OpenCloudOS-Kernel/net/xfrm/xfrm_user.c

3651 lines
84 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/* xfrm_user.c: User interface to configure xfrm engine.
*
* Copyright (C) 2002 David S. Miller (davem@redhat.com)
*
* Changes:
* Mitsuru KANDA @USAGI
* Kazunori MIYAZAWA @USAGI
* Kunihiro Ishiguro <kunihiro@ipinfusion.com>
* IPv6 support
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
*
*/
#include <linux/compat.h>
#include <linux/crypto.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/socket.h>
#include <linux/string.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/pfkeyv2.h>
#include <linux/ipsec.h>
#include <linux/init.h>
#include <linux/security.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <net/netlink.h>
#include <net/ah.h>
#include <linux/uaccess.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <linux/in6.h>
#endif
#include <asm/unaligned.h>
static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type)
{
struct nlattr *rt = attrs[type];
struct xfrm_algo *algp;
if (!rt)
return 0;
algp = nla_data(rt);
if (nla_len(rt) < (int)xfrm_alg_len(algp))
return -EINVAL;
switch (type) {
case XFRMA_ALG_AUTH:
case XFRMA_ALG_CRYPT:
case XFRMA_ALG_COMP:
break;
default:
return -EINVAL;
}
algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
return 0;
}
static int verify_auth_trunc(struct nlattr **attrs)
{
struct nlattr *rt = attrs[XFRMA_ALG_AUTH_TRUNC];
struct xfrm_algo_auth *algp;
if (!rt)
return 0;
algp = nla_data(rt);
if (nla_len(rt) < (int)xfrm_alg_auth_len(algp))
return -EINVAL;
algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
return 0;
}
static int verify_aead(struct nlattr **attrs)
{
struct nlattr *rt = attrs[XFRMA_ALG_AEAD];
struct xfrm_algo_aead *algp;
if (!rt)
return 0;
algp = nla_data(rt);
if (nla_len(rt) < (int)aead_len(algp))
return -EINVAL;
algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
return 0;
}
static void verify_one_addr(struct nlattr **attrs, enum xfrm_attr_type_t type,
xfrm_address_t **addrp)
{
struct nlattr *rt = attrs[type];
if (rt && addrp)
*addrp = nla_data(rt);
}
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
static inline int verify_sec_ctx_len(struct nlattr **attrs)
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
{
struct nlattr *rt = attrs[XFRMA_SEC_CTX];
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
struct xfrm_user_sec_ctx *uctx;
if (!rt)
return 0;
uctx = nla_data(rt);
if (uctx->len > nla_len(rt) ||
uctx->len != (sizeof(struct xfrm_user_sec_ctx) + uctx->ctx_len))
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
return -EINVAL;
return 0;
}
static inline int verify_replay(struct xfrm_usersa_info *p,
struct nlattr **attrs)
{
struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL];
xfrm_user: ensure user supplied esn replay window is valid The current code fails to ensure that the netlink message actually contains as many bytes as the header indicates. If a user creates a new state or updates an existing one but does not supply the bytes for the whole ESN replay window, the kernel copies random heap bytes into the replay bitmap, the ones happen to follow the XFRMA_REPLAY_ESN_VAL netlink attribute. This leads to following issues: 1. The replay window has random bits set confusing the replay handling code later on. 2. A malicious user could use this flaw to leak up to ~3.5kB of heap memory when she has access to the XFRM netlink interface (requires CAP_NET_ADMIN). Known users of the ESN replay window are strongSwan and Steffen's iproute2 patch (<http://patchwork.ozlabs.org/patch/85962/>). The latter uses the interface with a bitmap supplied while the former does not. strongSwan is therefore prone to run into issue 1. To fix both issues without breaking existing userland allow using the XFRMA_REPLAY_ESN_VAL netlink attribute with either an empty bitmap or a fully specified one. For the former case we initialize the in-kernel bitmap with zero, for the latter we copy the user supplied bitmap. For state updates the full bitmap must be supplied. To prevent overflows in the bitmap length calculation the maximum size of bmp_len is limited to 128 by this patch -- resulting in a maximum replay window of 4096 packets. This should be sufficient for all real life scenarios (RFC 4303 recommends a default replay window size of 64). Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Martin Willi <martin@revosec.ch> Cc: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: Mathias Krause <minipli@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-20 18:01:49 +08:00
struct xfrm_replay_state_esn *rs;
if (!rt)
return (p->flags & XFRM_STATE_ESN) ? -EINVAL : 0;
xfrm_user: ensure user supplied esn replay window is valid The current code fails to ensure that the netlink message actually contains as many bytes as the header indicates. If a user creates a new state or updates an existing one but does not supply the bytes for the whole ESN replay window, the kernel copies random heap bytes into the replay bitmap, the ones happen to follow the XFRMA_REPLAY_ESN_VAL netlink attribute. This leads to following issues: 1. The replay window has random bits set confusing the replay handling code later on. 2. A malicious user could use this flaw to leak up to ~3.5kB of heap memory when she has access to the XFRM netlink interface (requires CAP_NET_ADMIN). Known users of the ESN replay window are strongSwan and Steffen's iproute2 patch (<http://patchwork.ozlabs.org/patch/85962/>). The latter uses the interface with a bitmap supplied while the former does not. strongSwan is therefore prone to run into issue 1. To fix both issues without breaking existing userland allow using the XFRMA_REPLAY_ESN_VAL netlink attribute with either an empty bitmap or a fully specified one. For the former case we initialize the in-kernel bitmap with zero, for the latter we copy the user supplied bitmap. For state updates the full bitmap must be supplied. To prevent overflows in the bitmap length calculation the maximum size of bmp_len is limited to 128 by this patch -- resulting in a maximum replay window of 4096 packets. This should be sufficient for all real life scenarios (RFC 4303 recommends a default replay window size of 64). Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Martin Willi <martin@revosec.ch> Cc: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: Mathias Krause <minipli@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-20 18:01:49 +08:00
rs = nla_data(rt);
xfrm_user: ensure user supplied esn replay window is valid The current code fails to ensure that the netlink message actually contains as many bytes as the header indicates. If a user creates a new state or updates an existing one but does not supply the bytes for the whole ESN replay window, the kernel copies random heap bytes into the replay bitmap, the ones happen to follow the XFRMA_REPLAY_ESN_VAL netlink attribute. This leads to following issues: 1. The replay window has random bits set confusing the replay handling code later on. 2. A malicious user could use this flaw to leak up to ~3.5kB of heap memory when she has access to the XFRM netlink interface (requires CAP_NET_ADMIN). Known users of the ESN replay window are strongSwan and Steffen's iproute2 patch (<http://patchwork.ozlabs.org/patch/85962/>). The latter uses the interface with a bitmap supplied while the former does not. strongSwan is therefore prone to run into issue 1. To fix both issues without breaking existing userland allow using the XFRMA_REPLAY_ESN_VAL netlink attribute with either an empty bitmap or a fully specified one. For the former case we initialize the in-kernel bitmap with zero, for the latter we copy the user supplied bitmap. For state updates the full bitmap must be supplied. To prevent overflows in the bitmap length calculation the maximum size of bmp_len is limited to 128 by this patch -- resulting in a maximum replay window of 4096 packets. This should be sufficient for all real life scenarios (RFC 4303 recommends a default replay window size of 64). Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Martin Willi <martin@revosec.ch> Cc: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: Mathias Krause <minipli@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-20 18:01:49 +08:00
if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8)
return -EINVAL;
if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) &&
nla_len(rt) != sizeof(*rs))
return -EINVAL;
/* As only ESP and AH support ESN feature. */
if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH))
return -EINVAL;
if (p->replay_window != 0)
return -EINVAL;
return 0;
}
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
static int verify_newsa_info(struct xfrm_usersa_info *p,
struct nlattr **attrs)
{
int err;
err = -EINVAL;
switch (p->family) {
case AF_INET:
break;
case AF_INET6:
#if IS_ENABLED(CONFIG_IPV6)
break;
#else
err = -EAFNOSUPPORT;
goto out;
#endif
default:
goto out;
}
switch (p->sel.family) {
case AF_UNSPEC:
break;
case AF_INET:
if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
goto out;
break;
case AF_INET6:
#if IS_ENABLED(CONFIG_IPV6)
if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128)
goto out;
break;
#else
err = -EAFNOSUPPORT;
goto out;
#endif
default:
goto out;
}
err = -EINVAL;
switch (p->id.proto) {
case IPPROTO_AH:
if ((!attrs[XFRMA_ALG_AUTH] &&
!attrs[XFRMA_ALG_AUTH_TRUNC]) ||
attrs[XFRMA_ALG_AEAD] ||
attrs[XFRMA_ALG_CRYPT] ||
attrs[XFRMA_ALG_COMP] ||
attrs[XFRMA_TFCPAD])
goto out;
break;
case IPPROTO_ESP:
if (attrs[XFRMA_ALG_COMP])
goto out;
if (!attrs[XFRMA_ALG_AUTH] &&
!attrs[XFRMA_ALG_AUTH_TRUNC] &&
!attrs[XFRMA_ALG_CRYPT] &&
!attrs[XFRMA_ALG_AEAD])
goto out;
if ((attrs[XFRMA_ALG_AUTH] ||
attrs[XFRMA_ALG_AUTH_TRUNC] ||
attrs[XFRMA_ALG_CRYPT]) &&
attrs[XFRMA_ALG_AEAD])
goto out;
if (attrs[XFRMA_TFCPAD] &&
p->mode != XFRM_MODE_TUNNEL)
goto out;
break;
case IPPROTO_COMP:
if (!attrs[XFRMA_ALG_COMP] ||
attrs[XFRMA_ALG_AEAD] ||
attrs[XFRMA_ALG_AUTH] ||
attrs[XFRMA_ALG_AUTH_TRUNC] ||
attrs[XFRMA_ALG_CRYPT] ||
attrs[XFRMA_TFCPAD] ||
(ntohl(p->id.spi) >= 0x10000))
goto out;
break;
#if IS_ENABLED(CONFIG_IPV6)
case IPPROTO_DSTOPTS:
case IPPROTO_ROUTING:
if (attrs[XFRMA_ALG_COMP] ||
attrs[XFRMA_ALG_AUTH] ||
attrs[XFRMA_ALG_AUTH_TRUNC] ||
attrs[XFRMA_ALG_AEAD] ||
attrs[XFRMA_ALG_CRYPT] ||
attrs[XFRMA_ENCAP] ||
attrs[XFRMA_SEC_CTX] ||
attrs[XFRMA_TFCPAD] ||
!attrs[XFRMA_COADDR])
goto out;
break;
#endif
default:
goto out;
}
if ((err = verify_aead(attrs)))
goto out;
if ((err = verify_auth_trunc(attrs)))
goto out;
if ((err = verify_one_alg(attrs, XFRMA_ALG_AUTH)))
goto out;
if ((err = verify_one_alg(attrs, XFRMA_ALG_CRYPT)))
goto out;
if ((err = verify_one_alg(attrs, XFRMA_ALG_COMP)))
goto out;
if ((err = verify_sec_ctx_len(attrs)))
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
goto out;
if ((err = verify_replay(p, attrs)))
goto out;
err = -EINVAL;
switch (p->mode) {
case XFRM_MODE_TRANSPORT:
case XFRM_MODE_TUNNEL:
case XFRM_MODE_ROUTEOPTIMIZATION:
case XFRM_MODE_BEET:
break;
default:
goto out;
}
err = 0;
if (attrs[XFRMA_MTIMER_THRESH])
if (!attrs[XFRMA_ENCAP])
err = -EINVAL;
out:
return err;
}
static int attach_one_algo(struct xfrm_algo **algpp, u8 *props,
struct xfrm_algo_desc *(*get_byname)(const char *, int),
struct nlattr *rta)
{
struct xfrm_algo *p, *ualg;
struct xfrm_algo_desc *algo;
if (!rta)
return 0;
ualg = nla_data(rta);
algo = get_byname(ualg->alg_name, 1);
if (!algo)
return -ENOSYS;
*props = algo->desc.sadb_alg_id;
p = kmemdup(ualg, xfrm_alg_len(ualg), GFP_KERNEL);
if (!p)
return -ENOMEM;
strcpy(p->alg_name, algo->name);
*algpp = p;
return 0;
}
static int attach_crypt(struct xfrm_state *x, struct nlattr *rta)
{
struct xfrm_algo *p, *ualg;
struct xfrm_algo_desc *algo;
if (!rta)
return 0;
ualg = nla_data(rta);
algo = xfrm_ealg_get_byname(ualg->alg_name, 1);
if (!algo)
return -ENOSYS;
x->props.ealgo = algo->desc.sadb_alg_id;
p = kmemdup(ualg, xfrm_alg_len(ualg), GFP_KERNEL);
if (!p)
return -ENOMEM;
strcpy(p->alg_name, algo->name);
x->ealg = p;
x->geniv = algo->uinfo.encr.geniv;
return 0;
}
static int attach_auth(struct xfrm_algo_auth **algpp, u8 *props,
struct nlattr *rta)
{
struct xfrm_algo *ualg;
struct xfrm_algo_auth *p;
struct xfrm_algo_desc *algo;
if (!rta)
return 0;
ualg = nla_data(rta);
algo = xfrm_aalg_get_byname(ualg->alg_name, 1);
if (!algo)
return -ENOSYS;
*props = algo->desc.sadb_alg_id;
p = kmalloc(sizeof(*p) + (ualg->alg_key_len + 7) / 8, GFP_KERNEL);
if (!p)
return -ENOMEM;
strcpy(p->alg_name, algo->name);
p->alg_key_len = ualg->alg_key_len;
p->alg_trunc_len = algo->uinfo.auth.icv_truncbits;
memcpy(p->alg_key, ualg->alg_key, (ualg->alg_key_len + 7) / 8);
*algpp = p;
return 0;
}
static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props,
struct nlattr *rta)
{
struct xfrm_algo_auth *p, *ualg;
struct xfrm_algo_desc *algo;
if (!rta)
return 0;
ualg = nla_data(rta);
algo = xfrm_aalg_get_byname(ualg->alg_name, 1);
if (!algo)
return -ENOSYS;
if (ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits)
return -EINVAL;
*props = algo->desc.sadb_alg_id;
p = kmemdup(ualg, xfrm_alg_auth_len(ualg), GFP_KERNEL);
if (!p)
return -ENOMEM;
strcpy(p->alg_name, algo->name);
if (!p->alg_trunc_len)
p->alg_trunc_len = algo->uinfo.auth.icv_truncbits;
*algpp = p;
return 0;
}
static int attach_aead(struct xfrm_state *x, struct nlattr *rta)
{
struct xfrm_algo_aead *p, *ualg;
struct xfrm_algo_desc *algo;
if (!rta)
return 0;
ualg = nla_data(rta);
algo = xfrm_aead_get_byname(ualg->alg_name, ualg->alg_icv_len, 1);
if (!algo)
return -ENOSYS;
x->props.ealgo = algo->desc.sadb_alg_id;
p = kmemdup(ualg, aead_len(ualg), GFP_KERNEL);
if (!p)
return -ENOMEM;
strcpy(p->alg_name, algo->name);
x->aead = p;
x->geniv = algo->uinfo.aead.geniv;
return 0;
}
static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_esn,
struct nlattr *rp)
{
struct xfrm_replay_state_esn *up;
unsigned int ulen;
if (!replay_esn || !rp)
return 0;
up = nla_data(rp);
xfrm_user: ensure user supplied esn replay window is valid The current code fails to ensure that the netlink message actually contains as many bytes as the header indicates. If a user creates a new state or updates an existing one but does not supply the bytes for the whole ESN replay window, the kernel copies random heap bytes into the replay bitmap, the ones happen to follow the XFRMA_REPLAY_ESN_VAL netlink attribute. This leads to following issues: 1. The replay window has random bits set confusing the replay handling code later on. 2. A malicious user could use this flaw to leak up to ~3.5kB of heap memory when she has access to the XFRM netlink interface (requires CAP_NET_ADMIN). Known users of the ESN replay window are strongSwan and Steffen's iproute2 patch (<http://patchwork.ozlabs.org/patch/85962/>). The latter uses the interface with a bitmap supplied while the former does not. strongSwan is therefore prone to run into issue 1. To fix both issues without breaking existing userland allow using the XFRMA_REPLAY_ESN_VAL netlink attribute with either an empty bitmap or a fully specified one. For the former case we initialize the in-kernel bitmap with zero, for the latter we copy the user supplied bitmap. For state updates the full bitmap must be supplied. To prevent overflows in the bitmap length calculation the maximum size of bmp_len is limited to 128 by this patch -- resulting in a maximum replay window of 4096 packets. This should be sufficient for all real life scenarios (RFC 4303 recommends a default replay window size of 64). Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Martin Willi <martin@revosec.ch> Cc: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: Mathias Krause <minipli@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-20 18:01:49 +08:00
ulen = xfrm_replay_state_esn_len(up);
/* Check the overall length and the internal bitmap length to avoid
* potential overflow. */
if (nla_len(rp) < (int)ulen ||
xfrm_replay_state_esn_len(replay_esn) != ulen ||
replay_esn->bmp_len != up->bmp_len)
return -EINVAL;
if (up->replay_window > up->bmp_len * sizeof(__u32) * 8)
return -EINVAL;
return 0;
}
static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn,
struct xfrm_replay_state_esn **preplay_esn,
struct nlattr *rta)
{
struct xfrm_replay_state_esn *p, *pp, *up;
unsigned int klen, ulen;
if (!rta)
return 0;
up = nla_data(rta);
xfrm_user: ensure user supplied esn replay window is valid The current code fails to ensure that the netlink message actually contains as many bytes as the header indicates. If a user creates a new state or updates an existing one but does not supply the bytes for the whole ESN replay window, the kernel copies random heap bytes into the replay bitmap, the ones happen to follow the XFRMA_REPLAY_ESN_VAL netlink attribute. This leads to following issues: 1. The replay window has random bits set confusing the replay handling code later on. 2. A malicious user could use this flaw to leak up to ~3.5kB of heap memory when she has access to the XFRM netlink interface (requires CAP_NET_ADMIN). Known users of the ESN replay window are strongSwan and Steffen's iproute2 patch (<http://patchwork.ozlabs.org/patch/85962/>). The latter uses the interface with a bitmap supplied while the former does not. strongSwan is therefore prone to run into issue 1. To fix both issues without breaking existing userland allow using the XFRMA_REPLAY_ESN_VAL netlink attribute with either an empty bitmap or a fully specified one. For the former case we initialize the in-kernel bitmap with zero, for the latter we copy the user supplied bitmap. For state updates the full bitmap must be supplied. To prevent overflows in the bitmap length calculation the maximum size of bmp_len is limited to 128 by this patch -- resulting in a maximum replay window of 4096 packets. This should be sufficient for all real life scenarios (RFC 4303 recommends a default replay window size of 64). Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Martin Willi <martin@revosec.ch> Cc: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: Mathias Krause <minipli@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-20 18:01:49 +08:00
klen = xfrm_replay_state_esn_len(up);
ulen = nla_len(rta) >= (int)klen ? klen : sizeof(*up);
xfrm_user: ensure user supplied esn replay window is valid The current code fails to ensure that the netlink message actually contains as many bytes as the header indicates. If a user creates a new state or updates an existing one but does not supply the bytes for the whole ESN replay window, the kernel copies random heap bytes into the replay bitmap, the ones happen to follow the XFRMA_REPLAY_ESN_VAL netlink attribute. This leads to following issues: 1. The replay window has random bits set confusing the replay handling code later on. 2. A malicious user could use this flaw to leak up to ~3.5kB of heap memory when she has access to the XFRM netlink interface (requires CAP_NET_ADMIN). Known users of the ESN replay window are strongSwan and Steffen's iproute2 patch (<http://patchwork.ozlabs.org/patch/85962/>). The latter uses the interface with a bitmap supplied while the former does not. strongSwan is therefore prone to run into issue 1. To fix both issues without breaking existing userland allow using the XFRMA_REPLAY_ESN_VAL netlink attribute with either an empty bitmap or a fully specified one. For the former case we initialize the in-kernel bitmap with zero, for the latter we copy the user supplied bitmap. For state updates the full bitmap must be supplied. To prevent overflows in the bitmap length calculation the maximum size of bmp_len is limited to 128 by this patch -- resulting in a maximum replay window of 4096 packets. This should be sufficient for all real life scenarios (RFC 4303 recommends a default replay window size of 64). Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Martin Willi <martin@revosec.ch> Cc: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: Mathias Krause <minipli@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-20 18:01:49 +08:00
p = kzalloc(klen, GFP_KERNEL);
if (!p)
return -ENOMEM;
xfrm_user: ensure user supplied esn replay window is valid The current code fails to ensure that the netlink message actually contains as many bytes as the header indicates. If a user creates a new state or updates an existing one but does not supply the bytes for the whole ESN replay window, the kernel copies random heap bytes into the replay bitmap, the ones happen to follow the XFRMA_REPLAY_ESN_VAL netlink attribute. This leads to following issues: 1. The replay window has random bits set confusing the replay handling code later on. 2. A malicious user could use this flaw to leak up to ~3.5kB of heap memory when she has access to the XFRM netlink interface (requires CAP_NET_ADMIN). Known users of the ESN replay window are strongSwan and Steffen's iproute2 patch (<http://patchwork.ozlabs.org/patch/85962/>). The latter uses the interface with a bitmap supplied while the former does not. strongSwan is therefore prone to run into issue 1. To fix both issues without breaking existing userland allow using the XFRMA_REPLAY_ESN_VAL netlink attribute with either an empty bitmap or a fully specified one. For the former case we initialize the in-kernel bitmap with zero, for the latter we copy the user supplied bitmap. For state updates the full bitmap must be supplied. To prevent overflows in the bitmap length calculation the maximum size of bmp_len is limited to 128 by this patch -- resulting in a maximum replay window of 4096 packets. This should be sufficient for all real life scenarios (RFC 4303 recommends a default replay window size of 64). Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Martin Willi <martin@revosec.ch> Cc: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: Mathias Krause <minipli@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-20 18:01:49 +08:00
pp = kzalloc(klen, GFP_KERNEL);
if (!pp) {
kfree(p);
return -ENOMEM;
}
xfrm_user: ensure user supplied esn replay window is valid The current code fails to ensure that the netlink message actually contains as many bytes as the header indicates. If a user creates a new state or updates an existing one but does not supply the bytes for the whole ESN replay window, the kernel copies random heap bytes into the replay bitmap, the ones happen to follow the XFRMA_REPLAY_ESN_VAL netlink attribute. This leads to following issues: 1. The replay window has random bits set confusing the replay handling code later on. 2. A malicious user could use this flaw to leak up to ~3.5kB of heap memory when she has access to the XFRM netlink interface (requires CAP_NET_ADMIN). Known users of the ESN replay window are strongSwan and Steffen's iproute2 patch (<http://patchwork.ozlabs.org/patch/85962/>). The latter uses the interface with a bitmap supplied while the former does not. strongSwan is therefore prone to run into issue 1. To fix both issues without breaking existing userland allow using the XFRMA_REPLAY_ESN_VAL netlink attribute with either an empty bitmap or a fully specified one. For the former case we initialize the in-kernel bitmap with zero, for the latter we copy the user supplied bitmap. For state updates the full bitmap must be supplied. To prevent overflows in the bitmap length calculation the maximum size of bmp_len is limited to 128 by this patch -- resulting in a maximum replay window of 4096 packets. This should be sufficient for all real life scenarios (RFC 4303 recommends a default replay window size of 64). Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Martin Willi <martin@revosec.ch> Cc: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: Mathias Krause <minipli@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-20 18:01:49 +08:00
memcpy(p, up, ulen);
memcpy(pp, up, ulen);
*replay_esn = p;
*preplay_esn = pp;
return 0;
}
static inline unsigned int xfrm_user_sec_ctx_size(struct xfrm_sec_ctx *xfrm_ctx)
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
{
unsigned int len = 0;
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
if (xfrm_ctx) {
len += sizeof(struct xfrm_user_sec_ctx);
len += xfrm_ctx->ctx_len;
}
return len;
}
static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p)
{
memcpy(&x->id, &p->id, sizeof(x->id));
memcpy(&x->sel, &p->sel, sizeof(x->sel));
memcpy(&x->lft, &p->lft, sizeof(x->lft));
x->props.mode = p->mode;
xfrm: Guard IPsec anti replay window against replay bitmap For legacy IPsec anti replay mechanism: bitmap in struct xfrm_replay_state could only provide a 32 bits window size limit in current design, thus user level parameter sadb_sa_replay should honor this limit, otherwise misleading outputs("replay=244") by setkey -D will be: 192.168.25.2 192.168.22.2 esp mode=transport spi=147561170(0x08cb9ad2) reqid=0(0x00000000) E: aes-cbc 9a8d7468 7655cf0b 719d27be b0ddaac2 A: hmac-sha1 2d2115c2 ebf7c126 1c54f186 3b139b58 264a7331 seq=0x00000000 replay=244 flags=0x00000000 state=mature created: Sep 17 14:00:00 2013 current: Sep 17 14:00:22 2013 diff: 22(s) hard: 30(s) soft: 26(s) last: Sep 17 14:00:00 2013 hard: 0(s) soft: 0(s) current: 1408(bytes) hard: 0(bytes) soft: 0(bytes) allocated: 22 hard: 0 soft: 0 sadb_seq=1 pid=4854 refcnt=0 192.168.22.2 192.168.25.2 esp mode=transport spi=255302123(0x0f3799eb) reqid=0(0x00000000) E: aes-cbc 6485d990 f61a6bd5 e5660252 608ad282 A: hmac-sha1 0cca811a eb4fa893 c47ae56c 98f6e413 87379a88 seq=0x00000000 replay=244 flags=0x00000000 state=mature created: Sep 17 14:00:00 2013 current: Sep 17 14:00:22 2013 diff: 22(s) hard: 30(s) soft: 26(s) last: Sep 17 14:00:00 2013 hard: 0(s) soft: 0(s) current: 1408(bytes) hard: 0(bytes) soft: 0(bytes) allocated: 22 hard: 0 soft: 0 sadb_seq=0 pid=4854 refcnt=0 And also, optimizing xfrm_replay_check window checking by setting the desirable x->props.replay_window with only doing the comparison once for all when xfrm_state is first born. Signed-off-by: Fan Du <fan.du@windriver.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2013-09-17 15:14:13 +08:00
x->props.replay_window = min_t(unsigned int, p->replay_window,
sizeof(x->replay.bitmap) * 8);
x->props.reqid = p->reqid;
x->props.family = p->family;
memcpy(&x->props.saddr, &p->saddr, sizeof(x->props.saddr));
x->props.flags = p->flags;
if (!x->sel.family && !(p->flags & XFRM_STATE_AF_UNSPEC))
x->sel.family = p->family;
}
/*
* someday when pfkey also has support, we could have the code
* somehow made shareable and move it to xfrm_state.c - JHS
*
*/
static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs,
int update_esn)
{
struct nlattr *rp = attrs[XFRMA_REPLAY_VAL];
struct nlattr *re = update_esn ? attrs[XFRMA_REPLAY_ESN_VAL] : NULL;
struct nlattr *lt = attrs[XFRMA_LTIME_VAL];
struct nlattr *et = attrs[XFRMA_ETIMER_THRESH];
struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH];
struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH];
if (re) {
struct xfrm_replay_state_esn *replay_esn;
replay_esn = nla_data(re);
memcpy(x->replay_esn, replay_esn,
xfrm_replay_state_esn_len(replay_esn));
memcpy(x->preplay_esn, replay_esn,
xfrm_replay_state_esn_len(replay_esn));
}
if (rp) {
struct xfrm_replay_state *replay;
replay = nla_data(rp);
memcpy(&x->replay, replay, sizeof(*replay));
memcpy(&x->preplay, replay, sizeof(*replay));
}
if (lt) {
struct xfrm_lifetime_cur *ltime;
ltime = nla_data(lt);
x->curlft.bytes = ltime->bytes;
x->curlft.packets = ltime->packets;
x->curlft.add_time = ltime->add_time;
x->curlft.use_time = ltime->use_time;
}
if (et)
x->replay_maxage = nla_get_u32(et);
if (rt)
x->replay_maxdiff = nla_get_u32(rt);
if (mt)
x->mapping_maxage = nla_get_u32(mt);
}
static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m)
{
if (attrs[XFRMA_SET_MARK]) {
m->v = nla_get_u32(attrs[XFRMA_SET_MARK]);
if (attrs[XFRMA_SET_MARK_MASK])
m->m = nla_get_u32(attrs[XFRMA_SET_MARK_MASK]);
else
m->m = 0xffffffff;
} else {
m->v = m->m = 0;
}
}
static struct xfrm_state *xfrm_state_construct(struct net *net,
struct xfrm_usersa_info *p,
struct nlattr **attrs,
int *errp)
{
struct xfrm_state *x = xfrm_state_alloc(net);
int err = -ENOMEM;
if (!x)
goto error_no_put;
copy_from_user_state(x, p);
if (attrs[XFRMA_ENCAP]) {
x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]),
sizeof(*x->encap), GFP_KERNEL);
if (x->encap == NULL)
goto error;
}
if (attrs[XFRMA_COADDR]) {
x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]),
sizeof(*x->coaddr), GFP_KERNEL);
if (x->coaddr == NULL)
goto error;
}
if (attrs[XFRMA_SA_EXTRA_FLAGS])
x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]);
if ((err = attach_aead(x, attrs[XFRMA_ALG_AEAD])))
goto error;
if ((err = attach_auth_trunc(&x->aalg, &x->props.aalgo,
attrs[XFRMA_ALG_AUTH_TRUNC])))
goto error;
if (!x->props.aalgo) {
if ((err = attach_auth(&x->aalg, &x->props.aalgo,
attrs[XFRMA_ALG_AUTH])))
goto error;
}
if ((err = attach_crypt(x, attrs[XFRMA_ALG_CRYPT])))
goto error;
if ((err = attach_one_algo(&x->calg, &x->props.calgo,
xfrm_calg_get_byname,
attrs[XFRMA_ALG_COMP])))
goto error;
if (attrs[XFRMA_TFCPAD])
x->tfcpad = nla_get_u32(attrs[XFRMA_TFCPAD]);
xfrm_mark_get(attrs, &x->mark);
xfrm_smark_init(attrs, &x->props.smark);
net: xfrm: support setting an output mark. On systems that use mark-based routing it may be necessary for routing lookups to use marks in order for packets to be routed correctly. An example of such a system is Android, which uses socket marks to route packets via different networks. Currently, routing lookups in tunnel mode always use a mark of zero, making routing incorrect on such systems. This patch adds a new output_mark element to the xfrm state and a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output mark differs from the existing xfrm mark in two ways: 1. The xfrm mark is used to match xfrm policies and states, while the xfrm output mark is used to set the mark (and influence the routing) of the packets emitted by those states. 2. The existing mark is constrained to be a subset of the bits of the originating socket or transformed packet, but the output mark is arbitrary and depends only on the state. The use of a separate mark provides additional flexibility. For example: - A packet subject to two transforms (e.g., transport mode inside tunnel mode) can have two different output marks applied to it, one for the transport mode SA and one for the tunnel mode SA. - On a system where socket marks determine routing, the packets emitted by an IPsec tunnel can be routed based on a mark that is determined by the tunnel, not by the marks of the unencrypted packets. - Support for setting the output marks can be introduced without breaking any existing setups that employ both mark-based routing and xfrm tunnel mode. Simply changing the code to use the xfrm mark for routing output packets could xfrm mark could change behaviour in a way that breaks these setups. If the output mark is unspecified or set to zero, the mark is not set or changed. Tested: make allyesconfig; make -j64 Tested: https://android-review.googlesource.com/452776 Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2017-08-11 01:11:33 +08:00
if (attrs[XFRMA_IF_ID])
x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
net: xfrm: support setting an output mark. On systems that use mark-based routing it may be necessary for routing lookups to use marks in order for packets to be routed correctly. An example of such a system is Android, which uses socket marks to route packets via different networks. Currently, routing lookups in tunnel mode always use a mark of zero, making routing incorrect on such systems. This patch adds a new output_mark element to the xfrm state and a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output mark differs from the existing xfrm mark in two ways: 1. The xfrm mark is used to match xfrm policies and states, while the xfrm output mark is used to set the mark (and influence the routing) of the packets emitted by those states. 2. The existing mark is constrained to be a subset of the bits of the originating socket or transformed packet, but the output mark is arbitrary and depends only on the state. The use of a separate mark provides additional flexibility. For example: - A packet subject to two transforms (e.g., transport mode inside tunnel mode) can have two different output marks applied to it, one for the transport mode SA and one for the tunnel mode SA. - On a system where socket marks determine routing, the packets emitted by an IPsec tunnel can be routed based on a mark that is determined by the tunnel, not by the marks of the unencrypted packets. - Support for setting the output marks can be introduced without breaking any existing setups that employ both mark-based routing and xfrm tunnel mode. Simply changing the code to use the xfrm mark for routing output packets could xfrm mark could change behaviour in a way that breaks these setups. If the output mark is unspecified or set to zero, the mark is not set or changed. Tested: make allyesconfig; make -j64 Tested: https://android-review.googlesource.com/452776 Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2017-08-11 01:11:33 +08:00
err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]);
if (err)
goto error;
if (attrs[XFRMA_SEC_CTX]) {
err = security_xfrm_state_alloc(x,
nla_data(attrs[XFRMA_SEC_CTX]));
if (err)
goto error;
}
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn,
attrs[XFRMA_REPLAY_ESN_VAL])))
goto error;
x->km.seq = p->seq;
x->replay_maxdiff = net->xfrm.sysctl_aevent_rseqth;
/* sysctl_xfrm_aevent_etime is in 100ms units */
x->replay_maxage = (net->xfrm.sysctl_aevent_etime*HZ)/XFRM_AE_ETH_M;
if ((err = xfrm_init_replay(x)))
goto error;
/* override default values from above */
xfrm_update_ae_params(x, attrs, 0);
/* configure the hardware if offload is requested */
if (attrs[XFRMA_OFFLOAD_DEV]) {
err = xfrm_dev_state_add(net, x,
nla_data(attrs[XFRMA_OFFLOAD_DEV]));
if (err)
goto error;
}
return x;
error:
x->km.state = XFRM_STATE_DEAD;
xfrm_state_put(x);
error_no_put:
*errp = err;
return NULL;
}
static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_usersa_info *p = nlmsg_data(nlh);
struct xfrm_state *x;
int err;
struct km_event c;
err = verify_newsa_info(p, attrs);
if (err)
return err;
x = xfrm_state_construct(net, p, attrs, &err);
if (!x)
return err;
xfrm_state_hold(x);
if (nlh->nlmsg_type == XFRM_MSG_NEWSA)
err = xfrm_state_add(x);
else
err = xfrm_state_update(x);
xfrm_audit_state_add(x, err ? 0 : 1, true);
if (err < 0) {
x->km.state = XFRM_STATE_DEAD;
xfrm_dev_state_delete(x);
__xfrm_state_put(x);
goto out;
}
if (x->km.state == XFRM_STATE_VOID)
x->km.state = XFRM_STATE_VALID;
c.seq = nlh->nlmsg_seq;
c.portid = nlh->nlmsg_pid;
c.event = nlh->nlmsg_type;
km_state_notify(x, &c);
out:
xfrm_state_put(x);
return err;
}
static struct xfrm_state *xfrm_user_state_lookup(struct net *net,
struct xfrm_usersa_id *p,
struct nlattr **attrs,
int *errp)
{
struct xfrm_state *x = NULL;
struct xfrm_mark m;
int err;
u32 mark = xfrm_mark_get(attrs, &m);
if (xfrm_id_proto_match(p->proto, IPSEC_PROTO_ANY)) {
err = -ESRCH;
x = xfrm_state_lookup(net, mark, &p->daddr, p->spi, p->proto, p->family);
} else {
xfrm_address_t *saddr = NULL;
verify_one_addr(attrs, XFRMA_SRCADDR, &saddr);
if (!saddr) {
err = -EINVAL;
goto out;
}
err = -ESRCH;
x = xfrm_state_lookup_byaddr(net, mark,
&p->daddr, saddr,
p->proto, p->family);
}
out:
if (!x && errp)
*errp = err;
return x;
}
static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_state *x;
int err = -ESRCH;
struct km_event c;
struct xfrm_usersa_id *p = nlmsg_data(nlh);
x = xfrm_user_state_lookup(net, p, attrs, &err);
if (x == NULL)
return err;
if ((err = security_xfrm_state_delete(x)) != 0)
[LSM-IPsec]: SELinux Authorize This patch contains a fix for the previous patch that adds security contexts to IPsec policies and security associations. In the previous patch, no authorization (besides the check for write permissions to SAD and SPD) is required to delete IPsec policies and security assocations with security contexts. Thus a user authorized to change SAD and SPD can bypass the IPsec policy authorization by simply deleteing policies with security contexts. To fix this security hole, an additional authorization check is added for removing security policies and security associations with security contexts. Note that if no security context is supplied on add or present on policy to be deleted, the SELinux module allows the change unconditionally. The hook is called on deletion when no context is present, which we may want to change. At present, I left it up to the module. LSM changes: The patch adds two new LSM hooks: xfrm_policy_delete and xfrm_state_delete. The new hooks are necessary to authorize deletion of IPsec policies that have security contexts. The existing hooks xfrm_policy_free and xfrm_state_free lack the context to do the authorization, so I decided to split authorization of deletion and memory management of security data, as is typical in the LSM interface. Use: The new delete hooks are checked when xfrm_policy or xfrm_state are deleted by either the xfrm_user interface (xfrm_get_policy, xfrm_del_sa) or the pfkey interface (pfkey_spddelete, pfkey_delete). SELinux changes: The new policy_delete and state_delete functions are added. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 14:39:49 +08:00
goto out;
if (xfrm_state_kern(x)) {
[LSM-IPsec]: SELinux Authorize This patch contains a fix for the previous patch that adds security contexts to IPsec policies and security associations. In the previous patch, no authorization (besides the check for write permissions to SAD and SPD) is required to delete IPsec policies and security assocations with security contexts. Thus a user authorized to change SAD and SPD can bypass the IPsec policy authorization by simply deleteing policies with security contexts. To fix this security hole, an additional authorization check is added for removing security policies and security associations with security contexts. Note that if no security context is supplied on add or present on policy to be deleted, the SELinux module allows the change unconditionally. The hook is called on deletion when no context is present, which we may want to change. At present, I left it up to the module. LSM changes: The patch adds two new LSM hooks: xfrm_policy_delete and xfrm_state_delete. The new hooks are necessary to authorize deletion of IPsec policies that have security contexts. The existing hooks xfrm_policy_free and xfrm_state_free lack the context to do the authorization, so I decided to split authorization of deletion and memory management of security data, as is typical in the LSM interface. Use: The new delete hooks are checked when xfrm_policy or xfrm_state are deleted by either the xfrm_user interface (xfrm_get_policy, xfrm_del_sa) or the pfkey interface (pfkey_spddelete, pfkey_delete). SELinux changes: The new policy_delete and state_delete functions are added. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 14:39:49 +08:00
err = -EPERM;
goto out;
}
err = xfrm_state_delete(x);
[LSM-IPsec]: SELinux Authorize This patch contains a fix for the previous patch that adds security contexts to IPsec policies and security associations. In the previous patch, no authorization (besides the check for write permissions to SAD and SPD) is required to delete IPsec policies and security assocations with security contexts. Thus a user authorized to change SAD and SPD can bypass the IPsec policy authorization by simply deleteing policies with security contexts. To fix this security hole, an additional authorization check is added for removing security policies and security associations with security contexts. Note that if no security context is supplied on add or present on policy to be deleted, the SELinux module allows the change unconditionally. The hook is called on deletion when no context is present, which we may want to change. At present, I left it up to the module. LSM changes: The patch adds two new LSM hooks: xfrm_policy_delete and xfrm_state_delete. The new hooks are necessary to authorize deletion of IPsec policies that have security contexts. The existing hooks xfrm_policy_free and xfrm_state_free lack the context to do the authorization, so I decided to split authorization of deletion and memory management of security data, as is typical in the LSM interface. Use: The new delete hooks are checked when xfrm_policy or xfrm_state are deleted by either the xfrm_user interface (xfrm_get_policy, xfrm_del_sa) or the pfkey interface (pfkey_spddelete, pfkey_delete). SELinux changes: The new policy_delete and state_delete functions are added. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 14:39:49 +08:00
if (err < 0)
goto out;
c.seq = nlh->nlmsg_seq;
c.portid = nlh->nlmsg_pid;
c.event = nlh->nlmsg_type;
km_state_notify(x, &c);
[LSM-IPsec]: SELinux Authorize This patch contains a fix for the previous patch that adds security contexts to IPsec policies and security associations. In the previous patch, no authorization (besides the check for write permissions to SAD and SPD) is required to delete IPsec policies and security assocations with security contexts. Thus a user authorized to change SAD and SPD can bypass the IPsec policy authorization by simply deleteing policies with security contexts. To fix this security hole, an additional authorization check is added for removing security policies and security associations with security contexts. Note that if no security context is supplied on add or present on policy to be deleted, the SELinux module allows the change unconditionally. The hook is called on deletion when no context is present, which we may want to change. At present, I left it up to the module. LSM changes: The patch adds two new LSM hooks: xfrm_policy_delete and xfrm_state_delete. The new hooks are necessary to authorize deletion of IPsec policies that have security contexts. The existing hooks xfrm_policy_free and xfrm_state_free lack the context to do the authorization, so I decided to split authorization of deletion and memory management of security data, as is typical in the LSM interface. Use: The new delete hooks are checked when xfrm_policy or xfrm_state are deleted by either the xfrm_user interface (xfrm_get_policy, xfrm_del_sa) or the pfkey interface (pfkey_spddelete, pfkey_delete). SELinux changes: The new policy_delete and state_delete functions are added. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 14:39:49 +08:00
out:
xfrm_audit_state_delete(x, err ? 0 : 1, true);
[LSM-IPsec]: SELinux Authorize This patch contains a fix for the previous patch that adds security contexts to IPsec policies and security associations. In the previous patch, no authorization (besides the check for write permissions to SAD and SPD) is required to delete IPsec policies and security assocations with security contexts. Thus a user authorized to change SAD and SPD can bypass the IPsec policy authorization by simply deleteing policies with security contexts. To fix this security hole, an additional authorization check is added for removing security policies and security associations with security contexts. Note that if no security context is supplied on add or present on policy to be deleted, the SELinux module allows the change unconditionally. The hook is called on deletion when no context is present, which we may want to change. At present, I left it up to the module. LSM changes: The patch adds two new LSM hooks: xfrm_policy_delete and xfrm_state_delete. The new hooks are necessary to authorize deletion of IPsec policies that have security contexts. The existing hooks xfrm_policy_free and xfrm_state_free lack the context to do the authorization, so I decided to split authorization of deletion and memory management of security data, as is typical in the LSM interface. Use: The new delete hooks are checked when xfrm_policy or xfrm_state are deleted by either the xfrm_user interface (xfrm_get_policy, xfrm_del_sa) or the pfkey interface (pfkey_spddelete, pfkey_delete). SELinux changes: The new policy_delete and state_delete functions are added. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 14:39:49 +08:00
xfrm_state_put(x);
return err;
}
static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p)
{
memset(p, 0, sizeof(*p));
memcpy(&p->id, &x->id, sizeof(p->id));
memcpy(&p->sel, &x->sel, sizeof(p->sel));
memcpy(&p->lft, &x->lft, sizeof(p->lft));
memcpy(&p->curlft, &x->curlft, sizeof(p->curlft));
put_unaligned(x->stats.replay_window, &p->stats.replay_window);
put_unaligned(x->stats.replay, &p->stats.replay);
put_unaligned(x->stats.integrity_failed, &p->stats.integrity_failed);
memcpy(&p->saddr, &x->props.saddr, sizeof(p->saddr));
p->mode = x->props.mode;
p->replay_window = x->props.replay_window;
p->reqid = x->props.reqid;
p->family = x->props.family;
p->flags = x->props.flags;
p->seq = x->km.seq;
}
struct xfrm_dump_info {
struct sk_buff *in_skb;
struct sk_buff *out_skb;
u32 nlmsg_seq;
u16 nlmsg_flags;
};
static int copy_sec_ctx(struct xfrm_sec_ctx *s, struct sk_buff *skb)
{
struct xfrm_user_sec_ctx *uctx;
struct nlattr *attr;
int ctx_size = sizeof(*uctx) + s->ctx_len;
attr = nla_reserve(skb, XFRMA_SEC_CTX, ctx_size);
if (attr == NULL)
return -EMSGSIZE;
uctx = nla_data(attr);
uctx->exttype = XFRMA_SEC_CTX;
uctx->len = ctx_size;
uctx->ctx_doi = s->ctx_doi;
uctx->ctx_alg = s->ctx_alg;
uctx->ctx_len = s->ctx_len;
memcpy(uctx + 1, s->ctx_str, s->ctx_len);
return 0;
}
static int copy_user_offload(struct xfrm_state_offload *xso, struct sk_buff *skb)
{
struct xfrm_user_offload *xuo;
struct nlattr *attr;
attr = nla_reserve(skb, XFRMA_OFFLOAD_DEV, sizeof(*xuo));
if (attr == NULL)
return -EMSGSIZE;
xuo = nla_data(attr);
memset(xuo, 0, sizeof(*xuo));
xuo->ifindex = xso->dev->ifindex;
xuo->flags = xso->flags;
return 0;
}
static bool xfrm_redact(void)
{
return IS_ENABLED(CONFIG_SECURITY) &&
security_locked_down(LOCKDOWN_XFRM_SECRET);
}
static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
{
struct xfrm_algo *algo;
struct xfrm_algo_auth *ap;
struct nlattr *nla;
bool redact_secret = xfrm_redact();
nla = nla_reserve(skb, XFRMA_ALG_AUTH,
sizeof(*algo) + (auth->alg_key_len + 7) / 8);
if (!nla)
return -EMSGSIZE;
algo = nla_data(nla);
strncpy(algo->alg_name, auth->alg_name, sizeof(algo->alg_name));
if (redact_secret && auth->alg_key_len)
memset(algo->alg_key, 0, (auth->alg_key_len + 7) / 8);
else
memcpy(algo->alg_key, auth->alg_key,
(auth->alg_key_len + 7) / 8);
algo->alg_key_len = auth->alg_key_len;
nla = nla_reserve(skb, XFRMA_ALG_AUTH_TRUNC, xfrm_alg_auth_len(auth));
if (!nla)
return -EMSGSIZE;
ap = nla_data(nla);
memcpy(ap, auth, sizeof(struct xfrm_algo_auth));
if (redact_secret && auth->alg_key_len)
memset(ap->alg_key, 0, (auth->alg_key_len + 7) / 8);
else
memcpy(ap->alg_key, auth->alg_key,
(auth->alg_key_len + 7) / 8);
return 0;
}
static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb)
{
struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_AEAD, aead_len(aead));
struct xfrm_algo_aead *ap;
bool redact_secret = xfrm_redact();
if (!nla)
return -EMSGSIZE;
ap = nla_data(nla);
memcpy(ap, aead, sizeof(*aead));
if (redact_secret && aead->alg_key_len)
memset(ap->alg_key, 0, (aead->alg_key_len + 7) / 8);
else
memcpy(ap->alg_key, aead->alg_key,
(aead->alg_key_len + 7) / 8);
return 0;
}
static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb)
{
struct xfrm_algo *ap;
bool redact_secret = xfrm_redact();
struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_CRYPT,
xfrm_alg_len(ealg));
if (!nla)
return -EMSGSIZE;
ap = nla_data(nla);
memcpy(ap, ealg, sizeof(*ealg));
if (redact_secret && ealg->alg_key_len)
memset(ap->alg_key, 0, (ealg->alg_key_len + 7) / 8);
else
memcpy(ap->alg_key, ealg->alg_key,
(ealg->alg_key_len + 7) / 8);
return 0;
}
static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m)
{
int ret = 0;
if (m->v | m->m) {
ret = nla_put_u32(skb, XFRMA_SET_MARK, m->v);
if (!ret)
ret = nla_put_u32(skb, XFRMA_SET_MARK_MASK, m->m);
}
return ret;
}
/* Don't change this without updating xfrm_sa_len! */
static int copy_to_user_state_extra(struct xfrm_state *x,
struct xfrm_usersa_info *p,
struct sk_buff *skb)
{
int ret = 0;
copy_to_user_state(x, p);
if (x->props.extra_flags) {
ret = nla_put_u32(skb, XFRMA_SA_EXTRA_FLAGS,
x->props.extra_flags);
if (ret)
goto out;
}
if (x->coaddr) {
ret = nla_put(skb, XFRMA_COADDR, sizeof(*x->coaddr), x->coaddr);
if (ret)
goto out;
}
if (x->lastused) {
ret = nla_put_u64_64bit(skb, XFRMA_LASTUSED, x->lastused,
XFRMA_PAD);
if (ret)
goto out;
}
if (x->aead) {
ret = copy_to_user_aead(x->aead, skb);
if (ret)
goto out;
}
if (x->aalg) {
ret = copy_to_user_auth(x->aalg, skb);
if (ret)
goto out;
}
if (x->ealg) {
ret = copy_to_user_ealg(x->ealg, skb);
if (ret)
goto out;
}
if (x->calg) {
ret = nla_put(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg);
if (ret)
goto out;
}
if (x->encap) {
ret = nla_put(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap);
if (ret)
goto out;
}
if (x->tfcpad) {
ret = nla_put_u32(skb, XFRMA_TFCPAD, x->tfcpad);
if (ret)
goto out;
}
ret = xfrm_mark_put(skb, &x->mark);
if (ret)
goto out;
ret = xfrm_smark_put(skb, &x->props.smark);
if (ret)
goto out;
if (x->replay_esn)
ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL,
xfrm_replay_state_esn_len(x->replay_esn),
x->replay_esn);
else
ret = nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay),
&x->replay);
if (ret)
goto out;
if(x->xso.dev)
ret = copy_user_offload(&x->xso, skb);
if (ret)
goto out;
if (x->if_id) {
ret = nla_put_u32(skb, XFRMA_IF_ID, x->if_id);
net: xfrm: support setting an output mark. On systems that use mark-based routing it may be necessary for routing lookups to use marks in order for packets to be routed correctly. An example of such a system is Android, which uses socket marks to route packets via different networks. Currently, routing lookups in tunnel mode always use a mark of zero, making routing incorrect on such systems. This patch adds a new output_mark element to the xfrm state and a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output mark differs from the existing xfrm mark in two ways: 1. The xfrm mark is used to match xfrm policies and states, while the xfrm output mark is used to set the mark (and influence the routing) of the packets emitted by those states. 2. The existing mark is constrained to be a subset of the bits of the originating socket or transformed packet, but the output mark is arbitrary and depends only on the state. The use of a separate mark provides additional flexibility. For example: - A packet subject to two transforms (e.g., transport mode inside tunnel mode) can have two different output marks applied to it, one for the transport mode SA and one for the tunnel mode SA. - On a system where socket marks determine routing, the packets emitted by an IPsec tunnel can be routed based on a mark that is determined by the tunnel, not by the marks of the unencrypted packets. - Support for setting the output marks can be introduced without breaking any existing setups that employ both mark-based routing and xfrm tunnel mode. Simply changing the code to use the xfrm mark for routing output packets could xfrm mark could change behaviour in a way that breaks these setups. If the output mark is unspecified or set to zero, the mark is not set or changed. Tested: make allyesconfig; make -j64 Tested: https://android-review.googlesource.com/452776 Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2017-08-11 01:11:33 +08:00
if (ret)
goto out;
}
if (x->security) {
ret = copy_sec_ctx(x->security, skb);
if (ret)
goto out;
}
if (x->mapping_maxage)
ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage);
out:
return ret;
}
static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
{
struct xfrm_dump_info *sp = ptr;
struct sk_buff *in_skb = sp->in_skb;
struct sk_buff *skb = sp->out_skb;
struct xfrm_translator *xtr;
struct xfrm_usersa_info *p;
struct nlmsghdr *nlh;
int err;
nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, sp->nlmsg_seq,
XFRM_MSG_NEWSA, sizeof(*p), sp->nlmsg_flags);
if (nlh == NULL)
return -EMSGSIZE;
p = nlmsg_data(nlh);
err = copy_to_user_state_extra(x, p, skb);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
nlmsg_end(skb, nlh);
xtr = xfrm_get_translator();
if (xtr) {
err = xtr->alloc_compat(skb, nlh);
xfrm_put_translator(xtr);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
}
return 0;
}
static int xfrm_dump_sa_done(struct netlink_callback *cb)
{
struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1];
struct sock *sk = cb->skb->sk;
struct net *net = sock_net(sk);
if (cb->args[0])
xfrm_state_walk_done(walk, net);
return 0;
}
static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1];
struct xfrm_dump_info info;
BUILD_BUG_ON(sizeof(struct xfrm_state_walk) >
sizeof(cb->args) - sizeof(cb->args[0]));
info.in_skb = cb->skb;
info.out_skb = skb;
info.nlmsg_seq = cb->nlh->nlmsg_seq;
info.nlmsg_flags = NLM_F_MULTI;
if (!cb->args[0]) {
struct nlattr *attrs[XFRMA_MAX+1];
struct xfrm_address_filter *filter = NULL;
u8 proto = 0;
int 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 20:07:28 +08:00
err = nlmsg_parse_deprecated(cb->nlh, 0, attrs, XFRMA_MAX,
xfrma_policy, cb->extack);
if (err < 0)
return err;
if (attrs[XFRMA_ADDRESS_FILTER]) {
filter = kmemdup(nla_data(attrs[XFRMA_ADDRESS_FILTER]),
sizeof(*filter), GFP_KERNEL);
if (filter == NULL)
return -ENOMEM;
}
if (attrs[XFRMA_PROTO])
proto = nla_get_u8(attrs[XFRMA_PROTO]);
xfrm_state_walk_init(walk, proto, filter);
cb->args[0] = 1;
}
(void) xfrm_state_walk(net, walk, dump_one_state, &info);
return skb->len;
}
static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb,
struct xfrm_state *x, u32 seq)
{
struct xfrm_dump_info info;
struct sk_buff *skb;
int err;
skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
if (!skb)
return ERR_PTR(-ENOMEM);
info.in_skb = in_skb;
info.out_skb = skb;
info.nlmsg_seq = seq;
info.nlmsg_flags = 0;
err = dump_one_state(x, 0, &info);
if (err) {
kfree_skb(skb);
return ERR_PTR(err);
}
return skb;
}
/* A wrapper for nlmsg_multicast() checking that nlsk is still available.
* Must be called with RCU read lock.
*/
static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
u32 pid, unsigned int group)
{
struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
struct xfrm_translator *xtr;
if (!nlsk) {
kfree_skb(skb);
return -EPIPE;
}
xtr = xfrm_get_translator();
if (xtr) {
int err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
xfrm_put_translator(xtr);
if (err) {
kfree_skb(skb);
return err;
}
}
return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
}
static inline unsigned int xfrm_spdinfo_msgsize(void)
{
return NLMSG_ALIGN(4)
+ nla_total_size(sizeof(struct xfrmu_spdinfo))
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
+ nla_total_size(sizeof(struct xfrmu_spdhinfo))
+ nla_total_size(sizeof(struct xfrmu_spdhthresh))
+ nla_total_size(sizeof(struct xfrmu_spdhthresh));
}
static int build_spdinfo(struct sk_buff *skb, struct net *net,
u32 portid, u32 seq, u32 flags)
{
struct xfrmk_spdinfo si;
struct xfrmu_spdinfo spc;
struct xfrmu_spdhinfo sph;
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
struct xfrmu_spdhthresh spt4, spt6;
struct nlmsghdr *nlh;
int err;
u32 *f;
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
unsigned lseq;
nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_NEWSPDINFO, sizeof(u32), 0);
if (nlh == NULL) /* shouldn't really happen ... */
return -EMSGSIZE;
f = nlmsg_data(nlh);
*f = flags;
xfrm_spd_getinfo(net, &si);
spc.incnt = si.incnt;
spc.outcnt = si.outcnt;
spc.fwdcnt = si.fwdcnt;
spc.inscnt = si.inscnt;
spc.outscnt = si.outscnt;
spc.fwdscnt = si.fwdscnt;
sph.spdhcnt = si.spdhcnt;
sph.spdhmcnt = si.spdhmcnt;
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
do {
lseq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
spt4.lbits = net->xfrm.policy_hthresh.lbits4;
spt4.rbits = net->xfrm.policy_hthresh.rbits4;
spt6.lbits = net->xfrm.policy_hthresh.lbits6;
spt6.rbits = net->xfrm.policy_hthresh.rbits6;
} while (read_seqretry(&net->xfrm.policy_hthresh.lock, lseq));
err = nla_put(skb, XFRMA_SPD_INFO, sizeof(spc), &spc);
if (!err)
err = nla_put(skb, XFRMA_SPD_HINFO, sizeof(sph), &sph);
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
if (!err)
err = nla_put(skb, XFRMA_SPD_IPV4_HTHRESH, sizeof(spt4), &spt4);
if (!err)
err = nla_put(skb, XFRMA_SPD_IPV6_HTHRESH, sizeof(spt6), &spt6);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
}
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
static int xfrm_set_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrmu_spdhthresh *thresh4 = NULL;
struct xfrmu_spdhthresh *thresh6 = NULL;
/* selector prefixlen thresholds to hash policies */
if (attrs[XFRMA_SPD_IPV4_HTHRESH]) {
struct nlattr *rta = attrs[XFRMA_SPD_IPV4_HTHRESH];
if (nla_len(rta) < sizeof(*thresh4))
return -EINVAL;
thresh4 = nla_data(rta);
if (thresh4->lbits > 32 || thresh4->rbits > 32)
return -EINVAL;
}
if (attrs[XFRMA_SPD_IPV6_HTHRESH]) {
struct nlattr *rta = attrs[XFRMA_SPD_IPV6_HTHRESH];
if (nla_len(rta) < sizeof(*thresh6))
return -EINVAL;
thresh6 = nla_data(rta);
if (thresh6->lbits > 128 || thresh6->rbits > 128)
return -EINVAL;
}
if (thresh4 || thresh6) {
write_seqlock(&net->xfrm.policy_hthresh.lock);
if (thresh4) {
net->xfrm.policy_hthresh.lbits4 = thresh4->lbits;
net->xfrm.policy_hthresh.rbits4 = thresh4->rbits;
}
if (thresh6) {
net->xfrm.policy_hthresh.lbits6 = thresh6->lbits;
net->xfrm.policy_hthresh.rbits6 = thresh6->rbits;
}
write_sequnlock(&net->xfrm.policy_hthresh.lock);
xfrm_policy_hash_rebuild(net);
}
return 0;
}
static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct sk_buff *r_skb;
u32 *flags = nlmsg_data(nlh);
u32 sportid = NETLINK_CB(skb).portid;
u32 seq = nlh->nlmsg_seq;
int err;
r_skb = nlmsg_new(xfrm_spdinfo_msgsize(), GFP_ATOMIC);
if (r_skb == NULL)
return -ENOMEM;
err = build_spdinfo(r_skb, net, sportid, seq, *flags);
BUG_ON(err < 0);
return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid);
}
static inline unsigned int xfrm_sadinfo_msgsize(void)
{
return NLMSG_ALIGN(4)
+ nla_total_size(sizeof(struct xfrmu_sadhinfo))
+ nla_total_size(4); /* XFRMA_SAD_CNT */
}
static int build_sadinfo(struct sk_buff *skb, struct net *net,
u32 portid, u32 seq, u32 flags)
{
struct xfrmk_sadinfo si;
struct xfrmu_sadhinfo sh;
struct nlmsghdr *nlh;
int err;
u32 *f;
nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_NEWSADINFO, sizeof(u32), 0);
if (nlh == NULL) /* shouldn't really happen ... */
return -EMSGSIZE;
f = nlmsg_data(nlh);
*f = flags;
xfrm_sad_getinfo(net, &si);
sh.sadhmcnt = si.sadhmcnt;
sh.sadhcnt = si.sadhcnt;
err = nla_put_u32(skb, XFRMA_SAD_CNT, si.sadcnt);
if (!err)
err = nla_put(skb, XFRMA_SAD_HINFO, sizeof(sh), &sh);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
}
static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct sk_buff *r_skb;
u32 *flags = nlmsg_data(nlh);
u32 sportid = NETLINK_CB(skb).portid;
u32 seq = nlh->nlmsg_seq;
int err;
r_skb = nlmsg_new(xfrm_sadinfo_msgsize(), GFP_ATOMIC);
if (r_skb == NULL)
return -ENOMEM;
err = build_sadinfo(r_skb, net, sportid, seq, *flags);
BUG_ON(err < 0);
return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid);
}
static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_usersa_id *p = nlmsg_data(nlh);
struct xfrm_state *x;
struct sk_buff *resp_skb;
int err = -ESRCH;
x = xfrm_user_state_lookup(net, p, attrs, &err);
if (x == NULL)
goto out_noput;
resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq);
if (IS_ERR(resp_skb)) {
err = PTR_ERR(resp_skb);
} else {
err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid);
}
xfrm_state_put(x);
out_noput:
return err;
}
static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_state *x;
struct xfrm_userspi_info *p;
struct xfrm_translator *xtr;
struct sk_buff *resp_skb;
xfrm_address_t *daddr;
int family;
int err;
u32 mark;
struct xfrm_mark m;
u32 if_id = 0;
p = nlmsg_data(nlh);
err = verify_spi_info(p->info.id.proto, p->min, p->max);
if (err)
goto out_noput;
family = p->info.family;
daddr = &p->info.id.daddr;
x = NULL;
mark = xfrm_mark_get(attrs, &m);
if (attrs[XFRMA_IF_ID])
if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
if (p->info.seq) {
x = xfrm_find_acq_byseq(net, mark, p->info.seq);
if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) {
xfrm_state_put(x);
x = NULL;
}
}
if (!x)
x = xfrm_find_acq(net, &m, p->info.mode, p->info.reqid,
if_id, p->info.id.proto, daddr,
&p->info.saddr, 1,
family);
err = -ENOENT;
if (x == NULL)
goto out_noput;
err = xfrm_alloc_spi(x, p->min, p->max);
if (err)
goto out;
resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq);
if (IS_ERR(resp_skb)) {
err = PTR_ERR(resp_skb);
goto out;
}
xtr = xfrm_get_translator();
if (xtr) {
err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
xfrm_put_translator(xtr);
if (err) {
kfree_skb(resp_skb);
goto out;
}
}
err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid);
out:
xfrm_state_put(x);
out_noput:
return err;
}
static int verify_policy_dir(u8 dir)
{
switch (dir) {
case XFRM_POLICY_IN:
case XFRM_POLICY_OUT:
case XFRM_POLICY_FWD:
break;
default:
return -EINVAL;
}
return 0;
}
static int verify_policy_type(u8 type)
{
switch (type) {
case XFRM_POLICY_TYPE_MAIN:
#ifdef CONFIG_XFRM_SUB_POLICY
case XFRM_POLICY_TYPE_SUB:
#endif
break;
default:
return -EINVAL;
}
return 0;
}
static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
{
int ret;
switch (p->share) {
case XFRM_SHARE_ANY:
case XFRM_SHARE_SESSION:
case XFRM_SHARE_USER:
case XFRM_SHARE_UNIQUE:
break;
default:
return -EINVAL;
}
switch (p->action) {
case XFRM_POLICY_ALLOW:
case XFRM_POLICY_BLOCK:
break;
default:
return -EINVAL;
}
switch (p->sel.family) {
case AF_INET:
if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
return -EINVAL;
break;
case AF_INET6:
#if IS_ENABLED(CONFIG_IPV6)
if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128)
return -EINVAL;
break;
#else
return -EAFNOSUPPORT;
#endif
default:
return -EINVAL;
}
ret = verify_policy_dir(p->dir);
if (ret)
return ret;
xfrm: policy: Fix out-of-bound array accesses in __xfrm_policy_unlink UBSAN report this: UBSAN: Undefined behaviour in net/xfrm/xfrm_policy.c:1289:24 index 6 is out of range for type 'unsigned int [6]' CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.4.162-514.55.6.9.x86_64+ #13 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 0000000000000000 1466cf39b41b23c9 ffff8801f6b07a58 ffffffff81cb35f4 0000000041b58ab3 ffffffff83230f9c ffffffff81cb34e0 ffff8801f6b07a80 ffff8801f6b07a20 1466cf39b41b23c9 ffffffff851706e0 ffff8801f6b07ae8 Call Trace: <IRQ> [<ffffffff81cb35f4>] __dump_stack lib/dump_stack.c:15 [inline] <IRQ> [<ffffffff81cb35f4>] dump_stack+0x114/0x1a0 lib/dump_stack.c:51 [<ffffffff81d94225>] ubsan_epilogue+0x12/0x8f lib/ubsan.c:164 [<ffffffff81d954db>] __ubsan_handle_out_of_bounds+0x16e/0x1b2 lib/ubsan.c:382 [<ffffffff82a25acd>] __xfrm_policy_unlink+0x3dd/0x5b0 net/xfrm/xfrm_policy.c:1289 [<ffffffff82a2e572>] xfrm_policy_delete+0x52/0xb0 net/xfrm/xfrm_policy.c:1309 [<ffffffff82a3319b>] xfrm_policy_timer+0x30b/0x590 net/xfrm/xfrm_policy.c:243 [<ffffffff813d3927>] call_timer_fn+0x237/0x990 kernel/time/timer.c:1144 [<ffffffff813d8e7e>] __run_timers kernel/time/timer.c:1218 [inline] [<ffffffff813d8e7e>] run_timer_softirq+0x6ce/0xb80 kernel/time/timer.c:1401 [<ffffffff8120d6f9>] __do_softirq+0x299/0xe10 kernel/softirq.c:273 [<ffffffff8120e676>] invoke_softirq kernel/softirq.c:350 [inline] [<ffffffff8120e676>] irq_exit+0x216/0x2c0 kernel/softirq.c:391 [<ffffffff82c5edab>] exiting_irq arch/x86/include/asm/apic.h:652 [inline] [<ffffffff82c5edab>] smp_apic_timer_interrupt+0x8b/0xc0 arch/x86/kernel/apic/apic.c:926 [<ffffffff82c5c985>] apic_timer_interrupt+0xa5/0xb0 arch/x86/entry/entry_64.S:735 <EOI> [<ffffffff81188096>] ? native_safe_halt+0x6/0x10 arch/x86/include/asm/irqflags.h:52 [<ffffffff810834d7>] arch_safe_halt arch/x86/include/asm/paravirt.h:111 [inline] [<ffffffff810834d7>] default_idle+0x27/0x430 arch/x86/kernel/process.c:446 [<ffffffff81085f05>] arch_cpu_idle+0x15/0x20 arch/x86/kernel/process.c:437 [<ffffffff8132abc3>] default_idle_call+0x53/0x90 kernel/sched/idle.c:92 [<ffffffff8132b32d>] cpuidle_idle_call kernel/sched/idle.c:156 [inline] [<ffffffff8132b32d>] cpu_idle_loop kernel/sched/idle.c:251 [inline] [<ffffffff8132b32d>] cpu_startup_entry+0x60d/0x9a0 kernel/sched/idle.c:299 [<ffffffff8113e119>] start_secondary+0x3c9/0x560 arch/x86/kernel/smpboot.c:245 The issue is triggered as this: xfrm_add_policy -->verify_newpolicy_info //check the index provided by user with XFRM_POLICY_MAX //In my case, the index is 0x6E6BB6, so it pass the check. -->xfrm_policy_construct //copy the user's policy and set xfrm_policy_timer -->xfrm_policy_insert --> __xfrm_policy_link //use the orgin dir, in my case is 2 --> xfrm_gen_index //generate policy index, there is 0x6E6BB6 then xfrm_policy_timer be fired xfrm_policy_timer --> xfrm_policy_id2dir //get dir from (policy index & 7), in my case is 6 --> xfrm_policy_delete --> __xfrm_policy_unlink //access policy_count[dir], trigger out of range access Add xfrm_policy_id2dir check in verify_newpolicy_info, make sure the computed dir is valid, to fix the issue. Reported-by: Hulk Robot <hulkci@huawei.com> Fixes: e682adf021be ("xfrm: Try to honor policy index if it's supplied by user") Signed-off-by: YueHaibing <yuehaibing@huawei.com> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2019-02-28 15:18:59 +08:00
if (p->index && (xfrm_policy_id2dir(p->index) != p->dir))
return -EINVAL;
return 0;
}
static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs)
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
{
struct nlattr *rt = attrs[XFRMA_SEC_CTX];
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
struct xfrm_user_sec_ctx *uctx;
if (!rt)
return 0;
uctx = nla_data(rt);
selinux: add gfp argument to security_xfrm_policy_alloc and fix callers security_xfrm_policy_alloc can be called in atomic context so the allocation should be done with GFP_ATOMIC. Add an argument to let the callers choose the appropriate way. In order to do so a gfp argument needs to be added to the method xfrm_policy_alloc_security in struct security_operations and to the internal function selinux_xfrm_alloc_user. After that switch to GFP_ATOMIC in the atomic callers and leave GFP_KERNEL as before for the rest. The path that needed the gfp argument addition is: security_xfrm_policy_alloc -> security_ops.xfrm_policy_alloc_security -> all users of xfrm_policy_alloc_security (e.g. selinux_xfrm_policy_alloc) -> selinux_xfrm_alloc_user (here the allocation used to be GFP_KERNEL only) Now adding a gfp argument to selinux_xfrm_alloc_user requires us to also add it to security_context_to_sid which is used inside and prior to this patch did only GFP_KERNEL allocation. So add gfp argument to security_context_to_sid and adjust all of its callers as well. CC: Paul Moore <paul@paul-moore.com> CC: Dave Jones <davej@redhat.com> CC: Steffen Klassert <steffen.klassert@secunet.com> CC: Fan Du <fan.du@windriver.com> CC: David S. Miller <davem@davemloft.net> CC: LSM list <linux-security-module@vger.kernel.org> CC: SELinux list <selinux@tycho.nsa.gov> Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Acked-by: Paul Moore <paul@paul-moore.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-03-07 19:44:19 +08:00
return security_xfrm_policy_alloc(&pol->security, uctx, GFP_KERNEL);
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
}
static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut,
int nr)
{
int i;
xp->xfrm_nr = nr;
for (i = 0; i < nr; i++, ut++) {
struct xfrm_tmpl *t = &xp->xfrm_vec[i];
memcpy(&t->id, &ut->id, sizeof(struct xfrm_id));
memcpy(&t->saddr, &ut->saddr,
sizeof(xfrm_address_t));
t->reqid = ut->reqid;
t->mode = ut->mode;
t->share = ut->share;
t->optional = ut->optional;
t->aalgos = ut->aalgos;
t->ealgos = ut->ealgos;
t->calgos = ut->calgos;
/* If all masks are ~0, then we allow all algorithms. */
t->allalgs = !~(t->aalgos & t->ealgos & t->calgos);
t->encap_family = ut->family;
}
}
static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
{
u16 prev_family;
int i;
if (nr > XFRM_MAX_DEPTH)
return -EINVAL;
prev_family = family;
for (i = 0; i < nr; i++) {
/* We never validated the ut->family value, so many
* applications simply leave it at zero. The check was
* never made and ut->family was ignored because all
* templates could be assumed to have the same family as
* the policy itself. Now that we will have ipv4-in-ipv6
* and ipv6-in-ipv4 tunnels, this is no longer true.
*/
if (!ut[i].family)
ut[i].family = family;
switch (ut[i].mode) {
case XFRM_MODE_TUNNEL:
case XFRM_MODE_BEET:
break;
default:
if (ut[i].family != prev_family)
return -EINVAL;
break;
}
xfrm: validate template mode XFRM mode parameters passed as part of the user templates in the IP_XFRM_POLICY are never properly validated. Passing values other than valid XFRM modes can cause stack-out-of-bounds reads to occur later in the XFRM processing: [ 140.535608] ================================================================ [ 140.543058] BUG: KASAN: stack-out-of-bounds in xfrm_state_find+0x17e4/0x1cc4 [ 140.550306] Read of size 4 at addr ffffffc0238a7a58 by task repro/5148 [ 140.557369] [ 140.558927] Call trace: [ 140.558936] dump_backtrace+0x0/0x388 [ 140.558940] show_stack+0x24/0x30 [ 140.558946] __dump_stack+0x24/0x2c [ 140.558949] dump_stack+0x8c/0xd0 [ 140.558956] print_address_description+0x74/0x234 [ 140.558960] kasan_report+0x240/0x264 [ 140.558963] __asan_report_load4_noabort+0x2c/0x38 [ 140.558967] xfrm_state_find+0x17e4/0x1cc4 [ 140.558971] xfrm_resolve_and_create_bundle+0x40c/0x1fb8 [ 140.558975] xfrm_lookup+0x238/0x1444 [ 140.558977] xfrm_lookup_route+0x48/0x11c [ 140.558984] ip_route_output_flow+0x88/0xc4 [ 140.558991] raw_sendmsg+0xa74/0x266c [ 140.558996] inet_sendmsg+0x258/0x3b0 [ 140.559002] sock_sendmsg+0xbc/0xec [ 140.559005] SyS_sendto+0x3a8/0x5a8 [ 140.559008] el0_svc_naked+0x34/0x38 [ 140.559009] [ 140.592245] page dumped because: kasan: bad access detected [ 140.597981] page_owner info is not active (free page?) [ 140.603267] [ 140.653503] ================================================================ Signed-off-by: Sean Tranchetti <stranche@codeaurora.org> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2018-09-20 03:54:56 +08:00
if (ut[i].mode >= XFRM_MODE_MAX)
return -EINVAL;
prev_family = ut[i].family;
switch (ut[i].family) {
case AF_INET:
break;
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
break;
#endif
default:
return -EINVAL;
}
if (!xfrm_id_proto_valid(ut[i].id.proto))
return -EINVAL;
}
return 0;
}
static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs)
{
struct nlattr *rt = attrs[XFRMA_TMPL];
if (!rt) {
pol->xfrm_nr = 0;
} else {
struct xfrm_user_tmpl *utmpl = nla_data(rt);
int nr = nla_len(rt) / sizeof(*utmpl);
int err;
err = validate_tmpl(nr, utmpl, pol->family);
if (err)
return err;
copy_templates(pol, utmpl, nr);
}
return 0;
}
static int copy_from_user_policy_type(u8 *tp, struct nlattr **attrs)
{
struct nlattr *rt = attrs[XFRMA_POLICY_TYPE];
struct xfrm_userpolicy_type *upt;
u8 type = XFRM_POLICY_TYPE_MAIN;
int err;
if (rt) {
upt = nla_data(rt);
type = upt->type;
}
err = verify_policy_type(type);
if (err)
return err;
*tp = type;
return 0;
}
static void copy_from_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p)
{
xp->priority = p->priority;
xp->index = p->index;
memcpy(&xp->selector, &p->sel, sizeof(xp->selector));
memcpy(&xp->lft, &p->lft, sizeof(xp->lft));
xp->action = p->action;
xp->flags = p->flags;
xp->family = p->sel.family;
/* XXX xp->share = p->share; */
}
static void copy_to_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p, int dir)
{
memset(p, 0, sizeof(*p));
memcpy(&p->sel, &xp->selector, sizeof(p->sel));
memcpy(&p->lft, &xp->lft, sizeof(p->lft));
memcpy(&p->curlft, &xp->curlft, sizeof(p->curlft));
p->priority = xp->priority;
p->index = xp->index;
p->sel.family = xp->family;
p->dir = dir;
p->action = xp->action;
p->flags = xp->flags;
p->share = XFRM_SHARE_ANY; /* XXX xp->share */
}
static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_userpolicy_info *p, struct nlattr **attrs, int *errp)
{
struct xfrm_policy *xp = xfrm_policy_alloc(net, GFP_KERNEL);
int err;
if (!xp) {
*errp = -ENOMEM;
return NULL;
}
copy_from_user_policy(xp, p);
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
err = copy_from_user_policy_type(&xp->type, attrs);
if (err)
goto error;
if (!(err = copy_from_user_tmpl(xp, attrs)))
err = copy_from_user_sec_ctx(xp, attrs);
if (err)
goto error;
xfrm_mark_get(attrs, &xp->mark);
if (attrs[XFRMA_IF_ID])
xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
return xp;
error:
*errp = err;
xp->walk.dead = 1;
xfrm_policy_destroy(xp);
return NULL;
}
static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_userpolicy_info *p = nlmsg_data(nlh);
struct xfrm_policy *xp;
struct km_event c;
int err;
int excl;
err = verify_newpolicy_info(p);
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
if (err)
return err;
err = verify_sec_ctx_len(attrs);
if (err)
return err;
xp = xfrm_policy_construct(net, p, attrs, &err);
if (!xp)
return err;
/* shouldn't excl be based on nlh flags??
* Aha! this is anti-netlink really i.e more pfkey derived
* in netlink excl is a flag and you wouldn't need
* a type XFRM_MSG_UPDPOLICY - JHS */
excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY;
err = xfrm_policy_insert(p->dir, xp, excl);
xfrm_audit_policy_add(xp, err ? 0 : 1, true);
if (err) {
security_xfrm_policy_free(xp->security);
kfree(xp);
return err;
}
c.event = nlh->nlmsg_type;
c.seq = nlh->nlmsg_seq;
c.portid = nlh->nlmsg_pid;
km_policy_notify(xp, p->dir, &c);
xfrm_pol_put(xp);
return 0;
}
static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb)
{
struct xfrm_user_tmpl vec[XFRM_MAX_DEPTH];
int i;
if (xp->xfrm_nr == 0)
return 0;
for (i = 0; i < xp->xfrm_nr; i++) {
struct xfrm_user_tmpl *up = &vec[i];
struct xfrm_tmpl *kp = &xp->xfrm_vec[i];
memset(up, 0, sizeof(*up));
memcpy(&up->id, &kp->id, sizeof(up->id));
up->family = kp->encap_family;
memcpy(&up->saddr, &kp->saddr, sizeof(up->saddr));
up->reqid = kp->reqid;
up->mode = kp->mode;
up->share = kp->share;
up->optional = kp->optional;
up->aalgos = kp->aalgos;
up->ealgos = kp->ealgos;
up->calgos = kp->calgos;
}
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
return nla_put(skb, XFRMA_TMPL,
sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr, vec);
}
static inline int copy_to_user_state_sec_ctx(struct xfrm_state *x, struct sk_buff *skb)
{
if (x->security) {
return copy_sec_ctx(x->security, skb);
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
}
return 0;
}
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
static inline int copy_to_user_sec_ctx(struct xfrm_policy *xp, struct sk_buff *skb)
{
if (xp->security)
return copy_sec_ctx(xp->security, skb);
return 0;
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
}
static inline unsigned int userpolicy_type_attrsize(void)
{
#ifdef CONFIG_XFRM_SUB_POLICY
return nla_total_size(sizeof(struct xfrm_userpolicy_type));
#else
return 0;
#endif
}
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
#ifdef CONFIG_XFRM_SUB_POLICY
static int copy_to_user_policy_type(u8 type, struct sk_buff *skb)
{
xfrm_user: prevent leaking 2 bytes of kernel memory struct xfrm_userpolicy_type has two holes, so we should not use C99 style initializer. KMSAN report: BUG: KMSAN: kernel-infoleak in copyout lib/iov_iter.c:140 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x1b14/0x2800 lib/iov_iter.c:571 CPU: 1 PID: 4520 Comm: syz-executor841 Not tainted 4.17.0+ #5 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:113 kmsan_report+0x188/0x2a0 mm/kmsan/kmsan.c:1117 kmsan_internal_check_memory+0x138/0x1f0 mm/kmsan/kmsan.c:1211 kmsan_copy_to_user+0x7a/0x160 mm/kmsan/kmsan.c:1253 copyout lib/iov_iter.c:140 [inline] _copy_to_iter+0x1b14/0x2800 lib/iov_iter.c:571 copy_to_iter include/linux/uio.h:106 [inline] skb_copy_datagram_iter+0x422/0xfa0 net/core/datagram.c:431 skb_copy_datagram_msg include/linux/skbuff.h:3268 [inline] netlink_recvmsg+0x6f1/0x1900 net/netlink/af_netlink.c:1959 sock_recvmsg_nosec net/socket.c:802 [inline] sock_recvmsg+0x1d6/0x230 net/socket.c:809 ___sys_recvmsg+0x3fe/0x810 net/socket.c:2279 __sys_recvmmsg+0x58e/0xe30 net/socket.c:2391 do_sys_recvmmsg+0x2a6/0x3e0 net/socket.c:2472 __do_sys_recvmmsg net/socket.c:2485 [inline] __se_sys_recvmmsg net/socket.c:2481 [inline] __x64_sys_recvmmsg+0x15d/0x1c0 net/socket.c:2481 do_syscall_64+0x15b/0x230 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x446ce9 RSP: 002b:00007fc307918db8 EFLAGS: 00000293 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 00000000006dbc24 RCX: 0000000000446ce9 RDX: 000000000000000a RSI: 0000000020005040 RDI: 0000000000000003 RBP: 00000000006dbc20 R08: 0000000020004e40 R09: 0000000000000000 R10: 0000000040000000 R11: 0000000000000293 R12: 0000000000000000 R13: 00007ffc8d2df32f R14: 00007fc3079199c0 R15: 0000000000000001 Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline] kmsan_save_stack mm/kmsan/kmsan.c:294 [inline] kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:685 kmsan_memcpy_origins+0x11d/0x170 mm/kmsan/kmsan.c:527 __msan_memcpy+0x109/0x160 mm/kmsan/kmsan_instr.c:413 __nla_put lib/nlattr.c:569 [inline] nla_put+0x276/0x340 lib/nlattr.c:627 copy_to_user_policy_type net/xfrm/xfrm_user.c:1678 [inline] dump_one_policy+0xbe1/0x1090 net/xfrm/xfrm_user.c:1708 xfrm_policy_walk+0x45a/0xd00 net/xfrm/xfrm_policy.c:1013 xfrm_dump_policy+0x1c0/0x2a0 net/xfrm/xfrm_user.c:1749 netlink_dump+0x9b5/0x1550 net/netlink/af_netlink.c:2226 __netlink_dump_start+0x1131/0x1270 net/netlink/af_netlink.c:2323 netlink_dump_start include/linux/netlink.h:214 [inline] xfrm_user_rcv_msg+0x8a3/0x9b0 net/xfrm/xfrm_user.c:2577 netlink_rcv_skb+0x37e/0x600 net/netlink/af_netlink.c:2448 xfrm_netlink_rcv+0xb2/0xf0 net/xfrm/xfrm_user.c:2598 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0x1680/0x1750 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901 sock_sendmsg_nosec net/socket.c:629 [inline] sock_sendmsg net/socket.c:639 [inline] ___sys_sendmsg+0xec8/0x1320 net/socket.c:2117 __sys_sendmsg net/socket.c:2155 [inline] __do_sys_sendmsg net/socket.c:2164 [inline] __se_sys_sendmsg net/socket.c:2162 [inline] __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162 do_syscall_64+0x15b/0x230 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Local variable description: ----upt.i@dump_one_policy Variable was created at: dump_one_policy+0x78/0x1090 net/xfrm/xfrm_user.c:1689 xfrm_policy_walk+0x45a/0xd00 net/xfrm/xfrm_policy.c:1013 Byte 130 of 137 is uninitialized Memory access starts at ffff88019550407f Fixes: c0144beaeca42 ("[XFRM] netlink: Use nla_put()/NLA_PUT() variantes") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2018-06-19 12:35:07 +08:00
struct xfrm_userpolicy_type upt;
/* Sadly there are two holes in struct xfrm_userpolicy_type */
memset(&upt, 0, sizeof(upt));
upt.type = type;
return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt);
}
#else
static inline int copy_to_user_policy_type(u8 type, struct sk_buff *skb)
{
return 0;
}
#endif
static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr)
{
struct xfrm_dump_info *sp = ptr;
struct xfrm_userpolicy_info *p;
struct sk_buff *in_skb = sp->in_skb;
struct sk_buff *skb = sp->out_skb;
struct xfrm_translator *xtr;
struct nlmsghdr *nlh;
int err;
nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, sp->nlmsg_seq,
XFRM_MSG_NEWPOLICY, sizeof(*p), sp->nlmsg_flags);
if (nlh == NULL)
return -EMSGSIZE;
p = nlmsg_data(nlh);
copy_to_user_policy(xp, p, dir);
err = copy_to_user_tmpl(xp, skb);
if (!err)
err = copy_to_user_sec_ctx(xp, skb);
if (!err)
err = copy_to_user_policy_type(xp->type, skb);
if (!err)
err = xfrm_mark_put(skb, &xp->mark);
if (!err)
err = xfrm_if_id_put(skb, xp->if_id);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
nlmsg_end(skb, nlh);
xtr = xfrm_get_translator();
if (xtr) {
err = xtr->alloc_compat(skb, nlh);
xfrm_put_translator(xtr);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
}
return 0;
}
static int xfrm_dump_policy_done(struct netlink_callback *cb)
{
struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args;
struct net *net = sock_net(cb->skb->sk);
xfrm_policy_walk_done(walk, net);
return 0;
}
static int xfrm_dump_policy_start(struct netlink_callback *cb)
{
struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args;
BUILD_BUG_ON(sizeof(*walk) > sizeof(cb->args));
xfrm_policy_walk_init(walk, XFRM_POLICY_TYPE_ANY);
return 0;
}
static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args;
struct xfrm_dump_info info;
info.in_skb = cb->skb;
info.out_skb = skb;
info.nlmsg_seq = cb->nlh->nlmsg_seq;
info.nlmsg_flags = NLM_F_MULTI;
(void) xfrm_policy_walk(net, walk, dump_one_policy, &info);
return skb->len;
}
static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb,
struct xfrm_policy *xp,
int dir, u32 seq)
{
struct xfrm_dump_info info;
struct sk_buff *skb;
int err;
skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!skb)
return ERR_PTR(-ENOMEM);
info.in_skb = in_skb;
info.out_skb = skb;
info.nlmsg_seq = seq;
info.nlmsg_flags = 0;
err = dump_one_policy(xp, dir, 0, &info);
if (err) {
kfree_skb(skb);
return ERR_PTR(err);
}
return skb;
}
static int xfrm_notify_userpolicy(struct net *net)
{
struct xfrm_userpolicy_default *up;
int len = NLMSG_ALIGN(sizeof(*up));
struct nlmsghdr *nlh;
struct sk_buff *skb;
int err;
skb = nlmsg_new(len, GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_GETDEFAULT, sizeof(*up), 0);
if (nlh == NULL) {
kfree_skb(skb);
return -EMSGSIZE;
}
up = nlmsg_data(nlh);
up->in = net->xfrm.policy_default[XFRM_POLICY_IN];
up->fwd = net->xfrm.policy_default[XFRM_POLICY_FWD];
up->out = net->xfrm.policy_default[XFRM_POLICY_OUT];
nlmsg_end(skb, nlh);
rcu_read_lock();
err = xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
rcu_read_unlock();
return err;
}
static bool xfrm_userpolicy_is_valid(__u8 policy)
{
return policy == XFRM_USERPOLICY_BLOCK ||
policy == XFRM_USERPOLICY_ACCEPT;
}
static int xfrm_set_default(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_userpolicy_default *up = nlmsg_data(nlh);
if (xfrm_userpolicy_is_valid(up->in))
net->xfrm.policy_default[XFRM_POLICY_IN] = up->in;
if (xfrm_userpolicy_is_valid(up->fwd))
net->xfrm.policy_default[XFRM_POLICY_FWD] = up->fwd;
if (xfrm_userpolicy_is_valid(up->out))
net->xfrm.policy_default[XFRM_POLICY_OUT] = up->out;
rt_genid_bump_all(net);
xfrm_notify_userpolicy(net);
return 0;
}
static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct sk_buff *r_skb;
struct nlmsghdr *r_nlh;
struct net *net = sock_net(skb->sk);
struct xfrm_userpolicy_default *r_up;
int len = NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_default));
u32 portid = NETLINK_CB(skb).portid;
u32 seq = nlh->nlmsg_seq;
r_skb = nlmsg_new(len, GFP_ATOMIC);
if (!r_skb)
return -ENOMEM;
r_nlh = nlmsg_put(r_skb, portid, seq, XFRM_MSG_GETDEFAULT, sizeof(*r_up), 0);
if (!r_nlh) {
kfree_skb(r_skb);
return -EMSGSIZE;
}
r_up = nlmsg_data(r_nlh);
r_up->in = net->xfrm.policy_default[XFRM_POLICY_IN];
r_up->fwd = net->xfrm.policy_default[XFRM_POLICY_FWD];
r_up->out = net->xfrm.policy_default[XFRM_POLICY_OUT];
nlmsg_end(r_skb, r_nlh);
return nlmsg_unicast(net->xfrm.nlsk, r_skb, portid);
}
static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_policy *xp;
struct xfrm_userpolicy_id *p;
u8 type = XFRM_POLICY_TYPE_MAIN;
int err;
struct km_event c;
int delete;
struct xfrm_mark m;
u32 if_id = 0;
p = nlmsg_data(nlh);
delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY;
err = copy_from_user_policy_type(&type, attrs);
if (err)
return err;
err = verify_policy_dir(p->dir);
if (err)
return err;
if (attrs[XFRMA_IF_ID])
if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
xfrm_mark_get(attrs, &m);
if (p->index)
xp = xfrm_policy_byid(net, &m, if_id, type, p->dir,
p->index, delete, &err);
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
else {
struct nlattr *rt = attrs[XFRMA_SEC_CTX];
struct xfrm_sec_ctx *ctx;
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
err = verify_sec_ctx_len(attrs);
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
if (err)
return err;
ctx = NULL;
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
if (rt) {
struct xfrm_user_sec_ctx *uctx = nla_data(rt);
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
selinux: add gfp argument to security_xfrm_policy_alloc and fix callers security_xfrm_policy_alloc can be called in atomic context so the allocation should be done with GFP_ATOMIC. Add an argument to let the callers choose the appropriate way. In order to do so a gfp argument needs to be added to the method xfrm_policy_alloc_security in struct security_operations and to the internal function selinux_xfrm_alloc_user. After that switch to GFP_ATOMIC in the atomic callers and leave GFP_KERNEL as before for the rest. The path that needed the gfp argument addition is: security_xfrm_policy_alloc -> security_ops.xfrm_policy_alloc_security -> all users of xfrm_policy_alloc_security (e.g. selinux_xfrm_policy_alloc) -> selinux_xfrm_alloc_user (here the allocation used to be GFP_KERNEL only) Now adding a gfp argument to selinux_xfrm_alloc_user requires us to also add it to security_context_to_sid which is used inside and prior to this patch did only GFP_KERNEL allocation. So add gfp argument to security_context_to_sid and adjust all of its callers as well. CC: Paul Moore <paul@paul-moore.com> CC: Dave Jones <davej@redhat.com> CC: Steffen Klassert <steffen.klassert@secunet.com> CC: Fan Du <fan.du@windriver.com> CC: David S. Miller <davem@davemloft.net> CC: LSM list <linux-security-module@vger.kernel.org> CC: SELinux list <selinux@tycho.nsa.gov> Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Acked-by: Paul Moore <paul@paul-moore.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-03-07 19:44:19 +08:00
err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
if (err)
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
return err;
}
xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir,
&p->sel, ctx, delete, &err);
security_xfrm_policy_free(ctx);
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
}
if (xp == NULL)
return -ENOENT;
if (!delete) {
struct sk_buff *resp_skb;
resp_skb = xfrm_policy_netlink(skb, xp, p->dir, nlh->nlmsg_seq);
if (IS_ERR(resp_skb)) {
err = PTR_ERR(resp_skb);
} else {
err = nlmsg_unicast(net->xfrm.nlsk, resp_skb,
NETLINK_CB(skb).portid);
}
} else {
xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
if (err != 0)
[LSM-IPsec]: SELinux Authorize This patch contains a fix for the previous patch that adds security contexts to IPsec policies and security associations. In the previous patch, no authorization (besides the check for write permissions to SAD and SPD) is required to delete IPsec policies and security assocations with security contexts. Thus a user authorized to change SAD and SPD can bypass the IPsec policy authorization by simply deleteing policies with security contexts. To fix this security hole, an additional authorization check is added for removing security policies and security associations with security contexts. Note that if no security context is supplied on add or present on policy to be deleted, the SELinux module allows the change unconditionally. The hook is called on deletion when no context is present, which we may want to change. At present, I left it up to the module. LSM changes: The patch adds two new LSM hooks: xfrm_policy_delete and xfrm_state_delete. The new hooks are necessary to authorize deletion of IPsec policies that have security contexts. The existing hooks xfrm_policy_free and xfrm_state_free lack the context to do the authorization, so I decided to split authorization of deletion and memory management of security data, as is typical in the LSM interface. Use: The new delete hooks are checked when xfrm_policy or xfrm_state are deleted by either the xfrm_user interface (xfrm_get_policy, xfrm_del_sa) or the pfkey interface (pfkey_spddelete, pfkey_delete). SELinux changes: The new policy_delete and state_delete functions are added. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 14:39:49 +08:00
goto out;
c.data.byid = p->index;
c.event = nlh->nlmsg_type;
c.seq = nlh->nlmsg_seq;
c.portid = nlh->nlmsg_pid;
km_policy_notify(xp, p->dir, &c);
}
[LSM-IPsec]: SELinux Authorize This patch contains a fix for the previous patch that adds security contexts to IPsec policies and security associations. In the previous patch, no authorization (besides the check for write permissions to SAD and SPD) is required to delete IPsec policies and security assocations with security contexts. Thus a user authorized to change SAD and SPD can bypass the IPsec policy authorization by simply deleteing policies with security contexts. To fix this security hole, an additional authorization check is added for removing security policies and security associations with security contexts. Note that if no security context is supplied on add or present on policy to be deleted, the SELinux module allows the change unconditionally. The hook is called on deletion when no context is present, which we may want to change. At present, I left it up to the module. LSM changes: The patch adds two new LSM hooks: xfrm_policy_delete and xfrm_state_delete. The new hooks are necessary to authorize deletion of IPsec policies that have security contexts. The existing hooks xfrm_policy_free and xfrm_state_free lack the context to do the authorization, so I decided to split authorization of deletion and memory management of security data, as is typical in the LSM interface. Use: The new delete hooks are checked when xfrm_policy or xfrm_state are deleted by either the xfrm_user interface (xfrm_get_policy, xfrm_del_sa) or the pfkey interface (pfkey_spddelete, pfkey_delete). SELinux changes: The new policy_delete and state_delete functions are added. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 14:39:49 +08:00
out:
xfrm_pol_put(xp);
return err;
}
static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct km_event c;
struct xfrm_usersa_flush *p = nlmsg_data(nlh);
int err;
xfrm: destroy xfrm_state synchronously on net exit path xfrm_state_put() moves struct xfrm_state to the GC list and schedules the GC work to clean it up. On net exit call path, xfrm_state_flush() is called to clean up and xfrm_flush_gc() is called to wait for the GC work to complete before exit. However, this doesn't work because one of the ->destructor(), ipcomp_destroy(), schedules the same GC work again inside the GC work. It is hard to wait for such a nested async callback. This is also why syzbot still reports the following warning: WARNING: CPU: 1 PID: 33 at net/ipv6/xfrm6_tunnel.c:351 xfrm6_tunnel_net_exit+0x2cb/0x500 net/ipv6/xfrm6_tunnel.c:351 ... ops_exit_list.isra.0+0xb0/0x160 net/core/net_namespace.c:153 cleanup_net+0x51d/0xb10 net/core/net_namespace.c:551 process_one_work+0xd0c/0x1ce0 kernel/workqueue.c:2153 worker_thread+0x143/0x14a0 kernel/workqueue.c:2296 kthread+0x357/0x430 kernel/kthread.c:246 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352 In fact, it is perfectly fine to bypass GC and destroy xfrm_state synchronously on net exit call path, because it is in process context and doesn't need a work struct to do any blocking work. This patch introduces xfrm_state_put_sync() which simply bypasses GC, and lets its callers to decide whether to use this synchronous version. On net exit path, xfrm_state_fini() and xfrm6_tunnel_net_exit() use it. And, as ipcomp_destroy() itself is blocking, it can use xfrm_state_put_sync() directly too. Also rename xfrm_state_gc_destroy() to ___xfrm_state_destroy() to reflect this change. Fixes: b48c05ab5d32 ("xfrm: Fix warning in xfrm6_tunnel_net_exit.") Reported-and-tested-by: syzbot+e9aebef558e3ed673934@syzkaller.appspotmail.com Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2019-02-01 05:05:49 +08:00
err = xfrm_state_flush(net, p->proto, true, false);
if (err) {
if (err == -ESRCH) /* empty table */
return 0;
return err;
}
c.data.proto = p->proto;
c.event = nlh->nlmsg_type;
c.seq = nlh->nlmsg_seq;
c.portid = nlh->nlmsg_pid;
c.net = net;
km_state_notify(NULL, &c);
return 0;
}
static inline unsigned int xfrm_aevent_msgsize(struct xfrm_state *x)
{
unsigned int replay_size = x->replay_esn ?
xfrm_replay_state_esn_len(x->replay_esn) :
sizeof(struct xfrm_replay_state);
return NLMSG_ALIGN(sizeof(struct xfrm_aevent_id))
+ nla_total_size(replay_size)
+ nla_total_size_64bit(sizeof(struct xfrm_lifetime_cur))
+ nla_total_size(sizeof(struct xfrm_mark))
+ nla_total_size(4) /* XFRM_AE_RTHR */
+ nla_total_size(4); /* XFRM_AE_ETHR */
}
static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c)
{
struct xfrm_aevent_id *id;
struct nlmsghdr *nlh;
int err;
nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_NEWAE, sizeof(*id), 0);
if (nlh == NULL)
return -EMSGSIZE;
id = nlmsg_data(nlh);
memset(&id->sa_id, 0, sizeof(id->sa_id));
memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr));
id->sa_id.spi = x->id.spi;
id->sa_id.family = x->props.family;
id->sa_id.proto = x->id.proto;
memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr));
id->reqid = x->props.reqid;
id->flags = c->data.aevent;
if (x->replay_esn) {
err = nla_put(skb, XFRMA_REPLAY_ESN_VAL,
xfrm_replay_state_esn_len(x->replay_esn),
x->replay_esn);
} else {
err = nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay),
&x->replay);
}
if (err)
goto out_cancel;
err = nla_put_64bit(skb, XFRMA_LTIME_VAL, sizeof(x->curlft), &x->curlft,
XFRMA_PAD);
if (err)
goto out_cancel;
if (id->flags & XFRM_AE_RTHR) {
err = nla_put_u32(skb, XFRMA_REPLAY_THRESH, x->replay_maxdiff);
if (err)
goto out_cancel;
}
if (id->flags & XFRM_AE_ETHR) {
err = nla_put_u32(skb, XFRMA_ETIMER_THRESH,
x->replay_maxage * 10 / HZ);
if (err)
goto out_cancel;
}
err = xfrm_mark_put(skb, &x->mark);
if (err)
goto out_cancel;
err = xfrm_if_id_put(skb, x->if_id);
if (err)
goto out_cancel;
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
out_cancel:
nlmsg_cancel(skb, nlh);
return err;
}
static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_state *x;
struct sk_buff *r_skb;
int err;
struct km_event c;
u32 mark;
struct xfrm_mark m;
struct xfrm_aevent_id *p = nlmsg_data(nlh);
struct xfrm_usersa_id *id = &p->sa_id;
mark = xfrm_mark_get(attrs, &m);
x = xfrm_state_lookup(net, mark, &id->daddr, id->spi, id->proto, id->family);
if (x == NULL)
return -ESRCH;
r_skb = nlmsg_new(xfrm_aevent_msgsize(x), GFP_ATOMIC);
if (r_skb == NULL) {
xfrm_state_put(x);
return -ENOMEM;
}
/*
* XXX: is this lock really needed - none of the other
* gets lock (the concern is things getting updated
* while we are still reading) - jhs
*/
spin_lock_bh(&x->lock);
c.data.aevent = p->flags;
c.seq = nlh->nlmsg_seq;
c.portid = nlh->nlmsg_pid;
err = build_aevent(r_skb, x, &c);
BUG_ON(err < 0);
err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).portid);
spin_unlock_bh(&x->lock);
xfrm_state_put(x);
return err;
}
static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_state *x;
struct km_event c;
int err = -EINVAL;
u32 mark = 0;
struct xfrm_mark m;
struct xfrm_aevent_id *p = nlmsg_data(nlh);
struct nlattr *rp = attrs[XFRMA_REPLAY_VAL];
struct nlattr *re = attrs[XFRMA_REPLAY_ESN_VAL];
struct nlattr *lt = attrs[XFRMA_LTIME_VAL];
struct nlattr *et = attrs[XFRMA_ETIMER_THRESH];
struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH];
if (!lt && !rp && !re && !et && !rt)
return err;
/* pedantic mode - thou shalt sayeth replaceth */
if (!(nlh->nlmsg_flags&NLM_F_REPLACE))
return err;
mark = xfrm_mark_get(attrs, &m);
x = xfrm_state_lookup(net, mark, &p->sa_id.daddr, p->sa_id.spi, p->sa_id.proto, p->sa_id.family);
if (x == NULL)
return -ESRCH;
if (x->km.state != XFRM_STATE_VALID)
goto out;
err = xfrm_replay_verify_len(x->replay_esn, re);
if (err)
goto out;
spin_lock_bh(&x->lock);
xfrm_update_ae_params(x, attrs, 1);
spin_unlock_bh(&x->lock);
c.event = nlh->nlmsg_type;
c.seq = nlh->nlmsg_seq;
c.portid = nlh->nlmsg_pid;
c.data.aevent = XFRM_AE_CU;
km_state_notify(x, &c);
err = 0;
out:
xfrm_state_put(x);
return err;
}
static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct km_event c;
u8 type = XFRM_POLICY_TYPE_MAIN;
int err;
err = copy_from_user_policy_type(&type, attrs);
if (err)
return err;
err = xfrm_policy_flush(net, type, true);
if (err) {
if (err == -ESRCH) /* empty table */
return 0;
return err;
}
c.data.type = type;
c.event = nlh->nlmsg_type;
c.seq = nlh->nlmsg_seq;
c.portid = nlh->nlmsg_pid;
c.net = net;
km_policy_notify(NULL, 0, &c);
return 0;
}
static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_policy *xp;
struct xfrm_user_polexpire *up = nlmsg_data(nlh);
struct xfrm_userpolicy_info *p = &up->pol;
u8 type = XFRM_POLICY_TYPE_MAIN;
int err = -ENOENT;
struct xfrm_mark m;
u32 if_id = 0;
err = copy_from_user_policy_type(&type, attrs);
if (err)
return err;
err = verify_policy_dir(p->dir);
if (err)
return err;
if (attrs[XFRMA_IF_ID])
if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
xfrm_mark_get(attrs, &m);
if (p->index)
xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index,
0, &err);
else {
struct nlattr *rt = attrs[XFRMA_SEC_CTX];
struct xfrm_sec_ctx *ctx;
err = verify_sec_ctx_len(attrs);
if (err)
return err;
ctx = NULL;
if (rt) {
struct xfrm_user_sec_ctx *uctx = nla_data(rt);
selinux: add gfp argument to security_xfrm_policy_alloc and fix callers security_xfrm_policy_alloc can be called in atomic context so the allocation should be done with GFP_ATOMIC. Add an argument to let the callers choose the appropriate way. In order to do so a gfp argument needs to be added to the method xfrm_policy_alloc_security in struct security_operations and to the internal function selinux_xfrm_alloc_user. After that switch to GFP_ATOMIC in the atomic callers and leave GFP_KERNEL as before for the rest. The path that needed the gfp argument addition is: security_xfrm_policy_alloc -> security_ops.xfrm_policy_alloc_security -> all users of xfrm_policy_alloc_security (e.g. selinux_xfrm_policy_alloc) -> selinux_xfrm_alloc_user (here the allocation used to be GFP_KERNEL only) Now adding a gfp argument to selinux_xfrm_alloc_user requires us to also add it to security_context_to_sid which is used inside and prior to this patch did only GFP_KERNEL allocation. So add gfp argument to security_context_to_sid and adjust all of its callers as well. CC: Paul Moore <paul@paul-moore.com> CC: Dave Jones <davej@redhat.com> CC: Steffen Klassert <steffen.klassert@secunet.com> CC: Fan Du <fan.du@windriver.com> CC: David S. Miller <davem@davemloft.net> CC: LSM list <linux-security-module@vger.kernel.org> CC: SELinux list <selinux@tycho.nsa.gov> Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Acked-by: Paul Moore <paul@paul-moore.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-03-07 19:44:19 +08:00
err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
if (err)
return err;
}
xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir,
&p->sel, ctx, 0, &err);
security_xfrm_policy_free(ctx);
}
if (xp == NULL)
return -ENOENT;
if (unlikely(xp->walk.dead))
goto out;
err = 0;
if (up->hard) {
xfrm_policy_delete(xp, p->dir);
xfrm_audit_policy_delete(xp, 1, true);
}
km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid);
out:
xfrm_pol_put(xp);
return err;
}
static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_state *x;
int err;
struct xfrm_user_expire *ue = nlmsg_data(nlh);
struct xfrm_usersa_info *p = &ue->state;
struct xfrm_mark m;
u32 mark = xfrm_mark_get(attrs, &m);
x = xfrm_state_lookup(net, mark, &p->id.daddr, p->id.spi, p->id.proto, p->family);
err = -ENOENT;
if (x == NULL)
return err;
spin_lock_bh(&x->lock);
err = -EINVAL;
if (x->km.state != XFRM_STATE_VALID)
goto out;
km_state_expired(x, ue->hard, nlh->nlmsg_pid);
if (ue->hard) {
__xfrm_state_delete(x);
xfrm_audit_state_delete(x, 1, true);
}
err = 0;
out:
spin_unlock_bh(&x->lock);
xfrm_state_put(x);
return err;
}
static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct net *net = sock_net(skb->sk);
struct xfrm_policy *xp;
struct xfrm_user_tmpl *ut;
int i;
struct nlattr *rt = attrs[XFRMA_TMPL];
struct xfrm_mark mark;
struct xfrm_user_acquire *ua = nlmsg_data(nlh);
struct xfrm_state *x = xfrm_state_alloc(net);
int err = -ENOMEM;
if (!x)
goto nomem;
xfrm_mark_get(attrs, &mark);
err = verify_newpolicy_info(&ua->policy);
if (err)
goto free_state;
err = verify_sec_ctx_len(attrs);
if (err)
goto free_state;
/* build an XP */
xp = xfrm_policy_construct(net, &ua->policy, attrs, &err);
if (!xp)
goto free_state;
memcpy(&x->id, &ua->id, sizeof(ua->id));
memcpy(&x->props.saddr, &ua->saddr, sizeof(ua->saddr));
memcpy(&x->sel, &ua->sel, sizeof(ua->sel));
xp->mark.m = x->mark.m = mark.m;
xp->mark.v = x->mark.v = mark.v;
ut = nla_data(rt);
/* extract the templates and for each call km_key */
for (i = 0; i < xp->xfrm_nr; i++, ut++) {
struct xfrm_tmpl *t = &xp->xfrm_vec[i];
memcpy(&x->id, &t->id, sizeof(x->id));
x->props.mode = t->mode;
x->props.reqid = t->reqid;
x->props.family = ut->family;
t->aalgos = ua->aalgos;
t->ealgos = ua->ealgos;
t->calgos = ua->calgos;
err = km_query(x, t, xp);
}
xfrm_state_free(x);
kfree(xp);
return 0;
free_state:
xfrm_state_free(x);
nomem:
return err;
}
#ifdef CONFIG_XFRM_MIGRATE
static int copy_from_user_migrate(struct xfrm_migrate *ma,
struct xfrm_kmaddress *k,
struct nlattr **attrs, int *num)
{
struct nlattr *rt = attrs[XFRMA_MIGRATE];
struct xfrm_user_migrate *um;
int i, num_migrate;
if (k != NULL) {
struct xfrm_user_kmaddress *uk;
uk = nla_data(attrs[XFRMA_KMADDRESS]);
memcpy(&k->local, &uk->local, sizeof(k->local));
memcpy(&k->remote, &uk->remote, sizeof(k->remote));
k->family = uk->family;
k->reserved = uk->reserved;
}
um = nla_data(rt);
num_migrate = nla_len(rt) / sizeof(*um);
if (num_migrate <= 0 || num_migrate > XFRM_MAX_DEPTH)
return -EINVAL;
for (i = 0; i < num_migrate; i++, um++, ma++) {
memcpy(&ma->old_daddr, &um->old_daddr, sizeof(ma->old_daddr));
memcpy(&ma->old_saddr, &um->old_saddr, sizeof(ma->old_saddr));
memcpy(&ma->new_daddr, &um->new_daddr, sizeof(ma->new_daddr));
memcpy(&ma->new_saddr, &um->new_saddr, sizeof(ma->new_saddr));
ma->proto = um->proto;
ma->mode = um->mode;
ma->reqid = um->reqid;
ma->old_family = um->old_family;
ma->new_family = um->new_family;
}
*num = i;
return 0;
}
static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct xfrm_userpolicy_id *pi = nlmsg_data(nlh);
struct xfrm_migrate m[XFRM_MAX_DEPTH];
struct xfrm_kmaddress km, *kmp;
u8 type;
int err;
int n = 0;
struct net *net = sock_net(skb->sk);
struct xfrm_encap_tmpl *encap = NULL;
xfrm: Check if_id in xfrm_migrate This patch enables distinguishing SAs and SPs based on if_id during the xfrm_migrate flow. This ensures support for xfrm interfaces throughout the SA/SP lifecycle. When there are multiple existing SPs with the same direction, the same xfrm_selector and different endpoint addresses, xfrm_migrate might fail with ENODATA. Specifically, the code path for performing xfrm_migrate is: Stage 1: find policy to migrate with xfrm_migrate_policy_find(sel, dir, type, net) Stage 2: find and update state(s) with xfrm_migrate_state_find(mp, net) Stage 3: update endpoint address(es) of template(s) with xfrm_policy_migrate(pol, m, num_migrate) Currently "Stage 1" always returns the first xfrm_policy that matches, and "Stage 3" looks for the xfrm_tmpl that matches the old endpoint address. Thus if there are multiple xfrm_policy with same selector, direction, type and net, "Stage 1" might rertun a wrong xfrm_policy and "Stage 3" will fail with ENODATA because it cannot find a xfrm_tmpl with the matching endpoint address. The fix is to allow userspace to pass an if_id and add if_id to the matching rule in Stage 1 and Stage 2 since if_id is a unique ID for xfrm_policy and xfrm_state. For compatibility, if_id will only be checked if the attribute is set. Tested with additions to Android's kernel unit test suite: https://android-review.googlesource.com/c/kernel/tests/+/1668886 Signed-off-by: Yan Yan <evitayan@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2022-01-19 08:00:13 +08:00
u32 if_id = 0;
if (attrs[XFRMA_MIGRATE] == NULL)
return -EINVAL;
kmp = attrs[XFRMA_KMADDRESS] ? &km : NULL;
err = copy_from_user_policy_type(&type, attrs);
if (err)
return err;
err = copy_from_user_migrate((struct xfrm_migrate *)m, kmp, attrs, &n);
if (err)
return err;
if (!n)
return 0;
if (attrs[XFRMA_ENCAP]) {
encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]),
sizeof(*encap), GFP_KERNEL);
if (!encap)
return -ENOMEM;
}
xfrm: Check if_id in xfrm_migrate This patch enables distinguishing SAs and SPs based on if_id during the xfrm_migrate flow. This ensures support for xfrm interfaces throughout the SA/SP lifecycle. When there are multiple existing SPs with the same direction, the same xfrm_selector and different endpoint addresses, xfrm_migrate might fail with ENODATA. Specifically, the code path for performing xfrm_migrate is: Stage 1: find policy to migrate with xfrm_migrate_policy_find(sel, dir, type, net) Stage 2: find and update state(s) with xfrm_migrate_state_find(mp, net) Stage 3: update endpoint address(es) of template(s) with xfrm_policy_migrate(pol, m, num_migrate) Currently "Stage 1" always returns the first xfrm_policy that matches, and "Stage 3" looks for the xfrm_tmpl that matches the old endpoint address. Thus if there are multiple xfrm_policy with same selector, direction, type and net, "Stage 1" might rertun a wrong xfrm_policy and "Stage 3" will fail with ENODATA because it cannot find a xfrm_tmpl with the matching endpoint address. The fix is to allow userspace to pass an if_id and add if_id to the matching rule in Stage 1 and Stage 2 since if_id is a unique ID for xfrm_policy and xfrm_state. For compatibility, if_id will only be checked if the attribute is set. Tested with additions to Android's kernel unit test suite: https://android-review.googlesource.com/c/kernel/tests/+/1668886 Signed-off-by: Yan Yan <evitayan@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2022-01-19 08:00:13 +08:00
if (attrs[XFRMA_IF_ID])
if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap, if_id);
kfree(encap);
return err;
}
#else
static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
return -ENOPROTOOPT;
}
#endif
#ifdef CONFIG_XFRM_MIGRATE
static int copy_to_user_migrate(const struct xfrm_migrate *m, struct sk_buff *skb)
{
struct xfrm_user_migrate um;
memset(&um, 0, sizeof(um));
um.proto = m->proto;
um.mode = m->mode;
um.reqid = m->reqid;
um.old_family = m->old_family;
memcpy(&um.old_daddr, &m->old_daddr, sizeof(um.old_daddr));
memcpy(&um.old_saddr, &m->old_saddr, sizeof(um.old_saddr));
um.new_family = m->new_family;
memcpy(&um.new_daddr, &m->new_daddr, sizeof(um.new_daddr));
memcpy(&um.new_saddr, &m->new_saddr, sizeof(um.new_saddr));
return nla_put(skb, XFRMA_MIGRATE, sizeof(um), &um);
}
static int copy_to_user_kmaddress(const struct xfrm_kmaddress *k, struct sk_buff *skb)
{
struct xfrm_user_kmaddress uk;
memset(&uk, 0, sizeof(uk));
uk.family = k->family;
uk.reserved = k->reserved;
memcpy(&uk.local, &k->local, sizeof(uk.local));
memcpy(&uk.remote, &k->remote, sizeof(uk.remote));
return nla_put(skb, XFRMA_KMADDRESS, sizeof(uk), &uk);
}
static inline unsigned int xfrm_migrate_msgsize(int num_migrate, int with_kma,
int with_encp)
{
return NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_id))
+ (with_kma ? nla_total_size(sizeof(struct xfrm_kmaddress)) : 0)
+ (with_encp ? nla_total_size(sizeof(struct xfrm_encap_tmpl)) : 0)
+ nla_total_size(sizeof(struct xfrm_user_migrate) * num_migrate)
+ userpolicy_type_attrsize();
}
static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m,
int num_migrate, const struct xfrm_kmaddress *k,
const struct xfrm_selector *sel,
const struct xfrm_encap_tmpl *encap, u8 dir, u8 type)
{
const struct xfrm_migrate *mp;
struct xfrm_userpolicy_id *pol_id;
struct nlmsghdr *nlh;
int i, err;
nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_MIGRATE, sizeof(*pol_id), 0);
if (nlh == NULL)
return -EMSGSIZE;
pol_id = nlmsg_data(nlh);
/* copy data from selector, dir, and type to the pol_id */
memset(pol_id, 0, sizeof(*pol_id));
memcpy(&pol_id->sel, sel, sizeof(pol_id->sel));
pol_id->dir = dir;
if (k != NULL) {
err = copy_to_user_kmaddress(k, skb);
if (err)
goto out_cancel;
}
if (encap) {
err = nla_put(skb, XFRMA_ENCAP, sizeof(*encap), encap);
if (err)
goto out_cancel;
}
err = copy_to_user_policy_type(type, skb);
if (err)
goto out_cancel;
for (i = 0, mp = m ; i < num_migrate; i++, mp++) {
err = copy_to_user_migrate(mp, skb);
if (err)
goto out_cancel;
}
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
out_cancel:
nlmsg_cancel(skb, nlh);
return err;
}
static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
const struct xfrm_migrate *m, int num_migrate,
const struct xfrm_kmaddress *k,
const struct xfrm_encap_tmpl *encap)
{
struct net *net = &init_net;
struct sk_buff *skb;
int err;
skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k, !!encap),
GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
/* build migrate */
err = build_migrate(skb, m, num_migrate, k, sel, encap, dir, type);
BUG_ON(err < 0);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE);
}
#else
static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
const struct xfrm_migrate *m, int num_migrate,
const struct xfrm_kmaddress *k,
const struct xfrm_encap_tmpl *encap)
{
return -ENOPROTOOPT;
}
#endif
#define XMSGSIZE(type) sizeof(struct type)
const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
[XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info),
[XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
[XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
[XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info),
[XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
[XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
[XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userspi_info),
[XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_acquire),
[XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_expire),
[XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info),
[XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info),
[XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_polexpire),
[XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush),
[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0,
[XFRM_MSG_NEWAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
[XFRM_MSG_GETAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
[XFRM_MSG_REPORT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report),
[XFRM_MSG_MIGRATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
[XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = sizeof(u32),
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
[XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32),
[XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32),
[XFRM_MSG_SETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default),
[XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default),
};
EXPORT_SYMBOL_GPL(xfrm_msg_min);
#undef XMSGSIZE
const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
[XFRMA_SA] = { .len = sizeof(struct xfrm_usersa_info)},
[XFRMA_POLICY] = { .len = sizeof(struct xfrm_userpolicy_info)},
[XFRMA_LASTUSED] = { .type = NLA_U64},
[XFRMA_ALG_AUTH_TRUNC] = { .len = sizeof(struct xfrm_algo_auth)},
[XFRMA_ALG_AEAD] = { .len = sizeof(struct xfrm_algo_aead) },
[XFRMA_ALG_AUTH] = { .len = sizeof(struct xfrm_algo) },
[XFRMA_ALG_CRYPT] = { .len = sizeof(struct xfrm_algo) },
[XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) },
[XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) },
[XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) },
[XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) },
[XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) },
[XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) },
[XFRMA_REPLAY_THRESH] = { .type = NLA_U32 },
[XFRMA_ETIMER_THRESH] = { .type = NLA_U32 },
[XFRMA_SRCADDR] = { .len = sizeof(xfrm_address_t) },
[XFRMA_COADDR] = { .len = sizeof(xfrm_address_t) },
[XFRMA_POLICY_TYPE] = { .len = sizeof(struct xfrm_userpolicy_type)},
[XFRMA_MIGRATE] = { .len = sizeof(struct xfrm_user_migrate) },
[XFRMA_KMADDRESS] = { .len = sizeof(struct xfrm_user_kmaddress) },
[XFRMA_MARK] = { .len = sizeof(struct xfrm_mark) },
[XFRMA_TFCPAD] = { .type = NLA_U32 },
[XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) },
[XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 },
[XFRMA_PROTO] = { .type = NLA_U8 },
[XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) },
[XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) },
[XFRMA_SET_MARK] = { .type = NLA_U32 },
[XFRMA_SET_MARK_MASK] = { .type = NLA_U32 },
[XFRMA_IF_ID] = { .type = NLA_U32 },
};
EXPORT_SYMBOL_GPL(xfrma_policy);
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
[XFRMA_SPD_IPV4_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
[XFRMA_SPD_IPV6_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
};
static const struct xfrm_link {
int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **);
int (*start)(struct netlink_callback *);
int (*dump)(struct sk_buff *, struct netlink_callback *);
int (*done)(struct netlink_callback *);
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
const struct nla_policy *nla_pol;
int nla_max;
} xfrm_dispatch[XFRM_NR_MSGTYPES] = {
[XFRM_MSG_NEWSA - XFRM_MSG_BASE] = { .doit = xfrm_add_sa },
[XFRM_MSG_DELSA - XFRM_MSG_BASE] = { .doit = xfrm_del_sa },
[XFRM_MSG_GETSA - XFRM_MSG_BASE] = { .doit = xfrm_get_sa,
.dump = xfrm_dump_sa,
.done = xfrm_dump_sa_done },
[XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_add_policy },
[XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy },
[XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy,
.start = xfrm_dump_policy_start,
.dump = xfrm_dump_policy,
.done = xfrm_dump_policy_done },
[XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = { .doit = xfrm_alloc_userspi },
[XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_acquire },
[XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_sa_expire },
[XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_add_policy },
[XFRM_MSG_UPDSA - XFRM_MSG_BASE] = { .doit = xfrm_add_sa },
[XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_pol_expire},
[XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = { .doit = xfrm_flush_sa },
[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_flush_policy },
[XFRM_MSG_NEWAE - XFRM_MSG_BASE] = { .doit = xfrm_new_ae },
[XFRM_MSG_GETAE - XFRM_MSG_BASE] = { .doit = xfrm_get_ae },
[XFRM_MSG_MIGRATE - XFRM_MSG_BASE] = { .doit = xfrm_do_migrate },
[XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = { .doit = xfrm_get_sadinfo },
xfrm: configure policy hash table thresholds by netlink Enable to specify local and remote prefix length thresholds for the policy hash table via a netlink XFRM_MSG_NEWSPDINFO message. prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh). example: struct xfrmu_spdhthresh thresh4 = { .lbits = 0; .rbits = 24; }; struct xfrmu_spdhthresh thresh6 = { .lbits = 0; .rbits = 56; }; struct nlmsghdr *hdr; struct nl_msg *msg; msg = nlmsg_alloc(); hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST); nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4); nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6); nla_send_auto(sk, msg); The numbers are the policy selector minimum prefix lengths to put a policy in the hash table. - lbits is the local threshold (source address for out policies, destination address for in and fwd policies). - rbits is the remote threshold (destination address for out policies, source address for in and fwd policies). The default values are: XFRMA_SPD_IPV4_HTHRESH: 32 32 XFRMA_SPD_IPV6_HTHRESH: 128 128 Dynamic re-building of the SPD is performed when the thresholds values are changed. The current thresholds can be read via a XFRM_MSG_GETSPDINFO request: the kernel replies to XFRM_MSG_GETSPDINFO requests by an XFRM_MSG_NEWSPDINFO message, with both attributes XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH. Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-08-29 22:16:05 +08:00
[XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = { .doit = xfrm_set_spdinfo,
.nla_pol = xfrma_spd_policy,
.nla_max = XFRMA_SPD_MAX },
[XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = { .doit = xfrm_get_spdinfo },
[XFRM_MSG_SETDEFAULT - XFRM_MSG_BASE] = { .doit = xfrm_set_default },
[XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = { .doit = xfrm_get_default },
};
static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct nlattr *attrs[XFRMA_MAX+1];
const struct xfrm_link *link;
struct nlmsghdr *nlh64 = NULL;
int type, err;
type = nlh->nlmsg_type;
if (type > XFRM_MSG_MAX)
return -EINVAL;
type -= XFRM_MSG_BASE;
link = &xfrm_dispatch[type];
/* All operations require privileges, even GET */
if (!netlink_net_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (in_compat_syscall()) {
struct xfrm_translator *xtr = xfrm_get_translator();
if (!xtr)
return -EOPNOTSUPP;
nlh64 = xtr->rcv_msg_compat(nlh, link->nla_max,
link->nla_pol, extack);
xfrm_put_translator(xtr);
if (IS_ERR(nlh64))
return PTR_ERR(nlh64);
if (nlh64)
nlh = nlh64;
}
if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) &&
(nlh->nlmsg_flags & NLM_F_DUMP)) {
struct netlink_dump_control c = {
.start = link->start,
.dump = link->dump,
.done = link->done,
};
if (link->dump == NULL) {
err = -EINVAL;
goto err;
}
err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
goto 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 20:07:28 +08:00
err = nlmsg_parse_deprecated(nlh, xfrm_msg_min[type], attrs,
link->nla_max ? : XFRMA_MAX,
link->nla_pol ? : xfrma_policy, extack);
if (err < 0)
goto err;
if (link->doit == NULL) {
err = -EINVAL;
goto err;
}
err = link->doit(skb, nlh, attrs);
/* We need to free skb allocated in xfrm_alloc_compat() before
* returning from this function, because consume_skb() won't take
* care of frag_list since netlink destructor sets
* sbk->head to NULL. (see netlink_skb_destructor())
*/
if (skb_has_frag_list(skb)) {
kfree_skb(skb_shinfo(skb)->frag_list);
skb_shinfo(skb)->frag_list = NULL;
}
err:
kvfree(nlh64);
return err;
}
static void xfrm_netlink_rcv(struct sk_buff *skb)
{
struct net *net = sock_net(skb->sk);
mutex_lock(&net->xfrm.xfrm_cfg_mutex);
netlink_rcv_skb(skb, &xfrm_user_rcv_msg);
mutex_unlock(&net->xfrm.xfrm_cfg_mutex);
}
static inline unsigned int xfrm_expire_msgsize(void)
{
return NLMSG_ALIGN(sizeof(struct xfrm_user_expire))
+ nla_total_size(sizeof(struct xfrm_mark));
}
static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c)
{
struct xfrm_user_expire *ue;
struct nlmsghdr *nlh;
int err;
nlh = nlmsg_put(skb, c->portid, 0, XFRM_MSG_EXPIRE, sizeof(*ue), 0);
if (nlh == NULL)
return -EMSGSIZE;
ue = nlmsg_data(nlh);
copy_to_user_state(x, &ue->state);
ue->hard = (c->data.hard != 0) ? 1 : 0;
/* clear the padding bytes */
memset_after(ue, 0, hard);
err = xfrm_mark_put(skb, &x->mark);
if (err)
return err;
err = xfrm_if_id_put(skb, x->if_id);
if (err)
return err;
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
}
static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c)
{
struct net *net = xs_net(x);
struct sk_buff *skb;
skb = nlmsg_new(xfrm_expire_msgsize(), GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
if (build_expire(skb, x, c) < 0) {
kfree_skb(skb);
return -EMSGSIZE;
}
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
}
static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c)
{
struct net *net = xs_net(x);
struct sk_buff *skb;
int err;
skb = nlmsg_new(xfrm_aevent_msgsize(x), GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
err = build_aevent(skb, x, c);
BUG_ON(err < 0);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS);
}
static int xfrm_notify_sa_flush(const struct km_event *c)
{
struct net *net = c->net;
struct xfrm_usersa_flush *p;
struct nlmsghdr *nlh;
struct sk_buff *skb;
int len = NLMSG_ALIGN(sizeof(struct xfrm_usersa_flush));
skb = nlmsg_new(len, GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_FLUSHSA, sizeof(*p), 0);
if (nlh == NULL) {
kfree_skb(skb);
return -EMSGSIZE;
}
p = nlmsg_data(nlh);
p->proto = c->data.proto;
nlmsg_end(skb, nlh);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
}
static inline unsigned int xfrm_sa_len(struct xfrm_state *x)
{
unsigned int l = 0;
if (x->aead)
l += nla_total_size(aead_len(x->aead));
if (x->aalg) {
l += nla_total_size(sizeof(struct xfrm_algo) +
(x->aalg->alg_key_len + 7) / 8);
l += nla_total_size(xfrm_alg_auth_len(x->aalg));
}
if (x->ealg)
l += nla_total_size(xfrm_alg_len(x->ealg));
if (x->calg)
l += nla_total_size(sizeof(*x->calg));
if (x->encap)
l += nla_total_size(sizeof(*x->encap));
if (x->tfcpad)
l += nla_total_size(sizeof(x->tfcpad));
if (x->replay_esn)
l += nla_total_size(xfrm_replay_state_esn_len(x->replay_esn));
else
l += nla_total_size(sizeof(struct xfrm_replay_state));
if (x->security)
l += nla_total_size(sizeof(struct xfrm_user_sec_ctx) +
x->security->ctx_len);
if (x->coaddr)
l += nla_total_size(sizeof(*x->coaddr));
if (x->props.extra_flags)
l += nla_total_size(sizeof(x->props.extra_flags));
if (x->xso.dev)
l += nla_total_size(sizeof(struct xfrm_user_offload));
if (x->props.smark.v | x->props.smark.m) {
l += nla_total_size(sizeof(x->props.smark.v));
l += nla_total_size(sizeof(x->props.smark.m));
}
if (x->if_id)
l += nla_total_size(sizeof(x->if_id));
/* Must count x->lastused as it may become non-zero behind our back. */
l += nla_total_size_64bit(sizeof(u64));
if (x->mapping_maxage)
l += nla_total_size(sizeof(x->mapping_maxage));
return l;
}
static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c)
{
struct net *net = xs_net(x);
struct xfrm_usersa_info *p;
struct xfrm_usersa_id *id;
struct nlmsghdr *nlh;
struct sk_buff *skb;
unsigned int len = xfrm_sa_len(x);
unsigned int headlen;
int err;
headlen = sizeof(*p);
if (c->event == XFRM_MSG_DELSA) {
len += nla_total_size(headlen);
headlen = sizeof(*id);
len += nla_total_size(sizeof(struct xfrm_mark));
}
len += NLMSG_ALIGN(headlen);
skb = nlmsg_new(len, GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
nlh = nlmsg_put(skb, c->portid, c->seq, c->event, headlen, 0);
err = -EMSGSIZE;
if (nlh == NULL)
goto out_free_skb;
p = nlmsg_data(nlh);
if (c->event == XFRM_MSG_DELSA) {
struct nlattr *attr;
id = nlmsg_data(nlh);
memset(id, 0, sizeof(*id));
memcpy(&id->daddr, &x->id.daddr, sizeof(id->daddr));
id->spi = x->id.spi;
id->family = x->props.family;
id->proto = x->id.proto;
attr = nla_reserve(skb, XFRMA_SA, sizeof(*p));
err = -EMSGSIZE;
if (attr == NULL)
goto out_free_skb;
p = nla_data(attr);
}
err = copy_to_user_state_extra(x, p, skb);
if (err)
goto out_free_skb;
nlmsg_end(skb, nlh);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
out_free_skb:
kfree_skb(skb);
return err;
}
static int xfrm_send_state_notify(struct xfrm_state *x, const struct km_event *c)
{
switch (c->event) {
case XFRM_MSG_EXPIRE:
return xfrm_exp_state_notify(x, c);
case XFRM_MSG_NEWAE:
return xfrm_aevent_state_notify(x, c);
case XFRM_MSG_DELSA:
case XFRM_MSG_UPDSA:
case XFRM_MSG_NEWSA:
return xfrm_notify_sa(x, c);
case XFRM_MSG_FLUSHSA:
return xfrm_notify_sa_flush(c);
default:
printk(KERN_NOTICE "xfrm_user: Unknown SA event %d\n",
c->event);
break;
}
return 0;
}
static inline unsigned int xfrm_acquire_msgsize(struct xfrm_state *x,
struct xfrm_policy *xp)
{
return NLMSG_ALIGN(sizeof(struct xfrm_user_acquire))
+ nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr)
+ nla_total_size(sizeof(struct xfrm_mark))
+ nla_total_size(xfrm_user_sec_ctx_size(x->security))
+ userpolicy_type_attrsize();
}
static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
struct xfrm_tmpl *xt, struct xfrm_policy *xp)
{
__u32 seq = xfrm_get_acqseq();
struct xfrm_user_acquire *ua;
struct nlmsghdr *nlh;
int err;
nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_ACQUIRE, sizeof(*ua), 0);
if (nlh == NULL)
return -EMSGSIZE;
ua = nlmsg_data(nlh);
memcpy(&ua->id, &x->id, sizeof(ua->id));
memcpy(&ua->saddr, &x->props.saddr, sizeof(ua->saddr));
memcpy(&ua->sel, &x->sel, sizeof(ua->sel));
copy_to_user_policy(xp, &ua->policy, XFRM_POLICY_OUT);
ua->aalgos = xt->aalgos;
ua->ealgos = xt->ealgos;
ua->calgos = xt->calgos;
ua->seq = x->km.seq = seq;
err = copy_to_user_tmpl(xp, skb);
if (!err)
err = copy_to_user_state_sec_ctx(x, skb);
if (!err)
err = copy_to_user_policy_type(xp->type, skb);
if (!err)
err = xfrm_mark_put(skb, &xp->mark);
if (!err)
err = xfrm_if_id_put(skb, xp->if_id);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
}
static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt,
struct xfrm_policy *xp)
{
struct net *net = xs_net(x);
struct sk_buff *skb;
int err;
skb = nlmsg_new(xfrm_acquire_msgsize(x, xp), GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
err = build_acquire(skb, x, xt, xp);
BUG_ON(err < 0);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE);
}
/* User gives us xfrm_user_policy_info followed by an array of 0
* or more templates.
*/
static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt,
u8 *data, int len, int *dir)
{
struct net *net = sock_net(sk);
struct xfrm_userpolicy_info *p = (struct xfrm_userpolicy_info *)data;
struct xfrm_user_tmpl *ut = (struct xfrm_user_tmpl *) (p + 1);
struct xfrm_policy *xp;
int nr;
switch (sk->sk_family) {
case AF_INET:
if (opt != IP_XFRM_POLICY) {
*dir = -EOPNOTSUPP;
return NULL;
}
break;
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
if (opt != IPV6_XFRM_POLICY) {
*dir = -EOPNOTSUPP;
return NULL;
}
break;
#endif
default:
*dir = -EINVAL;
return NULL;
}
*dir = -EINVAL;
if (len < sizeof(*p) ||
verify_newpolicy_info(p))
return NULL;
nr = ((len - sizeof(*p)) / sizeof(*ut));
if (validate_tmpl(nr, ut, p->sel.family))
return NULL;
if (p->dir > XFRM_POLICY_OUT)
return NULL;
xp = xfrm_policy_alloc(net, GFP_ATOMIC);
if (xp == NULL) {
*dir = -ENOBUFS;
return NULL;
}
copy_from_user_policy(xp, p);
xp->type = XFRM_POLICY_TYPE_MAIN;
copy_templates(xp, ut, nr);
*dir = p->dir;
return xp;
}
static inline unsigned int xfrm_polexpire_msgsize(struct xfrm_policy *xp)
{
return NLMSG_ALIGN(sizeof(struct xfrm_user_polexpire))
+ nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr)
+ nla_total_size(xfrm_user_sec_ctx_size(xp->security))
+ nla_total_size(sizeof(struct xfrm_mark))
+ userpolicy_type_attrsize();
}
static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
int dir, const struct km_event *c)
{
struct xfrm_user_polexpire *upe;
int hard = c->data.hard;
struct nlmsghdr *nlh;
int err;
nlh = nlmsg_put(skb, c->portid, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe), 0);
if (nlh == NULL)
return -EMSGSIZE;
upe = nlmsg_data(nlh);
copy_to_user_policy(xp, &upe->pol, dir);
err = copy_to_user_tmpl(xp, skb);
if (!err)
err = copy_to_user_sec_ctx(xp, skb);
if (!err)
err = copy_to_user_policy_type(xp->type, skb);
if (!err)
err = xfrm_mark_put(skb, &xp->mark);
if (!err)
err = xfrm_if_id_put(skb, xp->if_id);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
upe->hard = !!hard;
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
}
static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
{
struct net *net = xp_net(xp);
struct sk_buff *skb;
int err;
skb = nlmsg_new(xfrm_polexpire_msgsize(xp), GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
err = build_polexpire(skb, xp, dir, c);
BUG_ON(err < 0);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
}
static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c)
{
unsigned int len = nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr);
struct net *net = xp_net(xp);
struct xfrm_userpolicy_info *p;
struct xfrm_userpolicy_id *id;
struct nlmsghdr *nlh;
struct sk_buff *skb;
unsigned int headlen;
int err;
headlen = sizeof(*p);
if (c->event == XFRM_MSG_DELPOLICY) {
len += nla_total_size(headlen);
headlen = sizeof(*id);
}
len += userpolicy_type_attrsize();
len += nla_total_size(sizeof(struct xfrm_mark));
len += NLMSG_ALIGN(headlen);
skb = nlmsg_new(len, GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
nlh = nlmsg_put(skb, c->portid, c->seq, c->event, headlen, 0);
err = -EMSGSIZE;
if (nlh == NULL)
goto out_free_skb;
p = nlmsg_data(nlh);
if (c->event == XFRM_MSG_DELPOLICY) {
struct nlattr *attr;
id = nlmsg_data(nlh);
memset(id, 0, sizeof(*id));
id->dir = dir;
if (c->data.byid)
id->index = xp->index;
else
memcpy(&id->sel, &xp->selector, sizeof(id->sel));
attr = nla_reserve(skb, XFRMA_POLICY, sizeof(*p));
err = -EMSGSIZE;
if (attr == NULL)
goto out_free_skb;
p = nla_data(attr);
}
copy_to_user_policy(xp, p, dir);
err = copy_to_user_tmpl(xp, skb);
if (!err)
err = copy_to_user_policy_type(xp->type, skb);
if (!err)
err = xfrm_mark_put(skb, &xp->mark);
if (!err)
err = xfrm_if_id_put(skb, xp->if_id);
if (err)
goto out_free_skb;
nlmsg_end(skb, nlh);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
out_free_skb:
kfree_skb(skb);
return err;
}
static int xfrm_notify_policy_flush(const struct km_event *c)
{
struct net *net = c->net;
struct nlmsghdr *nlh;
struct sk_buff *skb;
int err;
skb = nlmsg_new(userpolicy_type_attrsize(), GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_FLUSHPOLICY, 0, 0);
err = -EMSGSIZE;
if (nlh == NULL)
goto out_free_skb;
err = copy_to_user_policy_type(c->data.type, skb);
if (err)
goto out_free_skb;
nlmsg_end(skb, nlh);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
out_free_skb:
kfree_skb(skb);
return err;
}
static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
{
switch (c->event) {
case XFRM_MSG_NEWPOLICY:
case XFRM_MSG_UPDPOLICY:
case XFRM_MSG_DELPOLICY:
return xfrm_notify_policy(xp, dir, c);
case XFRM_MSG_FLUSHPOLICY:
return xfrm_notify_policy_flush(c);
case XFRM_MSG_POLEXPIRE:
return xfrm_exp_policy_notify(xp, dir, c);
default:
printk(KERN_NOTICE "xfrm_user: Unknown Policy event %d\n",
c->event);
}
return 0;
}
static inline unsigned int xfrm_report_msgsize(void)
{
return NLMSG_ALIGN(sizeof(struct xfrm_user_report));
}
static int build_report(struct sk_buff *skb, u8 proto,
struct xfrm_selector *sel, xfrm_address_t *addr)
{
struct xfrm_user_report *ur;
struct nlmsghdr *nlh;
nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_REPORT, sizeof(*ur), 0);
if (nlh == NULL)
return -EMSGSIZE;
ur = nlmsg_data(nlh);
ur->proto = proto;
memcpy(&ur->sel, sel, sizeof(ur->sel));
if (addr) {
int err = nla_put(skb, XFRMA_COADDR, sizeof(*addr), addr);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
}
}
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
}
static int xfrm_send_report(struct net *net, u8 proto,
struct xfrm_selector *sel, xfrm_address_t *addr)
{
struct sk_buff *skb;
int err;
skb = nlmsg_new(xfrm_report_msgsize(), GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
err = build_report(skb, proto, sel, addr);
BUG_ON(err < 0);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT);
}
static inline unsigned int xfrm_mapping_msgsize(void)
{
return NLMSG_ALIGN(sizeof(struct xfrm_user_mapping));
}
static int build_mapping(struct sk_buff *skb, struct xfrm_state *x,
xfrm_address_t *new_saddr, __be16 new_sport)
{
struct xfrm_user_mapping *um;
struct nlmsghdr *nlh;
nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_MAPPING, sizeof(*um), 0);
if (nlh == NULL)
return -EMSGSIZE;
um = nlmsg_data(nlh);
memcpy(&um->id.daddr, &x->id.daddr, sizeof(um->id.daddr));
um->id.spi = x->id.spi;
um->id.family = x->props.family;
um->id.proto = x->id.proto;
memcpy(&um->new_saddr, new_saddr, sizeof(um->new_saddr));
memcpy(&um->old_saddr, &x->props.saddr, sizeof(um->old_saddr));
um->new_sport = new_sport;
um->old_sport = x->encap->encap_sport;
um->reqid = x->props.reqid;
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
}
static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
__be16 sport)
{
struct net *net = xs_net(x);
struct sk_buff *skb;
int err;
if (x->id.proto != IPPROTO_ESP)
return -EINVAL;
if (!x->encap)
return -EINVAL;
skb = nlmsg_new(xfrm_mapping_msgsize(), GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
err = build_mapping(skb, x, ipaddr, sport);
BUG_ON(err < 0);
return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING);
}
static bool xfrm_is_alive(const struct km_event *c)
{
return (bool)xfrm_acquire_is_on(c->net);
}
static struct xfrm_mgr netlink_mgr = {
.notify = xfrm_send_state_notify,
.acquire = xfrm_send_acquire,
.compile_policy = xfrm_compile_policy,
.notify_policy = xfrm_send_policy_notify,
.report = xfrm_send_report,
.migrate = xfrm_send_migrate,
.new_mapping = xfrm_send_mapping,
.is_alive = xfrm_is_alive,
};
static int __net_init xfrm_user_net_init(struct net *net)
{
struct sock *nlsk;
struct netlink_kernel_cfg cfg = {
.groups = XFRMNLGRP_MAX,
.input = xfrm_netlink_rcv,
};
nlsk = netlink_kernel_create(net, NETLINK_XFRM, &cfg);
if (nlsk == NULL)
return -ENOMEM;
net->xfrm.nlsk_stash = nlsk; /* Don't set to NULL */
rcu_assign_pointer(net->xfrm.nlsk, nlsk);
return 0;
}
static void __net_exit xfrm_user_net_pre_exit(struct net *net)
{
RCU_INIT_POINTER(net->xfrm.nlsk, NULL);
}
static void __net_exit xfrm_user_net_exit(struct list_head *net_exit_list)
{
struct net *net;
list_for_each_entry(net, net_exit_list, exit_list)
netlink_kernel_release(net->xfrm.nlsk_stash);
}
static struct pernet_operations xfrm_user_net_ops = {
.init = xfrm_user_net_init,
.pre_exit = xfrm_user_net_pre_exit,
.exit_batch = xfrm_user_net_exit,
};
static int __init xfrm_user_init(void)
{
int rv;
printk(KERN_INFO "Initializing XFRM netlink socket\n");
rv = register_pernet_subsys(&xfrm_user_net_ops);
if (rv < 0)
return rv;
rv = xfrm_register_km(&netlink_mgr);
if (rv < 0)
unregister_pernet_subsys(&xfrm_user_net_ops);
return rv;
}
static void __exit xfrm_user_exit(void)
{
xfrm_unregister_km(&netlink_mgr);
unregister_pernet_subsys(&xfrm_user_net_ops);
}
module_init(xfrm_user_init);
module_exit(xfrm_user_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM);