summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
5 dayssmb: server: pass struct smbdirect_socket to smb_direct_qpair_handler()Stefan Metzmacher1-5/+4
This will make it easier to move function to the common code in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: pass struct smbdirect_socket to smb_direct_cm_handler()Stefan Metzmacher1-3/+2
This will make it easier to move function to the common code in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: pass struct smbdirect_socket to ↵Stefan Metzmacher1-19/+13
smb_direct_disconnect_rdma_connection() This will make it easier to move function to the common code in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: pass struct smbdirect_socket to smb_direct_init_params()Stefan Metzmacher1-3/+2
This will make it easier to move function to the common code in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: pass struct smbdirect_socket to smb_direct_get_max_fr_pages()Stefan Metzmacher1-4/+2
This will make it easier to move function to the common code in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: pass struct smbdirect_socket to smb_direct_{create,destroy}_pools()Stefan Metzmacher1-10/+9
This will make it easier to move function to the common code in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: pass struct smbdirect_socket to {get_free,put}_recvmsg()Stefan Metzmacher1-20/+17
This will make it easier to move function to the common code in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.workqueueStefan Metzmacher1-10/+12
We still use the single global workqueue, but this will allow us to share common code soon. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: implement correct keepalive and timeout handling for smbdirectStefan Metzmacher1-0/+74
Now client and server behave in the same way and we can start to share common functions. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.idle.immediate_workStefan Metzmacher1-12/+9
With this commit the server only uses struct smbdirect_socket! It doesn't use the idle timer yet, but it will be added soon, from there we'll be ready split common functions. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.rdma.legacy_iwarpStefan Metzmacher1-4/+2
Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of ↵Stefan Metzmacher1-12/+14
smbdirect_socket_parameters.{initiator_depth,responder_resources} This will make it easier to specify these from the outside of the core code first and then negotiate the value with the peer. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket_parameters.negotiate_timeout_msec ↵Stefan Metzmacher1-3/+4
and change to 5s The server negotiations timer is just 5 seconds in Windows, so use the same. See [MS-SMBD] 3.1.7.2 Connection Arrival. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: fill smbdirect_socket_parameters at the beginning and use the ↵Stefan Metzmacher1-14/+15
values from there This is what we should do and it also simplifies the following changes. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: pass ksmbd_transport to get_smbd_max_read_write_size()Stefan Metzmacher3-6/+25
We should use the per connection value. And for TCP return NT_STATUS_INVALID_PARAMETER if any SMB2_CHANNEL_RDMA_V1* is used. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: remove useless casts from KSMBD_TRANS/SMBD_TRANSStefan Metzmacher1-2/+2
At best they gain nothing, at worst we procude real bugs. Note container_of() already casts to a pointer of the given type. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: replace smb_trans_direct_transfort() with SMBD_TRANS()Stefan Metzmacher1-13/+7
The spelling of smb_trans_direct_transfort was wrong anyway and we don't need the logic twice. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.recv_io.{posted,credits}Stefan Metzmacher1-35/+30
This will make it possible to introduce common helper functions in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: manage recv credits by counting posted recv_io and granted creditsStefan Metzmacher1-32/+21
(At least for me) the logic maintaining the count of posted recv_io messages and the count of granted credits is much easier to understand. From there we can easily calculate the number of new_credits we'll grant to the peer in outgoing send_io messages. This will simplify the move to common logic that can be shared between client and server in the following patches. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: take the recv_credit_target from the negotiate req and always ↵Stefan Metzmacher1-3/+10
limit the range The clients sends the initial recv_credit_target in the negotiate req, so we should use that. We also limit the range between 1 and our local defined sp->recv_credit_max. This will simplify further logic changes. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of struct smbdirect_rw_ioStefan Metzmacher1-23/+14
This will allow us to create functions in the common smbdirect code to be used by the server in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use smbdirect_socket.rw_io.creditsStefan Metzmacher1-22/+22
This will allow to us to have functions moved into common code in future (even if it's only used by the server). Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of struct smbdirect_send_batchStefan Metzmacher1-14/+7
This makes it easier to move functions to the common smbdirect code in future. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.send_io.credits.{count,wait_queue}Stefan Metzmacher1-15/+13
This will is used by the client already and will allow to create common helper functions. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of ↵Stefan Metzmacher1-16/+10
smbdirect_socket.send_io.pending.{count,zero_wait_queue} This will is used by the client already and will allow to create common helper functions. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.disconnect_workStefan Metzmacher1-10/+12
Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket_init()Stefan Metzmacher1-11/+1
Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: don't wait for info->send_pending == 0 on errorStefan Metzmacher1-6/+11
Instead we just wake up the waiters and let them return -ENOTCONN. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: move smb_direct_disconnect_rdma_work() into free_transport()Stefan Metzmacher1-4/+7
The logic is also needed when smb_direct_handle_connect_request() calls free_transport(), because rdma_accept() and RDMA_CM_EVENT_ESTABLISHED could already be reached. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: only turn into SMBDIRECT_SOCKET_CONNECTED when negotiation is doneStefan Metzmacher1-15/+69
From SMBDIRECT_SOCKET_CREATED we now go via the following stages: 1. SMBDIRECT_SOCKET_RDMA_CONNECT_NEEDED This indicated rdma_accept needs to be called 2. SMBDIRECT_SOCKET_RDMA_CONNECT_RUNNING This waits for RDMA_CM_EVENT_ESTABLISHED to arrive 3. SMBDIRECT_SOCKET_NEGOTIATE_NEEDED This waits for the negotiate request to arrive 4. SMBDIRECT_SOCKET_NEGOTIATE_RUNNING This indicates the negotiate request arrived and needs to be processed 5. SMBDIRECT_SOCKET_CONNECTED The connection is ready to use This avoids the extra 'bool negotiation_requested' and makes the steps more clear. In future we may want to add trace points when changing the states, which would be useful for debugging. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.status_waitStefan Metzmacher1-9/+7
This will allow us to have common helper functions soon. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: queue post_recv_credits_work in put_recvmsg() and avoid ↵Stefan Metzmacher1-34/+11
count_avail_recvmsg This is basically what the client is doing in put_receive_buffer(). It means we don't need complicated work to maintain count_avail_recvmsg. But we keep the logic to queue post_recv_credits_work if the peer raises the requested credit_target and put_receive_buffer() is not called. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: add a pr_info() when the server starts runningStefan Metzmacher1-0/+1
We already have a message like: ksmbd: kill command received when the server stops running. This makes it easier for debugging in order to match any possible warnings/errors in dmesg with restarted server. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make only use of wake_up[_all]() in transport_rdma.cStefan Metzmacher1-9/+9
wake_up_interruptible(() doesn't wake up tasks waiting with wait_event(). So we better wake_up[_all]() in order to wake up all tasks in order to simplify the logic. As we currently don't use any wait_event_*_exclusive() it doesn't really matter if we use wake_up() or wake_up_all(). But in this patch I try to use wake_up() for expected situations and wake_up_all() for situations of a broken connection. So don't need to adjust things in future when we may use wait_event_*_exclusive() in order to wake up only one process that should make progress. Changing the wait_event_*() code in order to keep wait_event(), wait_event_interruptible() and wait_event_interruptible_timeout() or changing them to wait_event_killable(), wait_event_killable_timeout(), wait_event_killable_exclusive() is something to think about in a future patch. The goal here is to avoid that some tasks are not woken and freeze forever. Also note that this patch only changes the existing wake_up*() calls. Adding more wake_up*() calls for other wait queues is also deferred to a future patch. Link: https://lore.kernel.org/linux-cifs/13851363-0dc9-465c-9ced-3ede4904eef0@samba.org/T/#t Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.{send,recv}_io.mem.{cache,pool}Stefan Metzmacher1-27/+23
This will allow common helper functions to be created later. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of struct smbdirect_send_ioStefan Metzmacher1-48/+39
This is already used by the client and will allow us to use common helper functions soon. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of SMBDIRECT_RECV_IO_MAX_SGEStefan Metzmacher1-3/+2
Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.recv_io.reassembly.*Stefan Metzmacher1-47/+43
This is also used by the client and will allow us to introduce common helper functions soon. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket.recv_io.free.{list,lock}Stefan Metzmacher1-15/+12
This is already used by the client and will allow us to add common helper functions soon. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of struct smbdirect_recv_ioStefan Metzmacher1-35/+26
This will allow us to move helper functions into common code soon as the client already uses smbdirect_recv_io. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of smbdirect_socket->recv_io.expectedStefan Metzmacher1-19/+25
The expected incoming message type can be per connection. Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of common smbdirect_socket_parametersStefan Metzmacher1-44/+49
Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: Long Li <longli@microsoft.com> Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Hyunchul Lee <hyc.lee@gmail.com> Cc: Meetakshi Setiya <meetakshisetiyaoss@gmail.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of common smbdirect_socketStefan Metzmacher1-108/+133
This is the next step in the direction of a common smbdirect layer. Currently only structures are shared, but that will change over time until everything is shared. Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: Long Li <longli@microsoft.com> Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Hyunchul Lee <hyc.lee@gmail.com> Cc: Meetakshi Setiya <meetakshisetiyaoss@gmail.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of common smbdirect.hStefan Metzmacher5-20/+18
Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: Long Li <longli@microsoft.com> Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Hyunchul Lee <hyc.lee@gmail.com> Cc: Meetakshi Setiya <meetakshisetiyaoss@gmail.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: make use of common smbdirect_pdu.hStefan Metzmacher2-64/+24
Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: Long Li <longli@microsoft.com> Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Hyunchul Lee <hyc.lee@gmail.com> Cc: Meetakshi Setiya <meetakshisetiyaoss@gmail.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: server: fix IRD/ORD negotiation with the clientStefan Metzmacher1-14/+85
Already do real negotiation in smb_direct_handle_connect_request() where we see the requested initiator_depth and responder_resources from the client. We should detect legacy iwarp clients using MPA v1 with the custom IRD/ORD negotiation. We need to send the custom IRD/ORD in big endian, but we need to try to let clients with broken requests using little endian (older cifs.ko) to work. Note the reason why this uses u8 for initiator_depth and responder_resources is that the rdma layer also uses it. Acked-by: Namjae Jeon <linkinjeon@kernel.org> Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: linux-rdma@vger.kernel.org Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers") Signed-off-by: Stefan Metzmacher <metze@samba.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: client: let smbd_post_send_iter() call ib_dma_map_single() for the ↵Stefan Metzmacher1-22/+21
header first This will simplify further changes, the important part is that request->num_sge >= 1 is only set if request->sge[0].* is valid. Note that ib_dma_sync_single_for_device() is called in smbd_post_send() for each sge, so the device will still see the packet header even if it's modified after calling ib_dma_map_single(). Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: Long Li <longli@microsoft.com> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: client: defer calling ib_alloc_pd() after we are connectedStefan Metzmacher1-8/+11
The protection domain is not needed until we're connected. This makes further changes easier to follow... Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: Long Li <longli@microsoft.com> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: client: allocate smbdirect workqueue at the beginning of ↵Stefan Metzmacher1-13/+14
_smbd_get_connection() This will simplify further changes when moving to common code. Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: Long Li <longli@microsoft.com> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Signed-off-by: Steve French <stfrench@microsoft.com>
5 dayssmb: client: make consitent use of spin_lock_irq{save,restore}() in smbdirect.cStefan Metzmacher1-11/+15
There is a mix of using spin_lock(), spin_lock_irq() and spin_lock_irqsave() and it seems at least enqueue_reassembly() was wrong in using just spin_lock() as it's called via recv_done() from a SOFTIRQ as we're using IB_POLL_SOFTIRQ. And Documentation/kernel-hacking/locking.rst section "Cheat Sheet For Locking" says: - Otherwise (== data can be touched in an interrupt), use spin_lock_irqsave() and spin_unlock_irqrestore(). So in order to keep it simple and safe we use that version now. It will help merging functions into common code and have consistent locking in all cases. Cc: Steve French <smfrench@gmail.com> Cc: Tom Talpey <tom@talpey.com> Cc: Long Li <longli@microsoft.com> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Stefan Metzmacher <metze@samba.org> Signed-off-by: Steve French <stfrench@microsoft.com>
generated by cgit v1.2.3 (git 2.39.0) at 2025-10-03 21:07:16 +0300