thout the extra overhead of skb_cow_data.
This patch reduces memcpy by 50% on my encrypted NBD benchmarks.
Reported-by: Vakul Garg
Reviewed-by: Vakul Garg
Tested-by: Vakul Garg
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 80 +++-
1
On Sat, Aug 11, 2018 at 11:54:53AM -0700, David Miller wrote:
> From: Doron Roberts-Kedes
> Date: Thu, 9 Aug 2018 15:43:44 -0700
>
> The reason is that we usually never need to "map" an SKB on receive,
> and on transmit the SKB geometry is normalized by the destinatio
On Wed, Aug 08, 2018 at 12:14:30PM -0700, David Miller wrote:
> From: Doron Roberts-Kedes
> Date: Tue, 7 Aug 2018 11:09:39 -0700
>
> > +static int __skb_nsg(struct sk_buff *skb, int offset, int len,
> > +unsigned int recursion_level)
> > +{
> >
thout the extra overhead of skb_cow_data. This
function mimics the structure of skb_to_sgvec.
Reported-by: Vakul Garg
Reviewed-by: Vakul Garg
Tested-by: Vakul Garg
Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Doron Roberts-Kedes
---
net/tl
On Tue, Aug 07, 2018 at 04:10:50PM +, Vakul Garg wrote:
>
>
> > -Original Message-
> > From: Doron Roberts-Kedes [mailto:doro...@fb.com]
> > Sent: Tuesday, August 7, 2018 1:18 AM
> > To: David S . Miller
> > Cc: Vakul Garg ; Dave Watson
>
ed to map the skb without the extra overhead of skb_cow_data. This
function mimics the structure of skb_to_sgvec.
Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 96 ++--
1 file changed
ed to map the skb without the extra overhead of skb_cow_data. This
function mimics the structure of skb_to_sgvec.
Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 93 ++--
1 file changed
On Fri, Aug 03, 2018 at 11:49:02AM -0700, Doron Roberts-Kedes wrote:
> On Fri, Aug 03, 2018 at 01:23:33AM +, Vakul Garg wrote:
> >
> >
> > > -Original Message-
> > > From: Doron Roberts-Kedes [mailto:doro...@fb.com]
> > > Sent: Friday
On Fri, Aug 03, 2018 at 01:23:33AM +, Vakul Garg wrote:
>
>
> > -Original Message-
> > From: Doron Roberts-Kedes [mailto:doro...@fb.com]
> > Sent: Friday, August 3, 2018 6:00 AM
> > To: David S . Miller
> > Cc: Dave Watson ; Vakul Garg
>
ed to map the skb without the extra overhead of skb_cow_data. This
function mimics the structure of skb_to_sgvec.
Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 89 ++--
1 file changed
On Thu, Aug 02, 2018 at 09:50:58AM -0700, Dave Watson wrote:
> On 08/02/18 09:50 PM, Vakul Garg wrote:
> > Function decrypt_skb() made a bad assumption that number of sg entries
> > required for mapping skb to be decrypted would always be less than
> > MAX_SKB_FRAGS. The required count of sg entrie
tls_push_record either returns 0 on success or a negative value on failure.
This patch removes code that would only be executed if tls_push_record
were to return a positive value.
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 6 ++
1 file changed, 2 insertions(+), 4 deletions
amount by which the iter was actually advanced.
Instead, only revert by the amount that the iter was advanced.
Fixes: 4718799817c5 ("tls: Fix zerocopy_from_iter iov handling")
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 12 +---
1 file changed, 5 insertions(+), 7
This series fixes the improper iov_iter_revert introcded in
"tls: Fix zerocopy_from_iter iov handling".
Changes from v1:
- call iov_iter_revert inside zerocopy_from_iter
Doron Roberts-Kedes (2):
tls: Remove dead code in tls_sw_sendmsg
tls: Fix improper revert in zerocopy_from_
discussion of why zerocopy for vmalloc data is not a good idea.
Discovered while testing NBD traffic encrypted with ktls.
Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
di
On Tue, Jul 24, 2018 at 05:13:26AM +, Vakul Garg wrote:
>
> > -Original Message-
> > From: Doron Roberts-Kedes [mailto:doro...@fb.com]
> > Sent: Tuesday, July 24, 2018 3:50 AM
> > @@ -811,6 +809,7 @@ int tls_sw_recvmsg(struct sock *sk,
> >
amount by which the iter was actually advanced.
Instead, mimic the tx path which reverts by the difference before and
after zerocopy_from_iter.
Fixes: 4718799817c5 ("tls: Fix zerocopy_from_iter iov handling")
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 13 +++
discussion of why zerocopy for vmalloc data is not a good idea.
Discovered while testing NBD traffic encrypted with ktls.
Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
di
hecking sk->sk_shutdown & RCV_SHUTDOWN, as in tcp_recvmsg,
fixes this problem.
Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Acked-by: Dave Watson
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/tls/tls_sw
t;tls: RX path for ktls")
Acked-by: Dave Watson
Signed-off-by: Doron Roberts-Kedes
---
net/tls/tls_sw.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 173d8b89072d..b6e118499083 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -701
TCP window to go to
zero, so the remainder of the message will never arrive.
Incrementing the value returned by __strp_recv by the amount otherwise
stored in early_eaten prevents stalls of this nature.
Signed-off-by: Doron Roberts-Kedes
---
net/strparser/strparser.c | 17 +
1
overhead that results when a receiving thread unpauses the strparser
and waits for the next message to be delivered by the workqueue thread.
This patch more than doubled the IOPS achieved in a benchmark of NBD
traffic encrypted using ktls.
Signed-off-by: Doron Roberts-Kedes
---
include/net
parser for messages")
Reviewed-by: Tejun Heo
Signed-off-by: Doron Roberts-Kedes
---
net/strparser/strparser.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 805b139..092bebc 100644
--- a/net/strparser/strpars
en there is sufficient data to
complete the partial message. Incrementing stm->accum_len before using
it to calculate strp->need_bytes solves this problem.
Found while testing net/tls_sw recv path.
Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Signed-off-
24 matches
Mail list logo
