netfilter: nft_log: complete NFTA_LOG_FLAGS attr support
NFTA_LOG_FLAGS attribute is already supported, but the related
NF_LOG_XXX flags are not exposed to the userspace. So we cannot
explicitly enable log flags to log uid, tcp sequence, ip options
and so on, i.e. such rule "nft add rule filter output log uid"
is not supported yet.
So move NF_LOG_XXX macro definitions to the uapi/../nf_log.h. In
order to keep consistent with other modules, change NF_LOG_MASK to
refer to all supported log flags. On the other hand, add a new
NF_LOG_DEFAULT_MASK to refer to the original default log flags.
Finally, if user specify the unsupported log flags or NFTA_LOG_GROUP
and NFTA_LOG_FLAGS are set at the same time, report EINVAL to the
userspace.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: xt_socket: fix transparent match for IPv6 request sockets
The introduction of TCP_NEW_SYN_RECV state, and the addition of request
sockets to the ehash table seems to have broken the --transparent option
of the socket match for IPv6 (around commit a9407000).
Now that the socket lookup finds the TCP_NEW_SYN_RECV socket instead of the
listener, the --transparent option tries to match on the no_srccheck flag
of the request socket.
Unfortunately, that flag was only set for IPv4 sockets in tcp_v4_init_req()
by copying the transparent flag of the listener socket. This effectively
causes '-m socket --transparent' not match on the ACK packet sent by the
client in a TCP handshake.
Based on the suggestion from Eric Dumazet, this change moves the code
initializing no_srccheck to tcp_conn_request(), rendering the above
scenario working again.
Fixes: a940700003 ("netfilter: xt_socket: prepare for TCP_NEW_SYN_RECV support") Signed-off-by: Alex Badics <alex.badics@balabit.com> Signed-off-by: KOVACS Krisztian <hidden@balabit.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: evict stale entries when user reads /proc/net/nf_conntrack
Fabian reports a possible conntrack memory leak (could not reproduce so
far), however, one minor issue can be easily resolved:
> cat /proc/net/nf_conntrack | wc -l = 5
> 4 minutes required to clean up the table.
We should not report those timed-out entries to the user in first place.
And instead of just skipping those timed-out entries while iterating over
the table we can also zap them (we already do this during ctnetlink
walks, but I forgot about the /proc interface).
Fixes: f330a7fdbe16 ("netfilter: conntrack: get rid of conntrack timer") Reported-by: Fabian Frederick <fabf@skynet.be> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Vishwanath Pai [Thu, 22 Sep 2016 16:43:44 +0000 (12:43 -0400)]
netfilter: xt_hashlimit: Create revision 2 to support higher pps rates
Create a new revision for the hashlimit iptables extension module. Rev 2
will support higher pps of upto 1 million, Version 1 supports only 10k.
To support this we have to increase the size of the variables avg and
burst in hashlimit_cfg to 64-bit. Create two new structs hashlimit_cfg2
and xt_hashlimit_mtinfo2 and also create newer versions of all the
functions for match, checkentry and destroy.
Some of the functions like hashlimit_mt, hashlimit_mt_check etc are very
similar in both rev1 and rev2 with only minor changes, so I have split
those functions and moved all the common code to a *_common function.
Signed-off-by: Vishwanath Pai <vpai@akamai.com> Signed-off-by: Joshua Hunt <johunt@akamai.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Vishwanath Pai [Thu, 22 Sep 2016 16:42:46 +0000 (12:42 -0400)]
netfilter: xt_hashlimit: Prepare for revision 2
I am planning to add a revision 2 for the hashlimit xtables module to
support higher packets per second rates. This patch renames all the
functions and variables related to revision 1 by adding _v1 at the
end of the names.
Signed-off-by: Vishwanath Pai <vpai@akamai.com> Signed-off-by: Joshua Hunt <johunt@akamai.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nft_ct: report error if mark and dir specified simultaneously
NFT_CT_MARK is unrelated to direction, so if NFTA_CT_DIRECTION attr is
specified, report EINVAL to the userspace. This validation check was
already done at nft_ct_get_init, but we missed it in nft_ct_set_init.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nft_ct: unnecessary to require dir when use ct l3proto/protocol
Currently, if the user want to match ct l3proto, we must specify the
direction, for example:
# nft add rule filter input ct original l3proto ipv4
^^^^^^^^
Otherwise, error message will be reported:
# nft add rule filter input ct l3proto ipv4
nft add rule filter input ct l3proto ipv4
<cmdline>:1:1-38: Error: Could not process rule: Invalid argument
add rule filter input ct l3proto ipv4
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Actually, there's no need to require NFTA_CT_DIRECTION attr, because
ct l3proto and protocol are unrelated to direction.
And for compatibility, even if the user specify the NFTA_CT_DIRECTION
attr, do not report error, just skip it.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: seqadj: Fix the wrong ack adjust for the RST packet without ack
It is valid that the TCP RST packet which does not set ack flag, and bytes
of ack number are zero. But current seqadj codes would adjust the "0" ack
to invalid ack number. Actually seqadj need to check the ack flag before
adjust it for these RST packets.
The following is my test case
client is 10.26.98.245, and add one iptable rule:
iptables -I INPUT -p tcp --sport 12345 -m connbytes --connbytes 2:
--connbytes-dir reply --connbytes-mode packets -j REJECT --reject-with
tcp-reset
This iptables rule could generate on TCP RST without ack flag.
server:10.172.135.55
Enable the synproxy with seqadjust by the following iptables rules
iptables -t raw -A PREROUTING -i eth0 -p tcp -d 10.172.135.55 --dport 12345
-m tcp --syn -j CT --notrack
netfilter: replace list_head with single linked list
The netfilter hook list never uses the prev pointer, and so can be trimmed to
be a simple singly-linked list.
In addition to having a more light weight structure for hook traversal,
struct net becomes 5568 bytes (down from 6400) and struct net_device becomes
2176 bytes (down from 2240).
A future patch will modify the hook drop and outfn functions. This will
cause the line lengths to take up too much space. This is simply a
readability change.
Signed-off-by: Aaron Conole <aconole@bytheb.org> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: Only allow sane values in nf_register_net_hook
This commit adds an upfront check for sane values to be passed when
registering a netfilter hook. This will be used in a future patch for a
simplified hook list traversal.
Signed-off-by: Aaron Conole <aconole@bytheb.org> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: Remove explicit rcu_read_lock in nf_hook_slow
All of the callers of nf_hook_slow already hold the rcu_read_lock, so this
cleanup removes the recursive call. This is just a cleanup, as the locking
code gracefully handles this situation.
Signed-off-by: Aaron Conole <aconole@bytheb.org> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: call nf_hook_ingress with rcu_read_lock
This commit ensures that the rcu read-side lock is held while the
ingress hook is called. This ensures that a call to nf_hook_slow (and
ultimately nf_ingress) will be read protected.
Signed-off-by: Aaron Conole <aconole@bytheb.org> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: call nf_hook_state_init with rcu_read_lock held
This makes things simpler because we can store the head of the list
in the nf_state structure without worrying about concurrent add/delete
of hook elements from the list.
A future commit will make use of this to implement a simpler
linked-list.
This replaces the last uses of NF_HOOK_THRESH().
Followup patch will remove it and rename nf_hook_thresh.
The reason is that inet (non-bridge) netfilter no longer invokes the
hooks from hooks, so we do no longer need the thresh value to skip hooks
with a lower priority.
The bridge netfilter however may need to do this. br_nf_hook_thresh is a
wrapper that is supposed to do this, i.e. only call hooks with a
priority that exceeds NF_BR_PRI_BRNF.
It's used only in the recursion cases of br_netfilter. It invokes
nf_hook_slow while holding an rcu read-side critical section to make a
future cleanup simpler.
netfilter: xt_TCPMSS: Refactor the codes to decrease one condition check and more readable
The origin codes perform two condition checks with dst_mtu(skb_dst(skb))
and in_mtu. And the last statement is "min(dst_mtu(skb_dst(skb)),
in_mtu) - minlen". It may let reader think about how about the result.
Would it be negative.
Now assign the result of min(dst_mtu(skb_dst(skb)), in_mtu) to a new
variable, then only perform one condition check, and it is more readable.
Signed-off-by: Gao Feng <fgao@ikuai8.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nf_tables: check tprot_set first when we use xt.thoff
pkt->xt.thoff is not always set properly, but we use it without any check.
For payload expr, it will cause wrong results. For nftrace, we may notify
the wrong network or transport header to the user space, furthermore,
input the following nft rules, warning message will be printed out:
# nft add rule arp filter output meta nftrace set 1
netfilter: nf_tables: improve nft payload fast eval
There's an off-by-one issue in nft_payload_fast_eval, skb_tail_pointer
and ptr + priv->len all point to the last valid address plus 1. So if
they are equal, we can still fetch the valid data. It's unnecessary to
fall back to nft_payload_eval.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nf_queue: improve queue range support for bridge family
After commit ac2863445686 ("netfilter: bridge: add nf_afinfo to enable
queuing to userspace"), we can queue packets to the user space in bridge
family. But when the user specify the queue range, packets will be only
delivered to the first queue num. Because in nfqueue_hash, we only support
ipv4 and ipv6 family. Now add support for bridge family too.
Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nft_queue: add _SREG_QNUM attr to select the queue number
Currently, the user can specify the queue numbers by _QUEUE_NUM and
_QUEUE_TOTAL attributes, this is enough in most situations.
But acctually, it is not very flexible, for example:
tcp dport 80 mapped to queue0
tcp dport 81 mapped to queue1
tcp dport 82 mapped to queue2
In order to do this thing, we must add 3 nft rules, and more
mapping meant more rules ...
So take one register to select the queue number, then we can add one
simple rule to mapping queues, maybe like this:
queue num tcp dport map { 80:0, 81:1, 82:2 ... }
Florian Westphal also proposed wider usage scenarios:
queue num jhash ip saddr . ip daddr mod ...
queue num meta cpu ...
queue num meta mark ...
The last point is how to load a queue number from sreg, although we can
use *(u16*)®s->data[reg] to load the queue number, just like nat expr
to load its l4port do.
But we will cooperate with hash expr, meta cpu, meta mark expr and so on.
They all store the result to u32 type, so cast it to u16 pointer and
dereference it will generate wrong result in the big endian system.
So just keep it simple, we treat queue number as u32 type, although u16
type is already enough.
Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nf_tables: validate maximum value of u32 netlink attributes
Fetch value and validate u32 netlink attribute. This validation is
usually required when the u32 netlink attributes are being stored in a
field whose size is smaller.
This patch revisits 4da449ae1df9 ("netfilter: nft_exthdr: Add size check
on u8 nft_exthdr attributes").
Fixes: 96518518cc41 ("netfilter: add nftables") Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Laura Garcia Liebana <nevola@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nft_numgen: add number generation offset
Add support of an offset value for incremental counter and random. With
this option the sysadmin is able to start the counter to a certain value
and then apply the generated number.
Example:
meta mark set numgen inc mod 2 offset 100
This will generate marks with the serie 100, 101, 100, 101, ...
Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Laura Garcia Liebana <nevola@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The overflow validation in the init() function establishes that the
maximum value that the hash could reach is less than U32_MAX, which is
likely to be true.
The fix detects the overflow when the maximum hash value is less than
the offset itself.
netfilter: nft_numgen: fix race between num generate and store it
After we generate a new number, we still use the priv->counter and
store it to the dreg. This is not correct, another cpu may already
change it to a new number. So we must use the generated number, not
the priv->counter itself.
Fixes: 91dbc6be0a62 ("netfilter: nf_tables: add number generator expression") Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
These counters sit in hot path and do show up in perf, this is especially
true for 'found' and 'searched' which get incremented for every packet
processed.
- on busy systems found and searched will overflow every few hours
(these are 32bit integers), other more busy ones every few days.
- for debugging there are better methods, such as iptables' trace target,
the conntrack log sysctls. Nowadays we also have perf tool.
This removes packet path stat counters except those that
are expected to be 0 (or close to 0) on a normal system, e.g.
'insert_failed' (race happened) or 'invalid' (proto tracker rejects).
The insert stat is retained for the ctnetlink case.
The found stat is retained for the tuple-is-taken check when NAT has to
determine if it needs to pick a different source address.
Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nf_tables: don't drop IPv6 packets that cannot parse transport
This is overly conservative and not flexible at all, so better let them
go through and let the filtering policy decide what to do with them. We
use skb_header_pointer() all over the place so we would just fail to
match when trying to access fields from malformed traffic.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nf_tables_bridge: use nft_set_pktinfo_ipv{4, 6}_validate
Consolidate pktinfo setup and validation by using the new generic
functions so we converge to the netdev family codebase.
We only need a linear IPv4 and IPv6 header from the reject expression,
so move nft_bridge_iphdr_validate() and nft_bridge_ip6hdr_validate()
to net/bridge/netfilter/nft_reject_bridge.c.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
These functions are extracted from the netdev family, they initialize
the pktinfo structure and validate that the IPv4 and IPv6 headers are
well-formed given that these functions are called from a path where
layer 3 sanitization did not happen yet.
These functions are placed in include/net/netfilter/nf_tables_ipv{4,6}.h
so they can be reused by a follow up patch to use them from the bridge
family too.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nf_tables: ensure proper initialization of nft_pktinfo fields
This patch introduces nft_set_pktinfo_unspec() that ensures proper
initialization all of pktinfo fields for non-IP traffic. This is used
by the bridge, netdev and arp families.
This new function relies on nft_set_pktinfo_proto_unspec() to set a new
tprot_set field that indicates if transport protocol information is
available. Remain fields are zeroed.
The meta expression has been also updated to check to tprot_set in first
place given that zero is a valid tprot value. Even a handcrafted packet
may come with the IPPROTO_RAW (255) protocol number so we can't rely on
this value as tprot unset.
Reported-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nft_dynset: allow to invert match criteria
The dynset expression matches if we can fit a new entry into the set.
If there is no room for it, then it breaks the rule evaluation.
This patch introduces the inversion flag so you can add rules to
explicitly drop packets that don't fit into the set. For example:
# nft filter input flow table xyz size 4 { ip saddr timeout 120s counter } overflow drop
This is useful to provide a replacement for connlimit.
For the rule above, every new entry uses the IPv4 address as key in the
set, this entry gets a timeout of 120 seconds that gets refresh on every
packet seen. If we get new flow and our set already contains 4 entries
already, then this packet is dropped.
You can already express this in positive logic, assuming default policy
to drop:
netfilter: nf_conntrack: remove unused ctl_table_path member in nf_conntrack_l3proto
After commit adf0516845bc ("netfilter: remove ip_conntrack* sysctl
compat code"), ctl_table_path member in struct nf_conntrack_l3proto{}
is not used anymore, remove it.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
netfilter: nft_queue: check the validation of queues_total and queuenum
Although the validation of queues_total and queuenum is checked in nft
utility, but user can add nft rules via nfnetlink, so it is necessary
to check the validation at the nft_queue expr init routine too.
Tested by run ./nft-test.py any/queue.t:
any/queue.t: 6 unit tests, 0 error, 0 warning
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Marco Angaroni [Tue, 30 Aug 2016 16:52:22 +0000 (18:52 +0200)]
netfilter: nf_ct_sip: allow tab character in SIP headers
Current parsing methods for SIP headers do not allow the presence of
tab characters between header name and header value. As a result Call-ID
SIP headers like the following are discarded by IPVS SIP persistence
engine:
In above examples Call-IDs are represented as strings in C language.
Obviously in real message we have byte "09" before/after colon (":").
Proposed fix is in nf_conntrack_sip module.
Function sip_skip_whitespace() should skip tabs in addition to spaces,
since in SIP grammar whitespace (WSP) corresponds to space or tab.
Below is an extract of relevant SIP ABNF syntax.
Call-ID = ( "Call-ID" / "i" ) HCOLON callid
callid = word [ "@" word ]
This is patch renames the existing function to nft_overquota() and make
it return a boolean that tells us if we have exceeded our byte quota.
Just a cleanup.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Marco Angaroni [Tue, 30 Aug 2016 16:48:24 +0000 (18:48 +0200)]
netfilter: nf_ct_sip: correct allowed characters in Call-ID SIP header
Current parsing methods for SIP header Call-ID do not check correctly all
characters allowed by RFC 3261. In particular "," character is allowed
instead of "'" character. As a result Call-ID headers like the following
are discarded by IPVS SIP persistence engine.
Call-ID: -.!%*_+`'~()<>:\"/[]?{}
Above example is composed using all non-alphanumeric characters listed
in RFC 3261 for Call-ID header syntax.
Proposed fix is in nf_conntrack_sip module; function iswordc() checks this
range: (c >= '(' && c <= '/') which includes these characters: ()*+,-./
They are all allowed except ",". Instead "'" is not included in the list.
Below is an extract of relevant SIP ABNF syntax.
Call-ID = ( "Call-ID" / "i" ) HCOLON callid
callid = word [ "@" word ]
Marco Angaroni [Tue, 30 Aug 2016 16:48:19 +0000 (18:48 +0200)]
netfilter: nf_ct_sip: correct parsing of continuation lines in SIP headers
Current parsing methods for SIP headers do not properly manage
continuation lines: in case of Call-ID header the first character of
Call-ID header value is truncated. As a result IPVS SIP persistence
engine hashes over a call-id that is not exactly the one present in
the originale message.
In above example Call-ID is represented as a string in C language.
Obviously in real message the first bytes after colon (":") are
"20 0d 0a 20".
Proposed fix is in nf_conntrack_sip module.
Since sip_follow_continuation() function walks past the leading
spaces or tabs of the continuation line, sip_skip_whitespace()
should simply return the ouput of sip_follow_continuation().
Otherwise another iteration of the for loop is done and dptr
is incremented by one pointing to the second character of the
first word in the header.
Below is an extract of relevant SIP ABNF syntax.
Call-ID = ( "Call-ID" / "i" ) HCOLON callid
callid = word [ "@" word ]
Gao Feng [Thu, 25 Aug 2016 15:08:47 +0000 (23:08 +0800)]
netfilter: gre: Use consistent GRE and PTTP header structure instead of the ones defined by netfilter
There are two existing strutures which defines the GRE and PPTP header.
So use these two structures instead of the ones defined by netfilter to
keep consitent with other codes.
Signed-off-by: Gao Feng <fgao@ikuai8.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
gpio_to_irq does not return NO_IRQ but instead returns a negative
error code on failure. Returning NO_IRQ from the function has no
negative effects as we only compare the result to the expected
interrupt number, but it's better to return a proper failure
code for consistency, and we should remove NO_IRQ from the kernel
entirely.
Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Richard Cochran <richardcochran@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Reported-by: Ma Yuying <yuma@redhat.com> Suggested-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: Bert Kenward <bkenward@solarflare.com> Reviewed-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
perf, bpf: fix conditional call to bpf_overflow_handler
The newly added bpf_overflow_handler function is only built of both
CONFIG_EVENT_TRACING and CONFIG_BPF_SYSCALL are enabled, but the caller
only checks the latter:
kernel/events/core.c: In function 'perf_event_alloc':
kernel/events/core.c:9106:27: error: 'bpf_overflow_handler' undeclared (first use in this function)
This changes the caller so we also skip this call if CONFIG_EVENT_TRACING
is disabled entirely.
Signed-off-by: Arnd Bergmann <arnd@arndb.de> Fixes: aa6a5f3cb2b2 ("perf, bpf: add perf events core support for BPF_PROG_TYPE_PERF_EVENT programs") Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
We get 1 warning when building kernel with W=1:
drivers/net/ethernet/arc/emac_mdio.c:107:5: warning: no previous prototype for 'arc_mdio_reset' [-Wmissing-prototypes]
In fact, this function is only used in the file in which it is
declared and don't need a declaration, but can be made static.
so this patch marks this function with 'static'.
Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
We get a few warnings when building kernel with W=1:
drivers/net/usb/lan78xx.c:1182:6: warning: no previous prototype for 'lan78xx_defer_kevent' [-Wmissing-prototypes]
drivers/net/usb/lan78xx.c:1409:5: warning: no previous prototype for 'lan78xx_nway_reset' [-Wmissing-prototypes]
drivers/net/usb/lan78xx.c:2000:5: warning: no previous prototype for 'lan78xx_set_mac_addr' [-Wmissing-prototypes]
....
In fact, these functions are only used in the file in which they are
declared and don't need a declaration, but can be made static.
so this patch marks these functions with 'static'.
Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Adds support for several infrastructure operations that are done as part of
debug data collection.
Signed-off-by: Tomer Tayar <Tomer.Tayar@qlogic.com> Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Mon, 5 Sep 2016 10:26:33 +0000 (13:26 +0300)]
bnx2x: Add support for segmentation of tunnels with outer checksums
Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Yuval Mintz <Yuval.Mintz@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 6 Sep 2016 20:53:29 +0000 (13:53 -0700)]
Merge tag 'rxrpc-rewrite-20160904-2' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs
David Howells says:
====================
rxrpc: Split output code from sendmsg code
Here's a set of small patches that split the packet transmission code from
the sendmsg code and simply rearrange the new file to make it more
logically laid out ready for being rewritten. An enum is also moved out of
the header file to there as it's only used there. This needs to be applied
on top of the just-posted fixes patch set.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Haishuang Yan [Sun, 4 Sep 2016 10:52:51 +0000 (18:52 +0800)]
vxlan: Update tx_errors statistics if vxlan_build_skb return err.
If vxlan_build_skb return err < 0, tx_errors should be also increased.
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com> Acked-by: Jiri Benc <jbenc@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net/mlx4_en: protect ring->xdp_prog with rcu_read_lock
Depending on the preempt mode, the bpf_prog stored in xdp_prog may be
freed despite the use of call_rcu inside bpf_prog_put. The situation is
possible when running in PREEMPT_RCU=y mode, for instance, since the rcu
callback for destroying the bpf prog can run even during the bh handling
in the mlx4 rx path.
Several options were considered before this patch was settled on:
Add a napi_synchronize loop in mlx4_xdp_set, which would occur after all
of the rings are updated with the new program.
This approach has the disadvantage that as the number of rings
increases, the speed of update will slow down significantly due to
napi_synchronize's msleep(1).
Add a new rcu_head in bpf_prog_aux, to be used by a new bpf_prog_put_bh.
The action of the bpf_prog_put_bh would be to then call bpf_prog_put
later. Those drivers that consume a bpf prog in a bh context (like mlx4)
would then use the bpf_prog_put_bh instead when the ring is up. This has
the problem of complexity, in maintaining proper refcnts and rcu lists,
and would likely be harder to review. In addition, this approach to
freeing must be exclusive with other frees of the bpf prog, for instance
a _bh prog must not be referenced from a prog array that is consumed by
a non-_bh prog.
The placement of rcu_read_lock in this patch is functionally the same as
putting an rcu_read_lock in napi_poll. Actually doing so could be a
potentially controversial change, but would bring the implementation in
line with sk_busy_loop (though of course the nature of those two paths
is substantially different), and would also avoid future copy/paste
problems with future supporters of XDP. Still, this patch does not take
that opinionated option.
Testing was done with kernels in either PREEMPT_RCU=y or
CONFIG_PREEMPT_VOLUNTARY=y+PREEMPT_RCU=n modes, with neither exhibiting
any drawback. With PREEMPT_RCU=n, the extra call to rcu_read_lock did
not show up in the perf report whatsoever, and with PREEMPT_RCU=y the
overhead of rcu_read_lock (according to perf) was the same before/after.
In the rx path, rcu_read_lock is eventually called for every packet
from netif_receive_skb_internal, so the napi poll call's rcu_read_lock
is easily amortized.
v2:
Remove extra rcu_read_lock in mlx4_en_process_rx_cq body
Annotate xdp_prog with __rcu, and convert all usages to rcu_assign or
rcu_dereference[_protected] as appropriate.
Add explicit mutex lock around rcu_assign instead of xchg loop.
Fixes: d576acf0a22 ("net/mlx4_en: add page recycle to prepare rx ring for tx support") Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> Signed-off-by: Brenden Blanco <bblanco@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 6 Sep 2016 20:33:20 +0000 (13:33 -0700)]
Merge branch 'mediatek-rx-path-enhancements'
Sean Wang says:
====================
net: ethernet: mediatek: add enhancements to RX path
Changes since v1:
- fix message typos and add coverletter
Changes since v2:
- split from the previous series for submitting add enhancements as
a series targeting 'net-next' and add indents before comments.
Changes since v3:
- merge the patch using PDMA RX path
- fixed the input of mtk_poll_rx is with the remaining budget
Changes since v4:
- save one wmb and register update when no packet is being handled
inside mtk_poll_rx call
- fixed incorrect return packet count from mtk_napi_rx
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Sean Wang [Sat, 3 Sep 2016 09:59:27 +0000 (17:59 +0800)]
net: ethernet: mediatek: enhance RX path by aggregating more SKBs into NAPI
The patch adds support for aggregating more SKBs feed into NAPI in
order to get more benefits from generic receive offload (GRO) by
peeking at the RX ring status and moving more packets right before
returning from NAPI RX polling handler if NAPI budgets are still
available and some packets already present in hardware.
Signed-off-by: Sean Wang <sean.wang@mediatek.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sean Wang [Sat, 3 Sep 2016 09:59:26 +0000 (17:59 +0800)]
net: ethernet: mediatek: enhance RX path by reducing the frequency of the memory barrier used
The patch makes move wmb() to outside the loop that could help
RX path handling more faster although that RX descriptors aren't
freed for DMA to use as soon as possible, but based on my experiment
and the result shows it still can reach about 943Mbpis without
performance drop that is tested based on the setup with one port
using Giga PHY and 256 RX descriptors for DMA to move.
Signed-off-by: Sean Wang <sean.wang@mediatek.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Joe Perches [Fri, 2 Sep 2016 22:58:01 +0000 (15:58 -0700)]
hso: Use a more common logging style
Macros that end in an underscore are just odd.
Add hso_dbg(level, fmt, ...) and use it everwhere instead.
Several uses had additional unnecessary newlines as the
macro added a newline. Remove the newline from the macro
and add newlines to each use as appropriate.
Remove now unused D<digit> macros.
Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Add Microchip Linux Driver Support as maintainer
because this driver is maintaining by Microchip.
Signed-off-by: Woojung Huh <Woojung.huh@gmail.com> Acked-by: Steve Glendinning <steve.glendinning@shawell.net> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 6 Sep 2016 19:58:14 +0000 (12:58 -0700)]
Merge branch 'mv88e6xxx-isolate-Global2'
Vivien Didelot says:
====================
net: dsa: mv88e6xxx: isolate Global2 support
Registers of Marvell chips are organized in internal SMI devices.
One of them at address 0x1C is called Global2. It provides an extended
set of registers, used for interrupt control, EEPROM access, indirect
PHY access (to bypass the PHY Polling Unit) and cross-chip setup.
Most chips have it, but some others don't (older ones such as 6060).
Now that its related code is isolated in mv88e6xxx_g2_* functions, move
it to its own global2.c file, making most of its setup code static.
Then make its compilation optional, which allows to reduce the size of
the mv88e6xxx driver for devices such as home routers embedding Ethernet
chips without Global2 support.
It is present on most recent chips, thus enable its support by default.
Changes in v2: fail probe if GLOBAL2 is required but not enabled.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Vivien Didelot [Fri, 2 Sep 2016 18:45:33 +0000 (14:45 -0400)]
net: dsa: mv88e6xxx: move Global2 code
Marvell chips are composed of multiple SMI devices. One of them at
address 0x1C is called Global2. It provides an extended set of
registers, used for interrupt control, EEPROM access, indirect PHY
access (to bypass the PHY Polling Unit) and cross-chip related setup.
Most chips have it, but some others don't (older ones such as 6060).
Now that its related code is isolated in mv88e6xxx_g2_* functions, move
it to its own global2.c file, making most of its setup code static.
Document each registers in the meantime.
Its compilation can be later avoided for chips without such registers.
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vivien Didelot [Fri, 2 Sep 2016 18:45:32 +0000 (14:45 -0400)]
net: dsa: mv88e6xxx: fix module naming
Since the mv88e6xxx.c file has been renamed, the driver compiled as a
module is called chip.ko instead of mv88e6xxx.ko. Fix this.
Fixes: fad09c73c270 ("net: dsa: mv88e6xxx: rename single-chip support") Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com> Signed-off-by: David S. Miller <davem@davemloft.net>
====================
Netfilter updates for net-next
The following patchset contains Netfilter updates for your net-next
tree. Most relevant updates are the removal of per-conntrack timers to
use a workqueue/garbage collection approach instead from Florian
Westphal, the hash and numgen expression for nf_tables from Laura
Garcia, updates on nf_tables hash set to honor the NLM_F_EXCL flag,
removal of ip_conntrack sysctl and many other incremental updates on our
Netfilter codebase.
More specifically, they are:
1) Retrieve only 4 bytes to fetch ports in case of non-linear skb
transport area in dccp, sctp, tcp, udp and udplite protocol
conntrackers, from Gao Feng.
2) Missing whitespace on error message in physdev match, from Hangbin Liu.
3) Skip redundant IPv4 checksum calculation in nf_dup_ipv4, from Liping Zhang.
4) Add nf_ct_expires() helper function and use it, from Florian Westphal.
5) Replace opencoded nf_ct_kill() call in IPVS conntrack support, also
from Florian.
6) Rename nf_tables set implementation to nft_set_{name}.c
7) Introduce the hash expression to allow arbitrary hashing of selector
concatenations, from Laura Garcia Liebana.
8) Remove ip_conntrack sysctl backward compatibility code, this code has
been around for long time already, and we have two interfaces to do
this already: nf_conntrack sysctl and ctnetlink.
9) Use nf_conntrack_get_ht() helper function whenever possible, instead
of opencoding fetch of hashtable pointer and size, patch from Liping Zhang.
10) Add quota expression for nf_tables.
11) Add number generator expression for nf_tables, this supports
incremental and random generators that can be combined with maps,
very useful for load balancing purpose, again from Laura Garcia Liebana.
12) Fix a typo in a debug message in FTP conntrack helper, from Colin Ian King.
13) Introduce a nft_chain_parse_hook() helper function to parse chain hook
configuration, this is used by a follow up patch to perform better chain
update validation.
14) Add rhashtable_lookup_get_insert_key() to rhashtable and use it from the
nft_set_hash implementation to honor the NLM_F_EXCL flag.
15) Missing nulls check in nf_conntrack from nf_conntrack_tuple_taken(),
patch from Florian Westphal.
16) Don't use the DYING bit to know if the conntrack event has been already
delivered, instead a state variable to track event re-delivery
states, also from Florian.
17) Remove the per-conntrack timer, use the workqueue approach that was
discussed during the NFWS, from Florian Westphal.
18) Use the netlink conntrack table dump path to kill stale entries,
again from Florian.
19) Add a garbage collector to get rid of stale conntracks, from
Florian.
20) Reschedule garbage collector if eviction rate is high.
21) Get rid of the __nf_ct_kill_acct() helper.
22) Use ARPHRD_ETHER instead of hardcoded 1 from ARP logger.
23) Make nf_log_set() interface assertive on unsupported families.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The workqueue "afs_lock_manager" queues work item &vnode->lock_work,
per vnode. Since there can be multiple vnodes and since their work items
can be executed concurrently, alloc_workqueue has been used to replace
the deprecated create_singlethread_workqueue instance.
The WQ_MEM_RECLAIM flag has been set to ensure forward progress under
memory pressure because the workqueue is being used on a memory reclaim
path.
Since there are fixed number of work items, explicit concurrency
limit is unnecessary here.
Signed-off-by: Bhaktipriya Shridhar <bhaktipriya96@gmail.com> Signed-off-by: David Howells <dhowells@redhat.com>
The workqueue "afs_callback_update_worker" queues multiple work items
viz &vnode->cb_broken_work, &server->cb_break_work which require strict
execution ordering. Hence, an ordered dedicated workqueue has been used.
Since the workqueue is being used on a memory reclaim path, WQ_MEM_RECLAIM
has been set to ensure forward progress under memory pressure.
Signed-off-by: Bhaktipriya Shridhar <bhaktipriya96@gmail.com> Signed-off-by: David Howells <dhowells@redhat.com>
The workqueue "afs_async_calls" queues work item
&call->async_work per afs_call. Since there could be multiple calls and since
these calls can be run concurrently, alloc_workqueue has been used to replace
the deprecated create_singlethread_workqueue instance.
The WQ_MEM_RECLAIM flag has been set to ensure forward progress under
memory pressure because the workqueue is being used on a memory reclaim
path.
Since there are fixed number of work items, explicit concurrency
limit is unnecessary here.
Signed-off-by: Bhaktipriya Shridhar <bhaktipriya96@gmail.com> Signed-off-by: David Howells <dhowells@redhat.com>
The workqueue "afs_vlocation_update_worker" queues a single work item
&afs_vlocation_update and hence it doesn't require execution ordering.
Hence, alloc_workqueue has been used to replace the deprecated
create_singlethread_workqueue instance.
Since the workqueue is being used on a memory reclaim path, WQ_MEM_RECLAIM
flag has been set to ensure forward progress under memory pressure.
Since there are fixed number of work items, explicit concurrency
limit is unnecessary here.
Signed-off-by: Bhaktipriya Shridhar <bhaktipriya96@gmail.com> Signed-off-by: David Howells <dhowells@redhat.com>
Paul Burton [Fri, 2 Sep 2016 14:22:48 +0000 (15:22 +0100)]
net: ti: cpmac: Fix compiler warning due to type confusion
cpmac_start_xmit() used the max() macro on skb->len (an unsigned int)
and ETH_ZLEN (a signed int literal). This led to the following compiler
warning:
In file included from include/linux/list.h:8:0,
from include/linux/module.h:9,
from drivers/net/ethernet/ti/cpmac.c:19:
drivers/net/ethernet/ti/cpmac.c: In function 'cpmac_start_xmit':
include/linux/kernel.h:748:17: warning: comparison of distinct pointer
types lacks a cast
(void) (&_max1 == &_max2); \
^
drivers/net/ethernet/ti/cpmac.c:560:8: note: in expansion of macro 'max'
len = max(skb->len, ETH_ZLEN);
^
On top of this, it assigned the result of the max() macro to a signed
integer whilst all further uses of it result in it being cast to varying
widths of unsigned integer.
Fix this up by using max_t to ensure the comparison is performed as
unsigned integers, and for consistency change the type of the len
variable to unsigned int.
Signed-off-by: Paul Burton <paul.burton@imgtec.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Adds support for ndo_get_vf_config, also fill the default mac address
that will be provided to the VF by firmware, in case user doesn't
provide one. So user can get the default MAC address address also
through ndo_get_vf_config.
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
WANG Cong [Fri, 2 Sep 2016 04:53:45 +0000 (21:53 -0700)]
netns: avoid disabling irq for netns id
We never read or change netns id in hardirq context,
the only place we read netns id in softirq context
is in vxlan_xmit(). So, it should be enough to just
disable BH.
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
WANG Cong [Fri, 2 Sep 2016 04:53:44 +0000 (21:53 -0700)]
vxlan: call peernet2id() in fdb notification
netns id should be already allocated each time we change
netns, that is, in dev_change_net_namespace() (more precisely
in rtnl_fill_ifinfo()). It is safe to just call peernet2id() here.
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Joe Stringer [Fri, 2 Sep 2016 01:01:47 +0000 (18:01 -0700)]
openvswitch: Free tmpl with tmpl_free.
When an error occurs during conntrack template creation as part of
actions validation, we need to free the template. Previously we've been
using nf_ct_put() to do this, but nf_ct_tmpl_free() is more appropriate.
Signed-off-by: Joe Stringer <joe@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
David Howells [Sun, 4 Sep 2016 12:10:10 +0000 (13:10 +0100)]
rxrpc: The client call state must be changed before attachment to conn
We must set the client call state to RXRPC_CALL_CLIENT_SEND_REQUEST before
attaching the call to the connection struct, not after, as it's liable to
receive errors and conn aborts as soon as the assignment is made - and
these will cause its state to be changed outside of the initiating thread's
control.
Signed-off-by: David Howells <dhowells@redhat.com>
David S. Miller [Sat, 3 Sep 2016 00:11:32 +0000 (17:11 -0700)]
Merge branch 'liquidio-CN23XX-part-2'
Raghu Vatsavayi says:
====================
liquidio CN23XX support
I am posting the remaining half of patchset after the
acceptance of first half. With this patchset I am able
to completely submit the code of V3 patchset which you
earlier advised me to split into smaller ones.
This V5 patch also addresses all the comments from previous
submission:
1) Avoid busy loop while reading registers.
2) Other minor comments about debug messages and constants.
Please apply patches in following order as some of the
patches depend on earlier patches.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>