00 48 b8 00 00 00 00 00 fc ff df 41 57 41 56 41 55 41 54 55 48 89 fd 48 83 c7 18 53 48 89 fa 48 c1 ea 03 48 83 ec 20 <80> 3c 02 00 0f 85 09 06 00 00 4c 8b 65 18 0f 1f 44 00 00 65 8b 1d RSP: 0018:ffff88800fda6bf8 EFLAGS: 00010282 RAX: dffffc0000000000 RBX: ffff8880050ed800 RCX: 0000000000000000 RDX: 0000000000000003 RSI: ffffffff99e34100 RDI: 0000000000000018 RBP: 0000000000000000 R08: fffffbfff346b553 R09: fffffbfff346b553 R10: 0000000000000001 R11: fffffbfff346b552 R12: ffffffffc0824940 R13: ffff888109e83800 R14: 00000000ffffffff R15: ffffffffc08249e0 FS: 00007f5042287680(0000) GS:ffff888119800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055ae1f4dbd90 CR3: 0000000006760002 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? rcu_read_lock_bh_held+0xa0/0xa0 dsmark_reset+0x3d/0xf0 [sch_dsmark] qdisc_reset+0xa9/0x680 qdisc_destroy+0x84/0x370 qdisc_create_dflt+0x1fe/0x380 attach_one_default_qdisc.constprop.41+0xa4/0x180 dev_activate+0x4d5/0x8c0 ? __dev_open+0x268/0x390 __dev_open+0x270/0x390 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Taehee Yoo <ap420073@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-05-23 14:38:53 +00:00
if (p->q)
qdisc_reset(p->q);
sch->qstats.backlog = 0;
sch->q.qlen = 0;
}
static void dsmark_destroy(struct Qdisc *sch)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
tcf_block_put(p->block);
qdisc_put(p->q);
if (p->mv != p->embedded)
kfree(p->mv);
}
static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl,
struct sk_buff *skb, struct tcmsg *tcm)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
struct nlattr *opts = NULL;
pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl);
if (!dsmark_valid_index(p, cl))
return -EINVAL;
tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1);
tcm->tcm_info = p->q->handle;
opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (opts == NULL)
goto nla_put_failure;
if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) ||
nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value))
goto nla_put_failure;
return nla_nest_end(skb, opts);
nla_put_failure:
nla_nest_cancel(skb, opts);
return -EMSGSIZE;
}
static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
struct nlattr *opts = NULL;
opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (opts == NULL)
goto nla_put_failure;
if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices))
goto nla_put_failure;
if (p->default_index != NO_DEFAULT_INDEX &&
nla_put_u16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index))
goto nla_put_failure;
if (p->set_tc_index &&
nla_put_flag(skb, TCA_DSMARK_SET_TC_INDEX))
goto nla_put_failure;
return nla_nest_end(skb, opts);
nla_put_failure:
nla_nest_cancel(skb, opts);
return -EMSGSIZE;
}
static const struct Qdisc_class_ops dsmark_class_ops = {
.graft = dsmark_graft,
.leaf = dsmark_leaf,
.find = dsmark_find,
.change = dsmark_change,
.delete = dsmark_delete,
.walk = dsmark_walk,
.tcf_block = dsmark_tcf_block,
.bind_tcf = dsmark_bind_filter,
.unbind_tcf = dsmark_unbind_filter,
.dump = dsmark_dump_class,
};
static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = {
.next = NULL,
.cl_ops = &dsmark_class_ops,
.id = "dsmark",
.priv_size = sizeof(struct dsmark_qdisc_data),
.enqueue = dsmark_enqueue,
.dequeue = dsmark_dequeue,
.peek = dsmark_peek,
.init = dsmark_init,
.reset = dsmark_reset,
.destroy = dsmark_destroy,
.change = NULL,
.dump = dsmark_dump,
.owner = THIS_MODULE,
};
static int __init dsmark_module_init(void)
{
return register_qdisc(&dsmark_qdisc_ops);
}
static void __exit dsmark_module_exit(void)
{
unregister_qdisc(&dsmark_qdisc_ops);
}
module_init(dsmark_module_init)
module_exit(dsmark_module_exit)
MODULE_LICENSE("GPL");