linux/net/ipv4/sysctl_net_ipv4.c

1215 lines
29 KiB
C
Raw Normal View History

/*
* sysctl_net_ipv4.c: sysctl interface to net IPV4 subsystem.
*
* Begun April 1, 1996, Mike Shaver.
* Added /proc/sys/net/ipv4 directory entry (empty =) ). [MS]
*/
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/seqlock.h>
#include <linux/init.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
#include <linux/nsproxy.h>
#include <linux/swap.h>
#include <net/snmp.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/cipso_ipv4.h>
#include <net/inet_frag.h>
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
#include <net/ping.h>
#include <net/protocol.h>
static int zero;
static int one = 1;
tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-11 10:00:43 +00:00
static int four = 4;
static int thousand = 1000;
tcp: TSO packets automatic sizing After hearing many people over past years complaining against TSO being bursty or even buggy, we are proud to present automatic sizing of TSO packets. One part of the problem is that tcp_tso_should_defer() uses an heuristic relying on upcoming ACKS instead of a timer, but more generally, having big TSO packets makes little sense for low rates, as it tends to create micro bursts on the network, and general consensus is to reduce the buffering amount. This patch introduces a per socket sk_pacing_rate, that approximates the current sending rate, and allows us to size the TSO packets so that we try to send one packet every ms. This field could be set by other transports. Patch has no impact for high speed flows, where having large TSO packets makes sense to reach line rate. For other flows, this helps better packet scheduling and ACK clocking. This patch increases performance of TCP flows in lossy environments. A new sysctl (tcp_min_tso_segs) is added, to specify the minimal size of a TSO packet (default being 2). A follow-up patch will provide a new packet scheduler (FQ), using sk_pacing_rate as an input to perform optional per flow pacing. This explains why we chose to set sk_pacing_rate to twice the current rate, allowing 'slow start' ramp up. sk_pacing_rate = 2 * cwnd * mss / srtt v2: Neal Cardwell reported a suspect deferring of last two segments on initial write of 10 MSS, I had to change tcp_tso_should_defer() to take into account tp->xmit_size_goal_segs Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Van Jacobson <vanj@google.com> Cc: Tom Herbert <therbert@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-27 12:46:32 +00:00
static int gso_max_segs = GSO_MAX_SEGS;
static int tcp_retr1_max = 255;
static int ip_local_port_range_min[] = { 1, 1 };
static int ip_local_port_range_max[] = { 65535, 65535 };
static int tcp_adv_win_scale_min = -31;
static int tcp_adv_win_scale_max = 31;
static int ip_privileged_port_min;
static int ip_privileged_port_max = 65535;
static int ip_ttl_min = 1;
static int ip_ttl_max = 255;
static int tcp_syn_retries_min = 1;
static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
/* Update system visible IP port range */
static void set_local_port_range(struct net *net, int range[2])
{
bool same_parity = !((range[0] ^ range[1]) & 1);
ipv4: disable BH when changing ip local port range This fixes the following lockdep warning: [ INFO: inconsistent lock state ] 4.3.0-rc7+ #1197 Not tainted --------------------------------- inconsistent {IN-SOFTIRQ-R} -> {SOFTIRQ-ON-W} usage. sysctl/1019 [HC0[0]:SC0[0]:HE1:SE1] takes: (&(&net->ipv4.ip_local_ports.lock)->seqcount){+.+-..}, at: [<ffffffff81921de7>] ipv4_local_port_range+0xb4/0x12a {IN-SOFTIRQ-R} state was registered at: [<ffffffff810bd682>] __lock_acquire+0x2f6/0xdf0 [<ffffffff810be6d5>] lock_acquire+0x11c/0x1a4 [<ffffffff818e599c>] inet_get_local_port_range+0x4e/0xae [<ffffffff8166e8e3>] udp_flow_src_port.constprop.40+0x23/0x116 [<ffffffff81671cb9>] vxlan_xmit_one+0x219/0xa6a [<ffffffff81672f75>] vxlan_xmit+0xa6b/0xaa5 [<ffffffff817f2deb>] dev_hard_start_xmit+0x2ae/0x465 [<ffffffff817f35ed>] __dev_queue_xmit+0x531/0x633 [<ffffffff817f3702>] dev_queue_xmit_sk+0x13/0x15 [<ffffffff818004a5>] neigh_resolve_output+0x12f/0x14d [<ffffffff81959cfa>] ip6_finish_output2+0x344/0x39f [<ffffffff8195bf58>] ip6_finish_output+0x88/0x8e [<ffffffff8195bfef>] ip6_output+0x91/0xe5 [<ffffffff819792ae>] dst_output_sk+0x47/0x4c [<ffffffff81979392>] NF_HOOK_THRESH.constprop.30+0x38/0x82 [<ffffffff8197981e>] mld_sendpack+0x189/0x266 [<ffffffff8197b28b>] mld_ifc_timer_expire+0x1ef/0x223 [<ffffffff810de581>] call_timer_fn+0xfb/0x28c [<ffffffff810ded1e>] run_timer_softirq+0x1c7/0x1f1 Fixes: b8f1a55639e6 ("udp: Add function to make source port for UDP tunnels") Cc: Tom Herbert <tom@herbertland.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-03 22:32:57 +00:00
write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
if (same_parity && !net->ipv4.ip_local_ports.warned) {
net->ipv4.ip_local_ports.warned = true;
pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n");
}
net->ipv4.ip_local_ports.range[0] = range[0];
net->ipv4.ip_local_ports.range[1] = range[1];
ipv4: disable BH when changing ip local port range This fixes the following lockdep warning: [ INFO: inconsistent lock state ] 4.3.0-rc7+ #1197 Not tainted --------------------------------- inconsistent {IN-SOFTIRQ-R} -> {SOFTIRQ-ON-W} usage. sysctl/1019 [HC0[0]:SC0[0]:HE1:SE1] takes: (&(&net->ipv4.ip_local_ports.lock)->seqcount){+.+-..}, at: [<ffffffff81921de7>] ipv4_local_port_range+0xb4/0x12a {IN-SOFTIRQ-R} state was registered at: [<ffffffff810bd682>] __lock_acquire+0x2f6/0xdf0 [<ffffffff810be6d5>] lock_acquire+0x11c/0x1a4 [<ffffffff818e599c>] inet_get_local_port_range+0x4e/0xae [<ffffffff8166e8e3>] udp_flow_src_port.constprop.40+0x23/0x116 [<ffffffff81671cb9>] vxlan_xmit_one+0x219/0xa6a [<ffffffff81672f75>] vxlan_xmit+0xa6b/0xaa5 [<ffffffff817f2deb>] dev_hard_start_xmit+0x2ae/0x465 [<ffffffff817f35ed>] __dev_queue_xmit+0x531/0x633 [<ffffffff817f3702>] dev_queue_xmit_sk+0x13/0x15 [<ffffffff818004a5>] neigh_resolve_output+0x12f/0x14d [<ffffffff81959cfa>] ip6_finish_output2+0x344/0x39f [<ffffffff8195bf58>] ip6_finish_output+0x88/0x8e [<ffffffff8195bfef>] ip6_output+0x91/0xe5 [<ffffffff819792ae>] dst_output_sk+0x47/0x4c [<ffffffff81979392>] NF_HOOK_THRESH.constprop.30+0x38/0x82 [<ffffffff8197981e>] mld_sendpack+0x189/0x266 [<ffffffff8197b28b>] mld_ifc_timer_expire+0x1ef/0x223 [<ffffffff810de581>] call_timer_fn+0xfb/0x28c [<ffffffff810ded1e>] run_timer_softirq+0x1c7/0x1f1 Fixes: b8f1a55639e6 ("udp: Add function to make source port for UDP tunnels") Cc: Tom Herbert <tom@herbertland.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-03 22:32:57 +00:00
write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
static int ipv4_local_port_range(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
struct net *net =
container_of(table->data, struct net, ipv4.ip_local_ports.range);
int ret;
int range[2];
struct ctl_table tmp = {
.data = &range,
.maxlen = sizeof(range),
.mode = table->mode,
.extra1 = &ip_local_port_range_min,
.extra2 = &ip_local_port_range_max,
};
inet_get_local_port_range(net, &range[0], &range[1]);
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && ret == 0) {
/* Ensure that the upper limit is not smaller than the lower,
* and that the lower does not encroach upon the privileged
* port limit.
*/
if ((range[1] < range[0]) ||
(range[0] < net->ipv4.sysctl_ip_prot_sock))
ret = -EINVAL;
else
set_local_port_range(net, range);
}
return ret;
}
/* Validate changes from /proc interface. */
static int ipv4_privileged_ports(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct net *net = container_of(table->data, struct net,
ipv4.sysctl_ip_prot_sock);
int ret;
int pports;
int range[2];
struct ctl_table tmp = {
.data = &pports,
.maxlen = sizeof(pports),
.mode = table->mode,
.extra1 = &ip_privileged_port_min,
.extra2 = &ip_privileged_port_max,
};
pports = net->ipv4.sysctl_ip_prot_sock;
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && ret == 0) {
inet_get_local_port_range(net, &range[0], &range[1]);
/* Ensure that the local port range doesn't overlap with the
* privileged port range.
*/
if (range[0] < pports)
ret = -EINVAL;
else
net->ipv4.sysctl_ip_prot_sock = pports;
}
return ret;
}
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high)
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
{
kgid_t *data = table->data;
struct net *net =
container_of(table->data, struct net, ipv4.ping_group_range.range);
unsigned int seq;
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
do {
seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
*low = data[0];
*high = data[1];
} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
}
/* Update system visible IP port range */
static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high)
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
{
kgid_t *data = table->data;
struct net *net =
container_of(table->data, struct net, ipv4.ping_group_range.range);
write_seqlock(&net->ipv4.ping_group_range.lock);
data[0] = low;
data[1] = high;
write_sequnlock(&net->ipv4.ping_group_range.lock);
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
}
/* Validate changes from /proc interface. */
static int ipv4_ping_group_range(struct ctl_table *table, int write,
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
struct user_namespace *user_ns = current_user_ns();
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
int ret;
gid_t urange[2];
kgid_t low, high;
struct ctl_table tmp = {
.data = &urange,
.maxlen = sizeof(urange),
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
.mode = table->mode,
.extra1 = &ip_ping_group_range_min,
.extra2 = &ip_ping_group_range_max,
};
inet_get_ping_group_range_table(table, &low, &high);
urange[0] = from_kgid_munged(user_ns, low);
urange[1] = from_kgid_munged(user_ns, high);
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && ret == 0) {
low = make_kgid(user_ns, urange[0]);
high = make_kgid(user_ns, urange[1]);
if (!gid_valid(low) || !gid_valid(high) ||
(urange[1] < urange[0]) || gid_lt(high, low)) {
low = make_kgid(&init_user_ns, 1);
high = make_kgid(&init_user_ns, 0);
}
set_ping_group_range(table, low, high);
}
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
return ret;
}
static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
char val[TCP_CA_NAME_MAX];
struct ctl_table tbl = {
.data = val,
.maxlen = TCP_CA_NAME_MAX,
};
int ret;
tcp_get_default_congestion_control(val);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0)
ret = tcp_set_default_congestion_control(val);
return ret;
}
static int proc_tcp_available_congestion_control(struct ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, };
int ret;
tbl.data = kmalloc(tbl.maxlen, GFP_USER);
if (!tbl.data)
return -ENOMEM;
tcp_get_available_congestion_control(tbl.data, TCP_CA_BUF_MAX);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
kfree(tbl.data);
return ret;
}
static int proc_allowed_congestion_control(struct ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX };
int ret;
tbl.data = kmalloc(tbl.maxlen, GFP_USER);
if (!tbl.data)
return -ENOMEM;
tcp_get_allowed_congestion_control(tbl.data, tbl.maxlen);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0)
ret = tcp_set_allowed_congestion_control(tbl.data);
kfree(tbl.data);
return ret;
}
static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
int ret;
u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
if (!tbl.data)
return -ENOMEM;
rcu_read_lock();
ctxt = rcu_dereference(tcp_fastopen_ctx);
if (ctxt)
memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
else
memset(user_key, 0, sizeof(user_key));
rcu_read_unlock();
snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
user_key[0], user_key[1], user_key[2], user_key[3]);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0) {
if (sscanf(tbl.data, "%x-%x-%x-%x", user_key, user_key + 1,
user_key + 2, user_key + 3) != 4) {
ret = -EINVAL;
goto bad_key;
}
/* Generate a dummy secret but don't publish it. This
* is needed so we don't regenerate a new key on the
* first invocation of tcp_fastopen_cookie_gen
*/
tcp_fastopen_init_key_once(false);
tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
}
bad_key:
pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
user_key[0], user_key[1], user_key[2], user_key[3],
(char *)tbl.data, ret);
kfree(tbl.data);
return ret;
}
static void proc_configure_early_demux(int enabled, int protocol)
{
struct net_protocol *ipprot;
#if IS_ENABLED(CONFIG_IPV6)
struct inet6_protocol *ip6prot;
#endif
rcu_read_lock();
ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot)
ipprot->early_demux = enabled ? ipprot->early_demux_handler :
NULL;
#if IS_ENABLED(CONFIG_IPV6)
ip6prot = rcu_dereference(inet6_protos[protocol]);
if (ip6prot)
ip6prot->early_demux = enabled ? ip6prot->early_demux_handler :
NULL;
#endif
rcu_read_unlock();
}
static int proc_tcp_early_demux(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int ret = 0;
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (write && !ret) {
int enabled = init_net.ipv4.sysctl_tcp_early_demux;
proc_configure_early_demux(enabled, IPPROTO_TCP);
}
return ret;
}
static int proc_udp_early_demux(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int ret = 0;
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (write && !ret) {
int enabled = init_net.ipv4.sysctl_udp_early_demux;
proc_configure_early_demux(enabled, IPPROTO_UDP);
}
return ret;
}
net/tcp_fastopen: Disable active side TFO in certain scenarios Middlebox firewall issues can potentially cause server's data being blackholed after a successful 3WHS using TFO. Following are the related reports from Apple: https://www.nanog.org/sites/default/files/Paasch_Network_Support.pdf Slide 31 identifies an issue where the client ACK to the server's data sent during a TFO'd handshake is dropped. C ---> syn-data ---> S C <--- syn/ack ----- S C (accept & write) C <---- data ------- S C ----- ACK -> X S [retry and timeout] https://www.ietf.org/proceedings/94/slides/slides-94-tcpm-13.pdf Slide 5 shows a similar situation that the server's data gets dropped after 3WHS. C ---- syn-data ---> S C <--- syn/ack ----- S C ---- ack --------> S S (accept & write) C? X <- data ------ S [retry and timeout] This is the worst failure b/c the client can not detect such behavior to mitigate the situation (such as disabling TFO). Failing to proceed, the application (e.g., SSL library) may simply timeout and retry with TFO again, and the process repeats indefinitely. The proposed solution is to disable active TFO globally under the following circumstances: 1. client side TFO socket detects out of order FIN 2. client side TFO socket receives out of order RST We disable active side TFO globally for 1hr at first. Then if it happens again, we disable it for 2h, then 4h, 8h, ... And we reset the timeout to 1hr if a client side TFO sockets not opened on loopback has successfully received data segs from server. And we examine this condition during close(). The rational behind it is that when such firewall issue happens, application running on the client should eventually close the socket as it is not able to get the data it is expecting. Or application running on the server should close the socket as it is not able to receive any response from client. In both cases, out of order FIN or RST will get received on the client given that the firewall will not block them as no data are in those frames. And we want to disable active TFO globally as it helps if the middle box is very close to the client and most of the connections are likely to fail. Also, add a debug sysctl: tcp_fastopen_blackhole_detect_timeout_sec: the initial timeout to use when firewall blackhole issue happens. This can be set and read. When setting it to 0, it means to disable the active disable logic. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-20 21:45:46 +00:00
static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
int ret;
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (write && ret == 0)
tcp_fastopen_active_timeout_reset();
return ret;
}
static int proc_tcp_available_ulp(struct ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, };
int ret;
tbl.data = kmalloc(tbl.maxlen, GFP_USER);
if (!tbl.data)
return -ENOMEM;
tcp_get_available_ulp(tbl.data, TCP_ULP_BUF_MAX);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
kfree(tbl.data);
net/tcp_fastopen: Disable active side TFO in certain scenarios Middlebox firewall issues can potentially cause server's data being blackholed after a successful 3WHS using TFO. Following are the related reports from Apple: https://www.nanog.org/sites/default/files/Paasch_Network_Support.pdf Slide 31 identifies an issue where the client ACK to the server's data sent during a TFO'd handshake is dropped. C ---> syn-data ---> S C <--- syn/ack ----- S C (accept & write) C <---- data ------- S C ----- ACK -> X S [retry and timeout] https://www.ietf.org/proceedings/94/slides/slides-94-tcpm-13.pdf Slide 5 shows a similar situation that the server's data gets dropped after 3WHS. C ---- syn-data ---> S C <--- syn/ack ----- S C ---- ack --------> S S (accept & write) C? X <- data ------ S [retry and timeout] This is the worst failure b/c the client can not detect such behavior to mitigate the situation (such as disabling TFO). Failing to proceed, the application (e.g., SSL library) may simply timeout and retry with TFO again, and the process repeats indefinitely. The proposed solution is to disable active TFO globally under the following circumstances: 1. client side TFO socket detects out of order FIN 2. client side TFO socket receives out of order RST We disable active side TFO globally for 1hr at first. Then if it happens again, we disable it for 2h, then 4h, 8h, ... And we reset the timeout to 1hr if a client side TFO sockets not opened on loopback has successfully received data segs from server. And we examine this condition during close(). The rational behind it is that when such firewall issue happens, application running on the client should eventually close the socket as it is not able to get the data it is expecting. Or application running on the server should close the socket as it is not able to receive any response from client. In both cases, out of order FIN or RST will get received on the client given that the firewall will not block them as no data are in those frames. And we want to disable active TFO globally as it helps if the middle box is very close to the client and most of the connections are likely to fail. Also, add a debug sysctl: tcp_fastopen_blackhole_detect_timeout_sec: the initial timeout to use when firewall blackhole issue happens. This can be set and read. When setting it to 0, it means to disable the active disable logic. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-20 21:45:46 +00:00
return ret;
}
static struct ctl_table ipv4_table[] = {
{
.procname = "tcp_retrans_collapse",
.data = &sysctl_tcp_retrans_collapse,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_max_orphans",
.data = &sysctl_tcp_max_orphans,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_fastopen",
.data = &sysctl_tcp_fastopen,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_fastopen_key",
.mode = 0600,
.maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
.proc_handler = proc_tcp_fastopen_key,
},
net/tcp_fastopen: Disable active side TFO in certain scenarios Middlebox firewall issues can potentially cause server's data being blackholed after a successful 3WHS using TFO. Following are the related reports from Apple: https://www.nanog.org/sites/default/files/Paasch_Network_Support.pdf Slide 31 identifies an issue where the client ACK to the server's data sent during a TFO'd handshake is dropped. C ---> syn-data ---> S C <--- syn/ack ----- S C (accept & write) C <---- data ------- S C ----- ACK -> X S [retry and timeout] https://www.ietf.org/proceedings/94/slides/slides-94-tcpm-13.pdf Slide 5 shows a similar situation that the server's data gets dropped after 3WHS. C ---- syn-data ---> S C <--- syn/ack ----- S C ---- ack --------> S S (accept & write) C? X <- data ------ S [retry and timeout] This is the worst failure b/c the client can not detect such behavior to mitigate the situation (such as disabling TFO). Failing to proceed, the application (e.g., SSL library) may simply timeout and retry with TFO again, and the process repeats indefinitely. The proposed solution is to disable active TFO globally under the following circumstances: 1. client side TFO socket detects out of order FIN 2. client side TFO socket receives out of order RST We disable active side TFO globally for 1hr at first. Then if it happens again, we disable it for 2h, then 4h, 8h, ... And we reset the timeout to 1hr if a client side TFO sockets not opened on loopback has successfully received data segs from server. And we examine this condition during close(). The rational behind it is that when such firewall issue happens, application running on the client should eventually close the socket as it is not able to get the data it is expecting. Or application running on the server should close the socket as it is not able to receive any response from client. In both cases, out of order FIN or RST will get received on the client given that the firewall will not block them as no data are in those frames. And we want to disable active TFO globally as it helps if the middle box is very close to the client and most of the connections are likely to fail. Also, add a debug sysctl: tcp_fastopen_blackhole_detect_timeout_sec: the initial timeout to use when firewall blackhole issue happens. This can be set and read. When setting it to 0, it means to disable the active disable logic. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-20 21:45:46 +00:00
{
.procname = "tcp_fastopen_blackhole_timeout_sec",
.data = &sysctl_tcp_fastopen_blackhole_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_tfo_blackhole_detect_timeout,
.extra1 = &zero,
},
{
.procname = "tcp_abort_on_overflow",
.data = &sysctl_tcp_abort_on_overflow,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_stdurg",
.data = &sysctl_tcp_stdurg,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_rfc1337",
.data = &sysctl_tcp_rfc1337,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "inet_peer_threshold",
.data = &inet_peer_threshold,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "inet_peer_minttl",
.data = &inet_peer_minttl,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "inet_peer_maxttl",
.data = &inet_peer_maxttl,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "tcp_fack",
.data = &sysctl_tcp_fack,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_recovery",
.data = &sysctl_tcp_recovery,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_max_reordering",
.data = &sysctl_tcp_max_reordering,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_dsack",
.data = &sysctl_tcp_dsack,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_mem",
.maxlen = sizeof(sysctl_tcp_mem),
.data = &sysctl_tcp_mem,
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "tcp_wmem",
.data = &sysctl_tcp_wmem,
.maxlen = sizeof(sysctl_tcp_wmem),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
Revert "net: limit tcp/udp rmem/wmem to SOCK_{RCV,SND}BUF_MIN" Commit 8133534c760d4083 ("net: limit tcp/udp rmem/wmem to SOCK_{RCV,SND}BUF_MIN") modified four sysctls to enforce that the values written to them are not less than SOCK_MIN_{RCV,SND}BUF. That change causes 4096 to no longer be accepted as a valid value for 'min' in tcp_wmem and udp_wmem_min. 4096 has been the default for both of those sysctls for a long time, and unfortunately seems to be an extremely popular setting. This change breaks a large number of sysctl configurations at Facebook. That commit referred to b1cb59cf2efe7971 ("net: sysctl_net_core: check SNDBUF and RCVBUF for min length"), which choose to use the SOCK_MIN constants as the lower limits to avoid nasty bugs. But AFAICS, a limit of SOCK_MIN_SNDBUF isn't necessary to do that: the BUG_ON cited in the commit message seems to have happened because unix_stream_sendmsg() expects a minimum of a full page (ie SK_MEM_QUANTUM) and the math broke, not because it had less than SOCK_MIN_SNDBUF allocated. This particular issue doesn't seem to affect TCP however: using a setting of "1 1 1" for tcp_{r,w}mem works, although it's obviously suboptimal. SK_MEM_QUANTUM would be a nice minimum, but it's 64K on some archs, so there would still be breakage. Since a value of one doesn't seem to cause any problems, we can drop the minimum 8133534c added to fix this. This reverts commit 8133534c760d4083f79d2cde42c636ccc0b2792e. Fixes: 8133534c760d4083 ("net: limit tcp/udp rmem/wmem to SOCK_MIN...") Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Sorin Dumitru <sorin@returnze.ro> Signed-off-by: Calvin Owens <calvinowens@fb.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-13 21:21:34 +00:00
.extra1 = &one,
},
{
.procname = "tcp_rmem",
.data = &sysctl_tcp_rmem,
.maxlen = sizeof(sysctl_tcp_rmem),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
Revert "net: limit tcp/udp rmem/wmem to SOCK_{RCV,SND}BUF_MIN" Commit 8133534c760d4083 ("net: limit tcp/udp rmem/wmem to SOCK_{RCV,SND}BUF_MIN") modified four sysctls to enforce that the values written to them are not less than SOCK_MIN_{RCV,SND}BUF. That change causes 4096 to no longer be accepted as a valid value for 'min' in tcp_wmem and udp_wmem_min. 4096 has been the default for both of those sysctls for a long time, and unfortunately seems to be an extremely popular setting. This change breaks a large number of sysctl configurations at Facebook. That commit referred to b1cb59cf2efe7971 ("net: sysctl_net_core: check SNDBUF and RCVBUF for min length"), which choose to use the SOCK_MIN constants as the lower limits to avoid nasty bugs. But AFAICS, a limit of SOCK_MIN_SNDBUF isn't necessary to do that: the BUG_ON cited in the commit message seems to have happened because unix_stream_sendmsg() expects a minimum of a full page (ie SK_MEM_QUANTUM) and the math broke, not because it had less than SOCK_MIN_SNDBUF allocated. This particular issue doesn't seem to affect TCP however: using a setting of "1 1 1" for tcp_{r,w}mem works, although it's obviously suboptimal. SK_MEM_QUANTUM would be a nice minimum, but it's 64K on some archs, so there would still be breakage. Since a value of one doesn't seem to cause any problems, we can drop the minimum 8133534c added to fix this. This reverts commit 8133534c760d4083f79d2cde42c636ccc0b2792e. Fixes: 8133534c760d4083 ("net: limit tcp/udp rmem/wmem to SOCK_MIN...") Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Sorin Dumitru <sorin@returnze.ro> Signed-off-by: Calvin Owens <calvinowens@fb.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-13 21:21:34 +00:00
.extra1 = &one,
},
{
.procname = "tcp_app_win",
.data = &sysctl_tcp_app_win,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_adv_win_scale",
.data = &sysctl_tcp_adv_win_scale,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &tcp_adv_win_scale_min,
.extra2 = &tcp_adv_win_scale_max,
},
{
.procname = "tcp_frto",
.data = &sysctl_tcp_frto,
.maxlen = sizeof(int),
tcp: track min RTT using windowed min-filter Kathleen Nichols' algorithm for tracking the minimum RTT of a data stream over some measurement window. It uses constant space and constant time per update. Yet it almost always delivers the same minimum as an implementation that has to keep all the data in the window. The measurement window is tunable via sysctl.net.ipv4.tcp_min_rtt_wlen with a default value of 5 minutes. The algorithm keeps track of the best, 2nd best & 3rd best min values, maintaining an invariant that the measurement time of the n'th best >= n-1'th best. It also makes sure that the three values are widely separated in the time window since that bounds the worse case error when that data is monotonically increasing over the window. Upon getting a new min, we can forget everything earlier because it has no value - the new min is less than everything else in the window by definition and it's the most recent. So we restart fresh on every new min and overwrites the 2nd & 3rd choices. The same property holds for the 2nd & 3rd best. Therefore we have to maintain two invariants to maximize the information in the samples, one on values (1st.v <= 2nd.v <= 3rd.v) and the other on times (now-win <=1st.t <= 2nd.t <= 3rd.t <= now). These invariants determine the structure of the code The RTT input to the windowed filter is the minimum RTT measured from ACK or SACK, or as the last resort from TCP timestamps. The accessor tcp_min_rtt() returns the minimum RTT seen in the window. ~0U indicates it is not available. The minimum is 1usec even if the true RTT is below that. Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-17 04:57:42 +00:00
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_min_rtt_wlen",
.data = &sysctl_tcp_min_rtt_wlen,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_low_latency",
.data = &sysctl_tcp_low_latency,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_no_metrics_save",
.data = &sysctl_tcp_nometrics_save,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_moderate_rcvbuf",
.data = &sysctl_tcp_moderate_rcvbuf,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_tso_win_divisor",
.data = &sysctl_tcp_tso_win_divisor,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_congestion_control",
.mode = 0644,
.maxlen = TCP_CA_NAME_MAX,
.proc_handler = proc_tcp_congestion_control,
},
{
.procname = "tcp_workaround_signed_windows",
.data = &sysctl_tcp_workaround_signed_windows,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Tom Herbert <therbert@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 05:50:31 +00:00
{
.procname = "tcp_limit_output_bytes",
.data = &sysctl_tcp_limit_output_bytes,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_challenge_ack_limit",
.data = &sysctl_tcp_challenge_ack_limit,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_slow_start_after_idle",
.data = &sysctl_tcp_slow_start_after_idle,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#ifdef CONFIG_NETLABEL
{
.procname = "cipso_cache_enable",
.data = &cipso_v4_cache_enabled,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "cipso_cache_bucket_size",
.data = &cipso_v4_cache_bucketsize,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "cipso_rbm_optfmt",
.data = &cipso_v4_rbm_optfmt,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "cipso_rbm_strictvalid",
.data = &cipso_v4_rbm_strictvalid,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif /* CONFIG_NETLABEL */
{
.procname = "tcp_available_congestion_control",
.maxlen = TCP_CA_BUF_MAX,
.mode = 0444,
.proc_handler = proc_tcp_available_congestion_control,
},
{
.procname = "tcp_allowed_congestion_control",
.maxlen = TCP_CA_BUF_MAX,
.mode = 0644,
.proc_handler = proc_allowed_congestion_control,
},
{
.procname = "tcp_thin_linear_timeouts",
.data = &sysctl_tcp_thin_linear_timeouts,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
tcp: early retransmit This patch implements RFC 5827 early retransmit (ER) for TCP. It reduces DUPACK threshold (dupthresh) if outstanding packets are less than 4 to recover losses by fast recovery instead of timeout. While the algorithm is simple, small but frequent network reordering makes this feature dangerous: the connection repeatedly enter false recovery and degrade performance. Therefore we implement a mitigation suggested in the appendix of the RFC that delays entering fast recovery by a small interval, i.e., RTT/4. Currently ER is conservative and is disabled for the rest of the connection after the first reordering event. A large scale web server experiment on the performance impact of ER is summarized in section 6 of the paper "Proportional Rate Reduction for TCP”, IMC 2011. http://conferences.sigcomm.org/imc/2011/docs/p155.pdf Note that Linux has a similar feature called THIN_DUPACK. The differences are THIN_DUPACK do not mitigate reorderings and is only used after slow start. Currently ER is disabled if THIN_DUPACK is enabled. I would be happy to merge THIN_DUPACK feature with ER if people think it's a good idea. ER is enabled by sysctl_tcp_early_retrans: 0: Disables ER 1: Reduce dupthresh to packets_out - 1 when outstanding packets < 4. 2: (Default) reduce dupthresh like mode 1. In addition, delay entering fast recovery by RTT/4. Note: mode 2 is implemented in the third part of this patch series. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-02 13:30:03 +00:00
{
.procname = "tcp_early_retrans",
.data = &sysctl_tcp_early_retrans,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-11 10:00:43 +00:00
.extra2 = &four,
tcp: early retransmit This patch implements RFC 5827 early retransmit (ER) for TCP. It reduces DUPACK threshold (dupthresh) if outstanding packets are less than 4 to recover losses by fast recovery instead of timeout. While the algorithm is simple, small but frequent network reordering makes this feature dangerous: the connection repeatedly enter false recovery and degrade performance. Therefore we implement a mitigation suggested in the appendix of the RFC that delays entering fast recovery by a small interval, i.e., RTT/4. Currently ER is conservative and is disabled for the rest of the connection after the first reordering event. A large scale web server experiment on the performance impact of ER is summarized in section 6 of the paper "Proportional Rate Reduction for TCP”, IMC 2011. http://conferences.sigcomm.org/imc/2011/docs/p155.pdf Note that Linux has a similar feature called THIN_DUPACK. The differences are THIN_DUPACK do not mitigate reorderings and is only used after slow start. Currently ER is disabled if THIN_DUPACK is enabled. I would be happy to merge THIN_DUPACK feature with ER if people think it's a good idea. ER is enabled by sysctl_tcp_early_retrans: 0: Disables ER 1: Reduce dupthresh to packets_out - 1 when outstanding packets < 4. 2: (Default) reduce dupthresh like mode 1. In addition, delay entering fast recovery by RTT/4. Note: mode 2 is implemented in the third part of this patch series. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-02 13:30:03 +00:00
},
tcp: TSO packets automatic sizing After hearing many people over past years complaining against TSO being bursty or even buggy, we are proud to present automatic sizing of TSO packets. One part of the problem is that tcp_tso_should_defer() uses an heuristic relying on upcoming ACKS instead of a timer, but more generally, having big TSO packets makes little sense for low rates, as it tends to create micro bursts on the network, and general consensus is to reduce the buffering amount. This patch introduces a per socket sk_pacing_rate, that approximates the current sending rate, and allows us to size the TSO packets so that we try to send one packet every ms. This field could be set by other transports. Patch has no impact for high speed flows, where having large TSO packets makes sense to reach line rate. For other flows, this helps better packet scheduling and ACK clocking. This patch increases performance of TCP flows in lossy environments. A new sysctl (tcp_min_tso_segs) is added, to specify the minimal size of a TSO packet (default being 2). A follow-up patch will provide a new packet scheduler (FQ), using sk_pacing_rate as an input to perform optional per flow pacing. This explains why we chose to set sk_pacing_rate to twice the current rate, allowing 'slow start' ramp up. sk_pacing_rate = 2 * cwnd * mss / srtt v2: Neal Cardwell reported a suspect deferring of last two segments on initial write of 10 MSS, I had to change tcp_tso_should_defer() to take into account tp->xmit_size_goal_segs Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Van Jacobson <vanj@google.com> Cc: Tom Herbert <therbert@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-27 12:46:32 +00:00
{
.procname = "tcp_min_tso_segs",
.data = &sysctl_tcp_min_tso_segs,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
tcp: TSO packets automatic sizing After hearing many people over past years complaining against TSO being bursty or even buggy, we are proud to present automatic sizing of TSO packets. One part of the problem is that tcp_tso_should_defer() uses an heuristic relying on upcoming ACKS instead of a timer, but more generally, having big TSO packets makes little sense for low rates, as it tends to create micro bursts on the network, and general consensus is to reduce the buffering amount. This patch introduces a per socket sk_pacing_rate, that approximates the current sending rate, and allows us to size the TSO packets so that we try to send one packet every ms. This field could be set by other transports. Patch has no impact for high speed flows, where having large TSO packets makes sense to reach line rate. For other flows, this helps better packet scheduling and ACK clocking. This patch increases performance of TCP flows in lossy environments. A new sysctl (tcp_min_tso_segs) is added, to specify the minimal size of a TSO packet (default being 2). A follow-up patch will provide a new packet scheduler (FQ), using sk_pacing_rate as an input to perform optional per flow pacing. This explains why we chose to set sk_pacing_rate to twice the current rate, allowing 'slow start' ramp up. sk_pacing_rate = 2 * cwnd * mss / srtt v2: Neal Cardwell reported a suspect deferring of last two segments on initial write of 10 MSS, I had to change tcp_tso_should_defer() to take into account tp->xmit_size_goal_segs Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Van Jacobson <vanj@google.com> Cc: Tom Herbert <therbert@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-27 12:46:32 +00:00
.extra2 = &gso_max_segs,
},
{
.procname = "tcp_pacing_ss_ratio",
.data = &sysctl_tcp_pacing_ss_ratio,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &thousand,
},
{
.procname = "tcp_pacing_ca_ratio",
.data = &sysctl_tcp_pacing_ca_ratio,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &thousand,
},
tcp: auto corking With the introduction of TCP Small Queues, TSO auto sizing, and TCP pacing, we can implement Automatic Corking in the kernel, to help applications doing small write()/sendmsg() to TCP sockets. Idea is to change tcp_push() to check if the current skb payload is under skb optimal size (a multiple of MSS bytes) If under 'size_goal', and at least one packet is still in Qdisc or NIC TX queues, set the TCP Small Queue Throttled bit, so that the push will be delayed up to TX completion time. This delay might allow the application to coalesce more bytes in the skb in following write()/sendmsg()/sendfile() system calls. The exact duration of the delay is depending on the dynamics of the system, and might be zero if no packet for this flow is actually held in Qdisc or NIC TX ring. Using FQ/pacing is a way to increase the probability of autocorking being triggered. Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control this feature and default it to 1 (enabled) Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking This counter is incremented every time we detected skb was under used and its flush was deferred. Tested: Interesting effects when using line buffered commands under ssh. Excellent performance results in term of cpu usage and total throughput. lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128 9410.39 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128': 35209.439626 task-clock # 2.901 CPUs utilized 2,294 context-switches # 0.065 K/sec 101 CPU-migrations # 0.003 K/sec 4,079 page-faults # 0.116 K/sec 97,923,241,298 cycles # 2.781 GHz [83.31%] 51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%] 25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%] 102,225,978,536 instructions # 1.04 insns per cycle # 0.51 stalled cycles per insn [83.38%] 18,657,696,819 branches # 529.906 M/sec [83.29%] 91,679,646 branch-misses # 0.49% of all branches [83.40%] 12.136204899 seconds time elapsed lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128 6624.89 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128': 40045.864494 task-clock # 3.301 CPUs utilized 171 context-switches # 0.004 K/sec 53 CPU-migrations # 0.001 K/sec 4,080 page-faults # 0.102 K/sec 111,340,458,645 cycles # 2.780 GHz [83.34%] 61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%] 29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%] 108,654,349,355 instructions # 0.98 insns per cycle # 0.57 stalled cycles per insn [83.34%] 19,552,170,748 branches # 488.244 M/sec [83.34%] 157,875,417 branch-misses # 0.81% of all branches [83.34%] 12.130267788 seconds time elapsed Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-06 06:36:05 +00:00
{
.procname = "tcp_autocorking",
.data = &sysctl_tcp_autocorking,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
tcp: helpers to mitigate ACK loops by rate-limiting out-of-window dupacks Helpers for mitigating ACK loops by rate-limiting dupacks sent in response to incoming out-of-window packets. This patch includes: - rate-limiting logic - sysctl to control how often we allow dupacks to out-of-window packets - SNMP counter for cases where we rate-limited our dupack sending The rate-limiting logic in this patch decides to not send dupacks in response to out-of-window segments if (a) they are SYNs or pure ACKs and (b) the remote endpoint is sending them faster than the configured rate limit. We rate-limit our responses rather than blocking them entirely or resetting the connection, because legitimate connections can rely on dupacks in response to some out-of-window segments. For example, zero window probes are typically sent with a sequence number that is below the current window, and ZWPs thus expect to thus elicit a dupack in response. We allow dupacks in response to TCP segments with data, because these may be spurious retransmissions for which the remote endpoint wants to receive DSACKs. This is safe because segments with data can't realistically be part of ACK loops, which by their nature consist of each side sending pure/data-less ACKs to each other. The dupack interval is controlled by a new sysctl knob, tcp_invalid_ratelimit, given in milliseconds, in case an administrator needs to dial this upward in the face of a high-rate DoS attack. The name and units are chosen to be analogous to the existing analogous knob for ICMP, icmp_ratelimit. The default value for tcp_invalid_ratelimit is 500ms, which allows at most one such dupack per 500ms. This is chosen to be 2x faster than the 1-second minimum RTO interval allowed by RFC 6298 (section 2, rule 2.4). We allow the extra 2x factor because network delay variations can cause packets sent at 1 second intervals to be compressed and arrive much closer. Reported-by: Avery Fay <avery@mixpanel.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-02-06 21:04:38 +00:00
{
.procname = "tcp_invalid_ratelimit",
.data = &sysctl_tcp_invalid_ratelimit,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
{
.procname = "tcp_available_ulp",
.maxlen = TCP_ULP_BUF_MAX,
.mode = 0444,
.proc_handler = proc_tcp_available_ulp,
},
{
.procname = "icmp_msgs_per_sec",
.data = &sysctl_icmp_msgs_per_sec,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
{
.procname = "icmp_msgs_burst",
.data = &sysctl_icmp_msgs_burst,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
{
.procname = "udp_mem",
.data = &sysctl_udp_mem,
.maxlen = sizeof(sysctl_udp_mem),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "udp_rmem_min",
.data = &sysctl_udp_rmem_min,
.maxlen = sizeof(sysctl_udp_rmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
Revert "net: limit tcp/udp rmem/wmem to SOCK_{RCV,SND}BUF_MIN" Commit 8133534c760d4083 ("net: limit tcp/udp rmem/wmem to SOCK_{RCV,SND}BUF_MIN") modified four sysctls to enforce that the values written to them are not less than SOCK_MIN_{RCV,SND}BUF. That change causes 4096 to no longer be accepted as a valid value for 'min' in tcp_wmem and udp_wmem_min. 4096 has been the default for both of those sysctls for a long time, and unfortunately seems to be an extremely popular setting. This change breaks a large number of sysctl configurations at Facebook. That commit referred to b1cb59cf2efe7971 ("net: sysctl_net_core: check SNDBUF and RCVBUF for min length"), which choose to use the SOCK_MIN constants as the lower limits to avoid nasty bugs. But AFAICS, a limit of SOCK_MIN_SNDBUF isn't necessary to do that: the BUG_ON cited in the commit message seems to have happened because unix_stream_sendmsg() expects a minimum of a full page (ie SK_MEM_QUANTUM) and the math broke, not because it had less than SOCK_MIN_SNDBUF allocated. This particular issue doesn't seem to affect TCP however: using a setting of "1 1 1" for tcp_{r,w}mem works, although it's obviously suboptimal. SK_MEM_QUANTUM would be a nice minimum, but it's 64K on some archs, so there would still be breakage. Since a value of one doesn't seem to cause any problems, we can drop the minimum 8133534c added to fix this. This reverts commit 8133534c760d4083f79d2cde42c636ccc0b2792e. Fixes: 8133534c760d4083 ("net: limit tcp/udp rmem/wmem to SOCK_MIN...") Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Sorin Dumitru <sorin@returnze.ro> Signed-off-by: Calvin Owens <calvinowens@fb.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-13 21:21:34 +00:00
.extra1 = &one
},
{
.procname = "udp_wmem_min",
.data = &sysctl_udp_wmem_min,
.maxlen = sizeof(sysctl_udp_wmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
Revert "net: limit tcp/udp rmem/wmem to SOCK_{RCV,SND}BUF_MIN" Commit 8133534c760d4083 ("net: limit tcp/udp rmem/wmem to SOCK_{RCV,SND}BUF_MIN") modified four sysctls to enforce that the values written to them are not less than SOCK_MIN_{RCV,SND}BUF. That change causes 4096 to no longer be accepted as a valid value for 'min' in tcp_wmem and udp_wmem_min. 4096 has been the default for both of those sysctls for a long time, and unfortunately seems to be an extremely popular setting. This change breaks a large number of sysctl configurations at Facebook. That commit referred to b1cb59cf2efe7971 ("net: sysctl_net_core: check SNDBUF and RCVBUF for min length"), which choose to use the SOCK_MIN constants as the lower limits to avoid nasty bugs. But AFAICS, a limit of SOCK_MIN_SNDBUF isn't necessary to do that: the BUG_ON cited in the commit message seems to have happened because unix_stream_sendmsg() expects a minimum of a full page (ie SK_MEM_QUANTUM) and the math broke, not because it had less than SOCK_MIN_SNDBUF allocated. This particular issue doesn't seem to affect TCP however: using a setting of "1 1 1" for tcp_{r,w}mem works, although it's obviously suboptimal. SK_MEM_QUANTUM would be a nice minimum, but it's 64K on some archs, so there would still be breakage. Since a value of one doesn't seem to cause any problems, we can drop the minimum 8133534c added to fix this. This reverts commit 8133534c760d4083f79d2cde42c636ccc0b2792e. Fixes: 8133534c760d4083 ("net: limit tcp/udp rmem/wmem to SOCK_MIN...") Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Sorin Dumitru <sorin@returnze.ro> Signed-off-by: Calvin Owens <calvinowens@fb.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-13 21:21:34 +00:00
.extra1 = &one
},
{ }
};
static struct ctl_table ipv4_net_table[] = {
{
.procname = "icmp_echo_ignore_all",
.data = &init_net.ipv4.sysctl_icmp_echo_ignore_all,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "icmp_echo_ignore_broadcasts",
.data = &init_net.ipv4.sysctl_icmp_echo_ignore_broadcasts,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "icmp_ignore_bogus_error_responses",
.data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "icmp_errors_use_inbound_ifaddr",
.data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "icmp_ratelimit",
.data = &init_net.ipv4.sysctl_icmp_ratelimit,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
{
.procname = "icmp_ratemask",
.data = &init_net.ipv4.sysctl_icmp_ratemask,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
{
.procname = "ping_group_range",
.data = &init_net.ipv4.ping_group_range.range,
.maxlen = sizeof(gid_t)*2,
net: ipv4: add IPPROTO_ICMP socket kind This patch adds IPPROTO_ICMP socket kind. It makes it possible to send ICMP_ECHO messages and receive the corresponding ICMP_ECHOREPLY messages without any special privileges. In other words, the patch makes it possible to implement setuid-less and CAP_NET_RAW-less /bin/ping. In order not to increase the kernel's attack surface, the new functionality is disabled by default, but is enabled at bootup by supporting Linux distributions, optionally with restriction to a group or a group range (see below). Similar functionality is implemented in Mac OS X: http://www.manpagez.com/man/4/icmp/ A new ping socket is created with socket(PF_INET, SOCK_DGRAM, PROT_ICMP) Message identifiers (octets 4-5 of ICMP header) are interpreted as local ports. Addresses are stored in struct sockaddr_in. No port numbers are reserved for privileged processes, port 0 is reserved for API ("let the kernel pick a free number"). There is no notion of remote ports, remote port numbers provided by the user (e.g. in connect()) are ignored. Data sent and received include ICMP headers. This is deliberate to: 1) Avoid the need to transport headers values like sequence numbers by other means. 2) Make it easier to port existing programs using raw sockets. ICMP headers given to send() are checked and sanitized. The type must be ICMP_ECHO and the code must be zero (future extensions might relax this, see below). The id is set to the number (local port) of the socket, the checksum is always recomputed. ICMP reply packets received from the network are demultiplexed according to their id's, and are returned by recv() without any modifications. IP header information and ICMP errors of those packets may be obtained via ancillary data (IP_RECVTTL, IP_RETOPTS, and IP_RECVERR). ICMP source quenches and redirects are reported as fake errors via the error queue (IP_RECVERR); the next hop address for redirects is saved to ee_info (in network order). socket(2) is restricted to the group range specified in "/proc/sys/net/ipv4/ping_group_range". It is "1 0" by default, meaning that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions to the single group (to either make /sbin/ping g+s and owned by this group or to grant permissions to the "netadmins" group), "0 4294967295" would enable it for the world, "100 4294967295" would enable it for the users, but not daemons. The existing code might be (in the unlikely case anyone needs it) extended rather easily to handle other similar pairs of ICMP messages (Timestamp/Reply, Information Request/Reply, Address Mask Request/Reply etc.). Userspace ping util & patch for it: http://openwall.info/wiki/people/segoon/ping For Openwall GNU/*/Linux it was the last step on the road to the setuid-less distro. A revision of this patch (for RHEL5/OpenVZ kernels) is in use in Owl-current, such as in the 2011/03/12 LiveCD ISOs: http://mirrors.kernel.org/openwall/Owl/current/iso/ Initially this functionality was written by Pavel Kankovsky for Linux 2.4.32, but unfortunately it was never made public. All ping options (-b, -p, -Q, -R, -s, -t, -T, -M, -I), are tested with the patch. PATCH v3: - switched to flowi4. - minor changes to be consistent with raw sockets code. PATCH v2: - changed ping_debug() to pr_debug(). - removed CONFIG_IP_PING. - removed ping_seq_fops.owner field (unused for procfs). - switched to proc_net_fops_create(). - switched to %pK in seq_printf(). PATCH v1: - fixed checksumming bug. - CAP_NET_RAW may not create icmp sockets anymore. RFC v2: - minor cleanups. - introduced sysctl'able group range to restrict socket(2). Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-13 10:01:00 +00:00
.mode = 0644,
.proc_handler = ipv4_ping_group_range,
},
{
.procname = "tcp_ecn",
.data = &init_net.ipv4.sysctl_tcp_ecn,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
tcp: add rfc3168, section 6.1.1.1. fallback This work as a follow-up of commit f7b3bec6f516 ("net: allow setting ecn via routing table") and adds RFC3168 section 6.1.1.1. fallback for outgoing ECN connections. In other words, this work adds a retry with a non-ECN setup SYN packet, as suggested from the RFC on the first timeout: [...] A host that receives no reply to an ECN-setup SYN within the normal SYN retransmission timeout interval MAY resend the SYN and any subsequent SYN retransmissions with CWR and ECE cleared. [...] Schematic client-side view when assuming the server is in tcp_ecn=2 mode, that is, Linux default since 2009 via commit 255cac91c3c9 ("tcp: extend ECN sysctl to allow server-side only ECN"): 1) Normal ECN-capable path: SYN ECE CWR -----> <----- SYN ACK ECE ACK -----> 2) Path with broken middlebox, when client has fallback: SYN ECE CWR ----X crappy middlebox drops packet (timeout, rtx) SYN -----> <----- SYN ACK ACK -----> In case we would not have the fallback implemented, the middlebox drop point would basically end up as: SYN ECE CWR ----X crappy middlebox drops packet (timeout, rtx) SYN ECE CWR ----X crappy middlebox drops packet (timeout, rtx) SYN ECE CWR ----X crappy middlebox drops packet (timeout, rtx) In any case, it's rather a smaller percentage of sites where there would occur such additional setup latency: it was found in end of 2014 that ~56% of IPv4 and 65% of IPv6 servers of Alexa 1 million list would negotiate ECN (aka tcp_ecn=2 default), 0.42% of these webservers will fail to connect when trying to negotiate with ECN (tcp_ecn=1) due to timeouts, which the fallback would mitigate with a slight latency trade-off. Recent related paper on this topic: Brian Trammell, Mirja Kühlewind, Damiano Boppart, Iain Learmonth, Gorry Fairhurst, and Richard Scheffenegger: "Enabling Internet-Wide Deployment of Explicit Congestion Notification." Proc. PAM 2015, New York. http://ecn.ethz.ch/ecn-pam15.pdf Thus, when net.ipv4.tcp_ecn=1 is being set, the patch will perform RFC3168, section 6.1.1.1. fallback on timeout. For users explicitly not wanting this which can be in DC use case, we add a net.ipv4.tcp_ecn_fallback knob that allows for disabling the fallback. tp->ecn_flags are not being cleared in tcp_ecn_clear_syn() on output, but rather we let tcp_ecn_rcv_synack() take that over on input path in case a SYN ACK ECE was delayed. Thus a spurious SYN retransmission will not prevent ECN being negotiated eventually in that case. Reference: https://www.ietf.org/proceedings/92/slides/slides-92-iccrg-1.pdf Reference: https://www.ietf.org/proceedings/89/slides/slides-89-tsvarea-1.pdf Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Mirja Kühlewind <mirja.kuehlewind@tik.ee.ethz.ch> Signed-off-by: Brian Trammell <trammell@tik.ee.ethz.ch> Cc: Eric Dumazet <edumazet@google.com> Cc: Dave That <dave.taht@gmail.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-19 19:04:22 +00:00
{
.procname = "tcp_ecn_fallback",
.data = &init_net.ipv4.sysctl_tcp_ecn_fallback,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip_dynaddr",
.data = &init_net.ipv4.sysctl_ip_dynaddr,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip_early_demux",
.data = &init_net.ipv4.sysctl_ip_early_demux,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "udp_early_demux",
.data = &init_net.ipv4.sysctl_udp_early_demux,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_udp_early_demux
},
{
.procname = "tcp_early_demux",
.data = &init_net.ipv4.sysctl_tcp_early_demux,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_tcp_early_demux
},
{
.procname = "ip_default_ttl",
.data = &init_net.ipv4.sysctl_ip_default_ttl,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &ip_ttl_min,
.extra2 = &ip_ttl_max,
},
{
.procname = "ip_local_port_range",
.maxlen = sizeof(init_net.ipv4.ip_local_ports.range),
.data = &init_net.ipv4.ip_local_ports.range,
.mode = 0644,
.proc_handler = ipv4_local_port_range,
},
{
.procname = "ip_local_reserved_ports",
.data = &init_net.ipv4.sysctl_local_reserved_ports,
.maxlen = 65536,
.mode = 0644,
.proc_handler = proc_do_large_bitmap,
},
{
.procname = "ip_no_pmtu_disc",
.data = &init_net.ipv4.sysctl_ip_no_pmtu_disc,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 09:01:15 +00:00
{
.procname = "ip_forward_use_pmtu",
.data = &init_net.ipv4.sysctl_ip_fwd_use_pmtu,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "ip_nonlocal_bind",
.data = &init_net.ipv4.sysctl_ip_nonlocal_bind,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "fwmark_reflect",
.data = &init_net.ipv4.sysctl_fwmark_reflect,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_fwmark_accept",
.data = &init_net.ipv4.sysctl_tcp_fwmark_accept,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_NET_L3_MASTER_DEV
{
.procname = "tcp_l3mdev_accept",
.data = &init_net.ipv4.sysctl_tcp_l3mdev_accept,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
#endif
{
.procname = "tcp_mtu_probing",
.data = &init_net.ipv4.sysctl_tcp_mtu_probing,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_base_mss",
.data = &init_net.ipv4.sysctl_tcp_base_mss,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_probe_threshold",
.data = &init_net.ipv4.sysctl_tcp_probe_threshold,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_probe_interval",
.data = &init_net.ipv4.sysctl_tcp_probe_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
IGMP: Inhibit reports for local multicast groups The range of addresses between 224.0.0.0 and 224.0.0.255 inclusive, is reserved for the use of routing protocols and other low-level topology discovery or maintenance protocols, such as gateway discovery and group membership reporting. Multicast routers should not forward any multicast datagram with destination addresses in this range, regardless of its TTL. Currently, IGMP reports are generated for this reserved range of addresses even though a router will ignore this information since it has no purpose. However, the presence of reserved group addresses in an IGMP membership report uses up network bandwidth and can also obscure addresses of interest when inspecting membership reports using packet inspection or debug messages. Although the RFCs for the various version of IGMP (e.g.RFC 3376 for v3) do not specify that the reserved addresses be excluded from membership reports, it should do no harm in doing so. In particular there should be no adverse effect in any IGMP snooping functionality since 224.0.0.x is specifically excluded as per RFC 4541 (IGMP and MLD Snooping Switches Considerations) section 2.1.2. Data Forwarding Rules: 2) Packets with a destination IP (DIP) address in the 224.0.0.X range which are not IGMP must be forwarded on all ports. IGMP reports for local multicast groups can now be optionally inhibited by means of a system control variable (by setting the value to zero) e.g.: echo 0 > /proc/sys/net/ipv4/igmp_link_local_mcast_reports To retain backwards compatibility the previous behaviour is retained by default on system boot or reverted by setting the value back to non-zero e.g.: echo 1 > /proc/sys/net/ipv4/igmp_link_local_mcast_reports Signed-off-by: Philip Downey <pdowney@brocade.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 15:46:26 +00:00
{
.procname = "igmp_link_local_mcast_reports",
.data = &init_net.ipv4.sysctl_igmp_llm_reports,
IGMP: Inhibit reports for local multicast groups The range of addresses between 224.0.0.0 and 224.0.0.255 inclusive, is reserved for the use of routing protocols and other low-level topology discovery or maintenance protocols, such as gateway discovery and group membership reporting. Multicast routers should not forward any multicast datagram with destination addresses in this range, regardless of its TTL. Currently, IGMP reports are generated for this reserved range of addresses even though a router will ignore this information since it has no purpose. However, the presence of reserved group addresses in an IGMP membership report uses up network bandwidth and can also obscure addresses of interest when inspecting membership reports using packet inspection or debug messages. Although the RFCs for the various version of IGMP (e.g.RFC 3376 for v3) do not specify that the reserved addresses be excluded from membership reports, it should do no harm in doing so. In particular there should be no adverse effect in any IGMP snooping functionality since 224.0.0.x is specifically excluded as per RFC 4541 (IGMP and MLD Snooping Switches Considerations) section 2.1.2. Data Forwarding Rules: 2) Packets with a destination IP (DIP) address in the 224.0.0.X range which are not IGMP must be forwarded on all ports. IGMP reports for local multicast groups can now be optionally inhibited by means of a system control variable (by setting the value to zero) e.g.: echo 0 > /proc/sys/net/ipv4/igmp_link_local_mcast_reports To retain backwards compatibility the previous behaviour is retained by default on system boot or reverted by setting the value back to non-zero e.g.: echo 1 > /proc/sys/net/ipv4/igmp_link_local_mcast_reports Signed-off-by: Philip Downey <pdowney@brocade.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 15:46:26 +00:00
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "igmp_max_memberships",
.data = &init_net.ipv4.sysctl_igmp_max_memberships,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "igmp_max_msf",
.data = &init_net.ipv4.sysctl_igmp_max_msf,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#ifdef CONFIG_IP_MULTICAST
{
.procname = "igmp_qrv",
.data = &init_net.ipv4.sysctl_igmp_qrv,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one
},
#endif
{
.procname = "tcp_keepalive_time",
.data = &init_net.ipv4.sysctl_tcp_keepalive_time,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "tcp_keepalive_probes",
.data = &init_net.ipv4.sysctl_tcp_keepalive_probes,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_keepalive_intvl",
.data = &init_net.ipv4.sysctl_tcp_keepalive_intvl,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "tcp_syn_retries",
.data = &init_net.ipv4.sysctl_tcp_syn_retries,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &tcp_syn_retries_min,
.extra2 = &tcp_syn_retries_max
},
{
.procname = "tcp_synack_retries",
.data = &init_net.ipv4.sysctl_tcp_synack_retries,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#ifdef CONFIG_SYN_COOKIES
{
.procname = "tcp_syncookies",
.data = &init_net.ipv4.sysctl_tcp_syncookies,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#endif
{
.procname = "tcp_reordering",
.data = &init_net.ipv4.sysctl_tcp_reordering,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_retries1",
.data = &init_net.ipv4.sysctl_tcp_retries1,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra2 = &tcp_retr1_max
},
{
.procname = "tcp_retries2",
.data = &init_net.ipv4.sysctl_tcp_retries2,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_orphan_retries",
.data = &init_net.ipv4.sysctl_tcp_orphan_retries,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_fin_timeout",
.data = &init_net.ipv4.sysctl_tcp_fin_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "tcp_notsent_lowat",
.data = &init_net.ipv4.sysctl_tcp_notsent_lowat,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_douintvec,
},
{
.procname = "tcp_tw_reuse",
.data = &init_net.ipv4.sysctl_tcp_tw_reuse,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_max_tw_buckets",
.data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_max_syn_backlog",
.data = &init_net.ipv4.sysctl_max_syn_backlog,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
net: ipv4: Consider failed nexthops in multipath routes Multipath route lookups should consider knowledge about next hops and not select a hop that is known to be failed. Example: [h2] [h3] 15.0.0.5 | | 3| 3| [SP1] [SP2]--+ 1 2 1 2 | | /-------------+ | | \ / | | X | | / \ | | / \---------------\ | 1 2 1 2 12.0.0.2 [TOR1] 3-----------------3 [TOR2] 12.0.0.3 4 4 \ / \ / \ / -------| |-----/ 1 2 [TOR3] 3| | [h1] 12.0.0.1 host h1 with IP 12.0.0.1 has 2 paths to host h3 at 15.0.0.5: root@h1:~# ip ro ls ... 12.0.0.0/24 dev swp1 proto kernel scope link src 12.0.0.1 15.0.0.0/16 nexthop via 12.0.0.2 dev swp1 weight 1 nexthop via 12.0.0.3 dev swp1 weight 1 ... If the link between tor3 and tor1 is down and the link between tor1 and tor2 then tor1 is effectively cut-off from h1. Yet the route lookups in h1 are alternating between the 2 routes: ping 15.0.0.5 gets one and ssh 15.0.0.5 gets the other. Connections that attempt to use the 12.0.0.2 nexthop fail since that neighbor is not reachable: root@h1:~# ip neigh show ... 12.0.0.3 dev swp1 lladdr 00:02:00:00:00:1b REACHABLE 12.0.0.2 dev swp1 FAILED ... The failed path can be avoided by considering known neighbor information when selecting next hops. If the neighbor lookup fails we have no knowledge about the nexthop, so give it a shot. If there is an entry then only select the nexthop if the state is sane. This is similar to what fib_detect_death does. To maintain backward compatibility use of the neighbor information is based on a new sysctl, fib_multipath_use_neigh. Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Reviewed-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-07 14:21:00 +00:00
#ifdef CONFIG_IP_ROUTE_MULTIPATH
{
.procname = "fib_multipath_use_neigh",
.data = &init_net.ipv4.sysctl_fib_multipath_use_neigh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
{
.procname = "fib_multipath_hash_policy",
.data = &init_net.ipv4.sysctl_fib_multipath_hash_policy,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
net: ipv4: Consider failed nexthops in multipath routes Multipath route lookups should consider knowledge about next hops and not select a hop that is known to be failed. Example: [h2] [h3] 15.0.0.5 | | 3| 3| [SP1] [SP2]--+ 1 2 1 2 | | /-------------+ | | \ / | | X | | / \ | | / \---------------\ | 1 2 1 2 12.0.0.2 [TOR1] 3-----------------3 [TOR2] 12.0.0.3 4 4 \ / \ / \ / -------| |-----/ 1 2 [TOR3] 3| | [h1] 12.0.0.1 host h1 with IP 12.0.0.1 has 2 paths to host h3 at 15.0.0.5: root@h1:~# ip ro ls ... 12.0.0.0/24 dev swp1 proto kernel scope link src 12.0.0.1 15.0.0.0/16 nexthop via 12.0.0.2 dev swp1 weight 1 nexthop via 12.0.0.3 dev swp1 weight 1 ... If the link between tor3 and tor1 is down and the link between tor1 and tor2 then tor1 is effectively cut-off from h1. Yet the route lookups in h1 are alternating between the 2 routes: ping 15.0.0.5 gets one and ssh 15.0.0.5 gets the other. Connections that attempt to use the 12.0.0.2 nexthop fail since that neighbor is not reachable: root@h1:~# ip neigh show ... 12.0.0.3 dev swp1 lladdr 00:02:00:00:00:1b REACHABLE 12.0.0.2 dev swp1 FAILED ... The failed path can be avoided by considering known neighbor information when selecting next hops. If the neighbor lookup fails we have no knowledge about the nexthop, so give it a shot. If there is an entry then only select the nexthop if the state is sane. This is similar to what fib_detect_death does. To maintain backward compatibility use of the neighbor information is based on a new sysctl, fib_multipath_use_neigh. Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Reviewed-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-07 14:21:00 +00:00
.extra1 = &zero,
.extra2 = &one,
},
#endif
{
.procname = "ip_unprivileged_port_start",
.maxlen = sizeof(int),
.data = &init_net.ipv4.sysctl_ip_prot_sock,
.mode = 0644,
.proc_handler = ipv4_privileged_ports,
},
#ifdef CONFIG_NET_L3_MASTER_DEV
{
.procname = "udp_l3mdev_accept",
.data = &init_net.ipv4.sysctl_udp_l3mdev_accept,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
#endif
{
.procname = "tcp_sack",
.data = &init_net.ipv4.sysctl_tcp_sack,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_window_scaling",
.data = &init_net.ipv4.sysctl_tcp_window_scaling,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_timestamps",
.data = &init_net.ipv4.sysctl_tcp_timestamps,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{ }
};
static __net_init int ipv4_sysctl_init_net(struct net *net)
{
struct ctl_table *table;
table = ipv4_net_table;
if (!net_eq(net, &init_net)) {
int i;
table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL);
if (!table)
goto err_alloc;
/* Update the variables to point into the current struct net */
for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++)
table[i].data += (void *)net - (void *)&init_net;
}
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
if (!net->ipv4.ipv4_hdr)
goto err_reg;
net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
if (!net->ipv4.sysctl_local_reserved_ports)
goto err_ports;
return 0;
err_ports:
unregister_net_sysctl_table(net->ipv4.ipv4_hdr);
err_reg:
if (!net_eq(net, &init_net))
kfree(table);
err_alloc:
return -ENOMEM;
}
static __net_exit void ipv4_sysctl_exit_net(struct net *net)
{
struct ctl_table *table;
kfree(net->ipv4.sysctl_local_reserved_ports);
table = net->ipv4.ipv4_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv4.ipv4_hdr);
kfree(table);
}
static __net_initdata struct pernet_operations ipv4_sysctl_ops = {
.init = ipv4_sysctl_init_net,
.exit = ipv4_sysctl_exit_net,
};
static __init int sysctl_ipv4_init(void)
{
struct ctl_table_header *hdr;
hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table);
if (!hdr)
return -ENOMEM;
if (register_pernet_subsys(&ipv4_sysctl_ops)) {
unregister_net_sysctl_table(hdr);
return -ENOMEM;
}
return 0;
}
__initcall(sysctl_ipv4_init);