linux_dsm_epyc7002/net/decnet/dn_fib.c

800 lines
19 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 21:07:57 +07:00
// SPDX-License-Identifier: GPL-2.0
/*
* DECnet An implementation of the DECnet protocol suite for the LINUX
* operating system. DECnet is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* DECnet Routing Forwarding Information Base (Glue/Info List)
*
* Author: Steve Whitehouse <SteveW@ACM.org>
*
*
* Changes:
* Alexey Kuznetsov : SMP locking changes
* Steve Whitehouse : Rewrote it... Well to be more correct, I
* copied most of it from the ipv4 fib code.
* Steve Whitehouse : Updated it in style and fixed a few bugs
* which were fixed in the ipv4 code since
* this code was copied from it.
*
*/
#include <linux/string.h>
#include <linux/net.h>
#include <linux/socket.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 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/sockios.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/netdevice.h>
#include <linux/timer.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/uaccess.h>
#include <net/neighbour.h>
#include <net/dst.h>
#include <net/flow.h>
#include <net/fib_rules.h>
#include <net/dn.h>
#include <net/dn_route.h>
#include <net/dn_fib.h>
#include <net/dn_neigh.h>
#include <net/dn_dev.h>
#include <net/rtnh.h>
#define RT_MIN_TABLE 1
#define for_fib_info() { struct dn_fib_info *fi;\
for(fi = dn_fib_info_list; fi; fi = fi->fib_next)
#define endfor_fib_info() }
#define for_nexthops(fi) { int nhsel; const struct dn_fib_nh *nh;\
for(nhsel = 0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++)
#define change_nexthops(fi) { int nhsel; struct dn_fib_nh *nh;\
for(nhsel = 0, nh = (struct dn_fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++)
#define endfor_nexthops(fi) }
static DEFINE_SPINLOCK(dn_fib_multipath_lock);
static struct dn_fib_info *dn_fib_info_list;
static DEFINE_SPINLOCK(dn_fib_info_lock);
static struct
{
int error;
u8 scope;
} dn_fib_props[RTN_MAX+1] = {
[RTN_UNSPEC] = { .error = 0, .scope = RT_SCOPE_NOWHERE },
[RTN_UNICAST] = { .error = 0, .scope = RT_SCOPE_UNIVERSE },
[RTN_LOCAL] = { .error = 0, .scope = RT_SCOPE_HOST },
[RTN_BROADCAST] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE },
[RTN_ANYCAST] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE },
[RTN_MULTICAST] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE },
[RTN_BLACKHOLE] = { .error = -EINVAL, .scope = RT_SCOPE_UNIVERSE },
[RTN_UNREACHABLE] = { .error = -EHOSTUNREACH, .scope = RT_SCOPE_UNIVERSE },
[RTN_PROHIBIT] = { .error = -EACCES, .scope = RT_SCOPE_UNIVERSE },
[RTN_THROW] = { .error = -EAGAIN, .scope = RT_SCOPE_UNIVERSE },
[RTN_NAT] = { .error = 0, .scope = RT_SCOPE_NOWHERE },
[RTN_XRESOLVE] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE },
};
static int dn_fib_sync_down(__le16 local, struct net_device *dev, int force);
static int dn_fib_sync_up(struct net_device *dev);
void dn_fib_free_info(struct dn_fib_info *fi)
{
if (fi->fib_dead == 0) {
printk(KERN_DEBUG "DECnet: BUG! Attempt to free alive dn_fib_info\n");
return;
}
change_nexthops(fi) {
if (nh->nh_dev)
dev_put(nh->nh_dev);
nh->nh_dev = NULL;
} endfor_nexthops(fi);
kfree(fi);
}
void dn_fib_release_info(struct dn_fib_info *fi)
{
spin_lock(&dn_fib_info_lock);
if (fi && --fi->fib_treeref == 0) {
if (fi->fib_next)
fi->fib_next->fib_prev = fi->fib_prev;
if (fi->fib_prev)
fi->fib_prev->fib_next = fi->fib_next;
if (fi == dn_fib_info_list)
dn_fib_info_list = fi->fib_next;
fi->fib_dead = 1;
dn_fib_info_put(fi);
}
spin_unlock(&dn_fib_info_lock);
}
static inline int dn_fib_nh_comp(const struct dn_fib_info *fi, const struct dn_fib_info *ofi)
{
const struct dn_fib_nh *onh = ofi->fib_nh;
for_nexthops(fi) {
if (nh->nh_oif != onh->nh_oif ||
nh->nh_gw != onh->nh_gw ||
nh->nh_scope != onh->nh_scope ||
nh->nh_weight != onh->nh_weight ||
((nh->nh_flags^onh->nh_flags)&~RTNH_F_DEAD))
return -1;
onh++;
} endfor_nexthops(fi);
return 0;
}
static inline struct dn_fib_info *dn_fib_find_info(const struct dn_fib_info *nfi)
{
for_fib_info() {
if (fi->fib_nhs != nfi->fib_nhs)
continue;
if (nfi->fib_protocol == fi->fib_protocol &&
nfi->fib_prefsrc == fi->fib_prefsrc &&
nfi->fib_priority == fi->fib_priority &&
memcmp(nfi->fib_metrics, fi->fib_metrics, sizeof(fi->fib_metrics)) == 0 &&
((nfi->fib_flags^fi->fib_flags)&~RTNH_F_DEAD) == 0 &&
(nfi->fib_nhs == 0 || dn_fib_nh_comp(fi, nfi) == 0))
return fi;
} endfor_fib_info();
return NULL;
}
static int dn_fib_count_nhs(const struct nlattr *attr)
{
struct rtnexthop *nhp = nla_data(attr);
int nhs = 0, nhlen = nla_len(attr);
while (rtnh_ok(nhp, nhlen)) {
nhs++;
nhp = rtnh_next(nhp, &nhlen);
}
/* leftover implies invalid nexthop configuration, discard it */
return nhlen > 0 ? 0 : nhs;
}
static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr,
const struct rtmsg *r)
{
struct rtnexthop *nhp = nla_data(attr);
int nhlen = nla_len(attr);
change_nexthops(fi) {
int attrlen;
if (!rtnh_ok(nhp, nhlen))
return -EINVAL;
nh->nh_flags = (r->rtm_flags&~0xFF) | nhp->rtnh_flags;
nh->nh_oif = nhp->rtnh_ifindex;
nh->nh_weight = nhp->rtnh_hops + 1;
attrlen = rtnh_attrlen(nhp);
if (attrlen > 0) {
struct nlattr *gw_attr;
gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY);
nh->nh_gw = gw_attr ? nla_get_le16(gw_attr) : 0;
}
nhp = rtnh_next(nhp, &nhlen);
} endfor_nexthops(fi);
return 0;
}
static int dn_fib_check_nh(const struct rtmsg *r, struct dn_fib_info *fi, struct dn_fib_nh *nh)
{
int err;
if (nh->nh_gw) {
struct flowidn fld;
struct dn_fib_res res;
if (nh->nh_flags&RTNH_F_ONLINK) {
struct net_device *dev;
if (r->rtm_scope >= RT_SCOPE_LINK)
return -EINVAL;
if (dnet_addr_type(nh->nh_gw) != RTN_UNICAST)
return -EINVAL;
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 01:56:21 +07:00
if ((dev = __dev_get_by_index(&init_net, nh->nh_oif)) == NULL)
return -ENODEV;
if (!(dev->flags&IFF_UP))
return -ENETDOWN;
nh->nh_dev = dev;
dev_hold(dev);
nh->nh_scope = RT_SCOPE_LINK;
return 0;
}
memset(&fld, 0, sizeof(fld));
fld.daddr = nh->nh_gw;
fld.flowidn_oif = nh->nh_oif;
fld.flowidn_scope = r->rtm_scope + 1;
if (fld.flowidn_scope < RT_SCOPE_LINK)
fld.flowidn_scope = RT_SCOPE_LINK;
if ((err = dn_fib_lookup(&fld, &res)) != 0)
return err;
err = -EINVAL;
if (res.type != RTN_UNICAST && res.type != RTN_LOCAL)
goto out;
nh->nh_scope = res.scope;
nh->nh_oif = DN_FIB_RES_OIF(res);
nh->nh_dev = DN_FIB_RES_DEV(res);
if (nh->nh_dev == NULL)
goto out;
dev_hold(nh->nh_dev);
err = -ENETDOWN;
if (!(nh->nh_dev->flags & IFF_UP))
goto out;
err = 0;
out:
dn_fib_res_put(&res);
return err;
} else {
struct net_device *dev;
if (nh->nh_flags&(RTNH_F_PERVASIVE|RTNH_F_ONLINK))
return -EINVAL;
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 01:56:21 +07:00
dev = __dev_get_by_index(&init_net, nh->nh_oif);
if (dev == NULL || dev->dn_ptr == NULL)
return -ENODEV;
if (!(dev->flags&IFF_UP))
return -ENETDOWN;
nh->nh_dev = dev;
dev_hold(nh->nh_dev);
nh->nh_scope = RT_SCOPE_HOST;
}
return 0;
}
struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct nlattr *attrs[],
const struct nlmsghdr *nlh, int *errp)
{
int err;
struct dn_fib_info *fi = NULL;
struct dn_fib_info *ofi;
int nhs = 1;
if (r->rtm_type > RTN_MAX)
goto err_inval;
if (dn_fib_props[r->rtm_type].scope > r->rtm_scope)
goto err_inval;
if (attrs[RTA_MULTIPATH] &&
(nhs = dn_fib_count_nhs(attrs[RTA_MULTIPATH])) == 0)
goto err_inval;
fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
err = -ENOBUFS;
if (fi == NULL)
goto failure;
fi->fib_protocol = r->rtm_protocol;
fi->fib_nhs = nhs;
fi->fib_flags = r->rtm_flags;
if (attrs[RTA_PRIORITY])
fi->fib_priority = nla_get_u32(attrs[RTA_PRIORITY]);
if (attrs[RTA_METRICS]) {
struct nlattr *attr;
int rem;
nla_for_each_nested(attr, attrs[RTA_METRICS], rem) {
int type = nla_type(attr);
if (type) {
if (type > RTAX_MAX || type == RTAX_CC_ALGO ||
nla_len(attr) < 4)
goto err_inval;
fi->fib_metrics[type-1] = nla_get_u32(attr);
}
}
}
if (attrs[RTA_PREFSRC])
fi->fib_prefsrc = nla_get_le16(attrs[RTA_PREFSRC]);
if (attrs[RTA_MULTIPATH]) {
if ((err = dn_fib_get_nhs(fi, attrs[RTA_MULTIPATH], r)) != 0)
goto failure;
if (attrs[RTA_OIF] &&
fi->fib_nh->nh_oif != nla_get_u32(attrs[RTA_OIF]))
goto err_inval;
if (attrs[RTA_GATEWAY] &&
fi->fib_nh->nh_gw != nla_get_le16(attrs[RTA_GATEWAY]))
goto err_inval;
} else {
struct dn_fib_nh *nh = fi->fib_nh;
if (attrs[RTA_OIF])
nh->nh_oif = nla_get_u32(attrs[RTA_OIF]);
if (attrs[RTA_GATEWAY])
nh->nh_gw = nla_get_le16(attrs[RTA_GATEWAY]);
nh->nh_flags = r->rtm_flags;
nh->nh_weight = 1;
}
if (r->rtm_type == RTN_NAT) {
if (!attrs[RTA_GATEWAY] || nhs != 1 || attrs[RTA_OIF])
goto err_inval;
fi->fib_nh->nh_gw = nla_get_le16(attrs[RTA_GATEWAY]);
goto link_it;
}
if (dn_fib_props[r->rtm_type].error) {
if (attrs[RTA_GATEWAY] || attrs[RTA_OIF] || attrs[RTA_MULTIPATH])
goto err_inval;
goto link_it;
}
if (r->rtm_scope > RT_SCOPE_HOST)
goto err_inval;
if (r->rtm_scope == RT_SCOPE_HOST) {
struct dn_fib_nh *nh = fi->fib_nh;
/* Local address is added */
if (nhs != 1 || nh->nh_gw)
goto err_inval;
nh->nh_scope = RT_SCOPE_NOWHERE;
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 01:56:21 +07:00
nh->nh_dev = dev_get_by_index(&init_net, fi->fib_nh->nh_oif);
err = -ENODEV;
if (nh->nh_dev == NULL)
goto failure;
} else {
change_nexthops(fi) {
if ((err = dn_fib_check_nh(r, fi, nh)) != 0)
goto failure;
} endfor_nexthops(fi)
}
if (fi->fib_prefsrc) {
if (r->rtm_type != RTN_LOCAL || !attrs[RTA_DST] ||
fi->fib_prefsrc != nla_get_le16(attrs[RTA_DST]))
if (dnet_addr_type(fi->fib_prefsrc) != RTN_LOCAL)
goto err_inval;
}
link_it:
if ((ofi = dn_fib_find_info(fi)) != NULL) {
fi->fib_dead = 1;
dn_fib_free_info(fi);
ofi->fib_treeref++;
return ofi;
}
fi->fib_treeref++;
refcount_set(&fi->fib_clntref, 1);
spin_lock(&dn_fib_info_lock);
fi->fib_next = dn_fib_info_list;
fi->fib_prev = NULL;
if (dn_fib_info_list)
dn_fib_info_list->fib_prev = fi;
dn_fib_info_list = fi;
spin_unlock(&dn_fib_info_lock);
return fi;
err_inval:
err = -EINVAL;
failure:
*errp = err;
if (fi) {
fi->fib_dead = 1;
dn_fib_free_info(fi);
}
return NULL;
}
int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn *fld, struct dn_fib_res *res)
{
int err = dn_fib_props[type].error;
if (err == 0) {
if (fi->fib_flags & RTNH_F_DEAD)
return 1;
res->fi = fi;
switch (type) {
case RTN_NAT:
DN_FIB_RES_RESET(*res);
refcount_inc(&fi->fib_clntref);
return 0;
case RTN_UNICAST:
case RTN_LOCAL:
for_nexthops(fi) {
if (nh->nh_flags & RTNH_F_DEAD)
continue;
if (!fld->flowidn_oif ||
fld->flowidn_oif == nh->nh_oif)
break;
}
if (nhsel < fi->fib_nhs) {
res->nh_sel = nhsel;
refcount_inc(&fi->fib_clntref);
return 0;
}
endfor_nexthops(fi);
res->fi = NULL;
return 1;
default:
net_err_ratelimited("DECnet: impossible routing event : dn_fib_semantic_match type=%d\n",
type);
res->fi = NULL;
return -EINVAL;
}
}
return err;
}
void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res)
{
struct dn_fib_info *fi = res->fi;
int w;
spin_lock_bh(&dn_fib_multipath_lock);
if (fi->fib_power <= 0) {
int power = 0;
change_nexthops(fi) {
if (!(nh->nh_flags&RTNH_F_DEAD)) {
power += nh->nh_weight;
nh->nh_power = nh->nh_weight;
}
} endfor_nexthops(fi);
fi->fib_power = power;
if (power < 0) {
spin_unlock_bh(&dn_fib_multipath_lock);
res->nh_sel = 0;
return;
}
}
w = jiffies % fi->fib_power;
change_nexthops(fi) {
if (!(nh->nh_flags&RTNH_F_DEAD) && nh->nh_power) {
if ((w -= nh->nh_power) <= 0) {
nh->nh_power--;
fi->fib_power--;
res->nh_sel = nhsel;
spin_unlock_bh(&dn_fib_multipath_lock);
return;
}
}
} endfor_nexthops(fi);
res->nh_sel = 0;
spin_unlock_bh(&dn_fib_multipath_lock);
}
static inline u32 rtm_get_table(struct nlattr *attrs[], u8 table)
{
if (attrs[RTA_TABLE])
table = nla_get_u32(attrs[RTA_TABLE]);
return table;
}
static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct dn_fib_table *tb;
struct rtmsg *r = nlmsg_data(nlh);
struct nlattr *attrs[RTA_MAX+1];
int err;
if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 19:07:28 +07:00
err = nlmsg_parse_deprecated(nlh, sizeof(*r), attrs, RTA_MAX,
rtm_dn_policy, extack);
if (err < 0)
return err;
tb = dn_fib_get_table(rtm_get_table(attrs, r->rtm_table), 0);
if (!tb)
return -ESRCH;
return tb->delete(tb, r, attrs, nlh, &NETLINK_CB(skb));
}
static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct dn_fib_table *tb;
struct rtmsg *r = nlmsg_data(nlh);
struct nlattr *attrs[RTA_MAX+1];
int err;
if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 19:07:28 +07:00
err = nlmsg_parse_deprecated(nlh, sizeof(*r), attrs, RTA_MAX,
rtm_dn_policy, extack);
if (err < 0)
return err;
tb = dn_fib_get_table(rtm_get_table(attrs, r->rtm_table), 1);
if (!tb)
return -ENOBUFS;
return tb->insert(tb, r, attrs, nlh, &NETLINK_CB(skb));
}
static void fib_magic(int cmd, int type, __le16 dst, int dst_len, struct dn_ifaddr *ifa)
{
struct dn_fib_table *tb;
struct {
struct nlmsghdr nlh;
struct rtmsg rtm;
} req;
struct {
struct nlattr hdr;
__le16 dst;
} dst_attr = {
.dst = dst,
};
struct {
struct nlattr hdr;
__le16 prefsrc;
} prefsrc_attr = {
.prefsrc = ifa->ifa_local,
};
struct {
struct nlattr hdr;
u32 oif;
} oif_attr = {
.oif = ifa->ifa_dev->dev->ifindex,
};
struct nlattr *attrs[RTA_MAX+1] = {
[RTA_DST] = (struct nlattr *) &dst_attr,
[RTA_PREFSRC] = (struct nlattr * ) &prefsrc_attr,
[RTA_OIF] = (struct nlattr *) &oif_attr,
};
memset(&req.rtm, 0, sizeof(req.rtm));
if (type == RTN_UNICAST)
tb = dn_fib_get_table(RT_MIN_TABLE, 1);
else
tb = dn_fib_get_table(RT_TABLE_LOCAL, 1);
if (tb == NULL)
return;
req.nlh.nlmsg_len = sizeof(req);
req.nlh.nlmsg_type = cmd;
req.nlh.nlmsg_flags = NLM_F_REQUEST|NLM_F_CREATE|NLM_F_APPEND;
req.nlh.nlmsg_pid = 0;
req.nlh.nlmsg_seq = 0;
req.rtm.rtm_dst_len = dst_len;
req.rtm.rtm_table = tb->n;
req.rtm.rtm_protocol = RTPROT_KERNEL;
req.rtm.rtm_scope = (type != RTN_LOCAL ? RT_SCOPE_LINK : RT_SCOPE_HOST);
req.rtm.rtm_type = type;
if (cmd == RTM_NEWROUTE)
tb->insert(tb, &req.rtm, attrs, &req.nlh, NULL);
else
tb->delete(tb, &req.rtm, attrs, &req.nlh, NULL);
}
static void dn_fib_add_ifaddr(struct dn_ifaddr *ifa)
{
fib_magic(RTM_NEWROUTE, RTN_LOCAL, ifa->ifa_local, 16, ifa);
#if 0
if (!(dev->flags&IFF_UP))
return;
/* In the future, we will want to add default routes here */
#endif
}
static void dn_fib_del_ifaddr(struct dn_ifaddr *ifa)
{
int found_it = 0;
struct net_device *dev;
struct dn_dev *dn_db;
struct dn_ifaddr *ifa2;
ASSERT_RTNL();
/* Scan device list */
rcu_read_lock();
for_each_netdev_rcu(&init_net, dev) {
dn_db = rcu_dereference(dev->dn_ptr);
if (dn_db == NULL)
continue;
for (ifa2 = rcu_dereference(dn_db->ifa_list);
ifa2 != NULL;
ifa2 = rcu_dereference(ifa2->ifa_next)) {
if (ifa2->ifa_local == ifa->ifa_local) {
found_it = 1;
break;
}
}
}
rcu_read_unlock();
if (found_it == 0) {
fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 16, ifa);
if (dnet_addr_type(ifa->ifa_local) != RTN_LOCAL) {
if (dn_fib_sync_down(ifa->ifa_local, NULL, 0))
dn_fib_flush();
}
}
}
static void dn_fib_disable_addr(struct net_device *dev, int force)
{
if (dn_fib_sync_down(0, dev, force))
dn_fib_flush();
dn_rt_cache_flush(0);
neigh_ifdown(&dn_neigh_table, dev);
}
static int dn_fib_dnaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct dn_ifaddr *ifa = (struct dn_ifaddr *)ptr;
switch (event) {
case NETDEV_UP:
dn_fib_add_ifaddr(ifa);
dn_fib_sync_up(ifa->ifa_dev->dev);
dn_rt_cache_flush(-1);
break;
case NETDEV_DOWN:
dn_fib_del_ifaddr(ifa);
if (ifa->ifa_dev && ifa->ifa_dev->ifa_list == NULL) {
dn_fib_disable_addr(ifa->ifa_dev->dev, 1);
} else {
dn_rt_cache_flush(-1);
}
break;
}
return NOTIFY_DONE;
}
static int dn_fib_sync_down(__le16 local, struct net_device *dev, int force)
{
int ret = 0;
int scope = RT_SCOPE_NOWHERE;
if (force)
scope = -1;
for_fib_info() {
/*
* This makes no sense for DECnet.... we will almost
* certainly have more than one local address the same
* over all our interfaces. It needs thinking about
* some more.
*/
if (local && fi->fib_prefsrc == local) {
fi->fib_flags |= RTNH_F_DEAD;
ret++;
} else if (dev && fi->fib_nhs) {
int dead = 0;
change_nexthops(fi) {
if (nh->nh_flags&RTNH_F_DEAD)
dead++;
else if (nh->nh_dev == dev &&
nh->nh_scope != scope) {
spin_lock_bh(&dn_fib_multipath_lock);
nh->nh_flags |= RTNH_F_DEAD;
fi->fib_power -= nh->nh_power;
nh->nh_power = 0;
spin_unlock_bh(&dn_fib_multipath_lock);
dead++;
}
} endfor_nexthops(fi)
if (dead == fi->fib_nhs) {
fi->fib_flags |= RTNH_F_DEAD;
ret++;
}
}
} endfor_fib_info();
return ret;
}
static int dn_fib_sync_up(struct net_device *dev)
{
int ret = 0;
if (!(dev->flags&IFF_UP))
return 0;
for_fib_info() {
int alive = 0;
change_nexthops(fi) {
if (!(nh->nh_flags&RTNH_F_DEAD)) {
alive++;
continue;
}
if (nh->nh_dev == NULL || !(nh->nh_dev->flags&IFF_UP))
continue;
if (nh->nh_dev != dev || dev->dn_ptr == NULL)
continue;
alive++;
spin_lock_bh(&dn_fib_multipath_lock);
nh->nh_power = 0;
nh->nh_flags &= ~RTNH_F_DEAD;
spin_unlock_bh(&dn_fib_multipath_lock);
} endfor_nexthops(fi);
if (alive > 0) {
fi->fib_flags &= ~RTNH_F_DEAD;
ret++;
}
} endfor_fib_info();
return ret;
}
static struct notifier_block dn_fib_dnaddr_notifier = {
.notifier_call = dn_fib_dnaddr_event,
};
void __exit dn_fib_cleanup(void)
{
dn_fib_table_cleanup();
dn_fib_rules_cleanup();
unregister_dnaddr_notifier(&dn_fib_dnaddr_notifier);
}
void __init dn_fib_init(void)
{
dn_fib_table_init();
dn_fib_rules_init();
register_dnaddr_notifier(&dn_fib_dnaddr_notifier);
rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_NEWROUTE,
dn_fib_rtm_newroute, NULL, 0);
rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_DELROUTE,
dn_fib_rtm_delroute, NULL, 0);
}