| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAKyyzSSs1PUfJXTPDWTbWU5p+b54qti_N_6kR6mJWWrp__rykw@mail.gmail.com>
Date: Tue, 3 Jun 2014 14:54:29 +0300
From: Igor Royzis <igorr@...rtex.com>
To: "Michael S. Tsirkin" <mst@...hat.com>
Cc: "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Tom Herbert <therbert@...gle.com>,
Daniel Borkmann <dborkman@...hat.com>,
Nicolas Dichtel <nicolas.dichtel@...nd.com>,
Simon Horman <horms@...ge.net.au>,
Joe Perches <joe@...ches.com>, Jiri Pirko <jiri@...nulli.us>,
Florian Westphal <fw@...len.de>,
Paul Durrant <Paul.Durrant@...rix.com>,
Thomas Graf <tgraf@...g.ch>, Jan Beulich <JBeulich@...e.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
Miklos Szeredi <mszeredi@...e.cz>,
linux-kernel <linux-kernel@...r.kernel.org>,
netdev <netdev@...r.kernel.org>,
Anton Nayshtut <anton@...rtex.com>
Subject: Re: [PATCH] Fixed zero copy GSO without orphaning the fragments
Eric, could you please provide a feedback on the suggestion to move
the pointer from skb_shared_info to skbuff? If we must fit
skb_shared_info till the 'frags' field into 1 cache line (I honestly
don't quite understand why (the whole structure as well as the skb's
data will always require > 1 cache line anyway) and I would
appreciate if you elaborate on this more), then moving the pointer to
the parent fragment off skb_shared_info should help. Am I right?
The pointer is essential if we want to solve the incorrect way the
kernel handles a combination of packet segmentation (of any reason, in
our case it was a VM guest not supporting GRO) and zero-copy feature.
Disabling zero-copy for segmented packets is a workaround but an
efficient solution would require either:
a) a pointer in skb_shared_info, or
b) a pointer in skbuff, or
c) reusing a [currently unused] existing pointer/field in a skb
structure, which is a bad idea and I list it for completeness only.
Please comment,
-Igor
On Sun, Jun 1, 2014 at 3:21 PM, Michael S. Tsirkin <mst@...hat.com> wrote:
> On Sun, Jun 01, 2014 at 02:39:39PM +0300, Igor Royzis wrote:
>> The patch discussion seems got lost due to a delay it took us to get
>> the numbers. We believe that a 24% improvement in VM's network
>> performance (and probably the better improvement the more guests are
>> running on a host) is worth commenting and getting to some conclusion.
>
> Absolutely, but we need to find a way to address Eric's comments.
>
>> > Before your patch :
>> >
>> > sizeof(struct skb_shared_info)=0x140
>> > offsetof(struct skb_shared_info, frags[1])=0x40
>> >
>> > SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) -> 0x140
>> >
>> > After your patch :
>> >
>> > sizeof(struct skb_shared_info)=0x148
>> > offsetof(struct skb_shared_info, frags[1])=0x48
>> >
>> > SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) -> 0x180
>> >
>> > Thats a serious bump, because it increases all skb truesizes, and
>> > typical skb with one fragment will use 2 cache lines instead of one in
>> > struct skb_shared_info, so this adds memory pressure in fast path.
>> >
>> > So while this patch might increase performance for some workloads,
>> > it generally decreases performance on many others.
>>
>> Would moving the parent fragment pointer from skb_shared_info to
>> skbuff solve this issue?
>>
>> Regards,
>> -Igor
>>
>> On Sun, May 25, 2014 at 1:54 PM, Igor Royzis <igorr@...rtex.com> wrote:
>> >> If true, I'd like to see some performance numbers please.
>> >
>> > The numbers have been obtained by running iperf between 2 QEMU Win2012
>> > VMs, 4 vCPU/ 4GB RAM each.
>> > iperf parameters: -w 256K -l 256K -t 300
>> > Original kernel 3.15.0-rc5: 34.4 Gbytes transferred, 984
>> > Mbits/sec bandwidth.
>> > Kernel 3.15.0-rc5 with our patch: 42.5 Gbytes transferred, 1.22
>> > Gbits/sec bandwidth.
>> >
>> > Overall improvement is about 24%.
>> > Below are raw iperf outputs.
>> >
>> > kernel 3.15.0-rc5:
>> > C:\iperf>iperf -c 192.168.11.2 -w 256K -l 256K -t 300
>> > ------------------------------------------------------------
>> > Client connecting to 192.168.11.2, TCP port 5001
>> > TCP window size: 256 KByte
>> > ------------------------------------------------------------
>> > [ 3] local 192.168.11.1 port 49167 connected with 192.168.11.2 port 5001
>> > [ ID] Interval Transfer Bandwidth
>> > [ 3] 0.0-300.7 sec 34.4 GBytes 984 Mbits/sec
>> >
>> > kernel 3.15.0-rc5-patched:
>> > C:\iperf>iperf -c 192.168.11.2 -w 256K -l 256K -t 300
>> > ------------------------------------------------------------
>> > Client connecting to 192.168.11.2, TCP port 5001
>> > TCP window size: 256 KByte
>> > ------------------------------------------------------------
>> > [ 3] local 192.168.11.1 port 49167 connected with 192.168.11.2 port 5001
>> > [ ID] Interval Transfer Bandwidth
>> > [ 3] 0.0-300.7 sec 42.5 GBytes 1.22 Gbits/sec
>> >
>> > On Tue, May 20, 2014 at 2:50 PM, Michael S. Tsirkin <mst@...hat.com> wrote:
>> >>
>> >> On Tue, May 20, 2014 at 02:24:21PM +0300, Igor Royzis wrote:
>> >> > Fix accessing GSO fragments memory (and a possible corruption therefore) after
>> >> > reporting completion in a zero copy callback. The previous fix in the commit 1fd819ec
>> >> > orphaned frags which eliminates zero copy advantages. The fix makes the completion
>> >> > called after all the fragments were processed avoiding unnecessary orphaning/copying
>> >> > from userspace.
>> >> >
>> >> > The GSO fragments corruption issue was observed in a typical QEMU/KVM VM setup that
>> >> > hosts a Windows guest (since QEMU virtio-net Windows driver doesn't support GRO).
>> >> > The fix has been verified by running the HCK OffloadLSO test.
>> >> >
>> >> > Signed-off-by: Igor Royzis <igorr@...rtex.com>
>> >> > Signed-off-by: Anton Nayshtut <anton@...rtex.com>
>> >>
>> >> OK but with 1fd819ec there's no corruption, correct?
>> >> So this patch is in fact an optimization?
>> >> If true, I'd like to see some performance numbers please.
>> >>
>> >> Thanks!
>> >>
>> >> > ---
>> >> > include/linux/skbuff.h | 1 +
>> >> > net/core/skbuff.c | 18 +++++++++++++-----
>> >> > 2 files changed, 14 insertions(+), 5 deletions(-)
>> >> >
>> >> > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
>> >> > index 08074a8..8c49edc 100644
>> >> > --- a/include/linux/skbuff.h
>> >> > +++ b/include/linux/skbuff.h
>> >> > @@ -287,6 +287,7 @@ struct skb_shared_info {
>> >> > struct sk_buff *frag_list;
>> >> > struct skb_shared_hwtstamps hwtstamps;
>> >> > __be32 ip6_frag_id;
>> >> > + struct sk_buff *zcopy_src;
>> >> >
>> >> > /*
>> >> > * Warning : all fields before dataref are cleared in __alloc_skb()
>> >> > diff --git a/net/core/skbuff.c b/net/core/skbuff.c
>> >> > index 1b62343..6fa6342 100644
>> >> > --- a/net/core/skbuff.c
>> >> > +++ b/net/core/skbuff.c
>> >> > @@ -610,14 +610,18 @@ EXPORT_SYMBOL(__kfree_skb);
>> >> > */
>> >> > void kfree_skb(struct sk_buff *skb)
>> >> > {
>> >> > + struct sk_buff *zcopy_src;
>> >> > if (unlikely(!skb))
>> >> > return;
>> >> > if (likely(atomic_read(&skb->users) == 1))
>> >> > smp_rmb();
>> >> > else if (likely(!atomic_dec_and_test(&skb->users)))
>> >> > return;
>> >> > + zcopy_src = skb_shinfo(skb)->zcopy_src;
>> >> > trace_kfree_skb(skb, __builtin_return_address(0));
>> >> > __kfree_skb(skb);
>> >> > + if (unlikely(zcopy_src))
>> >> > + kfree_skb(zcopy_src);
>> >> > }
>> >> > EXPORT_SYMBOL(kfree_skb);
>> >> >
>> >> > @@ -662,14 +666,18 @@ EXPORT_SYMBOL(skb_tx_error);
>> >> > */
>> >> > void consume_skb(struct sk_buff *skb)
>> >> > {
>> >> > + struct sk_buff *zcopy_src;
>> >> > if (unlikely(!skb))
>> >> > return;
>> >> > if (likely(atomic_read(&skb->users) == 1))
>> >> > smp_rmb();
>> >> > else if (likely(!atomic_dec_and_test(&skb->users)))
>> >> > return;
>> >> > + zcopy_src = skb_shinfo(skb)->zcopy_src;
>> >> > trace_consume_skb(skb);
>> >> > __kfree_skb(skb);
>> >> > + if (unlikely(zcopy_src))
>> >> > + consume_skb(zcopy_src);
>> >> > }
>> >> > EXPORT_SYMBOL(consume_skb);
>> >> >
>> >> > @@ -2867,7 +2875,6 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
>> >> > skb_frag_t *frag = skb_shinfo(head_skb)->frags;
>> >> > unsigned int mss = skb_shinfo(head_skb)->gso_size;
>> >> > unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
>> >> > - struct sk_buff *frag_skb = head_skb;
>> >> > unsigned int offset = doffset;
>> >> > unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
>> >> > unsigned int headroom;
>> >> > @@ -2913,7 +2920,6 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
>> >> > i = 0;
>> >> > nfrags = skb_shinfo(list_skb)->nr_frags;
>> >> > frag = skb_shinfo(list_skb)->frags;
>> >> > - frag_skb = list_skb;
>> >> > pos += skb_headlen(list_skb);
>> >> >
>> >> > while (pos < offset + len) {
>> >> > @@ -2975,6 +2981,11 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
>> >> > nskb->data - tnl_hlen,
>> >> > doffset + tnl_hlen);
>> >> >
>> >> > + if (skb_shinfo(head_skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
>> >> > + skb_shinfo(nskb)->zcopy_src = head_skb;
>> >> > + atomic_inc(&head_skb->users);
>> >> > + }
>> >> > +
>> >> > if (nskb->len == len + doffset)
>> >> > goto perform_csum_check;
>> >> >
>> >> > @@ -3001,7 +3012,6 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
>> >> > i = 0;
>> >> > nfrags = skb_shinfo(list_skb)->nr_frags;
>> >> > frag = skb_shinfo(list_skb)->frags;
>> >> > - frag_skb = list_skb;
>> >> >
>> >> > BUG_ON(!nfrags);
>> >> >
>> >> > @@ -3016,8 +3026,6 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
>> >> > goto err;
>> >> > }
>> >> >
>> >> > - if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
>> >> > - goto err;
>> >> >
>> >> > *nskb_frag = *frag;
>> >> > __skb_frag_ref(nskb_frag);
>> >> > --
>> >> > 1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists