Re: [PATCH 4.18 093/150] rds: RDS (tcp) hangs on sendto() to unresponding address

2018-11-04 Thread Ka-Cheong Poon
-by: Ka-Cheong Poon Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/rds/send.c | 13 ++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/net/rds/send.c b/net/rds/send.c index 59f17a2335f4..0e54ca0f4e9e 100644 --- a/net/rds

Re: [PATCH 4.18 093/150] rds: RDS (tcp) hangs on sendto() to unresponding address

2018-11-04 Thread Ka-Cheong Poon
-by: Ka-Cheong Poon Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/rds/send.c | 13 ++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/net/rds/send.c b/net/rds/send.c index 59f17a2335f4..0e54ca0f4e9e 100644 --- a/net/rds

Re: [PATCH] net/rds/Kconfig: RDS should depend on IPV6

2018-07-25 Thread Ka-Cheong Poon
On 07/26/2018 06:36 AM, Santosh Shilimkar wrote: On 7/25/2018 3:20 PM, Anders Roxell wrote: Build error, implicit declaration of function __inet6_ehashfn shows up When RDS is enabled but not IPV6. net/rds/connection.c: In function ‘rds_conn_bucket’: net/rds/connection.c:67:9: error: implicit

Re: [PATCH] net/rds/Kconfig: RDS should depend on IPV6

2018-07-25 Thread Ka-Cheong Poon
On 07/26/2018 06:36 AM, Santosh Shilimkar wrote: On 7/25/2018 3:20 PM, Anders Roxell wrote: Build error, implicit declaration of function __inet6_ehashfn shows up When RDS is enabled but not IPV6. net/rds/connection.c: In function ‘rds_conn_bucket’: net/rds/connection.c:67:9: error: implicit

Re: [PATCH v2 net-next 1/2] tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive

2018-04-26 Thread Ka-Cheong Poon
On 04/26/2018 05:43 AM, Eric Dumazet wrote: When adding tcp mmap() implementation, I forgot that socket lock had to be taken before current->mm->mmap_sem. syzbot eventually caught the bug. Since we can not lock the socket in tcp mmap() handler we have to split the operation in two phases. 1)

Re: [PATCH v2 net-next 1/2] tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive

2018-04-26 Thread Ka-Cheong Poon
On 04/26/2018 05:43 AM, Eric Dumazet wrote: When adding tcp mmap() implementation, I forgot that socket lock had to be taken before current->mm->mmap_sem. syzbot eventually caught the bug. Since we can not lock the socket in tcp mmap() handler we have to split the operation in two phases. 1)