kernel_optimize_test/net/sctp/sysctl.c
Xin Long aef587be42 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 14:18:32 -08:00

522 lines
12 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/* SCTP kernel implementation
* (C) Copyright IBM Corp. 2002, 2004
* Copyright (c) 2002 Intel Corp.
*
* This file is part of the SCTP kernel implementation
*
* Sysctl related interfaces for SCTP.
*
* Please send any bug reports or fixes you make to the
* email address(es):
* lksctp developers <linux-sctp@vger.kernel.org>
*
* 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>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <net/sctp/structs.h>
#include <net/sctp/sctp.h>
#include <linux/sysctl.h>
static int timer_max = 86400000; /* ms in one day */
static int sack_timer_min = 1;
static int sack_timer_max = 500;
static int addr_scope_max = SCTP_SCOPE_POLICY_MAX;
static int rwnd_scale_max = 16;
static int rto_alpha_min = 0;
static int rto_beta_min = 0;
static int rto_alpha_max = 1000;
static int rto_beta_max = 1000;
static int pf_expose_max = SCTP_PF_EXPOSE_MAX;
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;
static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
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,
void __user *buffer, size_t *lenp,
loff_t *ppos);
static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
static struct ctl_table sctp_table[] = {
{
.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 */ }
};
static struct ctl_table sctp_net_table[] = {
{
.procname = "rto_initial",
.data = &init_net.sctp.rto_initial,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
.extra2 = &timer_max
},
{
.procname = "rto_min",
.data = &init_net.sctp.rto_min,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_sctp_do_rto_min,
.extra1 = SYSCTL_ONE,
.extra2 = &init_net.sctp.rto_max
},
{
.procname = "rto_max",
.data = &init_net.sctp.rto_max,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_sctp_do_rto_max,
.extra1 = &init_net.sctp.rto_min,
.extra2 = &timer_max
},
{
.procname = "rto_alpha_exp_divisor",
.data = &init_net.sctp.rto_alpha,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_sctp_do_alpha_beta,
.extra1 = &rto_alpha_min,
.extra2 = &rto_alpha_max,
},
{
.procname = "rto_beta_exp_divisor",
.data = &init_net.sctp.rto_beta,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_sctp_do_alpha_beta,
.extra1 = &rto_beta_min,
.extra2 = &rto_beta_max,
},
{
.procname = "max_burst",
.data = &init_net.sctp.max_burst,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_INT_MAX,
},
{
.procname = "cookie_preserve_enable",
.data = &init_net.sctp.cookie_preserve_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "cookie_hmac_alg",
.data = &init_net.sctp.sctp_hmac_alg,
.maxlen = 8,
.mode = 0644,
.proc_handler = proc_sctp_do_hmac_alg,
},
{
.procname = "valid_cookie_life",
.data = &init_net.sctp.valid_cookie_life,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
.extra2 = &timer_max
},
{
.procname = "sack_timeout",
.data = &init_net.sctp.sack_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &sack_timer_min,
.extra2 = &sack_timer_max,
},
{
.procname = "hb_interval",
.data = &init_net.sctp.hb_interval,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
.extra2 = &timer_max
},
{
.procname = "association_max_retrans",
.data = &init_net.sctp.max_retrans_association,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
.extra2 = SYSCTL_INT_MAX,
},
{
.procname = "path_max_retrans",
.data = &init_net.sctp.max_retrans_path,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
.extra2 = SYSCTL_INT_MAX,
},
{
.procname = "max_init_retransmits",
.data = &init_net.sctp.max_retrans_init,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
.extra2 = SYSCTL_INT_MAX,
},
{
.procname = "pf_retrans",
.data = &init_net.sctp.pf_retrans,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_INT_MAX,
},
{
.procname = "sndbuf_policy",
.data = &init_net.sctp.sndbuf_policy,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "rcvbuf_policy",
.data = &init_net.sctp.rcvbuf_policy,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "default_auto_asconf",
.data = &init_net.sctp.default_auto_asconf,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "addip_enable",
.data = &init_net.sctp.addip_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "addip_noauth_enable",
.data = &init_net.sctp.addip_noauth,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "prsctp_enable",
.data = &init_net.sctp.prsctp_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "reconf_enable",
.data = &init_net.sctp.reconf_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "auth_enable",
.data = &init_net.sctp.auth_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_sctp_do_auth,
},
{
.procname = "intl_enable",
.data = &init_net.sctp.intl_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "ecn_enable",
.data = &init_net.sctp.ecn_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "addr_scope_policy",
.data = &init_net.sctp.scope_policy,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = &addr_scope_max,
},
{
.procname = "rwnd_update_shift",
.data = &init_net.sctp.rwnd_upd_shift,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
.extra2 = &rwnd_scale_max,
},
{
.procname = "max_autoclose",
.data = &init_net.sctp.max_autoclose,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = &proc_doulongvec_minmax,
.extra1 = &max_autoclose_min,
.extra2 = &max_autoclose_max,
},
{
.procname = "pf_enable",
.data = &init_net.sctp.pf_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.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,
},
{ /* sentinel */ }
};
static int proc_sctp_do_hmac_alg(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;
bool changed = false;
char *none = "none";
char tmp[8] = {0};
int ret;
memset(&tbl, 0, sizeof(struct ctl_table));
if (write) {
tbl.data = tmp;
tbl.maxlen = sizeof(tmp);
} else {
tbl.data = net->sctp.sctp_hmac_alg ? : none;
tbl.maxlen = strlen(tbl.data);
}
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0) {
#ifdef CONFIG_CRYPTO_MD5
if (!strncmp(tmp, "md5", 3)) {
net->sctp.sctp_hmac_alg = "md5";
changed = true;
}
#endif
#ifdef CONFIG_CRYPTO_SHA1
if (!strncmp(tmp, "sha1", 4)) {
net->sctp.sctp_hmac_alg = "sha1";
changed = true;
}
#endif
if (!strncmp(tmp, "none", 4)) {
net->sctp.sctp_hmac_alg = NULL;
changed = true;
}
if (!changed)
ret = -EINVAL;
}
return ret;
}
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;
struct ctl_table tbl;
int ret, new_value;
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;
ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0) {
if (new_value > max || new_value < min)
return -EINVAL;
net->sctp.rto_min = new_value;
}
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;
struct ctl_table tbl;
int ret, new_value;
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;
ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0) {
if (new_value > max || new_value < min)
return -EINVAL;
net->sctp.rto_max = new_value;
}
return ret;
}
static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
if (write)
pr_warn_once("Changing rto_alpha or rto_beta may lead to "
"suboptimal rtt/srtt estimations!\n");
return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
}
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);
if (write && ret == 0) {
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;
}
int sctp_sysctl_net_register(struct net *net)
{
struct ctl_table *table;
int i;
table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
if (!table)
return -ENOMEM;
for (i = 0; table[i].data; i++)
table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
if (net->sctp.sysctl_header == NULL) {
kfree(table);
return -ENOMEM;
}
return 0;
}
void sctp_sysctl_net_unregister(struct net *net)
{
struct ctl_table *table;
table = net->sctp.sysctl_header->ctl_table_arg;
unregister_net_sysctl_table(net->sctp.sysctl_header);
kfree(table);
}
static struct ctl_table_header *sctp_sysctl_header;
/* Sysctl registration. */
void sctp_sysctl_register(void)
{
sctp_sysctl_header = register_net_sysctl(&init_net, "net/sctp", sctp_table);
}
/* Sysctl deregistration. */
void sctp_sysctl_unregister(void)
{
unregister_net_sysctl_table(sctp_sysctl_header);
}