2019-05-23 16:14:41 +07:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2008-01-11 21:57:09 +07:00
|
|
|
/* SCTP kernel implementation
|
2005-04-17 05:20:36 +07:00
|
|
|
* (C) Copyright IBM Corp. 2002, 2004
|
|
|
|
* Copyright (c) 2002 Intel Corp.
|
|
|
|
*
|
2008-01-11 21:57:09 +07:00
|
|
|
* This file is part of the SCTP kernel implementation
|
2005-04-17 05:20:36 +07:00
|
|
|
*
|
|
|
|
* Sysctl related interfaces for SCTP.
|
|
|
|
*
|
|
|
|
* Please send any bug reports or fixes you make to the
|
|
|
|
* email address(es):
|
2013-07-23 19:51:47 +07:00
|
|
|
* lksctp developers <linux-sctp@vger.kernel.org>
|
2005-04-17 05:20:36 +07:00
|
|
|
*
|
|
|
|
* Written or modified by:
|
|
|
|
* Mingqin Liu <liuming@us.ibm.com>
|
|
|
|
* Jon Grimm <jgrimm@us.ibm.com>
|
|
|
|
* Ardelle Fan <ardelle.fan@intel.com>
|
|
|
|
* Ryan Layer <rmlayer@us.ibm.com>
|
|
|
|
* Sridhar Samudrala <sri@us.ibm.com>
|
|
|
|
*/
|
|
|
|
|
net: sctp: fix permissions for rto_alpha and rto_beta knobs
Commit 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs
to jiffies conversions.") has silently changed permissions for
rto_alpha and rto_beta knobs from 0644 to 0444. The purpose of
this was to discourage users from tweaking rto_alpha and
rto_beta knobs in production environments since they are key
to correctly compute rtt/srtt.
RFC4960 under section 6.3.1. RTO Calculation says regarding
rto_alpha and rto_beta under rule C3 and C4:
[...]
C3) When a new RTT measurement R' is made, set
RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
and
SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
Note: The value of SRTT used in the update to RTTVAR
is its value before updating SRTT itself using the
second assignment. After the computation, update
RTO <- SRTT + 4 * RTTVAR.
C4) When data is in flight and when allowed by rule C5
below, a new RTT measurement MUST be made each round
trip. Furthermore, new RTT measurements SHOULD be
made no more than once per round trip for a given
destination transport address. There are two reasons
for this recommendation: First, it appears that
measuring more frequently often does not in practice
yield any significant benefit [ALLMAN99]; second,
if measurements are made more often, then the values
of RTO.Alpha and RTO.Beta in rule C3 above should be
adjusted so that SRTT and RTTVAR still adjust to
changes at roughly the same rate (in terms of how many
round trips it takes them to reflect new values) as
they would if making only one measurement per
round-trip and using RTO.Alpha and RTO.Beta as given
in rule C3. However, the exact nature of these
adjustments remains a research issue.
[...]
While it is discouraged to adjust rto_alpha and rto_beta
and not further specified how to adjust them, the RFC also
doesn't explicitly forbid it, but rather gives a RECOMMENDED
default value (rto_alpha=3, rto_beta=2). We have a couple
of users relying on the old permissions before they got
changed. That said, if someone really has the urge to adjust
them, we could allow it with a warning in the log.
Fixes: 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs to jiffies conversions.")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-15 05:59:14 +07:00
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
#include <net/sctp/structs.h>
|
2005-09-06 08:07:42 +07:00
|
|
|
#include <net/sctp/sctp.h>
|
2005-04-17 05:20:36 +07:00
|
|
|
#include <linux/sysctl.h>
|
|
|
|
|
2006-08-23 03:29:17 +07:00
|
|
|
static int timer_max = 86400000; /* ms in one day */
|
2009-05-13 05:03:20 +07:00
|
|
|
static int sack_timer_min = 1;
|
|
|
|
static int sack_timer_max = 500;
|
2017-08-05 18:59:53 +07:00
|
|
|
static int addr_scope_max = SCTP_SCOPE_POLICY_MAX;
|
2009-11-24 03:53:57 +07:00
|
|
|
static int rwnd_scale_max = 16;
|
net: sctp: fix permissions for rto_alpha and rto_beta knobs
Commit 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs
to jiffies conversions.") has silently changed permissions for
rto_alpha and rto_beta knobs from 0644 to 0444. The purpose of
this was to discourage users from tweaking rto_alpha and
rto_beta knobs in production environments since they are key
to correctly compute rtt/srtt.
RFC4960 under section 6.3.1. RTO Calculation says regarding
rto_alpha and rto_beta under rule C3 and C4:
[...]
C3) When a new RTT measurement R' is made, set
RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
and
SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
Note: The value of SRTT used in the update to RTTVAR
is its value before updating SRTT itself using the
second assignment. After the computation, update
RTO <- SRTT + 4 * RTTVAR.
C4) When data is in flight and when allowed by rule C5
below, a new RTT measurement MUST be made each round
trip. Furthermore, new RTT measurements SHOULD be
made no more than once per round trip for a given
destination transport address. There are two reasons
for this recommendation: First, it appears that
measuring more frequently often does not in practice
yield any significant benefit [ALLMAN99]; second,
if measurements are made more often, then the values
of RTO.Alpha and RTO.Beta in rule C3 above should be
adjusted so that SRTT and RTTVAR still adjust to
changes at roughly the same rate (in terms of how many
round trips it takes them to reflect new values) as
they would if making only one measurement per
round-trip and using RTO.Alpha and RTO.Beta as given
in rule C3. However, the exact nature of these
adjustments remains a research issue.
[...]
While it is discouraged to adjust rto_alpha and rto_beta
and not further specified how to adjust them, the RFC also
doesn't explicitly forbid it, but rather gives a RECOMMENDED
default value (rto_alpha=3, rto_beta=2). We have a couple
of users relying on the old permissions before they got
changed. That said, if someone really has the urge to adjust
them, we could allow it with a warning in the log.
Fixes: 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs to jiffies conversions.")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-15 05:59:14 +07:00
|
|
|
static int rto_alpha_min = 0;
|
|
|
|
static int rto_beta_min = 0;
|
|
|
|
static int rto_alpha_max = 1000;
|
|
|
|
static int rto_beta_max = 1000;
|
sctp: add pf_expose per netns and sock and asoc
As said in rfc7829, section 3, point 12:
The SCTP stack SHOULD expose the PF state of its destination
addresses to the ULP as well as provide the means to notify the
ULP of state transitions of its destination addresses from
active to PF, and vice versa. However, it is recommended that
an SCTP stack implementing SCTP-PF also allows for the ULP to be
kept ignorant of the PF state of its destinations and the
associated state transitions, thus allowing for retention of the
simpler state transition model of [RFC4960] in the ULP.
Not only does it allow to expose the PF state to ULP, but also
allow to ignore sctp-pf to ULP.
So this patch is to add pf_expose per netns, sock and asoc. And in
sctp_assoc_control_transport(), ulp_notify will be set to false if
asoc->expose is not 'enabled' in next patch.
It also allows a user to change pf_expose per netns by sysctl, and
pf_expose per sock and asoc will be initialized with it.
Note that pf_expose also works for SCTP_GET_PEER_ADDR_INFO sockopt,
to not allow a user to query the state of a sctp-pf peer address
when pf_expose is 'disabled', as said in section 7.3.
v1->v2:
- Fix a build warning noticed by Nathan Chancellor.
v2->v3:
- set pf_expose to UNUSED by default to keep compatible with old
applications.
v3->v4:
- add a new entry for pf_expose on ip-sysctl.txt, as Marcelo suggested.
- change this patch to 1/5, and move sctp_assoc_control_transport
change into 2/5, as Marcelo suggested.
- use SCTP_PF_EXPOSE_UNSET instead of SCTP_PF_EXPOSE_UNUSED, and
set SCTP_PF_EXPOSE_UNSET to 0 in enum, as Marcelo suggested.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-08 12:20:32 +07:00
|
|
|
static int pf_expose_max = SCTP_PF_EXPOSE_MAX;
|
2019-11-08 12:20:35 +07:00
|
|
|
static int ps_retrans_max = SCTP_PS_RETRANS_MAX;
|
net: sctp: fix permissions for rto_alpha and rto_beta knobs
Commit 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs
to jiffies conversions.") has silently changed permissions for
rto_alpha and rto_beta knobs from 0644 to 0444. The purpose of
this was to discourage users from tweaking rto_alpha and
rto_beta knobs in production environments since they are key
to correctly compute rtt/srtt.
RFC4960 under section 6.3.1. RTO Calculation says regarding
rto_alpha and rto_beta under rule C3 and C4:
[...]
C3) When a new RTT measurement R' is made, set
RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
and
SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
Note: The value of SRTT used in the update to RTTVAR
is its value before updating SRTT itself using the
second assignment. After the computation, update
RTO <- SRTT + 4 * RTTVAR.
C4) When data is in flight and when allowed by rule C5
below, a new RTT measurement MUST be made each round
trip. Furthermore, new RTT measurements SHOULD be
made no more than once per round trip for a given
destination transport address. There are two reasons
for this recommendation: First, it appears that
measuring more frequently often does not in practice
yield any significant benefit [ALLMAN99]; second,
if measurements are made more often, then the values
of RTO.Alpha and RTO.Beta in rule C3 above should be
adjusted so that SRTT and RTTVAR still adjust to
changes at roughly the same rate (in terms of how many
round trips it takes them to reflect new values) as
they would if making only one measurement per
round-trip and using RTO.Alpha and RTO.Beta as given
in rule C3. However, the exact nature of these
adjustments remains a research issue.
[...]
While it is discouraged to adjust rto_alpha and rto_beta
and not further specified how to adjust them, the RFC also
doesn't explicitly forbid it, but rather gives a RECOMMENDED
default value (rto_alpha=3, rto_beta=2). We have a couple
of users relying on the old permissions before they got
changed. That said, if someone really has the urge to adjust
them, we could allow it with a warning in the log.
Fixes: 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs to jiffies conversions.")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-15 05:59:14 +07:00
|
|
|
|
2011-12-16 19:44:15 +07:00
|
|
|
static unsigned long max_autoclose_min = 0;
|
|
|
|
static unsigned long max_autoclose_max =
|
|
|
|
(MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
|
|
|
|
? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2013-12-11 08:50:40 +07:00
|
|
|
static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
|
2012-10-24 16:20:03 +07:00
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos);
|
2013-12-11 08:50:39 +07:00
|
|
|
static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
|
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos);
|
|
|
|
static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
|
2012-10-24 16:20:03 +07:00
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos);
|
net: sctp: fix permissions for rto_alpha and rto_beta knobs
Commit 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs
to jiffies conversions.") has silently changed permissions for
rto_alpha and rto_beta knobs from 0644 to 0444. The purpose of
this was to discourage users from tweaking rto_alpha and
rto_beta knobs in production environments since they are key
to correctly compute rtt/srtt.
RFC4960 under section 6.3.1. RTO Calculation says regarding
rto_alpha and rto_beta under rule C3 and C4:
[...]
C3) When a new RTT measurement R' is made, set
RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
and
SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
Note: The value of SRTT used in the update to RTTVAR
is its value before updating SRTT itself using the
second assignment. After the computation, update
RTO <- SRTT + 4 * RTTVAR.
C4) When data is in flight and when allowed by rule C5
below, a new RTT measurement MUST be made each round
trip. Furthermore, new RTT measurements SHOULD be
made no more than once per round trip for a given
destination transport address. There are two reasons
for this recommendation: First, it appears that
measuring more frequently often does not in practice
yield any significant benefit [ALLMAN99]; second,
if measurements are made more often, then the values
of RTO.Alpha and RTO.Beta in rule C3 above should be
adjusted so that SRTT and RTTVAR still adjust to
changes at roughly the same rate (in terms of how many
round trips it takes them to reflect new values) as
they would if making only one measurement per
round-trip and using RTO.Alpha and RTO.Beta as given
in rule C3. However, the exact nature of these
adjustments remains a research issue.
[...]
While it is discouraged to adjust rto_alpha and rto_beta
and not further specified how to adjust them, the RFC also
doesn't explicitly forbid it, but rather gives a RECOMMENDED
default value (rto_alpha=3, rto_beta=2). We have a couple
of users relying on the old permissions before they got
changed. That said, if someone really has the urge to adjust
them, we could allow it with a warning in the log.
Fixes: 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs to jiffies conversions.")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-15 05:59:14 +07:00
|
|
|
static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
|
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos);
|
net: sctp: cache auth_enable per endpoint
Currently, it is possible to create an SCTP socket, then switch
auth_enable via sysctl setting to 1 and crash the system on connect:
Oops[#1]:
CPU: 0 PID: 0 Comm: swapper Not tainted 3.14.1-mipsgit-20140415 #1
task: ffffffff8056ce80 ti: ffffffff8055c000 task.ti: ffffffff8055c000
[...]
Call Trace:
[<ffffffff8043c4e8>] sctp_auth_asoc_set_default_hmac+0x68/0x80
[<ffffffff8042b300>] sctp_process_init+0x5e0/0x8a4
[<ffffffff8042188c>] sctp_sf_do_5_1B_init+0x234/0x34c
[<ffffffff804228c8>] sctp_do_sm+0xb4/0x1e8
[<ffffffff80425a08>] sctp_endpoint_bh_rcv+0x1c4/0x214
[<ffffffff8043af68>] sctp_rcv+0x588/0x630
[<ffffffff8043e8e8>] sctp6_rcv+0x10/0x24
[<ffffffff803acb50>] ip6_input+0x2c0/0x440
[<ffffffff8030fc00>] __netif_receive_skb_core+0x4a8/0x564
[<ffffffff80310650>] process_backlog+0xb4/0x18c
[<ffffffff80313cbc>] net_rx_action+0x12c/0x210
[<ffffffff80034254>] __do_softirq+0x17c/0x2ac
[<ffffffff800345e0>] irq_exit+0x54/0xb0
[<ffffffff800075a4>] ret_from_irq+0x0/0x4
[<ffffffff800090ec>] rm7k_wait_irqoff+0x24/0x48
[<ffffffff8005e388>] cpu_startup_entry+0xc0/0x148
[<ffffffff805a88b0>] start_kernel+0x37c/0x398
Code: dd0900b8 000330f8 0126302d <dcc60000> 50c0fff1 0047182a a48306a0
03e00008 00000000
---[ end trace b530b0551467f2fd ]---
Kernel panic - not syncing: Fatal exception in interrupt
What happens while auth_enable=0 in that case is, that
ep->auth_hmacs is initialized to NULL in sctp_auth_init_hmacs()
when endpoint is being created.
After that point, if an admin switches over to auth_enable=1,
the machine can crash due to NULL pointer dereference during
reception of an INIT chunk. When we enter sctp_process_init()
via sctp_sf_do_5_1B_init() in order to respond to an INIT chunk,
the INIT verification succeeds and while we walk and process
all INIT params via sctp_process_param() we find that
net->sctp.auth_enable is set, therefore do not fall through,
but invoke sctp_auth_asoc_set_default_hmac() instead, and thus,
dereference what we have set to NULL during endpoint
initialization phase.
The fix is to make auth_enable immutable by caching its value
during endpoint initialization, so that its original value is
being carried along until destruction. The bug seems to originate
from the very first days.
Fix in joint work with Daniel Borkmann.
Reported-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-17 22:26:50 +07:00
|
|
|
static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
|
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos);
|
2013-12-11 08:50:39 +07:00
|
|
|
|
2013-06-12 13:04:25 +07:00
|
|
|
static struct ctl_table sctp_table[] = {
|
2012-08-07 14:29:57 +07:00
|
|
|
{
|
|
|
|
.procname = "sctp_mem",
|
|
|
|
.data = &sysctl_sctp_mem,
|
|
|
|
.maxlen = sizeof(sysctl_sctp_mem),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_doulongvec_minmax
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.procname = "sctp_rmem",
|
|
|
|
.data = &sysctl_sctp_rmem,
|
|
|
|
.maxlen = sizeof(sysctl_sctp_rmem),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec,
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.procname = "sctp_wmem",
|
|
|
|
.data = &sysctl_sctp_wmem,
|
|
|
|
.maxlen = sizeof(sysctl_sctp_wmem),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec,
|
|
|
|
},
|
|
|
|
|
|
|
|
{ /* sentinel */ }
|
|
|
|
};
|
|
|
|
|
2013-06-12 13:04:25 +07:00
|
|
|
static struct ctl_table sctp_net_table[] = {
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
.procname = "rto_initial",
|
2012-08-07 14:29:57 +07:00
|
|
|
.data = &init_net.sctp.rto_initial,
|
2006-08-23 03:29:17 +07:00
|
|
|
.maxlen = sizeof(unsigned int),
|
2005-04-17 05:20:36 +07:00
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ONE,
|
2006-08-23 03:29:17 +07:00
|
|
|
.extra2 = &timer_max
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
|
|
|
{
|
|
|
|
.procname = "rto_min",
|
2012-08-07 14:29:57 +07:00
|
|
|
.data = &init_net.sctp.rto_min,
|
2006-08-23 03:29:17 +07:00
|
|
|
.maxlen = sizeof(unsigned int),
|
2005-04-17 05:20:36 +07:00
|
|
|
.mode = 0644,
|
2013-12-11 08:50:39 +07:00
|
|
|
.proc_handler = proc_sctp_do_rto_min,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ONE,
|
2013-12-11 08:50:39 +07:00
|
|
|
.extra2 = &init_net.sctp.rto_max
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
|
|
|
{
|
|
|
|
.procname = "rto_max",
|
2012-08-07 14:29:57 +07:00
|
|
|
.data = &init_net.sctp.rto_max,
|
2006-08-23 03:29:17 +07:00
|
|
|
.maxlen = sizeof(unsigned int),
|
2005-04-17 05:20:36 +07:00
|
|
|
.mode = 0644,
|
2013-12-11 08:50:39 +07:00
|
|
|
.proc_handler = proc_sctp_do_rto_max,
|
|
|
|
.extra1 = &init_net.sctp.rto_min,
|
2006-08-23 03:29:17 +07:00
|
|
|
.extra2 = &timer_max
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "rto_alpha_exp_divisor",
|
|
|
|
.data = &init_net.sctp.rto_alpha,
|
|
|
|
.maxlen = sizeof(int),
|
net: sctp: fix permissions for rto_alpha and rto_beta knobs
Commit 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs
to jiffies conversions.") has silently changed permissions for
rto_alpha and rto_beta knobs from 0644 to 0444. The purpose of
this was to discourage users from tweaking rto_alpha and
rto_beta knobs in production environments since they are key
to correctly compute rtt/srtt.
RFC4960 under section 6.3.1. RTO Calculation says regarding
rto_alpha and rto_beta under rule C3 and C4:
[...]
C3) When a new RTT measurement R' is made, set
RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
and
SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
Note: The value of SRTT used in the update to RTTVAR
is its value before updating SRTT itself using the
second assignment. After the computation, update
RTO <- SRTT + 4 * RTTVAR.
C4) When data is in flight and when allowed by rule C5
below, a new RTT measurement MUST be made each round
trip. Furthermore, new RTT measurements SHOULD be
made no more than once per round trip for a given
destination transport address. There are two reasons
for this recommendation: First, it appears that
measuring more frequently often does not in practice
yield any significant benefit [ALLMAN99]; second,
if measurements are made more often, then the values
of RTO.Alpha and RTO.Beta in rule C3 above should be
adjusted so that SRTT and RTTVAR still adjust to
changes at roughly the same rate (in terms of how many
round trips it takes them to reflect new values) as
they would if making only one measurement per
round-trip and using RTO.Alpha and RTO.Beta as given
in rule C3. However, the exact nature of these
adjustments remains a research issue.
[...]
While it is discouraged to adjust rto_alpha and rto_beta
and not further specified how to adjust them, the RFC also
doesn't explicitly forbid it, but rather gives a RECOMMENDED
default value (rto_alpha=3, rto_beta=2). We have a couple
of users relying on the old permissions before they got
changed. That said, if someone really has the urge to adjust
them, we could allow it with a warning in the log.
Fixes: 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs to jiffies conversions.")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-15 05:59:14 +07:00
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_sctp_do_alpha_beta,
|
|
|
|
.extra1 = &rto_alpha_min,
|
|
|
|
.extra2 = &rto_alpha_max,
|
2012-08-07 14:29:57 +07:00
|
|
|
},
|
|
|
|
{
|
|
|
|
.procname = "rto_beta_exp_divisor",
|
|
|
|
.data = &init_net.sctp.rto_beta,
|
|
|
|
.maxlen = sizeof(int),
|
net: sctp: fix permissions for rto_alpha and rto_beta knobs
Commit 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs
to jiffies conversions.") has silently changed permissions for
rto_alpha and rto_beta knobs from 0644 to 0444. The purpose of
this was to discourage users from tweaking rto_alpha and
rto_beta knobs in production environments since they are key
to correctly compute rtt/srtt.
RFC4960 under section 6.3.1. RTO Calculation says regarding
rto_alpha and rto_beta under rule C3 and C4:
[...]
C3) When a new RTT measurement R' is made, set
RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
and
SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
Note: The value of SRTT used in the update to RTTVAR
is its value before updating SRTT itself using the
second assignment. After the computation, update
RTO <- SRTT + 4 * RTTVAR.
C4) When data is in flight and when allowed by rule C5
below, a new RTT measurement MUST be made each round
trip. Furthermore, new RTT measurements SHOULD be
made no more than once per round trip for a given
destination transport address. There are two reasons
for this recommendation: First, it appears that
measuring more frequently often does not in practice
yield any significant benefit [ALLMAN99]; second,
if measurements are made more often, then the values
of RTO.Alpha and RTO.Beta in rule C3 above should be
adjusted so that SRTT and RTTVAR still adjust to
changes at roughly the same rate (in terms of how many
round trips it takes them to reflect new values) as
they would if making only one measurement per
round-trip and using RTO.Alpha and RTO.Beta as given
in rule C3. However, the exact nature of these
adjustments remains a research issue.
[...]
While it is discouraged to adjust rto_alpha and rto_beta
and not further specified how to adjust them, the RFC also
doesn't explicitly forbid it, but rather gives a RECOMMENDED
default value (rto_alpha=3, rto_beta=2). We have a couple
of users relying on the old permissions before they got
changed. That said, if someone really has the urge to adjust
them, we could allow it with a warning in the log.
Fixes: 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs to jiffies conversions.")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-15 05:59:14 +07:00
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_sctp_do_alpha_beta,
|
|
|
|
.extra1 = &rto_beta_min,
|
|
|
|
.extra2 = &rto_beta_max,
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
|
|
|
{
|
|
|
|
.procname = "max_burst",
|
2012-08-07 14:29:57 +07:00
|
|
|
.data = &init_net.sctp.max_burst,
|
2005-04-17 05:20:36 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ZERO,
|
|
|
|
.extra2 = SYSCTL_INT_MAX,
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "cookie_preserve_enable",
|
|
|
|
.data = &init_net.sctp.cookie_preserve_enable,
|
2005-04-17 05:20:36 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
2012-08-07 14:29:57 +07:00
|
|
|
.proc_handler = proc_dointvec,
|
|
|
|
},
|
2012-10-24 16:20:03 +07:00
|
|
|
{
|
|
|
|
.procname = "cookie_hmac_alg",
|
2014-02-12 08:44:43 +07:00
|
|
|
.data = &init_net.sctp.sctp_hmac_alg,
|
2012-10-24 16:20:03 +07:00
|
|
|
.maxlen = 8,
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_sctp_do_hmac_alg,
|
|
|
|
},
|
2012-08-07 14:29:57 +07:00
|
|
|
{
|
|
|
|
.procname = "valid_cookie_life",
|
|
|
|
.data = &init_net.sctp.valid_cookie_life,
|
|
|
|
.maxlen = sizeof(unsigned int),
|
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ONE,
|
2012-08-07 14:29:57 +07:00
|
|
|
.extra2 = &timer_max
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
2005-04-29 02:02:04 +07:00
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "sack_timeout",
|
|
|
|
.data = &init_net.sctp.sack_timeout,
|
2005-04-29 02:02:04 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
2012-08-07 14:29:57 +07:00
|
|
|
.proc_handler = proc_dointvec_minmax,
|
|
|
|
.extra1 = &sack_timer_min,
|
|
|
|
.extra2 = &sack_timer_max,
|
2005-04-29 02:02:04 +07:00
|
|
|
},
|
2005-11-12 07:08:24 +07:00
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "hb_interval",
|
|
|
|
.data = &init_net.sctp.hb_interval,
|
|
|
|
.maxlen = sizeof(unsigned int),
|
2005-11-12 07:08:24 +07:00
|
|
|
.mode = 0644,
|
2012-08-07 14:29:57 +07:00
|
|
|
.proc_handler = proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ONE,
|
2012-08-07 14:29:57 +07:00
|
|
|
.extra2 = &timer_max
|
2005-11-12 07:08:24 +07:00
|
|
|
},
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "association_max_retrans",
|
|
|
|
.data = &init_net.sctp.max_retrans_association,
|
2005-04-17 05:20:36 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ONE,
|
|
|
|
.extra2 = SYSCTL_INT_MAX,
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
2012-07-21 14:56:07 +07:00
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "path_max_retrans",
|
|
|
|
.data = &init_net.sctp.max_retrans_path,
|
2012-07-21 14:56:07 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ONE,
|
|
|
|
.extra2 = SYSCTL_INT_MAX,
|
2012-07-21 14:56:07 +07:00
|
|
|
},
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
.procname = "max_init_retransmits",
|
2012-08-07 14:29:57 +07:00
|
|
|
.data = &init_net.sctp.max_retrans_init,
|
2005-04-17 05:20:36 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ONE,
|
|
|
|
.extra2 = SYSCTL_INT_MAX,
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "pf_retrans",
|
|
|
|
.data = &init_net.sctp.pf_retrans,
|
|
|
|
.maxlen = sizeof(int),
|
2005-04-17 05:20:36 +07:00
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ZERO,
|
2019-11-08 12:20:35 +07:00
|
|
|
.extra2 = &init_net.sctp.ps_retrans,
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.procname = "ps_retrans",
|
|
|
|
.data = &init_net.sctp.ps_retrans,
|
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec_minmax,
|
|
|
|
.extra1 = &init_net.sctp.pf_retrans,
|
|
|
|
.extra2 = &ps_retrans_max,
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "sndbuf_policy",
|
|
|
|
.data = &init_net.sctp.sndbuf_policy,
|
2006-01-18 02:55:17 +07:00
|
|
|
.maxlen = sizeof(int),
|
2005-04-17 05:20:36 +07:00
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec,
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "rcvbuf_policy",
|
|
|
|
.data = &init_net.sctp.rcvbuf_policy,
|
2011-04-26 15:36:05 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec,
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.procname = "default_auto_asconf",
|
2012-08-07 14:29:57 +07:00
|
|
|
.data = &init_net.sctp.default_auto_asconf,
|
2005-04-17 05:20:36 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec,
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "addip_enable",
|
|
|
|
.data = &init_net.sctp.addip_enable,
|
2005-04-17 05:20:36 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec,
|
2005-04-17 05:20:36 +07:00
|
|
|
},
|
2005-06-29 03:24:23 +07:00
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "addip_noauth_enable",
|
|
|
|
.data = &init_net.sctp.addip_noauth,
|
2009-05-13 05:03:20 +07:00
|
|
|
.maxlen = sizeof(int),
|
2005-06-29 03:24:23 +07:00
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec,
|
2007-08-16 06:07:44 +07:00
|
|
|
},
|
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "prsctp_enable",
|
|
|
|
.data = &init_net.sctp.prsctp_enable,
|
2007-09-17 09:31:35 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
2008-11-04 09:21:05 +07:00
|
|
|
.proc_handler = proc_dointvec,
|
2007-09-17 09:31:35 +07:00
|
|
|
},
|
2017-03-10 11:11:12 +07:00
|
|
|
{
|
|
|
|
.procname = "reconf_enable",
|
|
|
|
.data = &init_net.sctp.reconf_enable,
|
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec,
|
|
|
|
},
|
2007-10-25 04:24:26 +07:00
|
|
|
{
|
2012-08-07 14:29:57 +07:00
|
|
|
.procname = "auth_enable",
|
|
|
|
.data = &init_net.sctp.auth_enable,
|
2007-10-25 04:24:26 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
net: sctp: cache auth_enable per endpoint
Currently, it is possible to create an SCTP socket, then switch
auth_enable via sysctl setting to 1 and crash the system on connect:
Oops[#1]:
CPU: 0 PID: 0 Comm: swapper Not tainted 3.14.1-mipsgit-20140415 #1
task: ffffffff8056ce80 ti: ffffffff8055c000 task.ti: ffffffff8055c000
[...]
Call Trace:
[<ffffffff8043c4e8>] sctp_auth_asoc_set_default_hmac+0x68/0x80
[<ffffffff8042b300>] sctp_process_init+0x5e0/0x8a4
[<ffffffff8042188c>] sctp_sf_do_5_1B_init+0x234/0x34c
[<ffffffff804228c8>] sctp_do_sm+0xb4/0x1e8
[<ffffffff80425a08>] sctp_endpoint_bh_rcv+0x1c4/0x214
[<ffffffff8043af68>] sctp_rcv+0x588/0x630
[<ffffffff8043e8e8>] sctp6_rcv+0x10/0x24
[<ffffffff803acb50>] ip6_input+0x2c0/0x440
[<ffffffff8030fc00>] __netif_receive_skb_core+0x4a8/0x564
[<ffffffff80310650>] process_backlog+0xb4/0x18c
[<ffffffff80313cbc>] net_rx_action+0x12c/0x210
[<ffffffff80034254>] __do_softirq+0x17c/0x2ac
[<ffffffff800345e0>] irq_exit+0x54/0xb0
[<ffffffff800075a4>] ret_from_irq+0x0/0x4
[<ffffffff800090ec>] rm7k_wait_irqoff+0x24/0x48
[<ffffffff8005e388>] cpu_startup_entry+0xc0/0x148
[<ffffffff805a88b0>] start_kernel+0x37c/0x398
Code: dd0900b8 000330f8 0126302d <dcc60000> 50c0fff1 0047182a a48306a0
03e00008 00000000
---[ end trace b530b0551467f2fd ]---
Kernel panic - not syncing: Fatal exception in interrupt
What happens while auth_enable=0 in that case is, that
ep->auth_hmacs is initialized to NULL in sctp_auth_init_hmacs()
when endpoint is being created.
After that point, if an admin switches over to auth_enable=1,
the machine can crash due to NULL pointer dereference during
reception of an INIT chunk. When we enter sctp_process_init()
via sctp_sf_do_5_1B_init() in order to respond to an INIT chunk,
the INIT verification succeeds and while we walk and process
all INIT params via sctp_process_param() we find that
net->sctp.auth_enable is set, therefore do not fall through,
but invoke sctp_auth_asoc_set_default_hmac() instead, and thus,
dereference what we have set to NULL during endpoint
initialization phase.
The fix is to make auth_enable immutable by caching its value
during endpoint initialization, so that its original value is
being carried along until destruction. The bug seems to originate
from the very first days.
Fix in joint work with Daniel Borkmann.
Reported-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-17 22:26:50 +07:00
|
|
|
.proc_handler = proc_sctp_do_auth,
|
2007-10-25 04:24:26 +07:00
|
|
|
},
|
2017-12-14 23:41:32 +07:00
|
|
|
{
|
|
|
|
.procname = "intl_enable",
|
|
|
|
.data = &init_net.sctp.intl_enable,
|
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec,
|
|
|
|
},
|
2019-08-26 15:30:03 +07:00
|
|
|
{
|
|
|
|
.procname = "ecn_enable",
|
|
|
|
.data = &init_net.sctp.ecn_enable,
|
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec,
|
|
|
|
},
|
2009-09-03 18:55:47 +07:00
|
|
|
{
|
|
|
|
.procname = "addr_scope_policy",
|
2012-08-07 14:29:57 +07:00
|
|
|
.data = &init_net.sctp.scope_policy,
|
2009-09-03 18:55:47 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
2009-11-16 18:11:48 +07:00
|
|
|
.proc_handler = proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ZERO,
|
2009-09-03 18:55:47 +07:00
|
|
|
.extra2 = &addr_scope_max,
|
|
|
|
},
|
2009-11-24 03:53:57 +07:00
|
|
|
{
|
|
|
|
.procname = "rwnd_update_shift",
|
2012-08-07 14:29:57 +07:00
|
|
|
.data = &init_net.sctp.rwnd_upd_shift,
|
2009-11-24 03:53:57 +07:00
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = &proc_dointvec_minmax,
|
proc/sysctl: add shared variables for range check
In the sysctl code the proc_dointvec_minmax() function is often used to
validate the user supplied value between an allowed range. This
function uses the extra1 and extra2 members from struct ctl_table as
minimum and maximum allowed value.
On sysctl handler declaration, in every source file there are some
readonly variables containing just an integer which address is assigned
to the extra1 and extra2 members, so the sysctl range is enforced.
The special values 0, 1 and INT_MAX are very often used as range
boundary, leading duplication of variables like zero=0, one=1,
int_max=INT_MAX in different source files:
$ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l
248
Add a const int array containing the most commonly used values, some
macros to refer more easily to the correct array member, and use them
instead of creating a local one for every object file.
This is the bloat-o-meter output comparing the old and new binary
compiled with the default Fedora config:
# scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o
add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164)
Data old new delta
sysctl_vals - 12 +12
__kstrtab_sysctl_vals - 12 +12
max 14 10 -4
int_max 16 - -16
one 68 - -68
zero 128 28 -100
Total: Before=20583249, After=20583085, chg -0.00%
[mcroce@redhat.com: tipc: remove two unused variables]
Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com
[akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c]
[arnd@arndb.de: proc/sysctl: make firmware loader table conditional]
Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de
[akpm@linux-foundation.org: fix fs/eventpoll.c]
Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 05:58:50 +07:00
|
|
|
.extra1 = SYSCTL_ONE,
|
2009-11-24 03:53:57 +07:00
|
|
|
.extra2 = &rwnd_scale_max,
|
|
|
|
},
|
2011-12-16 19:44:15 +07:00
|
|
|
{
|
|
|
|
.procname = "max_autoclose",
|
2012-08-07 14:29:57 +07:00
|
|
|
.data = &init_net.sctp.max_autoclose,
|
2011-12-16 19:44:15 +07:00
|
|
|
.maxlen = sizeof(unsigned long),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = &proc_doulongvec_minmax,
|
|
|
|
.extra1 = &max_autoclose_min,
|
|
|
|
.extra2 = &max_autoclose_max,
|
|
|
|
},
|
2015-12-16 12:55:04 +07:00
|
|
|
{
|
|
|
|
.procname = "pf_enable",
|
|
|
|
.data = &init_net.sctp.pf_enable,
|
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec,
|
|
|
|
},
|
sctp: add pf_expose per netns and sock and asoc
As said in rfc7829, section 3, point 12:
The SCTP stack SHOULD expose the PF state of its destination
addresses to the ULP as well as provide the means to notify the
ULP of state transitions of its destination addresses from
active to PF, and vice versa. However, it is recommended that
an SCTP stack implementing SCTP-PF also allows for the ULP to be
kept ignorant of the PF state of its destinations and the
associated state transitions, thus allowing for retention of the
simpler state transition model of [RFC4960] in the ULP.
Not only does it allow to expose the PF state to ULP, but also
allow to ignore sctp-pf to ULP.
So this patch is to add pf_expose per netns, sock and asoc. And in
sctp_assoc_control_transport(), ulp_notify will be set to false if
asoc->expose is not 'enabled' in next patch.
It also allows a user to change pf_expose per netns by sysctl, and
pf_expose per sock and asoc will be initialized with it.
Note that pf_expose also works for SCTP_GET_PEER_ADDR_INFO sockopt,
to not allow a user to query the state of a sctp-pf peer address
when pf_expose is 'disabled', as said in section 7.3.
v1->v2:
- Fix a build warning noticed by Nathan Chancellor.
v2->v3:
- set pf_expose to UNUSED by default to keep compatible with old
applications.
v3->v4:
- add a new entry for pf_expose on ip-sysctl.txt, as Marcelo suggested.
- change this patch to 1/5, and move sctp_assoc_control_transport
change into 2/5, as Marcelo suggested.
- use SCTP_PF_EXPOSE_UNSET instead of SCTP_PF_EXPOSE_UNUSED, and
set SCTP_PF_EXPOSE_UNSET to 0 in enum, as Marcelo suggested.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-08 12:20:32 +07:00
|
|
|
{
|
|
|
|
.procname = "pf_expose",
|
|
|
|
.data = &init_net.sctp.pf_expose,
|
|
|
|
.maxlen = sizeof(int),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec_minmax,
|
|
|
|
.extra1 = SYSCTL_ZERO,
|
|
|
|
.extra2 = &pf_expose_max,
|
|
|
|
},
|
2013-08-10 03:09:41 +07:00
|
|
|
|
2009-12-08 22:55:01 +07:00
|
|
|
{ /* sentinel */ }
|
2005-04-17 05:20:36 +07:00
|
|
|
};
|
|
|
|
|
2013-12-11 08:50:40 +07:00
|
|
|
static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
|
2012-10-24 16:20:03 +07:00
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos)
|
|
|
|
{
|
|
|
|
struct net *net = current->nsproxy->net_ns;
|
2013-06-12 13:04:25 +07:00
|
|
|
struct ctl_table tbl;
|
2014-06-19 06:31:30 +07:00
|
|
|
bool changed = false;
|
2012-10-24 16:20:03 +07:00
|
|
|
char *none = "none";
|
2016-01-08 02:52:43 +07:00
|
|
|
char tmp[8] = {0};
|
2014-06-19 06:31:30 +07:00
|
|
|
int ret;
|
2012-10-24 16:20:03 +07:00
|
|
|
|
|
|
|
memset(&tbl, 0, sizeof(struct ctl_table));
|
|
|
|
|
|
|
|
if (write) {
|
|
|
|
tbl.data = tmp;
|
2014-06-19 06:31:30 +07:00
|
|
|
tbl.maxlen = sizeof(tmp);
|
2012-10-24 16:20:03 +07:00
|
|
|
} else {
|
|
|
|
tbl.data = net->sctp.sctp_hmac_alg ? : none;
|
|
|
|
tbl.maxlen = strlen(tbl.data);
|
|
|
|
}
|
|
|
|
|
2014-06-19 06:31:30 +07:00
|
|
|
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
|
|
|
|
if (write && ret == 0) {
|
2012-10-24 16:20:03 +07:00
|
|
|
#ifdef CONFIG_CRYPTO_MD5
|
|
|
|
if (!strncmp(tmp, "md5", 3)) {
|
|
|
|
net->sctp.sctp_hmac_alg = "md5";
|
2014-06-19 06:31:30 +07:00
|
|
|
changed = true;
|
2012-10-24 16:20:03 +07:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
#ifdef CONFIG_CRYPTO_SHA1
|
|
|
|
if (!strncmp(tmp, "sha1", 4)) {
|
|
|
|
net->sctp.sctp_hmac_alg = "sha1";
|
2014-06-19 06:31:30 +07:00
|
|
|
changed = true;
|
2012-10-24 16:20:03 +07:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
if (!strncmp(tmp, "none", 4)) {
|
|
|
|
net->sctp.sctp_hmac_alg = NULL;
|
2014-06-19 06:31:30 +07:00
|
|
|
changed = true;
|
2012-10-24 16:20:03 +07:00
|
|
|
}
|
|
|
|
if (!changed)
|
|
|
|
ret = -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-12-11 08:50:39 +07:00
|
|
|
static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
|
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos)
|
|
|
|
{
|
|
|
|
struct net *net = current->nsproxy->net_ns;
|
|
|
|
unsigned int min = *(unsigned int *) ctl->extra1;
|
|
|
|
unsigned int max = *(unsigned int *) ctl->extra2;
|
2014-06-19 06:31:30 +07:00
|
|
|
struct ctl_table tbl;
|
|
|
|
int ret, new_value;
|
2013-12-11 08:50:39 +07:00
|
|
|
|
|
|
|
memset(&tbl, 0, sizeof(struct ctl_table));
|
|
|
|
tbl.maxlen = sizeof(unsigned int);
|
|
|
|
|
|
|
|
if (write)
|
|
|
|
tbl.data = &new_value;
|
|
|
|
else
|
|
|
|
tbl.data = &net->sctp.rto_min;
|
2014-06-19 06:31:30 +07:00
|
|
|
|
2013-12-11 08:50:39 +07:00
|
|
|
ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
|
2014-06-19 06:31:30 +07:00
|
|
|
if (write && ret == 0) {
|
|
|
|
if (new_value > max || new_value < min)
|
2013-12-11 08:50:39 +07:00
|
|
|
return -EINVAL;
|
2014-06-19 06:31:30 +07:00
|
|
|
|
2013-12-11 08:50:39 +07:00
|
|
|
net->sctp.rto_min = new_value;
|
|
|
|
}
|
2014-06-19 06:31:30 +07:00
|
|
|
|
2013-12-11 08:50:39 +07:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
|
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos)
|
|
|
|
{
|
|
|
|
struct net *net = current->nsproxy->net_ns;
|
|
|
|
unsigned int min = *(unsigned int *) ctl->extra1;
|
|
|
|
unsigned int max = *(unsigned int *) ctl->extra2;
|
2014-06-19 06:31:30 +07:00
|
|
|
struct ctl_table tbl;
|
|
|
|
int ret, new_value;
|
2013-12-11 08:50:39 +07:00
|
|
|
|
|
|
|
memset(&tbl, 0, sizeof(struct ctl_table));
|
|
|
|
tbl.maxlen = sizeof(unsigned int);
|
|
|
|
|
|
|
|
if (write)
|
|
|
|
tbl.data = &new_value;
|
|
|
|
else
|
|
|
|
tbl.data = &net->sctp.rto_max;
|
2014-06-19 06:31:30 +07:00
|
|
|
|
2013-12-11 08:50:39 +07:00
|
|
|
ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
|
2014-06-19 06:31:30 +07:00
|
|
|
if (write && ret == 0) {
|
|
|
|
if (new_value > max || new_value < min)
|
2013-12-11 08:50:39 +07:00
|
|
|
return -EINVAL;
|
2014-06-19 06:31:30 +07:00
|
|
|
|
2013-12-11 08:50:39 +07:00
|
|
|
net->sctp.rto_max = new_value;
|
|
|
|
}
|
2014-06-19 06:31:30 +07:00
|
|
|
|
2013-12-11 08:50:39 +07:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
net: sctp: fix permissions for rto_alpha and rto_beta knobs
Commit 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs
to jiffies conversions.") has silently changed permissions for
rto_alpha and rto_beta knobs from 0644 to 0444. The purpose of
this was to discourage users from tweaking rto_alpha and
rto_beta knobs in production environments since they are key
to correctly compute rtt/srtt.
RFC4960 under section 6.3.1. RTO Calculation says regarding
rto_alpha and rto_beta under rule C3 and C4:
[...]
C3) When a new RTT measurement R' is made, set
RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
and
SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
Note: The value of SRTT used in the update to RTTVAR
is its value before updating SRTT itself using the
second assignment. After the computation, update
RTO <- SRTT + 4 * RTTVAR.
C4) When data is in flight and when allowed by rule C5
below, a new RTT measurement MUST be made each round
trip. Furthermore, new RTT measurements SHOULD be
made no more than once per round trip for a given
destination transport address. There are two reasons
for this recommendation: First, it appears that
measuring more frequently often does not in practice
yield any significant benefit [ALLMAN99]; second,
if measurements are made more often, then the values
of RTO.Alpha and RTO.Beta in rule C3 above should be
adjusted so that SRTT and RTTVAR still adjust to
changes at roughly the same rate (in terms of how many
round trips it takes them to reflect new values) as
they would if making only one measurement per
round-trip and using RTO.Alpha and RTO.Beta as given
in rule C3. However, the exact nature of these
adjustments remains a research issue.
[...]
While it is discouraged to adjust rto_alpha and rto_beta
and not further specified how to adjust them, the RFC also
doesn't explicitly forbid it, but rather gives a RECOMMENDED
default value (rto_alpha=3, rto_beta=2). We have a couple
of users relying on the old permissions before they got
changed. That said, if someone really has the urge to adjust
them, we could allow it with a warning in the log.
Fixes: 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs to jiffies conversions.")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-15 05:59:14 +07:00
|
|
|
static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
|
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos)
|
|
|
|
{
|
2014-06-30 18:52:09 +07:00
|
|
|
if (write)
|
|
|
|
pr_warn_once("Changing rto_alpha or rto_beta may lead to "
|
|
|
|
"suboptimal rtt/srtt estimations!\n");
|
net: sctp: fix permissions for rto_alpha and rto_beta knobs
Commit 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs
to jiffies conversions.") has silently changed permissions for
rto_alpha and rto_beta knobs from 0644 to 0444. The purpose of
this was to discourage users from tweaking rto_alpha and
rto_beta knobs in production environments since they are key
to correctly compute rtt/srtt.
RFC4960 under section 6.3.1. RTO Calculation says regarding
rto_alpha and rto_beta under rule C3 and C4:
[...]
C3) When a new RTT measurement R' is made, set
RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
and
SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
Note: The value of SRTT used in the update to RTTVAR
is its value before updating SRTT itself using the
second assignment. After the computation, update
RTO <- SRTT + 4 * RTTVAR.
C4) When data is in flight and when allowed by rule C5
below, a new RTT measurement MUST be made each round
trip. Furthermore, new RTT measurements SHOULD be
made no more than once per round trip for a given
destination transport address. There are two reasons
for this recommendation: First, it appears that
measuring more frequently often does not in practice
yield any significant benefit [ALLMAN99]; second,
if measurements are made more often, then the values
of RTO.Alpha and RTO.Beta in rule C3 above should be
adjusted so that SRTT and RTTVAR still adjust to
changes at roughly the same rate (in terms of how many
round trips it takes them to reflect new values) as
they would if making only one measurement per
round-trip and using RTO.Alpha and RTO.Beta as given
in rule C3. However, the exact nature of these
adjustments remains a research issue.
[...]
While it is discouraged to adjust rto_alpha and rto_beta
and not further specified how to adjust them, the RFC also
doesn't explicitly forbid it, but rather gives a RECOMMENDED
default value (rto_alpha=3, rto_beta=2). We have a couple
of users relying on the old permissions before they got
changed. That said, if someone really has the urge to adjust
them, we could allow it with a warning in the log.
Fixes: 3fd091e73b81 ("[SCTP]: Remove multiple levels of msecs to jiffies conversions.")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-15 05:59:14 +07:00
|
|
|
|
|
|
|
return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
|
|
|
|
}
|
|
|
|
|
net: sctp: cache auth_enable per endpoint
Currently, it is possible to create an SCTP socket, then switch
auth_enable via sysctl setting to 1 and crash the system on connect:
Oops[#1]:
CPU: 0 PID: 0 Comm: swapper Not tainted 3.14.1-mipsgit-20140415 #1
task: ffffffff8056ce80 ti: ffffffff8055c000 task.ti: ffffffff8055c000
[...]
Call Trace:
[<ffffffff8043c4e8>] sctp_auth_asoc_set_default_hmac+0x68/0x80
[<ffffffff8042b300>] sctp_process_init+0x5e0/0x8a4
[<ffffffff8042188c>] sctp_sf_do_5_1B_init+0x234/0x34c
[<ffffffff804228c8>] sctp_do_sm+0xb4/0x1e8
[<ffffffff80425a08>] sctp_endpoint_bh_rcv+0x1c4/0x214
[<ffffffff8043af68>] sctp_rcv+0x588/0x630
[<ffffffff8043e8e8>] sctp6_rcv+0x10/0x24
[<ffffffff803acb50>] ip6_input+0x2c0/0x440
[<ffffffff8030fc00>] __netif_receive_skb_core+0x4a8/0x564
[<ffffffff80310650>] process_backlog+0xb4/0x18c
[<ffffffff80313cbc>] net_rx_action+0x12c/0x210
[<ffffffff80034254>] __do_softirq+0x17c/0x2ac
[<ffffffff800345e0>] irq_exit+0x54/0xb0
[<ffffffff800075a4>] ret_from_irq+0x0/0x4
[<ffffffff800090ec>] rm7k_wait_irqoff+0x24/0x48
[<ffffffff8005e388>] cpu_startup_entry+0xc0/0x148
[<ffffffff805a88b0>] start_kernel+0x37c/0x398
Code: dd0900b8 000330f8 0126302d <dcc60000> 50c0fff1 0047182a a48306a0
03e00008 00000000
---[ end trace b530b0551467f2fd ]---
Kernel panic - not syncing: Fatal exception in interrupt
What happens while auth_enable=0 in that case is, that
ep->auth_hmacs is initialized to NULL in sctp_auth_init_hmacs()
when endpoint is being created.
After that point, if an admin switches over to auth_enable=1,
the machine can crash due to NULL pointer dereference during
reception of an INIT chunk. When we enter sctp_process_init()
via sctp_sf_do_5_1B_init() in order to respond to an INIT chunk,
the INIT verification succeeds and while we walk and process
all INIT params via sctp_process_param() we find that
net->sctp.auth_enable is set, therefore do not fall through,
but invoke sctp_auth_asoc_set_default_hmac() instead, and thus,
dereference what we have set to NULL during endpoint
initialization phase.
The fix is to make auth_enable immutable by caching its value
during endpoint initialization, so that its original value is
being carried along until destruction. The bug seems to originate
from the very first days.
Fix in joint work with Daniel Borkmann.
Reported-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-17 22:26:50 +07:00
|
|
|
static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
|
|
|
|
void __user *buffer, size_t *lenp,
|
|
|
|
loff_t *ppos)
|
|
|
|
{
|
|
|
|
struct net *net = current->nsproxy->net_ns;
|
|
|
|
struct ctl_table tbl;
|
|
|
|
int new_value, ret;
|
|
|
|
|
|
|
|
memset(&tbl, 0, sizeof(struct ctl_table));
|
|
|
|
tbl.maxlen = sizeof(unsigned int);
|
|
|
|
|
|
|
|
if (write)
|
|
|
|
tbl.data = &new_value;
|
|
|
|
else
|
|
|
|
tbl.data = &net->sctp.auth_enable;
|
|
|
|
|
|
|
|
ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
|
2014-06-19 04:46:31 +07:00
|
|
|
if (write && ret == 0) {
|
net: sctp: cache auth_enable per endpoint
Currently, it is possible to create an SCTP socket, then switch
auth_enable via sysctl setting to 1 and crash the system on connect:
Oops[#1]:
CPU: 0 PID: 0 Comm: swapper Not tainted 3.14.1-mipsgit-20140415 #1
task: ffffffff8056ce80 ti: ffffffff8055c000 task.ti: ffffffff8055c000
[...]
Call Trace:
[<ffffffff8043c4e8>] sctp_auth_asoc_set_default_hmac+0x68/0x80
[<ffffffff8042b300>] sctp_process_init+0x5e0/0x8a4
[<ffffffff8042188c>] sctp_sf_do_5_1B_init+0x234/0x34c
[<ffffffff804228c8>] sctp_do_sm+0xb4/0x1e8
[<ffffffff80425a08>] sctp_endpoint_bh_rcv+0x1c4/0x214
[<ffffffff8043af68>] sctp_rcv+0x588/0x630
[<ffffffff8043e8e8>] sctp6_rcv+0x10/0x24
[<ffffffff803acb50>] ip6_input+0x2c0/0x440
[<ffffffff8030fc00>] __netif_receive_skb_core+0x4a8/0x564
[<ffffffff80310650>] process_backlog+0xb4/0x18c
[<ffffffff80313cbc>] net_rx_action+0x12c/0x210
[<ffffffff80034254>] __do_softirq+0x17c/0x2ac
[<ffffffff800345e0>] irq_exit+0x54/0xb0
[<ffffffff800075a4>] ret_from_irq+0x0/0x4
[<ffffffff800090ec>] rm7k_wait_irqoff+0x24/0x48
[<ffffffff8005e388>] cpu_startup_entry+0xc0/0x148
[<ffffffff805a88b0>] start_kernel+0x37c/0x398
Code: dd0900b8 000330f8 0126302d <dcc60000> 50c0fff1 0047182a a48306a0
03e00008 00000000
---[ end trace b530b0551467f2fd ]---
Kernel panic - not syncing: Fatal exception in interrupt
What happens while auth_enable=0 in that case is, that
ep->auth_hmacs is initialized to NULL in sctp_auth_init_hmacs()
when endpoint is being created.
After that point, if an admin switches over to auth_enable=1,
the machine can crash due to NULL pointer dereference during
reception of an INIT chunk. When we enter sctp_process_init()
via sctp_sf_do_5_1B_init() in order to respond to an INIT chunk,
the INIT verification succeeds and while we walk and process
all INIT params via sctp_process_param() we find that
net->sctp.auth_enable is set, therefore do not fall through,
but invoke sctp_auth_asoc_set_default_hmac() instead, and thus,
dereference what we have set to NULL during endpoint
initialization phase.
The fix is to make auth_enable immutable by caching its value
during endpoint initialization, so that its original value is
being carried along until destruction. The bug seems to originate
from the very first days.
Fix in joint work with Daniel Borkmann.
Reported-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-17 22:26:50 +07:00
|
|
|
struct sock *sk = net->sctp.ctl_sock;
|
|
|
|
|
|
|
|
net->sctp.auth_enable = new_value;
|
|
|
|
/* Update the value in the control socket */
|
|
|
|
lock_sock(sk);
|
|
|
|
sctp_sk(sk)->ep->auth_enable = new_value;
|
|
|
|
release_sock(sk);
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2012-08-07 14:23:59 +07:00
|
|
|
int sctp_sysctl_net_register(struct net *net)
|
|
|
|
{
|
2014-05-08 19:55:01 +07:00
|
|
|
struct ctl_table *table;
|
|
|
|
int i;
|
2012-08-07 14:23:59 +07:00
|
|
|
|
2014-05-08 19:55:01 +07:00
|
|
|
table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
|
|
|
|
if (!table)
|
|
|
|
return -ENOMEM;
|
2012-08-07 14:23:59 +07:00
|
|
|
|
2014-05-08 19:55:01 +07:00
|
|
|
for (i = 0; table[i].data; i++)
|
|
|
|
table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
|
2012-08-07 14:29:57 +07:00
|
|
|
|
2012-08-07 14:23:59 +07:00
|
|
|
net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
|
2014-05-08 19:55:02 +07:00
|
|
|
if (net->sctp.sysctl_header == NULL) {
|
|
|
|
kfree(table);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
2012-08-07 14:23:59 +07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void sctp_sysctl_net_unregister(struct net *net)
|
|
|
|
{
|
2013-01-24 23:02:47 +07:00
|
|
|
struct ctl_table *table;
|
|
|
|
|
|
|
|
table = net->sctp.sysctl_header->ctl_table_arg;
|
2012-08-07 14:23:59 +07:00
|
|
|
unregister_net_sysctl_table(net->sctp.sysctl_header);
|
2013-01-24 23:02:47 +07:00
|
|
|
kfree(table);
|
2012-08-07 14:23:59 +07:00
|
|
|
}
|
|
|
|
|
2013-12-23 11:16:51 +07:00
|
|
|
static struct ctl_table_header *sctp_sysctl_header;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
/* Sysctl registration. */
|
|
|
|
void sctp_sysctl_register(void)
|
|
|
|
{
|
2012-04-19 20:44:49 +07:00
|
|
|
sctp_sysctl_header = register_net_sysctl(&init_net, "net/sctp", sctp_table);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Sysctl deregistration. */
|
|
|
|
void sctp_sysctl_unregister(void)
|
|
|
|
{
|
2012-04-19 20:24:33 +07:00
|
|
|
unregister_net_sysctl_table(sctp_sysctl_header);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|