* [PATCH] fix a bug in emitting the 16-bit immediate operand of AND
From: zhuangfeiran @ 2012-03-29 9:27 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, eric.dumazet
When K >= 0xFFFF0000, AND needs the two least significant bytes of K as
its operand, but EMIT2() gives it the least significant byte of K and
0x2. EMIT() should be used here to replace EMIT2().
Signed-off-by: Feiran Zhuang <zhuangfeiran@ict.ac.cn>
---
arch/x86/net/bpf_jit_comp.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5671752..5a5b6e4 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -289,7 +289,7 @@ void bpf_jit_compile(struct sk_filter *fp)
EMIT2(0x24, K & 0xFF); /* and imm8,%al */
} else if (K >= 0xFFFF0000) {
EMIT2(0x66, 0x25); /* and imm16,%ax */
- EMIT2(K, 2);
+ EMIT(K, 2);
} else {
EMIT1_off32(0x25, K); /* and imm32,%eax */
}
--
1.7.5.4
^ permalink raw reply related
* 答复: 答复: [PATCH] set fake_rtable's dst to NULL to avoid kernel Oops.
From: Peter Huang (Peng) @ 2012-03-29 9:38 UTC (permalink / raw)
To: 'Eric Dumazet'
Cc: linux-kernel, harry.majun, zhoukang7, 'netdev'
In-Reply-To: <1333011120.2325.354.camel@edumazet-glaptop>
Thks for your mail.
>Check net/bridge/br_netfilter.c and commits e688a6048076 (net: introduce
>DST_NOPEER dst flag ) 4adf0af6818f3ea5 (bridge: send correct MTU value
>in PMTU (revised))
This patch already included in kernel-3.3, but for our case, virtual tap device's delayed
Deletion will also cause kernel oops even in kernel3.3.
>Apparently bug is because struct net_bridge is freed while its embedded
>fake_rtable is still used by some packets.
>I am not sure we are allowed to NULLify skb->dst, it might break
>netfilter.
Are you familiar with fake_rtable? I search the source, but only find one op that operate on the MTU.
>Maybe real fix would be to use a non embedded dst.
I agreed with you to, so at least until now this problem still exsits in the latest kernel, I will also look into it,
And try to modify it from the root.
Thanks again.
^ permalink raw reply
* Re: [Q/RFC] BPF use in broader scope
From: Li Yu @ 2012-03-29 9:49 UTC (permalink / raw)
To: Jiri Pirko; +Cc: netdev, eric.dumazet, davem, bhutchings, shemminger
In-Reply-To: <20120329074443.GB2098@minipsycho>
于 2012年03月29日 15:44, Jiri Pirko 写道:
> Hi all.
>
> I came to an idea of using BPF infrastructure currently used in kernel,
> for computing hashes selecting TX ports in team device. Since the same
> data (skb) are alalyzed/used as for socket filtering, BPF seems so be quite
> suitable for this. It would allow userspace daemon to specify various
> kinds of TX selection algorithms.
>
> Here are proposed things to be done:
> 1) introduce in-kernel api for creating sk-unattached filters (I have
> the patch cooked up already)
>
> 2) extend current BPF machine to allow XOR operation. Not sure if this
> is doable or what the best of doing this is.
>
> 3) add possibility to pass some data to the machine via
> pre-filling "Scratch Memory Store". I think this can be done easily
> moving "u32 mem[BPF_MEMWORDS];" to bpf_func caller and pass it as the
> second function parameter. That should not break anything.
>
> Then the computed hash can be either stored into Scratch memory or returned
> directly (where ordinary sk filters return len).
>
> Does this seems reasonable? Thoughts, comments?
>
Very interesting.
I am working on a blktrace like utility for networking subsystem. It
needs a trace events filter to avoid to generate too much results which
user does not interesting, it seem that the generic BPF is the best
choice here.
So far, the "skbtrace" need to filter two kinds of objects: the skb and
socket, so I think that above "Scratch Memory Store" is necessary indeed.
Thanks.
Yu
> Thanks!
>
> Jirka
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply
* Re: [PATCH 2/3] tcp: Initial repair mode
From: Pavel Emelyanov @ 2012-03-29 9:52 UTC (permalink / raw)
To: Glauber Costa; +Cc: Linux Netdev List, David Miller
In-Reply-To: <4F734864.6000007@parallels.com>
On 03/28/2012 09:20 PM, Glauber Costa wrote:
>> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
>> index 9e7f9ba..65ae921 100644
>> --- a/net/ipv4/tcp.c
>> +++ b/net/ipv4/tcp.c
>> @@ -1935,7 +1935,9 @@ void tcp_close(struct sock *sk, long timeout)
>> * advertise a zero window, then kill -9 the FTP client, wheee...
>> * Note: timeout is always zero in such a case.
>> */
>> - if (data_was_unread) {
>> + if (tcp_sk(sk)->repair) {
>> + sk->sk_prot->disconnect(sk, 0);
>> + } else if (data_was_unread) {
>> /* Unread data was tossed, zap the connection. */
>> NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
>> tcp_set_state(sk, TCP_CLOSE);
>> @@ -2074,6 +2076,8 @@ int tcp_disconnect(struct sock *sk, int flags)
>> /* ABORT function of RFC793 */
>> if (old_state == TCP_LISTEN) {
>> inet_csk_listen_stop(sk);
>> + } else if (unlikely(tp->repair)) {
>> + sk->sk_err = ECONNABORTED;
>> } else if (tcp_need_reset(old_state) ||
>> (tp->snd_nxt != tp->write_seq&&
>> (1<< old_state)& (TCPF_CLOSING | TCPF_LAST_ACK))) {
>
> The patch looks good in general.
> Single nitpick is that maybe you should be consistent in your use of
> unlikely. All of them seems equally unlikely, so I'd say you should wrap
> both.
OK, will fix this.
>>
>> + case TCP_REPAIR:
>> + if (!tcp_can_repair_sock(sk))
>> + err = -EPERM;
>> + else if (val == 1) {
>> + tp->repair = 1;
>> + sk->sk_reuse = 2;
>> + tp->repair_queue = TCP_NO_QUEUE;
>> + } else if (val == 0) {
>> + tp->repair = 0;
>> + sk->sk_reuse = 0;
>> + tcp_send_window_probe(sk);
>> + } else
>> + err = -EINVAL;
>> +
>> + break;
>> +
>> + case TCP_REPAIR_QUEUE:
>
> Don't we need to test tcp_can_repair_sock() in all of them?
> I understand that TCP_REPAIR always comes before the other ones,
> so that means the socket is already in repair mode. But what
> should be the behavior in case the process drops privileges?
> Should it still be able to continue with the repair?
I believe it should. Because this model gives us the ability to do
both -- let others repair socket in non-root mode and keep one at
hands, giving it to anybody else only when the repair is complete.
> My first impression is that we need CAP_NET_ADMIN all along, so we
> should make sure it's there.
>
> .
>
^ permalink raw reply
* Re: [PATCH 2/3] tcp: Initial repair mode
From: Pavel Emelyanov @ 2012-03-29 9:53 UTC (permalink / raw)
To: Ben Hutchings; +Cc: Linux Netdev List, David Miller
In-Reply-To: <1332967158.2624.42.camel@bwh-desktop.uk.solarflarecom.com>
On 03/29/2012 12:39 AM, Ben Hutchings wrote:
> On Wed, 2012-03-28 at 19:37 +0400, Pavel Emelyanov wrote:
> [...]
>> * Ability to forcibly bind a socket to a port
>>
>> The sk->sk_reuse is set to 2 denoting, that the socket is question
>> should be bound as if all the others in the system are configured
>> with the SO_REUSEADDR option.
>
> Shouldn't this constant be named?
Agree, I will fix this up.
> [...]
>> --- a/net/ipv4/tcp.c
>> +++ b/net/ipv4/tcp.c
> [...]
>> + case TCP_REPAIR_QUEUE:
>> + if (!tp->repair)
>> + err = -EPERM;
>> + else if (val <= TCP_QUEUES_NR)
>
> Off-by-one.
Oops :( Thanks for noticing!
>> + tp->repair_queue = val;
>> + else
>> + err = -EINVAL;
>> + break;
> [...]
>
^ permalink raw reply
* Re: [PATCH 3/3] tcp: Repair socket queues
From: Li Yu @ 2012-03-29 10:30 UTC (permalink / raw)
To: Pavel Emelyanov; +Cc: Linux Netdev List, David Miller
In-Reply-To: <4F733062.9020800@parallels.com>
于 2012年03月28日 23:38, Pavel Emelyanov 写道:
> Reading queues under repair mode is done with recvmsg call.
> The queue-under-repair set by TCP_REPAIR_QUEUE option is used
> to determine which queue should be read. Thus both send and
> receive queue can be read with this.
>
> Caller must pass the MSG_PEEK flag.
>
> Writing to queues is done with sendmsg call and yet again --
> the repair-queue option can be used to push data into the
> receive queue.
>
> When putting an skb into receive queue a zero tcp header is
> appented to its head to address the tcp_hdr(skb)->syn and
> the ->fin checks by the (after repair) tcp_recvmsg. These
> flags flags are both set to zero and that's why.
>
> The fin cannot be met in the queue while reading the source
> socket, since the repair only works for closed/established
> sockets and queueing fin packet always changes its state.
>
> The syn in the queue denotes that the respective skb's seq
> is "off-by-one" as compared to the actual payload lenght. Thus,
> at the rcv queue refill we can just drop this flag and set the
> skb's sequences to precice values. IOW -- emulate the situation
> when the packet with data and syn is splitted into two -- a
> packet with syn and a packet with data and the former one is
> already "eaten".
>
> When the repair mode is turned off, the write queue seqs are
> updated so that the whole queue is considered to be 'already sent,
> waiting for ACKs' (write_seq = snd_nxt<= snd_una). From the
> protocol POV the send queue looks like it was sent, but the data
> between the write_seq and snd_nxt is lost in the network.
>
> This helps to avoid another sockoption for setting the snd_nxt
> sequence. Leaving the whole queue in a 'not yet sent' state (as
> it will be after sendmsg-s) will not allow to receive any acks
> from the peer since the ack_seq will be after the snd_nxt. Thus
> even the ack for the window probe will be dropped and the
> connection will be 'locked' with the zero peer window.
>
Do we need to restore various TCP options switch bits. e.g. window
scale factor, sack_ok and so on.
En, I think the recorded mss_cache may be need to restored too.
Thanks.
Yu
> Signed-off-by: Pavel Emelyanov<xemul@parallels.com>
> ---
> net/ipv4/tcp.c | 89 +++++++++++++++++++++++++++++++++++++++++++++++--
> net/ipv4/tcp_output.c | 1 +
> 2 files changed, 87 insertions(+), 3 deletions(-)
>
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index 65ae921..2ab3a31 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -911,6 +911,39 @@ static inline int select_size(const struct sock *sk, bool sg)
> return tmp;
> }
>
> +static int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
> +{
> + struct sk_buff *skb;
> + struct tcp_skb_cb *cb;
> + struct tcphdr *th;
> +
> + skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
> + if (!skb)
> + goto err;
> +
> + th = (struct tcphdr *)skb_put(skb, sizeof(*th));
> + skb_reset_transport_header(skb);
> + memset(th, 0, sizeof(*th));
> +
> + if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
> + goto err_free;
> +
> + cb = TCP_SKB_CB(skb);
> +
> + TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
> + TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
> + TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;
> +
> + tcp_queue_rcv(sk, skb, sizeof(*th));
> +
> + return size;
> +
> +err_free:
> + kfree_skb(skb);
> +err:
> + return -ENOMEM;
> +}
> +
> int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
> size_t size)
> {
> @@ -932,6 +965,19 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
> if ((err = sk_stream_wait_connect(sk,&timeo)) != 0)
> goto out_err;
>
> + if (unlikely(tp->repair)) {
> + if (tp->repair_queue == TCP_RECV_QUEUE) {
> + copied = tcp_send_rcvq(sk, msg, size);
> + goto out;
> + }
> +
> + err = -EINVAL;
> + if (tp->repair_queue == TCP_NO_QUEUE)
> + goto out_err;
> +
> + /* 'common' sending to sendq */
> + }
> +
> /* This should be in poll */
> clear_bit(SOCK_ASYNC_NOSPACE,&sk->sk_socket->flags);
>
> @@ -1089,7 +1135,7 @@ new_segment:
> if ((seglen -= copy) == 0&& iovlen == 0)
> goto out;
>
> - if (skb->len< max || (flags& MSG_OOB))
> + if (skb->len< max || (flags& MSG_OOB) || tp->repair)
> continue;
>
> if (forced_push(tp)) {
> @@ -1102,7 +1148,7 @@ new_segment:
> wait_for_sndbuf:
> set_bit(SOCK_NOSPACE,&sk->sk_socket->flags);
> wait_for_memory:
> - if (copied)
> + if (copied&& !tp->repair)
> tcp_push(sk, flags& ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
>
> if ((err = sk_stream_wait_memory(sk,&timeo)) != 0)
> @@ -1113,7 +1159,7 @@ wait_for_memory:
> }
>
> out:
> - if (copied)
> + if (copied&& !tp->repair)
> tcp_push(sk, flags, mss_now, tp->nonagle);
> release_sock(sk);
> return copied;
> @@ -1187,6 +1233,24 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
> return -EAGAIN;
> }
>
> +static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
> +{
> + struct sk_buff *skb;
> + int copied = 0, err = 0;
> +
> + /* XXX -- need to support SO_PEEK_OFF */
> +
> + skb_queue_walk(&sk->sk_write_queue, skb) {
> + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len);
> + if (err)
> + break;
> +
> + copied += skb->len;
> + }
> +
> + return err ?: copied;
> +}
> +
> /* Clean up the receive buffer for full frames taken by the user,
> * then send an ACK if necessary. COPIED is the number of bytes
> * tcp_recvmsg has given to the user so far, it speeds up the
> @@ -1432,6 +1496,21 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
> if (flags& MSG_OOB)
> goto recv_urg;
>
> + if (unlikely(tp->repair)) {
> + err = -EPERM;
> + if (!(flags& MSG_PEEK))
> + goto out;
> +
> + if (tp->repair_queue == TCP_SEND_QUEUE)
> + goto recv_sndq;
> +
> + err = -EINVAL;
> + if (tp->repair_queue == TCP_NO_QUEUE)
> + goto out;
> +
> + /* 'common' recv queue MSG_PEEK-ing */
> + }
> +
> seq =&tp->copied_seq;
> if (flags& MSG_PEEK) {
> peek_seq = tp->copied_seq;
> @@ -1783,6 +1862,10 @@ out:
> recv_urg:
> err = tcp_recv_urg(sk, msg, len, flags);
> goto out;
> +
> +recv_sndq:
> + err = tcp_peek_sndq(sk, msg, len);
> + goto out;
> }
> EXPORT_SYMBOL(tcp_recvmsg);
>
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 4e2ce39..b29d612 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2796,6 +2796,7 @@ void tcp_send_window_probe(struct sock *sk)
> {
> if (sk->sk_state == TCP_ESTABLISHED) {
> tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
> + tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
> tcp_xmit_probe_skb(sk, 0);
> }
> }
^ permalink raw reply
* Re: [PATCH 3/3] tcp: Repair socket queues
From: Pavel Emelyanov @ 2012-03-29 10:36 UTC (permalink / raw)
To: Li Yu; +Cc: Linux Netdev List, David Miller
In-Reply-To: <4F7439AE.6050006@gmail.com>
On 03/29/2012 02:30 PM, Li Yu wrote:
> 于 2012年03月28日 23:38, Pavel Emelyanov 写道:
>> Reading queues under repair mode is done with recvmsg call.
>> The queue-under-repair set by TCP_REPAIR_QUEUE option is used
>> to determine which queue should be read. Thus both send and
>> receive queue can be read with this.
>>
>> Caller must pass the MSG_PEEK flag.
>>
>> Writing to queues is done with sendmsg call and yet again --
>> the repair-queue option can be used to push data into the
>> receive queue.
>>
>> When putting an skb into receive queue a zero tcp header is
>> appented to its head to address the tcp_hdr(skb)->syn and
>> the ->fin checks by the (after repair) tcp_recvmsg. These
>> flags flags are both set to zero and that's why.
>>
>> The fin cannot be met in the queue while reading the source
>> socket, since the repair only works for closed/established
>> sockets and queueing fin packet always changes its state.
>>
>> The syn in the queue denotes that the respective skb's seq
>> is "off-by-one" as compared to the actual payload lenght. Thus,
>> at the rcv queue refill we can just drop this flag and set the
>> skb's sequences to precice values. IOW -- emulate the situation
>> when the packet with data and syn is splitted into two -- a
>> packet with syn and a packet with data and the former one is
>> already "eaten".
>>
>> When the repair mode is turned off, the write queue seqs are
>> updated so that the whole queue is considered to be 'already sent,
>> waiting for ACKs' (write_seq = snd_nxt<= snd_una). From the
>> protocol POV the send queue looks like it was sent, but the data
>> between the write_seq and snd_nxt is lost in the network.
>>
>> This helps to avoid another sockoption for setting the snd_nxt
>> sequence. Leaving the whole queue in a 'not yet sent' state (as
>> it will be after sendmsg-s) will not allow to receive any acks
>> from the peer since the ack_seq will be after the snd_nxt. Thus
>> even the ack for the window probe will be dropped and the
>> connection will be 'locked' with the zero peer window.
>>
>
> Do we need to restore various TCP options switch bits. e.g. window
> scale factor, sack_ok and so on.
SACK-s -- yes, this is in TODO list. Various window stuff -- not necessary.
TCP will eventually negotiate proper values again.
> En, I think the recorded mss_cache may be need to restored too.
Same with mss. As far as I understand this one will be re-detected after
a connection restore.
> Thanks.
>
> Yu
^ permalink raw reply
* Re: [PATCH 3/3] tcp: Repair socket queues
From: Li Yu @ 2012-03-29 10:41 UTC (permalink / raw)
To: Pavel Emelyanov; +Cc: Linux Netdev List, David Miller
In-Reply-To: <4F743B32.4050107@parallels.com>
于 2012年03月29日 18:36, Pavel Emelyanov 写道:
> On 03/29/2012 02:30 PM, Li Yu wrote:
>> 于 2012年03月28日 23:38, Pavel Emelyanov 写道:
>>> Reading queues under repair mode is done with recvmsg call.
>>> The queue-under-repair set by TCP_REPAIR_QUEUE option is used
>>> to determine which queue should be read. Thus both send and
>>> receive queue can be read with this.
>>>
>>> Caller must pass the MSG_PEEK flag.
>>>
>>> Writing to queues is done with sendmsg call and yet again --
>>> the repair-queue option can be used to push data into the
>>> receive queue.
>>>
>>> When putting an skb into receive queue a zero tcp header is
>>> appented to its head to address the tcp_hdr(skb)->syn and
>>> the ->fin checks by the (after repair) tcp_recvmsg. These
>>> flags flags are both set to zero and that's why.
>>>
>>> The fin cannot be met in the queue while reading the source
>>> socket, since the repair only works for closed/established
>>> sockets and queueing fin packet always changes its state.
>>>
>>> The syn in the queue denotes that the respective skb's seq
>>> is "off-by-one" as compared to the actual payload lenght. Thus,
>>> at the rcv queue refill we can just drop this flag and set the
>>> skb's sequences to precice values. IOW -- emulate the situation
>>> when the packet with data and syn is splitted into two -- a
>>> packet with syn and a packet with data and the former one is
>>> already "eaten".
>>>
>>> When the repair mode is turned off, the write queue seqs are
>>> updated so that the whole queue is considered to be 'already sent,
>>> waiting for ACKs' (write_seq = snd_nxt<= snd_una). From the
>>> protocol POV the send queue looks like it was sent, but the data
>>> between the write_seq and snd_nxt is lost in the network.
>>>
>>> This helps to avoid another sockoption for setting the snd_nxt
>>> sequence. Leaving the whole queue in a 'not yet sent' state (as
>>> it will be after sendmsg-s) will not allow to receive any acks
>>> from the peer since the ack_seq will be after the snd_nxt. Thus
>>> even the ack for the window probe will be dropped and the
>>> connection will be 'locked' with the zero peer window.
>>>
>>
>> Do we need to restore various TCP options switch bits. e.g. window
>> scale factor, sack_ok and so on.
>
> SACK-s -- yes, this is in TODO list. Various window stuff -- not necessary.
> TCP will eventually negotiate proper values again.
>
>> En, I think the recorded mss_cache may be need to restored too.
>
> Same with mss. As far as I understand this one will be re-detected after
> a connection restore.
>
After the connection are repaired, it directly enter ESTABLISHED state,
so this TCP connection has no chance to negotiate such optional
features, such negotiation only can occurs at 3WHS.
Thanks.
Yu
>> Thanks.
>>
>> Yu
>
^ permalink raw reply
* Re: [PATCH 3/3] tcp: Repair socket queues
From: Li Yu @ 2012-03-29 10:41 UTC (permalink / raw)
To: Pavel Emelyanov; +Cc: Linux Netdev List, David Miller
In-Reply-To: <4F743B32.4050107@parallels.com>
于 2012年03月29日 18:36, Pavel Emelyanov 写道:
> On 03/29/2012 02:30 PM, Li Yu wrote:
>> 于 2012年03月28日 23:38, Pavel Emelyanov 写道:
>>> Reading queues under repair mode is done with recvmsg call.
>>> The queue-under-repair set by TCP_REPAIR_QUEUE option is used
>>> to determine which queue should be read. Thus both send and
>>> receive queue can be read with this.
>>>
>>> Caller must pass the MSG_PEEK flag.
>>>
>>> Writing to queues is done with sendmsg call and yet again --
>>> the repair-queue option can be used to push data into the
>>> receive queue.
>>>
>>> When putting an skb into receive queue a zero tcp header is
>>> appented to its head to address the tcp_hdr(skb)->syn and
>>> the ->fin checks by the (after repair) tcp_recvmsg. These
>>> flags flags are both set to zero and that's why.
>>>
>>> The fin cannot be met in the queue while reading the source
>>> socket, since the repair only works for closed/established
>>> sockets and queueing fin packet always changes its state.
>>>
>>> The syn in the queue denotes that the respective skb's seq
>>> is "off-by-one" as compared to the actual payload lenght. Thus,
>>> at the rcv queue refill we can just drop this flag and set the
>>> skb's sequences to precice values. IOW -- emulate the situation
>>> when the packet with data and syn is splitted into two -- a
>>> packet with syn and a packet with data and the former one is
>>> already "eaten".
>>>
>>> When the repair mode is turned off, the write queue seqs are
>>> updated so that the whole queue is considered to be 'already sent,
>>> waiting for ACKs' (write_seq = snd_nxt<= snd_una). From the
>>> protocol POV the send queue looks like it was sent, but the data
>>> between the write_seq and snd_nxt is lost in the network.
>>>
>>> This helps to avoid another sockoption for setting the snd_nxt
>>> sequence. Leaving the whole queue in a 'not yet sent' state (as
>>> it will be after sendmsg-s) will not allow to receive any acks
>>> from the peer since the ack_seq will be after the snd_nxt. Thus
>>> even the ack for the window probe will be dropped and the
>>> connection will be 'locked' with the zero peer window.
>>>
>>
>> Do we need to restore various TCP options switch bits. e.g. window
>> scale factor, sack_ok and so on.
>
> SACK-s -- yes, this is in TODO list. Various window stuff -- not necessary.
> TCP will eventually negotiate proper values again.
>
>> En, I think the recorded mss_cache may be need to restored too.
>
> Same with mss. As far as I understand this one will be re-detected after
> a connection restore.
>
After the connection are repaired, it directly enter ESTABLISHED state,
so this TCP connection has no chance to negotiate such optional
features, such negotiation only can occur at 3WHS.
Thanks.
Yu
>> Thanks.
>>
>> Yu
>
^ permalink raw reply
* Re: [BUGFIX][PATCH 2/3] memcg/tcp: remove static_branch_slow_dec() at changing limit
From: Glauber Costa @ 2012-03-29 10:58 UTC (permalink / raw)
To: KAMEZAWA Hiroyuki; +Cc: netdev, David Miller, Andrew Morton
In-Reply-To: <4F740A41.6040002@jp.fujitsu.com>
On 03/29/2012 09:07 AM, KAMEZAWA Hiroyuki wrote:
> tcp memcontrol uses static_branch to optimize limit=RESOURCE_MAX case.
> If all cgroup's limit=RESOUCE_MAX, resource usage is not accounted.
> But it's buggy now.
>
> For example, do following
> # while sleep 1;do
> echo 9223372036854775807> /cgroup/memory/A/memory.kmem.tcp.limit_in_bytes;
> echo 300M> /cgroup/memory/A/memory.kmem.tcp.limit_in_bytes;
> done
>
> and run network application under A. tcp's usage is sometimes accounted
> and sometimes not accounted because of frequent changes of static_branch.
> Then, finally, you can see broken tcp.usage_in_bytes.
> WARN_ON() is printed because res_counter->usage goes below 0.
> ==
> kernel: ------------[ cut here ]----------
> kernel: WARNING: at kernel/res_counter.c:96 res_counter_uncharge_locked+0x37/0x40()
> <snip>
> kernel: Pid: 17753, comm: bash Tainted: G W 3.3.0+ #99
> kernel: Call Trace:
> kernel:<IRQ> [<ffffffff8104cc9f>] warn_slowpath_common+0x7f/0xc0
> kernel: [<ffffffff810d7e88>] ? rb_reserve__next_event+0x68/0x470
> kernel: [<ffffffff8104ccfa>] warn_slowpath_null+0x1a/0x20
> kernel: [<ffffffff810b4e37>] res_counter_uncharge_locked+0x37/0x40
> ...
> ==
>
> This patch removes static_branch_slow_dec() at changing res_counter's
> limit to RESOUCE_MAX. By this, once accounting started, the accountting
> will continue until the tcp cgroup is destroyed.
>
> I think this will not be problem in real use.
>
So...
Are the warnings still there if you have your other patch in this series?
Maybe what we should do is, flush the resource counters so they go back
to 0 besides decrementing the static branch. This way we get a more
consistent behavior.
Another thing to keep in mind, is that the static branch will only be
inactive if we turn off *all* controllers. You see this happening
because you are only testing with one.
So even if we go to the route you're proposing, we could probably try
doing something on the
global level, instead of a per-memcg boolean flat.
^ permalink raw reply
* Re: [PATCH linux-next] dmaengine: add context parameter fixups
From: Vinod Koul @ 2012-03-29 10:59 UTC (permalink / raw)
To: Mark Brown
Cc: fabio.estevam, alsa-devel, samuel, paul.gortmaker, Takashi Iwai,
netdev, linux-kernel, Alexandre Bounine, linux-next,
dan.j.williams, Fabio Estevam, lrg
In-Reply-To: <20120328155106.GY3232@opensource.wolfsonmicro.com>
On Wed, 2012-03-28 at 16:51 +0100, Mark Brown wrote:
> On Wed, Mar 28, 2012 at 05:44:22PM +0200, Takashi Iwai wrote:
> > Mark Brown wrote:
>
> > > No, not yet - it was only sent after the merge window. Quite why nobody
> > > managed to notice it before then I don't know. It'll go to him soon, or
> > > at least to Takashi, but don't know if it'll make -rc1 or not.
>
> > How is the situation now?
>
> > FYI, I'm going to send a pull request to Linus tomorrow or on Friday.
> > If anything needed to be merged in rc1, it must be there in time.
>
> It's in my tree, I didn't see an enormous rush to get it in TBH.
I should be sending the pull request for slave-dma to Linus this
evening.
Can you please include the fix I did in your tree in your pull request.
--
~Vinod
^ permalink raw reply
* Re: 答复: 答复: [PATCH] set fake_rtable's dst to NULL to avoid kernel Oops.
From: Eric Dumazet @ 2012-03-29 11:31 UTC (permalink / raw)
To: Peter Huang (Peng); +Cc: linux-kernel, harry.majun, zhoukang7, 'netdev'
In-Reply-To: <004501cd0d8f$c4e133b0$4ea39b10$%huangpeng@huawei.com>
On Thu, 2012-03-29 at 17:38 +0800, Peter Huang (Peng) wrote:
> Thks for your mail.
>
> >Check net/bridge/br_netfilter.c and commits e688a6048076 (net: introduce
> >DST_NOPEER dst flag ) 4adf0af6818f3ea5 (bridge: send correct MTU value
> >in PMTU (revised))
>
> This patch already included in kernel-3.3, but for our case, virtual tap device's delayed
> Deletion will also cause kernel oops even in kernel3.3.
I was suggesting you take a look at the commit content ;)
Then you can see the code in br_nf_local_in(), a bit cleaner than yours.
^ permalink raw reply
* 答复: 答复: 答复: [PATCH] set fake_rtable's dst to NULL to avoid kernel Oops.
From: Peter Huang (Peng) @ 2012-03-29 11:41 UTC (permalink / raw)
To: 'Eric Dumazet'
Cc: linux-kernel, harry.majun, zhoukang7, 'netdev'
In-Reply-To: <1333020682.2325.517.camel@edumazet-glaptop>
> >Check net/bridge/br_netfilter.c and commits e688a6048076 (net: introduce
> >DST_NOPEER dst flag ) 4adf0af6818f3ea5 (bridge: send correct MTU value
> >in PMTU (revised))
>
> This patch already included in kernel-3.3, but for our case, virtual tap device's delayed
> Deletion will also cause kernel oops even in kernel3.3.
>I was suggesting you take a look at the commit content ;)
>Then you can see the code in br_nf_local_in(), a bit cleaner than yours.
Yes, I will look into it, and trying to find out why this patch didn't work for our case.
Thanks for your advice:)
^ permalink raw reply
* Re: [PATCH] fix a bug in emitting the 16-bit immediate operand of AND
From: Eric Dumazet @ 2012-03-29 11:45 UTC (permalink / raw)
To: zhuangfeiran@ict.ac.cn; +Cc: davem, netdev, linux-kernel
In-Reply-To: <4F742AE4.6050006@ict.ac.cn>
Le jeudi 29 mars 2012 à 17:27 +0800, zhuangfeiran@ict.ac.cn a écrit :
> When K >= 0xFFFF0000, AND needs the two least significant bytes of K as
> its operand, but EMIT2() gives it the least significant byte of K and
> 0x2. EMIT() should be used here to replace EMIT2().
>
> Signed-off-by: Feiran Zhuang <zhuangfeiran@ict.ac.cn>
> ---
> arch/x86/net/bpf_jit_comp.c | 2 +-
> 1 files changed, 1 insertions(+), 1 deletions(-)
>
> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
> index 5671752..5a5b6e4 100644
> --- a/arch/x86/net/bpf_jit_comp.c
> +++ b/arch/x86/net/bpf_jit_comp.c
> @@ -289,7 +289,7 @@ void bpf_jit_compile(struct sk_filter *fp)
> EMIT2(0x24, K & 0xFF); /* and imm8,%al */
> } else if (K >= 0xFFFF0000) {
> EMIT2(0x66, 0x25); /* and imm16,%ax */
> - EMIT2(K, 2);
> + EMIT(K, 2);
> } else {
> EMIT1_off32(0x25, K); /* and imm32,%eax */
> }
Good catch, thanks !
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
^ permalink raw reply
* Re: [REGRESSION][PATCH] bpf_jit drops the ball on indirect negative mem references
From: Jan Seiffert @ 2012-03-29 11:54 UTC (permalink / raw)
To: netdev; +Cc: Eric Dumazet, linux-kernel, David S. Miller, Matt Evans
In-Reply-To: <1332967172.2325.22.camel@edumazet-glaptop>
Eric Dumazet schrieb:
> On Wed, 2012-03-28 at 22:26 +0200, Jan Seiffert wrote:
> [snip]
>> Say you have a UDP socket, and you want to filter for bogus source
>> addresses (drop already in kernel to save the context switch).
>> To have only one bpf program for ipv4 and ipv6 (you have to checked
>> the same bogus v4 addresses in mapped space), there is a point where
>> it elegant to have a negative offset saved in the X register.
> Cool, thats a valid use, thanks.
>
>
> Problem is you slow down the jit in its normal use, for a very specific
> use.
>
> Please rework your patch so that absolute loads of positive offsets
> (known at compile time) dont have to test negative offsets at run time.
>
> You add two instructions per load, and thats not good.
>
> Something like :
>
> sk_load_word:
> .globl sk_load_word
>
> test %esi,%esi
> js bpf_slow_path_word_neg
>
> sk_load_word_positive_offset:
> .globl sk_load_word_positive_offset
>
> mov %r9d,%eax # hlen
> sub %esi,%eax # hlen - offset
> cmp $3,%eax
>
> ...
>
>
>
Ok, to keep the ball rolling here is a V2 with the changes you suggested:
Consider the following test program:
#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <pcap-bpf.h>
#define die(x) do {perror(x); return 1;} while (0)
struct bpf_insn udp_filter[] = {
/* 0 */ BPF_STMT(BPF_LDX|BPF_W|BPF_IMM, -1048576+(0)), /* leax net[0] */
/* 1 */ BPF_STMT(BPF_LD|BPF_B|BPF_IND, 0), /* ldb [x+0] */
/* 2 */ BPF_STMT(BPF_RET|BPF_A, 0), /* ret a */
};
int main(int argc, char *argv[])
{
char buf[512];
struct sockaddr_in addr;
struct bpf_program prg;
socklen_t addr_s;
ssize_t res;
int fd;
addr.sin_family = AF_INET;
addr.sin_port = htons(5000);
addr.sin_addr.s_addr = 0;
addr_s = sizeof(addr);
prg.bf_len = sizeof(udp_filter)/sizeof(udp_filter[0]);
prg.bf_insns = udp_filter;
if(-1 == (fd = socket(AF_INET, SOCK_DGRAM, 0)))
die("socket");
if(-1 == bind(fd, (struct sockaddr *)&addr, sizeof(addr)))
die("bind");
if(-1 == setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prg, sizeof(prg)))
die("setsockopt");
res = recvfrom(fd, buf, sizeof(buf), 0, (struct sockaddr *)&addr, &addr_s);
if(res != -1)
printf("packet received: %zi bytes\n", res);
else
die("recvfrom");
return 0;
}
when used with the bpf jit disabled works:
console 1 $ ./bpf
console 2 $ echo "hello" | nc -u localhost 5000
console 1: packet received: 6 bytes
When the bpf jit gets enabled (echo 100 >
/proc/sys/net/core/bpf_jit_enable) the same program stops working:
console 1 $ ./bpf
console 2 $ echo "hello" | nc -u localhost 5000
console 1:
The reason is that both jits (x86 and powerpc) do not handle negative
memory references like SKF_NET_OFF or SKF_LL_OFF, only the simple
ancillary data references are supported (by mapping to special
instructions).
In the case of an absolute reference, the jit aborts the translation
if a negative reference is seen, also a negative k on the indirect
load aborts the translation, but if X is negative to begin with, only
the error handler is reached at runtime which drops the whole packet.
I propose the following patch to fix this situation.
Lightly tested on x86, but the powerpc asm part is prop. wrong.
Signed-of-by: Jan Seiffert <kaffeemonster@googlemail.com>
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index af1ab5e..e9b57b3 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -49,6 +49,10 @@
* Assembly helpers from arch/powerpc/net/bpf_jit.S:
*/
extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
+extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
+extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
+extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
#define FUNCTION_DESCR_SIZE 24
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index ff4506e..e590aa5 100644
--- a/arch/powerpc/net/bpf_jit_64.S
+++ b/arch/powerpc/net/bpf_jit_64.S
@@ -31,14 +31,13 @@
* then branch directly to slow_path_XXX if required. (In fact, could
* load a spare GPR with the address of slow_path_generic and pass size
* as an argument, making the call site a mtlr, li and bllr.)
- *
- * Technically, the "is addr < 0" check is unnecessary & slowing down
- * the ABS path, as it's statically checked on generation.
*/
.globl sk_load_word
sk_load_word:
cmpdi r_addr, 0
- blt bpf_error
+ blt bpf_slow_path_word_neg
+ .globl sk_load_word_positive_offset
+sk_load_word_positive_offset:
/* Are we accessing past headlen? */
subi r_scratch1, r_HL, 4
cmpd r_scratch1, r_addr
@@ -51,7 +50,9 @@ sk_load_word:
.globl sk_load_half
sk_load_half:
cmpdi r_addr, 0
- blt bpf_error
+ blt bpf_slow_path_half_neg
+ .globl sk_load_half_positive_offset
+sk_load_half_positive_offset:
subi r_scratch1, r_HL, 2
cmpd r_scratch1, r_addr
blt bpf_slow_path_half
@@ -61,7 +62,9 @@ sk_load_half:
.globl sk_load_byte
sk_load_byte:
cmpdi r_addr, 0
- blt bpf_error
+ blt bpf_slow_path_byte_neg
+ .globl sk_load_byte_positive_offset
+sk_load_byte_positive_offset:
cmpd r_HL, r_addr
ble bpf_slow_path_byte
lbzx r_A, r_D, r_addr
@@ -69,22 +72,20 @@ sk_load_byte:
/*
* BPF_S_LDX_B_MSH: ldxb 4*([offset]&0xf)
- * r_addr is the offset value, already known positive
+ * r_addr is the offset value
*/
.globl sk_load_byte_msh
sk_load_byte_msh:
+ cmpdi r_addr, 0
+ blt bpf_slow_path_byte_msh_neg
+ .globl sk_load_byte_msh_positive_offset
+sk_load_byte_msh_positive_offset:
cmpd r_HL, r_addr
ble bpf_slow_path_byte_msh
lbzx r_X, r_D, r_addr
rlwinm r_X, r_X, 2, 32-4-2, 31-2
blr
-bpf_error:
- /* Entered with cr0 = lt */
- li r3, 0
- /* Generated code will 'blt epilogue', returning 0. */
- blr
-
/* Call out to skb_copy_bits:
* We'll need to back up our volatile regs first; we have
* local variable space at r1+(BPF_PPC_STACK_BASIC).
@@ -136,3 +137,85 @@ bpf_slow_path_byte_msh:
lbz r_X, BPF_PPC_STACK_BASIC+(2*8)(r1)
rlwinm r_X, r_X, 2, 32-4-2, 31-2
blr
+
+/* Call out to bpf_internal_load_pointer_neg_helper:
+ * We'll need to back up our volatile regs first; we have
+ * local variable space at r1+(BPF_PPC_STACK_BASIC).
+ * Allocate a new stack frame here to remain ABI-compliant in
+ * stashing LR.
+ */
+#define sk_negative_common(SIZE) \
+ mflr r0; \
+ std r0, 16(r1); \
+ /* R3 goes in parameter space of caller's frame */ \
+ std r_skb, (BPF_PPC_STACKFRAME+48)(r1); \
+ std r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \
+ std r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \
+ stdu r1, -BPF_PPC_SLOWPATH_FRAME(r1); \
+ /* R3 = r_skb, as passed */ \
+ mr r4, r_addr; \
+ li r5, SIZE; \
+ bl bpf_internal_load_pointer_neg_helper; \
+ /* R3 != 0 on success */ \
+ addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \
+ ld r0, 16(r1); \
+ ld r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \
+ ld r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \
+ mtlr r0; \
+ cmpldi r3, 0; \
+ beq bpf_error_slow; /* cr0 = EQ */ \
+ mr r_addr, r3; \
+ ld r_skb, (BPF_PPC_STACKFRAME+48)(r1); \
+ /* Great success! */
+
+bpf_slow_path_word_neg:
+ lis r_scratch1,-32 /* SKF_LL_OFF */
+ cmpd r_addr, r_scratch1 /* addr < SKF_* */
+ blt bpf_error /* cr0 = LT */
+ .globl sk_load_word_negative_offset
+sk_load_word_negative_offset:
+ sk_negative_common(4)
+ lwz r_A, 0(r_addr)
+ blr
+
+bpf_slow_path_half_neg:
+ lis r_scratch1,-32 /* SKF_LL_OFF */
+ cmpd r_addr, r_scratch1 /* addr < SKF_* */
+ blt bpf_error /* cr0 = LT */
+ .globl sk_load_half_negative_offset
+sk_load_half_negative_offset:
+ sk_negative_common(2)
+ lhz r_A, 0(r_addr)
+ blr
+
+bpf_slow_path_byte_neg:
+ lis r_scratch1,-32 /* SKF_LL_OFF */
+ cmpd r_addr, r_scratch1 /* addr < SKF_* */
+ blt bpf_error /* cr0 = LT */
+ .globl sk_load_byte_negative_offset
+sk_load_byte_negative_offset:
+ sk_negative_common(1)
+ lbz r_A, 0(r_addr)
+ blr
+
+bpf_slow_path_byte_msh_neg:
+ lis r_scratch1,-32 /* SKF_LL_OFF */
+ cmpd r_addr, r_scratch1 /* addr < SKF_* */
+ blt bpf_error /* cr0 = LT */
+ .globl sk_load_byte_msh_negative_offset
+sk_load_byte_msh_negative_offset:
+ sk_negative_common(1)
+ lbz r_X, 0(r_addr)
+ rlwinm r_X, r_X, 2, 32-4-2, 31-2
+ blr
+
+bpf_error_slow:
+ /* fabricate a cr0 = lt */
+ li r_scratch1, -1
+ cmpdi r_scratch1, 0
+bpf_error:
+ /* Entered with cr0 = lt */
+ li r3, 0
+ /* Generated code will 'blt epilogue', returning 0. */
+ blr
+
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 73619d3..2dc8b14 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -127,6 +127,9 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
PPC_BLR();
}
+#define CHOOSE_LOAD_FUNC(K, func) \
+ ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
+
/* Assemble the body code between the prologue & epilogue. */
static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
struct codegen_context *ctx,
@@ -391,21 +394,16 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
/*** Absolute loads from packet header/data ***/
case BPF_S_LD_W_ABS:
- func = sk_load_word;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_word);
goto common_load;
case BPF_S_LD_H_ABS:
- func = sk_load_half;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_half);
goto common_load;
case BPF_S_LD_B_ABS:
- func = sk_load_byte;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
common_load:
- /*
- * Load from [K]. Reference with the (negative)
- * SKF_NET_OFF/SKF_LL_OFF offsets is unsupported.
- */
+ /* Load from [K]. */
ctx->seen |= SEEN_DATAREF;
- if ((int)K < 0)
- return -ENOTSUPP;
PPC_LI64(r_scratch1, func);
PPC_MTLR(r_scratch1);
PPC_LI32(r_addr, K);
@@ -429,7 +427,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
common_load_ind:
/*
* Load from [X + K]. Negative offsets are tested for
- * in the helper functions, and result in a 'ret 0'.
+ * in the helper functions.
*/
ctx->seen |= SEEN_DATAREF | SEEN_XREG;
PPC_LI64(r_scratch1, func);
@@ -443,13 +441,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
break;
case BPF_S_LDX_B_MSH:
- /*
- * x86 version drops packet (RET 0) when K<0, whereas
- * interpreter does allow K<0 (__load_pointer, special
- * ancillary data). common_load returns ENOTSUPP if K<0,
- * so we fall back to interpreter & filter works.
- */
- func = sk_load_byte_msh;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
goto common_load;
break;
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 6687022..63ae130 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -18,17 +18,18 @@
* r9d : hlen = skb->len - skb->data_len
*/
#define SKBDATA %r8
+#define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */
-sk_load_word_ind:
- .globl sk_load_word_ind
-
- add %ebx,%esi /* offset += X */
-# test %esi,%esi /* if (offset < 0) goto bpf_error; */
- js bpf_error
-
+ .p2align 1
sk_load_word:
.globl sk_load_word
+ test %esi,%esi
+ js bpf_slow_path_word_neg
+
+sk_load_word_positive_offset:
+ .globl sk_load_word_positive_offset
+
mov %r9d,%eax # hlen
sub %esi,%eax # hlen - offset
cmp $3,%eax
@@ -37,16 +38,16 @@ sk_load_word:
bswap %eax /* ntohl() */
ret
-
-sk_load_half_ind:
- .globl sk_load_half_ind
-
- add %ebx,%esi /* offset += X */
- js bpf_error
-
+ .p2align 1
sk_load_half:
.globl sk_load_half
+ test %esi,%esi
+ js bpf_slow_path_half_neg
+
+sk_load_half_positive_offset:
+ .globl sk_load_half_positive_offset
+
mov %r9d,%eax
sub %esi,%eax # hlen - offset
cmp $1,%eax
@@ -55,14 +56,16 @@ sk_load_half:
rol $8,%ax # ntohs()
ret
-sk_load_byte_ind:
- .globl sk_load_byte_ind
- add %ebx,%esi /* offset += X */
- js bpf_error
-
+ .p2align 1
sk_load_byte:
.globl sk_load_byte
+ test %esi,%esi
+ js bpf_slow_path_byte_neg
+
+sk_load_byte_positive_offset:
+ .globl sk_load_byte_positive_offset
+
cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte */
jle bpf_slow_path_byte
movzbl (SKBDATA,%rsi),%eax
@@ -73,25 +76,22 @@ sk_load_byte:
*
* Implements BPF_S_LDX_B_MSH : ldxb 4*([offset]&0xf)
* Must preserve A accumulator (%eax)
- * Inputs : %esi is the offset value, already known positive
+ * Inputs : %esi is the offset value
*/
-ENTRY(sk_load_byte_msh)
- CFI_STARTPROC
+ .p2align 1
+sk_load_byte_msh:
+ .globl sk_load_byte_msh
+ test %esi,%esi
+ js bpf_slow_path_byte_msh_neg
+
+sk_load_byte_msh_positive_offset:
+ .globl sk_load_byte_msh_positive_offset
cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
jle bpf_slow_path_byte_msh
movzbl (SKBDATA,%rsi),%ebx
and $15,%bl
shl $2,%bl
ret
- CFI_ENDPROC
-ENDPROC(sk_load_byte_msh)
-
-bpf_error:
-# force a return 0 from jit handler
- xor %eax,%eax
- mov -8(%rbp),%rbx
- leaveq
- ret
/* rsi contains offset and can be scratched */
#define bpf_slow_path_common(LEN) \
@@ -108,6 +108,7 @@ bpf_error:
pop %rdi
+ .p2align 1
bpf_slow_path_word:
bpf_slow_path_common(4)
js bpf_error
@@ -115,6 +116,7 @@ bpf_slow_path_word:
bswap %eax
ret
+ .p2align 1
bpf_slow_path_half:
bpf_slow_path_common(2)
js bpf_error
@@ -123,12 +125,14 @@ bpf_slow_path_half:
movzwl %ax,%eax
ret
+ .p2align 1
bpf_slow_path_byte:
bpf_slow_path_common(1)
js bpf_error
movzbl -12(%rbp),%eax
ret
+ .p2align 1
bpf_slow_path_byte_msh:
xchg %eax,%ebx /* dont lose A , X is about to be scratched */
bpf_slow_path_common(1)
@@ -138,3 +142,73 @@ bpf_slow_path_byte_msh:
shl $2,%al
xchg %eax,%ebx
ret
+
+#define sk_negative_common(SIZE) \
+ push %rdi; /* save skb */ \
+ push %r9; \
+ push SKBDATA; \
+/* rsi already has offset */ \
+ mov $SIZE,%ecx; /* size */ \
+ call bpf_internal_load_pointer_neg_helper; \
+ test %rax,%rax; \
+ pop SKBDATA; \
+ pop %r9; \
+ pop %rdi; \
+ jz bpf_error
+
+
+ .p2align 1
+bpf_slow_path_word_neg:
+ cmp SKF_MAX_NEG_OFF, %esi /* test range */
+ jl bpf_error /* offset lower -> error */
+sk_load_word_negative_offset:
+ .globl sk_load_word_negative_offset
+ sk_negative_common(4)
+ mov (%rax), %eax
+ bswap %eax
+ ret
+
+ .p2align 1
+bpf_slow_path_half_neg:
+ cmp SKF_MAX_NEG_OFF, %esi
+ jl bpf_error
+sk_load_half_negative_offset:
+ .globl sk_load_half_negative_offset
+ sk_negative_common(2)
+ mov (%rax),%ax
+ rol $8,%ax
+ movzwl %ax,%eax
+ ret
+
+ .p2align 1
+bpf_slow_path_byte_neg:
+ cmp SKF_MAX_NEG_OFF, %esi
+ jl bpf_error
+sk_load_byte_negative_offset:
+ .globl sk_load_byte_negative_offset
+ sk_negative_common(1)
+ movzbl (%rax), %eax
+ ret
+
+ .p2align 1
+bpf_slow_path_byte_msh_neg:
+ cmp SKF_MAX_NEG_OFF, %esi
+ jl bpf_error
+sk_load_byte_msh_negative_offset:
+ .globl sk_load_byte_msh_negative_offset
+ xchg %eax,%ebx /* dont lose A , X is about to be scratched */
+ sk_negative_common(1)
+ movzbl (%rax),%eax
+ and $15,%al
+ shl $2,%al
+ xchg %eax,%ebx
+ ret
+
+ .p2align 1
+bpf_error:
+# force a return 0 from jit handler
+ xor %eax,%eax
+ mov -8(%rbp),%rbx
+ leaveq
+ ret
+
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5671752..c20374f 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -30,7 +30,10 @@ int bpf_jit_enable __read_mostly;
* assembly code in arch/x86/net/bpf_jit.S
*/
extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
-extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[];
+extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
+extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
+extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
{
@@ -117,6 +120,8 @@ static inline void bpf_flush_icache(void *start, void *end)
set_fs(old_fs);
}
+#define CHOOSE_LOAD_FUNC(K, func) \
+ ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
void bpf_jit_compile(struct sk_filter *fp)
{
@@ -473,44 +478,42 @@ void bpf_jit_compile(struct sk_filter *fp)
#endif
break;
case BPF_S_LD_W_ABS:
- func = sk_load_word;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_word);
common_load: seen |= SEEN_DATAREF;
- if ((int)K < 0) {
- /* Abort the JIT because __load_pointer() is needed. */
- goto out;
- }
t_offset = func - (image + addrs[i]);
EMIT1_off32(0xbe, K); /* mov imm32,%esi */
EMIT1_off32(0xe8, t_offset); /* call */
break;
case BPF_S_LD_H_ABS:
- func = sk_load_half;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_half);
goto common_load;
case BPF_S_LD_B_ABS:
- func = sk_load_byte;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
goto common_load;
case BPF_S_LDX_B_MSH:
- if ((int)K < 0) {
- /* Abort the JIT because __load_pointer() is needed. */
- goto out;
- }
+ func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
seen |= SEEN_DATAREF | SEEN_XREG;
- t_offset = sk_load_byte_msh - (image + addrs[i]);
+ t_offset = func - (image + addrs[i]);
EMIT1_off32(0xbe, K); /* mov imm32,%esi */
EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
break;
case BPF_S_LD_W_IND:
- func = sk_load_word_ind;
+ func = sk_load_word;
common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG;
t_offset = func - (image + addrs[i]);
- EMIT1_off32(0xbe, K); /* mov imm32,%esi */
+ if (K) {
+ EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */
+ EMIT(K, 4);
+ } else {
+ EMIT2(0x89,0xde); /* mov %ebx,%esi */
+ }
EMIT1_off32(0xe8, t_offset); /* call sk_load_xxx_ind */
break;
case BPF_S_LD_H_IND:
- func = sk_load_half_ind;
+ func = sk_load_half;
goto common_load_ind;
case BPF_S_LD_B_IND:
- func = sk_load_byte_ind;
+ func = sk_load_byte;
goto common_load_ind;
case BPF_S_JMP_JA:
t_offset = addrs[i + K] - addrs[i];
diff --git a/net/core/filter.c b/net/core/filter.c
index 5dea452..04ca613 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -41,7 +41,7 @@
#include <linux/ratelimit.h>
/* No hurry in this branch */
-static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
+void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
{
u8 *ptr = NULL;
@@ -54,13 +54,14 @@ static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
return ptr;
return NULL;
}
+EXPORT_SYMBOL(bpf_internal_load_pointer_neg_helper);
static inline void *load_pointer(const struct sk_buff *skb, int k,
unsigned int size, void *buffer)
{
if (k >= 0)
return skb_header_pointer(skb, k, size, buffer);
- return __load_pointer(skb, k, size);
+ return bpf_internal_load_pointer_neg_helper(skb, k, size);
}
/**
^ permalink raw reply related
* Re: [PATCH -3.2.y] igb: Fix locking to silence ASSERT_RTNL() warning during suspend/resume
From: Srivatsa S. Bhat @ 2012-03-29 12:31 UTC (permalink / raw)
To: netdev
Cc: Greg KH, zheng.z.yan, aaron.f.brown, jeffrey.t.kirsher,
David S. Miller, stable, srivatsa.bhat,
linux-kernel@vger.kernel.org, alexander.h.duyck, carolyn.wyborny,
eric.dumazet, Ben Hutchings
In-Reply-To: <1332777648.3500.93.camel@deadeye>
[ CC'ing netdev mailing list and lkml. I have put relevant info by hand to
preserve the context, since I didn't find any archives for the stable
mailing list, to give a link to. ]
On 03/26/2012 09:30 PM, Ben Hutchings wrote:
> On Mon, 2012-03-26 at 17:37 +0530, Srivatsa S. Bhat wrote:
>> From: Zheng Yan <zheng.z.yan@intel.com>
>>
>> [ Upstream commit 749ab2cd127046df79084b6b9165b23491b1db5f ]
>>
>> During suspend/resume (and possibly in other scenarios as well), the
>> ASSERT_RTNL() warning is triggered in netif_set_real_num_tx/rx_queues()
>> functions, something like:
[ 374.073765] RTNL: assertion failed at net/core/dev.c (1718)
[ 374.073767] Pid: 566, comm: kworker/u:4 Not tainted 3.2.13-0.0.0.2.0f8ab74-trace #1
[ 374.073769] RTNL: assertion failed at net/core/dev.c (1718)
[ 374.073771] Call Trace:
[ 374.073772] Pid: 5271, comm: kworker/u:10 Not tainted 3.2.13-0.0.0.2.0f8ab74-trace #1
[ 374.073775] Call Trace:
[ 374.073780] [<ffffffff81385e3e>] netif_set_real_num_tx_queues+0x1ae/0x1d0
[ 374.073785] [<ffffffff81385e3e>] netif_set_real_num_tx_queues+0x1ae/0x1d0
[ 374.073792] [<ffffffffa0323f92>] igb_set_interrupt_capability+0x152/0x1f0 [igb]
[ 374.073797] [<ffffffffa0323f92>] igb_set_interrupt_capability+0x152/0x1f0 [igb]
[ 374.073814] [<ffffffffa0328968>] igb_init_interrupt_scheme+0x28/0x330 [igb]
[ 374.073819] [<ffffffffa0328968>] igb_init_interrupt_scheme+0x28/0x330 [igb]
[ 374.073823] [<ffffffffa0329a9c>] igb_resume+0x9c/0x160 [igb]
[ 374.073828] [<ffffffffa0329a9c>] igb_resume+0x9c/0x160 [igb]
[ 374.073831] [<ffffffff812707b2>] pci_legacy_resume+0x42/0x60
[ 374.073835] [<ffffffff812707b2>] pci_legacy_resume+0x42/0x60
[ 374.073837] [<ffffffff812709c0>] pci_pm_resume+0x90/0xd0
[ 374.073840] [<ffffffff812709c0>] pci_pm_resume+0x90/0xd0
[ 374.073843] [<ffffffff8131b59c>] pm_op+0x10c/0x1e0
[ 374.073847] [<ffffffff8131b59c>] pm_op+0x10c/0x1e0
[ 374.073849] [<ffffffff8131c5ca>] device_resume+0x27a/0x2c0
[ 374.073852] [<ffffffff8131c5ca>] device_resume+0x27a/0x2c0
[ 374.073854] [<ffffffff8131c631>] async_resume+0x21/0x50
[ 374.073857] [<ffffffff8131c631>] async_resume+0x21/0x50
[ 374.073860] [<ffffffff8107e564>] async_run_entry_fn+0x84/0x180
[ 374.073864] [<ffffffff8107e564>] async_run_entry_fn+0x84/0x180
[ 374.073867] [<ffffffff8106ecb1>] process_one_work+0x171/0x350
[ 374.073871] [<ffffffff8106ecb1>] process_one_work+0x171/0x350
[ 374.073874] [<ffffffff8107e4e0>] ? async_schedule+0x20/0x20
[ 374.073876] [<ffffffff8107e4e0>] ? async_schedule+0x20/0x20
[ 374.073879] [<ffffffff81071eeb>] worker_thread+0x18b/0x430
[ 374.073881] [<ffffffff81071eeb>] worker_thread+0x18b/0x430
[ 374.073884] [<ffffffff81071d60>] ? manage_workers+0x120/0x120
[ 374.073887] [<ffffffff81071d60>] ? manage_workers+0x120/0x120
[ 374.073890] [<ffffffff8107683e>] kthread+0x9e/0xb0
[ 374.073892] [<ffffffff8107683e>] kthread+0x9e/0xb0
[ 374.073896] [<ffffffff81451e04>] kernel_thread_helper+0x4/0x10
[ 374.073899] [<ffffffff81451e04>] kernel_thread_helper+0x4/0x10
[ 374.073902] [<ffffffff81447c21>] ? retint_restore_args+0x13/0x13
[ 374.073905] [<ffffffff81447c21>] ? retint_restore_args+0x13/0x13
[ 374.073907] [<ffffffff810767a0>] ? kthread_worker_fn+0x1b0/0x1b0
[ 374.073911] [<ffffffff810767a0>] ? kthread_worker_fn+0x1b0/0x1b0
[ 374.073913] [<ffffffff81451e00>] ? gs_change+0x13/0x13
[ 374.073915] [<ffffffff81451e00>] ? gs_change+0x13/0x13
>> diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
>> index 222954d..8775087 100644
>> --- a/drivers/net/ethernet/intel/igb/igb_main.c
>> +++ b/drivers/net/ethernet/intel/igb/igb_main.c
>> @@ -6697,7 +6697,18 @@ static int igb_resume(struct pci_dev *pdev)
>> pci_enable_wake(pdev, PCI_D3hot, 0);
>> pci_enable_wake(pdev, PCI_D3cold, 0);
>>
>> - if (igb_init_interrupt_scheme(adapter)) {
>> + if (!rtnl_is_locked()) {
>
> This doesn't tell whether this process holds the lock. So it suppresses
> the warning but doesn't fix the real bug.
>
> Ben.
>
> You mean to say that this issue needs to be revisited in mainline too?
On 03/27/2012 07:57 PM, Ben Hutchings wrote:
| Oh, yes. Because you said this was a smaller patch for stable, I didn't
| realise that mainline had this problem too.
>
>> + /*
>> + * shut up ASSERT_RTNL() warning in
>> + * netif_set_real_num_tx/rx_queues.
>> + */
>> + rtnl_lock();
>> + err = igb_init_interrupt_scheme(adapter);
>> + rtnl_unlock();
>> + } else {
>> + err = igb_init_interrupt_scheme(adapter);
>> + }
>> + if (err) {
>> dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
>> return -ENOMEM;
>> }
>
>
Regards,
Srivatsa S. Bhat
^ permalink raw reply
* Re: [PATCH V3 0/6] net/mlx4_en: DCB QoS support
From: Or Gerlitz @ 2012-03-29 12:33 UTC (permalink / raw)
To: Eric Dumazet
Cc: David S. Miller, netdev, Roland Dreier, Yevgeny Petrilin,
Oren Duer, Amir Vadai, John Fastabend, Amir Vadai
In-Reply-To: <1332990846.3402.5.camel@edumazet-laptop>
On Thu, Mar 29, 2012 at 5:14 AM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> Le jeudi 29 mars 2012 à 00:21 +0200, Or Gerlitz a écrit :
>
>> For the ratelimit Eric D. provided feedback and it was implemented along his suggestion,
>
>
> My suggestion was exactly the following :
>
> /sys/class/net/eth2/qos/0/ratelimit
> ...
> /sys/class/net/eth2/qos/7/ratelimit
>
>> and now John and Ben have other suggestions,
>
> I dont think so.
> Amir provided in V2 something that was not what I suggested.
>
> /sys/class/net/eth2/ratelimit/tc0
> ...
> /sys/class/net/eth2/ratelimit/tc7
>
>
> And this is where John, Ben were complaining.
> [ Obviously I totally agree with them ]
to be precise they were suggesting to go e.g through DCBNL and not sysfs,
anyway,Amir works to implement this along their suggestion
Or
^ permalink raw reply
* [Q] ipv6: RTM_GETROUTE interpretation of RTA_IIF
From: Shmulik Ladkani @ 2012-03-29 13:03 UTC (permalink / raw)
To: netdev
Hi,
In IPv4, if the RTA_IIF attribute is specified in an RTM_GETROUTE
message, then a route is searched as if a packet was received on the
specified iif interface - i.e. 'inet_rtm_getroute()' calls
'ip_route_input()'.
However in IPv6, RTA_IIF is not interpreted in the same way:
'inet6_rtm_getroute()' always calls 'ip6_route_output()', regardless the
RTA_IIF attribute.
As a result, in IPv6 there's no way to use RTM_GETROUTE in order to look
for a route as if a packet was received on a specific interface.
I'd like to modify 'inet6_rtm_getroute()' so that RTA_IIF is interpreted
in the same way as in IPv4's 'inet_rtm_getroute()'.
Before I come up with a patch, I'd like to know whether current
interpretation of RTA_IIF in 'inet6_rtm_getroute()' is deliberate.
Regards,
Shmulik
^ permalink raw reply
* Re: [REGRESSION][PATCH] bpf_jit drops the ball on indirect negative mem references
From: Eric Dumazet @ 2012-03-29 13:57 UTC (permalink / raw)
To: Jan Seiffert; +Cc: netdev, linux-kernel, David S. Miller, Matt Evans
In-Reply-To: <4F744D58.3070009@googlemail.com>
Le jeudi 29 mars 2012 à 13:54 +0200, Jan Seiffert a écrit :
> Ok, to keep the ball rolling here is a V2 with the changes you suggested:
>
...
> I propose the following patch to fix this situation.
> Lightly tested on x86, but the powerpc asm part is prop. wrong.
>
>
> Signed-of-by: Jan Seiffert <kaffeemonster@googlemail.com>
>
x86 part seems very good at first glance, I'll test it and give my
feedback soon.
Thanks !
^ permalink raw reply
* Re: [Q/RFC] BPF use in broader scope
From: Nuno Martins @ 2012-03-29 14:04 UTC (permalink / raw)
To: Jiri Pirko
Cc: netdev, eric.dumazet, davem, bhutchings, shemminger,
Alfredo Matos
In-Reply-To: <20120329074443.GB2098@minipsycho>
On Thu, Mar 29, 2012 at 8:44 AM, Jiri Pirko <jpirko@redhat.com> wrote:
> Hi all.
>
> I came to an idea of using BPF infrastructure currently used in kernel,
> for computing hashes selecting TX ports in team device. Since the same
> data (skb) are alalyzed/used as for socket filtering, BPF seems so be quite
> suitable for this. It would allow userspace daemon to specify various
> kinds of TX selection algorithms.
>
> Here are proposed things to be done:
> 1) introduce in-kernel api for creating sk-unattached filters (I have
> the patch cooked up already)
>
> 2) extend current BPF machine to allow XOR operation. Not sure if this
> is doable or what the best of doing this is.
>
> 3) add possibility to pass some data to the machine via
> pre-filling "Scratch Memory Store". I think this can be done easily
> moving "u32 mem[BPF_MEMWORDS];" to bpf_func caller and pass it as the
> second function parameter. That should not break anything.
>
> Then the computed hash can be either stored into Scratch memory or returned
> directly (where ordinary sk filters return len).
>
> Does this seems reasonable? Thoughts, comments?
>
Hi all,
I've also been working on mechanism that requires creating custom BFP
filters, but for PID based packet filtering. It allows attaching
custom filters to a
socket, through setsocketopt, making it possible to detect when packets belongs
to a target process id (previously identified through kprobes).
The in-kernel api we use, enables registering and unregistering filter
functions,
which are then stored on a filter function list.
When attaching the custom filter function, it replaces the current
filter, releasing the JIT code if necessary. However, the newly
attached filter function does not get JIT compiled (bpf_jit_compile)
to allow custom functions without having to provide the corresponding
ASM code.
Using the JIT extensions that Jirka mentions in step 3 could also allows to
compile custom.
We are in the process of making the source code available through a
project page dedicated to PID monitoring, and will (hopefully) send a
Q/RFC to this list tomorrow.
> Thanks!
Thanks.
>
> Jirka
>
Nuno Martins
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH] Lockd: pass network namespace to creation and destruction routines
From: Stanislav Kinsbursky @ 2012-03-29 14:23 UTC (permalink / raw)
To: Trond.Myklebust
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
These routines are called from locks reclaimer() kernel thread. This thread
works in "init_net" network context and currently relays on presence on lockd
thread and it's per-net resources. Thus lockd_up() and lockd_down() can't use
current network context. So let's pass corrent one into them.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
---
fs/lockd/clntlock.c | 10 +++++-----
fs/lockd/svc.c | 7 +++----
fs/nfsd/nfssvc.c | 6 +++---
include/linux/lockd/bind.h | 4 ++--
4 files changed, 13 insertions(+), 14 deletions(-)
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index ba1dc2e..32b3c2b 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -56,7 +56,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
u32 nlm_version = (nlm_init->nfs_version == 2) ? 1 : 4;
int status;
- status = lockd_up();
+ status = lockd_up(nlm_init->net);
if (status < 0)
return ERR_PTR(status);
@@ -65,7 +65,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
nlm_init->hostname, nlm_init->noresvport,
nlm_init->net);
if (host == NULL) {
- lockd_down();
+ lockd_down(nlm_init->net);
return ERR_PTR(-ENOLCK);
}
@@ -81,7 +81,7 @@ EXPORT_SYMBOL_GPL(nlmclnt_init);
void nlmclnt_done(struct nlm_host *host)
{
nlmclnt_release_host(host);
- lockd_down();
+ lockd_down(host->net);
}
EXPORT_SYMBOL_GPL(nlmclnt_done);
@@ -224,7 +224,7 @@ reclaimer(void *ptr)
allow_signal(SIGKILL);
down_write(&host->h_rwsem);
- lockd_up(); /* note: this cannot fail as lockd is already running */
+ lockd_up(host->net); /* note: this cannot fail as lockd is already running */
dprintk("lockd: reclaiming locks for host %s\n", host->h_name);
@@ -275,6 +275,6 @@ restart:
/* Release host handle after use */
nlmclnt_release_host(host);
- lockd_down();
+ lockd_down(host->net);
return 0;
}
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index b34100e..ce4c80e 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -295,11 +295,10 @@ static void lockd_down_net(struct net *net)
/*
* Bring up the lockd process if it's not already up.
*/
-int lockd_up(void)
+int lockd_up(struct net *net)
{
struct svc_serv *serv;
int error = 0;
- struct net *net = current->nsproxy->net_ns;
mutex_lock(&nlmsvc_mutex);
/*
@@ -377,12 +376,12 @@ EXPORT_SYMBOL_GPL(lockd_up);
* Decrement the user count and bring down lockd if we're the last.
*/
void
-lockd_down(void)
+lockd_down(struct net *net)
{
mutex_lock(&nlmsvc_mutex);
if (nlmsvc_users) {
if (--nlmsvc_users) {
- lockd_down_net(current->nsproxy->net_ns);
+ lockd_down_net(net);
goto out;
}
} else {
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index fce472f..0f3e35b 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -220,7 +220,7 @@ static int nfsd_startup(unsigned short port, int nrservs)
ret = nfsd_init_socks(port);
if (ret)
goto out_racache;
- ret = lockd_up();
+ ret = lockd_up(&init_net);
if (ret)
goto out_racache;
ret = nfs4_state_start();
@@ -229,7 +229,7 @@ static int nfsd_startup(unsigned short port, int nrservs)
nfsd_up = true;
return 0;
out_lockd:
- lockd_down();
+ lockd_down(&init_net);
out_racache:
nfsd_racache_shutdown();
return ret;
@@ -246,7 +246,7 @@ static void nfsd_shutdown(void)
if (!nfsd_up)
return;
nfs4_state_shutdown();
- lockd_down();
+ lockd_down(&init_net);
nfsd_racache_shutdown();
nfsd_up = false;
}
diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h
index 11a966e..4d24d64 100644
--- a/include/linux/lockd/bind.h
+++ b/include/linux/lockd/bind.h
@@ -54,7 +54,7 @@ extern void nlmclnt_done(struct nlm_host *host);
extern int nlmclnt_proc(struct nlm_host *host, int cmd,
struct file_lock *fl);
-extern int lockd_up(void);
-extern void lockd_down(void);
+extern int lockd_up(struct net *net);
+extern void lockd_down(struct net *net);
#endif /* LINUX_LOCKD_BIND_H */
^ permalink raw reply related
* Re: [PATCH] Lockd: pass network namespace to creation and destruction routines
From: Stanislav Kinsbursky @ 2012-03-29 14:36 UTC (permalink / raw)
To: Trond.Myklebust@netapp.com
Cc: linux-nfs@vger.kernel.org, Pavel Emelianov, neilb@suse.de,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
James Bottomley, bfields@fieldses.org, davem@davemloft.net,
devel@openvz.org
In-Reply-To: <20120329142209.20506.43224.stgit@localhost6.localdomain6>
This patch has a flaw. Thus will be v2.
Sorry.
--
Best regards,
Stanislav Kinsbursky
^ permalink raw reply
* [PATCH v2] Lockd: pass network namespace to creation and destruction routines
From: Stanislav Kinsbursky @ 2012-03-29 14:54 UTC (permalink / raw)
To: Trond.Myklebust
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
v2: dereference of most probably already released nlm_host removed in
nlmclnt_done() and reclaimer().
These routines are called from locks reclaimer() kernel thread. This thread
works in "init_net" network context and currently relays on persence on lockd
thread and it's per-net resources. Thus lockd_up() and lockd_down() can't relay
on current network context. So let's pass corrent one into them.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
---
fs/lockd/clntlock.c | 13 ++++++++-----
fs/lockd/svc.c | 7 +++----
fs/nfsd/nfssvc.c | 6 +++---
include/linux/lockd/bind.h | 4 ++--
4 files changed, 16 insertions(+), 14 deletions(-)
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index ba1dc2e..ca0a080 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -56,7 +56,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
u32 nlm_version = (nlm_init->nfs_version == 2) ? 1 : 4;
int status;
- status = lockd_up();
+ status = lockd_up(nlm_init->net);
if (status < 0)
return ERR_PTR(status);
@@ -65,7 +65,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
nlm_init->hostname, nlm_init->noresvport,
nlm_init->net);
if (host == NULL) {
- lockd_down();
+ lockd_down(nlm_init->net);
return ERR_PTR(-ENOLCK);
}
@@ -80,8 +80,10 @@ EXPORT_SYMBOL_GPL(nlmclnt_init);
*/
void nlmclnt_done(struct nlm_host *host)
{
+ struct net *net = host->net;
+
nlmclnt_release_host(host);
- lockd_down();
+ lockd_down(net);
}
EXPORT_SYMBOL_GPL(nlmclnt_done);
@@ -220,11 +222,12 @@ reclaimer(void *ptr)
struct nlm_wait *block;
struct file_lock *fl, *next;
u32 nsmstate;
+ struct net *net = host->net;
allow_signal(SIGKILL);
down_write(&host->h_rwsem);
- lockd_up(); /* note: this cannot fail as lockd is already running */
+ lockd_up(net); /* note: this cannot fail as lockd is already running */
dprintk("lockd: reclaiming locks for host %s\n", host->h_name);
@@ -275,6 +278,6 @@ restart:
/* Release host handle after use */
nlmclnt_release_host(host);
- lockd_down();
+ lockd_down(net);
return 0;
}
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index b34100e..ce4c80e 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -295,11 +295,10 @@ static void lockd_down_net(struct net *net)
/*
* Bring up the lockd process if it's not already up.
*/
-int lockd_up(void)
+int lockd_up(struct net *net)
{
struct svc_serv *serv;
int error = 0;
- struct net *net = current->nsproxy->net_ns;
mutex_lock(&nlmsvc_mutex);
/*
@@ -377,12 +376,12 @@ EXPORT_SYMBOL_GPL(lockd_up);
* Decrement the user count and bring down lockd if we're the last.
*/
void
-lockd_down(void)
+lockd_down(struct net *net)
{
mutex_lock(&nlmsvc_mutex);
if (nlmsvc_users) {
if (--nlmsvc_users) {
- lockd_down_net(current->nsproxy->net_ns);
+ lockd_down_net(net);
goto out;
}
} else {
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index fce472f..0f3e35b 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -220,7 +220,7 @@ static int nfsd_startup(unsigned short port, int nrservs)
ret = nfsd_init_socks(port);
if (ret)
goto out_racache;
- ret = lockd_up();
+ ret = lockd_up(&init_net);
if (ret)
goto out_racache;
ret = nfs4_state_start();
@@ -229,7 +229,7 @@ static int nfsd_startup(unsigned short port, int nrservs)
nfsd_up = true;
return 0;
out_lockd:
- lockd_down();
+ lockd_down(&init_net);
out_racache:
nfsd_racache_shutdown();
return ret;
@@ -246,7 +246,7 @@ static void nfsd_shutdown(void)
if (!nfsd_up)
return;
nfs4_state_shutdown();
- lockd_down();
+ lockd_down(&init_net);
nfsd_racache_shutdown();
nfsd_up = false;
}
diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h
index 11a966e..4d24d64 100644
--- a/include/linux/lockd/bind.h
+++ b/include/linux/lockd/bind.h
@@ -54,7 +54,7 @@ extern void nlmclnt_done(struct nlm_host *host);
extern int nlmclnt_proc(struct nlm_host *host, int cmd,
struct file_lock *fl);
-extern int lockd_up(void);
-extern void lockd_down(void);
+extern int lockd_up(struct net *net);
+extern void lockd_down(struct net *net);
#endif /* LINUX_LOCKD_BIND_H */
^ permalink raw reply related
* [PATCH V4 4/8] net/mlx4_en: sk_prio <=> UP for untagged traffic
From: Amir Vadai @ 2012-03-29 15:03 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Yevgeny Petrilin, Oren Duer, Amir Vadai,
Amir Vadai
In-Reply-To: <1333033418-1669-1-git-send-email-amirv@mellanox.com>
Since vlan egress map is only good for tagged traffic, need to have other
mapping to be used by untagged traffic.
For that, the driver uses sch_mqprio mapping. This mapping could be set by
using tc tool from iproute2 package.
Mapped UP will be used by the HW for QoS purposes, but won't go out on the
wire.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 18 ++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 2 +-
2 files changed, 19 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 9b456ae..44dbe1f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -45,6 +45,14 @@
#include "mlx4_en.h"
#include "en_port.h"
+static int mlx4_en_setup_tc(struct net_device *dev, u8 up)
+{
+ if (up != MLX4_EN_NUM_UP)
+ return -EINVAL;
+
+ return 0;
+}
+
static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -1042,6 +1050,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
.ndo_poll_controller = mlx4_en_netpoll,
#endif
.ndo_set_features = mlx4_en_set_features,
+ .ndo_setup_tc = mlx4_en_setup_tc,
};
int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
@@ -1130,6 +1139,15 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
+ netdev_set_num_tc(dev, MLX4_EN_NUM_UP);
+
+ /* First 9 rings are for UP 0 */
+ netdev_set_tc_queue(dev, 0, MLX4_EN_NUM_TX_RINGS + 1, 0);
+
+ /* Partition Tx queues evenly amongst UP's 1-7 */
+ for (i = 1; i < MLX4_EN_NUM_UP; i++)
+ netdev_set_tc_queue(dev, i, 1, MLX4_EN_NUM_TX_RINGS + i);
+
SET_ETHTOOL_OPS(dev, &mlx4_en_ethtool_ops);
/* Set defualt MAC */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 94a605a..d9bab53 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -577,7 +577,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb)
return MLX4_EN_NUM_TX_RINGS + (vlan_tag >> 13);
}
- return __skb_tx_hash(dev, skb, MLX4_EN_NUM_TX_RINGS);
+ return skb_tx_hash(dev, skb);
}
static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt)
--
1.7.8.2
^ permalink raw reply related
* [PATCH V4 5/8] net/route: export symbol ip_tos2prio
From: Amir Vadai @ 2012-03-29 15:03 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Yevgeny Petrilin, Oren Duer, Amir Vadai,
Amir Vadai
In-Reply-To: <1333033418-1669-1-git-send-email-amirv@mellanox.com>
Need to export this to enable drivers use rt_tos2priority()
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
net/ipv4/route.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 12ccf88..69e0b86 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -230,7 +230,7 @@ const __u8 ip_tos2prio[16] = {
TC_PRIO_INTERACTIVE_BULK,
ECN_OR_COST(INTERACTIVE_BULK)
};
-
+EXPORT_SYMBOL(ip_tos2prio);
/*
* Route cache.
--
1.7.8.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox