linux_dsm_epyc7002/net/xfrm/xfrm_input.c

809 lines
18 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 21:07:57 +07:00
// SPDX-License-Identifier: GPL-2.0
/*
* xfrm_input.c
*
* Changes:
* YOSHIFUJI Hideaki @USAGI
* Split up af-specific portion
*
*/
#include <linux/bottom_half.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/percpu.h>
#include <net/dst.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/ip_tunnels.h>
#include <net/ip6_tunnel.h>
#include "xfrm_inout.h"
struct xfrm_trans_tasklet {
struct tasklet_struct tasklet;
struct sk_buff_head queue;
};
struct xfrm_trans_cb {
union {
struct inet_skb_parm h4;
#if IS_ENABLED(CONFIG_IPV6)
struct inet6_skb_parm h6;
#endif
} header;
int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb);
};
#define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0]))
static DEFINE_SPINLOCK(xfrm_input_afinfo_lock);
static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[AF_INET6 + 1];
static struct gro_cells gro_cells;
static struct net_device xfrm_napi_dev;
static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet);
int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo)
{
int err = 0;
if (WARN_ON(afinfo->family >= ARRAY_SIZE(xfrm_input_afinfo)))
return -EAFNOSUPPORT;
spin_lock_bh(&xfrm_input_afinfo_lock);
if (unlikely(xfrm_input_afinfo[afinfo->family] != NULL))
err = -EEXIST;
else
rcu_assign_pointer(xfrm_input_afinfo[afinfo->family], afinfo);
spin_unlock_bh(&xfrm_input_afinfo_lock);
return err;
}
EXPORT_SYMBOL(xfrm_input_register_afinfo);
int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo)
{
int err = 0;
spin_lock_bh(&xfrm_input_afinfo_lock);
if (likely(xfrm_input_afinfo[afinfo->family] != NULL)) {
if (unlikely(xfrm_input_afinfo[afinfo->family] != afinfo))
err = -EINVAL;
else
RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->family], NULL);
}
spin_unlock_bh(&xfrm_input_afinfo_lock);
synchronize_rcu();
return err;
}
EXPORT_SYMBOL(xfrm_input_unregister_afinfo);
static const struct xfrm_input_afinfo *xfrm_input_get_afinfo(unsigned int family)
{
const struct xfrm_input_afinfo *afinfo;
if (WARN_ON_ONCE(family >= ARRAY_SIZE(xfrm_input_afinfo)))
return NULL;
rcu_read_lock();
afinfo = rcu_dereference(xfrm_input_afinfo[family]);
if (unlikely(!afinfo))
rcu_read_unlock();
return afinfo;
}
static int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, u8 protocol,
int err)
{
int ret;
const struct xfrm_input_afinfo *afinfo = xfrm_input_get_afinfo(family);
if (!afinfo)
return -EAFNOSUPPORT;
ret = afinfo->callback(skb, protocol, err);
rcu_read_unlock();
return ret;
}
struct sec_path *secpath_set(struct sk_buff *skb)
{
struct sec_path *sp, *tmp = skb_ext_find(skb, SKB_EXT_SEC_PATH);
sp = skb_ext_add(skb, SKB_EXT_SEC_PATH);
if (!sp)
return NULL;
if (tmp) /* reused existing one (was COW'd if needed) */
return sp;
/* allocated new secpath */
memset(sp->ovec, 0, sizeof(sp->ovec));
sp->olen = 0;
sp->len = 0;
return sp;
}
EXPORT_SYMBOL(secpath_set);
/* Fetch spi and seq from ipsec header */
int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq)
{
int offset, offset_seq;
int hlen;
switch (nexthdr) {
case IPPROTO_AH:
hlen = sizeof(struct ip_auth_hdr);
offset = offsetof(struct ip_auth_hdr, spi);
offset_seq = offsetof(struct ip_auth_hdr, seq_no);
break;
case IPPROTO_ESP:
hlen = sizeof(struct ip_esp_hdr);
offset = offsetof(struct ip_esp_hdr, spi);
offset_seq = offsetof(struct ip_esp_hdr, seq_no);
break;
case IPPROTO_COMP:
if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr)))
return -EINVAL;
*spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2)));
*seq = 0;
return 0;
default:
return 1;
}
if (!pskb_may_pull(skb, hlen))
return -EINVAL;
*spi = *(__be32 *)(skb_transport_header(skb) + offset);
*seq = *(__be32 *)(skb_transport_header(skb) + offset_seq);
return 0;
}
EXPORT_SYMBOL(xfrm_parse_spi);
static int xfrm4_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb)
{
struct iphdr *iph;
int optlen = 0;
int err = -EINVAL;
if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) {
struct ip_beet_phdr *ph;
int phlen;
if (!pskb_may_pull(skb, sizeof(*ph)))
goto out;
ph = (struct ip_beet_phdr *)skb->data;
phlen = sizeof(*ph) + ph->padlen;
optlen = ph->hdrlen * 8 + (IPV4_BEET_PHMAXLEN - phlen);
if (optlen < 0 || optlen & 3 || optlen > 250)
goto out;
XFRM_MODE_SKB_CB(skb)->protocol = ph->nexthdr;
if (!pskb_may_pull(skb, phlen))
goto out;
__skb_pull(skb, phlen);
}
skb_push(skb, sizeof(*iph));
skb_reset_network_header(skb);
skb_mac_header_rebuild(skb);
xfrm4_beet_make_header(skb);
iph = ip_hdr(skb);
iph->ihl += optlen / 4;
iph->tot_len = htons(skb->len);
iph->daddr = x->sel.daddr.a4;
iph->saddr = x->sel.saddr.a4;
iph->check = 0;
iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
err = 0;
out:
return err;
}
static void ipip_ecn_decapsulate(struct sk_buff *skb)
{
struct iphdr *inner_iph = ipip_hdr(skb);
if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
IP_ECN_set_ce(inner_iph);
}
static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
{
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
goto out;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto out;
err = skb_unclone(skb, GFP_ATOMIC);
if (err)
goto out;
if (x->props.flags & XFRM_STATE_DECAP_DSCP)
ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipip_hdr(skb));
if (!(x->props.flags & XFRM_STATE_NOECN))
ipip_ecn_decapsulate(skb);
skb_reset_network_header(skb);
skb_mac_header_rebuild(skb);
if (skb->mac_len)
eth_hdr(skb)->h_proto = skb->protocol;
err = 0;
out:
return err;
}
static void ipip6_ecn_decapsulate(struct sk_buff *skb)
{
struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
IP6_ECN_set_ce(skb, inner_iph);
}
static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
{
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6)
goto out;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
err = skb_unclone(skb, GFP_ATOMIC);
if (err)
goto out;
if (x->props.flags & XFRM_STATE_DECAP_DSCP)
ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)),
ipipv6_hdr(skb));
if (!(x->props.flags & XFRM_STATE_NOECN))
ipip6_ecn_decapsulate(skb);
skb_reset_network_header(skb);
skb_mac_header_rebuild(skb);
if (skb->mac_len)
eth_hdr(skb)->h_proto = skb->protocol;
err = 0;
out:
return err;
}
static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb)
{
struct ipv6hdr *ip6h;
int size = sizeof(struct ipv6hdr);
int err;
err = skb_cow_head(skb, size + skb->mac_len);
if (err)
goto out;
__skb_push(skb, size);
skb_reset_network_header(skb);
skb_mac_header_rebuild(skb);
xfrm6_beet_make_header(skb);
ip6h = ipv6_hdr(skb);
ip6h->payload_len = htons(skb->len - size);
ip6h->daddr = x->sel.daddr.in6;
ip6h->saddr = x->sel.saddr.in6;
err = 0;
out:
return err;
}
/* Remove encapsulation header.
*
* The IP header will be moved over the top of the encapsulation
* header.
*
* On entry, the transport header shall point to where the IP header
* should be and the network header shall be set to where the IP
* header currently is. skb->data shall point to the start of the
* payload.
*/
static int
xfrm_inner_mode_encap_remove(struct xfrm_state *x,
const struct xfrm_mode *inner_mode,
struct sk_buff *skb)
{
switch (inner_mode->encap) {
case XFRM_MODE_BEET:
if (inner_mode->family == AF_INET)
return xfrm4_remove_beet_encap(x, skb);
if (inner_mode->family == AF_INET6)
return xfrm6_remove_beet_encap(x, skb);
break;
case XFRM_MODE_TUNNEL:
if (inner_mode->family == AF_INET)
return xfrm4_remove_tunnel_encap(x, skb);
if (inner_mode->family == AF_INET6)
return xfrm6_remove_tunnel_encap(x, skb);
break;
}
WARN_ON_ONCE(1);
return -EOPNOTSUPP;
}
static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
{
const struct xfrm_mode *inner_mode = &x->inner_mode;
const struct xfrm_state_afinfo *afinfo;
int err = -EAFNOSUPPORT;
rcu_read_lock();
afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode.family);
if (likely(afinfo))
err = afinfo->extract_input(x, skb);
rcu_read_unlock();
if (err)
return err;
if (x->sel.family == AF_UNSPEC) {
inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
if (!inner_mode)
return -EAFNOSUPPORT;
}
switch (inner_mode->family) {
case AF_INET:
skb->protocol = htons(ETH_P_IP);
break;
case AF_INET6:
skb->protocol = htons(ETH_P_IPV6);
break;
default:
WARN_ON_ONCE(1);
break;
}
return xfrm_inner_mode_encap_remove(x, inner_mode, skb);
}
/* Remove encapsulation header.
*
* The IP header will be moved over the top of the encapsulation header.
*
* On entry, skb_transport_header() shall point to where the IP header
* should be and skb_network_header() shall be set to where the IP header
* currently is. skb->data shall point to the start of the payload.
*/
static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
{
int ihl = skb->data - skb_transport_header(skb);
if (skb->transport_header != skb->network_header) {
memmove(skb_transport_header(skb),
skb_network_header(skb), ihl);
skb->network_header = skb->transport_header;
}
ip_hdr(skb)->tot_len = htons(skb->len + ihl);
skb_reset_transport_header(skb);
return 0;
}
static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_IPV6)
int ihl = skb->data - skb_transport_header(skb);
if (skb->transport_header != skb->network_header) {
memmove(skb_transport_header(skb),
skb_network_header(skb), ihl);
skb->network_header = skb->transport_header;
}
ipv6_hdr(skb)->payload_len = htons(skb->len + ihl -
sizeof(struct ipv6hdr));
skb_reset_transport_header(skb);
return 0;
#else
WARN_ON_ONCE(1);
return -EAFNOSUPPORT;
#endif
}
static int xfrm_inner_mode_input(struct xfrm_state *x,
const struct xfrm_mode *inner_mode,
struct sk_buff *skb)
{
switch (inner_mode->encap) {
case XFRM_MODE_BEET:
case XFRM_MODE_TUNNEL:
return xfrm_prepare_input(x, skb);
case XFRM_MODE_TRANSPORT:
if (inner_mode->family == AF_INET)
return xfrm4_transport_input(x, skb);
if (inner_mode->family == AF_INET6)
return xfrm6_transport_input(x, skb);
break;
case XFRM_MODE_ROUTEOPTIMIZATION:
WARN_ON_ONCE(1);
break;
default:
WARN_ON_ONCE(1);
break;
}
return -EOPNOTSUPP;
}
int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
{
const struct xfrm_state_afinfo *afinfo;
struct net *net = dev_net(skb->dev);
const struct xfrm_mode *inner_mode;
int err;
__be32 seq;
__be32 seq_hi;
struct xfrm_state *x = NULL;
xfrm_address_t *daddr;
u32 mark = skb->mark;
unsigned int family = AF_UNSPEC;
int decaps = 0;
int async = 0;
bool xfrm_gro = false;
bool crypto_done = false;
struct xfrm_offload *xo = xfrm_offload(skb);
struct sec_path *sp;
if (encap_type < 0) {
x = xfrm_input_state(skb);
if (unlikely(x->km.state != XFRM_STATE_VALID)) {
if (x->km.state == XFRM_STATE_ACQ)
XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
else
XFRM_INC_STATS(net,
LINUX_MIB_XFRMINSTATEINVALID);
xfrm: release device reference for invalid state An ESP packet could be decrypted in async mode if the input handler for this packet returns -EINPROGRESS in xfrm_input(). At this moment the device reference in skb is held. Later xfrm_input() will be invoked again to resume the processing. If the transform state is still valid it would continue to release the device reference and there won't be a problem; however if the transform state is not valid when async resumption happens, the packet will be dropped while the device reference is still being held. When the device is deleted for some reason and the reference to this device is not properly released, the kernel will keep logging like: unregister_netdevice: waiting for ppp2 to become free. Usage count = 1 The issue is observed when running IPsec traffic over a PPPoE device based on a bridge interface. By terminating the PPPoE connection on the server end for multiple times, the PPPoE device on the client side will eventually get stuck on the above warning message. This patch will check the async mode first and continue to release device reference in async resumption, before it is dropped due to invalid state. v2: Do not assign address family from outer_mode in the transform if the state is invalid v3: Release device reference in the error path instead of jumping to resume Fixes: 4ce3dbe397d7b ("xfrm: Fix xfrm_input() to verify state is valid when (encap_type < 0)") Signed-off-by: Xiaodong Xu <stid.smth@gmail.com> Reported-by: Bo Chen <chenborfc@163.com> Tested-by: Bo Chen <chenborfc@163.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2019-11-12 06:05:46 +07:00
if (encap_type == -1)
dev_put(skb->dev);
goto drop;
}
family = x->outer_mode.family;
/* An encap_type of -1 indicates async resumption. */
if (encap_type == -1) {
async = 1;
seq = XFRM_SKB_CB(skb)->seq.input.low;
goto resume;
}
/* encap_type < -1 indicates a GRO call. */
encap_type = 0;
seq = XFRM_SPI_SKB_CB(skb)->seq;
if (xo && (xo->flags & CRYPTO_DONE)) {
crypto_done = true;
family = XFRM_SPI_SKB_CB(skb)->family;
if (!(xo->status & CRYPTO_SUCCESS)) {
if (xo->status &
(CRYPTO_TRANSPORT_AH_AUTH_FAILED |
CRYPTO_TRANSPORT_ESP_AUTH_FAILED |
CRYPTO_TUNNEL_AH_AUTH_FAILED |
CRYPTO_TUNNEL_ESP_AUTH_FAILED)) {
xfrm_audit_state_icvfail(x, skb,
x->type->proto);
x->stats.integrity_failed++;
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR);
goto drop;
}
if (xo->status & CRYPTO_INVALID_PROTOCOL) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR);
goto drop;
}
XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
goto drop;
}
if ((err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
goto drop;
}
}
goto lock;
}
family = XFRM_SPI_SKB_CB(skb)->family;
/* if tunnel is present override skb->mark value with tunnel i_key */
switch (family) {
case AF_INET:
if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4)
mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key);
break;
case AF_INET6:
if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6)
mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key);
break;
}
sp = secpath_set(skb);
if (!sp) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR);
goto drop;
}
seq = 0;
if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) {
secpath_reset(skb);
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
goto drop;
}
daddr = (xfrm_address_t *)(skb_network_header(skb) +
XFRM_SPI_SKB_CB(skb)->daddroff);
do {
sp = skb_sec_path(skb);
if (sp->len == XFRM_MAX_DEPTH) {
secpath_reset(skb);
XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
goto drop;
}
x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family);
if (x == NULL) {
secpath_reset(skb);
XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
xfrm_audit_state_notfound(skb, family, spi, seq);
goto drop;
}
skb->mark = xfrm_smark_get(skb->mark, x);
sp->xvec[sp->len++] = x;
skb_dst_force(skb);
if (!skb_dst(skb)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR);
goto drop;
}
lock:
spin_lock(&x->lock);
if (unlikely(x->km.state != XFRM_STATE_VALID)) {
if (x->km.state == XFRM_STATE_ACQ)
XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
else
XFRM_INC_STATS(net,
LINUX_MIB_XFRMINSTATEINVALID);
goto drop_unlock;
}
if ((x->encap ? x->encap->encap_type : 0) != encap_type) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
goto drop_unlock;
}
if (x->repl->check(x, skb, seq)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
goto drop_unlock;
}
if (xfrm_state_check_expire(x)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEEXPIRED);
goto drop_unlock;
}
spin_unlock(&x->lock);
if (xfrm_tunnel_check(skb, x, family)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
goto drop;
}
seq_hi = htonl(xfrm_replay_seqhi(x, seq));
XFRM_SKB_CB(skb)->seq.input.low = seq;
XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
xfrm: Fix crash observed during device unregistration and decryption A crash is observed when a decrypted packet is processed in receive path. get_rps_cpus() tries to dereference the skb->dev fields but it appears that the device is freed from the poison pattern. [<ffffffc000af58ec>] get_rps_cpu+0x94/0x2f0 [<ffffffc000af5f94>] netif_rx_internal+0x140/0x1cc [<ffffffc000af6094>] netif_rx+0x74/0x94 [<ffffffc000bc0b6c>] xfrm_input+0x754/0x7d0 [<ffffffc000bc0bf8>] xfrm_input_resume+0x10/0x1c [<ffffffc000ba6eb8>] esp_input_done+0x20/0x30 [<ffffffc0000b64c8>] process_one_work+0x244/0x3fc [<ffffffc0000b7324>] worker_thread+0x2f8/0x418 [<ffffffc0000bb40c>] kthread+0xe0/0xec -013|get_rps_cpu( | dev = 0xFFFFFFC08B688000, | skb = 0xFFFFFFC0C76AAC00 -> ( | dev = 0xFFFFFFC08B688000 -> ( | name = "...................................................... | name_hlist = (next = 0xAAAAAAAAAAAAAAAA, pprev = 0xAAAAAAAAAAA Following are the sequence of events observed - - Encrypted packet in receive path from netdevice is queued - Encrypted packet queued for decryption (asynchronous) - Netdevice brought down and freed - Packet is decrypted and returned through callback in esp_input_done - Packet is queued again for process in network stack using netif_rx Since the device appears to have been freed, the dereference of skb->dev in get_rps_cpus() leads to an unhandled page fault exception. Fix this by holding on to device reference when queueing packets asynchronously and releasing the reference on call back return. v2: Make the change generic to xfrm as mentioned by Steffen and update the title to xfrm Suggested-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Jerome Stanislaus <jeromes@codeaurora.org> Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-24 11:39:50 +07:00
dev_hold(skb->dev);
if (crypto_done)
nexthdr = x->type_offload->input_tail(x, skb);
else
nexthdr = x->type->input(x, skb);
if (nexthdr == -EINPROGRESS)
return 0;
resume:
xfrm: Fix crash observed during device unregistration and decryption A crash is observed when a decrypted packet is processed in receive path. get_rps_cpus() tries to dereference the skb->dev fields but it appears that the device is freed from the poison pattern. [<ffffffc000af58ec>] get_rps_cpu+0x94/0x2f0 [<ffffffc000af5f94>] netif_rx_internal+0x140/0x1cc [<ffffffc000af6094>] netif_rx+0x74/0x94 [<ffffffc000bc0b6c>] xfrm_input+0x754/0x7d0 [<ffffffc000bc0bf8>] xfrm_input_resume+0x10/0x1c [<ffffffc000ba6eb8>] esp_input_done+0x20/0x30 [<ffffffc0000b64c8>] process_one_work+0x244/0x3fc [<ffffffc0000b7324>] worker_thread+0x2f8/0x418 [<ffffffc0000bb40c>] kthread+0xe0/0xec -013|get_rps_cpu( | dev = 0xFFFFFFC08B688000, | skb = 0xFFFFFFC0C76AAC00 -> ( | dev = 0xFFFFFFC08B688000 -> ( | name = "...................................................... | name_hlist = (next = 0xAAAAAAAAAAAAAAAA, pprev = 0xAAAAAAAAAAA Following are the sequence of events observed - - Encrypted packet in receive path from netdevice is queued - Encrypted packet queued for decryption (asynchronous) - Netdevice brought down and freed - Packet is decrypted and returned through callback in esp_input_done - Packet is queued again for process in network stack using netif_rx Since the device appears to have been freed, the dereference of skb->dev in get_rps_cpus() leads to an unhandled page fault exception. Fix this by holding on to device reference when queueing packets asynchronously and releasing the reference on call back return. v2: Make the change generic to xfrm as mentioned by Steffen and update the title to xfrm Suggested-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Jerome Stanislaus <jeromes@codeaurora.org> Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-24 11:39:50 +07:00
dev_put(skb->dev);
spin_lock(&x->lock);
if (nexthdr <= 0) {
if (nexthdr == -EBADMSG) {
xfrm_audit_state_icvfail(x, skb,
x->type->proto);
x->stats.integrity_failed++;
}
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR);
goto drop_unlock;
}
/* only the first xfrm gets the encap type */
encap_type = 0;
if (async && x->repl->recheck(x, skb, seq)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
goto drop_unlock;
}
x->repl->advance(x, seq);
x->curlft.bytes += skb->len;
x->curlft.packets++;
spin_unlock(&x->lock);
XFRM_MODE_SKB_CB(skb)->protocol = nexthdr;
inner_mode = &x->inner_mode;
if (x->sel.family == AF_UNSPEC) {
inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
if (inner_mode == NULL) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
goto drop;
}
}
if (xfrm_inner_mode_input(x, inner_mode, skb)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
goto drop;
}
if (x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL) {
decaps = 1;
break;
}
/*
* We need the inner address. However, we only get here for
* transport mode so the outer address is identical.
*/
daddr = &x->id.daddr;
family = x->outer_mode.family;
err = xfrm_parse_spi(skb, nexthdr, &spi, &seq);
if (err < 0) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
goto drop;
}
crypto_done = false;
} while (!err);
err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
if (err)
goto drop;
nf_reset_ct(skb);
if (decaps) {
sp = skb_sec_path(skb);
if (sp)
sp->olen = 0;
skb_dst_drop(skb);
gro_cells_receive(&gro_cells, skb);
return 0;
} else {
xo = xfrm_offload(skb);
if (xo)
xfrm_gro = xo->flags & XFRM_GRO;
err = -EAFNOSUPPORT;
rcu_read_lock();
afinfo = xfrm_state_afinfo_get_rcu(x->inner_mode.family);
if (likely(afinfo))
err = afinfo->transport_finish(skb, xfrm_gro || async);
rcu_read_unlock();
if (xfrm_gro) {
sp = skb_sec_path(skb);
if (sp)
sp->olen = 0;
skb_dst_drop(skb);
gro_cells_receive(&gro_cells, skb);
return err;
}
return err;
}
drop_unlock:
spin_unlock(&x->lock);
drop:
xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1);
kfree_skb(skb);
return 0;
}
EXPORT_SYMBOL(xfrm_input);
int xfrm_input_resume(struct sk_buff *skb, int nexthdr)
{
return xfrm_input(skb, nexthdr, 0, -1);
}
EXPORT_SYMBOL(xfrm_input_resume);
static void xfrm_trans_reinject(unsigned long data)
{
struct xfrm_trans_tasklet *trans = (void *)data;
struct sk_buff_head queue;
struct sk_buff *skb;
__skb_queue_head_init(&queue);
skb_queue_splice_init(&trans->queue, &queue);
while ((skb = __skb_dequeue(&queue)))
XFRM_TRANS_SKB_CB(skb)->finish(dev_net(skb->dev), NULL, skb);
}
int xfrm_trans_queue(struct sk_buff *skb,
int (*finish)(struct net *, struct sock *,
struct sk_buff *))
{
struct xfrm_trans_tasklet *trans;
trans = this_cpu_ptr(&xfrm_trans_tasklet);
if (skb_queue_len(&trans->queue) >= netdev_max_backlog)
return -ENOBUFS;
XFRM_TRANS_SKB_CB(skb)->finish = finish;
__skb_queue_tail(&trans->queue, skb);
tasklet_schedule(&trans->tasklet);
return 0;
}
EXPORT_SYMBOL(xfrm_trans_queue);
void __init xfrm_input_init(void)
{
int err;
int i;
init_dummy_netdev(&xfrm_napi_dev);
err = gro_cells_init(&gro_cells, &xfrm_napi_dev);
if (err)
gro_cells.cells = NULL;
for_each_possible_cpu(i) {
struct xfrm_trans_tasklet *trans;
trans = &per_cpu(xfrm_trans_tasklet, i);
__skb_queue_head_init(&trans->queue);
tasklet_init(&trans->tasklet, xfrm_trans_reinject,
(unsigned long)trans);
}
}