* Re: [PATCH bpf-next] bpf_load: add map name to load_maps error message
From: Daniel Borkmann @ 2018-11-07 21:41 UTC (permalink / raw)
To: Song Liu, John Fastabend
Cc: shannon.nelson, Alexei Starovoitov, Networking,
shannon.lee.nelson
In-Reply-To: <CAPhsuW4-zJ=2QPUW7rz-rq3KHm_YJ3SnPTHVbddY5tZi3TjEwg@mail.gmail.com>
On 11/07/2018 01:26 AM, Song Liu wrote:
> On Mon, Oct 29, 2018 at 3:12 PM John Fastabend <john.fastabend@gmail.com> wrote:
>>
>> On 10/29/2018 02:14 PM, Shannon Nelson wrote:
>>> To help when debugging bpf/xdp load issues, have the load_map()
>>> error message include the number and name of the map that
>>> failed.
>>>
>>> Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
>>> ---
>>> samples/bpf/bpf_load.c | 4 ++--
>>> 1 file changed, 2 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
>>> index 89161c9..5de0357 100644
>>> --- a/samples/bpf/bpf_load.c
>>> +++ b/samples/bpf/bpf_load.c
>>> @@ -282,8 +282,8 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps,
>>> numa_node);
>>> }
>>> if (map_fd[i] < 0) {
>>> - printf("failed to create a map: %d %s\n",
>>> - errno, strerror(errno));
>>> + printf("failed to create map %d (%s): %d %s\n",
>>> + i, maps[i].name, errno, strerror(errno));
>>> return 1;
>>> }
>>> maps[i].fd = map_fd[i];
>>>
>>
>> LGTM
>>
>> Acked-by: John Fastabend <john.fastabend@gmail.com>
>
> Acked-by: Song Liu <songliubraving@fb.com>
Applied to bpf-next, thanks!
^ permalink raw reply
* Re: [PATCH bpf-next] xdp: sample code for redirecting vlan packets to specific cpus
From: Daniel Borkmann @ 2018-11-07 21:44 UTC (permalink / raw)
To: John Fastabend, Shannon Nelson, ast
Cc: netdev, eric.dumazet, silviu.smarandache, shannon.lee.nelson
In-Reply-To: <499cc6e8-f533-3b90-b053-b3a1c7fa3a15@gmail.com>
On 10/29/2018 11:11 PM, John Fastabend wrote:
> On 10/29/2018 02:19 PM, Shannon Nelson wrote:
>> This is an example of using XDP to redirect the processing of
>> particular vlan packets to specific CPUs. This is in response
>> to comments received on a kernel patch put forth previously
>> to do something similar using RPS.
>> https://www.spinics.net/lists/netdev/msg528210.html
>> [PATCH net-next] net: enable RPS on vlan devices
>>
>> This XDP application watches for inbound vlan-tagged packets
>> and redirects those packets to be processed on a specific CPU
>> as configured in a BPF map. The BPF map can be modified by
>> this user program, which can also load and unload the kernel
>> XDP code.
>>
>> One example use is for supporting VMs where we can't control the
>> OS being used: we'd like to separate the VM CPU processing from
>> the host's CPUs as a way to help mitigate L1TF related issues.
>> When running the VM's traffic on a vlan we can stick the host's
>> Rx processing on one set of CPUs separate from the VM's CPUs.
>>
>> This example currently uses a vlan key and cpu value in the
>> BPF map, so only can do one CPU per vlan. This could easily
>> be modified to use a bitpattern of CPUs rather than a CPU id
>> to allow multiple CPUs per vlan.
>
> Great, so does this solve your use case then? At least on drivers
> with XDP support?
>
>>
>> Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
>> ---
>
> Some really small and trivial nits below.
>
> Acked-by: John Fastabend <john.fastabend@gmail.com>
>
> [...]
>
>> + if (install) {
>> +
>
> new line probably not needed.
>
>> + /* check to see if already installed */
>> + errno = 0;
>> + access(pin_prog_name, R_OK);
>> + if (errno != ENOENT) {
>> + fprintf(stderr, "ERR: %s is already installed\n", argv[0]);
>> + return -1;
>> + }
>> +
>> + /* load the XDP program and maps with the convenient library */
>> + if (load_bpf_file(filename)) {
>> + fprintf(stderr, "ERR: load_bpf_file(%s): \n%s",
>> + filename, bpf_log_buf);
>> + return -1;
>> + }
>> + if (!prog_fd[0]) {
>> + fprintf(stderr, "ERR: load_bpf_file(%s): %d %s\n",
>> + filename, errno, strerror(errno));
>> + return -1;
>> + }
>> +
>> + /* pin the XDP program and maps */
>> + if (bpf_obj_pin(prog_fd[0], pin_prog_name) < 0) {
>> + fprintf(stderr, "ERR: bpf_obj_pin(%s): %d %s\n",
>> + pin_prog_name, errno, strerror(errno));
>> + if (errno == 2)
>> + fprintf(stderr, " (is the BPF fs mounted on /sys/fs/bpf?)\n");
>> + return -1;
>> + }
>> + if (bpf_obj_pin(map_fd[0], pin_vlanmap_name) < 0) {
>> + fprintf(stderr, "ERR: bpf_obj_pin(%s): %d %s\n",
>> + pin_vlanmap_name, errno, strerror(errno));
>> + return -1;
>> + }
>> + if (bpf_obj_pin(map_fd[2], pin_countermap_name) < 0) {
>> + fprintf(stderr, "ERR: bpf_obj_pin(%s): %d %s\n",
>> + pin_countermap_name, errno, strerror(errno));
>> + return -1;
>> + }
>> +
>> + /* prep the vlan map with "not used" values */
>> + c64 = UNDEF_CPU;
>> + for (v64 = 0; v64 < 4096; v64++) {
>
> maybe #define MAX_VLANS 4096 just to avoid constants.
>
>> + if (bpf_map_update_elem(map_fd[0], &v64, &c64, 0)) {
>> + fprintf(stderr, "ERR: preping vlan map failed on v=%llu: %d %s\n",
>> + v64, errno, strerror(errno));
>> + return -1;
>> + }
>> + }
>> +
>> + /* prep the cpumap with queue sizes */
>> + c64 = 128+64; /* see note in xdp_redirect_cpu_user.c */
>> + for (v64 = 0; v64 < MAX_CPUS; v64++) {
>> + if (bpf_map_update_elem(map_fd[1], &v64, &c64, 0)) {
>> + if (errno == ENODEV) {
>> + /* Save the last CPU number attempted
>> + * into the counters map
>> + */
>> + c64 = CPU_COUNT;
>> + ret = bpf_map_update_elem(map_fd[2], &c64, &v64, 0);
>> + break;
>> + }
>> +
>> + fprintf(stderr, "ERR: preping cpu map failed on v=%llu: %d %s\n",
>> + v64, errno, strerror(errno));
>> + return -1;
>> + }
>> + }
>> +
>> + /* wire the XDP program to the device */
>> + if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], 0) < 0) {
>> + fprintf(stderr, "ERR: bpf_set_link_xdp_fd(): %d %s\n",
>> + errno, strerror(errno));
>> + return -1;
>> + }
>> +
>> + return 0;
>> + }
>> +
>> + if (remove) {
>> +
Ditto
>> + /* unlink the program from the device */
>> + if (bpf_set_link_xdp_fd(ifindex, -1, 0) < 0)
>> + fprintf(stderr, "ERR: bpf_set_link_xdp_fd(): %d %s\n",
>> + errno, strerror(errno));
>> +
>> + /* unlink pinned files */
>> + if (unlink(pin_prog_name))
>> + fprintf(stderr, "ERR: unlink(%s): %d %s\n",
>> + pin_prog_name, errno, strerror(errno));
>> + if (unlink(pin_vlanmap_name))
>> + fprintf(stderr, "ERR: unlink(%s): %d %s\n",
>> + pin_vlanmap_name, errno, strerror(errno));
>> + if (unlink(pin_countermap_name))
>> + fprintf(stderr, "ERR: unlink(%s): %d %s\n",
>> + pin_countermap_name, errno, strerror(errno));
>> +
>> + return 0;
>> + }
>> +
>> + if (vlan == 0) {
>> + fprintf(stderr, "ERR: required option --vlan missing\n");
>> + goto error;
>> + }
>> +
>> + if (cpu == MAX_CPUS && vlan > 0) {
>> + fprintf(stderr, "ERR: required option --cpu missing\n");
>> + goto error;
>> + }
>> +
>> + vfd = bpf_obj_get(pin_vlanmap_name);
>> + if (vfd < 0) {
>> + fprintf(stderr, "ERR: can't find pinned map %s: %d %s\n",
>> + pin_vlanmap_name, errno, strerror(errno));
>> + if (errno == ENOENT)
>> + fprintf(stderr, " (has %s been installed yet?)\n", argv[0]);
>> + return -1;
>> + }
>> +
>> + /* decode the requested action */
>> + if (vlan > 0) {
>> + /* check cpu against the max value found */
>> + cfd = bpf_obj_get(pin_countermap_name);
>> + if (cfd < 0) {
>> + fprintf(stderr, "ERR: can't find pinned map %s: %d %s\n",
>> + pin_countermap_name, errno, strerror(errno));
>> + return -1;
>> + }
>> + c64 = CPU_COUNT;
>> + ret = bpf_map_lookup_elem(cfd, &c64, &v64);
>> + if (cpu >= v64) {
>
> Need to check ret code?
Yeah, I expect this would have another respin, thanks!
>> + fprintf(stderr, "ERR: cpu %d greater than max %llu\n", cpu, v64);
>> + return -1;
>> + }
>> +
>> + /* Note that the value and key pointers really do need to be
>> + * pointers to 64-bit values, else things get a bit muddled.
>> + */
>> + v64 = vlan;
>> + c64 = cpu;
>> + ret = bpf_map_update_elem(vfd, &v64, &c64, 0);
>> + if (ret) {
>> + fprintf(stderr, "Adding vlan %d CPU %d failed: %d %s\n",
>> + vlan, cpu, errno, strerror(errno));
>> + return -1;
>> + }
>> +
>> + } else {
>> + v64 = -vlan;
>> + c64 = UNDEF_CPU;
>> +
>> + /* We can't actually delete from a TYPE_ARRAY map, so we
>> + * simply set it to an undefined value.
>> + */
>> + ret = bpf_map_update_elem(vfd, &v64, &c64, 0);
>> + if (ret) {
>> + fprintf(stderr, "Delete of vlan %llu failed: %d %s\n",
>> + v64, errno, strerror(errno));
>> + return -1;
>> + }
>> + }
>> +
>> + return 0;
>> +
>> +error:
>> + usage(argv);
>> + return -1;
>> +}
>>
>
^ permalink raw reply
* Re: [PATCH bpf-next v2 02/13] bpf: btf: Add BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO
From: Alexei Starovoitov @ 2018-11-07 21:49 UTC (permalink / raw)
To: Edward Cree
Cc: Martin Lau, Yonghong Song, Alexei Starovoitov,
daniel@iogearbox.net, netdev@vger.kernel.org, Kernel Team
In-Reply-To: <2ea1e869-5f28-6beb-9fb1-15ae5a396077@solarflare.com>
On Wed, Nov 07, 2018 at 07:29:31PM +0000, Edward Cree wrote:
> Whereas I don't, and I don't feel like my core criticisms have
> been addressed _at all_. The only answer I get to "BTF should
> store type and instance information in separate records" is
> "it's a debuginfo",
...
> I am just trying to organise
> BTF to consist of separate _parts_ for types and instances,
> rather than forcing both into the same Procrustean bed.
BTF does not have and should not have instances.
BTF is debug info only.
This is not negotiable.
Loading BTF into the kernel does not create an instance of anything.
The kernel verifies BTF and BTF blob sits there waiting to be pointed at
by the actual instance.
Today these instances are maps and programs.
A single program can have multiple instances of the functions
which debug info is described in BTF.
Multiple prograrms (with multiple functions) can point
to the same BTF blob description.
Consider that in single C file there will be multliple functions,
many maps, global variables (in the future) they will be created
by individual prog_load/map_create syscalls.
Before that the _single_ blob of BTF data for the whole C file
will be loaded, since functions, maps share most of
the type and name information.
In elf files the instances of functions have names.
These names go into symbol table of the elf. Dynamic linker
is using these symbols to connect different instances.
In BPF world we use IDs to connect instances.
There is btd if, map id, prog id.
You can argue that bpf_prog_load has prog_name attribute.
So the instance of the program sort of have name already,
but this name is for debug only. It doesn't have to be unique
and the kernel is not relying on the name to connect instances.
Example:
1: int foo(struct __sk_buff *skb, char arg2)
2: {
3: return skb->len;
4: }
Line 1 goes into BTF to describe the function (with names and types).
Line 1 also goes into line_info .BTF.ext elf section as a string.
Line 3 and 4 go into line_info as well as strings.
llvm compiles it into something:
.text
.globl foo
.type foo, @function
foo:
r0 = *(u32 *)(r1 + 0)
exit
.section .BTF
.byte X
.byte Y
.section .BTF.ext
.byte X
.byte Y
That 'foo' name goes into symbol table and together with the body
form the future instance of the function.
libbpf takes 'foo' from symbol table of elf and passes it
as bpf_attr.prog_name to the kernel along with bpf instructions
to create an instance.
The name 'foo' in symbol table doesn't have to match with
BTF 'foo' name and '.*foo.*' substring in line_info.
If you decide to use the sequence:
"""
.globl foo
.type foo, @function
foo:
""
in your ebpf_asm to parse and store into BTF as a function name
I would strongly argue against, since it would be incorrectly
conflating the instance of the function with debug purpose
of BTF.
Right now we do not have a concrete proposal for assembler text of BTF.
When LLVM emits BTF into .s it emits them as raw bytes.
So I'm looking forward to your ideas how to describe BTF in .s
Note such .s must have freedom to describe 'int bar(struct __sk_buff *a1, char a2)'
as debug info while having '.globl foo; foo:' as symbol name.
Your other 'criticism' was about libbpf's bpf_map_find_btf_info()
and ____btf_map_* hack. Yes. It is a hack and I'm open to change it
if there are better suggestions. It's a convention between
libbpf and program writers that produce elf. It's not a kernel abi.
Nothing to do with BTF and this instance vs debug info discussion.
> (I don't feel like we're making progress in understanding one
> another here; maybe we should have a telephone discussion?
> Sadly I'm not going to Plumbers, else that would be the
> perfect place to thrash this out.)
Happy to jump on the call to explain it again.
10:30am pacific time works for me tomorrow.
^ permalink raw reply
* Re: [PATCH bpf] bpf: Fix IPv6 dport byte order in bpf_sk_lookup_udp
From: Joe Stringer @ 2018-11-07 21:51 UTC (permalink / raw)
To: rdna; +Cc: netdev, ast, daniel, Joe Stringer, kernel-team
In-Reply-To: <20181107213607.2658130-1-rdna@fb.com>
On Wed, 7 Nov 2018 at 13:37, Andrey Ignatov <rdna@fb.com> wrote:
>
> Lookup functions in sk_lookup have different expectations about byte
> order of provided arguments.
>
> Specifically __inet_lookup, __udp4_lib_lookup and __udp6_lib_lookup
> expect dport to be in network byte order and do ntohs(dport) internally.
>
> At the same time __inet6_lookup expects dport to be in host byte order
> and correspondingly name the argument hnum.
>
> sk_lookup works correctly with __inet_lookup, __udp4_lib_lookup and
> __inet6_lookup with regard to dport. But in __udp6_lib_lookup case it
> uses host instead of expected network byte order. It makes result
> returned by bpf_sk_lookup_udp for IPv6 incorrect.
>
> The patch fixes byte order of dport passed to __udp6_lib_lookup.
>
> Originally sk_lookup properly handled UDPv6, but not TCPv6. 5ef0ae84f02a
> fixes TCPv6 but breaks UDPv6.
>
> Fixes: 5ef0ae84f02a ("bpf: Fix IPv6 dport byte-order in bpf_sk_lookup")
> Signed-off-by: Andrey Ignatov <rdna@fb.com>
Thanks for the fix, makes sense.
Acked-by: Joe Stringer <joe@wand.net.nz>
^ permalink raw reply
* Re: [PATCH bpf] bpf: Fix IPv6 dport byte order in bpf_sk_lookup_udp
From: Martin Lau @ 2018-11-07 21:55 UTC (permalink / raw)
To: Andrey Ignatov
Cc: netdev@vger.kernel.org, ast@kernel.org, daniel@iogearbox.net,
joe@wand.net.nz, Kernel Team
In-Reply-To: <20181107213607.2658130-1-rdna@fb.com>
On Wed, Nov 07, 2018 at 01:36:07PM -0800, Andrey Ignatov wrote:
> Lookup functions in sk_lookup have different expectations about byte
> order of provided arguments.
>
> Specifically __inet_lookup, __udp4_lib_lookup and __udp6_lib_lookup
> expect dport to be in network byte order and do ntohs(dport) internally.
>
> At the same time __inet6_lookup expects dport to be in host byte order
> and correspondingly name the argument hnum.
>
> sk_lookup works correctly with __inet_lookup, __udp4_lib_lookup and
> __inet6_lookup with regard to dport. But in __udp6_lib_lookup case it
> uses host instead of expected network byte order. It makes result
> returned by bpf_sk_lookup_udp for IPv6 incorrect.
>
> The patch fixes byte order of dport passed to __udp6_lib_lookup.
>
> Originally sk_lookup properly handled UDPv6, but not TCPv6. 5ef0ae84f02a
> fixes TCPv6 but breaks UDPv6.
>
> Fixes: 5ef0ae84f02a ("bpf: Fix IPv6 dport byte-order in bpf_sk_lookup")
> Signed-off-by: Andrey Ignatov <rdna@fb.com>
Good catch.
Acked-by: Martin KaFai Lau <kafai@fb.com>
> ---
> net/core/filter.c | 5 ++---
> 1 file changed, 2 insertions(+), 3 deletions(-)
>
> diff --git a/net/core/filter.c b/net/core/filter.c
> index e521c5ebc7d1..9a1327eb25fa 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -4852,18 +4852,17 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
> } else {
> struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
> struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
> - u16 hnum = ntohs(tuple->ipv6.dport);
> int sdif = inet6_sdif(skb);
>
> if (proto == IPPROTO_TCP)
> sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
> src6, tuple->ipv6.sport,
> - dst6, hnum,
> + dst6, ntohs(tuple->ipv6.dport),
> dif, sdif, &refcounted);
> else if (likely(ipv6_bpf_stub))
> sk = ipv6_bpf_stub->udp6_lib_lookup(net,
> src6, tuple->ipv6.sport,
> - dst6, hnum,
> + dst6, tuple->ipv6.dport,
> dif, sdif,
> &udp_table, skb);
> #endif
> --
> 2.17.1
>
^ permalink raw reply
* [PATCH ipsec-next 00/11] xfrm: policy: add inexact policy search tree
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev
This series attempts to improve xfrm policy lookup performance when
a lot of (several hundred or even thousands) inexact policies exist
on a system.
On insert, a policy is either placed in hash table (all direct (/32 for
ipv4, /128 policies, or all policies matching a user-configured threshold).
All other policies get inserted into inexact list as per priority.
Lookup then scans inexact list for first matching entry.
This series instead makes it so that inexact policy is added to exactly
one of four different search list classes.
1. "Any:Any" list, containing policies where both saddr and daddr are
wildcards or have very coarse prefixes, e.g. 10.0.0.0/8 and the like.
2. "saddr:any" list, containing policies with a fixed saddr/prefixlen,
but without destination restrictions.
These lists are stored in rbtree nodes; each node contains those
policies matching saddr/prefixlen.
3. "Any:daddr" list. Similar to 2), except for policies where only the
destinations are specified.
4. "saddr:daddr" lists, containing policies that match the given
source/destination network.
The root of the saddr/daddr tree is stored in the nodes of the
'daddr' tree.
This diagram illustrates the list classes, and their
placement in the lookup hierarchy:
xfrm_pol_inexact_bin = hash(dir,type,family,if_id);
|
+---- root_d: sorted by daddr:prefix
| |
| xfrm_pol_inexact_node
| |
| +- root: sorted by saddr/prefix
| | |
| | xfrm_pol_inexact_node
| | |
| | + root: unused
| | |
| | + hhead: saddr:daddr policies
| |
| +- coarse policies and all any:daddr policies
|
+---- root_s: sorted by saddr:prefix
| |
| xfrm_pol_inexact_node
| |
| + root: unused
| |
| + hhead: saddr:any policies
|
+---- coarse policies and all any:any policies
First we obtain inexact bin by hashing direction, family and other 'must
match' criteria.
Next, we search root_d using packets' destination ip address.
If we find a matching node, we search that nodes' source address tree
using packets src address.
We also search the bins root_s tree using packets source address.
This initial lookup now has created a 'candidate set' consisting
of up to four hlist heads to the four search classes.
Each list gets scanned for first matching entry.
Out of those up the one with the highest priority is chosen.
In case several policies had same priority, most recent one is used to
match old behaviour.
Locking rules:
insert requires net->xfrm.xfrm_policy_lock spinlock held + BH off
(no change to current kernel).
Insert/removal of a tree node needs increment of its sequence count.
lookup requires rcu read lock, lookups in a tree need to sample
the sequence count of the bin that tree is located in as well and
re-try in case it has changed.
Results on my kvm test setup, using 4 netns:
# 1.2 1.1 3.1 3.10 2.1 2.2
# eth1 eth1 veth0 veth0 eth1 eth1
# ns1 ---- ns3 ----- ns4 ---- ns2
ns3 and ns4 are connected via ipsec tunnel.
'Dummy policies' below means that i created 1k non-matching
policies in both ns3 and ns4.
20 parallel netperf (mbits, unidirectional TCP_STREAM):
normal:
993.518000 (no dummy policies)
796.32 (with dummy policies)
patched:
991.335 (no dummy policies)
989.684 (with dummy policies)
20 parallel TCP_RR, trans. per second:
normal:
32413.930000 (no dummy policies)
17725.970000 (with dummy policies)
patched:
32314.51 (no dummy policies)
32326.190000 (with dummy policies)
caveats:
1. Won't work unless large part of policies have no common saddr/daddr pairs.
Extreme example: adding 10k 0.0.0.0/0 -> 0.0.0.0/0
policies may require search of all policies, just like current kernel.
2. The policy add sequence
a daddr 10.0.0.0/26
b daddr 10.0.0.64/26
c daddr 10.0.0.0/24
When c gets added, search nodes for a and b have to be merged with
the new subnet, as it contains both.
This also means that a single policy rule with a small subnet value
can cause severe tree degradation and thus longer search lists.
3. Causes (small) performance degradation when setup only has few policies.
4. Policies need an additional hlist, as MIGRATE doesn't consider if_id,
but the patchset makes the if_id part of the initial hash lookup.
Could be avoided by not considering if_id as part of initial bin lookup,
but then increases list length a lot when we have lots of xfrm interfaces.
5. In oder to solve 'two matching candidates have same priority, which
takes precedence?' problem I added a number to xfrm_policy struct that
maps to its index in the complete inexact list.
This was necessary to make sure same sequence of policy-add commands
keeps on returning same lookup result compared to older kernel.
This work doesn't prevent us from re-adding a new flow caching scheme,
but so far i found no good solution (all have various DoS or degradation
issues).
Comments or questions welcome.
Florian Westphal (11):
selftests: add xfrm policy test script
xfrm: security: iterate all, not inexact lists
xfrm: policy: split list insertion into a helper
xfrm: policy: return NULL when inexact search needed
xfrm: policy: store inexact policies in an rhashtable
xfrm: policy: consider if_id when hashing inexact policy
xfrm: policy: add inexact policy search tree infrastructure
xfrm: policy: store inexact policies in a tree ordered by destination address
xfrm: policy: check reinserted policies match their node
xfrm: policy: store inexact policies in a tree ordered by source address
xfrm: policy: add 2nd-level saddr trees for inexact policies
include/net/netns/xfrm.h | 2
include/net/xfrm.h | 3
net/xfrm/xfrm_policy.c | 1234 ++++++++++++++++++++++++++---
tools/testing/selftests/net/Makefile | 3
tools/testing/selftests/net/xfrm_policy.sh | 276 ++++++
5 files changed, 1391 insertions(+), 127 deletions(-)
^ permalink raw reply
* [PATCH ipsec-next 01/11] selftests: add xfrm policy test script
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
add a script that adds a ipsec tunnel between two network
namespaces plus following policies:
.0/24 -> ipsec tunnel
.240/28 -> bypass
.253/32 -> ipsec tunnel
Then check that .254 bypasses tunnel (match /28 exception),
and .2 (match /24) and .253 (match direct policy) pass through the
tunnel.
Abuses iptables to check if ping did resolve an ipsec policy or not.
Also adds a bunch of 'block' rules that are not supposed to match.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
tools/testing/selftests/net/Makefile | 3 +-
tools/testing/selftests/net/xfrm_policy.sh | 276 +++++++++++++++++++++
2 files changed, 278 insertions(+), 1 deletion(-)
create mode 100755 tools/testing/selftests/net/xfrm_policy.sh
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 256d82d5fa87..4c7df17d4f42 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -4,7 +4,8 @@
CFLAGS = -Wall -Wl,--no-as-needed -O2 -g
CFLAGS += -I../../../../usr/include/
-TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
+TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \
+ rtnetlink.sh xfrm_policy.sh
TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
TEST_PROGS_EXTENDED := in_netns.sh
diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh
new file mode 100755
index 000000000000..72f9e3dfbea1
--- /dev/null
+++ b/tools/testing/selftests/net/xfrm_policy.sh
@@ -0,0 +1,276 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check xfrm policy resolution. Topology:
+#
+# 1.2 1.1 3.1 3.10 2.1 2.2
+# eth1 eth1 veth0 veth0 eth1 eth1
+# ns1 ---- ns3 ----- ns4 ---- ns2
+#
+# ns3 and ns4 are connected via ipsec tunnel.
+# pings from ns1 to ns2 (and vice versa) are supposed to work like this:
+# ns1: ping 10.0.2.2: passes via ipsec tunnel.
+# ns2: ping 10.0.1.2: passes via ipsec tunnel.
+
+# ns1: ping 10.0.1.253: passes via ipsec tunnel (direct policy)
+# ns2: ping 10.0.2.253: passes via ipsec tunnel (direct policy)
+#
+# ns1: ping 10.0.2.254: does NOT pass via ipsec tunnel (exception)
+# ns2: ping 10.0.1.254: does NOT pass via ipsec tunnel (exception)
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+KEY_SHA=0xdeadbeef1234567890abcdefabcdefabcdefabcd
+KEY_AES=0x0123456789abcdef0123456789012345
+SPI1=0x1
+SPI2=0x2
+
+do_esp() {
+ local ns=$1
+ local me=$2
+ local remote=$3
+ local lnet=$4
+ local rnet=$5
+ local spi_out=$6
+ local spi_in=$7
+
+ ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet
+ ip -net $ns xfrm state add src $me dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet
+
+ # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
+ ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow
+ # to fwd decrypted packets after esp processing:
+ ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow
+}
+
+do_exception() {
+ local ns=$1
+ local me=$2
+ local remote=$3
+ local encryptip=$4
+ local plain=$5
+
+ # network $plain passes without tunnel
+ ip -net $ns xfrm policy add dst $plain dir out priority 10 action allow
+
+ # direct policy for $encryptip, use tunnel, higher prio takes precedence
+ ip -net $ns xfrm policy add dst $encryptip dir out tmpl src $me dst $remote proto esp mode tunnel priority 1 action allow
+}
+
+# policies that are not supposed to match any packets generated in this test.
+do_dummies4() {
+ local ns=$1
+
+ for i in $(seq 10 16);do
+ # dummy policy with wildcard src/dst.
+ echo netns exec $ns ip xfrm policy add src 0.0.0.0/0 dst 10.$i.99.0/30 dir out action block
+ echo netns exec $ns ip xfrm policy add src 10.$i.99.0/30 dst 0.0.0.0/0 dir out action block
+ for j in $(seq 32 64);do
+ echo netns exec $ns ip xfrm policy add src 10.$i.1.0/30 dst 10.$i.$j.0/30 dir out action block
+ # silly, as it encompasses the one above too, but its allowed:
+ echo netns exec $ns ip xfrm policy add src 10.$i.1.0/29 dst 10.$i.$j.0/29 dir out action block
+ # and yet again, even more broad one.
+ echo netns exec $ns ip xfrm policy add src 10.$i.1.0/24 dst 10.$i.$j.0/24 dir out action block
+ echo netns exec $ns ip xfrm policy add src 10.$i.$j.0/24 dst 10.$i.1.0/24 dir fwd action block
+ done
+ done | ip -batch /dev/stdin
+}
+
+do_dummies6() {
+ local ns=$1
+
+ for i in $(seq 10 16);do
+ for j in $(seq 32 64);do
+ echo netns exec $ns ip xfrm policy add src dead:$i::/64 dst dead:$i:$j::/64 dir out action block
+ echo netns exec $ns ip xfrm policy add src dead:$i:$j::/64 dst dead:$i::/24 dir fwd action block
+ done
+ done | ip -batch /dev/stdin
+}
+
+check_ipt_policy_count()
+{
+ ns=$1
+
+ ip netns exec $ns iptables-save -c |grep policy | ( read c rest
+ ip netns exec $ns iptables -Z
+ if [ x"$c" = x'[0:0]' ]; then
+ exit 0
+ elif [ x"$c" = x ]; then
+ echo "ERROR: No counters"
+ ret=1
+ exit 111
+ else
+ exit 1
+ fi
+ )
+}
+
+check_xfrm() {
+ # 0: iptables -m policy rule count == 0
+ # 1: iptables -m policy rule count != 0
+ rval=$1
+ ip=$2
+ ret=0
+
+ ip netns exec ns1 ping -q -c 1 10.0.2.$ip > /dev/null
+
+ check_ipt_policy_count ns3
+ if [ $? -ne $rval ] ; then
+ ret=1
+ fi
+ check_ipt_policy_count ns4
+ if [ $? -ne $rval ] ; then
+ ret=1
+ fi
+
+ ip netns exec ns2 ping -q -c 1 10.0.1.$ip > /dev/null
+
+ check_ipt_policy_count ns3
+ if [ $? -ne $rval ] ; then
+ ret=1
+ fi
+ check_ipt_policy_count ns4
+ if [ $? -ne $rval ] ; then
+ ret=1
+ fi
+
+ return $ret
+}
+
+#check for needed privileges
+if [ "$(id -u)" -ne 0 ];then
+ echo "SKIP: Need root privileges"
+ exit $ksft_skip
+fi
+
+ip -Version 2>/dev/null >/dev/null
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without the ip tool"
+ exit $ksft_skip
+fi
+
+# needed to check if policy lookup got valid ipsec result
+iptables --version 2>/dev/null >/dev/null
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without iptables tool"
+ exit $ksft_skip
+fi
+
+for i in 1 2 3 4; do
+ ip netns add ns$i
+ ip -net ns$i link set lo up
+done
+
+DEV=veth0
+ip link add $DEV netns ns1 type veth peer name eth1 netns ns3
+ip link add $DEV netns ns2 type veth peer name eth1 netns ns4
+
+ip link add $DEV netns ns3 type veth peer name veth0 netns ns4
+
+DEV=veth0
+for i in 1 2; do
+ ip -net ns$i link set $DEV up
+ ip -net ns$i addr add 10.0.$i.2/24 dev $DEV
+ ip -net ns$i addr add dead:$i::2/64 dev $DEV
+
+ ip -net ns$i addr add 10.0.$i.253 dev $DEV
+ ip -net ns$i addr add 10.0.$i.254 dev $DEV
+ ip -net ns$i addr add dead:$i::fd dev $DEV
+ ip -net ns$i addr add dead:$i::fe dev $DEV
+done
+
+for i in 3 4; do
+ip -net ns$i link set eth1 up
+ip -net ns$i link set veth0 up
+done
+
+ip -net ns1 route add default via 10.0.1.1
+ip -net ns2 route add default via 10.0.2.1
+
+ip -net ns3 addr add 10.0.1.1/24 dev eth1
+ip -net ns3 addr add 10.0.3.1/24 dev veth0
+ip -net ns3 addr add 2001:1::1/64 dev eth1
+ip -net ns3 addr add 2001:3::1/64 dev veth0
+
+ip -net ns3 route add default via 10.0.3.10
+
+ip -net ns4 addr add 10.0.2.1/24 dev eth1
+ip -net ns4 addr add 10.0.3.10/24 dev veth0
+ip -net ns4 addr add 2001:2::1/64 dev eth1
+ip -net ns4 addr add 2001:3::10/64 dev veth0
+ip -net ns4 route add default via 10.0.3.1
+
+for j in 4 6; do
+ for i in 3 4;do
+ ip netns exec ns$i sysctl net.ipv$j.conf.eth1.forwarding=1 > /dev/null
+ ip netns exec ns$i sysctl net.ipv$j.conf.veth0.forwarding=1 > /dev/null
+ done
+done
+
+# abuse iptables rule counter to check if ping matches a policy
+ip netns exec ns3 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
+ip netns exec ns4 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not insert iptables rule"
+ for i in 1 2 3 4;do ip netns del ns$i;done
+ exit $ksft_skip
+fi
+
+# localip remoteip localnet remotenet
+do_esp ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+do_esp ns3 dead:3::1 dead:3::10 dead:1::/64 dead:2::/64 $SPI1 $SPI2
+do_esp ns4 10.0.3.10 10.0.3.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+do_esp ns4 dead:3::10 dead:3::1 dead:2::/64 dead:1::/64 $SPI2 $SPI1
+
+do_dummies4 ns3
+do_dummies6 ns4
+
+# ping to .254 should use ipsec, exception is not installed.
+check_xfrm 1 254
+if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .254 to use ipsec tunnel"
+ ret=1
+else
+ echo "PASS: policy before exception matches"
+fi
+
+# installs exceptions
+# localip remoteip encryptdst plaindst
+do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28
+do_exception ns4 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28
+
+do_exception ns3 dead:3::1 dead:3::10 dead:2::fd dead:2:f0::/96
+do_exception ns4 dead:3::10 dead:3::1 dead:1::fd dead:1:f0::/96
+
+# ping to .254 should now be excluded from the tunnel
+check_xfrm 0 254
+if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .254 to fail"
+ ret=1
+else
+ echo "PASS: ping to .254 bypassed ipsec tunnel"
+fi
+
+# ping to .253 should use use ipsec due to direct policy exception.
+check_xfrm 1 253
+if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .253 to use ipsec tunnel"
+ ret=1
+else
+ echo "PASS: direct policy matches"
+fi
+
+# ping to .2 should use ipsec.
+check_xfrm 1 2
+if [ $? -ne 0 ]; then
+ echo "FAIL: expected ping to .2 to use ipsec tunnel"
+ ret=1
+else
+ echo "PASS: policy matches"
+fi
+
+for i in 1 2 3 4;do ip netns del ns$i;done
+
+exit $ret
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 02/11] xfrm: security: iterate all, not inexact lists
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
currently all non-socket policies are either hashed in the dst table,
or placed on the 'inexact list'. When flushing, we first walk the
table, then the (per-direction) inexact lists.
When we try and get rid of the inexact lists to having "n" inexact
lists (e.g. per-af inexact lists, or sorted into a tree), this walk
would become more complicated.
Simplify this: walk the 'all' list and skip socket policies during
traversal so we don't need to handle exact and inexact policies
separately anymore.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/xfrm/xfrm_policy.c | 93 ++++++++++++------------------------------
1 file changed, 26 insertions(+), 67 deletions(-)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 119a427d9b2b..39d0db2a50d9 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -892,36 +892,19 @@ EXPORT_SYMBOL(xfrm_policy_byid);
static inline int
xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
{
- int dir, err = 0;
+ struct xfrm_policy *pol;
+ int err = 0;
- for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
- struct xfrm_policy *pol;
- int i;
+ list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+ if (pol->walk.dead ||
+ xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX ||
+ pol->type != type)
+ continue;
- hlist_for_each_entry(pol,
- &net->xfrm.policy_inexact[dir], bydst) {
- if (pol->type != type)
- continue;
- err = security_xfrm_policy_delete(pol->security);
- if (err) {
- xfrm_audit_policy_delete(pol, 0, task_valid);
- return err;
- }
- }
- for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) {
- hlist_for_each_entry(pol,
- net->xfrm.policy_bydst[dir].table + i,
- bydst) {
- if (pol->type != type)
- continue;
- err = security_xfrm_policy_delete(
- pol->security);
- if (err) {
- xfrm_audit_policy_delete(pol, 0,
- task_valid);
- return err;
- }
- }
+ err = security_xfrm_policy_delete(pol->security);
+ if (err) {
+ xfrm_audit_policy_delete(pol, 0, task_valid);
+ return err;
}
}
return err;
@@ -937,6 +920,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
{
int dir, err = 0, cnt = 0;
+ struct xfrm_policy *pol;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
@@ -944,46 +928,21 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
if (err)
goto out;
- for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
- struct xfrm_policy *pol;
- int i;
-
- again1:
- hlist_for_each_entry(pol,
- &net->xfrm.policy_inexact[dir], bydst) {
- if (pol->type != type)
- continue;
- __xfrm_policy_unlink(pol, dir);
- spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
- cnt++;
-
- xfrm_audit_policy_delete(pol, 1, task_valid);
-
- xfrm_policy_kill(pol);
-
- spin_lock_bh(&net->xfrm.xfrm_policy_lock);
- goto again1;
- }
-
- for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) {
- again2:
- hlist_for_each_entry(pol,
- net->xfrm.policy_bydst[dir].table + i,
- bydst) {
- if (pol->type != type)
- continue;
- __xfrm_policy_unlink(pol, dir);
- spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
- cnt++;
-
- xfrm_audit_policy_delete(pol, 1, task_valid);
- xfrm_policy_kill(pol);
-
- spin_lock_bh(&net->xfrm.xfrm_policy_lock);
- goto again2;
- }
- }
+again:
+ list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+ dir = xfrm_policy_id2dir(pol->index);
+ if (pol->walk.dead ||
+ dir >= XFRM_POLICY_MAX ||
+ pol->type != type)
+ continue;
+ __xfrm_policy_unlink(pol, dir);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+ cnt++;
+ xfrm_audit_policy_delete(pol, 1, task_valid);
+ xfrm_policy_kill(pol);
+ spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+ goto again;
}
if (!cnt)
err = -ESRCH;
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 03/11] xfrm: policy: split list insertion into a helper
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
... so we can reuse this later without code duplication when we add
policy to a second inexact list.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/xfrm/xfrm_policy.c | 43 ++++++++++++++++++++++++++----------------
1 file changed, 27 insertions(+), 16 deletions(-)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 39d0db2a50d9..20d6815be0d7 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -740,18 +740,12 @@ static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
return false;
}
-int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
+static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
+ struct xfrm_policy *policy,
+ bool excl)
{
- struct net *net = xp_net(policy);
- struct xfrm_policy *pol;
- struct xfrm_policy *delpol;
- struct hlist_head *chain;
- struct hlist_node *newpos;
+ struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL;
- spin_lock_bh(&net->xfrm.xfrm_policy_lock);
- chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
- delpol = NULL;
- newpos = NULL;
hlist_for_each_entry(pol, chain, bydst) {
if (pol->type == policy->type &&
pol->if_id == policy->if_id &&
@@ -759,24 +753,41 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
xfrm_policy_mark_match(policy, pol) &&
xfrm_sec_ctx_match(pol->security, policy->security) &&
!WARN_ON(delpol)) {
- if (excl) {
- spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
- return -EEXIST;
- }
+ if (excl)
+ return ERR_PTR(-EEXIST);
delpol = pol;
if (policy->priority > pol->priority)
continue;
} else if (policy->priority >= pol->priority) {
- newpos = &pol->bydst;
+ newpos = pol;
continue;
}
if (delpol)
break;
}
if (newpos)
- hlist_add_behind_rcu(&policy->bydst, newpos);
+ hlist_add_behind_rcu(&policy->bydst, &newpos->bydst);
else
hlist_add_head_rcu(&policy->bydst, chain);
+
+ return delpol;
+}
+
+int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
+{
+ struct net *net = xp_net(policy);
+ struct xfrm_policy *delpol;
+ struct hlist_head *chain;
+
+ spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+ chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
+ delpol = xfrm_policy_insert_list(chain, policy, excl);
+
+ if (IS_ERR(delpol)) {
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+ return PTR_ERR(delpol);
+ }
+
__xfrm_policy_link(policy, dir);
/* After previous checking, family can either be AF_INET or AF_INET6 */
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 04/11] xfrm: policy: return NULL when inexact search needed
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
currently policy_hash_bysel() returns the hash bucket list
(for exact policies), or the inexact list (when policy uses a prefix).
Searching this inexact list is slow, so it might be better to pre-sort
inexact lists into a tree or another data structure for faster
searching.
However, due to 'any' policies, that need to be searched in any case,
doing so will require that 'inexact' policies need to be handled
specially to decide the best search strategy. So change hash_bysel()
and return NULL if the policy can't be handled via the policy hash
table.
Right now, we simply use the inexact list when this happens, but
future patch can then implement a different strategy.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/xfrm/xfrm_policy.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 20d6815be0d7..b00c265f6be3 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -365,7 +365,7 @@ static struct hlist_head *policy_hash_bysel(struct net *net,
hash = __sel_hash(sel, family, hmask, dbits, sbits);
if (hash == hmask + 1)
- return &net->xfrm.policy_inexact[dir];
+ return NULL;
return rcu_dereference_check(net->xfrm.policy_bydst[dir].table,
lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash;
@@ -625,6 +625,8 @@ static void xfrm_hash_rebuild(struct work_struct *work)
chain = policy_hash_bysel(net, &policy->selector,
policy->family,
xfrm_policy_id2dir(policy->index));
+ if (!chain)
+ chain = &net->xfrm.policy_inexact[dir];
hlist_for_each_entry(pol, chain, bydst) {
if (policy->priority >= pol->priority)
newpos = &pol->bydst;
@@ -781,7 +783,12 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
- delpol = xfrm_policy_insert_list(chain, policy, excl);
+ if (chain) {
+ delpol = xfrm_policy_insert_list(chain, policy, excl);
+ } else {
+ chain = &net->xfrm.policy_inexact[dir];
+ delpol = xfrm_policy_insert_list(chain, policy, excl);
+ }
if (IS_ERR(delpol)) {
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
@@ -829,6 +836,8 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
*err = 0;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, sel, sel->family, dir);
+ if (!chain)
+ chain = &net->xfrm.policy_inexact[dir];
ret = NULL;
hlist_for_each_entry(pol, chain, bydst) {
if (pol->type == type &&
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 05/11] xfrm: policy: store inexact policies in an rhashtable
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
Switch packet-path lookups for inexact policies to rhashtable.
In this initial version, we now no longer need to search policies with
non-matching address family and type.
Next patch will add the if_id as well so lookups from the xfrm interface
driver only need to search inexact policies for that device.
Future patches will augment the hlist in each rhash bucket with a tree
and pre-sort policies according to daddr/prefix.
A single rhashtable is used. In order to avoid a full rhashtable walk on
netns exit, the bins get placed on a pernet list, i.e. we add almost no
cost for network namespaces that had no xfrm policies.
The inexact lists are kept in place, and policies are added to both the
per-rhash-inexact list and a pernet one.
The latter is needed for the control plane to handle migrate -- these
requests do not consider the if_id, so if we'd remove the inexact_list
now we would have to search all hash buckets and then figure
out which matching policy candidate is the most recent one -- this appears
a bit harder than just keeping the 'old' inexact list for this purpose.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/netns/xfrm.h | 2 +
include/net/xfrm.h | 1 +
net/xfrm/xfrm_policy.c | 350 +++++++++++++++++++++++++++++++++++++--
3 files changed, 335 insertions(+), 18 deletions(-)
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 9991e5ef52cc..59f45b1e9dac 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -5,6 +5,7 @@
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
+#include <linux/rhashtable-types.h>
#include <linux/xfrm.h>
#include <net/dst_ops.h>
@@ -53,6 +54,7 @@ struct netns_xfrm {
unsigned int policy_count[XFRM_POLICY_MAX * 2];
struct work_struct policy_hash_work;
struct xfrm_policy_hthresh policy_hthresh;
+ struct list_head inexact_bins;
struct sock *nlsk;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 0eb390c205af..870fa9b27f7e 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -596,6 +596,7 @@ struct xfrm_policy {
u16 family;
struct xfrm_sec_ctx *security;
struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH];
+ struct hlist_node bydst_inexact_list;
struct rcu_head rcu;
};
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b00c265f6be3..5c7e7399323f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -26,6 +26,7 @@
#include <linux/cache.h>
#include <linux/cpu.h>
#include <linux/audit.h>
+#include <linux/rhashtable.h>
#include <net/dst.h>
#include <net/flow.h>
#include <net/xfrm.h>
@@ -45,6 +46,22 @@ struct xfrm_flo {
u8 flags;
};
+struct xfrm_pol_inexact_key {
+ possible_net_t net;
+ u16 family;
+ u8 dir, type;
+};
+
+struct xfrm_pol_inexact_bin {
+ struct xfrm_pol_inexact_key k;
+ struct rhash_head head;
+ struct hlist_head hhead;
+
+ /* slow path below */
+ struct list_head inexact_bins;
+ struct rcu_head rcu;
+};
+
static DEFINE_SPINLOCK(xfrm_if_cb_lock);
static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
@@ -55,6 +72,9 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
static struct kmem_cache *xfrm_dst_cache __ro_after_init;
static __read_mostly seqcount_t xfrm_policy_hash_generation;
+static struct rhashtable xfrm_policy_inexact_table;
+static const struct rhashtable_params xfrm_pol_inexact_params;
+
static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr);
static int stale_bundle(struct dst_entry *dst);
static int xfrm_bundle_ok(struct xfrm_dst *xdst);
@@ -64,6 +84,18 @@ static void __xfrm_policy_link(struct xfrm_policy *pol, int dir);
static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
int dir);
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir);
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup_rcu(struct net *net,
+ u8 type, u16 family, u8 dir);
+static struct xfrm_policy *
+xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
+ bool excl);
+static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
+ struct xfrm_policy *policy);
+
static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy)
{
return refcount_inc_not_zero(&policy->refcnt);
@@ -269,6 +301,7 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
if (policy) {
write_pnet(&policy->xp_net, net);
INIT_LIST_HEAD(&policy->walk.all);
+ INIT_HLIST_NODE(&policy->bydst_inexact_list);
INIT_HLIST_NODE(&policy->bydst);
INIT_HLIST_NODE(&policy->byidx);
rwlock_init(&policy->lock);
@@ -563,6 +596,107 @@ static void xfrm_hash_resize(struct work_struct *work)
mutex_unlock(&hash_resize_mutex);
}
+static void xfrm_hash_reset_inexact_table(struct net *net)
+{
+ struct xfrm_pol_inexact_bin *b;
+
+ lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+ list_for_each_entry(b, &net->xfrm.inexact_bins, inexact_bins)
+ INIT_HLIST_HEAD(&b->hhead);
+}
+
+/* Make sure *pol can be inserted into fastbin.
+ * Useful to check that later insert requests will be sucessful
+ * (provided xfrm_policy_lock is held throughout).
+ */
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
+{
+ struct xfrm_pol_inexact_bin *bin, *prev;
+ struct xfrm_pol_inexact_key k = {
+ .family = pol->family,
+ .type = pol->type,
+ .dir = dir,
+ };
+ struct net *net = xp_net(pol);
+
+ lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+ write_pnet(&k.net, net);
+ bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k,
+ xfrm_pol_inexact_params);
+ if (bin)
+ return bin;
+
+ bin = kzalloc(sizeof(*bin), GFP_ATOMIC);
+ if (!bin)
+ return NULL;
+
+ bin->k = k;
+ INIT_HLIST_HEAD(&bin->hhead);
+
+ prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
+ &bin->k, &bin->head,
+ xfrm_pol_inexact_params);
+ if (!prev) {
+ list_add(&bin->inexact_bins, &net->xfrm.inexact_bins);
+ return bin;
+ }
+
+ kfree(bin);
+
+ return IS_ERR(prev) ? NULL : prev;
+}
+
+static void xfrm_policy_inexact_delete_bin(struct net *net,
+ struct xfrm_pol_inexact_bin *b)
+{
+ lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+ if (!hlist_empty(&b->hhead))
+ return;
+
+ if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head,
+ xfrm_pol_inexact_params) == 0) {
+ list_del(&b->inexact_bins);
+ kfree_rcu(b, rcu);
+ }
+}
+
+static void __xfrm_policy_inexact_flush(struct net *net)
+{
+ struct xfrm_pol_inexact_bin *bin;
+
+ lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+ list_for_each_entry(bin, &net->xfrm.inexact_bins, inexact_bins)
+ xfrm_policy_inexact_delete_bin(net, bin);
+}
+
+static struct xfrm_policy *
+xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
+{
+ struct xfrm_pol_inexact_bin *bin;
+ struct xfrm_policy *delpol;
+ struct hlist_head *chain;
+ struct net *net;
+
+ bin = xfrm_policy_inexact_alloc_bin(policy, dir);
+ if (!bin)
+ return ERR_PTR(-ENOMEM);
+
+ delpol = xfrm_policy_insert_list(&bin->hhead, policy, excl);
+ if (delpol && excl)
+ return ERR_PTR(-EEXIST);
+
+ net = xp_net(policy);
+ chain = &net->xfrm.policy_inexact[dir];
+ xfrm_policy_insert_inexact_list(chain, policy);
+
+ return delpol;
+}
+
static void xfrm_hash_rebuild(struct work_struct *work)
{
struct net *net = container_of(work, struct net,
@@ -592,7 +726,45 @@ static void xfrm_hash_rebuild(struct work_struct *work)
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+ /* make sure that we can insert the indirect policies again before
+ * we start with destructive action.
+ */
+ list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) {
+ u8 dbits, sbits;
+
+ dir = xfrm_policy_id2dir(policy->index);
+ if (policy->walk.dead || dir >= XFRM_POLICY_MAX)
+ continue;
+
+ if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
+ if (policy->family == AF_INET) {
+ dbits = rbits4;
+ sbits = lbits4;
+ } else {
+ dbits = rbits6;
+ sbits = lbits6;
+ }
+ } else {
+ if (policy->family == AF_INET) {
+ dbits = lbits4;
+ sbits = rbits4;
+ } else {
+ dbits = lbits6;
+ sbits = rbits6;
+ }
+ }
+
+ if (policy->selector.prefixlen_d < dbits ||
+ policy->selector.prefixlen_s < sbits)
+ continue;
+
+ if (!xfrm_policy_inexact_alloc_bin(policy, dir))
+ goto out_unlock;
+ }
+
/* reset the bydst and inexact table in all directions */
+ xfrm_hash_reset_inexact_table(net);
+
for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
hmask = net->xfrm.policy_bydst[dir].hmask;
@@ -625,8 +797,13 @@ static void xfrm_hash_rebuild(struct work_struct *work)
chain = policy_hash_bysel(net, &policy->selector,
policy->family,
xfrm_policy_id2dir(policy->index));
- if (!chain)
- chain = &net->xfrm.policy_inexact[dir];
+ if (!chain) {
+ void *p = xfrm_policy_inexact_insert(policy, dir, 0);
+
+ WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p));
+ continue;
+ }
+
hlist_for_each_entry(pol, chain, bydst) {
if (policy->priority >= pol->priority)
newpos = &pol->bydst;
@@ -639,6 +816,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
hlist_add_head_rcu(&policy->bydst, chain);
}
+out_unlock:
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
mutex_unlock(&hash_resize_mutex);
@@ -742,6 +920,84 @@ static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
return false;
}
+static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
+{
+ const struct xfrm_pol_inexact_key *k = data;
+ u32 a = k->type << 24 | k->dir << 16 | k->family;
+
+ return jhash_2words(a, net_hash_mix(read_pnet(&k->net)), seed);
+}
+
+static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed)
+{
+ const struct xfrm_pol_inexact_bin *b = data;
+
+ return xfrm_pol_bin_key(&b->k, 0, seed);
+}
+
+static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg,
+ const void *ptr)
+{
+ const struct xfrm_pol_inexact_key *key = arg->key;
+ const struct xfrm_pol_inexact_bin *b = ptr;
+ int ret;
+
+ if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net)))
+ return -1;
+
+ ret = b->k.dir ^ key->dir;
+ if (ret)
+ return ret;
+
+ ret = b->k.type ^ key->type;
+ if (ret)
+ return ret;
+
+ ret = b->k.family ^ key->family;
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static const struct rhashtable_params xfrm_pol_inexact_params = {
+ .head_offset = offsetof(struct xfrm_pol_inexact_bin, head),
+ .hashfn = xfrm_pol_bin_key,
+ .obj_hashfn = xfrm_pol_bin_obj,
+ .obj_cmpfn = xfrm_pol_bin_cmp,
+ .automatic_shrinking = true,
+};
+
+static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
+ struct xfrm_policy *policy)
+{
+ struct xfrm_policy *pol, *delpol = NULL;
+ struct hlist_node *newpos = NULL;
+
+ hlist_for_each_entry(pol, chain, bydst_inexact_list) {
+ if (pol->type == policy->type &&
+ pol->if_id == policy->if_id &&
+ !selector_cmp(&pol->selector, &policy->selector) &&
+ xfrm_policy_mark_match(policy, pol) &&
+ xfrm_sec_ctx_match(pol->security, policy->security) &&
+ !WARN_ON(delpol)) {
+ delpol = pol;
+ if (policy->priority > pol->priority)
+ continue;
+ } else if (policy->priority >= pol->priority) {
+ newpos = &pol->bydst_inexact_list;
+ continue;
+ }
+ if (delpol)
+ break;
+ }
+
+ if (newpos)
+ hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
+ else
+ hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
+}
+
static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
struct xfrm_policy *policy,
bool excl)
@@ -767,6 +1023,7 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
if (delpol)
break;
}
+
if (newpos)
hlist_add_behind_rcu(&policy->bydst, &newpos->bydst);
else
@@ -783,12 +1040,10 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
- if (chain) {
+ if (chain)
delpol = xfrm_policy_insert_list(chain, policy, excl);
- } else {
- chain = &net->xfrm.policy_inexact[dir];
- delpol = xfrm_policy_insert_list(chain, policy, excl);
- }
+ else
+ delpol = xfrm_policy_inexact_insert(policy, dir, excl);
if (IS_ERR(delpol)) {
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
@@ -830,14 +1085,24 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
struct xfrm_sec_ctx *ctx, int delete,
int *err)
{
- struct xfrm_policy *pol, *ret;
+ struct xfrm_pol_inexact_bin *bin = NULL;
+ struct xfrm_policy *pol, *ret = NULL;
struct hlist_head *chain;
*err = 0;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, sel, sel->family, dir);
- if (!chain)
- chain = &net->xfrm.policy_inexact[dir];
+ if (!chain) {
+ bin = xfrm_policy_inexact_lookup(net, type,
+ sel->family, dir);
+ if (!bin) {
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+ return NULL;
+ }
+
+ chain = &bin->hhead;
+ }
+
ret = NULL;
hlist_for_each_entry(pol, chain, bydst) {
if (pol->type == type &&
@@ -854,6 +1119,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
return pol;
}
__xfrm_policy_unlink(pol, dir);
+ xfrm_policy_inexact_delete_bin(net, bin);
}
ret = pol;
break;
@@ -964,7 +1230,9 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
goto again;
}
- if (!cnt)
+ if (cnt)
+ __xfrm_policy_inexact_flush(net);
+ else
err = -ESRCH;
out:
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
@@ -1063,21 +1331,50 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
if (match)
ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid,
dir);
-
return ret;
}
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir)
+{
+ struct xfrm_pol_inexact_key k = {
+ .family = family,
+ .type = type,
+ .dir = dir,
+ };
+
+ write_pnet(&k.net, net);
+
+ return rhashtable_lookup(&xfrm_policy_inexact_table, &k,
+ xfrm_pol_inexact_params);
+}
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir)
+{
+ struct xfrm_pol_inexact_bin *bin;
+
+ lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+ rcu_read_lock();
+ bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir);
+ rcu_read_unlock();
+
+ return bin;
+}
+
static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
const struct flowi *fl,
u16 family, u8 dir,
u32 if_id)
{
- int err;
- struct xfrm_policy *pol, *ret;
const xfrm_address_t *daddr, *saddr;
+ struct xfrm_pol_inexact_bin *bin;
+ struct xfrm_policy *pol, *ret;
struct hlist_head *chain;
unsigned int sequence;
u32 priority;
+ int err;
daddr = xfrm_flowi_daddr(fl, family);
saddr = xfrm_flowi_saddr(fl, family);
@@ -1108,7 +1405,10 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
break;
}
}
- chain = &net->xfrm.policy_inexact[dir];
+ bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir);
+ if (!bin)
+ goto skip_inexact;
+ chain = &bin->hhead;
hlist_for_each_entry_rcu(pol, chain, bydst) {
if ((pol->priority >= priority) && ret)
break;
@@ -1127,6 +1427,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
}
}
+skip_inexact:
if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence))
goto retry;
@@ -1218,6 +1519,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
/* Socket policies are not hashed. */
if (!hlist_unhashed(&pol->bydst)) {
hlist_del_rcu(&pol->bydst);
+ hlist_del_init(&pol->bydst_inexact_list);
hlist_del(&pol->byidx);
}
@@ -2795,13 +3097,17 @@ static void xfrm_statistics_fini(struct net *net)
static int __net_init xfrm_policy_init(struct net *net)
{
unsigned int hmask, sz;
- int dir;
+ int dir, err;
- if (net_eq(net, &init_net))
+ if (net_eq(net, &init_net)) {
xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache",
sizeof(struct xfrm_dst),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
NULL);
+ err = rhashtable_init(&xfrm_policy_inexact_table,
+ &xfrm_pol_inexact_params);
+ BUG_ON(err);
+ }
hmask = 8 - 1;
sz = (hmask+1) * sizeof(struct hlist_head);
@@ -2836,6 +3142,7 @@ static int __net_init xfrm_policy_init(struct net *net)
seqlock_init(&net->xfrm.policy_hthresh.lock);
INIT_LIST_HEAD(&net->xfrm.policy_all);
+ INIT_LIST_HEAD(&net->xfrm.inexact_bins);
INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
return 0;
@@ -2854,6 +3161,7 @@ static int __net_init xfrm_policy_init(struct net *net)
static void xfrm_policy_fini(struct net *net)
{
+ struct xfrm_pol_inexact_bin *bin, *tmp;
unsigned int sz;
int dir;
@@ -2879,6 +3187,12 @@ static void xfrm_policy_fini(struct net *net)
sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head);
WARN_ON(!hlist_empty(net->xfrm.policy_byidx));
xfrm_hash_free(net->xfrm.policy_byidx, sz);
+
+ list_for_each_entry_safe(bin, tmp, &net->xfrm.inexact_bins,
+ inexact_bins) {
+ WARN_ON(!hlist_empty(&bin->hhead));
+ xfrm_policy_inexact_delete_bin(net, bin);
+ }
}
static int __net_init xfrm_net_init(struct net *net)
@@ -3044,7 +3358,7 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *
}
}
chain = &net->xfrm.policy_inexact[dir];
- hlist_for_each_entry(pol, chain, bydst) {
+ hlist_for_each_entry(pol, chain, bydst_inexact_list) {
if ((pol->priority >= priority) && ret)
break;
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 06/11] xfrm: policy: consider if_id when hashing inexact policy
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
This avoids searches of polices that cannot match in the first
place due to different interface id by placing them in different bins.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/xfrm/xfrm_policy.c | 25 ++++++++++++++++---------
1 file changed, 16 insertions(+), 9 deletions(-)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5c7e7399323f..dda27fd7b8a4 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -48,6 +48,7 @@ struct xfrm_flo {
struct xfrm_pol_inexact_key {
possible_net_t net;
+ u32 if_id;
u16 family;
u8 dir, type;
};
@@ -85,11 +86,12 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
int dir);
static struct xfrm_pol_inexact_bin *
-xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir);
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir,
+ u32 if_id);
static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_lookup_rcu(struct net *net,
- u8 type, u16 family, u8 dir);
+ u8 type, u16 family, u8 dir, u32 if_id);
static struct xfrm_policy *
xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
bool excl);
@@ -618,6 +620,7 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
.family = pol->family,
.type = pol->type,
.dir = dir,
+ .if_id = pol->if_id,
};
struct net *net = xp_net(pol);
@@ -925,7 +928,8 @@ static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
const struct xfrm_pol_inexact_key *k = data;
u32 a = k->type << 24 | k->dir << 16 | k->family;
- return jhash_2words(a, net_hash_mix(read_pnet(&k->net)), seed);
+ return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)),
+ seed);
}
static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed)
@@ -957,7 +961,7 @@ static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg,
if (ret)
return ret;
- return 0;
+ return b->k.if_id ^ key->if_id;
}
static const struct rhashtable_params xfrm_pol_inexact_params = {
@@ -1094,7 +1098,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
chain = policy_hash_bysel(net, sel, sel->family, dir);
if (!chain) {
bin = xfrm_policy_inexact_lookup(net, type,
- sel->family, dir);
+ sel->family, dir, if_id);
if (!bin) {
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
return NULL;
@@ -1335,12 +1339,14 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
}
static struct xfrm_pol_inexact_bin *
-xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir)
+xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family,
+ u8 dir, u32 if_id)
{
struct xfrm_pol_inexact_key k = {
.family = family,
.type = type,
.dir = dir,
+ .if_id = if_id,
};
write_pnet(&k.net, net);
@@ -1350,14 +1356,15 @@ xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir)
}
static struct xfrm_pol_inexact_bin *
-xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir)
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family,
+ u8 dir, u32 if_id)
{
struct xfrm_pol_inexact_bin *bin;
lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
rcu_read_lock();
- bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir);
+ bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
rcu_read_unlock();
return bin;
@@ -1405,7 +1412,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
break;
}
}
- bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir);
+ bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
if (!bin)
goto skip_inexact;
chain = &bin->hhead;
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 07/11] xfrm: policy: add inexact policy search tree infrastructure
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
At this time inexact policies are all searched in-order until the first
match is found. After removal of the flow cache, this resolution has
to be performed for every packetm resulting in major slowdown when
number of inexact policies is high.
This adds infrastructure to later sort inexact policies into a tree.
This only introduces a single class: any:any.
Next patch will add a search tree to pre-sort policies that
have a fixed daddr/prefixlen, so in this patch the any:any class
will still be used for all policies.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/xfrm.h | 1 +
net/xfrm/xfrm_policy.c | 301 +++++++++++++++++++++++++++++++++--------
2 files changed, 248 insertions(+), 54 deletions(-)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 870fa9b27f7e..9df6dca17155 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -577,6 +577,7 @@ struct xfrm_policy {
/* This lock only affects elements except for entry. */
rwlock_t lock;
refcount_t refcnt;
+ u32 pos;
struct timer_list timer;
atomic_t genid;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index dda27fd7b8a4..4eb12e9b40c2 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -46,6 +46,9 @@ struct xfrm_flo {
u8 flags;
};
+/* prefixes smaller than this are stored in lists, not trees. */
+#define INEXACT_PREFIXLEN_IPV4 16
+#define INEXACT_PREFIXLEN_IPV6 48
struct xfrm_pol_inexact_key {
possible_net_t net;
u32 if_id;
@@ -56,6 +59,7 @@ struct xfrm_pol_inexact_key {
struct xfrm_pol_inexact_bin {
struct xfrm_pol_inexact_key k;
struct rhash_head head;
+ /* list containing '*:*' policies */
struct hlist_head hhead;
/* slow path below */
@@ -63,6 +67,16 @@ struct xfrm_pol_inexact_bin {
struct rcu_head rcu;
};
+enum xfrm_pol_inexact_candidate_type {
+ XFRM_POL_CAND_ANY,
+
+ XFRM_POL_CAND_MAX,
+};
+
+struct xfrm_pol_inexact_candidates {
+ struct hlist_head *res[XFRM_POL_CAND_MAX];
+};
+
static DEFINE_SPINLOCK(xfrm_if_cb_lock);
static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
@@ -98,6 +112,12 @@ xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
struct xfrm_policy *policy);
+static bool
+xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
+ struct xfrm_pol_inexact_bin *b,
+ const xfrm_address_t *saddr,
+ const xfrm_address_t *daddr);
+
static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy)
{
return refcount_inc_not_zero(&policy->refcnt);
@@ -652,13 +672,48 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
return IS_ERR(prev) ? NULL : prev;
}
-static void xfrm_policy_inexact_delete_bin(struct net *net,
- struct xfrm_pol_inexact_bin *b)
+static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr,
+ int family, u8 prefixlen)
{
- lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+ if (xfrm_addr_any(addr, family))
+ return true;
+
+ if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6)
+ return true;
+
+ if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4)
+ return true;
+
+ return false;
+}
+
+static bool
+xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy)
+{
+ const xfrm_address_t *addr;
+ bool saddr_any, daddr_any;
+ u8 prefixlen;
+
+ addr = &policy->selector.saddr;
+ prefixlen = policy->selector.prefixlen_s;
- if (!hlist_empty(&b->hhead))
+ saddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
+ policy->family,
+ prefixlen);
+ addr = &policy->selector.daddr;
+ prefixlen = policy->selector.prefixlen_d;
+ daddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
+ policy->family,
+ prefixlen);
+ return saddr_any && daddr_any;
+}
+
+static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit)
+{
+ if (!hlist_empty(&b->hhead)) {
+ WARN_ON_ONCE(net_exit);
return;
+ }
if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head,
xfrm_pol_inexact_params) == 0) {
@@ -667,14 +722,23 @@ static void xfrm_policy_inexact_delete_bin(struct net *net,
}
}
+static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b)
+{
+ struct net *net = read_pnet(&b->k.net);
+
+ spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+ __xfrm_policy_inexact_prune_bin(b, false);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+}
+
static void __xfrm_policy_inexact_flush(struct net *net)
{
- struct xfrm_pol_inexact_bin *bin;
+ struct xfrm_pol_inexact_bin *bin, *t;
lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
- list_for_each_entry(bin, &net->xfrm.inexact_bins, inexact_bins)
- xfrm_policy_inexact_delete_bin(net, bin);
+ list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins)
+ __xfrm_policy_inexact_prune_bin(bin, false);
}
static struct xfrm_policy *
@@ -689,14 +753,28 @@ xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
if (!bin)
return ERR_PTR(-ENOMEM);
- delpol = xfrm_policy_insert_list(&bin->hhead, policy, excl);
- if (delpol && excl)
+ net = xp_net(policy);
+ lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+ if (xfrm_policy_inexact_insert_use_any_list(policy)) {
+ chain = &bin->hhead;
+ goto insert_to_list;
+ }
+
+ chain = &bin->hhead;
+insert_to_list:
+ delpol = xfrm_policy_insert_list(chain, policy, excl);
+ if (delpol && excl) {
+ __xfrm_policy_inexact_prune_bin(bin, false);
return ERR_PTR(-EEXIST);
+ }
- net = xp_net(policy);
chain = &net->xfrm.policy_inexact[dir];
xfrm_policy_insert_inexact_list(chain, policy);
+ if (delpol)
+ __xfrm_policy_inexact_prune_bin(bin, false);
+
return delpol;
}
@@ -733,6 +811,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
* we start with destructive action.
*/
list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) {
+ struct xfrm_pol_inexact_bin *bin;
u8 dbits, sbits;
dir = xfrm_policy_id2dir(policy->index);
@@ -761,7 +840,8 @@ static void xfrm_hash_rebuild(struct work_struct *work)
policy->selector.prefixlen_s < sbits)
continue;
- if (!xfrm_policy_inexact_alloc_bin(policy, dir))
+ bin = xfrm_policy_inexact_alloc_bin(policy, dir);
+ if (!bin)
goto out_unlock;
}
@@ -820,6 +900,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
}
out_unlock:
+ __xfrm_policy_inexact_flush(net);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
mutex_unlock(&hash_resize_mutex);
@@ -977,6 +1058,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
{
struct xfrm_policy *pol, *delpol = NULL;
struct hlist_node *newpos = NULL;
+ int i = 0;
hlist_for_each_entry(pol, chain, bydst_inexact_list) {
if (pol->type == policy->type &&
@@ -1000,6 +1082,11 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
else
hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
+
+ hlist_for_each_entry(pol, chain, bydst_inexact_list) {
+ pol->pos = i;
+ i++;
+ }
}
static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
@@ -1083,6 +1170,29 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
}
EXPORT_SYMBOL(xfrm_policy_insert);
+static struct xfrm_policy *
+__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id,
+ u8 type, int dir,
+ struct xfrm_selector *sel,
+ struct xfrm_sec_ctx *ctx)
+{
+ struct xfrm_policy *pol;
+
+ if (!chain)
+ return NULL;
+
+ hlist_for_each_entry(pol, chain, bydst) {
+ if (pol->type == type &&
+ pol->if_id == if_id &&
+ (mark & pol->mark.m) == pol->mark.v &&
+ !selector_cmp(sel, &pol->selector) &&
+ xfrm_sec_ctx_match(ctx, pol->security))
+ return pol;
+ }
+
+ return NULL;
+}
+
struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
u8 type, int dir,
struct xfrm_selector *sel,
@@ -1097,6 +1207,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, sel, sel->family, dir);
if (!chain) {
+ struct xfrm_pol_inexact_candidates cand;
+ int i;
+
bin = xfrm_policy_inexact_lookup(net, type,
sel->family, dir, if_id);
if (!bin) {
@@ -1104,35 +1217,46 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
return NULL;
}
- chain = &bin->hhead;
+ if (!xfrm_policy_find_inexact_candidates(&cand, bin,
+ &sel->saddr,
+ &sel->daddr)) {
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+ return NULL;
+ }
+
+ pol = NULL;
+ for (i = 0; i < ARRAY_SIZE(cand.res); i++) {
+ struct xfrm_policy *tmp;
+
+ tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark,
+ if_id, type, dir,
+ sel, ctx);
+ if (tmp && pol && tmp->pos < pol->pos)
+ pol = tmp;
+ }
+ } else {
+ pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir,
+ sel, ctx);
}
- ret = NULL;
- hlist_for_each_entry(pol, chain, bydst) {
- if (pol->type == type &&
- pol->if_id == if_id &&
- (mark & pol->mark.m) == pol->mark.v &&
- !selector_cmp(sel, &pol->selector) &&
- xfrm_sec_ctx_match(ctx, pol->security)) {
- xfrm_pol_hold(pol);
- if (delete) {
- *err = security_xfrm_policy_delete(
- pol->security);
- if (*err) {
- spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
- return pol;
- }
- __xfrm_policy_unlink(pol, dir);
- xfrm_policy_inexact_delete_bin(net, bin);
+ if (pol) {
+ xfrm_pol_hold(pol);
+ if (delete) {
+ *err = security_xfrm_policy_delete(pol->security);
+ if (*err) {
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+ return pol;
}
- ret = pol;
- break;
+ __xfrm_policy_unlink(pol, dir);
}
+ ret = pol;
}
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (ret && delete)
xfrm_policy_kill(ret);
+ if (bin && delete)
+ xfrm_policy_inexact_prune_bin(bin);
return ret;
}
EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
@@ -1338,6 +1462,20 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
return ret;
}
+static bool
+xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
+ struct xfrm_pol_inexact_bin *b,
+ const xfrm_address_t *saddr,
+ const xfrm_address_t *daddr)
+{
+ if (!b)
+ return false;
+
+ memset(cand, 0, sizeof(*cand));
+ cand->res[XFRM_POL_CAND_ANY] = &b->hhead;
+ return true;
+}
+
static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family,
u8 dir, u32 if_id)
@@ -1370,11 +1508,76 @@ xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family,
return bin;
}
+static struct xfrm_policy *
+__xfrm_policy_eval_candidates(struct hlist_head *chain,
+ struct xfrm_policy *prefer,
+ const struct flowi *fl,
+ u8 type, u16 family, int dir, u32 if_id)
+{
+ u32 priority = prefer ? prefer->priority : ~0u;
+ struct xfrm_policy *pol;
+
+ if (!chain)
+ return NULL;
+
+ hlist_for_each_entry_rcu(pol, chain, bydst) {
+ int err;
+
+ if (pol->priority > priority)
+ break;
+
+ err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
+ if (err) {
+ if (err != -ESRCH)
+ return ERR_PTR(err);
+
+ continue;
+ }
+
+ if (prefer) {
+ /* matches. Is it older than *prefer? */
+ if (pol->priority == priority &&
+ prefer->pos < pol->pos)
+ return prefer;
+ }
+
+ return pol;
+ }
+
+ return NULL;
+}
+
+static struct xfrm_policy *
+xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand,
+ struct xfrm_policy *prefer,
+ const struct flowi *fl,
+ u8 type, u16 family, int dir, u32 if_id)
+{
+ struct xfrm_policy *tmp;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(cand->res); i++) {
+ tmp = __xfrm_policy_eval_candidates(cand->res[i],
+ prefer,
+ fl, type, family, dir,
+ if_id);
+ if (!tmp)
+ continue;
+
+ if (IS_ERR(tmp))
+ return tmp;
+ prefer = tmp;
+ }
+
+ return prefer;
+}
+
static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
const struct flowi *fl,
u16 family, u8 dir,
u32 if_id)
{
+ struct xfrm_pol_inexact_candidates cand;
const xfrm_address_t *daddr, *saddr;
struct xfrm_pol_inexact_bin *bin;
struct xfrm_policy *pol, *ret;
@@ -1413,25 +1616,16 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
}
}
bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
- if (!bin)
+ if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr,
+ daddr))
goto skip_inexact;
- chain = &bin->hhead;
- hlist_for_each_entry_rcu(pol, chain, bydst) {
- if ((pol->priority >= priority) && ret)
- break;
- err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
- if (err) {
- if (err == -ESRCH)
- continue;
- else {
- ret = ERR_PTR(err);
- goto fail;
- }
- } else {
- ret = pol;
- break;
- }
+ pol = xfrm_policy_eval_candidates(&cand, ret, fl, type,
+ family, dir, if_id);
+ if (pol) {
+ ret = pol;
+ if (IS_ERR(pol))
+ goto fail;
}
skip_inexact:
@@ -3168,7 +3362,7 @@ static int __net_init xfrm_policy_init(struct net *net)
static void xfrm_policy_fini(struct net *net)
{
- struct xfrm_pol_inexact_bin *bin, *tmp;
+ struct xfrm_pol_inexact_bin *b, *t;
unsigned int sz;
int dir;
@@ -3195,11 +3389,10 @@ static void xfrm_policy_fini(struct net *net)
WARN_ON(!hlist_empty(net->xfrm.policy_byidx));
xfrm_hash_free(net->xfrm.policy_byidx, sz);
- list_for_each_entry_safe(bin, tmp, &net->xfrm.inexact_bins,
- inexact_bins) {
- WARN_ON(!hlist_empty(&bin->hhead));
- xfrm_policy_inexact_delete_bin(net, bin);
- }
+ spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+ list_for_each_entry_safe(b, t, &net->xfrm.inexact_bins, inexact_bins)
+ __xfrm_policy_inexact_prune_bin(b, true);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
}
static int __net_init xfrm_net_init(struct net *net)
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 08/11] xfrm: policy: store inexact policies in a tree ordered by destination address
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
This adds inexact lists per destination network, stored in a search tree.
Inexact lookups now return two 'candidate lists', the 'any' policies
('any' destionations), and a list of policies that share same
daddr/prefix.
Next patch will add a second search tree for 'saddr:any' policies
so we can avoid placing those on the 'any:any' list too.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/xfrm.h | 1 +
net/xfrm/xfrm_policy.c | 333 ++++++++++++++++++++++++++++++++++++++++-
2 files changed, 328 insertions(+), 6 deletions(-)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 9df6dca17155..fa4b3c877fcf 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -590,6 +590,7 @@ struct xfrm_policy {
struct xfrm_lifetime_cur curlft;
struct xfrm_policy_walk_entry walk;
struct xfrm_policy_queue polq;
+ bool bydst_reinsert;
u8 type;
u8 action;
u8 flags;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 4eb12e9b40c2..81447d5d02e6 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -49,6 +49,38 @@ struct xfrm_flo {
/* prefixes smaller than this are stored in lists, not trees. */
#define INEXACT_PREFIXLEN_IPV4 16
#define INEXACT_PREFIXLEN_IPV6 48
+
+struct xfrm_pol_inexact_node {
+ struct rb_node node;
+ union {
+ xfrm_address_t addr;
+ struct rcu_head rcu;
+ };
+ u8 prefixlen;
+
+ /* the policies matching this node, can be empty list */
+ struct hlist_head hhead;
+};
+
+/* xfrm inexact policy search tree:
+ * xfrm_pol_inexact_bin = hash(dir,type,family,if_id);
+ * |
+ * +---- root_d: sorted by daddr:prefix
+ * | |
+ * | xfrm_pol_inexact_node
+ * | |
+ * | +- coarse policies and all any:daddr policies
+ * |
+ * +---- coarse policies and all any:any policies
+ *
+ * Lookups return two candidate lists:
+ * 1. any:any list from top-level xfrm_pol_inexact_bin
+ * 2. any:daddr list from daddr tree
+ *
+ * This result set then needs to be searched for the policy with
+ * the lowest priority. If two results have same prio, youngest one wins.
+ */
+
struct xfrm_pol_inexact_key {
possible_net_t net;
u32 if_id;
@@ -62,12 +94,17 @@ struct xfrm_pol_inexact_bin {
/* list containing '*:*' policies */
struct hlist_head hhead;
+ seqcount_t count;
+ /* tree sorted by daddr/prefix */
+ struct rb_root root_d;
+
/* slow path below */
struct list_head inexact_bins;
struct rcu_head rcu;
};
enum xfrm_pol_inexact_candidate_type {
+ XFRM_POL_CAND_DADDR,
XFRM_POL_CAND_ANY,
XFRM_POL_CAND_MAX,
@@ -658,6 +695,8 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
bin->k = k;
INIT_HLIST_HEAD(&bin->hhead);
+ bin->root_d = RB_ROOT;
+ seqcount_init(&bin->count);
prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
&bin->k, &bin->head,
@@ -708,9 +747,211 @@ xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy)
return saddr_any && daddr_any;
}
+static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node,
+ const xfrm_address_t *addr, u8 prefixlen)
+{
+ node->addr = *addr;
+ node->prefixlen = prefixlen;
+}
+
+static struct xfrm_pol_inexact_node *
+xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen)
+{
+ struct xfrm_pol_inexact_node *node;
+
+ node = kzalloc(sizeof(*node), GFP_ATOMIC);
+ if (node)
+ xfrm_pol_inexact_node_init(node, addr, prefixlen);
+
+ return node;
+}
+
+static int xfrm_policy_addr_delta(const xfrm_address_t *a,
+ const xfrm_address_t *b,
+ u8 prefixlen, u16 family)
+{
+ unsigned int pdw, pbi;
+ int delta = 0;
+
+ switch (family) {
+ case AF_INET:
+ if (sizeof(long) == 4 && prefixlen == 0)
+ return ntohl(a->a4) - ntohl(b->a4);
+ return (ntohl(a->a4) & ((~0UL << (32 - prefixlen)))) -
+ (ntohl(b->a4) & ((~0UL << (32 - prefixlen))));
+ case AF_INET6:
+ pdw = prefixlen >> 5;
+ pbi = prefixlen & 0x1f;
+
+ if (pdw) {
+ delta = memcmp(a->a6, b->a6, pdw << 2);
+ if (delta)
+ return delta;
+ }
+ if (pbi) {
+ u32 mask = ~0u << (32 - pbi);
+
+ delta = (ntohl(a->a6[pdw]) & mask) -
+ (ntohl(b->a6[pdw]) & mask);
+ }
+ break;
+ default:
+ break;
+ }
+
+ return delta;
+}
+
+static void xfrm_policy_inexact_list_reinsert(struct net *net,
+ struct xfrm_pol_inexact_node *n,
+ u16 family)
+{
+ struct hlist_node *newpos = NULL;
+ struct xfrm_policy *policy, *p;
+
+ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+ if (!policy->bydst_reinsert)
+ continue;
+
+ WARN_ON_ONCE(policy->family != family);
+
+ policy->bydst_reinsert = false;
+ hlist_for_each_entry(p, &n->hhead, bydst) {
+ if (policy->priority >= p->priority)
+ newpos = &p->bydst;
+ else
+ break;
+ }
+
+ if (newpos)
+ hlist_add_behind(&policy->bydst, newpos);
+ else
+ hlist_add_head(&policy->bydst, &n->hhead);
+ }
+}
+
+/* merge nodes v and n */
+static void xfrm_policy_inexact_node_merge(struct net *net,
+ struct xfrm_pol_inexact_node *v,
+ struct xfrm_pol_inexact_node *n,
+ u16 family)
+{
+ struct xfrm_policy *tmp;
+
+ hlist_for_each_entry(tmp, &v->hhead, bydst)
+ tmp->bydst_reinsert = true;
+ hlist_for_each_entry(tmp, &n->hhead, bydst)
+ tmp->bydst_reinsert = true;
+
+ INIT_HLIST_HEAD(&n->hhead);
+ xfrm_policy_inexact_list_reinsert(net, n, family);
+}
+
+static struct xfrm_pol_inexact_node *
+xfrm_policy_inexact_insert_node(struct net *net,
+ struct rb_root *root,
+ xfrm_address_t *addr,
+ u16 family, u8 prefixlen, u8 dir)
+{
+ struct xfrm_pol_inexact_node *cached = NULL;
+ struct rb_node **p, *parent = NULL;
+ struct xfrm_pol_inexact_node *node;
+
+ p = &root->rb_node;
+ while (*p) {
+ int delta;
+
+ parent = *p;
+ node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
+
+ delta = xfrm_policy_addr_delta(addr, &node->addr,
+ node->prefixlen,
+ family);
+ if (delta == 0 && prefixlen >= node->prefixlen) {
+ WARN_ON_ONCE(cached); /* ipsec policies got lost */
+ return node;
+ }
+
+ if (delta < 0)
+ p = &parent->rb_left;
+ else
+ p = &parent->rb_right;
+
+ if (prefixlen < node->prefixlen) {
+ delta = xfrm_policy_addr_delta(addr, &node->addr,
+ prefixlen,
+ family);
+ if (delta)
+ continue;
+
+ /* This node is a subnet of the new prefix. It needs
+ * to be removed and re-inserted with the smaller
+ * prefix and all nodes that are now also covered
+ * by the reduced prefixlen.
+ */
+ rb_erase(&node->node, root);
+
+ if (!cached) {
+ xfrm_pol_inexact_node_init(node, addr,
+ prefixlen);
+ cached = node;
+ } else {
+ /* This node also falls within the new
+ * prefixlen. Merge the to-be-reinserted
+ * node and this one.
+ */
+ xfrm_policy_inexact_node_merge(net, node,
+ cached, family);
+ kfree_rcu(node, rcu);
+ }
+
+ /* restart */
+ p = &root->rb_node;
+ parent = NULL;
+ }
+ }
+
+ node = cached;
+ if (!node) {
+ node = xfrm_pol_inexact_node_alloc(addr, prefixlen);
+ if (!node)
+ return NULL;
+ }
+
+ rb_link_node_rcu(&node->node, parent, p);
+ rb_insert_color(&node->node, root);
+
+ return node;
+}
+
+static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm)
+{
+ struct xfrm_pol_inexact_node *node;
+ struct rb_node *rn = rb_first(r);
+
+ while (rn) {
+ node = rb_entry(rn, struct xfrm_pol_inexact_node, node);
+
+ rn = rb_next(rn);
+
+ if (!hlist_empty(&node->hhead)) {
+ WARN_ON_ONCE(rm);
+ continue;
+ }
+
+ rb_erase(&node->node, r);
+ kfree_rcu(node, rcu);
+ }
+}
+
static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit)
{
- if (!hlist_empty(&b->hhead)) {
+ write_seqcount_begin(&b->count);
+ xfrm_policy_inexact_gc_tree(&b->root_d, net_exit);
+ write_seqcount_end(&b->count);
+
+ if (!RB_EMPTY_ROOT(&b->root_d) ||
+ !hlist_empty(&b->hhead)) {
WARN_ON_ONCE(net_exit);
return;
}
@@ -741,6 +982,37 @@ static void __xfrm_policy_inexact_flush(struct net *net)
__xfrm_policy_inexact_prune_bin(bin, false);
}
+static struct hlist_head *
+xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
+ struct xfrm_policy *policy, u8 dir)
+{
+ struct xfrm_pol_inexact_node *n;
+ struct net *net;
+
+ net = xp_net(policy);
+ lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+ if (xfrm_policy_inexact_insert_use_any_list(policy))
+ return &bin->hhead;
+
+ if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
+ policy->family,
+ policy->selector.prefixlen_d))
+ return &bin->hhead;
+
+ /* daddr is fixed */
+ write_seqcount_begin(&bin->count);
+ n = xfrm_policy_inexact_insert_node(net,
+ &bin->root_d,
+ &policy->selector.daddr,
+ policy->family,
+ policy->selector.prefixlen_d, dir);
+ write_seqcount_end(&bin->count);
+ if (!n)
+ return NULL;
+ return &n->hhead;
+}
+
static struct xfrm_policy *
xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
{
@@ -756,13 +1028,12 @@ xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
net = xp_net(policy);
lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
- if (xfrm_policy_inexact_insert_use_any_list(policy)) {
- chain = &bin->hhead;
- goto insert_to_list;
+ chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir);
+ if (!chain) {
+ __xfrm_policy_inexact_prune_bin(bin, false);
+ return ERR_PTR(-ENOMEM);
}
- chain = &bin->hhead;
-insert_to_list:
delpol = xfrm_policy_insert_list(chain, policy, excl);
if (delpol && excl) {
__xfrm_policy_inexact_prune_bin(bin, false);
@@ -843,6 +1114,9 @@ static void xfrm_hash_rebuild(struct work_struct *work)
bin = xfrm_policy_inexact_alloc_bin(policy, dir);
if (!bin)
goto out_unlock;
+
+ if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir))
+ goto out_unlock;
}
/* reset the bydst and inexact table in all directions */
@@ -1462,17 +1736,64 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
return ret;
}
+static struct xfrm_pol_inexact_node *
+xfrm_policy_lookup_inexact_addr(const struct rb_root *r,
+ seqcount_t *count,
+ const xfrm_address_t *addr, u16 family)
+{
+ const struct rb_node *parent;
+ int seq;
+
+again:
+ seq = read_seqcount_begin(count);
+
+ parent = rcu_dereference_raw(r->rb_node);
+ while (parent) {
+ struct xfrm_pol_inexact_node *node;
+ int delta;
+
+ node = rb_entry(parent, struct xfrm_pol_inexact_node, node);
+
+ delta = xfrm_policy_addr_delta(addr, &node->addr,
+ node->prefixlen, family);
+ if (delta < 0) {
+ parent = rcu_dereference_raw(parent->rb_left);
+ continue;
+ } else if (delta > 0) {
+ parent = rcu_dereference_raw(parent->rb_right);
+ continue;
+ }
+
+ return node;
+ }
+
+ if (read_seqcount_retry(count, seq))
+ goto again;
+
+ return NULL;
+}
+
static bool
xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
struct xfrm_pol_inexact_bin *b,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr)
{
+ struct xfrm_pol_inexact_node *n;
+ u16 family;
+
if (!b)
return false;
+ family = b->k.family;
memset(cand, 0, sizeof(*cand));
cand->res[XFRM_POL_CAND_ANY] = &b->hhead;
+
+ n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr,
+ family);
+ if (n)
+ cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
+
return true;
}
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 09/11] xfrm: policy: check reinserted policies match their node
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
validate the re-inserted policies match the lookup node.
Policies that fail this test won't be returned in the candidate set.
This is enabled by default for now, it should not cause noticeable
reinsert slow down.
Such reinserts are needed when we have to merge an existing node
(e.g. for 10.0.0.0/28 because a overlapping subnet was added (e.g.
10.0.0.0/24), so whenever this happens existing policies have to
be placed on the list of the new node.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/xfrm/xfrm_policy.c | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 81447d5d02e6..57e28dcd7c53 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -806,10 +806,16 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
struct xfrm_pol_inexact_node *n,
u16 family)
{
+ unsigned int matched_s, matched_d;
struct hlist_node *newpos = NULL;
struct xfrm_policy *policy, *p;
+ matched_s = 0;
+ matched_d = 0;
+
list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+ bool matches_s, matches_d;
+
if (!policy->bydst_reinsert)
continue;
@@ -827,6 +833,32 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
hlist_add_behind(&policy->bydst, newpos);
else
hlist_add_head(&policy->bydst, &n->hhead);
+
+ /* paranoia checks follow.
+ * Check that the reinserted policy matches at least
+ * saddr or daddr for current node prefix.
+ *
+ * Matching both is fine, matching saddr in one policy
+ * (but not daddr) and then matching only daddr in another
+ * is a bug.
+ */
+ matches_s = xfrm_policy_addr_delta(&policy->selector.saddr,
+ &n->addr,
+ n->prefixlen,
+ family) == 0;
+ matches_d = xfrm_policy_addr_delta(&policy->selector.daddr,
+ &n->addr,
+ n->prefixlen,
+ family) == 0;
+ if (matches_s && matches_d)
+ continue;
+
+ WARN_ON_ONCE(!matches_s && !matches_d);
+ if (matches_s)
+ matched_s++;
+ if (matches_d)
+ matched_d++;
+ WARN_ON_ONCE(matched_s && matched_d);
}
}
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 10/11] xfrm: policy: store inexact policies in a tree ordered by source address
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
This adds the 'saddr:any' search class. It contains all policies that have
a fixed saddr/prefixlen, but 'any' destination.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/xfrm/xfrm_policy.c | 46 ++++++++++++++++++++++++++++++++++++++----
1 file changed, 42 insertions(+), 4 deletions(-)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 57e28dcd7c53..38e33326c856 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -71,11 +71,20 @@ struct xfrm_pol_inexact_node {
* | |
* | +- coarse policies and all any:daddr policies
* |
+ * +---- root_s: sorted by saddr:prefix
+ * | |
+ * | xfrm_pol_inexact_node
+ * | |
+ * | + root: unused
+ * | |
+ * | + hhead: saddr:any policies
+ * |
* +---- coarse policies and all any:any policies
*
- * Lookups return two candidate lists:
+ * Lookups return three candidate lists:
* 1. any:any list from top-level xfrm_pol_inexact_bin
* 2. any:daddr list from daddr tree
+ * 2. saddr:any list from saddr tree
*
* This result set then needs to be searched for the policy with
* the lowest priority. If two results have same prio, youngest one wins.
@@ -98,12 +107,16 @@ struct xfrm_pol_inexact_bin {
/* tree sorted by daddr/prefix */
struct rb_root root_d;
+ /* tree sorted by saddr/prefix */
+ struct rb_root root_s;
+
/* slow path below */
struct list_head inexact_bins;
struct rcu_head rcu;
};
enum xfrm_pol_inexact_candidate_type {
+ XFRM_POL_CAND_SADDR,
XFRM_POL_CAND_DADDR,
XFRM_POL_CAND_ANY,
@@ -696,6 +709,7 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
bin->k = k;
INIT_HLIST_HEAD(&bin->hhead);
bin->root_d = RB_ROOT;
+ bin->root_s = RB_ROOT;
seqcount_init(&bin->count);
prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
@@ -980,9 +994,10 @@ static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool
{
write_seqcount_begin(&b->count);
xfrm_policy_inexact_gc_tree(&b->root_d, net_exit);
+ xfrm_policy_inexact_gc_tree(&b->root_s, net_exit);
write_seqcount_end(&b->count);
- if (!RB_EMPTY_ROOT(&b->root_d) ||
+ if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) ||
!hlist_empty(&b->hhead)) {
WARN_ON_ONCE(net_exit);
return;
@@ -1027,11 +1042,29 @@ xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
if (xfrm_policy_inexact_insert_use_any_list(policy))
return &bin->hhead;
- if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
+ /* saddr is wildcard */
+ if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
policy->family,
- policy->selector.prefixlen_d))
+ policy->selector.prefixlen_s))
return &bin->hhead;
+ if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
+ policy->family,
+ policy->selector.prefixlen_d)) {
+ write_seqcount_begin(&bin->count);
+ n = xfrm_policy_inexact_insert_node(net,
+ &bin->root_s,
+ &policy->selector.saddr,
+ policy->family,
+ policy->selector.prefixlen_s,
+ dir);
+ write_seqcount_end(&bin->count);
+ if (!n)
+ return NULL;
+
+ return &n->hhead;
+ }
+
/* daddr is fixed */
write_seqcount_begin(&bin->count);
n = xfrm_policy_inexact_insert_node(net,
@@ -1826,6 +1859,11 @@ xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
if (n)
cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
+ n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr,
+ family);
+ if (n)
+ cand->res[XFRM_POL_CAND_SADDR] = &n->hhead;
+
return true;
}
--
2.18.1
^ permalink raw reply related
* [PATCH ipsec-next 11/11] xfrm: policy: add 2nd-level saddr trees for inexact policies
From: Florian Westphal @ 2018-11-07 22:00 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <20181107220041.26205-1-fw@strlen.de>
This adds the fourth and final search class, containing policies
where both saddr and daddr have prefix lengths (i.e., not wildcards).
Inexact policies now end up in one of the following four search classes:
1. "Any:Any" list, containing policies where both saddr and daddr are
wildcards or have very coarse prefixes, e.g. 10.0.0.0/8 and the like.
2. "saddr:any" list, containing policies with a fixed saddr/prefixlen,
but without destination restrictions.
These lists are stored in rbtree nodes; each node contains those
policies matching saddr/prefixlen.
3. "Any:daddr" list. Similar to 2), except for policies where only the
destinations are specified.
4. "saddr:daddr" lists, containing only those policies that
match the given source/destination network.
The root of the saddr/daddr nodes gets stored in the nodes of the
'daddr' tree.
This diagram illustrates the list classes, and their
placement in the lookup hierarchy:
xfrm_pol_inexact_bin = hash(dir,type,family,if_id);
|
+---- root_d: sorted by daddr:prefix
| |
| xfrm_pol_inexact_node
| |
| +- root: sorted by saddr/prefix
| | |
| | xfrm_pol_inexact_node
| | |
| | + root: unused
| | |
| | + hhead: saddr:daddr policies
| |
| +- coarse policies and all any:daddr policies
|
+---- root_s: sorted by saddr:prefix
| |
| xfrm_pol_inexact_node
| |
| + root: unused
| |
| + hhead: saddr:any policies
|
+---- coarse policies and all any:any policies
lookup for an inexact policy returns pointers to the four relevant list
classes, after which each of the lists needs to be searched for the policy
with the higher priority.
This will only speed up lookups in case we have many policies and a
sizeable portion of these have disjunct saddr/daddr addresses.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/xfrm/xfrm_policy.c | 118 +++++++++++++++++++++++++++++++++++++----
1 file changed, 108 insertions(+), 10 deletions(-)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 38e33326c856..bd80b8a4322f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -58,6 +58,8 @@ struct xfrm_pol_inexact_node {
};
u8 prefixlen;
+ struct rb_root root;
+
/* the policies matching this node, can be empty list */
struct hlist_head hhead;
};
@@ -69,6 +71,14 @@ struct xfrm_pol_inexact_node {
* | |
* | xfrm_pol_inexact_node
* | |
+ * | +- root: sorted by saddr/prefix
+ * | | |
+ * | | xfrm_pol_inexact_node
+ * | | |
+ * | | + root: unused
+ * | | |
+ * | | + hhead: saddr:daddr policies
+ * | |
* | +- coarse policies and all any:daddr policies
* |
* +---- root_s: sorted by saddr:prefix
@@ -81,10 +91,11 @@ struct xfrm_pol_inexact_node {
* |
* +---- coarse policies and all any:any policies
*
- * Lookups return three candidate lists:
+ * Lookups return four candidate lists:
* 1. any:any list from top-level xfrm_pol_inexact_bin
* 2. any:daddr list from daddr tree
- * 2. saddr:any list from saddr tree
+ * 3. saddr:daddr list from 2nd level daddr tree
+ * 4. saddr:any list from saddr tree
*
* This result set then needs to be searched for the policy with
* the lowest priority. If two results have same prio, youngest one wins.
@@ -116,6 +127,7 @@ struct xfrm_pol_inexact_bin {
};
enum xfrm_pol_inexact_candidate_type {
+ XFRM_POL_CAND_BOTH,
XFRM_POL_CAND_SADDR,
XFRM_POL_CAND_DADDR,
XFRM_POL_CAND_ANY,
@@ -876,13 +888,82 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
}
}
+static void xfrm_policy_inexact_node_reinsert(struct net *net,
+ struct xfrm_pol_inexact_node *n,
+ struct rb_root *new,
+ u16 family)
+{
+ struct rb_node **p, *parent = NULL;
+ struct xfrm_pol_inexact_node *node;
+
+ /* we should not have another subtree here */
+ WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root));
+
+ p = &new->rb_node;
+ while (*p) {
+ u8 prefixlen;
+ int delta;
+
+ parent = *p;
+ node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
+
+ prefixlen = min(node->prefixlen, n->prefixlen);
+
+ delta = xfrm_policy_addr_delta(&n->addr, &node->addr,
+ prefixlen, family);
+ if (delta < 0) {
+ p = &parent->rb_left;
+ } else if (delta > 0) {
+ p = &parent->rb_right;
+ } else {
+ struct xfrm_policy *tmp;
+
+ hlist_for_each_entry(tmp, &node->hhead, bydst)
+ tmp->bydst_reinsert = true;
+ hlist_for_each_entry(tmp, &n->hhead, bydst)
+ tmp->bydst_reinsert = true;
+
+ INIT_HLIST_HEAD(&node->hhead);
+ xfrm_policy_inexact_list_reinsert(net, node, family);
+
+ if (node->prefixlen == n->prefixlen) {
+ kfree_rcu(n, rcu);
+ return;
+ }
+
+ rb_erase(*p, new);
+ kfree_rcu(n, rcu);
+ n = node;
+ n->prefixlen = prefixlen;
+ *p = new->rb_node;
+ parent = NULL;
+ }
+ }
+
+ rb_link_node_rcu(&n->node, parent, p);
+ rb_insert_color(&n->node, new);
+}
+
/* merge nodes v and n */
static void xfrm_policy_inexact_node_merge(struct net *net,
struct xfrm_pol_inexact_node *v,
struct xfrm_pol_inexact_node *n,
u16 family)
{
+ struct xfrm_pol_inexact_node *node;
struct xfrm_policy *tmp;
+ struct rb_node *rnode;
+
+ /* To-be-merged node v has a subtree.
+ *
+ * Dismantle it and insert its nodes to n->root.
+ */
+ while ((rnode = rb_first(&v->root)) != NULL) {
+ node = rb_entry(rnode, struct xfrm_pol_inexact_node, node);
+ rb_erase(&node->node, &v->root);
+ xfrm_policy_inexact_node_reinsert(net, node, &n->root,
+ family);
+ }
hlist_for_each_entry(tmp, &v->hhead, bydst)
tmp->bydst_reinsert = true;
@@ -978,9 +1059,10 @@ static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm)
while (rn) {
node = rb_entry(rn, struct xfrm_pol_inexact_node, node);
+ xfrm_policy_inexact_gc_tree(&node->root, rm);
rn = rb_next(rn);
- if (!hlist_empty(&node->hhead)) {
+ if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) {
WARN_ON_ONCE(rm);
continue;
}
@@ -1042,12 +1124,6 @@ xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
if (xfrm_policy_inexact_insert_use_any_list(policy))
return &bin->hhead;
- /* saddr is wildcard */
- if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
- policy->family,
- policy->selector.prefixlen_s))
- return &bin->hhead;
-
if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
policy->family,
policy->selector.prefixlen_d)) {
@@ -1075,6 +1151,23 @@ xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
write_seqcount_end(&bin->count);
if (!n)
return NULL;
+
+ /* saddr is wildcard */
+ if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
+ policy->family,
+ policy->selector.prefixlen_s))
+ return &n->hhead;
+
+ write_seqcount_begin(&bin->count);
+ n = xfrm_policy_inexact_insert_node(net,
+ &n->root,
+ &policy->selector.saddr,
+ policy->family,
+ policy->selector.prefixlen_s, dir);
+ write_seqcount_end(&bin->count);
+ if (!n)
+ return NULL;
+
return &n->hhead;
}
@@ -1856,8 +1949,13 @@ xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr,
family);
- if (n)
+ if (n) {
cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
+ n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr,
+ family);
+ if (n)
+ cand->res[XFRM_POL_CAND_BOTH] = &n->hhead;
+ }
n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr,
family);
--
2.18.1
^ permalink raw reply related
* Re: [PATCH rdma] net/mlx5: Fix XRC SRQ umem valid bits
From: Jason Gunthorpe @ 2018-11-07 22:07 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Doug Ledford, Yishai Hadas, RDMA mailing list, Artemy Kovalyov,
Saeed Mahameed, linux-netdev
In-Reply-To: <20181107073434.GJ9230@mtr-leonro.mtl.com>
On Wed, Nov 07, 2018 at 09:34:34AM +0200, Leon Romanovsky wrote:
> On Tue, Nov 06, 2018 at 03:11:53PM -0700, Jason Gunthorpe wrote:
> > On Tue, Nov 06, 2018 at 05:10:53PM -0500, Doug Ledford wrote:
> > > On Tue, 2018-11-06 at 22:02 +0000, Jason Gunthorpe wrote:
> > > > On Tue, Nov 06, 2018 at 04:31:08PM -0500, Doug Ledford wrote:
> > > > > On Wed, 2018-10-31 at 12:20 +0200, Leon Romanovsky wrote:
> > > > > > From: Yishai Hadas <yishaih@mellanox.com>
> > > > > >
> > > > > > Adapt XRC SRQ to the latest HW specification with fixed definition
> > > > > > around umem valid bits. The previous definition relied on a bit which
> > > > > > was taken for other purposes in legacy FW.
> > > > > >
> > > > > > Fixes: bd37197554eb ("net/mlx5: Update mlx5_ifc with DEVX UID bits")
> > > > > > Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
> > > > > > Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
> > > > > > Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
> > > > > > Hi Doug, Jason
> > > > > >
> > > > > > This commit fixes code sent in this merge window, so I'm not marking it
> > > > > > with any rdma-rc/rdma-next. It will be better to be sent during this merge
> > > > > > window if you have extra pull request to issue, or as a -rc material, if
> > > > > > not.
> > > > > >
> > > > > > BTW, we didn't combine reserved fields, because our convention is to align such
> > > > > > fields to 32 bits for better readability.
> > > > > >
> > > > > > Thanks
> > > > >
> > > > > This looks fine. Let me know when it's in the mlx5-next tree to pull.
> > > >
> > > > It needs to go to -rc...
> > > >
> > > > This needs a mlx5-rc branch for this I guess?
> > >
> > > I don't think so. As long as it's the first commit in mlx5-next, and
> > > mlx5-next is 4.20-rc1 based, then pulling this commit into the -rc tree
> > > will only pull the single commit. Then when we pull into for-next for
> > > the first time, we will get this in for-next too. That seems best to
> > > me.
> >
> > That works too, if Leon is fast :)
>
> Thank you both for suggestion.
>
> I did it.
> 99b77fef3c6c net/mlx5: Fix XRC SRQ umem valid bits
>
> It is first commit and it is based on -rc1.
Okay, I put this branch in -rc
Jason
^ permalink raw reply
* Re: [PATCH v3 1/2] kretprobe: produce sane stack traces
From: Aleksa Sarai @ 2018-11-08 7:46 UTC (permalink / raw)
To: Steven Rostedt
Cc: Naveen N. Rao, Anil S Keshavamurthy, David S. Miller,
Masami Hiramatsu, Jonathan Corbet, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Alexander Shishkin, Jiri Olsa,
Namhyung Kim, Shuah Khan, Alexei Starovoitov, Daniel Borkmann,
Brendan Gregg, Christian Brauner, Aleksa Sarai, netdev, linux-doc,
linux-kernel
In-Reply-To: <20181106171501.59ccabbc@gandalf.local.home>
[-- Attachment #1: Type: text/plain, Size: 1979 bytes --]
On 2018-11-06, Steven Rostedt <rostedt@goodmis.org> wrote:
> On Sun, 4 Nov 2018 22:59:13 +1100
> Aleksa Sarai <cyphar@cyphar.com> wrote:
>
> > The same issue is present in __save_stack_trace
> > (arch/x86/kernel/stacktrace.c). This is likely the only reason that --
> > as Steven said -- stacktraces wouldn't work with ftrace-graph (and thus
> > with the refactor both of you are discussing).
>
> By the way, I was playing with the the orc unwinder and stack traces
> from the function graph tracer return code, and got it working with the
> below patch. Caution, that patch also has a stack trace hardcoded in
> the return path of the function graph tracer, so you don't want to run
> function graph tracing without filtering.
Neat!
> diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
> index 169b3c44ee97..aaeca73218cc 100644
> --- a/kernel/trace/trace_functions_graph.c
> +++ b/kernel/trace/trace_functions_graph.c
> @@ -242,13 +242,16 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
> trace->calltime = current->ret_stack[index].calltime;
> trace->overrun = atomic_read(¤t->trace_overrun);
> trace->depth = index;
> +
> + trace_dump_stack(0);
Right, this works because save_stack is not being passed a pt_regs. But if
you pass a pt_regs (as happens with bpf_getstackid -- which is what
spawned this discussion) then the top-most entry of the stack will still
be a trampoline because there is no ftrace_graph_ret_addr call.
(I'm struggling with how to fix this -- I can't figure out what retp
should be if you have a pt_regs. ->sp doesn't appear to work -- it's off
by a few bytes.)
I will attach what I have at the moment to hopefully explain what the
issue I've found is (re-using the kretprobe architecture but with the
shadow-stack idea).
--
Aleksa Sarai
Senior Software Engineer (Containers)
SUSE Linux GmbH
<https://www.cyphar.com/>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* Re: [PATCH bpf-next 2/2] bpftool: support loading flow dissector
From: Stanislav Fomichev @ 2018-11-07 22:15 UTC (permalink / raw)
To: Quentin Monnet
Cc: Jakub Kicinski, Stanislav Fomichev, netdev, linux-kselftest, ast,
daniel, shuah, guro, jiong.wang, bhole_prashant_q7,
john.fastabend, jbenc, treeze.taeung, yhs, osk, sandipan
In-Reply-To: <6628387d-cf89-573f-7b9c-2d49ef19634e@netronome.com>
On 11/07, Quentin Monnet wrote:
> 2018-11-07 12:32 UTC-0800 ~ Jakub Kicinski <jakub.kicinski@netronome.com>
> > On Wed, 7 Nov 2018 20:08:53 +0000, Quentin Monnet wrote:
> > > > + err = bpf_obj_pin(bpf_program__fd(prog), pinfile);
> > > > + if (err) {
> > > > + p_err("failed to pin program %s",
> > > > + bpf_program__title(prog, false));
> > > > + goto err_close_obj;
> > > > + }
> > >
> > > I don't have the same opinion as Jakub for pinning :). I was hoping we
> > > could also load additional programs (for tail calls) for
> > > non-flow_dissector programs. Could this be an occasion to update the
> > > code in that direction?
> >
> > Do you mean having the bpftool construct an array for tail calling
> > automatically when loading an object? Or do a "mass pin" of all
> > programs in an object file?
> >
> > I'm not convinced about this strategy of auto assembling a tail call
> > array by assuming that a flow dissector object carries programs for
> > protocols in order (apart from the main program which doesn't have to
> > be first, for some reason).
>
> Not constructing the prog array, I don't think this should be the role of
> bpftool either. Much more a "mass pin", so that you have a link to each
> program loaded from the object file and can later add them to a prog array
> map with subsequent calls to bpftool.
I agree, constructing the jmp_table is a bit fragile with all the
dependencies on the order of the progs. I'll drop that and will send a
v2 that pins all the programs from the obj file instead and offloads
jmp_table construction to the user. So the supposed use case would be
something like the following:
bpftool prog load bpf_flow.o /sys/fs/bpf/flow type flow_dissector
bpftool map update pinned /sys/fs/bpf/flow/jmp_table \
key ... value pinned /sys/fs/bpf/flow/<PROTO>/0
bpftool map update ...
bpftool prog attach pinned /sys/fs/bpf/flow/flow_dissector/0 flow_dissector
^ permalink raw reply
* Re: [PATCH v3 1/2] kretprobe: produce sane stack traces
From: Aleksa Sarai @ 2018-11-08 8:04 UTC (permalink / raw)
To: Steven Rostedt
Cc: Naveen N. Rao, Anil S Keshavamurthy, David S. Miller,
Masami Hiramatsu, Jonathan Corbet, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Alexander Shishkin, Jiri Olsa,
Namhyung Kim, Shuah Khan, Alexei Starovoitov, Daniel Borkmann,
Brendan Gregg, Christian Brauner, Aleksa Sarai, netdev, linux-doc,
linux-kernel
In-Reply-To: <20181108074612.ldy6rozdpsdps6bf@yavin>
[-- Attachment #1: Type: text/plain, Size: 12219 bytes --]
On 2018-11-08, Aleksa Sarai <cyphar@cyphar.com> wrote:
> I will attach what I have at the moment to hopefully explain what the
> issue I've found is (re-using the kretprobe architecture but with the
> shadow-stack idea).
Here is the patch I have at the moment (it works, except for the
question I have about how to handle the top-level pt_regs -- I've marked
that code with XXX).
--
Aleksa Sarai
Senior Software Engineer (Containers)
SUSE Linux GmbH
<https://www.cyphar.com/>
--8<---------------------------------------------------------------------
Since the return address is modified by kretprobe, the various unwinders
can produce invalid and confusing stack traces. ftrace mostly solved
this problem by teaching each unwinder how to find the original return
address for stack trace purposes. This same technique can be applied to
kretprobes by simply adding a pointer to where the return address was
replaced in the stack, and then looking up the relevant
kretprobe_instance when a stack trace is requested.
[WIP: This is currently broken because the *first entry* will not be
overwritten since it looks like the stack pointer is different
when we are provided pt_regs. All other addresses are correctly
handled.]
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
arch/x86/events/core.c | 6 +++-
arch/x86/include/asm/ptrace.h | 1 +
arch/x86/kernel/kprobes/core.c | 5 ++--
arch/x86/kernel/stacktrace.c | 10 +++++--
arch/x86/kernel/unwind_frame.c | 2 ++
arch/x86/kernel/unwind_guess.c | 5 +++-
arch/x86/kernel/unwind_orc.c | 2 ++
include/linux/kprobes.h | 15 +++++++++-
kernel/kprobes.c | 55 ++++++++++++++++++++++++++++++++++
9 files changed, 93 insertions(+), 8 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index de32741d041a..d71062702179 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2371,7 +2371,11 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
return;
}
- if (perf_callchain_store(entry, regs->ip))
+ /* XXX: Currently broken -- stack_addr(regs) doesn't match entry. */
+ addr = regs->ip;
+ //addr = ftrace_graph_ret_addr(current, &state.graph_idx, addr, stack_addr(regs));
+ addr = kretprobe_ret_addr(current, addr, stack_addr(regs));
+ if (perf_callchain_store(entry, addr))
return;
for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index ee696efec99f..c4dfafd43e11 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -172,6 +172,7 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
return regs->sp;
}
#endif
+#define stack_addr(regs) ((unsigned long *) kernel_stack_pointer(regs))
#define GET_IP(regs) ((regs)->ip)
#define GET_FP(regs) ((regs)->bp)
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index b0d1e81c96bb..eb4da885020c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -69,8 +69,6 @@
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
-#define stack_addr(regs) ((unsigned long *)kernel_stack_pointer(regs))
-
#define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\
(((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \
(b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) | \
@@ -568,7 +566,8 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
{
unsigned long *sara = stack_addr(regs);
- ri->ret_addr = (kprobe_opcode_t *) *sara;
+ ri->ret_addrp = (kprobe_opcode_t **) sara;
+ ri->ret_addr = *ri->ret_addrp;
/* Replace the return addr with trampoline addr */
*sara = (unsigned long) &kretprobe_trampoline;
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 7627455047c2..8a4fb3109d6b 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -8,6 +8,7 @@
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
#include <linux/export.h>
+#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
@@ -37,8 +38,13 @@ static void noinline __save_stack_trace(struct stack_trace *trace,
struct unwind_state state;
unsigned long addr;
- if (regs)
- save_stack_address(trace, regs->ip, nosched);
+ if (regs) {
+ /* XXX: Currently broken -- stack_addr(regs) doesn't match entry. */
+ addr = regs->ip;
+ //addr = ftrace_graph_ret_addr(current, &state.graph_idx, addr, stack_addr(regs));
+ addr = kretprobe_ret_addr(current, addr, stack_addr(regs));
+ save_stack_address(trace, addr, nosched);
+ }
for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 3dc26f95d46e..47062427e9a3 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -1,4 +1,5 @@
#include <linux/sched.h>
+#include <linux/kprobes.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/interrupt.h>
@@ -270,6 +271,7 @@ static bool update_stack_state(struct unwind_state *state,
addr = READ_ONCE_TASK_STACK(state->task, *addr_p);
state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
addr, addr_p);
+ state->ip = kretprobe_ret_addr(state->task, state->ip, addr_p);
}
/* Save the original stack pointer for unwind_dump(): */
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
index 4f0e17b90463..554fd7c5c331 100644
--- a/arch/x86/kernel/unwind_guess.c
+++ b/arch/x86/kernel/unwind_guess.c
@@ -1,5 +1,6 @@
#include <linux/sched.h>
#include <linux/ftrace.h>
+#include <linux/kprobes.h>
#include <asm/ptrace.h>
#include <asm/bitops.h>
#include <asm/stacktrace.h>
@@ -14,8 +15,10 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
addr = READ_ONCE_NOCHECK(*state->sp);
- return ftrace_graph_ret_addr(state->task, &state->graph_idx,
+ addr = ftrace_graph_ret_addr(state->task, &state->graph_idx,
addr, state->sp);
+ addr = kretprobe_ret_addr(state->task, addr, state->sp);
+ return addr;
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 26038eacf74a..b6393500d505 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -1,5 +1,6 @@
#include <linux/module.h>
#include <linux/sort.h>
+#include <linux/kprobes.h>
#include <asm/ptrace.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
@@ -462,6 +463,7 @@ bool unwind_next_frame(struct unwind_state *state)
state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
state->ip, (void *)ip_p);
+ state->ip = kretprobe_ret_addr(state->task, state->ip, (void *)ip_p);
state->sp = sp;
state->regs = NULL;
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index e909413e4e38..3a01f9998064 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -172,6 +172,7 @@ struct kretprobe_instance {
struct hlist_node hlist;
struct kretprobe *rp;
kprobe_opcode_t *ret_addr;
+ kprobe_opcode_t **ret_addrp;
struct task_struct *task;
char data[0];
};
@@ -203,6 +204,7 @@ static inline int kprobes_built_in(void)
extern void arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs);
extern int arch_trampoline_kprobe(struct kprobe *p);
+extern void kretprobe_trampoline(void);
#else /* CONFIG_KRETPROBES */
static inline void arch_prepare_kretprobe(struct kretprobe *rp,
struct pt_regs *regs)
@@ -212,6 +214,9 @@ static inline int arch_trampoline_kprobe(struct kprobe *p)
{
return 0;
}
+static inline void kretprobe_trampoline(void)
+{
+}
#endif /* CONFIG_KRETPROBES */
extern struct kretprobe_blackpoint kretprobe_blacklist[];
@@ -341,7 +346,7 @@ struct kprobe *get_kprobe(void *addr);
void kretprobe_hash_lock(struct task_struct *tsk,
struct hlist_head **head, unsigned long *flags);
void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags);
-struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk);
+struct hlist_head *kretprobe_inst_table_head(struct task_struct *tsk);
/* kprobe_running() will just return the current_kprobe on this CPU */
static inline struct kprobe *kprobe_running(void)
@@ -371,6 +376,9 @@ void unregister_kretprobe(struct kretprobe *rp);
int register_kretprobes(struct kretprobe **rps, int num);
void unregister_kretprobes(struct kretprobe **rps, int num);
+unsigned long kretprobe_ret_addr(struct task_struct *tsk, unsigned long ret,
+ unsigned long *retp);
+
void kprobe_flush_task(struct task_struct *tk);
void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
@@ -425,6 +433,11 @@ static inline void unregister_kretprobe(struct kretprobe *rp)
static inline void unregister_kretprobes(struct kretprobe **rps, int num)
{
}
+unsigned long kretprobe_ret_addr(struct task_struct *task, unsigned long ret,
+ unsigned long *retp)
+{
+ return ret;
+}
static inline void kprobe_flush_task(struct task_struct *tk)
{
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 90e98e233647..ed78141664ec 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -83,6 +83,11 @@ static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
return &(kretprobe_table_locks[hash].lock);
}
+struct hlist_head *kretprobe_inst_table_head(struct task_struct *tsk)
+{
+ return &kretprobe_inst_table[hash_ptr(tsk, KPROBE_HASH_BITS)];
+}
+
/* Blacklist -- list of struct kprobe_blacklist_entry */
static LIST_HEAD(kprobe_blacklist);
@@ -1206,6 +1211,15 @@ __releases(hlist_lock)
}
NOKPROBE_SYMBOL(kretprobe_table_unlock);
+static bool kretprobe_hash_is_locked(struct task_struct *tsk)
+{
+ unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
+ raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
+
+ return raw_spin_is_locked(hlist_lock);
+}
+NOKPROBE_SYMBOL(kretprobe_hash_is_locked);
+
/*
* This function is called from finish_task_switch when task tk becomes dead,
* so that we can recycle any function-return probe instances associated
@@ -1856,6 +1870,41 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
}
NOKPROBE_SYMBOL(pre_handler_kretprobe);
+unsigned long kretprobe_ret_addr(struct task_struct *tsk, unsigned long ret,
+ unsigned long *retp)
+{
+ struct kretprobe_instance *ri;
+ unsigned long flags = 0;
+ struct hlist_head *head;
+ bool need_lock;
+
+ if (likely(ret != (unsigned long) &kretprobe_trampoline))
+ return ret;
+
+ need_lock = !kretprobe_hash_is_locked(tsk);
+ if (WARN_ON(need_lock))
+ kretprobe_hash_lock(tsk, &head, &flags);
+ else
+ head = kretprobe_inst_table_head(tsk);
+
+ hlist_for_each_entry(ri, head, hlist) {
+ if (ri->task != current)
+ continue;
+ if (ri->ret_addr == (kprobe_opcode_t *) &kretprobe_trampoline)
+ continue;
+ if (ri->ret_addrp == (kprobe_opcode_t **) retp) {
+ ret = (unsigned long) ri->ret_addr;
+ goto out;
+ }
+ }
+
+out:
+ if (need_lock)
+ kretprobe_hash_unlock(tsk, &flags);
+ return ret;
+}
+NOKPROBE_SYMBOL(kretprobe_ret_addr);
+
bool __weak arch_kprobe_on_func_entry(unsigned long offset)
{
return !offset;
@@ -2005,6 +2054,12 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
}
NOKPROBE_SYMBOL(pre_handler_kretprobe);
+unsigned long kretprobe_ret_addr(struct task_struct *tsk, unsigned long ret,
+ unsigned long *retp)
+{
+ return ret;
+}
+NOKPROBE_SYMBOL(kretprobe_ret_addr);
#endif /* CONFIG_KRETPROBES */
/* Set the kprobe gone and remove its instruction buffer. */
--
2.19.1
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply related
* [PATCH net-next] sock: Reset dst when changing sk_mark via setsockopt
From: David Barmann @ 2018-11-07 22:33 UTC (permalink / raw)
To: netdev
When setting the SO_MARK socket option, the dst needs to be reset so
that a new route lookup is performed.
This fixes the case where an application wants to change routing by
setting a new sk_mark. If this is done after some packets have already
been sent, the dst is cached and has no effect.
Signed-off-by: David Barmann <david.barmann@stackpath.com>
---
net/core/sock.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/net/core/sock.c b/net/core/sock.c
index 6fcc4bc07d19..187badac24a3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -950,10 +950,14 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
clear_bit(SOCK_PASSSEC, &sock->flags);
break;
case SO_MARK:
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
ret = -EPERM;
- else
+ } else {
+ struct dst_entry *dst = sk_dst_get(sk);
sk->sk_mark = val;
+ sk_dst_reset(sk);
+ dst_release(dst);
+ }
break;
case SO_RXQ_OVFL:
--
2.14.4
^ permalink raw reply related
* [PATCH v2 bpf-next 0/3] bpftool: support loading flow dissector
From: Stanislav Fomichev @ 2018-11-07 22:43 UTC (permalink / raw)
To: netdev, linux-kselftest, ast, daniel, shuah, jakub.kicinski,
quentin.monnet
Cc: guro, jiong.wang, sdf, bhole_prashant_q7, john.fastabend, jbenc,
treeze.taeung, yhs, osk, sandipan
v2 changes:
* addressed comments/style issues from Jakub Kicinski & Quentin Monnet
* removed logic that populates jump table
* added cleanup for partial failure in bpf_object__pin
This patch series adds support for loading and attaching flow dissector
programs from the bpftool:
* first patch fixes flow dissector section name in the selftests (so
libbpf auto-detection works)
* second patch adds proper cleanup to bpf_object__pin which is now being
used to attach all flow dissector progs/maps
* third patch adds actual support to the bpftool
See third patch for the description/details.
Stanislav Fomichev (3):
selftests/bpf: rename flow dissector section to flow_dissector
libbpf: cleanup after partial failure in bpf_object__pin
bpftool: support loading flow dissector
.../bpftool/Documentation/bpftool-prog.rst | 26 +++--
tools/bpf/bpftool/bash-completion/bpftool | 2 +-
tools/bpf/bpftool/common.c | 30 +++---
tools/bpf/bpftool/main.h | 1 +
tools/bpf/bpftool/prog.c | 94 ++++++++++++++-----
tools/lib/bpf/libbpf.c | 58 ++++++++++--
tools/testing/selftests/bpf/bpf_flow.c | 2 +-
.../selftests/bpf/test_flow_dissector.sh | 2 +-
8 files changed, 151 insertions(+), 64 deletions(-)
--
2.19.1.930.g4563a0d9d0-goog
^ permalink raw reply
* [PATCH bpf-next 1/3] selftests/bpf: rename flow dissector section to flow_dissector
From: Stanislav Fomichev @ 2018-11-07 22:43 UTC (permalink / raw)
To: netdev, linux-kselftest, ast, daniel, shuah, jakub.kicinski,
quentin.monnet
Cc: guro, jiong.wang, sdf, bhole_prashant_q7, john.fastabend, jbenc,
treeze.taeung, yhs, osk, sandipan
In-Reply-To: <20181107224356.73080-1-sdf@google.com>
Makes it compatible with the logic that derives program type
from section name in libbpf_prog_type_by_name.
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
tools/testing/selftests/bpf/bpf_flow.c | 2 +-
tools/testing/selftests/bpf/test_flow_dissector.sh | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
index 107350a7821d..b9798f558ca7 100644
--- a/tools/testing/selftests/bpf/bpf_flow.c
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -116,7 +116,7 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
return BPF_DROP;
}
-SEC("dissect")
+SEC("flow_dissector")
int _dissect(struct __sk_buff *skb)
{
if (!skb->vlan_present)
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
index c0fb073b5eab..d23d4da66b83 100755
--- a/tools/testing/selftests/bpf/test_flow_dissector.sh
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -59,7 +59,7 @@ else
fi
# Attach BPF program
-./flow_dissector_load -p bpf_flow.o -s dissect
+./flow_dissector_load -p bpf_flow.o -s flow_dissector
# Setup
tc qdisc add dev lo ingress
--
2.19.1.930.g4563a0d9d0-goog
^ permalink raw reply related
* [PATCH bpf-next 2/3] libbpf: cleanup after partial failure in bpf_object__pin
From: Stanislav Fomichev @ 2018-11-07 22:43 UTC (permalink / raw)
To: netdev, linux-kselftest, ast, daniel, shuah, jakub.kicinski,
quentin.monnet
Cc: guro, jiong.wang, sdf, bhole_prashant_q7, john.fastabend, jbenc,
treeze.taeung, yhs, osk, sandipan
In-Reply-To: <20181107224356.73080-1-sdf@google.com>
bpftool will use bpf_object__pin in the next commit to pin all programs
and maps from the file; in case of a partial failure, we need to get
back to the clean state (undo previous program/map pins).
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
tools/lib/bpf/libbpf.c | 58 ++++++++++++++++++++++++++++++++++--------
1 file changed, 48 insertions(+), 10 deletions(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d6e62e90e8d4..309abe7196f3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1803,14 +1803,17 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
len = snprintf(buf, PATH_MAX, "%s/%s", path,
bpf_map__name(map));
- if (len < 0)
- return -EINVAL;
- else if (len >= PATH_MAX)
- return -ENAMETOOLONG;
+ if (len < 0) {
+ err = -EINVAL;
+ goto err_unpin_maps;
+ } else if (len >= PATH_MAX) {
+ err = -ENAMETOOLONG;
+ goto err_unpin_maps;
+ }
err = bpf_map__pin(map, buf);
if (err)
- return err;
+ goto err_unpin_maps;
}
bpf_object__for_each_program(prog, obj) {
@@ -1819,17 +1822,52 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
len = snprintf(buf, PATH_MAX, "%s/%s", path,
prog->section_name);
- if (len < 0)
- return -EINVAL;
- else if (len >= PATH_MAX)
- return -ENAMETOOLONG;
+ if (len < 0) {
+ err = -EINVAL;
+ goto err_unpin_programs;
+ } else if (len >= PATH_MAX) {
+ err = -ENAMETOOLONG;
+ goto err_unpin_programs;
+ }
err = bpf_program__pin(prog, buf);
if (err)
- return err;
+ goto err_unpin_programs;
}
return 0;
+
+err_unpin_programs:
+ bpf_object__for_each_program(prog, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ prog->section_name);
+ if (len < 0)
+ continue;
+ else if (len >= PATH_MAX)
+ continue;
+
+ unlink(buf);
+ }
+
+err_unpin_maps:
+ bpf_map__for_each(map, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0)
+ continue;
+ else if (len >= PATH_MAX)
+ continue;
+
+ unlink(buf);
+ }
+
+ return err;
}
void bpf_object__close(struct bpf_object *obj)
--
2.19.1.930.g4563a0d9d0-goog
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox