linux-hardened/net/ipv4/ip_sockglue.c

1590 lines
36 KiB
C
Raw Normal View History

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* The IP to API glue.
*
* Authors: see ip.c
*
* Fixes:
* Many : Split from ip.c , see ip.c for history.
* Martin Mares : TOS setting fixed.
* Alan Cox : Fixed a couple of oopses in Martin's
* TOS tweaks.
* Mike McLagan : Routing by source
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
#include <linux/slab.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/tcp_states.h>
#include <linux/udp.h>
#include <linux/igmp.h>
#include <linux/netfilter.h>
#include <linux/route.h>
#include <linux/mroute.h>
#include <net/inet_ecn.h>
#include <net/route.h>
#include <net/xfrm.h>
#include <net/compat.h>
#include <net/checksum.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/transp_v6.h>
#endif
#include <net/ip_fib.h>
#include <linux/errqueue.h>
#include <asm/uaccess.h>
/*
* SOL_IP control messages.
*/
static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
{
ipv4: PKTINFO doesnt need dst reference Le lundi 07 novembre 2011 à 15:33 +0100, Eric Dumazet a écrit : > At least, in recent kernels we dont change dst->refcnt in forwarding > patch (usinf NOREF skb->dst) > > One particular point is the atomic_inc(dst->refcnt) we have to perform > when queuing an UDP packet if socket asked PKTINFO stuff (for example a > typical DNS server has to setup this option) > > I have one patch somewhere that stores the information in skb->cb[] and > avoid the atomic_{inc|dec}(dst->refcnt). > OK I found it, I did some extra tests and believe its ready. [PATCH net-next] ipv4: IP_PKTINFO doesnt need dst reference When a socket uses IP_PKTINFO notifications, we currently force a dst reference for each received skb. Reader has to access dst to get needed information (rt_iif & rt_spec_dst) and must release dst reference. We also forced a dst reference if skb was put in socket backlog, even without IP_PKTINFO handling. This happens under stress/load. We can instead store the needed information in skb->cb[], so that only softirq handler really access dst, improving cache hit ratios. This removes two atomic operations per packet, and false sharing as well. On a benchmark using a mono threaded receiver (doing only recvmsg() calls), I can reach 720.000 pps instead of 570.000 pps. IP_PKTINFO is typically used by DNS servers, and any multihomed aware UDP application. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-09 08:24:35 +01:00
struct in_pktinfo info = *PKTINFO_SKB_CB(skb);
info.ipi_addr.s_addr = ip_hdr(skb)->daddr;
put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
}
static void ip_cmsg_recv_ttl(struct msghdr *msg, struct sk_buff *skb)
{
int ttl = ip_hdr(skb)->ttl;
put_cmsg(msg, SOL_IP, IP_TTL, sizeof(int), &ttl);
}
static void ip_cmsg_recv_tos(struct msghdr *msg, struct sk_buff *skb)
{
put_cmsg(msg, SOL_IP, IP_TOS, 1, &ip_hdr(skb)->tos);
}
static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb)
{
if (IPCB(skb)->opt.optlen == 0)
return;
put_cmsg(msg, SOL_IP, IP_RECVOPTS, IPCB(skb)->opt.optlen,
ip_hdr(skb) + 1);
}
static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
{
unsigned char optbuf[sizeof(struct ip_options) + 40];
struct ip_options *opt = (struct ip_options *)optbuf;
if (IPCB(skb)->opt.optlen == 0)
return;
if (ip_options_echo(opt, skb)) {
msg->msg_flags |= MSG_CTRUNC;
return;
}
ip_options_undo(opt);
put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data);
}
static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
int offset)
{
__wsum csum = skb->csum;
if (skb->ip_summed != CHECKSUM_COMPLETE)
return;
if (offset != 0)
csum = csum_sub(csum, csum_partial(skb_transport_header(skb),
offset, 0));
put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
}
[SECURITY]: TCP/UDP getpeersec This patch implements an application of the LSM-IPSec networking controls whereby an application can determine the label of the security association its TCP or UDP sockets are currently connected to via getsockopt and the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of an IPSec security association a particular TCP or UDP socket is using. The application can then use this security context to determine the security context for processing on behalf of the peer at the other end of this connection. In the case of UDP, the security context is for each individual packet. An example application is the inetd daemon, which could be modified to start daemons running at security contexts dependent on the remote client. Patch design approach: - Design for TCP The patch enables the SELinux LSM to set the peer security context for a socket based on the security context of the IPSec security association. The application may retrieve this context using getsockopt. When called, the kernel determines if the socket is a connected (TCP_ESTABLISHED) TCP socket and, if so, uses the dst_entry cache on the socket to retrieve the security associations. If a security association has a security context, the context string is returned, as for UNIX domain sockets. - Design for UDP Unlike TCP, UDP is connectionless. This requires a somewhat different API to retrieve the peer security context. With TCP, the peer security context stays the same throughout the connection, thus it can be retrieved at any time between when the connection is established and when it is torn down. With UDP, each read/write can have different peer and thus the security context might change every time. As a result the security context retrieval must be done TOGETHER with the packet retrieval. The solution is to build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). Patch implementation details: - Implementation for TCP The security context can be retrieved by applications using getsockopt with the existing SO_PEERSEC flag. As an example (ignoring error checking): getsockopt(sockfd, SOL_SOCKET, SO_PEERSEC, optbuf, &optlen); printf("Socket peer context is: %s\n", optbuf); The SELinux function, selinux_socket_getpeersec, is extended to check for labeled security associations for connected (TCP_ESTABLISHED == sk->sk_state) TCP sockets only. If so, the socket has a dst_cache of struct dst_entry values that may refer to security associations. If these have security associations with security contexts, the security context is returned. getsockopt returns a buffer that contains a security context string or the buffer is unmodified. - Implementation for UDP To retrieve the security context, the application first indicates to the kernel such desire by setting the IP_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for UDP should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_IP, IP_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_IP && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } ip_setsockopt is enhanced with a new socket option IP_PASSSEC to allow a server socket to receive security context of the peer. A new ancillary message type SCM_SECURITY. When the packet is received we get the security context from the sec_path pointer which is contained in the sk_buff, and copy it to the ancillary message space. An additional LSM hook, selinux_socket_getpeersec_udp, is defined to retrieve the security context from the SELinux space. The existing function, selinux_socket_getpeersec does not suit our purpose, because the security context is copied directly to user space, rather than to kernel space. Testing: We have tested the patch by setting up TCP and UDP connections between applications on two machines using the IPSec policies that result in labeled security associations being built. For TCP, we can then extract the peer security context using getsockopt on either end. For UDP, the receiving end can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-21 07:41:23 +01:00
static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
{
char *secdata;
u32 seclen, secid;
[SECURITY]: TCP/UDP getpeersec This patch implements an application of the LSM-IPSec networking controls whereby an application can determine the label of the security association its TCP or UDP sockets are currently connected to via getsockopt and the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of an IPSec security association a particular TCP or UDP socket is using. The application can then use this security context to determine the security context for processing on behalf of the peer at the other end of this connection. In the case of UDP, the security context is for each individual packet. An example application is the inetd daemon, which could be modified to start daemons running at security contexts dependent on the remote client. Patch design approach: - Design for TCP The patch enables the SELinux LSM to set the peer security context for a socket based on the security context of the IPSec security association. The application may retrieve this context using getsockopt. When called, the kernel determines if the socket is a connected (TCP_ESTABLISHED) TCP socket and, if so, uses the dst_entry cache on the socket to retrieve the security associations. If a security association has a security context, the context string is returned, as for UNIX domain sockets. - Design for UDP Unlike TCP, UDP is connectionless. This requires a somewhat different API to retrieve the peer security context. With TCP, the peer security context stays the same throughout the connection, thus it can be retrieved at any time between when the connection is established and when it is torn down. With UDP, each read/write can have different peer and thus the security context might change every time. As a result the security context retrieval must be done TOGETHER with the packet retrieval. The solution is to build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). Patch implementation details: - Implementation for TCP The security context can be retrieved by applications using getsockopt with the existing SO_PEERSEC flag. As an example (ignoring error checking): getsockopt(sockfd, SOL_SOCKET, SO_PEERSEC, optbuf, &optlen); printf("Socket peer context is: %s\n", optbuf); The SELinux function, selinux_socket_getpeersec, is extended to check for labeled security associations for connected (TCP_ESTABLISHED == sk->sk_state) TCP sockets only. If so, the socket has a dst_cache of struct dst_entry values that may refer to security associations. If these have security associations with security contexts, the security context is returned. getsockopt returns a buffer that contains a security context string or the buffer is unmodified. - Implementation for UDP To retrieve the security context, the application first indicates to the kernel such desire by setting the IP_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for UDP should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_IP, IP_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_IP && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } ip_setsockopt is enhanced with a new socket option IP_PASSSEC to allow a server socket to receive security context of the peer. A new ancillary message type SCM_SECURITY. When the packet is received we get the security context from the sec_path pointer which is contained in the sk_buff, and copy it to the ancillary message space. An additional LSM hook, selinux_socket_getpeersec_udp, is defined to retrieve the security context from the SELinux space. The existing function, selinux_socket_getpeersec does not suit our purpose, because the security context is copied directly to user space, rather than to kernel space. Testing: We have tested the patch by setting up TCP and UDP connections between applications on two machines using the IPSec policies that result in labeled security associations being built. For TCP, we can then extract the peer security context using getsockopt on either end. For UDP, the receiving end can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-21 07:41:23 +01:00
int err;
err = security_socket_getpeersec_dgram(NULL, skb, &secid);
if (err)
return;
err = security_secid_to_secctx(secid, &secdata, &seclen);
[SECURITY]: TCP/UDP getpeersec This patch implements an application of the LSM-IPSec networking controls whereby an application can determine the label of the security association its TCP or UDP sockets are currently connected to via getsockopt and the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of an IPSec security association a particular TCP or UDP socket is using. The application can then use this security context to determine the security context for processing on behalf of the peer at the other end of this connection. In the case of UDP, the security context is for each individual packet. An example application is the inetd daemon, which could be modified to start daemons running at security contexts dependent on the remote client. Patch design approach: - Design for TCP The patch enables the SELinux LSM to set the peer security context for a socket based on the security context of the IPSec security association. The application may retrieve this context using getsockopt. When called, the kernel determines if the socket is a connected (TCP_ESTABLISHED) TCP socket and, if so, uses the dst_entry cache on the socket to retrieve the security associations. If a security association has a security context, the context string is returned, as for UNIX domain sockets. - Design for UDP Unlike TCP, UDP is connectionless. This requires a somewhat different API to retrieve the peer security context. With TCP, the peer security context stays the same throughout the connection, thus it can be retrieved at any time between when the connection is established and when it is torn down. With UDP, each read/write can have different peer and thus the security context might change every time. As a result the security context retrieval must be done TOGETHER with the packet retrieval. The solution is to build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). Patch implementation details: - Implementation for TCP The security context can be retrieved by applications using getsockopt with the existing SO_PEERSEC flag. As an example (ignoring error checking): getsockopt(sockfd, SOL_SOCKET, SO_PEERSEC, optbuf, &optlen); printf("Socket peer context is: %s\n", optbuf); The SELinux function, selinux_socket_getpeersec, is extended to check for labeled security associations for connected (TCP_ESTABLISHED == sk->sk_state) TCP sockets only. If so, the socket has a dst_cache of struct dst_entry values that may refer to security associations. If these have security associations with security contexts, the security context is returned. getsockopt returns a buffer that contains a security context string or the buffer is unmodified. - Implementation for UDP To retrieve the security context, the application first indicates to the kernel such desire by setting the IP_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for UDP should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_IP, IP_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_IP && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } ip_setsockopt is enhanced with a new socket option IP_PASSSEC to allow a server socket to receive security context of the peer. A new ancillary message type SCM_SECURITY. When the packet is received we get the security context from the sec_path pointer which is contained in the sk_buff, and copy it to the ancillary message space. An additional LSM hook, selinux_socket_getpeersec_udp, is defined to retrieve the security context from the SELinux space. The existing function, selinux_socket_getpeersec does not suit our purpose, because the security context is copied directly to user space, rather than to kernel space. Testing: We have tested the patch by setting up TCP and UDP connections between applications on two machines using the IPSec policies that result in labeled security associations being built. For TCP, we can then extract the peer security context using getsockopt on either end. For UDP, the receiving end can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-21 07:41:23 +01:00
if (err)
return;
put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata);
security_release_secctx(secdata, seclen);
[SECURITY]: TCP/UDP getpeersec This patch implements an application of the LSM-IPSec networking controls whereby an application can determine the label of the security association its TCP or UDP sockets are currently connected to via getsockopt and the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of an IPSec security association a particular TCP or UDP socket is using. The application can then use this security context to determine the security context for processing on behalf of the peer at the other end of this connection. In the case of UDP, the security context is for each individual packet. An example application is the inetd daemon, which could be modified to start daemons running at security contexts dependent on the remote client. Patch design approach: - Design for TCP The patch enables the SELinux LSM to set the peer security context for a socket based on the security context of the IPSec security association. The application may retrieve this context using getsockopt. When called, the kernel determines if the socket is a connected (TCP_ESTABLISHED) TCP socket and, if so, uses the dst_entry cache on the socket to retrieve the security associations. If a security association has a security context, the context string is returned, as for UNIX domain sockets. - Design for UDP Unlike TCP, UDP is connectionless. This requires a somewhat different API to retrieve the peer security context. With TCP, the peer security context stays the same throughout the connection, thus it can be retrieved at any time between when the connection is established and when it is torn down. With UDP, each read/write can have different peer and thus the security context might change every time. As a result the security context retrieval must be done TOGETHER with the packet retrieval. The solution is to build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). Patch implementation details: - Implementation for TCP The security context can be retrieved by applications using getsockopt with the existing SO_PEERSEC flag. As an example (ignoring error checking): getsockopt(sockfd, SOL_SOCKET, SO_PEERSEC, optbuf, &optlen); printf("Socket peer context is: %s\n", optbuf); The SELinux function, selinux_socket_getpeersec, is extended to check for labeled security associations for connected (TCP_ESTABLISHED == sk->sk_state) TCP sockets only. If so, the socket has a dst_cache of struct dst_entry values that may refer to security associations. If these have security associations with security contexts, the security context is returned. getsockopt returns a buffer that contains a security context string or the buffer is unmodified. - Implementation for UDP To retrieve the security context, the application first indicates to the kernel such desire by setting the IP_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for UDP should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_IP, IP_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_IP && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } ip_setsockopt is enhanced with a new socket option IP_PASSSEC to allow a server socket to receive security context of the peer. A new ancillary message type SCM_SECURITY. When the packet is received we get the security context from the sec_path pointer which is contained in the sk_buff, and copy it to the ancillary message space. An additional LSM hook, selinux_socket_getpeersec_udp, is defined to retrieve the security context from the SELinux space. The existing function, selinux_socket_getpeersec does not suit our purpose, because the security context is copied directly to user space, rather than to kernel space. Testing: We have tested the patch by setting up TCP and UDP connections between applications on two machines using the IPSec policies that result in labeled security associations being built. For TCP, we can then extract the peer security context using getsockopt on either end. For UDP, the receiving end can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-21 07:41:23 +01:00
}
static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
{
struct sockaddr_in sin;
const struct iphdr *iph = ip_hdr(skb);
__be16 *ports = (__be16 *)skb_transport_header(skb);
if (skb_transport_offset(skb) + 4 > skb->len)
return;
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = iph->daddr;
sin.sin_port = ports[1];
memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin);
}
void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
int offset)
{
struct inet_sock *inet = inet_sk(skb->sk);
unsigned int flags = inet->cmsg_flags;
/* Ordered by supposed usage frequency */
if (flags & IP_CMSG_PKTINFO) {
ip_cmsg_recv_pktinfo(msg, skb);
flags &= ~IP_CMSG_PKTINFO;
if (!flags)
return;
}
if (flags & IP_CMSG_TTL) {
ip_cmsg_recv_ttl(msg, skb);
flags &= ~IP_CMSG_TTL;
if (!flags)
return;
}
if (flags & IP_CMSG_TOS) {
ip_cmsg_recv_tos(msg, skb);
flags &= ~IP_CMSG_TOS;
if (!flags)
return;
}
if (flags & IP_CMSG_RECVOPTS) {
ip_cmsg_recv_opts(msg, skb);
flags &= ~IP_CMSG_RECVOPTS;
if (!flags)
return;
}
if (flags & IP_CMSG_RETOPTS) {
ip_cmsg_recv_retopts(msg, skb);
[SECURITY]: TCP/UDP getpeersec This patch implements an application of the LSM-IPSec networking controls whereby an application can determine the label of the security association its TCP or UDP sockets are currently connected to via getsockopt and the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of an IPSec security association a particular TCP or UDP socket is using. The application can then use this security context to determine the security context for processing on behalf of the peer at the other end of this connection. In the case of UDP, the security context is for each individual packet. An example application is the inetd daemon, which could be modified to start daemons running at security contexts dependent on the remote client. Patch design approach: - Design for TCP The patch enables the SELinux LSM to set the peer security context for a socket based on the security context of the IPSec security association. The application may retrieve this context using getsockopt. When called, the kernel determines if the socket is a connected (TCP_ESTABLISHED) TCP socket and, if so, uses the dst_entry cache on the socket to retrieve the security associations. If a security association has a security context, the context string is returned, as for UNIX domain sockets. - Design for UDP Unlike TCP, UDP is connectionless. This requires a somewhat different API to retrieve the peer security context. With TCP, the peer security context stays the same throughout the connection, thus it can be retrieved at any time between when the connection is established and when it is torn down. With UDP, each read/write can have different peer and thus the security context might change every time. As a result the security context retrieval must be done TOGETHER with the packet retrieval. The solution is to build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). Patch implementation details: - Implementation for TCP The security context can be retrieved by applications using getsockopt with the existing SO_PEERSEC flag. As an example (ignoring error checking): getsockopt(sockfd, SOL_SOCKET, SO_PEERSEC, optbuf, &optlen); printf("Socket peer context is: %s\n", optbuf); The SELinux function, selinux_socket_getpeersec, is extended to check for labeled security associations for connected (TCP_ESTABLISHED == sk->sk_state) TCP sockets only. If so, the socket has a dst_cache of struct dst_entry values that may refer to security associations. If these have security associations with security contexts, the security context is returned. getsockopt returns a buffer that contains a security context string or the buffer is unmodified. - Implementation for UDP To retrieve the security context, the application first indicates to the kernel such desire by setting the IP_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for UDP should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_IP, IP_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_IP && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } ip_setsockopt is enhanced with a new socket option IP_PASSSEC to allow a server socket to receive security context of the peer. A new ancillary message type SCM_SECURITY. When the packet is received we get the security context from the sec_path pointer which is contained in the sk_buff, and copy it to the ancillary message space. An additional LSM hook, selinux_socket_getpeersec_udp, is defined to retrieve the security context from the SELinux space. The existing function, selinux_socket_getpeersec does not suit our purpose, because the security context is copied directly to user space, rather than to kernel space. Testing: We have tested the patch by setting up TCP and UDP connections between applications on two machines using the IPSec policies that result in labeled security associations being built. For TCP, we can then extract the peer security context using getsockopt on either end. For UDP, the receiving end can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-21 07:41:23 +01:00
flags &= ~IP_CMSG_RETOPTS;
if (!flags)
return;
}
if (flags & IP_CMSG_PASSSEC) {
[SECURITY]: TCP/UDP getpeersec This patch implements an application of the LSM-IPSec networking controls whereby an application can determine the label of the security association its TCP or UDP sockets are currently connected to via getsockopt and the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of an IPSec security association a particular TCP or UDP socket is using. The application can then use this security context to determine the security context for processing on behalf of the peer at the other end of this connection. In the case of UDP, the security context is for each individual packet. An example application is the inetd daemon, which could be modified to start daemons running at security contexts dependent on the remote client. Patch design approach: - Design for TCP The patch enables the SELinux LSM to set the peer security context for a socket based on the security context of the IPSec security association. The application may retrieve this context using getsockopt. When called, the kernel determines if the socket is a connected (TCP_ESTABLISHED) TCP socket and, if so, uses the dst_entry cache on the socket to retrieve the security associations. If a security association has a security context, the context string is returned, as for UNIX domain sockets. - Design for UDP Unlike TCP, UDP is connectionless. This requires a somewhat different API to retrieve the peer security context. With TCP, the peer security context stays the same throughout the connection, thus it can be retrieved at any time between when the connection is established and when it is torn down. With UDP, each read/write can have different peer and thus the security context might change every time. As a result the security context retrieval must be done TOGETHER with the packet retrieval. The solution is to build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). Patch implementation details: - Implementation for TCP The security context can be retrieved by applications using getsockopt with the existing SO_PEERSEC flag. As an example (ignoring error checking): getsockopt(sockfd, SOL_SOCKET, SO_PEERSEC, optbuf, &optlen); printf("Socket peer context is: %s\n", optbuf); The SELinux function, selinux_socket_getpeersec, is extended to check for labeled security associations for connected (TCP_ESTABLISHED == sk->sk_state) TCP sockets only. If so, the socket has a dst_cache of struct dst_entry values that may refer to security associations. If these have security associations with security contexts, the security context is returned. getsockopt returns a buffer that contains a security context string or the buffer is unmodified. - Implementation for UDP To retrieve the security context, the application first indicates to the kernel such desire by setting the IP_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for UDP should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_IP, IP_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_IP && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } ip_setsockopt is enhanced with a new socket option IP_PASSSEC to allow a server socket to receive security context of the peer. A new ancillary message type SCM_SECURITY. When the packet is received we get the security context from the sec_path pointer which is contained in the sk_buff, and copy it to the ancillary message space. An additional LSM hook, selinux_socket_getpeersec_udp, is defined to retrieve the security context from the SELinux space. The existing function, selinux_socket_getpeersec does not suit our purpose, because the security context is copied directly to user space, rather than to kernel space. Testing: We have tested the patch by setting up TCP and UDP connections between applications on two machines using the IPSec policies that result in labeled security associations being built. For TCP, we can then extract the peer security context using getsockopt on either end. For UDP, the receiving end can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-21 07:41:23 +01:00
ip_cmsg_recv_security(msg, skb);
flags &= ~IP_CMSG_PASSSEC;
if (!flags)
return;
}
if (flags & IP_CMSG_ORIGDSTADDR) {
ip_cmsg_recv_dstaddr(msg, skb);
flags &= ~IP_CMSG_ORIGDSTADDR;
if (!flags)
return;
}
if (flags & IP_CMSG_CHECKSUM)
ip_cmsg_recv_checksum(msg, skb, offset);
}
EXPORT_SYMBOL(ip_cmsg_recv_offset);
int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
bool allow_ipv6)
{
int err, val;
struct cmsghdr *cmsg;
struct net *net = sock_net(sk);
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
#if IS_ENABLED(CONFIG_IPV6)
if (allow_ipv6 &&
cmsg->cmsg_level == SOL_IPV6 &&
cmsg->cmsg_type == IPV6_PKTINFO) {
struct in6_pktinfo *src_info;
if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info)))
return -EINVAL;
src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
if (!ipv6_addr_v4mapped(&src_info->ipi6_addr))
return -EINVAL;
ipc->oif = src_info->ipi6_ifindex;
ipc->addr = src_info->ipi6_addr.s6_addr32[3];
continue;
}
#endif
if (cmsg->cmsg_level == SOL_SOCKET) {
err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc);
if (err)
return err;
continue;
}
if (cmsg->cmsg_level != SOL_IP)
continue;
switch (cmsg->cmsg_type) {
case IP_RETOPTS:
err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
/* Our caller is responsible for freeing ipc->opt */
err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
err < 40 ? err : 40);
if (err)
return err;
break;
case IP_PKTINFO:
{
struct in_pktinfo *info;
if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo)))
return -EINVAL;
info = (struct in_pktinfo *)CMSG_DATA(cmsg);
ipc->oif = info->ipi_ifindex;
ipc->addr = info->ipi_spec_dst.s_addr;
break;
}
case IP_TTL:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
return -EINVAL;
val = *(int *)CMSG_DATA(cmsg);
if (val < 1 || val > 255)
return -EINVAL;
ipc->ttl = val;
break;
case IP_TOS:
if (cmsg->cmsg_len == CMSG_LEN(sizeof(int)))
val = *(int *)CMSG_DATA(cmsg);
else if (cmsg->cmsg_len == CMSG_LEN(sizeof(u8)))
val = *(u8 *)CMSG_DATA(cmsg);
else
return -EINVAL;
if (val < 0 || val > 255)
return -EINVAL;
ipc->tos = val;
ipc->priority = rt_tos2priority(ipc->tos);
break;
default:
return -EINVAL;
}
}
return 0;
}
/* Special input handler for packets caught by router alert option.
They are selected only by protocol field, and then processed likely
local ones; but only if someone wants them! Otherwise, router
not running rsvpd will kill RSVP.
It is user level problem, what it will make with them.
I have no idea, how it will masquearde or NAT them (it is joke, joke :-)),
but receiver should be enough clever f.e. to forward mtrace requests,
sent to multicast group to reach destination designated router.
*/
struct ip_ra_chain __rcu *ip_ra_chain;
static DEFINE_SPINLOCK(ip_ra_lock);
static void ip_ra_destroy_rcu(struct rcu_head *head)
{
struct ip_ra_chain *ra = container_of(head, struct ip_ra_chain, rcu);
sock_put(ra->saved_sk);
kfree(ra);
}
int ip_ra_control(struct sock *sk, unsigned char on,
void (*destructor)(struct sock *))
{
struct ip_ra_chain *ra, *new_ra;
struct ip_ra_chain __rcu **rap;
if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num == IPPROTO_RAW)
return -EINVAL;
new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
spin_lock_bh(&ip_ra_lock);
for (rap = &ip_ra_chain;
(ra = rcu_dereference_protected(*rap,
lockdep_is_held(&ip_ra_lock))) != NULL;
rap = &ra->next) {
if (ra->sk == sk) {
if (on) {
spin_unlock_bh(&ip_ra_lock);
kfree(new_ra);
return -EADDRINUSE;
}
/* dont let ip_call_ra_chain() use sk again */
ra->sk = NULL;
RCU_INIT_POINTER(*rap, ra->next);
spin_unlock_bh(&ip_ra_lock);
if (ra->destructor)
ra->destructor(sk);
/*
* Delay sock_put(sk) and kfree(ra) after one rcu grace
* period. This guarantee ip_call_ra_chain() dont need
* to mess with socket refcounts.
*/
ra->saved_sk = sk;
call_rcu(&ra->rcu, ip_ra_destroy_rcu);
return 0;
}
}
if (!new_ra) {
spin_unlock_bh(&ip_ra_lock);
return -ENOBUFS;
}
new_ra->sk = sk;
new_ra->destructor = destructor;
RCU_INIT_POINTER(new_ra->next, ra);
rcu_assign_pointer(*rap, new_ra);
sock_hold(sk);
spin_unlock_bh(&ip_ra_lock);
return 0;
}
void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
__be16 port, u32 info, u8 *payload)
{
struct sock_exterr_skb *serr;
skb = skb_clone(skb, GFP_ATOMIC);
if (!skb)
return;
serr = SKB_EXT_ERR(skb);
serr->ee.ee_errno = err;
serr->ee.ee_origin = SO_EE_ORIGIN_ICMP;
serr->ee.ee_type = icmp_hdr(skb)->type;
serr->ee.ee_code = icmp_hdr(skb)->code;
serr->ee.ee_pad = 0;
serr->ee.ee_info = info;
serr->ee.ee_data = 0;
serr->addr_offset = (u8 *)&(((struct iphdr *)(icmp_hdr(skb) + 1))->daddr) -
skb_network_header(skb);
serr->port = port;
if (skb_pull(skb, payload - skb->data)) {
skb_reset_transport_header(skb);
if (sock_queue_err_skb(sk, skb) == 0)
return;
}
kfree_skb(skb);
}
void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info)
{
struct inet_sock *inet = inet_sk(sk);
struct sock_exterr_skb *serr;
struct iphdr *iph;
struct sk_buff *skb;
if (!inet->recverr)
return;
skb = alloc_skb(sizeof(struct iphdr), GFP_ATOMIC);
if (!skb)
return;
skb_put(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->daddr = daddr;
serr = SKB_EXT_ERR(skb);
serr->ee.ee_errno = err;
serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL;
serr->ee.ee_type = 0;
serr->ee.ee_code = 0;
serr->ee.ee_pad = 0;
serr->ee.ee_info = info;
serr->ee.ee_data = 0;
serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb);
serr->port = port;
__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
skb_reset_transport_header(skb);
if (sock_queue_err_skb(sk, skb))
kfree_skb(skb);
}
/* For some errors we have valid addr_offset even with zero payload and
* zero port. Also, addr_offset should be supported if port is set.
*/
static inline bool ipv4_datagram_support_addr(struct sock_exterr_skb *serr)
{
return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
}
ip: fix error queue empty skb handling When reading from the error queue, msg_name and msg_control are only populated for some errors. A new exception for empty timestamp skbs added a false positive on icmp errors without payload. `traceroute -M udpconn` only displayed gateways that return payload with the icmp error: the embedded network headers are pulled before sock_queue_err_skb, leaving an skb with skb->len == 0 otherwise. Fix this regression by refining when msg_name and msg_control branches are taken. The solutions for the two fields are independent. msg_name only makes sense for errors that configure serr->port and serr->addr_offset. Test the first instead of skb->len. This also fixes another issue. saddr could hold the wrong data, as serr->addr_offset is not initialized in some code paths, pointing to the start of the network header. It is only valid when serr->port is set (non-zero). msg_control support differs between IPv4 and IPv6. IPv4 only honors requests for ICMP and timestamps with SOF_TIMESTAMPING_OPT_CMSG. The skb->len test can simply be removed, because skb->dev is also tested and never true for empty skbs. IPv6 honors requests for all errors aside from local errors and timestamps on empty skbs. In both cases, make the policy more explicit by moving this logic to a new function that decides whether to process msg_control and that optionally prepares the necessary fields in skb->cb[]. After this change, the IPv4 and IPv6 paths are more similar. The last case is rxrpc. Here, simply refine to only match timestamps. Fixes: 49ca0d8bfaf3 ("net-timestamp: no-payload option") Reported-by: Jan Niehusmann <jan@gondor.com> Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1->v2 - fix local origin test inversion in ip6_datagram_support_cmsg - make v4 and v6 code paths more similar by introducing analogous ipv4_datagram_support_cmsg - fix compile bug in rxrpc Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-08 02:33:22 +01:00
/* IPv4 supports cmsg on all imcp errors and some timestamps
*
* Timestamp code paths do not initialize the fields expected by cmsg:
* the PKTINFO fields in skb->cb[]. Fill those in here.
*/
static bool ipv4_datagram_support_cmsg(const struct sock *sk,
struct sk_buff *skb,
int ee_origin)
net-timestamp: allow reading recv cmsg on errqueue with origin tstamp Allow reading of timestamps and cmsg at the same time on all relevant socket families. One use is to correlate timestamps with egress device, by asking for cmsg IP_PKTINFO. on AF_INET sockets, call the relevant function (ip_cmsg_recv). To avoid changing legacy expectations, only do so if the caller sets a new timestamping flag SOF_TIMESTAMPING_OPT_CMSG. on AF_INET6 sockets, IPV6_PKTINFO and all other recv cmsg are already returned for all origins. only change is to set ifindex, which is not initialized for all error origins. In both cases, only generate the pktinfo message if an ifindex is known. This is not the case for ACK timestamps. The difference between the protocol families is probably a historical accident as a result of the different conditions for generating cmsg in the relevant ip(v6)_recv_error function: ipv4: if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { ipv6: if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { At one time, this was the same test bar for the ICMP/ICMP6 distinction. This is no longer true. Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1 -> v2 large rewrite - integrate with existing pktinfo cmsg generation code - on ipv4: only send with new flag, to maintain legacy behavior - on ipv6: send at most a single pktinfo cmsg - on ipv6: initialize fields if not yet initialized The recv cmsg interfaces are also relevant to the discussion of whether looping packet headers is problematic. For v6, cmsgs that identify many headers are already returned. This patch expands that to v4. If it sounds reasonable, I will follow with patches 1. request timestamps without payload with SOF_TIMESTAMPING_OPT_TSONLY (http://patchwork.ozlabs.org/patch/366967/) 2. sysctl to conditionally drop all timestamps that have payload or cmsg from users without CAP_NET_RAW. Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-01 04:22:34 +01:00
{
ip: fix error queue empty skb handling When reading from the error queue, msg_name and msg_control are only populated for some errors. A new exception for empty timestamp skbs added a false positive on icmp errors without payload. `traceroute -M udpconn` only displayed gateways that return payload with the icmp error: the embedded network headers are pulled before sock_queue_err_skb, leaving an skb with skb->len == 0 otherwise. Fix this regression by refining when msg_name and msg_control branches are taken. The solutions for the two fields are independent. msg_name only makes sense for errors that configure serr->port and serr->addr_offset. Test the first instead of skb->len. This also fixes another issue. saddr could hold the wrong data, as serr->addr_offset is not initialized in some code paths, pointing to the start of the network header. It is only valid when serr->port is set (non-zero). msg_control support differs between IPv4 and IPv6. IPv4 only honors requests for ICMP and timestamps with SOF_TIMESTAMPING_OPT_CMSG. The skb->len test can simply be removed, because skb->dev is also tested and never true for empty skbs. IPv6 honors requests for all errors aside from local errors and timestamps on empty skbs. In both cases, make the policy more explicit by moving this logic to a new function that decides whether to process msg_control and that optionally prepares the necessary fields in skb->cb[]. After this change, the IPv4 and IPv6 paths are more similar. The last case is rxrpc. Here, simply refine to only match timestamps. Fixes: 49ca0d8bfaf3 ("net-timestamp: no-payload option") Reported-by: Jan Niehusmann <jan@gondor.com> Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1->v2 - fix local origin test inversion in ip6_datagram_support_cmsg - make v4 and v6 code paths more similar by introducing analogous ipv4_datagram_support_cmsg - fix compile bug in rxrpc Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-08 02:33:22 +01:00
struct in_pktinfo *info;
if (ee_origin == SO_EE_ORIGIN_ICMP)
return true;
net-timestamp: allow reading recv cmsg on errqueue with origin tstamp Allow reading of timestamps and cmsg at the same time on all relevant socket families. One use is to correlate timestamps with egress device, by asking for cmsg IP_PKTINFO. on AF_INET sockets, call the relevant function (ip_cmsg_recv). To avoid changing legacy expectations, only do so if the caller sets a new timestamping flag SOF_TIMESTAMPING_OPT_CMSG. on AF_INET6 sockets, IPV6_PKTINFO and all other recv cmsg are already returned for all origins. only change is to set ifindex, which is not initialized for all error origins. In both cases, only generate the pktinfo message if an ifindex is known. This is not the case for ACK timestamps. The difference between the protocol families is probably a historical accident as a result of the different conditions for generating cmsg in the relevant ip(v6)_recv_error function: ipv4: if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { ipv6: if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { At one time, this was the same test bar for the ICMP/ICMP6 distinction. This is no longer true. Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1 -> v2 large rewrite - integrate with existing pktinfo cmsg generation code - on ipv4: only send with new flag, to maintain legacy behavior - on ipv6: send at most a single pktinfo cmsg - on ipv6: initialize fields if not yet initialized The recv cmsg interfaces are also relevant to the discussion of whether looping packet headers is problematic. For v6, cmsgs that identify many headers are already returned. This patch expands that to v4. If it sounds reasonable, I will follow with patches 1. request timestamps without payload with SOF_TIMESTAMPING_OPT_TSONLY (http://patchwork.ozlabs.org/patch/366967/) 2. sysctl to conditionally drop all timestamps that have payload or cmsg from users without CAP_NET_RAW. Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-01 04:22:34 +01:00
ip: fix error queue empty skb handling When reading from the error queue, msg_name and msg_control are only populated for some errors. A new exception for empty timestamp skbs added a false positive on icmp errors without payload. `traceroute -M udpconn` only displayed gateways that return payload with the icmp error: the embedded network headers are pulled before sock_queue_err_skb, leaving an skb with skb->len == 0 otherwise. Fix this regression by refining when msg_name and msg_control branches are taken. The solutions for the two fields are independent. msg_name only makes sense for errors that configure serr->port and serr->addr_offset. Test the first instead of skb->len. This also fixes another issue. saddr could hold the wrong data, as serr->addr_offset is not initialized in some code paths, pointing to the start of the network header. It is only valid when serr->port is set (non-zero). msg_control support differs between IPv4 and IPv6. IPv4 only honors requests for ICMP and timestamps with SOF_TIMESTAMPING_OPT_CMSG. The skb->len test can simply be removed, because skb->dev is also tested and never true for empty skbs. IPv6 honors requests for all errors aside from local errors and timestamps on empty skbs. In both cases, make the policy more explicit by moving this logic to a new function that decides whether to process msg_control and that optionally prepares the necessary fields in skb->cb[]. After this change, the IPv4 and IPv6 paths are more similar. The last case is rxrpc. Here, simply refine to only match timestamps. Fixes: 49ca0d8bfaf3 ("net-timestamp: no-payload option") Reported-by: Jan Niehusmann <jan@gondor.com> Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1->v2 - fix local origin test inversion in ip6_datagram_support_cmsg - make v4 and v6 code paths more similar by introducing analogous ipv4_datagram_support_cmsg - fix compile bug in rxrpc Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-08 02:33:22 +01:00
if (ee_origin == SO_EE_ORIGIN_LOCAL)
return false;
/* Support IP_PKTINFO on tstamp packets if requested, to correlate
* timestamp with egress dev. Not possible for packets without dev
* or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
*/
if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
net-timestamp: allow reading recv cmsg on errqueue with origin tstamp Allow reading of timestamps and cmsg at the same time on all relevant socket families. One use is to correlate timestamps with egress device, by asking for cmsg IP_PKTINFO. on AF_INET sockets, call the relevant function (ip_cmsg_recv). To avoid changing legacy expectations, only do so if the caller sets a new timestamping flag SOF_TIMESTAMPING_OPT_CMSG. on AF_INET6 sockets, IPV6_PKTINFO and all other recv cmsg are already returned for all origins. only change is to set ifindex, which is not initialized for all error origins. In both cases, only generate the pktinfo message if an ifindex is known. This is not the case for ACK timestamps. The difference between the protocol families is probably a historical accident as a result of the different conditions for generating cmsg in the relevant ip(v6)_recv_error function: ipv4: if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { ipv6: if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { At one time, this was the same test bar for the ICMP/ICMP6 distinction. This is no longer true. Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1 -> v2 large rewrite - integrate with existing pktinfo cmsg generation code - on ipv4: only send with new flag, to maintain legacy behavior - on ipv6: send at most a single pktinfo cmsg - on ipv6: initialize fields if not yet initialized The recv cmsg interfaces are also relevant to the discussion of whether looping packet headers is problematic. For v6, cmsgs that identify many headers are already returned. This patch expands that to v4. If it sounds reasonable, I will follow with patches 1. request timestamps without payload with SOF_TIMESTAMPING_OPT_TSONLY (http://patchwork.ozlabs.org/patch/366967/) 2. sysctl to conditionally drop all timestamps that have payload or cmsg from users without CAP_NET_RAW. Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-01 04:22:34 +01:00
(!skb->dev))
return false;
ip: fix error queue empty skb handling When reading from the error queue, msg_name and msg_control are only populated for some errors. A new exception for empty timestamp skbs added a false positive on icmp errors without payload. `traceroute -M udpconn` only displayed gateways that return payload with the icmp error: the embedded network headers are pulled before sock_queue_err_skb, leaving an skb with skb->len == 0 otherwise. Fix this regression by refining when msg_name and msg_control branches are taken. The solutions for the two fields are independent. msg_name only makes sense for errors that configure serr->port and serr->addr_offset. Test the first instead of skb->len. This also fixes another issue. saddr could hold the wrong data, as serr->addr_offset is not initialized in some code paths, pointing to the start of the network header. It is only valid when serr->port is set (non-zero). msg_control support differs between IPv4 and IPv6. IPv4 only honors requests for ICMP and timestamps with SOF_TIMESTAMPING_OPT_CMSG. The skb->len test can simply be removed, because skb->dev is also tested and never true for empty skbs. IPv6 honors requests for all errors aside from local errors and timestamps on empty skbs. In both cases, make the policy more explicit by moving this logic to a new function that decides whether to process msg_control and that optionally prepares the necessary fields in skb->cb[]. After this change, the IPv4 and IPv6 paths are more similar. The last case is rxrpc. Here, simply refine to only match timestamps. Fixes: 49ca0d8bfaf3 ("net-timestamp: no-payload option") Reported-by: Jan Niehusmann <jan@gondor.com> Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1->v2 - fix local origin test inversion in ip6_datagram_support_cmsg - make v4 and v6 code paths more similar by introducing analogous ipv4_datagram_support_cmsg - fix compile bug in rxrpc Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-08 02:33:22 +01:00
info = PKTINFO_SKB_CB(skb);
net-timestamp: allow reading recv cmsg on errqueue with origin tstamp Allow reading of timestamps and cmsg at the same time on all relevant socket families. One use is to correlate timestamps with egress device, by asking for cmsg IP_PKTINFO. on AF_INET sockets, call the relevant function (ip_cmsg_recv). To avoid changing legacy expectations, only do so if the caller sets a new timestamping flag SOF_TIMESTAMPING_OPT_CMSG. on AF_INET6 sockets, IPV6_PKTINFO and all other recv cmsg are already returned for all origins. only change is to set ifindex, which is not initialized for all error origins. In both cases, only generate the pktinfo message if an ifindex is known. This is not the case for ACK timestamps. The difference between the protocol families is probably a historical accident as a result of the different conditions for generating cmsg in the relevant ip(v6)_recv_error function: ipv4: if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { ipv6: if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { At one time, this was the same test bar for the ICMP/ICMP6 distinction. This is no longer true. Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1 -> v2 large rewrite - integrate with existing pktinfo cmsg generation code - on ipv4: only send with new flag, to maintain legacy behavior - on ipv6: send at most a single pktinfo cmsg - on ipv6: initialize fields if not yet initialized The recv cmsg interfaces are also relevant to the discussion of whether looping packet headers is problematic. For v6, cmsgs that identify many headers are already returned. This patch expands that to v4. If it sounds reasonable, I will follow with patches 1. request timestamps without payload with SOF_TIMESTAMPING_OPT_TSONLY (http://patchwork.ozlabs.org/patch/366967/) 2. sysctl to conditionally drop all timestamps that have payload or cmsg from users without CAP_NET_RAW. Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-01 04:22:34 +01:00
info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
info->ipi_ifindex = skb->dev->ifindex;
return true;
}
/*
* Handle MSG_ERRQUEUE
*/
int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct sock_exterr_skb *serr;
struct sk_buff *skb;
DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct {
struct sock_extended_err ee;
struct sockaddr_in offender;
} errhdr;
int err;
int copied;
WARN_ON_ONCE(sk->sk_family == AF_INET6);
err = -EAGAIN;
skb = sock_dequeue_err_skb(sk);
if (!skb)
goto out;
copied = skb->len;
if (copied > len) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_msg(skb, 0, msg, copied);
if (unlikely(err)) {
kfree_skb(skb);
return err;
}
sock_recv_timestamp(msg, sk, skb);
serr = SKB_EXT_ERR(skb);
if (sin && ipv4_datagram_support_addr(serr)) {
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
serr->addr_offset);
sin->sin_port = serr->port;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
*addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
sin = &errhdr.offender;
memset(sin, 0, sizeof(*sin));
net-timestamp: allow reading recv cmsg on errqueue with origin tstamp Allow reading of timestamps and cmsg at the same time on all relevant socket families. One use is to correlate timestamps with egress device, by asking for cmsg IP_PKTINFO. on AF_INET sockets, call the relevant function (ip_cmsg_recv). To avoid changing legacy expectations, only do so if the caller sets a new timestamping flag SOF_TIMESTAMPING_OPT_CMSG. on AF_INET6 sockets, IPV6_PKTINFO and all other recv cmsg are already returned for all origins. only change is to set ifindex, which is not initialized for all error origins. In both cases, only generate the pktinfo message if an ifindex is known. This is not the case for ACK timestamps. The difference between the protocol families is probably a historical accident as a result of the different conditions for generating cmsg in the relevant ip(v6)_recv_error function: ipv4: if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { ipv6: if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { At one time, this was the same test bar for the ICMP/ICMP6 distinction. This is no longer true. Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1 -> v2 large rewrite - integrate with existing pktinfo cmsg generation code - on ipv4: only send with new flag, to maintain legacy behavior - on ipv6: send at most a single pktinfo cmsg - on ipv6: initialize fields if not yet initialized The recv cmsg interfaces are also relevant to the discussion of whether looping packet headers is problematic. For v6, cmsgs that identify many headers are already returned. This patch expands that to v4. If it sounds reasonable, I will follow with patches 1. request timestamps without payload with SOF_TIMESTAMPING_OPT_TSONLY (http://patchwork.ozlabs.org/patch/366967/) 2. sysctl to conditionally drop all timestamps that have payload or cmsg from users without CAP_NET_RAW. Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-01 04:22:34 +01:00
ip: fix error queue empty skb handling When reading from the error queue, msg_name and msg_control are only populated for some errors. A new exception for empty timestamp skbs added a false positive on icmp errors without payload. `traceroute -M udpconn` only displayed gateways that return payload with the icmp error: the embedded network headers are pulled before sock_queue_err_skb, leaving an skb with skb->len == 0 otherwise. Fix this regression by refining when msg_name and msg_control branches are taken. The solutions for the two fields are independent. msg_name only makes sense for errors that configure serr->port and serr->addr_offset. Test the first instead of skb->len. This also fixes another issue. saddr could hold the wrong data, as serr->addr_offset is not initialized in some code paths, pointing to the start of the network header. It is only valid when serr->port is set (non-zero). msg_control support differs between IPv4 and IPv6. IPv4 only honors requests for ICMP and timestamps with SOF_TIMESTAMPING_OPT_CMSG. The skb->len test can simply be removed, because skb->dev is also tested and never true for empty skbs. IPv6 honors requests for all errors aside from local errors and timestamps on empty skbs. In both cases, make the policy more explicit by moving this logic to a new function that decides whether to process msg_control and that optionally prepares the necessary fields in skb->cb[]. After this change, the IPv4 and IPv6 paths are more similar. The last case is rxrpc. Here, simply refine to only match timestamps. Fixes: 49ca0d8bfaf3 ("net-timestamp: no-payload option") Reported-by: Jan Niehusmann <jan@gondor.com> Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1->v2 - fix local origin test inversion in ip6_datagram_support_cmsg - make v4 and v6 code paths more similar by introducing analogous ipv4_datagram_support_cmsg - fix compile bug in rxrpc Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-08 02:33:22 +01:00
if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) {
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
if (inet_sk(sk)->cmsg_flags)
ip_cmsg_recv(msg, skb);
}
put_cmsg(msg, SOL_IP, IP_RECVERR, sizeof(errhdr), &errhdr);
/* Now we could try to dump offended packet options */
msg->msg_flags |= MSG_ERRQUEUE;
err = copied;
consume_skb(skb);
out:
return err;
}
/*
* Socket option code for IP. This is the end of the line after any
* TCP,UDP etc options on an IP socket.
*/
static bool setsockopt_needs_rtnl(int optname)
{
switch (optname) {
case IP_ADD_MEMBERSHIP:
case IP_ADD_SOURCE_MEMBERSHIP:
case IP_BLOCK_SOURCE:
case IP_DROP_MEMBERSHIP:
case IP_DROP_SOURCE_MEMBERSHIP:
case IP_MSFILTER:
case IP_UNBLOCK_SOURCE:
case MCAST_BLOCK_SOURCE:
case MCAST_MSFILTER:
case MCAST_JOIN_GROUP:
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_UNBLOCK_SOURCE:
return true;
}
return false;
}
static int do_ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
int val = 0, err;
bool needs_rtnl = setsockopt_needs_rtnl(optname);
switch (optname) {
case IP_PKTINFO:
case IP_RECVTTL:
case IP_RECVOPTS:
case IP_RECVTOS:
case IP_RETOPTS:
case IP_TOS:
case IP_TTL:
case IP_HDRINCL:
case IP_MTU_DISCOVER:
case IP_RECVERR:
case IP_ROUTER_ALERT:
case IP_FREEBIND:
case IP_PASSSEC:
case IP_TRANSPARENT:
case IP_MINTTL:
case IP_NODEFRAG:
inet: add IP_BIND_ADDRESS_NO_PORT to overcome bind(0) limitations When an application needs to force a source IP on an active TCP socket it has to use bind(IP, port=x). As most applications do not want to deal with already used ports, x is often set to 0, meaning the kernel is in charge to find an available port. But kernel does not know yet if this socket is going to be a listener or be connected. It has very limited choices (no full knowledge of final 4-tuple for a connect()) With limited ephemeral port range (about 32K ports), it is very easy to fill the space. This patch adds a new SOL_IP socket option, asking kernel to ignore the 0 port provided by application in bind(IP, port=0) and only remember the given IP address. The port will be automatically chosen at connect() time, in a way that allows sharing a source port as long as the 4-tuples are unique. This new feature is available for both IPv4 and IPv6 (Thanks Neal) Tested: Wrote a test program and checked its behavior on IPv4 and IPv6. strace(1) shows sequences of bind(IP=127.0.0.2, port=0) followed by connect(). Also getsockname() show that the port is still 0 right after bind() but properly allocated after connect(). socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 5 setsockopt(5, SOL_IP, IP_BIND_ADDRESS_NO_PORT, [1], 4) = 0 bind(5, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("127.0.0.2")}, 16) = 0 getsockname(5, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("127.0.0.2")}, [16]) = 0 connect(5, {sa_family=AF_INET, sin_port=htons(53174), sin_addr=inet_addr("127.0.0.3")}, 16) = 0 getsockname(5, {sa_family=AF_INET, sin_port=htons(38050), sin_addr=inet_addr("127.0.0.2")}, [16]) = 0 IPv6 test : socket(PF_INET6, SOCK_STREAM, IPPROTO_IP) = 7 setsockopt(7, SOL_IP, IP_BIND_ADDRESS_NO_PORT, [1], 4) = 0 bind(7, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = 0 getsockname(7, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, [28]) = 0 connect(7, {sa_family=AF_INET6, sin6_port=htons(57300), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = 0 getsockname(7, {sa_family=AF_INET6, sin6_port=htons(60964), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, [28]) = 0 I was able to bind()/connect() a million concurrent IPv4 sockets, instead of ~32000 before patch. lpaa23:~# ulimit -n 1000010 lpaa23:~# ./bind --connect --num-flows=1000000 & 1000000 sockets lpaa23:~# grep TCP /proc/net/sockstat TCP: inuse 2000063 orphan 0 tw 47 alloc 2000157 mem 66 Check that a given source port is indeed used by many different connections : lpaa23:~# ss -t src :40000 | head -10 State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 0 127.0.0.2:40000 127.0.202.33:44983 ESTAB 0 0 127.0.0.2:40000 127.2.27.240:44983 ESTAB 0 0 127.0.0.2:40000 127.2.98.5:44983 ESTAB 0 0 127.0.0.2:40000 127.0.124.196:44983 ESTAB 0 0 127.0.0.2:40000 127.2.139.38:44983 ESTAB 0 0 127.0.0.2:40000 127.1.59.80:44983 ESTAB 0 0 127.0.0.2:40000 127.3.6.228:44983 ESTAB 0 0 127.0.0.2:40000 127.0.38.53:44983 ESTAB 0 0 127.0.0.2:40000 127.1.197.10:44983 Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-07 06:17:57 +02:00
case IP_BIND_ADDRESS_NO_PORT:
case IP_UNICAST_IF:
case IP_MULTICAST_TTL:
case IP_MULTICAST_ALL:
case IP_MULTICAST_LOOP:
case IP_RECVORIGDSTADDR:
case IP_CHECKSUM:
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else if (optlen >= sizeof(char)) {
unsigned char ucval;
if (get_user(ucval, (unsigned char __user *) optval))
return -EFAULT;
val = (int) ucval;
}
}
/* If optlen==0, it is equivalent to val == 0 */
if (ip_mroute_opt(optname))
return ip_mroute_setsockopt(sk, optname, optval, optlen);
err = 0;
if (needs_rtnl)
rtnl_lock();
lock_sock(sk);
switch (optname) {
case IP_OPTIONS:
{
struct ip_options_rcu *old, *opt = NULL;
if (optlen > 40)
goto e_inval;
err = ip_options_get_from_user(sock_net(sk), &opt,
optval, optlen);
if (err)
break;
old = rcu_dereference_protected(inet->inet_opt,
lockdep_sock_is_held(sk));
if (inet->is_icsk) {
struct inet_connection_sock *icsk = inet_csk(sk);
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == PF_INET ||
(!((1 << sk->sk_state) &
(TCPF_LISTEN | TCPF_CLOSE)) &&
inet->inet_daddr != LOOPBACK4_IPV6)) {
#endif
if (old)
icsk->icsk_ext_hdr_len -= old->opt.optlen;
if (opt)
icsk->icsk_ext_hdr_len += opt->opt.optlen;
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
#if IS_ENABLED(CONFIG_IPV6)
}
#endif
}
rcu_assign_pointer(inet->inet_opt, opt);
if (old)
kfree_rcu(old, rcu);
break;
}
case IP_PKTINFO:
if (val)
inet->cmsg_flags |= IP_CMSG_PKTINFO;
else
inet->cmsg_flags &= ~IP_CMSG_PKTINFO;
break;
case IP_RECVTTL:
if (val)
inet->cmsg_flags |= IP_CMSG_TTL;
else
inet->cmsg_flags &= ~IP_CMSG_TTL;
break;
case IP_RECVTOS:
if (val)
inet->cmsg_flags |= IP_CMSG_TOS;
else
inet->cmsg_flags &= ~IP_CMSG_TOS;
break;
case IP_RECVOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RECVOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RECVOPTS;
break;
case IP_RETOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RETOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RETOPTS;
break;
case IP_PASSSEC:
if (val)
inet->cmsg_flags |= IP_CMSG_PASSSEC;
else
inet->cmsg_flags &= ~IP_CMSG_PASSSEC;
break;
case IP_RECVORIGDSTADDR:
if (val)
inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR;
else
inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
break;
case IP_CHECKSUM:
if (val) {
if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) {
inet_inc_convert_csum(sk);
inet->cmsg_flags |= IP_CMSG_CHECKSUM;
}
} else {
if (inet->cmsg_flags & IP_CMSG_CHECKSUM) {
inet_dec_convert_csum(sk);
inet->cmsg_flags &= ~IP_CMSG_CHECKSUM;
}
}
break;
case IP_TOS: /* This sets both TOS and Precedence */
if (sk->sk_type == SOCK_STREAM) {
val &= ~INET_ECN_MASK;
val |= inet->tos & INET_ECN_MASK;
}
if (inet->tos != val) {
inet->tos = val;
sk->sk_priority = rt_tos2priority(val);
sk_dst_reset(sk);
}
break;
case IP_TTL:
if (optlen < 1)
goto e_inval;
if (val != -1 && (val < 1 || val > 255))
goto e_inval;
inet->uc_ttl = val;
break;
case IP_HDRINCL:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
[SECURITY]: TCP/UDP getpeersec This patch implements an application of the LSM-IPSec networking controls whereby an application can determine the label of the security association its TCP or UDP sockets are currently connected to via getsockopt and the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of an IPSec security association a particular TCP or UDP socket is using. The application can then use this security context to determine the security context for processing on behalf of the peer at the other end of this connection. In the case of UDP, the security context is for each individual packet. An example application is the inetd daemon, which could be modified to start daemons running at security contexts dependent on the remote client. Patch design approach: - Design for TCP The patch enables the SELinux LSM to set the peer security context for a socket based on the security context of the IPSec security association. The application may retrieve this context using getsockopt. When called, the kernel determines if the socket is a connected (TCP_ESTABLISHED) TCP socket and, if so, uses the dst_entry cache on the socket to retrieve the security associations. If a security association has a security context, the context string is returned, as for UNIX domain sockets. - Design for UDP Unlike TCP, UDP is connectionless. This requires a somewhat different API to retrieve the peer security context. With TCP, the peer security context stays the same throughout the connection, thus it can be retrieved at any time between when the connection is established and when it is torn down. With UDP, each read/write can have different peer and thus the security context might change every time. As a result the security context retrieval must be done TOGETHER with the packet retrieval. The solution is to build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). Patch implementation details: - Implementation for TCP The security context can be retrieved by applications using getsockopt with the existing SO_PEERSEC flag. As an example (ignoring error checking): getsockopt(sockfd, SOL_SOCKET, SO_PEERSEC, optbuf, &optlen); printf("Socket peer context is: %s\n", optbuf); The SELinux function, selinux_socket_getpeersec, is extended to check for labeled security associations for connected (TCP_ESTABLISHED == sk->sk_state) TCP sockets only. If so, the socket has a dst_cache of struct dst_entry values that may refer to security associations. If these have security associations with security contexts, the security context is returned. getsockopt returns a buffer that contains a security context string or the buffer is unmodified. - Implementation for UDP To retrieve the security context, the application first indicates to the kernel such desire by setting the IP_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for UDP should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_IP, IP_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_IP && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } ip_setsockopt is enhanced with a new socket option IP_PASSSEC to allow a server socket to receive security context of the peer. A new ancillary message type SCM_SECURITY. When the packet is received we get the security context from the sec_path pointer which is contained in the sk_buff, and copy it to the ancillary message space. An additional LSM hook, selinux_socket_getpeersec_udp, is defined to retrieve the security context from the SELinux space. The existing function, selinux_socket_getpeersec does not suit our purpose, because the security context is copied directly to user space, rather than to kernel space. Testing: We have tested the patch by setting up TCP and UDP connections between applications on two machines using the IPSec policies that result in labeled security associations being built. For TCP, we can then extract the peer security context using getsockopt on either end. For UDP, the receiving end can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-21 07:41:23 +01:00
break;
}
inet->hdrincl = val ? 1 : 0;
break;
case IP_NODEFRAG:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
break;
}
inet->nodefrag = val ? 1 : 0;
break;
inet: add IP_BIND_ADDRESS_NO_PORT to overcome bind(0) limitations When an application needs to force a source IP on an active TCP socket it has to use bind(IP, port=x). As most applications do not want to deal with already used ports, x is often set to 0, meaning the kernel is in charge to find an available port. But kernel does not know yet if this socket is going to be a listener or be connected. It has very limited choices (no full knowledge of final 4-tuple for a connect()) With limited ephemeral port range (about 32K ports), it is very easy to fill the space. This patch adds a new SOL_IP socket option, asking kernel to ignore the 0 port provided by application in bind(IP, port=0) and only remember the given IP address. The port will be automatically chosen at connect() time, in a way that allows sharing a source port as long as the 4-tuples are unique. This new feature is available for both IPv4 and IPv6 (Thanks Neal) Tested: Wrote a test program and checked its behavior on IPv4 and IPv6. strace(1) shows sequences of bind(IP=127.0.0.2, port=0) followed by connect(). Also getsockname() show that the port is still 0 right after bind() but properly allocated after connect(). socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 5 setsockopt(5, SOL_IP, IP_BIND_ADDRESS_NO_PORT, [1], 4) = 0 bind(5, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("127.0.0.2")}, 16) = 0 getsockname(5, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("127.0.0.2")}, [16]) = 0 connect(5, {sa_family=AF_INET, sin_port=htons(53174), sin_addr=inet_addr("127.0.0.3")}, 16) = 0 getsockname(5, {sa_family=AF_INET, sin_port=htons(38050), sin_addr=inet_addr("127.0.0.2")}, [16]) = 0 IPv6 test : socket(PF_INET6, SOCK_STREAM, IPPROTO_IP) = 7 setsockopt(7, SOL_IP, IP_BIND_ADDRESS_NO_PORT, [1], 4) = 0 bind(7, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = 0 getsockname(7, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, [28]) = 0 connect(7, {sa_family=AF_INET6, sin6_port=htons(57300), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = 0 getsockname(7, {sa_family=AF_INET6, sin6_port=htons(60964), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, [28]) = 0 I was able to bind()/connect() a million concurrent IPv4 sockets, instead of ~32000 before patch. lpaa23:~# ulimit -n 1000010 lpaa23:~# ./bind --connect --num-flows=1000000 & 1000000 sockets lpaa23:~# grep TCP /proc/net/sockstat TCP: inuse 2000063 orphan 0 tw 47 alloc 2000157 mem 66 Check that a given source port is indeed used by many different connections : lpaa23:~# ss -t src :40000 | head -10 State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 0 127.0.0.2:40000 127.0.202.33:44983 ESTAB 0 0 127.0.0.2:40000 127.2.27.240:44983 ESTAB 0 0 127.0.0.2:40000 127.2.98.5:44983 ESTAB 0 0 127.0.0.2:40000 127.0.124.196:44983 ESTAB 0 0 127.0.0.2:40000 127.2.139.38:44983 ESTAB 0 0 127.0.0.2:40000 127.1.59.80:44983 ESTAB 0 0 127.0.0.2:40000 127.3.6.228:44983 ESTAB 0 0 127.0.0.2:40000 127.0.38.53:44983 ESTAB 0 0 127.0.0.2:40000 127.1.197.10:44983 Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-07 06:17:57 +02:00
case IP_BIND_ADDRESS_NO_PORT:
inet->bind_address_no_port = val ? 1 : 0;
break;
case IP_MTU_DISCOVER:
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
goto e_inval;
inet->pmtudisc = val;
break;
case IP_RECVERR:
inet->recverr = !!val;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
break;
case IP_MULTICAST_TTL:
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
if (optlen < 1)
goto e_inval;
if (val == -1)
val = 1;
if (val < 0 || val > 255)
goto e_inval;
inet->mc_ttl = val;
break;
case IP_MULTICAST_LOOP:
if (optlen < 1)
goto e_inval;
inet->mc_loop = !!val;
break;
ipv4: Implement IP_UNICAST_IF socket option. The IP_UNICAST_IF feature is needed by the Wine project. This patch implements the feature by setting the outgoing interface in a similar fashion to that of IP_MULTICAST_IF. A separate option is needed to handle this feature since the existing options do not provide all of the characteristics required by IP_UNICAST_IF, a summary is provided below. SO_BINDTODEVICE: * SO_BINDTODEVICE requires administrative privileges, IP_UNICAST_IF does not. From reading some old mailing list articles my understanding is that SO_BINDTODEVICE requires administrative privileges because it can override the administrator's routing settings. * The SO_BINDTODEVICE option restricts both outbound and inbound traffic, IP_UNICAST_IF only impacts outbound traffic. IP_PKTINFO: * Since IP_PKTINFO and IP_UNICAST_IF are independent options, implementing IP_UNICAST_IF with IP_PKTINFO will likely break some applications. * Implementing IP_UNICAST_IF on top of IP_PKTINFO significantly complicates the Wine codebase and reduces the socket performance (doing this requires a lot of extra communication between the "server" and "user" layers). bind(): * bind() does not work on broadcast packets, IP_UNICAST_IF is specifically intended to work with broadcast packets. * Like SO_BINDTODEVICE, bind() restricts both outbound and inbound traffic. Signed-off-by: Erich E. Hoover <ehoover@mines.edu> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-08 10:11:07 +01:00
case IP_UNICAST_IF:
{
struct net_device *dev = NULL;
int ifindex;
if (optlen != sizeof(int))
goto e_inval;
ifindex = (__force int)ntohl((__force __be32)val);
if (ifindex == 0) {
inet->uc_index = 0;
err = 0;
break;
}
dev = dev_get_by_index(sock_net(sk), ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if)
break;
inet->uc_index = ifindex;
err = 0;
break;
}
case IP_MULTICAST_IF:
{
struct ip_mreqn mreq;
struct net_device *dev = NULL;
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
/*
* Check the arguments are allowable
*/
if (optlen < sizeof(struct in_addr))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (optlen >= sizeof(struct ip_mreq)) {
if (copy_from_user(&mreq, optval,
sizeof(struct ip_mreq)))
break;
} else if (optlen >= sizeof(struct in_addr)) {
if (copy_from_user(&mreq.imr_address, optval,
sizeof(struct in_addr)))
break;
}
}
if (!mreq.imr_ifindex) {
if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) {
inet->mc_index = 0;
inet->mc_addr = 0;
err = 0;
break;
}
dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
if (dev)
mreq.imr_ifindex = dev->ifindex;
} else
dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if &&
mreq.imr_ifindex != sk->sk_bound_dev_if)
break;
inet->mc_index = mreq.imr_ifindex;
inet->mc_addr = mreq.imr_address.s_addr;
err = 0;
break;
}
case IP_ADD_MEMBERSHIP:
case IP_DROP_MEMBERSHIP:
{
struct ip_mreqn mreq;
err = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
if (optlen < sizeof(struct ip_mreq))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (copy_from_user(&mreq, optval, sizeof(struct ip_mreq)))
break;
}
if (optname == IP_ADD_MEMBERSHIP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case IP_MSFILTER:
{
struct ip_msfilter *msf;
if (optlen < IP_MSFILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
msf = kmalloc(optlen, GFP_KERNEL);
if (!msf) {
err = -ENOBUFS;
break;
}
err = -EFAULT;
if (copy_from_user(msf, optval, optlen)) {
kfree(msf);
break;
}
/* numsrc >= (1G-4) overflow in 32 bits */
if (msf->imsf_numsrc >= 0x3ffffffcU ||
msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
kfree(msf);
err = -ENOBUFS;
break;
}
if (IP_MSFILTER_SIZE(msf->imsf_numsrc) > optlen) {
kfree(msf);
err = -EINVAL;
break;
}
err = ip_mc_msfilter(sk, msf, 0);
kfree(msf);
break;
}
case IP_BLOCK_SOURCE:
case IP_UNBLOCK_SOURCE:
case IP_ADD_SOURCE_MEMBERSHIP:
case IP_DROP_SOURCE_MEMBERSHIP:
{
struct ip_mreq_source mreqs;
int omode, add;
if (optlen != sizeof(struct ip_mreq_source))
goto e_inval;
if (copy_from_user(&mreqs, optval, sizeof(mreqs))) {
err = -EFAULT;
break;
}
if (optname == IP_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == IP_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == IP_ADD_SOURCE_MEMBERSHIP) {
struct ip_mreqn mreq;
mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
mreq.imr_address.s_addr = mreqs.imr_interface;
mreq.imr_ifindex = 0;
err = ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* IP_DROP_SOURCE_MEMBERSHIP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs, 0);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in *psin;
struct ip_mreqn mreq;
if (optlen < sizeof(struct group_req))
goto e_inval;
err = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(greq)))
break;
psin = (struct sockaddr_in *)&greq.gr_group;
if (psin->sin_family != AF_INET)
goto e_inval;
memset(&mreq, 0, sizeof(mreq));
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_ifindex = greq.gr_interface;
if (optname == MCAST_JOIN_GROUP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
struct ip_mreq_source mreqs;
struct sockaddr_in *psin;
int omode, add;
if (optlen != sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
err = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET ||
greqs.gsr_source.ss_family != AF_INET) {
err = -EADDRNOTAVAIL;
break;
}
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreqs.imr_multiaddr = psin->sin_addr.s_addr;
psin = (struct sockaddr_in *)&greqs.gsr_source;
mreqs.imr_sourceaddr = psin->sin_addr.s_addr;
mreqs.imr_interface = 0; /* use index for mc_source */
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct ip_mreqn mreq;
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
mreq.imr_ifindex = greqs.gsr_interface;
err = ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
greqs.gsr_interface = mreq.imr_ifindex;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs,
greqs.gsr_interface);
break;
}
case MCAST_MSFILTER:
{
struct sockaddr_in *psin;
struct ip_msfilter *msf = NULL;
struct group_filter *gsf = NULL;
int msize, i, ifindex;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
gsf = kmalloc(optlen, GFP_KERNEL);
if (!gsf) {
err = -ENOBUFS;
break;
}
err = -EFAULT;
if (copy_from_user(gsf, optval, optlen))
goto mc_msf_out;
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffff ||
gsf->gf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
err = -EINVAL;
goto mc_msf_out;
}
msize = IP_MSFILTER_SIZE(gsf->gf_numsrc);
msf = kmalloc(msize, GFP_KERNEL);
if (!msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
ifindex = gsf->gf_interface;
psin = (struct sockaddr_in *)&gsf->gf_group;
if (psin->sin_family != AF_INET) {
err = -EADDRNOTAVAIL;
goto mc_msf_out;
}
msf->imsf_multiaddr = psin->sin_addr.s_addr;
msf->imsf_interface = 0;
msf->imsf_fmode = gsf->gf_fmode;
msf->imsf_numsrc = gsf->gf_numsrc;
err = -EADDRNOTAVAIL;
for (i = 0; i < gsf->gf_numsrc; ++i) {
psin = (struct sockaddr_in *)&gsf->gf_slist[i];
if (psin->sin_family != AF_INET)
goto mc_msf_out;
msf->imsf_slist[i] = psin->sin_addr.s_addr;
}
kfree(gsf);
gsf = NULL;
err = ip_mc_msfilter(sk, msf, ifindex);
mc_msf_out:
kfree(msf);
kfree(gsf);
break;
}
case IP_MULTICAST_ALL:
if (optlen < 1)
goto e_inval;
if (val != 0 && val != 1)
goto e_inval;
inet->mc_all = val;
break;
case IP_ROUTER_ALERT:
err = ip_ra_control(sk, val ? 1 : 0, NULL);
break;
case IP_FREEBIND:
if (optlen < 1)
goto e_inval;
inet->freebind = !!val;
break;
case IP_IPSEC_POLICY:
case IP_XFRM_POLICY:
err = -EPERM;
net: Allow userns root to control ipv4 Allow an unpriviled user who has created a user namespace, and then created a network namespace to effectively use the new network namespace, by reducing capable(CAP_NET_ADMIN) and capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns, CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls. Settings that merely control a single network device are allowed. Either the network device is a logical network device where restrictions make no difference or the network device is hardware NIC that has been explicity moved from the initial network namespace. In general policy and network stack state changes are allowed while resource control is left unchanged. Allow creating raw sockets. Allow the SIOCSARP ioctl to control the arp cache. Allow the SIOCSIFFLAG ioctl to allow setting network device flags. Allow the SIOCSIFADDR ioctl to allow setting a netdevice ipv4 address. Allow the SIOCSIFBRDADDR ioctl to allow setting a netdevice ipv4 broadcast address. Allow the SIOCSIFDSTADDR ioctl to allow setting a netdevice ipv4 destination address. Allow the SIOCSIFNETMASK ioctl to allow setting a netdevice ipv4 netmask. Allow the SIOCADDRT and SIOCDELRT ioctls to allow adding and deleting ipv4 routes. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting gre tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipip tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipsec virtual tunnel interfaces. Allow setting the MRT_INIT, MRT_DONE, MRT_ADD_VIF, MRT_DEL_VIF, MRT_ADD_MFC, MRT_DEL_MFC, MRT_ASSERT, MRT_PIM, MRT_TABLE socket options on multicast routing sockets. Allow setting and receiving IPOPT_CIPSO, IP_OPT_SEC, IP_OPT_SID and arbitrary ip options. Allow setting IP_SEC_POLICY/IP_XFRM_POLICY ipv4 socket option. Allow setting the IP_TRANSPARENT ipv4 socket option. Allow setting the TCP_REPAIR socket option. Allow setting the TCP_CONGESTION socket option. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 04:03:05 +01:00
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
break;
err = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IP_TRANSPARENT:
net: Allow userns root to control ipv4 Allow an unpriviled user who has created a user namespace, and then created a network namespace to effectively use the new network namespace, by reducing capable(CAP_NET_ADMIN) and capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns, CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls. Settings that merely control a single network device are allowed. Either the network device is a logical network device where restrictions make no difference or the network device is hardware NIC that has been explicity moved from the initial network namespace. In general policy and network stack state changes are allowed while resource control is left unchanged. Allow creating raw sockets. Allow the SIOCSARP ioctl to control the arp cache. Allow the SIOCSIFFLAG ioctl to allow setting network device flags. Allow the SIOCSIFADDR ioctl to allow setting a netdevice ipv4 address. Allow the SIOCSIFBRDADDR ioctl to allow setting a netdevice ipv4 broadcast address. Allow the SIOCSIFDSTADDR ioctl to allow setting a netdevice ipv4 destination address. Allow the SIOCSIFNETMASK ioctl to allow setting a netdevice ipv4 netmask. Allow the SIOCADDRT and SIOCDELRT ioctls to allow adding and deleting ipv4 routes. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting gre tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipip tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipsec virtual tunnel interfaces. Allow setting the MRT_INIT, MRT_DONE, MRT_ADD_VIF, MRT_DEL_VIF, MRT_ADD_MFC, MRT_DEL_MFC, MRT_ASSERT, MRT_PIM, MRT_TABLE socket options on multicast routing sockets. Allow setting and receiving IPOPT_CIPSO, IP_OPT_SEC, IP_OPT_SID and arbitrary ip options. Allow setting IP_SEC_POLICY/IP_XFRM_POLICY ipv4 socket option. Allow setting the IP_TRANSPARENT ipv4 socket option. Allow setting the TCP_REPAIR socket option. Allow setting the TCP_CONGESTION socket option. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 04:03:05 +01:00
if (!!val && !ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
err = -EPERM;
break;
}
if (optlen < 1)
goto e_inval;
inet->transparent = !!val;
break;
case IP_MINTTL:
if (optlen < 1)
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
inet->min_ttl = val;
break;
default:
err = -ENOPROTOOPT;
break;
}
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return err;
e_inval:
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return -EINVAL;
}
/**
net-timestamp: allow reading recv cmsg on errqueue with origin tstamp Allow reading of timestamps and cmsg at the same time on all relevant socket families. One use is to correlate timestamps with egress device, by asking for cmsg IP_PKTINFO. on AF_INET sockets, call the relevant function (ip_cmsg_recv). To avoid changing legacy expectations, only do so if the caller sets a new timestamping flag SOF_TIMESTAMPING_OPT_CMSG. on AF_INET6 sockets, IPV6_PKTINFO and all other recv cmsg are already returned for all origins. only change is to set ifindex, which is not initialized for all error origins. In both cases, only generate the pktinfo message if an ifindex is known. This is not the case for ACK timestamps. The difference between the protocol families is probably a historical accident as a result of the different conditions for generating cmsg in the relevant ip(v6)_recv_error function: ipv4: if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { ipv6: if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { At one time, this was the same test bar for the ICMP/ICMP6 distinction. This is no longer true. Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1 -> v2 large rewrite - integrate with existing pktinfo cmsg generation code - on ipv4: only send with new flag, to maintain legacy behavior - on ipv6: send at most a single pktinfo cmsg - on ipv6: initialize fields if not yet initialized The recv cmsg interfaces are also relevant to the discussion of whether looping packet headers is problematic. For v6, cmsgs that identify many headers are already returned. This patch expands that to v4. If it sounds reasonable, I will follow with patches 1. request timestamps without payload with SOF_TIMESTAMPING_OPT_TSONLY (http://patchwork.ozlabs.org/patch/366967/) 2. sysctl to conditionally drop all timestamps that have payload or cmsg from users without CAP_NET_RAW. Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-01 04:22:34 +01:00
* ipv4_pktinfo_prepare - transfer some info from rtable to skb
* @sk: socket
* @skb: buffer
*
* To support IP_CMSG_PKTINFO option, we store rt_iif and specific
* destination in skb->cb[] before dst drop.
* This way, receiver doesn't make cache line misses to read rtable.
*/
void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
{
ipv4: PKTINFO doesnt need dst reference Le lundi 07 novembre 2011 à 15:33 +0100, Eric Dumazet a écrit : > At least, in recent kernels we dont change dst->refcnt in forwarding > patch (usinf NOREF skb->dst) > > One particular point is the atomic_inc(dst->refcnt) we have to perform > when queuing an UDP packet if socket asked PKTINFO stuff (for example a > typical DNS server has to setup this option) > > I have one patch somewhere that stores the information in skb->cb[] and > avoid the atomic_{inc|dec}(dst->refcnt). > OK I found it, I did some extra tests and believe its ready. [PATCH net-next] ipv4: IP_PKTINFO doesnt need dst reference When a socket uses IP_PKTINFO notifications, we currently force a dst reference for each received skb. Reader has to access dst to get needed information (rt_iif & rt_spec_dst) and must release dst reference. We also forced a dst reference if skb was put in socket backlog, even without IP_PKTINFO handling. This happens under stress/load. We can instead store the needed information in skb->cb[], so that only softirq handler really access dst, improving cache hit ratios. This removes two atomic operations per packet, and false sharing as well. On a benchmark using a mono threaded receiver (doing only recvmsg() calls), I can reach 720.000 pps instead of 570.000 pps. IP_PKTINFO is typically used by DNS servers, and any multihomed aware UDP application. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-09 08:24:35 +01:00
struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) ||
ipv6_sk_rxinfo(sk);
ipv4: PKTINFO doesnt need dst reference Le lundi 07 novembre 2011 à 15:33 +0100, Eric Dumazet a écrit : > At least, in recent kernels we dont change dst->refcnt in forwarding > patch (usinf NOREF skb->dst) > > One particular point is the atomic_inc(dst->refcnt) we have to perform > when queuing an UDP packet if socket asked PKTINFO stuff (for example a > typical DNS server has to setup this option) > > I have one patch somewhere that stores the information in skb->cb[] and > avoid the atomic_{inc|dec}(dst->refcnt). > OK I found it, I did some extra tests and believe its ready. [PATCH net-next] ipv4: IP_PKTINFO doesnt need dst reference When a socket uses IP_PKTINFO notifications, we currently force a dst reference for each received skb. Reader has to access dst to get needed information (rt_iif & rt_spec_dst) and must release dst reference. We also forced a dst reference if skb was put in socket backlog, even without IP_PKTINFO handling. This happens under stress/load. We can instead store the needed information in skb->cb[], so that only softirq handler really access dst, improving cache hit ratios. This removes two atomic operations per packet, and false sharing as well. On a benchmark using a mono threaded receiver (doing only recvmsg() calls), I can reach 720.000 pps instead of 570.000 pps. IP_PKTINFO is typically used by DNS servers, and any multihomed aware UDP application. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-09 08:24:35 +01:00
if (prepare && skb_rtable(skb)) {
/* skb->cb is overloaded: prior to this point it is IP{6}CB
* which has interface index (iif) as the first member of the
* underlying inet{6}_skb_parm struct. This code then overlays
* PKTINFO_SKB_CB and in_pktinfo also has iif as the first
* element so the iif is picked up from the prior IPCB
*/
pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
ipv4: PKTINFO doesnt need dst reference Le lundi 07 novembre 2011 à 15:33 +0100, Eric Dumazet a écrit : > At least, in recent kernels we dont change dst->refcnt in forwarding > patch (usinf NOREF skb->dst) > > One particular point is the atomic_inc(dst->refcnt) we have to perform > when queuing an UDP packet if socket asked PKTINFO stuff (for example a > typical DNS server has to setup this option) > > I have one patch somewhere that stores the information in skb->cb[] and > avoid the atomic_{inc|dec}(dst->refcnt). > OK I found it, I did some extra tests and believe its ready. [PATCH net-next] ipv4: IP_PKTINFO doesnt need dst reference When a socket uses IP_PKTINFO notifications, we currently force a dst reference for each received skb. Reader has to access dst to get needed information (rt_iif & rt_spec_dst) and must release dst reference. We also forced a dst reference if skb was put in socket backlog, even without IP_PKTINFO handling. This happens under stress/load. We can instead store the needed information in skb->cb[], so that only softirq handler really access dst, improving cache hit ratios. This removes two atomic operations per packet, and false sharing as well. On a benchmark using a mono threaded receiver (doing only recvmsg() calls), I can reach 720.000 pps instead of 570.000 pps. IP_PKTINFO is typically used by DNS servers, and any multihomed aware UDP application. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-09 08:24:35 +01:00
} else {
pktinfo->ipi_ifindex = 0;
pktinfo->ipi_spec_dst.s_addr = 0;
}
skb_dst_drop(skb);
}
int ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
{
int err;
if (level != SOL_IP)
return -ENOPROTOOPT;
err = do_ip_setsockopt(sk, level, optname, optval, optlen);
#ifdef CONFIG_NETFILTER
/* we need to exclude all possible ENOPROTOOPTs except default case */
if (err == -ENOPROTOOPT && optname != IP_HDRINCL &&
optname != IP_IPSEC_POLICY &&
optname != IP_XFRM_POLICY &&
!ip_mroute_opt(optname)) {
lock_sock(sk);
err = nf_setsockopt(sk, PF_INET, optname, optval, optlen);
release_sock(sk);
}
#endif
return err;
}
EXPORT_SYMBOL(ip_setsockopt);
#ifdef CONFIG_COMPAT
int compat_ip_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
int err;
if (level != SOL_IP)
return -ENOPROTOOPT;
if (optname >= MCAST_JOIN_GROUP && optname <= MCAST_MSFILTER)
return compat_mc_setsockopt(sk, level, optname, optval, optlen,
ip_setsockopt);
err = do_ip_setsockopt(sk, level, optname, optval, optlen);
#ifdef CONFIG_NETFILTER
/* we need to exclude all possible ENOPROTOOPTs except default case */
if (err == -ENOPROTOOPT && optname != IP_HDRINCL &&
optname != IP_IPSEC_POLICY &&
optname != IP_XFRM_POLICY &&
!ip_mroute_opt(optname)) {
lock_sock(sk);
err = compat_nf_setsockopt(sk, PF_INET, optname,
optval, optlen);
release_sock(sk);
}
#endif
return err;
}
EXPORT_SYMBOL(compat_ip_setsockopt);
#endif
/*
* Get the options. Note for future reference. The GET of IP options gets
* the _received_ ones. The set sets the _sent_ ones.
*/
static bool getsockopt_needs_rtnl(int optname)
{
switch (optname) {
case IP_MSFILTER:
case MCAST_MSFILTER:
return true;
}
return false;
}
static int do_ip_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen, unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
bool needs_rtnl = getsockopt_needs_rtnl(optname);
int val, err = 0;
int len;
if (level != SOL_IP)
return -EOPNOTSUPP;
if (ip_mroute_opt(optname))
return ip_mroute_getsockopt(sk, optname, optval, optlen);
if (get_user(len, optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
if (needs_rtnl)
rtnl_lock();
lock_sock(sk);
switch (optname) {
case IP_OPTIONS:
{
unsigned char optbuf[sizeof(struct ip_options)+40];
struct ip_options *opt = (struct ip_options *)optbuf;
struct ip_options_rcu *inet_opt;
inet_opt = rcu_dereference_protected(inet->inet_opt,
lockdep_sock_is_held(sk));
opt->optlen = 0;
if (inet_opt)
memcpy(optbuf, &inet_opt->opt,
sizeof(struct ip_options) +
inet_opt->opt.optlen);
release_sock(sk);
if (opt->optlen == 0)
return put_user(0, optlen);
ip_options_undo(opt);
len = min_t(unsigned int, len, opt->optlen);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, opt->__data, len))
return -EFAULT;
return 0;
}
case IP_PKTINFO:
val = (inet->cmsg_flags & IP_CMSG_PKTINFO) != 0;
break;
case IP_RECVTTL:
val = (inet->cmsg_flags & IP_CMSG_TTL) != 0;
break;
case IP_RECVTOS:
val = (inet->cmsg_flags & IP_CMSG_TOS) != 0;
break;
case IP_RECVOPTS:
val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0;
break;
case IP_RETOPTS:
val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0;
break;
case IP_PASSSEC:
val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0;
break;
case IP_RECVORIGDSTADDR:
val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0;
break;
case IP_CHECKSUM:
val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0;
break;
case IP_TOS:
val = inet->tos;
break;
case IP_TTL:
{
struct net *net = sock_net(sk);
val = (inet->uc_ttl == -1 ?
net->ipv4.sysctl_ip_default_ttl :
inet->uc_ttl);
break;
}
case IP_HDRINCL:
val = inet->hdrincl;
break;
case IP_NODEFRAG:
val = inet->nodefrag;
break;
inet: add IP_BIND_ADDRESS_NO_PORT to overcome bind(0) limitations When an application needs to force a source IP on an active TCP socket it has to use bind(IP, port=x). As most applications do not want to deal with already used ports, x is often set to 0, meaning the kernel is in charge to find an available port. But kernel does not know yet if this socket is going to be a listener or be connected. It has very limited choices (no full knowledge of final 4-tuple for a connect()) With limited ephemeral port range (about 32K ports), it is very easy to fill the space. This patch adds a new SOL_IP socket option, asking kernel to ignore the 0 port provided by application in bind(IP, port=0) and only remember the given IP address. The port will be automatically chosen at connect() time, in a way that allows sharing a source port as long as the 4-tuples are unique. This new feature is available for both IPv4 and IPv6 (Thanks Neal) Tested: Wrote a test program and checked its behavior on IPv4 and IPv6. strace(1) shows sequences of bind(IP=127.0.0.2, port=0) followed by connect(). Also getsockname() show that the port is still 0 right after bind() but properly allocated after connect(). socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 5 setsockopt(5, SOL_IP, IP_BIND_ADDRESS_NO_PORT, [1], 4) = 0 bind(5, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("127.0.0.2")}, 16) = 0 getsockname(5, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("127.0.0.2")}, [16]) = 0 connect(5, {sa_family=AF_INET, sin_port=htons(53174), sin_addr=inet_addr("127.0.0.3")}, 16) = 0 getsockname(5, {sa_family=AF_INET, sin_port=htons(38050), sin_addr=inet_addr("127.0.0.2")}, [16]) = 0 IPv6 test : socket(PF_INET6, SOCK_STREAM, IPPROTO_IP) = 7 setsockopt(7, SOL_IP, IP_BIND_ADDRESS_NO_PORT, [1], 4) = 0 bind(7, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = 0 getsockname(7, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, [28]) = 0 connect(7, {sa_family=AF_INET6, sin6_port=htons(57300), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = 0 getsockname(7, {sa_family=AF_INET6, sin6_port=htons(60964), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, [28]) = 0 I was able to bind()/connect() a million concurrent IPv4 sockets, instead of ~32000 before patch. lpaa23:~# ulimit -n 1000010 lpaa23:~# ./bind --connect --num-flows=1000000 & 1000000 sockets lpaa23:~# grep TCP /proc/net/sockstat TCP: inuse 2000063 orphan 0 tw 47 alloc 2000157 mem 66 Check that a given source port is indeed used by many different connections : lpaa23:~# ss -t src :40000 | head -10 State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 0 127.0.0.2:40000 127.0.202.33:44983 ESTAB 0 0 127.0.0.2:40000 127.2.27.240:44983 ESTAB 0 0 127.0.0.2:40000 127.2.98.5:44983 ESTAB 0 0 127.0.0.2:40000 127.0.124.196:44983 ESTAB 0 0 127.0.0.2:40000 127.2.139.38:44983 ESTAB 0 0 127.0.0.2:40000 127.1.59.80:44983 ESTAB 0 0 127.0.0.2:40000 127.3.6.228:44983 ESTAB 0 0 127.0.0.2:40000 127.0.38.53:44983 ESTAB 0 0 127.0.0.2:40000 127.1.197.10:44983 Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-07 06:17:57 +02:00
case IP_BIND_ADDRESS_NO_PORT:
val = inet->bind_address_no_port;
break;
case IP_MTU_DISCOVER:
val = inet->pmtudisc;
break;
case IP_MTU:
{
struct dst_entry *dst;
val = 0;
dst = sk_dst_get(sk);
if (dst) {
val = dst_mtu(dst);
dst_release(dst);
}
if (!val) {
release_sock(sk);
return -ENOTCONN;
}
break;
}
case IP_RECVERR:
val = inet->recverr;
break;
case IP_MULTICAST_TTL:
val = inet->mc_ttl;
break;
case IP_MULTICAST_LOOP:
val = inet->mc_loop;
break;
ipv4: Implement IP_UNICAST_IF socket option. The IP_UNICAST_IF feature is needed by the Wine project. This patch implements the feature by setting the outgoing interface in a similar fashion to that of IP_MULTICAST_IF. A separate option is needed to handle this feature since the existing options do not provide all of the characteristics required by IP_UNICAST_IF, a summary is provided below. SO_BINDTODEVICE: * SO_BINDTODEVICE requires administrative privileges, IP_UNICAST_IF does not. From reading some old mailing list articles my understanding is that SO_BINDTODEVICE requires administrative privileges because it can override the administrator's routing settings. * The SO_BINDTODEVICE option restricts both outbound and inbound traffic, IP_UNICAST_IF only impacts outbound traffic. IP_PKTINFO: * Since IP_PKTINFO and IP_UNICAST_IF are independent options, implementing IP_UNICAST_IF with IP_PKTINFO will likely break some applications. * Implementing IP_UNICAST_IF on top of IP_PKTINFO significantly complicates the Wine codebase and reduces the socket performance (doing this requires a lot of extra communication between the "server" and "user" layers). bind(): * bind() does not work on broadcast packets, IP_UNICAST_IF is specifically intended to work with broadcast packets. * Like SO_BINDTODEVICE, bind() restricts both outbound and inbound traffic. Signed-off-by: Erich E. Hoover <ehoover@mines.edu> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-08 10:11:07 +01:00
case IP_UNICAST_IF:
val = (__force int)htonl((__u32) inet->uc_index);
break;
case IP_MULTICAST_IF:
{
struct in_addr addr;
len = min_t(unsigned int, len, sizeof(struct in_addr));
addr.s_addr = inet->mc_addr;
release_sock(sk);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &addr, len))
return -EFAULT;
return 0;
}
case IP_MSFILTER:
{
struct ip_msfilter msf;
if (len < IP_MSFILTER_SIZE(0)) {
err = -EINVAL;
goto out;
}
if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) {
err = -EFAULT;
goto out;
}
err = ip_mc_msfget(sk, &msf,
(struct ip_msfilter __user *)optval, optlen);
goto out;
}
case MCAST_MSFILTER:
{
struct group_filter gsf;
if (len < GROUP_FILTER_SIZE(0)) {
err = -EINVAL;
goto out;
}
if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) {
err = -EFAULT;
goto out;
}
err = ip_mc_gsfget(sk, &gsf,
(struct group_filter __user *)optval,
optlen);
goto out;
}
case IP_MULTICAST_ALL:
val = inet->mc_all;
break;
case IP_PKTOPTIONS:
{
struct msghdr msg;
release_sock(sk);
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
msg.msg_control = (__force void *) optval;
msg.msg_controllen = len;
msg.msg_flags = flags;
if (inet->cmsg_flags & IP_CMSG_PKTINFO) {
struct in_pktinfo info;
info.ipi_addr.s_addr = inet->inet_rcv_saddr;
info.ipi_spec_dst.s_addr = inet->inet_rcv_saddr;
info.ipi_ifindex = inet->mc_index;
put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
}
if (inet->cmsg_flags & IP_CMSG_TTL) {
int hlim = inet->mc_ttl;
put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
}
if (inet->cmsg_flags & IP_CMSG_TOS) {
int tos = inet->rcv_tos;
put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
}
len -= msg.msg_controllen;
return put_user(len, optlen);
}
case IP_FREEBIND:
val = inet->freebind;
break;
case IP_TRANSPARENT:
val = inet->transparent;
break;
case IP_MINTTL:
val = inet->min_ttl;
break;
default:
release_sock(sk);
return -ENOPROTOOPT;
}
release_sock(sk);
if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) {
unsigned char ucval = (unsigned char)val;
len = 1;
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &ucval, 1))
return -EFAULT;
} else {
len = min_t(unsigned int, sizeof(int), len);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &val, len))
return -EFAULT;
}
return 0;
out:
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return err;
}
int ip_getsockopt(struct sock *sk, int level,
int optname, char __user *optval, int __user *optlen)
{
int err;
err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0);
#ifdef CONFIG_NETFILTER
/* we need to exclude all possible ENOPROTOOPTs except default case */
if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&
!ip_mroute_opt(optname)) {
int len;
if (get_user(len, optlen))
return -EFAULT;
lock_sock(sk);
err = nf_getsockopt(sk, PF_INET, optname, optval,
&len);
release_sock(sk);
if (err >= 0)
err = put_user(len, optlen);
return err;
}
#endif
return err;
}
EXPORT_SYMBOL(ip_getsockopt);
#ifdef CONFIG_COMPAT
int compat_ip_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
int err;
if (optname == MCAST_MSFILTER)
return compat_mc_getsockopt(sk, level, optname, optval, optlen,
ip_getsockopt);
err = do_ip_getsockopt(sk, level, optname, optval, optlen,
MSG_CMSG_COMPAT);
#ifdef CONFIG_NETFILTER
/* we need to exclude all possible ENOPROTOOPTs except default case */
if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&
!ip_mroute_opt(optname)) {
int len;
if (get_user(len, optlen))
return -EFAULT;
lock_sock(sk);
err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len);
release_sock(sk);
if (err >= 0)
err = put_user(len, optlen);
return err;
}
#endif
return err;
}
EXPORT_SYMBOL(compat_ip_getsockopt);
#endif