.
Referring to the Linux kernel implementation, packets with PUSH
flag can also perform GRO. And if one of the packets containing
PUSH flag, the packets after GRO will carry PUSH flag.
Fixes: 0d2cbe59b719 ("lib/gro: support TCP/IPv4")
Cc: sta...@dpdk.org
Signed-off-b
control flag is provided
for marking that TCP packets carrying PSH flags can be merged.
Fixes: 0d2cbe59b719 ("lib/gro: support TCP/IPv4")
Cc: sta...@dpdk.org
Signed-off-by: Jun Qiu
---
lib/gro/gro_tcp4.c | 15 ++-
lib/gro/gro_tcp4.h | 21 +---
ation with lro_psh_flag set by default.
-Original Message-
From: Hu, Jiayu
Sent: Monday, September 5, 2022 12:03 PM
To: Thomas Monjalon
Cc: kumaraparameshwaran rathinavel ; dev@dpdk.org;
Jun Qiu
Subject: RE: [PATCH] gro: fix gro with tcp push flag
Hi Qiu,
I cannot find the original mail
dev@dpdk.org; David Marchand ; Hu, Jiayu
; Jun Qiu
Subject: Fwd: [PATCH] gro : fix pkt length when extra bytes are padded to
ethernet frame
On Tue, Oct 11, 2022 at 1:03 AM David Marchand
mailto:david.march...@redhat.com>> wrote:
On Mon, Oct 10, 2022 at 7:51 PM Kumara Parameshwaran
m
The memory of h->hash_rcu_cfg which allocated in
rte_hash_rcu_qsbr_add was leaked.
Signed-off-by: Jun Qiu
---
lib/hash/rte_cuckoo_hash.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/hash/rte_cuckoo_hash.c b/lib/hash/rte_cuckoo_hash.c
index 62c762439a..829b79c89a 100644
--- a/lib/h
The memory of h->hash_rcu_cfg which is allocated in
rte_hash_rcu_qsbr_add was leaked.
Fixes: 769b2de ("hash: implement RCU resources reclamation")
Cc: sta...@dpdk.org
Signed-off-by: Jun Qiu
---
lib/hash/rte_cuckoo_hash.c | 1 +
1 file changed, 1 insertion(+)
diff --g
: Tue, 26 Jul 2022 10:02:10 +0800
From: "humin (Q)"
To: Jun Qiu ,
Cc: , ,
Subject: Re: [PATCH] net/bonding: fix xmit l34 hash calculate for tcp
Message-ID:
Content-Type: text/plain; charset="UTF-8"; format=flowed
Acked-by: Min Hu (Connor)
? 2022/7/26 8:48, Jun Qiu ??:
>
, packets with PUSH
flag can also perform GRO. And if one of the packets containing
PUSH flag, the packets after GRO will carry PUSH flag.
Fixes: 0d2cbe59b719 ("lib/gro: support TCP/IPv4")
Cc: sta...@dpdk.org
Signed-off-by: Jun Qiu
---
lib/gro/gro_tcp4.c | 4 ++--
lib/gro/
.
Fixes: 726158060d55 ("net/bonding: fix potential out of bounds read")
Cc: sta...@dpdk.org
Signed-off-by: Jun Qiu
---
drivers/net/bonding/rte_eth_bond_pmd.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/bonding/rte_eth_bond_pmd.c
b/drivers/n
May be in rte_gro_reassemble_burst, where no delay is introduced, PUSH packets
can be merged
发件人: kumaraparameshwaran rathinavel
发送时间: 2022年7月26日 14:41
收件人: Jun Qiu
抄送: dev@dpdk.org; jiayu...@intel.com; sta...@dpdk.org
主题: Re: [PATCH] gro: fix gro with tcp push flag
On Tue, Jul 26, 2022 at
of thinking
of the padding field as the actual content of the packet.
We need to trim away this extra padding field during
GRO processing.
Fixes: 0d2cbe59b719 ("lib/gro: support TCP/IPv4")
Cc: sta...@dpdk.org
Signed-off-by: Jun Qiu
---
lib/gro/gro_tcp4.c | 7 ++-
lib/gro/gro_udp4.
rathinavel
Sent: Tuesday, July 26, 2022 3:08 PM
To: Jun Qiu
Cc: dev@dpdk.org; jiayu...@intel.com; sta...@dpdk.org
Subject: Re: [PATCH] gro: fix gro with tcp push flag
We should do it for the rte_gro_reassemble as well, with timer mode it could
lead to more duplicate ACKs. I had a proposal for
into the stack.
If you trim padding in merge_two_tcp4_packets(), then both "pkt_head" and
"pkt_tail" need to decide whether to trim or not, which can be a bit tricky to
handle.
-Original Message-
From: Hu, Jiayu
Sent: Thursday, July 28, 2022 9:56 AM
To: Jun Q
13 matches
Mail list logo
