OpenCloudOS-Kernel/net/sched/act_pedit.c

539 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/act_pedit.c Generic packet editor
*
* Authors: Jamal Hadi Salim (2002-4)
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/module.h>
#include <linux/init.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <linux/tc_act/tc_pedit.h>
#include <net/tc_act/tc_pedit.h>
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
#include <uapi/linux/tc_act/tc_pedit.h>
net/sched: act_pedit: validate the control action inside init() the following script: # tc filter add dev crash0 egress matchall \ > action pedit ex munge ip ttl set 10 pass index 90 # tc actions replace action pedit \ > ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action pedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: pedit action goto chain 42 keys 1 index 90 ref 2 bind 1 key #0 at ipv4+8: val 0a000000 mask 00ffffff cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff94a73db03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff94a6ee4c0700 RCX: 000000000000000a RDX: 0000000000000000 RSI: ffff94a6ed22c800 RDI: 0000000000000000 RBP: ffff94a73db03c80 R08: ffff94a7386fa4c8 R09: ffff94a73229ea20 R10: 0000000000000000 R11: 0000000000000000 R12: ffff94a6ed22cb00 R13: ffff94a6ed22cb08 R14: 0000000000000001 R15: ffff94a6ed22c800 FS: 0000000000000000(0000) GS:ffff94a73db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007120e002 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 4e ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffab1740387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffb18184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000f168fa695f9a9 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_pedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep aesni_intel snd_hda_core crypto_simd snd_seq cryptd glue_helper snd_seq_device snd_pcm joydev snd_timer pcspkr virtio_balloon snd soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper virtio_net net_failover syscopyarea sysfillrect sysimgblt failover virtio_blk fb_sys_fops virtio_console ttm drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_pedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:07 +08:00
#include <net/pkt_cls.h>
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 09:58:21 +08:00
static unsigned int pedit_net_id;
static struct tc_action_ops act_pedit_ops;
static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = {
[TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) },
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
[TCA_PEDIT_KEYS_EX] = { .type = NLA_NESTED },
};
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
static const struct nla_policy pedit_key_ex_policy[TCA_PEDIT_KEY_EX_MAX + 1] = {
[TCA_PEDIT_KEY_EX_HTYPE] = { .type = NLA_U16 },
[TCA_PEDIT_KEY_EX_CMD] = { .type = NLA_U16 },
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
};
static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla,
u8 n)
{
struct tcf_pedit_key_ex *keys_ex;
struct tcf_pedit_key_ex *k;
const struct nlattr *ka;
int err = -EINVAL;
int rem;
net/sched: act_pedit: fix WARN() in the traffic path when configuring act_pedit rules, the number of keys is validated only on addition of a new entry. This is not sufficient to avoid hitting a WARN() in the traffic path: for example, it is possible to replace a valid entry with a new one having 0 extended keys, thus causing splats in dmesg like: pedit BUG: index 42 WARNING: CPU: 2 PID: 4054 at net/sched/act_pedit.c:410 tcf_pedit_act+0xc84/0x1200 [act_pedit] [...] RIP: 0010:tcf_pedit_act+0xc84/0x1200 [act_pedit] Code: 89 fa 48 c1 ea 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e ac 00 00 00 48 8b 44 24 10 48 c7 c7 a0 c4 e4 c0 8b 70 18 e8 1c 30 95 ea <0f> 0b e9 a0 fa ff ff e8 00 03 f5 ea e9 14 f4 ff ff 48 89 58 40 e9 RSP: 0018:ffff888077c9f320 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffffac2983a2 RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff888053927bec RBP: dffffc0000000000 R08: ffffed100a726209 R09: ffffed100a726209 R10: 0000000000000001 R11: ffffed100a726208 R12: ffff88804beea780 R13: ffff888079a77400 R14: ffff88804beea780 R15: ffff888027ab2000 FS: 00007fdeec9bd740(0000) GS:ffff888053900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffdb3dfd000 CR3: 000000004adb4006 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x105/0x3f0 tcf_classify+0xf2/0x410 __dev_queue_xmit+0xcbf/0x2ae0 ip_finish_output2+0x711/0x1fb0 ip_output+0x1bf/0x4b0 ip_send_skb+0x37/0xa0 raw_sendmsg+0x180c/0x2430 sock_sendmsg+0xdb/0x110 __sys_sendto+0x257/0x2b0 __x64_sys_sendto+0xdd/0x1b0 do_syscall_64+0xa5/0x4e0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fdeeb72e993 Code: 48 8b 0d e0 74 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 0d d6 2c 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 4b cc 00 00 48 89 04 24 RSP: 002b:00007ffdb3de8a18 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 000055c81972b700 RCX: 00007fdeeb72e993 RDX: 0000000000000040 RSI: 000055c81972b700 RDI: 0000000000000003 RBP: 00007ffdb3dea130 R08: 000055c819728510 R09: 0000000000000010 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040 R13: 000055c81972b6c0 R14: 000055c81972969c R15: 0000000000000080 Fix this moving the check on 'nkeys' earlier in tcf_pedit_init(), so that attempts to install rules having 0 keys are always rejected with -EINVAL. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-20 06:47:33 +08:00
if (!nla)
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
return NULL;
keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL);
if (!keys_ex)
return ERR_PTR(-ENOMEM);
k = keys_ex;
nla_for_each_nested(ka, nla, rem) {
struct nlattr *tb[TCA_PEDIT_KEY_EX_MAX + 1];
if (!n) {
err = -EINVAL;
goto err_out;
}
n--;
if (nla_type(ka) != TCA_PEDIT_KEY_EX) {
err = -EINVAL;
goto err_out;
}
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
err = nla_parse_nested_deprecated(tb, TCA_PEDIT_KEY_EX_MAX,
ka, pedit_key_ex_policy,
NULL);
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
if (err)
goto err_out;
if (!tb[TCA_PEDIT_KEY_EX_HTYPE] ||
!tb[TCA_PEDIT_KEY_EX_CMD]) {
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
err = -EINVAL;
goto err_out;
}
k->htype = nla_get_u16(tb[TCA_PEDIT_KEY_EX_HTYPE]);
k->cmd = nla_get_u16(tb[TCA_PEDIT_KEY_EX_CMD]);
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
if (k->htype > TCA_PEDIT_HDR_TYPE_MAX ||
k->cmd > TCA_PEDIT_CMD_MAX) {
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
err = -EINVAL;
goto err_out;
}
k++;
}
if (n) {
err = -EINVAL;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
goto err_out;
}
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
return keys_ex;
err_out:
kfree(keys_ex);
return ERR_PTR(err);
}
static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
struct tcf_pedit_key_ex *keys_ex, int n)
{
struct nlattr *keys_start = nla_nest_start_noflag(skb,
TCA_PEDIT_KEYS_EX);
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
net/sched: act_pedit: fix dump of extended layered op in the (rare) case of failure in nla_nest_start(), missing NULL checks in tcf_pedit_key_ex_dump() can make the following command # tc action add action pedit ex munge ip ttl set 64 dereference a NULL pointer: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000007d1cd067 P4D 800000007d1cd067 PUD 7acd3067 PMD 0 Oops: 0002 [#1] SMP PTI CPU: 0 PID: 3336 Comm: tc Tainted: G E 4.18.0.pedit+ #425 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_pedit_dump+0x19d/0x358 [act_pedit] Code: be 02 00 00 00 48 89 df 66 89 44 24 20 e8 9b b1 fd e0 85 c0 75 46 8b 83 c8 00 00 00 49 83 c5 08 48 03 83 d0 00 00 00 4d 39 f5 <66> 89 04 25 00 00 00 00 0f 84 81 01 00 00 41 8b 45 00 48 8d 4c 24 RSP: 0018:ffffb5d4004478a8 EFLAGS: 00010246 RAX: ffff8880fcda2070 RBX: ffff8880fadd2900 RCX: 0000000000000000 RDX: 0000000000000002 RSI: ffffb5d4004478ca RDI: ffff8880fcda206e RBP: ffff8880fb9cb900 R08: 0000000000000008 R09: ffff8880fcda206e R10: ffff8880fadd2900 R11: 0000000000000000 R12: ffff8880fd26cf40 R13: ffff8880fc957430 R14: ffff8880fc957430 R15: ffff8880fb9cb988 FS: 00007f75a537a740(0000) GS:ffff8880fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a2fa005 CR4: 00000000001606f0 Call Trace: ? __nla_reserve+0x38/0x50 tcf_action_dump_1+0xd2/0x130 tcf_action_dump+0x6a/0xf0 tca_get_fill.constprop.31+0xa3/0x120 tcf_action_add+0xd1/0x170 tc_ctl_action+0x137/0x150 rtnetlink_rcv_msg+0x263/0x2d0 ? _cond_resched+0x15/0x40 ? rtnl_calcit.isra.30+0x110/0x110 netlink_rcv_skb+0x4d/0x130 netlink_unicast+0x1a3/0x250 netlink_sendmsg+0x2ae/0x3a0 sock_sendmsg+0x36/0x40 ___sys_sendmsg+0x26f/0x2d0 ? do_wp_page+0x8e/0x5f0 ? handle_pte_fault+0x6c3/0xf50 ? __handle_mm_fault+0x38e/0x520 ? __sys_sendmsg+0x5e/0xa0 __sys_sendmsg+0x5e/0xa0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f75a4583ba0 Code: c3 48 8b 05 f2 62 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d fd c3 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ae cc 00 00 48 89 04 24 RSP: 002b:00007fff60ee7418 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fff60ee7540 RCX: 00007f75a4583ba0 RDX: 0000000000000000 RSI: 00007fff60ee7490 RDI: 0000000000000003 RBP: 000000005b842d3e R08: 0000000000000002 R09: 0000000000000000 R10: 00007fff60ee6ea0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff60ee7554 R14: 0000000000000001 R15: 000000000066c100 Modules linked in: act_pedit(E) ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul ext4 crc32_pclmul mbcache ghash_clmulni_intel jbd2 pcbc snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer cryptd glue_helper snd joydev pcspkr soundcore virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi virtio_net net_failover virtio_blk virtio_console failover qxl crc32c_intel drm_kms_helper syscopyarea serio_raw sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix virtio_pci libata virtio_ring i2c_core virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_pedit] CR2: 0000000000000000 Like it's done for other TC actions, give up dumping pedit rules and return an error if nla_nest_start() returns NULL. Fixes: 71d0ed7079df ("net/act_pedit: Support using offset relative to the conventional network headers") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-28 04:56:22 +08:00
if (!keys_start)
goto nla_failure;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
for (; n > 0; n--) {
struct nlattr *key_start;
key_start = nla_nest_start_noflag(skb, TCA_PEDIT_KEY_EX);
net/sched: act_pedit: fix dump of extended layered op in the (rare) case of failure in nla_nest_start(), missing NULL checks in tcf_pedit_key_ex_dump() can make the following command # tc action add action pedit ex munge ip ttl set 64 dereference a NULL pointer: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000007d1cd067 P4D 800000007d1cd067 PUD 7acd3067 PMD 0 Oops: 0002 [#1] SMP PTI CPU: 0 PID: 3336 Comm: tc Tainted: G E 4.18.0.pedit+ #425 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_pedit_dump+0x19d/0x358 [act_pedit] Code: be 02 00 00 00 48 89 df 66 89 44 24 20 e8 9b b1 fd e0 85 c0 75 46 8b 83 c8 00 00 00 49 83 c5 08 48 03 83 d0 00 00 00 4d 39 f5 <66> 89 04 25 00 00 00 00 0f 84 81 01 00 00 41 8b 45 00 48 8d 4c 24 RSP: 0018:ffffb5d4004478a8 EFLAGS: 00010246 RAX: ffff8880fcda2070 RBX: ffff8880fadd2900 RCX: 0000000000000000 RDX: 0000000000000002 RSI: ffffb5d4004478ca RDI: ffff8880fcda206e RBP: ffff8880fb9cb900 R08: 0000000000000008 R09: ffff8880fcda206e R10: ffff8880fadd2900 R11: 0000000000000000 R12: ffff8880fd26cf40 R13: ffff8880fc957430 R14: ffff8880fc957430 R15: ffff8880fb9cb988 FS: 00007f75a537a740(0000) GS:ffff8880fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a2fa005 CR4: 00000000001606f0 Call Trace: ? __nla_reserve+0x38/0x50 tcf_action_dump_1+0xd2/0x130 tcf_action_dump+0x6a/0xf0 tca_get_fill.constprop.31+0xa3/0x120 tcf_action_add+0xd1/0x170 tc_ctl_action+0x137/0x150 rtnetlink_rcv_msg+0x263/0x2d0 ? _cond_resched+0x15/0x40 ? rtnl_calcit.isra.30+0x110/0x110 netlink_rcv_skb+0x4d/0x130 netlink_unicast+0x1a3/0x250 netlink_sendmsg+0x2ae/0x3a0 sock_sendmsg+0x36/0x40 ___sys_sendmsg+0x26f/0x2d0 ? do_wp_page+0x8e/0x5f0 ? handle_pte_fault+0x6c3/0xf50 ? __handle_mm_fault+0x38e/0x520 ? __sys_sendmsg+0x5e/0xa0 __sys_sendmsg+0x5e/0xa0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f75a4583ba0 Code: c3 48 8b 05 f2 62 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d fd c3 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ae cc 00 00 48 89 04 24 RSP: 002b:00007fff60ee7418 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fff60ee7540 RCX: 00007f75a4583ba0 RDX: 0000000000000000 RSI: 00007fff60ee7490 RDI: 0000000000000003 RBP: 000000005b842d3e R08: 0000000000000002 R09: 0000000000000000 R10: 00007fff60ee6ea0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff60ee7554 R14: 0000000000000001 R15: 000000000066c100 Modules linked in: act_pedit(E) ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul ext4 crc32_pclmul mbcache ghash_clmulni_intel jbd2 pcbc snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer cryptd glue_helper snd joydev pcspkr soundcore virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi virtio_net net_failover virtio_blk virtio_console failover qxl crc32c_intel drm_kms_helper syscopyarea serio_raw sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix virtio_pci libata virtio_ring i2c_core virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_pedit] CR2: 0000000000000000 Like it's done for other TC actions, give up dumping pedit rules and return an error if nla_nest_start() returns NULL. Fixes: 71d0ed7079df ("net/act_pedit: Support using offset relative to the conventional network headers") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-28 04:56:22 +08:00
if (!key_start)
goto nla_failure;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype) ||
net/sched: act_pedit: fix dump of extended layered op in the (rare) case of failure in nla_nest_start(), missing NULL checks in tcf_pedit_key_ex_dump() can make the following command # tc action add action pedit ex munge ip ttl set 64 dereference a NULL pointer: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000007d1cd067 P4D 800000007d1cd067 PUD 7acd3067 PMD 0 Oops: 0002 [#1] SMP PTI CPU: 0 PID: 3336 Comm: tc Tainted: G E 4.18.0.pedit+ #425 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_pedit_dump+0x19d/0x358 [act_pedit] Code: be 02 00 00 00 48 89 df 66 89 44 24 20 e8 9b b1 fd e0 85 c0 75 46 8b 83 c8 00 00 00 49 83 c5 08 48 03 83 d0 00 00 00 4d 39 f5 <66> 89 04 25 00 00 00 00 0f 84 81 01 00 00 41 8b 45 00 48 8d 4c 24 RSP: 0018:ffffb5d4004478a8 EFLAGS: 00010246 RAX: ffff8880fcda2070 RBX: ffff8880fadd2900 RCX: 0000000000000000 RDX: 0000000000000002 RSI: ffffb5d4004478ca RDI: ffff8880fcda206e RBP: ffff8880fb9cb900 R08: 0000000000000008 R09: ffff8880fcda206e R10: ffff8880fadd2900 R11: 0000000000000000 R12: ffff8880fd26cf40 R13: ffff8880fc957430 R14: ffff8880fc957430 R15: ffff8880fb9cb988 FS: 00007f75a537a740(0000) GS:ffff8880fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a2fa005 CR4: 00000000001606f0 Call Trace: ? __nla_reserve+0x38/0x50 tcf_action_dump_1+0xd2/0x130 tcf_action_dump+0x6a/0xf0 tca_get_fill.constprop.31+0xa3/0x120 tcf_action_add+0xd1/0x170 tc_ctl_action+0x137/0x150 rtnetlink_rcv_msg+0x263/0x2d0 ? _cond_resched+0x15/0x40 ? rtnl_calcit.isra.30+0x110/0x110 netlink_rcv_skb+0x4d/0x130 netlink_unicast+0x1a3/0x250 netlink_sendmsg+0x2ae/0x3a0 sock_sendmsg+0x36/0x40 ___sys_sendmsg+0x26f/0x2d0 ? do_wp_page+0x8e/0x5f0 ? handle_pte_fault+0x6c3/0xf50 ? __handle_mm_fault+0x38e/0x520 ? __sys_sendmsg+0x5e/0xa0 __sys_sendmsg+0x5e/0xa0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f75a4583ba0 Code: c3 48 8b 05 f2 62 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d fd c3 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ae cc 00 00 48 89 04 24 RSP: 002b:00007fff60ee7418 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fff60ee7540 RCX: 00007f75a4583ba0 RDX: 0000000000000000 RSI: 00007fff60ee7490 RDI: 0000000000000003 RBP: 000000005b842d3e R08: 0000000000000002 R09: 0000000000000000 R10: 00007fff60ee6ea0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff60ee7554 R14: 0000000000000001 R15: 000000000066c100 Modules linked in: act_pedit(E) ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul ext4 crc32_pclmul mbcache ghash_clmulni_intel jbd2 pcbc snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer cryptd glue_helper snd joydev pcspkr soundcore virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi virtio_net net_failover virtio_blk virtio_console failover qxl crc32c_intel drm_kms_helper syscopyarea serio_raw sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix virtio_pci libata virtio_ring i2c_core virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_pedit] CR2: 0000000000000000 Like it's done for other TC actions, give up dumping pedit rules and return an error if nla_nest_start() returns NULL. Fixes: 71d0ed7079df ("net/act_pedit: Support using offset relative to the conventional network headers") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-28 04:56:22 +08:00
nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd))
goto nla_failure;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
nla_nest_end(skb, key_start);
keys_ex++;
}
nla_nest_end(skb, keys_start);
return 0;
net/sched: act_pedit: fix dump of extended layered op in the (rare) case of failure in nla_nest_start(), missing NULL checks in tcf_pedit_key_ex_dump() can make the following command # tc action add action pedit ex munge ip ttl set 64 dereference a NULL pointer: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000007d1cd067 P4D 800000007d1cd067 PUD 7acd3067 PMD 0 Oops: 0002 [#1] SMP PTI CPU: 0 PID: 3336 Comm: tc Tainted: G E 4.18.0.pedit+ #425 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_pedit_dump+0x19d/0x358 [act_pedit] Code: be 02 00 00 00 48 89 df 66 89 44 24 20 e8 9b b1 fd e0 85 c0 75 46 8b 83 c8 00 00 00 49 83 c5 08 48 03 83 d0 00 00 00 4d 39 f5 <66> 89 04 25 00 00 00 00 0f 84 81 01 00 00 41 8b 45 00 48 8d 4c 24 RSP: 0018:ffffb5d4004478a8 EFLAGS: 00010246 RAX: ffff8880fcda2070 RBX: ffff8880fadd2900 RCX: 0000000000000000 RDX: 0000000000000002 RSI: ffffb5d4004478ca RDI: ffff8880fcda206e RBP: ffff8880fb9cb900 R08: 0000000000000008 R09: ffff8880fcda206e R10: ffff8880fadd2900 R11: 0000000000000000 R12: ffff8880fd26cf40 R13: ffff8880fc957430 R14: ffff8880fc957430 R15: ffff8880fb9cb988 FS: 00007f75a537a740(0000) GS:ffff8880fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a2fa005 CR4: 00000000001606f0 Call Trace: ? __nla_reserve+0x38/0x50 tcf_action_dump_1+0xd2/0x130 tcf_action_dump+0x6a/0xf0 tca_get_fill.constprop.31+0xa3/0x120 tcf_action_add+0xd1/0x170 tc_ctl_action+0x137/0x150 rtnetlink_rcv_msg+0x263/0x2d0 ? _cond_resched+0x15/0x40 ? rtnl_calcit.isra.30+0x110/0x110 netlink_rcv_skb+0x4d/0x130 netlink_unicast+0x1a3/0x250 netlink_sendmsg+0x2ae/0x3a0 sock_sendmsg+0x36/0x40 ___sys_sendmsg+0x26f/0x2d0 ? do_wp_page+0x8e/0x5f0 ? handle_pte_fault+0x6c3/0xf50 ? __handle_mm_fault+0x38e/0x520 ? __sys_sendmsg+0x5e/0xa0 __sys_sendmsg+0x5e/0xa0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f75a4583ba0 Code: c3 48 8b 05 f2 62 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d fd c3 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ae cc 00 00 48 89 04 24 RSP: 002b:00007fff60ee7418 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fff60ee7540 RCX: 00007f75a4583ba0 RDX: 0000000000000000 RSI: 00007fff60ee7490 RDI: 0000000000000003 RBP: 000000005b842d3e R08: 0000000000000002 R09: 0000000000000000 R10: 00007fff60ee6ea0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff60ee7554 R14: 0000000000000001 R15: 000000000066c100 Modules linked in: act_pedit(E) ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul ext4 crc32_pclmul mbcache ghash_clmulni_intel jbd2 pcbc snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer cryptd glue_helper snd joydev pcspkr soundcore virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi virtio_net net_failover virtio_blk virtio_console failover qxl crc32c_intel drm_kms_helper syscopyarea serio_raw sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix virtio_pci libata virtio_ring i2c_core virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_pedit] CR2: 0000000000000000 Like it's done for other TC actions, give up dumping pedit rules and return an error if nla_nest_start() returns NULL. Fixes: 71d0ed7079df ("net/act_pedit: Support using offset relative to the conventional network headers") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-28 04:56:22 +08:00
nla_failure:
nla_nest_cancel(skb, keys_start);
return -EINVAL;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
}
static int tcf_pedit_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
struct tcf_proto *tp, u32 flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, pedit_net_id);
bool bind = flags & TCA_ACT_FLAGS_BIND;
struct nlattr *tb[TCA_PEDIT_MAX + 1];
net/sched: act_pedit: validate the control action inside init() the following script: # tc filter add dev crash0 egress matchall \ > action pedit ex munge ip ttl set 10 pass index 90 # tc actions replace action pedit \ > ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action pedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: pedit action goto chain 42 keys 1 index 90 ref 2 bind 1 key #0 at ipv4+8: val 0a000000 mask 00ffffff cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff94a73db03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff94a6ee4c0700 RCX: 000000000000000a RDX: 0000000000000000 RSI: ffff94a6ed22c800 RDI: 0000000000000000 RBP: ffff94a73db03c80 R08: ffff94a7386fa4c8 R09: ffff94a73229ea20 R10: 0000000000000000 R11: 0000000000000000 R12: ffff94a6ed22cb00 R13: ffff94a6ed22cb08 R14: 0000000000000001 R15: ffff94a6ed22c800 FS: 0000000000000000(0000) GS:ffff94a73db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007120e002 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 4e ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffab1740387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffb18184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000f168fa695f9a9 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_pedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep aesni_intel snd_hda_core crypto_simd snd_seq cryptd glue_helper snd_seq_device snd_pcm joydev snd_timer pcspkr virtio_balloon snd soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper virtio_net net_failover syscopyarea sysfillrect sysimgblt failover virtio_blk fb_sys_fops virtio_console ttm drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_pedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:07 +08:00
struct tcf_chain *goto_ch = NULL;
struct tc_pedit_key *keys = NULL;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
struct tcf_pedit_key_ex *keys_ex;
struct tc_pedit *parm;
struct nlattr *pattr;
struct tcf_pedit *p;
int ret = 0, err;
int ksize;
u32 index;
if (!nla) {
NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed");
return -EINVAL;
}
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
err = nla_parse_nested_deprecated(tb, TCA_PEDIT_MAX, nla,
pedit_policy, NULL);
if (err < 0)
return err;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
pattr = tb[TCA_PEDIT_PARMS];
if (!pattr)
pattr = tb[TCA_PEDIT_PARMS_EX];
if (!pattr) {
NL_SET_ERR_MSG_MOD(extack, "Missing required TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute");
return -EINVAL;
}
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
parm = nla_data(pattr);
net/sched: act_pedit: fix WARN() in the traffic path when configuring act_pedit rules, the number of keys is validated only on addition of a new entry. This is not sufficient to avoid hitting a WARN() in the traffic path: for example, it is possible to replace a valid entry with a new one having 0 extended keys, thus causing splats in dmesg like: pedit BUG: index 42 WARNING: CPU: 2 PID: 4054 at net/sched/act_pedit.c:410 tcf_pedit_act+0xc84/0x1200 [act_pedit] [...] RIP: 0010:tcf_pedit_act+0xc84/0x1200 [act_pedit] Code: 89 fa 48 c1 ea 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e ac 00 00 00 48 8b 44 24 10 48 c7 c7 a0 c4 e4 c0 8b 70 18 e8 1c 30 95 ea <0f> 0b e9 a0 fa ff ff e8 00 03 f5 ea e9 14 f4 ff ff 48 89 58 40 e9 RSP: 0018:ffff888077c9f320 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffffac2983a2 RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff888053927bec RBP: dffffc0000000000 R08: ffffed100a726209 R09: ffffed100a726209 R10: 0000000000000001 R11: ffffed100a726208 R12: ffff88804beea780 R13: ffff888079a77400 R14: ffff88804beea780 R15: ffff888027ab2000 FS: 00007fdeec9bd740(0000) GS:ffff888053900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffdb3dfd000 CR3: 000000004adb4006 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x105/0x3f0 tcf_classify+0xf2/0x410 __dev_queue_xmit+0xcbf/0x2ae0 ip_finish_output2+0x711/0x1fb0 ip_output+0x1bf/0x4b0 ip_send_skb+0x37/0xa0 raw_sendmsg+0x180c/0x2430 sock_sendmsg+0xdb/0x110 __sys_sendto+0x257/0x2b0 __x64_sys_sendto+0xdd/0x1b0 do_syscall_64+0xa5/0x4e0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fdeeb72e993 Code: 48 8b 0d e0 74 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 0d d6 2c 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 4b cc 00 00 48 89 04 24 RSP: 002b:00007ffdb3de8a18 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 000055c81972b700 RCX: 00007fdeeb72e993 RDX: 0000000000000040 RSI: 000055c81972b700 RDI: 0000000000000003 RBP: 00007ffdb3dea130 R08: 000055c819728510 R09: 0000000000000010 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040 R13: 000055c81972b6c0 R14: 000055c81972969c R15: 0000000000000080 Fix this moving the check on 'nkeys' earlier in tcf_pedit_init(), so that attempts to install rules having 0 keys are always rejected with -EINVAL. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-20 06:47:33 +08:00
if (!parm->nkeys) {
NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
return -EINVAL;
}
ksize = parm->nkeys * sizeof(struct tc_pedit_key);
if (nla_len(pattr) < sizeof(*parm) + ksize) {
NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid");
return -EINVAL;
}
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
keys_ex = tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys);
if (IS_ERR(keys_ex))
return PTR_ERR(keys_ex);
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
ret = tcf_idr_create(tn, index, est, a,
&act_pedit_ops, bind, false, flags);
if (ret) {
tcf_idr_cleanup(tn, index);
goto out_free;
}
ret = ACT_P_CREATED;
} else if (err > 0) {
if (bind)
goto out_free;
if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
ret = -EEXIST;
goto out_release;
}
} else {
ret = err;
goto out_free;
}
net/sched: act_pedit: validate the control action inside init() the following script: # tc filter add dev crash0 egress matchall \ > action pedit ex munge ip ttl set 10 pass index 90 # tc actions replace action pedit \ > ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action pedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: pedit action goto chain 42 keys 1 index 90 ref 2 bind 1 key #0 at ipv4+8: val 0a000000 mask 00ffffff cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff94a73db03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff94a6ee4c0700 RCX: 000000000000000a RDX: 0000000000000000 RSI: ffff94a6ed22c800 RDI: 0000000000000000 RBP: ffff94a73db03c80 R08: ffff94a7386fa4c8 R09: ffff94a73229ea20 R10: 0000000000000000 R11: 0000000000000000 R12: ffff94a6ed22cb00 R13: ffff94a6ed22cb08 R14: 0000000000000001 R15: ffff94a6ed22c800 FS: 0000000000000000(0000) GS:ffff94a73db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007120e002 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 4e ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffab1740387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffb18184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000f168fa695f9a9 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_pedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep aesni_intel snd_hda_core crypto_simd snd_seq cryptd glue_helper snd_seq_device snd_pcm joydev snd_timer pcspkr virtio_balloon snd soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper virtio_net net_failover syscopyarea sysfillrect sysimgblt failover virtio_blk fb_sys_fops virtio_console ttm drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_pedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:07 +08:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0) {
ret = err;
goto out_release;
}
p = to_pedit(*a);
spin_lock_bh(&p->tcf_lock);
if (ret == ACT_P_CREATED ||
(p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys)) {
keys = kmalloc(ksize, GFP_ATOMIC);
if (!keys) {
spin_unlock_bh(&p->tcf_lock);
ret = -ENOMEM;
net/sched: act_pedit: validate the control action inside init() the following script: # tc filter add dev crash0 egress matchall \ > action pedit ex munge ip ttl set 10 pass index 90 # tc actions replace action pedit \ > ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action pedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: pedit action goto chain 42 keys 1 index 90 ref 2 bind 1 key #0 at ipv4+8: val 0a000000 mask 00ffffff cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff94a73db03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff94a6ee4c0700 RCX: 000000000000000a RDX: 0000000000000000 RSI: ffff94a6ed22c800 RDI: 0000000000000000 RBP: ffff94a73db03c80 R08: ffff94a7386fa4c8 R09: ffff94a73229ea20 R10: 0000000000000000 R11: 0000000000000000 R12: ffff94a6ed22cb00 R13: ffff94a6ed22cb08 R14: 0000000000000001 R15: ffff94a6ed22c800 FS: 0000000000000000(0000) GS:ffff94a73db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007120e002 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 4e ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffab1740387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffb18184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000f168fa695f9a9 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_pedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep aesni_intel snd_hda_core crypto_simd snd_seq cryptd glue_helper snd_seq_device snd_pcm joydev snd_timer pcspkr virtio_balloon snd soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper virtio_net net_failover syscopyarea sysfillrect sysimgblt failover virtio_blk fb_sys_fops virtio_console ttm drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_pedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:07 +08:00
goto put_chain;
}
kfree(p->tcfp_keys);
p->tcfp_keys = keys;
p->tcfp_nkeys = parm->nkeys;
}
memcpy(p->tcfp_keys, parm->keys, ksize);
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
p->tcfp_flags = parm->flags;
net/sched: act_pedit: validate the control action inside init() the following script: # tc filter add dev crash0 egress matchall \ > action pedit ex munge ip ttl set 10 pass index 90 # tc actions replace action pedit \ > ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action pedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: pedit action goto chain 42 keys 1 index 90 ref 2 bind 1 key #0 at ipv4+8: val 0a000000 mask 00ffffff cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff94a73db03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff94a6ee4c0700 RCX: 000000000000000a RDX: 0000000000000000 RSI: ffff94a6ed22c800 RDI: 0000000000000000 RBP: ffff94a73db03c80 R08: ffff94a7386fa4c8 R09: ffff94a73229ea20 R10: 0000000000000000 R11: 0000000000000000 R12: ffff94a6ed22cb00 R13: ffff94a6ed22cb08 R14: 0000000000000001 R15: ffff94a6ed22c800 FS: 0000000000000000(0000) GS:ffff94a73db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007120e002 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 4e ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffab1740387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffb18184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000f168fa695f9a9 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_pedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep aesni_intel snd_hda_core crypto_simd snd_seq cryptd glue_helper snd_seq_device snd_pcm joydev snd_timer pcspkr virtio_balloon snd soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper virtio_net net_failover syscopyarea sysfillrect sysimgblt failover virtio_blk fb_sys_fops virtio_console ttm drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_pedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:07 +08:00
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
kfree(p->tcfp_keys_ex);
p->tcfp_keys_ex = keys_ex;
spin_unlock_bh(&p->tcf_lock);
net/sched: act_pedit: validate the control action inside init() the following script: # tc filter add dev crash0 egress matchall \ > action pedit ex munge ip ttl set 10 pass index 90 # tc actions replace action pedit \ > ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action pedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: pedit action goto chain 42 keys 1 index 90 ref 2 bind 1 key #0 at ipv4+8: val 0a000000 mask 00ffffff cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff94a73db03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff94a6ee4c0700 RCX: 000000000000000a RDX: 0000000000000000 RSI: ffff94a6ed22c800 RDI: 0000000000000000 RBP: ffff94a73db03c80 R08: ffff94a7386fa4c8 R09: ffff94a73229ea20 R10: 0000000000000000 R11: 0000000000000000 R12: ffff94a6ed22cb00 R13: ffff94a6ed22cb08 R14: 0000000000000001 R15: ffff94a6ed22c800 FS: 0000000000000000(0000) GS:ffff94a73db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007120e002 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 4e ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffab1740387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffb18184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000f168fa695f9a9 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_pedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep aesni_intel snd_hda_core crypto_simd snd_seq cryptd glue_helper snd_seq_device snd_pcm joydev snd_timer pcspkr virtio_balloon snd soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper virtio_net net_failover syscopyarea sysfillrect sysimgblt failover virtio_blk fb_sys_fops virtio_console ttm drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_pedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:07 +08:00
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
return ret;
net/sched: act_pedit: validate the control action inside init() the following script: # tc filter add dev crash0 egress matchall \ > action pedit ex munge ip ttl set 10 pass index 90 # tc actions replace action pedit \ > ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action pedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: pedit action goto chain 42 keys 1 index 90 ref 2 bind 1 key #0 at ipv4+8: val 0a000000 mask 00ffffff cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff94a73db03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff94a6ee4c0700 RCX: 000000000000000a RDX: 0000000000000000 RSI: ffff94a6ed22c800 RDI: 0000000000000000 RBP: ffff94a73db03c80 R08: ffff94a7386fa4c8 R09: ffff94a73229ea20 R10: 0000000000000000 R11: 0000000000000000 R12: ffff94a6ed22cb00 R13: ffff94a6ed22cb08 R14: 0000000000000001 R15: ffff94a6ed22c800 FS: 0000000000000000(0000) GS:ffff94a73db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007120e002 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 4e ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffffab1740387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffb18184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000f168fa695f9a9 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_pedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep aesni_intel snd_hda_core crypto_simd snd_seq cryptd glue_helper snd_seq_device snd_pcm joydev snd_timer pcspkr virtio_balloon snd soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper virtio_net net_failover syscopyarea sysfillrect sysimgblt failover virtio_blk fb_sys_fops virtio_console ttm drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_pedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:07 +08:00
put_chain:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
out_release:
tcf_idr_release(*a, bind);
out_free:
kfree(keys_ex);
return ret;
}
static void tcf_pedit_cleanup(struct tc_action *a)
{
struct tcf_pedit *p = to_pedit(a);
struct tc_pedit_key *keys = p->tcfp_keys;
kfree(keys);
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
kfree(p->tcfp_keys_ex);
}
static bool offset_valid(struct sk_buff *skb, int offset)
{
if (offset > 0 && offset > skb->len)
return false;
if (offset < 0 && -offset > skb_headroom(skb))
return false;
return true;
}
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
static int pedit_skb_hdr_offset(struct sk_buff *skb,
enum pedit_header_type htype, int *hoffset)
{
int ret = -EINVAL;
switch (htype) {
case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
if (skb_mac_header_was_set(skb)) {
*hoffset = skb_mac_offset(skb);
ret = 0;
}
break;
case TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK:
case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
*hoffset = skb_network_offset(skb);
ret = 0;
break;
case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
if (skb_transport_header_was_set(skb)) {
*hoffset = skb_transport_offset(skb);
ret = 0;
}
break;
default:
ret = -EINVAL;
break;
}
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
return ret;
}
static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_pedit *p = to_pedit(a);
int i;
if (skb_unclone(skb, GFP_ATOMIC))
return p->tcf_action;
spin_lock(&p->tcf_lock);
tcf_lastuse_update(&p->tcf_tm);
if (p->tcfp_nkeys > 0) {
struct tc_pedit_key *tkey = p->tcfp_keys;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
struct tcf_pedit_key_ex *tkey_ex = p->tcfp_keys_ex;
enum pedit_header_type htype =
TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET;
for (i = p->tcfp_nkeys; i > 0; i--, tkey++) {
u32 *ptr, hdata;
int offset = tkey->off;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
int hoffset;
u32 val;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
int rc;
if (tkey_ex) {
htype = tkey_ex->htype;
cmd = tkey_ex->cmd;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
tkey_ex++;
}
rc = pedit_skb_hdr_offset(skb, htype, &hoffset);
if (rc) {
pr_info("tc action pedit bad header type specified (0x%x)\n",
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
htype);
goto bad;
}
if (tkey->offmask) {
u8 *d, _d;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
if (!offset_valid(skb, hoffset + tkey->at)) {
pr_info("tc action pedit 'at' offset %d out of bounds\n",
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
hoffset + tkey->at);
goto bad;
}
d = skb_header_pointer(skb, hoffset + tkey->at,
sizeof(_d), &_d);
if (!d)
goto bad;
offset += (*d & tkey->offmask) >> tkey->shift;
}
if (offset % 4) {
pr_info("tc action pedit offset must be on 32 bit boundaries\n");
goto bad;
}
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
if (!offset_valid(skb, hoffset + offset)) {
pr_info("tc action pedit offset %d out of bounds\n",
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
hoffset + offset);
goto bad;
}
ptr = skb_header_pointer(skb, hoffset + offset,
sizeof(hdata), &hdata);
if (!ptr)
goto bad;
/* just do it, baby */
switch (cmd) {
case TCA_PEDIT_KEY_EX_CMD_SET:
val = tkey->val;
break;
case TCA_PEDIT_KEY_EX_CMD_ADD:
val = (*ptr + tkey->val) & ~tkey->mask;
break;
default:
pr_info("tc action pedit bad command (%d)\n",
cmd);
goto bad;
}
*ptr = ((*ptr & tkey->mask) ^ val);
if (ptr == &hdata)
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
skb_store_bits(skb, hoffset + offset, ptr, 4);
}
goto done;
} else {
WARN(1, "pedit BUG: index %d\n", p->tcf_index);
}
bad:
p->tcf_qstats.overlimits++;
done:
bstats_update(&p->tcf_bstats, skb);
spin_unlock(&p->tcf_lock);
return p->tcf_action;
}
static void tcf_pedit_stats_update(struct tc_action *a, u64 bytes, u64 packets,
u64 drops, u64 lastuse, bool hw)
{
struct tcf_pedit *d = to_pedit(a);
struct tcf_t *tm = &d->tcf_tm;
tcf_action_update_stats(a, bytes, packets, drops, hw);
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_pedit *p = to_pedit(a);
struct tc_pedit *opt;
struct tcf_t t;
int s;
s = struct_size(opt, keys, p->tcfp_nkeys);
/* netlink spinlocks held above us - must use ATOMIC */
opt = kzalloc(s, GFP_ATOMIC);
if (unlikely(!opt))
return -ENOBUFS;
spin_lock_bh(&p->tcf_lock);
memcpy(opt->keys, p->tcfp_keys, flex_array_size(opt, keys, p->tcfp_nkeys));
opt->index = p->tcf_index;
opt->nkeys = p->tcfp_nkeys;
opt->flags = p->tcfp_flags;
opt->action = p->tcf_action;
opt->refcnt = refcount_read(&p->tcf_refcnt) - ref;
opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
if (p->tcfp_keys_ex) {
net/sched: act_pedit: fix dump of extended layered op in the (rare) case of failure in nla_nest_start(), missing NULL checks in tcf_pedit_key_ex_dump() can make the following command # tc action add action pedit ex munge ip ttl set 64 dereference a NULL pointer: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000007d1cd067 P4D 800000007d1cd067 PUD 7acd3067 PMD 0 Oops: 0002 [#1] SMP PTI CPU: 0 PID: 3336 Comm: tc Tainted: G E 4.18.0.pedit+ #425 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_pedit_dump+0x19d/0x358 [act_pedit] Code: be 02 00 00 00 48 89 df 66 89 44 24 20 e8 9b b1 fd e0 85 c0 75 46 8b 83 c8 00 00 00 49 83 c5 08 48 03 83 d0 00 00 00 4d 39 f5 <66> 89 04 25 00 00 00 00 0f 84 81 01 00 00 41 8b 45 00 48 8d 4c 24 RSP: 0018:ffffb5d4004478a8 EFLAGS: 00010246 RAX: ffff8880fcda2070 RBX: ffff8880fadd2900 RCX: 0000000000000000 RDX: 0000000000000002 RSI: ffffb5d4004478ca RDI: ffff8880fcda206e RBP: ffff8880fb9cb900 R08: 0000000000000008 R09: ffff8880fcda206e R10: ffff8880fadd2900 R11: 0000000000000000 R12: ffff8880fd26cf40 R13: ffff8880fc957430 R14: ffff8880fc957430 R15: ffff8880fb9cb988 FS: 00007f75a537a740(0000) GS:ffff8880fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a2fa005 CR4: 00000000001606f0 Call Trace: ? __nla_reserve+0x38/0x50 tcf_action_dump_1+0xd2/0x130 tcf_action_dump+0x6a/0xf0 tca_get_fill.constprop.31+0xa3/0x120 tcf_action_add+0xd1/0x170 tc_ctl_action+0x137/0x150 rtnetlink_rcv_msg+0x263/0x2d0 ? _cond_resched+0x15/0x40 ? rtnl_calcit.isra.30+0x110/0x110 netlink_rcv_skb+0x4d/0x130 netlink_unicast+0x1a3/0x250 netlink_sendmsg+0x2ae/0x3a0 sock_sendmsg+0x36/0x40 ___sys_sendmsg+0x26f/0x2d0 ? do_wp_page+0x8e/0x5f0 ? handle_pte_fault+0x6c3/0xf50 ? __handle_mm_fault+0x38e/0x520 ? __sys_sendmsg+0x5e/0xa0 __sys_sendmsg+0x5e/0xa0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f75a4583ba0 Code: c3 48 8b 05 f2 62 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d fd c3 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ae cc 00 00 48 89 04 24 RSP: 002b:00007fff60ee7418 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fff60ee7540 RCX: 00007f75a4583ba0 RDX: 0000000000000000 RSI: 00007fff60ee7490 RDI: 0000000000000003 RBP: 000000005b842d3e R08: 0000000000000002 R09: 0000000000000000 R10: 00007fff60ee6ea0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff60ee7554 R14: 0000000000000001 R15: 000000000066c100 Modules linked in: act_pedit(E) ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul ext4 crc32_pclmul mbcache ghash_clmulni_intel jbd2 pcbc snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer cryptd glue_helper snd joydev pcspkr soundcore virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi virtio_net net_failover virtio_blk virtio_console failover qxl crc32c_intel drm_kms_helper syscopyarea serio_raw sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix virtio_pci libata virtio_ring i2c_core virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_pedit] CR2: 0000000000000000 Like it's done for other TC actions, give up dumping pedit rules and return an error if nla_nest_start() returns NULL. Fixes: 71d0ed7079df ("net/act_pedit: Support using offset relative to the conventional network headers") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-28 04:56:22 +08:00
if (tcf_pedit_key_ex_dump(skb,
p->tcfp_keys_ex,
p->tcfp_nkeys))
goto nla_put_failure;
net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai <amir@vadai.me> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-07 15:56:07 +08:00
if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt))
goto nla_put_failure;
} else {
if (nla_put(skb, TCA_PEDIT_PARMS, s, opt))
goto nla_put_failure;
}
tcf_tm_dump(&t, &p->tcf_tm);
if (nla_put_64bit(skb, TCA_PEDIT_TM, sizeof(t), &t, TCA_PEDIT_PAD))
goto nla_put_failure;
spin_unlock_bh(&p->tcf_lock);
kfree(opt);
return skb->len;
nla_put_failure:
spin_unlock_bh(&p->tcf_lock);
nlmsg_trim(skb, b);
kfree(opt);
return -1;
}
static int tcf_pedit_walker(struct net *net, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, pedit_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, pedit_net_id);
return tcf_idr_search(tn, a, index);
}
static struct tc_action_ops act_pedit_ops = {
.kind = "pedit",
.id = TCA_ID_PEDIT,
.owner = THIS_MODULE,
.act = tcf_pedit_act,
.stats_update = tcf_pedit_stats_update,
.dump = tcf_pedit_dump,
.cleanup = tcf_pedit_cleanup,
.init = tcf_pedit_init,
.walk = tcf_pedit_walker,
.lookup = tcf_pedit_search,
.size = sizeof(struct tcf_pedit),
};
static __net_init int pedit_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, pedit_net_id);
return tc_action_net_init(net, tn, &act_pedit_ops);
}
static void __net_exit pedit_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, pedit_net_id);
}
static struct pernet_operations pedit_net_ops = {
.init = pedit_init_net,
.exit_batch = pedit_exit_net,
.id = &pedit_net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_AUTHOR("Jamal Hadi Salim(2002-4)");
MODULE_DESCRIPTION("Generic Packet Editor actions");
MODULE_LICENSE("GPL");
static int __init pedit_init_module(void)
{
return tcf_register_action(&act_pedit_ops, &pedit_net_ops);
}
static void __exit pedit_cleanup_module(void)
{
tcf_unregister_action(&act_pedit_ops, &pedit_net_ops);
}
module_init(pedit_init_module);
module_exit(pedit_cleanup_module);