* [PATCH 2/3] iscsi-target: Propigate queue_data_in + queue_status errors
From: Nicholas A. Bellinger @ 2016-10-31 5:25 UTC (permalink / raw)
To: target-devel
Cc: linux-rdma, Potnuri Bharat Teja, Steve Wise, Sagi Grimberg,
Nicholas Bellinger
In-Reply-To: <1477891554-26222-1-git-send-email-nab@linux-iscsi.org>
From: Nicholas Bellinger <nab@linux-iscsi.org>
This patch changes iscsi-target to propagate iscsit_transport
->iscsit_queue_data_in() and ->iscsit_queue_status() callback
errors, back up into target-core.
This allows target-core to retry failed iscsit_transport
callbacks using internal queue-full logic.
Reported-by: Potnuri Bharat Teja <bharat@chelsio.com>
Cc: Potnuri Bharat Teja <bharat@chelsio.com>
Reported-by: Steve Wise <swise@opengridcomputing.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
drivers/target/iscsi/iscsi_target.c | 3 +--
drivers/target/iscsi/iscsi_target_configfs.c | 13 +++++--------
drivers/target/iscsi/iscsi_target_util.c | 5 +++--
drivers/target/iscsi/iscsi_target_util.h | 2 +-
4 files changed, 10 insertions(+), 13 deletions(-)
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index b7d747e..1b03e85 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -482,8 +482,7 @@ int iscsit_del_np(struct iscsi_np *np)
int iscsit_queue_rsp(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
{
- iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
- return 0;
+ return iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
}
EXPORT_SYMBOL(iscsit_queue_rsp);
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 923c032..38a72d3 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -1395,11 +1395,10 @@ static u32 lio_sess_get_initiator_sid(
static int lio_queue_data_in(struct se_cmd *se_cmd)
{
struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
+ struct iscsi_conn *conn = cmd->conn;
cmd->i_state = ISTATE_SEND_DATAIN;
- cmd->conn->conn_transport->iscsit_queue_data_in(cmd->conn, cmd);
-
- return 0;
+ return conn->conn_transport->iscsit_queue_data_in(conn, cmd);
}
static int lio_write_pending(struct se_cmd *se_cmd)
@@ -1428,16 +1427,14 @@ static int lio_write_pending_status(struct se_cmd *se_cmd)
static int lio_queue_status(struct se_cmd *se_cmd)
{
struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
+ struct iscsi_conn *conn = cmd->conn;
cmd->i_state = ISTATE_SEND_STATUS;
if (cmd->se_cmd.scsi_status || cmd->sense_reason) {
- iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
- return 0;
+ return iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state);
}
- cmd->conn->conn_transport->iscsit_queue_status(cmd->conn, cmd);
-
- return 0;
+ return conn->conn_transport->iscsit_queue_status(conn, cmd);
}
static void lio_queue_tm_rsp(struct se_cmd *se_cmd)
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 1f38177..eb9c49a 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -565,7 +565,7 @@ static void iscsit_remove_cmd_from_immediate_queue(
}
}
-void iscsit_add_cmd_to_response_queue(
+int iscsit_add_cmd_to_response_queue(
struct iscsi_cmd *cmd,
struct iscsi_conn *conn,
u8 state)
@@ -576,7 +576,7 @@ void iscsit_add_cmd_to_response_queue(
if (!qr) {
pr_err("Unable to allocate memory for"
" struct iscsi_queue_req\n");
- return;
+ return -ENOMEM;
}
INIT_LIST_HEAD(&qr->qr_list);
qr->cmd = cmd;
@@ -588,6 +588,7 @@ void iscsit_add_cmd_to_response_queue(
spin_unlock_bh(&conn->response_queue_lock);
wake_up(&conn->queues_wq);
+ return 0;
}
struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *conn)
diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h
index 995f1cb..d96ec7d 100644
--- a/drivers/target/iscsi/iscsi_target_util.h
+++ b/drivers/target/iscsi/iscsi_target_util.h
@@ -23,7 +23,7 @@ extern int iscsit_find_cmd_for_recovery(struct iscsi_session *, struct iscsi_cmd
struct iscsi_conn_recovery **, itt_t);
extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
extern struct iscsi_queue_req *iscsit_get_cmd_from_immediate_queue(struct iscsi_conn *);
-extern void iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
+extern int iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
extern struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *);
extern void iscsit_remove_cmd_from_tx_queues(struct iscsi_cmd *, struct iscsi_conn *);
extern bool iscsit_conn_all_queues_empty(struct iscsi_conn *);
--
1.9.1
^ permalink raw reply related
* [PATCH 1/3] target: Fix unknown fabric callback queue-full errors
From: Nicholas A. Bellinger @ 2016-10-31 5:25 UTC (permalink / raw)
To: target-devel
Cc: linux-rdma, Potnuri Bharat Teja, Steve Wise, Sagi Grimberg,
Nicholas Bellinger
In-Reply-To: <1477891554-26222-1-git-send-email-nab@linux-iscsi.org>
From: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a set of queue-full response handling
bugs, where outgoing responses are leaked when a fabric
driver is propagating non -EAGAIN or -ENOMEM errors
to target-core.
It introduces TRANSPORT_COMPLETE_QF_ERR state used to
signal when CHECK_CONDITION status should be generated,
when fabric driver ->write_pending(), ->queue_data_in(),
or ->queue_status() callbacks fail with non -EAGAIN or
-ENOMEM errors, and data-transfer should not be retried.
Note all fabric driver -EAGAIN and -ENOMEM errors are
still retried indefinately with associated data-transfer
callbacks, following existing queue-full logic.
Also fix two missing ->queue_status() queue-full cases
related to CMD_T_ABORTED w/ TAS status handling.
Reported-by: Potnuri Bharat Teja <bharat@chelsio.com>
Cc: Potnuri Bharat Teja <bharat@chelsio.com>
Reported-by: Steve Wise <swise@opengridcomputing.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
drivers/target/target_core_transport.c | 102 ++++++++++++++++++++++-----------
include/target/target_core_base.h | 1 +
2 files changed, 69 insertions(+), 34 deletions(-)
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 7dfefd6..489aa95 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -64,8 +64,9 @@
struct kmem_cache *t10_alua_lba_map_mem_cache;
static void transport_complete_task_attr(struct se_cmd *cmd);
+static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason);
static void transport_handle_queue_full(struct se_cmd *cmd,
- struct se_device *dev);
+ struct se_device *dev, int err, bool write_pending);
static int transport_put_cmd(struct se_cmd *cmd);
static void target_complete_ok_work(struct work_struct *work);
@@ -811,7 +812,8 @@ void target_qf_do_work(struct work_struct *work)
if (cmd->t_state == TRANSPORT_COMPLETE_QF_WP)
transport_write_pending_qf(cmd);
- else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK)
+ else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK ||
+ cmd->t_state == TRANSPORT_COMPLETE_QF_ERR)
transport_complete_qf(cmd);
}
}
@@ -1720,7 +1722,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
}
trace_target_cmd_complete(cmd);
ret = cmd->se_tfo->queue_status(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
goto check_stop;
default:
@@ -1731,7 +1733,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
}
ret = transport_send_check_condition_and_sense(cmd, sense_reason, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
check_stop:
@@ -1740,8 +1742,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
return;
queue_full:
- cmd->t_state = TRANSPORT_COMPLETE_QF_OK;
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
}
EXPORT_SYMBOL(transport_generic_request_failure);
@@ -1980,13 +1981,29 @@ static void transport_complete_qf(struct se_cmd *cmd)
int ret = 0;
transport_complete_task_attr(cmd);
+ /*
+ * If a fabric driver ->write_pending() or ->queue_data_in() callback
+ * has returned neither -ENOMEM or -EAGAIN, assume it's fatal and
+ * the same callbacks should not be retried. Return CHECK_CONDITION
+ * if a scsi_status is not already set.
+ *
+ * If a fabric driver ->queue_status() has returned non zero, always
+ * keep retrying no matter what..
+ */
+ if (cmd->t_state == TRANSPORT_COMPLETE_QF_ERR) {
+ if (cmd->scsi_status)
+ goto queue_status;
- if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) {
- trace_target_cmd_complete(cmd);
- ret = cmd->se_tfo->queue_status(cmd);
- goto out;
+ cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
+ cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+ cmd->scsi_sense_length = TRANSPORT_SENSE_BUFFER;
+ translate_sense_reason(cmd, TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE);
+ goto queue_status;
}
+ if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE)
+ goto queue_status;
+
switch (cmd->data_direction) {
case DMA_FROM_DEVICE:
if (cmd->scsi_status)
@@ -2010,19 +2027,33 @@ static void transport_complete_qf(struct se_cmd *cmd)
break;
}
-out:
if (ret < 0) {
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
return;
}
transport_lun_remove_cmd(cmd);
transport_cmd_check_stop_to_fabric(cmd);
}
-static void transport_handle_queue_full(
- struct se_cmd *cmd,
- struct se_device *dev)
+static void transport_handle_queue_full(struct se_cmd *cmd, struct se_device *dev,
+ int err, bool write_pending)
{
+ /*
+ * -EAGAIN or -ENOMEM signals retry of ->write_pending() and/or
+ * ->queue_data_in() callbacks from new process context.
+ *
+ * Otherwise for other errors, transport_complete_qf() will send
+ * CHECK_CONDITION via ->queue_status() instead of attempting to
+ * retry associated fabric driver data-transfer callbacks.
+ */
+ if (err == -EAGAIN || err == -ENOMEM) {
+ cmd->t_state = (write_pending) ? TRANSPORT_COMPLETE_QF_WP :
+ TRANSPORT_COMPLETE_QF_OK;
+ } else {
+ pr_warn_ratelimited("Got unknown fabric queue status: %d\n", err);
+ cmd->t_state = TRANSPORT_COMPLETE_QF_ERR;
+ }
+
spin_lock_irq(&dev->qf_cmd_lock);
list_add_tail(&cmd->se_qf_node, &cmd->se_dev->qf_cmd_list);
atomic_inc_mb(&dev->dev_qf_count);
@@ -2086,7 +2117,7 @@ static void target_complete_ok_work(struct work_struct *work)
WARN_ON(!cmd->scsi_status);
ret = transport_send_check_condition_and_sense(
cmd, 0, 1);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
transport_lun_remove_cmd(cmd);
@@ -2112,7 +2143,7 @@ static void target_complete_ok_work(struct work_struct *work)
} else if (rc) {
ret = transport_send_check_condition_and_sense(cmd,
rc, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
transport_lun_remove_cmd(cmd);
@@ -2137,7 +2168,7 @@ static void target_complete_ok_work(struct work_struct *work)
if (target_read_prot_action(cmd)) {
ret = transport_send_check_condition_and_sense(cmd,
cmd->pi_err, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
transport_lun_remove_cmd(cmd);
@@ -2147,7 +2178,7 @@ static void target_complete_ok_work(struct work_struct *work)
trace_target_cmd_complete(cmd);
ret = cmd->se_tfo->queue_data_in(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
break;
case DMA_TO_DEVICE:
@@ -2160,7 +2191,7 @@ static void target_complete_ok_work(struct work_struct *work)
atomic_long_add(cmd->data_length,
&cmd->se_lun->lun_stats.tx_data_octets);
ret = cmd->se_tfo->queue_data_in(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
break;
}
@@ -2169,7 +2200,7 @@ static void target_complete_ok_work(struct work_struct *work)
queue_status:
trace_target_cmd_complete(cmd);
ret = cmd->se_tfo->queue_status(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
break;
default:
@@ -2183,8 +2214,8 @@ static void target_complete_ok_work(struct work_struct *work)
queue_full:
pr_debug("Handling complete_ok QUEUE_FULL: se_cmd: %p,"
" data_direction: %d\n", cmd, cmd->data_direction);
- cmd->t_state = TRANSPORT_COMPLETE_QF_OK;
- transport_handle_queue_full(cmd, cmd->se_dev);
+
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
}
void target_free_sgl(struct scatterlist *sgl, int nents)
@@ -2434,18 +2465,14 @@ void transport_kunmap_data_sg(struct se_cmd *cmd)
transport_cmd_check_stop(cmd, false, true);
ret = cmd->se_tfo->write_pending(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
- /* fabric drivers should only return -EAGAIN or -ENOMEM as error */
- WARN_ON(ret);
-
- return (!ret) ? 0 : TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return 0;
queue_full:
pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd);
- cmd->t_state = TRANSPORT_COMPLETE_QF_WP;
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, true);
return 0;
}
EXPORT_SYMBOL(transport_generic_new_cmd);
@@ -2455,10 +2482,10 @@ static void transport_write_pending_qf(struct se_cmd *cmd)
int ret;
ret = cmd->se_tfo->write_pending(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM) {
+ if (ret) {
pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n",
cmd);
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, true);
}
}
@@ -2951,6 +2978,8 @@ static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
__releases(&cmd->t_state_lock)
__acquires(&cmd->t_state_lock)
{
+ int ret;
+
assert_spin_locked(&cmd->t_state_lock);
WARN_ON_ONCE(!irqs_disabled());
@@ -2974,7 +3003,9 @@ static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
trace_target_cmd_complete(cmd);
spin_unlock_irq(&cmd->t_state_lock);
- cmd->se_tfo->queue_status(cmd);
+ ret = cmd->se_tfo->queue_status(cmd);
+ if (ret)
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
spin_lock_irq(&cmd->t_state_lock);
return 1;
@@ -2995,6 +3026,7 @@ int transport_check_aborted_status(struct se_cmd *cmd, int send_status)
void transport_send_task_abort(struct se_cmd *cmd)
{
unsigned long flags;
+ int ret;
spin_lock_irqsave(&cmd->t_state_lock, flags);
if (cmd->se_cmd_flags & (SCF_SENT_CHECK_CONDITION)) {
@@ -3030,7 +3062,9 @@ void transport_send_task_abort(struct se_cmd *cmd)
cmd->t_task_cdb[0], cmd->tag);
trace_target_cmd_complete(cmd);
- cmd->se_tfo->queue_status(cmd);
+ ret = cmd->se_tfo->queue_status(cmd);
+ if (ret)
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
}
static void target_tmr_work(struct work_struct *work)
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index c211900..6a5e439 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -119,6 +119,7 @@ enum transport_state_table {
TRANSPORT_ISTATE_PROCESSING = 11,
TRANSPORT_COMPLETE_QF_WP = 18,
TRANSPORT_COMPLETE_QF_OK = 19,
+ TRANSPORT_COMPLETE_QF_ERR = 20,
};
/* Used for struct se_cmd->se_cmd_flags */
--
1.9.1
^ permalink raw reply related
* [PATCH 0/3] target: Fix queue-full callback error signaling
From: Nicholas A. Bellinger @ 2016-10-31 5:25 UTC (permalink / raw)
To: target-devel
Cc: linux-rdma, Potnuri Bharat Teja, Steve Wise, Sagi Grimberg,
Nicholas Bellinger
From: Nicholas Bellinger <nab@linux-iscsi.org>
Hi folks,
This series contains target-core queue-full + iscsi-target
callback fixes for a bug reported by Steve and Potnuri
during recent v4.8.y iWARP/iser-target testing.
The first patch fixes target-core queue-full handling response
leaks with non -EAGAIN / -ENOMEM errors. It uses a new state
TRANSPORT_COMPLETE_QF_ERR to internally generate CHECK_CONDITION
for unknown fabric callback errors, to avoid attempting retry
of fabric data-transfer callbacks for this special case.
This means all non -EAGAIN / -ENOMEM fabric callback errors
during target_core_fabric_ops for:
*) ->write_pending()
*) ->queue_data_in()
*) ->queue_status()
will result in CHECK_CONDITION + LOGICAL_UNIT_COMMUNICATION_FAILURE,
if no non-zero se_cmd->scsi_status was previously set.
It also means target-core ->queue_status() errors retry indefinately,
or until session shutdown explicitly stops outstanding I/O.
The remaining changes are for propagating iscsit_transport
response failure back to target-core queue-full, and updating
iser-target to propagate isert_rdma_rw_ctx_post() errors from
RDMA R/W API back to target-core as well.
Please review.
--nab
Nicholas Bellinger (3):
target: Fix unknown fabric callback queue-full errors
iscsi-target: Propigate queue_data_in + queue_status errors
iser-target: Fix queue-full response handling
drivers/infiniband/ulp/isert/ib_isert.c | 53 +++++++++-----
drivers/target/iscsi/iscsi_target.c | 3 +-
drivers/target/iscsi/iscsi_target_configfs.c | 13 ++--
drivers/target/iscsi/iscsi_target_util.c | 5 +-
drivers/target/iscsi/iscsi_target_util.h | 2 +-
drivers/target/target_core_transport.c | 102 ++++++++++++++++++---------
include/target/target_core_base.h | 1 +
7 files changed, 114 insertions(+), 65 deletions(-)
--
1.9.1
^ permalink raw reply
* Re: [PATCH] IBcore/CM: Issue DREQ when receiving REQ/REP for stale QP
From: santosh.shilimkar-QHcLZuEGTsvQT0dZR+AlfA @ 2016-10-31 4:52 UTC (permalink / raw)
To: Sagi Grimberg, Hans Westgaard Ry, Doug Ledford, Sean Hefty,
Hal Rosenstock, Matan Barak, Erez Shitrit, Bart Van Assche,
Ira Weiny, Or Gerlitz, Hakon Bugge, Yuval Shaia,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <8df2c90e-8581-4ce8-fd18-92ac57eb6160-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
On 10/30/16 2:06 PM, Sagi Grimberg wrote:
>> from "InfiBand Architecture Specifications Volume 1":
>>
>> A QP is said to have a stale connection when only one side has
>> connection information. A stale connection may result if the remote CM
>> had dropped the connection and sent a DREQ but the DREQ was never
>> received by the local CM. Alternatively the remote CM may have lost
>> all record of past connections because its node crashed and rebooted,
>> while the local CM did not become aware of the remote node's reboot
>> and therefore did not clean up stale connections.
>>
>> and:
>>
>> A local CM may receive a REQ/REP for a stale connection. It shall
>> abort the connection issuing REJ to the REQ/REP. It shall then issue
>> DREQ with "DREQ:remote QPN” set to the remote QPN from the REQ/REP.
>>
>> This patch solves a problem with reuse of QPN. Current codebase, that
>> is IPoIB, relies on a REAP-mechanism to do cleanup of the structures
>> in CM. A problem with this is the timeconstants governing this
>> mechanism; they are up to 768 seconds and the interface may look
>> inresponsive in that period. Issuing a DREQ (and receiving a DREP)
>> does the necessary cleanup and the interface comes up.
>
> I like this fix, so,
>
Me too and hence suggested Hans to post it on rdma list when
saw this patch in internal review.
> Reviewed-by: Sagi Grimberg <sagi-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
>
> But I think the CM layer still is buggy in this area.
>
> In vol 1 the state transition table specifically states that DREP
> timeouts should move the cm_id to timewait state but the CM doesn't
> seem to maintain response timeouts on disconnect requests. If the
> DREQ happened to fail (send error completion) things are fine, but
> if the DREQ makes it to the peer but it doesn't reply then no one
> will take care of it (i.e. we will never see a TIMEWAIT event from
> this cm_id)...
>
> I recall some debugging session with Hal on this area a ~year ago
> with a new iser target (which didn't reply to DREQs on reboot
> sequences). iser initiator waits for a DISCONNECTED/TIMEWAIT events
> before destroying the cm_id (which never happened because of the
> above). I think I ended up working around that in iser to just go
> ahead and destroy the cm_id after issuing a DREQ (but now I realize
> it was never included so I'll probably dig it up again soon).
There is another fundamental issue with core CM code wrt DREQ
getting dropped. The the mad agent used to send the DREQ is
associated with a port and if this port is down, the IB link
layer will drop that DREQ as per SPEC. Similarly if the destination
port is down where the DREQ is suppose to reach, then the DREQ
gets dropped there too. These dropped CM ids are retried by MAD
agent on same port till the port comes back alive.
Am not sure in your case the ports were going down or not
but it was the case then IIUC, what you are doing for ISER is
still needed (up front destroying the cm id).
Regards,
Santosh
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: SQ overflow seen running isert traffic
From: Nicholas A. Bellinger @ 2016-10-31 3:40 UTC (permalink / raw)
To: Steve Wise
Cc: 'Sagi Grimberg', 'Potnuri Bharat Teja',
target-devel-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <005101d2294c$be5bb460$3b131d20$@opengridcomputing.com>
Hi Steve, Potnuri, & Co,
On Tue, 2016-10-18 at 09:34 -0500, Steve Wise wrote:
> >
> > > I tried out this change and it works fine with iwarp. I dont see SQ
> > > overflow. Apparently we have increased the sq too big to overflow. I am
> going
> > > to let it run with higher workloads for longer time, to see if it holds
> good.
> >
> > Actually on second thought, this patch is an overkill. Effectively we
> > now set:
> >
> > MAX_CMD=266
> > and max_rdma_ctx=128 so together we take 394 which seems to too much.
> >
> > If we go by the scheme of 1 rdma + 1 send for each IO we need:
> > - 128 sends
> > - 128 rdmas
> > - 10 miscs
> >
> > so this gives 266.
> >
> > Perhaps this is due to the fact that iWARP needs to register memory for
> > rdma reads as well? (and also rdma writes > 128k for chelsio HW right?)
> >
>
> iWARP definitely needs to register memory for the target of reads, due to
> REMOTE_WRITE requirement for the protocol. The source of a write doesn't need
> to register memory, but the SGE depth can cause multiple WRITE WRs to be
> required to service the IO. And in theory there should be some threshold where
> it might be better performance-wise to do a memory register + 1 WRITE vs X
> WRITEs.
>
> As you mentioned, the RW API should account for this, but perhaps it is still
> off some. Bharat, have a look into the RDMA-RW API and let us see if we can
> figure out if the additional SQ depth it adds is sufficient.
>
> > What is the workload you are running? with immediatedata enabled you
> > should issue reg+rdma_read+send only for writes > 8k.
> >
> > Does this happen when you run only reads for example?
> >
> > I guess its time to get the sq accounting into shape...
>
> So to sum up - 2 issues:
>
> 1) we believe the iSER + RW API correctly sizes the SQ, yet we're seeing SQ
> overflows. So the SQ sizing needs more investigation.
>
> 2) if the SQ is full, then the iSER/target code is supposed to resubmit. And
> apparently that isn't working.
>
For #2, target-core expects -ENOMEM or -EAGAIN return from fabric driver
callbacks to signal internal queue-full retry logic. Otherwise, the
extra se_cmd->cmd_kref response SCF_ACK_KREF is leaked until session
shutdown and/or reinstatement occurs.
AFAICT, Potunri's earlier hung task with v4.8.y + ABORT_TASK is likely
the earlier v4.1+ regression:
https://github.com/torvalds/linux/commit/527268df31e57cf2b6d417198717c6d6afdb1e3e
That said, there is room for improvement in target-core queue-full error
signaling, and iscsi-target/iser-target callback error propagation.
Sending out a series shortly to address these particular items.
Please have a look.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: RDMA developer gatherings around Kernel Summit and Linux Plumbers in Santa Fe
From: Christoph Lameter @ 2016-10-30 23:49 UTC (permalink / raw)
To: Or Gerlitz
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Doug Ledford,
skc-YOWKrPYUwWM, Weiny, Ira, Jason Gunthorpe, John Fleck,
Leon Romanovsky, Liran Liss, Matan Barak, Tzahi Oved
In-Reply-To: <CAJ3xEMiy8+yQTQKpuY8f57VJwWMwXryxQ09ghyTbDr91s=3w+g-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Sat, 29 Oct 2016, Or Gerlitz wrote:
> On Fri, Oct 28, 2016 at 8:17 PM, Christoph Lameter <cl-vYTEC60ixJUAvxtiuMwx3w@public.gmane.org> wrote:
>
> > - RDMA workshop on Tuesday, 1st of November
> > Meeting in Sweeney AB from 9am till 5pm.
> > See https://www.linuxplumbersconf.org/2016/ocw/events/LPC2016/schedule
> > This is part of the Kernel Summit and the Linux Plumbers
> > Conference. Only open to KS and LPC attendees with an invitation.
>
> isn't that open to all LPC attendees? didn't follow on the invitation
> requirement.. it's part of LPC
>
If you were invited to the KS or LPC then you can attend the RDMA
workshop.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH for-next V2 00/15][PULL request] Mellanox mlx5 core driver updates 2016-10-25
From: David Miller @ 2016-10-30 21:35 UTC (permalink / raw)
To: saeedm-VPRAkNaXOzVWk0Htik3J/w
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
ogerlitz-VPRAkNaXOzVWk0Htik3J/w, leonro-VPRAkNaXOzVWk0Htik3J/w,
talal-VPRAkNaXOzVWk0Htik3J/w, matanb-VPRAkNaXOzVWk0Htik3J/w
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Date: Sun, 30 Oct 2016 23:21:53 +0200
> This series contains some updates and fixes of mlx5 core and
> IB drivers with the addition of two features that demand
> new low level commands and infrastructure updates.
> - SRIOV VF max rate limit support
> - mlx5e tc support for FWD rules with counter.
>
> Needed for both net and rdma subsystems.
Pulled, thanks.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH for-next V2 15/15] net/mlx5e: Add tc support for FWD rule with counter
From: Saeed Mahameed @ 2016-10-30 21:22 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Or Gerlitz, Leon Romanovsky, Tal Alon, Matan Barak, Mark Bloch,
Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
When creating a FWD rule using tc create also a HW counter
for this rule.
Signed-off-by: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 ++-
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 20 +++++++++++---------
2 files changed, 13 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 5d9ac0d..c2e4728 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -419,7 +419,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
return -EINVAL;
}
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
out_priv = netdev_priv(out_dev);
attr->out_rep = out_priv->ppriv;
continue;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 8b2a383..53d9d6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -48,11 +48,12 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
struct mlx5_esw_flow_attr *attr)
{
- struct mlx5_flow_destination dest = { 0 };
+ struct mlx5_flow_destination dest[2] = {};
struct mlx5_fc *counter = NULL;
struct mlx5_flow_handle *rule;
void *misc;
int action;
+ int i = 0;
if (esw->mode != SRIOV_OFFLOADS)
return ERR_PTR(-EOPNOTSUPP);
@@ -60,15 +61,17 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
action = attr->action;
if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
- dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
- dest.vport_num = attr->out_rep->vport;
- action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- } else if (action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+ dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+ dest[i].vport_num = attr->out_rep->vport;
+ i++;
+ }
+ if (action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
counter = mlx5_fc_create(esw->dev, true);
if (IS_ERR(counter))
return ERR_CAST(counter);
- dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
- dest.counter = counter;
+ dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+ dest[i].counter = counter;
+ i++;
}
misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
@@ -81,8 +84,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
MLX5_MATCH_MISC_PARAMETERS;
rule = mlx5_add_flow_rules((struct mlx5_flow_table *)esw->fdb_table.fdb,
- spec, action, 0, &dest, 1);
-
+ spec, action, 0, dest, i);
if (IS_ERR(rule))
mlx5_fc_destroy(esw->dev, counter);
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH for-next V2 14/15] net/mlx5: Add option to add fwd rule with counter
From: Saeed Mahameed @ 2016-10-30 21:22 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Or Gerlitz, Leon Romanovsky, Tal Alon,
Matan Barak, Mark Bloch, Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm@mellanox.com>
From: Mark Bloch <markb@mellanox.com>
Currently the code supports only drop rules to possess counters,
add that ability also for fwd rules.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 24 +++++++++++++++++------
1 file changed, 18 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 6732287..0dfd998 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -374,6 +374,7 @@ static void del_rule(struct fs_node *node)
struct mlx5_core_dev *dev = get_dev(node);
int match_len = MLX5_ST_SZ_BYTES(fte_match_param);
int err;
+ bool update_fte = false;
match_value = mlx5_vzalloc(match_len);
if (!match_value) {
@@ -392,13 +393,23 @@ static void del_rule(struct fs_node *node)
list_del(&rule->next_ft);
mutex_unlock(&rule->dest_attr.ft->lock);
}
+
+ if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER &&
+ --fte->dests_size) {
+ modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+ fte->action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ update_fte = true;
+ goto out;
+ }
+
if ((fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
--fte->dests_size) {
modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST),
- err = mlx5_cmd_update_fte(dev, ft,
- fg->id,
- modify_mask,
- fte);
+ update_fte = true;
+ }
+out:
+ if (update_fte && fte->dests_size) {
+ err = mlx5_cmd_update_fte(dev, ft, fg->id, modify_mask, fte);
if (err)
mlx5_core_warn(dev,
"%s can't del rule fg id=%d fte_index=%d\n",
@@ -1287,8 +1298,9 @@ static bool counter_is_valid(struct mlx5_fc *counter, u32 action)
if (!counter)
return false;
- /* Hardware support counter for a drop action only */
- return action == (MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT);
+ return (action & (MLX5_FLOW_CONTEXT_ACTION_DROP |
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)) &&
+ (action & MLX5_FLOW_CONTEXT_ACTION_COUNT);
}
static bool dest_is_valid(struct mlx5_flow_destination *dest,
--
2.7.4
^ permalink raw reply related
* [PATCH for-next V2 13/15] net/mlx5: Add multi dest support
From: Saeed Mahameed @ 2016-10-30 21:22 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Or Gerlitz, Leon Romanovsky, Tal Alon, Matan Barak, Mark Bloch,
Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Currently when calling mlx5_add_flow_rule we accept
only one flow destination, this commit allows to pass
multiple destinations.
This change forces us to change the return structure to a more
flexible one. We introduce a flow handle (struct mlx5_flow_handle),
it holds internally the number for rules created and holds an array
where each cell points the to a flow rule.
>From the consumers (of mlx5_add_flow_rule) point of view this
change is only cosmetic and requires only to change the type
of the returned value they store.
>From the core point of view, we now need to use a loop when
allocating and deleting rules (e.g given to us a flow handler).
Signed-off-by: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
drivers/infiniband/hw/mlx5/main.c | 14 +-
drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/en.h | 14 +-
drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 38 +--
drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 49 ++--
.../ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 19 +-
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 6 +-
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 32 +--
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 68 ++---
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 22 +-
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 42 +--
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 289 ++++++++++++++-------
drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 5 +
include/linux/mlx5/fs.h | 28 +-
14 files changed, 374 insertions(+), 254 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d02341e..8e0dbd5 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1771,13 +1771,13 @@ static int mlx5_ib_destroy_flow(struct ib_flow *flow_id)
mutex_lock(&dev->flow_db.lock);
list_for_each_entry_safe(iter, tmp, &handler->list, list) {
- mlx5_del_flow_rule(iter->rule);
+ mlx5_del_flow_rules(iter->rule);
put_flow_table(dev, iter->prio, true);
list_del(&iter->list);
kfree(iter);
}
- mlx5_del_flow_rule(handler->rule);
+ mlx5_del_flow_rules(handler->rule);
put_flow_table(dev, handler->prio, true);
mutex_unlock(&dev->flow_db.lock);
@@ -1907,10 +1907,10 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
action = dst ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
- handler->rule = mlx5_add_flow_rule(ft, spec,
+ handler->rule = mlx5_add_flow_rules(ft, spec,
action,
MLX5_FS_DEFAULT_FLOW_TAG,
- dst);
+ dst, 1);
if (IS_ERR(handler->rule)) {
err = PTR_ERR(handler->rule);
@@ -1941,7 +1941,7 @@ static struct mlx5_ib_flow_handler *create_dont_trap_rule(struct mlx5_ib_dev *de
handler_dst = create_flow_rule(dev, ft_prio,
flow_attr, dst);
if (IS_ERR(handler_dst)) {
- mlx5_del_flow_rule(handler->rule);
+ mlx5_del_flow_rules(handler->rule);
ft_prio->refcount--;
kfree(handler);
handler = handler_dst;
@@ -2004,7 +2004,7 @@ static struct mlx5_ib_flow_handler *create_leftovers_rule(struct mlx5_ib_dev *de
&leftovers_specs[LEFTOVERS_UC].flow_attr,
dst);
if (IS_ERR(handler_ucast)) {
- mlx5_del_flow_rule(handler->rule);
+ mlx5_del_flow_rules(handler->rule);
ft_prio->refcount--;
kfree(handler);
handler = handler_ucast;
@@ -2046,7 +2046,7 @@ static struct mlx5_ib_flow_handler *create_sniffer_rule(struct mlx5_ib_dev *dev,
return handler_rx;
err_tx:
- mlx5_del_flow_rule(handler_rx->rule);
+ mlx5_del_flow_rules(handler_rx->rule);
ft_rx->refcount--;
kfree(handler_rx);
err:
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index dcdcd19..d5d0077 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -153,7 +153,7 @@ struct mlx5_ib_flow_handler {
struct list_head list;
struct ib_flow ibflow;
struct mlx5_ib_flow_prio *prio;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
};
struct mlx5_ib_flow_db {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 460363b..47ee8ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -520,7 +520,7 @@ struct mlx5e_vxlan_db {
struct mlx5e_l2_rule {
u8 addr[ETH_ALEN + 2];
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
};
struct mlx5e_flow_table {
@@ -541,10 +541,10 @@ struct mlx5e_tc_table {
struct mlx5e_vlan_table {
struct mlx5e_flow_table ft;
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
- struct mlx5_flow_rule *active_vlans_rule[VLAN_N_VID];
- struct mlx5_flow_rule *untagged_rule;
- struct mlx5_flow_rule *any_vlan_rule;
- bool filter_disabled;
+ struct mlx5_flow_handle *active_vlans_rule[VLAN_N_VID];
+ struct mlx5_flow_handle *untagged_rule;
+ struct mlx5_flow_handle *any_vlan_rule;
+ bool filter_disabled;
};
struct mlx5e_l2_table {
@@ -562,14 +562,14 @@ struct mlx5e_l2_table {
/* L3/L4 traffic type classifier */
struct mlx5e_ttc_table {
struct mlx5e_flow_table ft;
- struct mlx5_flow_rule *rules[MLX5E_NUM_TT];
+ struct mlx5_flow_handle *rules[MLX5E_NUM_TT];
};
#define ARFS_HASH_SHIFT BITS_PER_BYTE
#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
struct arfs_table {
struct mlx5e_flow_table ft;
- struct mlx5_flow_rule *default_rule;
+ struct mlx5_flow_handle *default_rule;
struct hlist_head rules_hash[ARFS_HASH_SIZE];
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index a8cb387..8ff22e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -56,7 +56,7 @@ struct arfs_tuple {
struct arfs_rule {
struct mlx5e_priv *priv;
struct work_struct arfs_work;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
struct hlist_node hlist;
int rxq;
/* Flow ID passed to ndo_rx_flow_steer */
@@ -104,7 +104,7 @@ static int arfs_disable(struct mlx5e_priv *priv)
tt = arfs_get_tt(i);
/* Modify ttc rules destination to bypass the aRFS tables*/
err = mlx5_modify_rule_destination(priv->fs.ttc.rules[tt],
- &dest);
+ &dest, NULL);
if (err) {
netdev_err(priv->netdev,
"%s: modify ttc destination failed\n",
@@ -137,7 +137,7 @@ int mlx5e_arfs_enable(struct mlx5e_priv *priv)
tt = arfs_get_tt(i);
/* Modify ttc rules destination to point on the aRFS FTs */
err = mlx5_modify_rule_destination(priv->fs.ttc.rules[tt],
- &dest);
+ &dest, NULL);
if (err) {
netdev_err(priv->netdev,
"%s: modify ttc destination failed err=%d\n",
@@ -151,7 +151,7 @@ int mlx5e_arfs_enable(struct mlx5e_priv *priv)
static void arfs_destroy_table(struct arfs_table *arfs_t)
{
- mlx5_del_flow_rule(arfs_t->default_rule);
+ mlx5_del_flow_rules(arfs_t->default_rule);
mlx5e_destroy_flow_table(&arfs_t->ft);
}
@@ -205,10 +205,10 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
goto out;
}
- arfs_t->default_rule = mlx5_add_flow_rule(arfs_t->ft.t, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG,
- &dest);
+ arfs_t->default_rule = mlx5_add_flow_rules(arfs_t->ft.t, spec,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ MLX5_FS_DEFAULT_FLOW_TAG,
+ &dest, 1);
if (IS_ERR(arfs_t->default_rule)) {
err = PTR_ERR(arfs_t->default_rule);
arfs_t->default_rule = NULL;
@@ -396,7 +396,7 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv)
spin_unlock_bh(&priv->fs.arfs.arfs_lock);
hlist_for_each_entry_safe(arfs_rule, htmp, &del_list, hlist) {
if (arfs_rule->rule)
- mlx5_del_flow_rule(arfs_rule->rule);
+ mlx5_del_flow_rules(arfs_rule->rule);
hlist_del(&arfs_rule->hlist);
kfree(arfs_rule);
}
@@ -420,7 +420,7 @@ static void arfs_del_rules(struct mlx5e_priv *priv)
hlist_for_each_entry_safe(rule, htmp, &del_list, hlist) {
cancel_work_sync(&rule->arfs_work);
if (rule->rule)
- mlx5_del_flow_rule(rule->rule);
+ mlx5_del_flow_rules(rule->rule);
hlist_del(&rule->hlist);
kfree(rule);
}
@@ -462,12 +462,12 @@ static struct arfs_table *arfs_get_table(struct mlx5e_arfs_tables *arfs,
return NULL;
}
-static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv,
- struct arfs_rule *arfs_rule)
+static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
+ struct arfs_rule *arfs_rule)
{
struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
struct arfs_tuple *tuple = &arfs_rule->tuple;
- struct mlx5_flow_rule *rule = NULL;
+ struct mlx5_flow_handle *rule = NULL;
struct mlx5_flow_destination dest;
struct arfs_table *arfs_table;
struct mlx5_flow_spec *spec;
@@ -544,9 +544,9 @@ static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv,
}
dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dest.tir_num = priv->direct_tir[arfs_rule->rxq].tirn;
- rule = mlx5_add_flow_rule(ft, spec, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG,
- &dest);
+ rule = mlx5_add_flow_rules(ft, spec, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ MLX5_FS_DEFAULT_FLOW_TAG,
+ &dest, 1);
if (IS_ERR(rule)) {
err = PTR_ERR(rule);
netdev_err(priv->netdev, "%s: add rule(filter id=%d, rq idx=%d) failed, err=%d\n",
@@ -559,14 +559,14 @@ static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv,
}
static void arfs_modify_rule_rq(struct mlx5e_priv *priv,
- struct mlx5_flow_rule *rule, u16 rxq)
+ struct mlx5_flow_handle *rule, u16 rxq)
{
struct mlx5_flow_destination dst;
int err = 0;
dst.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dst.tir_num = priv->direct_tir[rxq].tirn;
- err = mlx5_modify_rule_destination(rule, &dst);
+ err = mlx5_modify_rule_destination(rule, &dst, NULL);
if (err)
netdev_warn(priv->netdev,
"Failed to modfiy aRFS rule destination to rq=%d\n", rxq);
@@ -578,7 +578,7 @@ static void arfs_handle_work(struct work_struct *work)
struct arfs_rule,
arfs_work);
struct mlx5e_priv *priv = arfs_rule->priv;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
mutex_lock(&priv->state_lock);
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 36fbc6b..bed544d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -160,7 +160,7 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
{
struct mlx5_flow_table *ft = priv->fs.vlan.ft.t;
struct mlx5_flow_destination dest;
- struct mlx5_flow_rule **rule_p;
+ struct mlx5_flow_handle **rule_p;
int err = 0;
dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -187,10 +187,10 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
break;
}
- *rule_p = mlx5_add_flow_rule(ft, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG,
- &dest);
+ *rule_p = mlx5_add_flow_rules(ft, spec,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ MLX5_FS_DEFAULT_FLOW_TAG,
+ &dest, 1);
if (IS_ERR(*rule_p)) {
err = PTR_ERR(*rule_p);
@@ -229,20 +229,20 @@ static void mlx5e_del_vlan_rule(struct mlx5e_priv *priv,
switch (rule_type) {
case MLX5E_VLAN_RULE_TYPE_UNTAGGED:
if (priv->fs.vlan.untagged_rule) {
- mlx5_del_flow_rule(priv->fs.vlan.untagged_rule);
+ mlx5_del_flow_rules(priv->fs.vlan.untagged_rule);
priv->fs.vlan.untagged_rule = NULL;
}
break;
case MLX5E_VLAN_RULE_TYPE_ANY_VID:
if (priv->fs.vlan.any_vlan_rule) {
- mlx5_del_flow_rule(priv->fs.vlan.any_vlan_rule);
+ mlx5_del_flow_rules(priv->fs.vlan.any_vlan_rule);
priv->fs.vlan.any_vlan_rule = NULL;
}
break;
case MLX5E_VLAN_RULE_TYPE_MATCH_VID:
mlx5e_vport_context_update_vlans(priv);
if (priv->fs.vlan.active_vlans_rule[vid]) {
- mlx5_del_flow_rule(priv->fs.vlan.active_vlans_rule[vid]);
+ mlx5_del_flow_rules(priv->fs.vlan.active_vlans_rule[vid]);
priv->fs.vlan.active_vlans_rule[vid] = NULL;
}
mlx5e_vport_context_update_vlans(priv);
@@ -560,7 +560,7 @@ static void mlx5e_cleanup_ttc_rules(struct mlx5e_ttc_table *ttc)
for (i = 0; i < MLX5E_NUM_TT; i++) {
if (!IS_ERR_OR_NULL(ttc->rules[i])) {
- mlx5_del_flow_rule(ttc->rules[i]);
+ mlx5_del_flow_rules(ttc->rules[i]);
ttc->rules[i] = NULL;
}
}
@@ -616,13 +616,14 @@ static struct {
},
};
-static struct mlx5_flow_rule *mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
- struct mlx5_flow_table *ft,
- struct mlx5_flow_destination *dest,
- u16 etype,
- u8 proto)
+static struct mlx5_flow_handle *
+mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
+ struct mlx5_flow_table *ft,
+ struct mlx5_flow_destination *dest,
+ u16 etype,
+ u8 proto)
{
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
struct mlx5_flow_spec *spec;
int err = 0;
@@ -643,10 +644,10 @@ static struct mlx5_flow_rule *mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype);
}
- rule = mlx5_add_flow_rule(ft, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG,
- dest);
+ rule = mlx5_add_flow_rules(ft, spec,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ MLX5_FS_DEFAULT_FLOW_TAG,
+ dest, 1);
if (IS_ERR(rule)) {
err = PTR_ERR(rule);
netdev_err(priv->netdev, "%s: add rule failed\n", __func__);
@@ -660,7 +661,7 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv)
{
struct mlx5_flow_destination dest;
struct mlx5e_ttc_table *ttc;
- struct mlx5_flow_rule **rules;
+ struct mlx5_flow_handle **rules;
struct mlx5_flow_table *ft;
int tt;
int err;
@@ -801,7 +802,7 @@ static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv,
struct mlx5e_l2_rule *ai)
{
if (!IS_ERR_OR_NULL(ai->rule)) {
- mlx5_del_flow_rule(ai->rule);
+ mlx5_del_flow_rules(ai->rule);
ai->rule = NULL;
}
}
@@ -847,9 +848,9 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
break;
}
- ai->rule = mlx5_add_flow_rule(ft, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG, &dest);
+ ai->rule = mlx5_add_flow_rules(ft, spec,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ MLX5_FS_DEFAULT_FLOW_TAG, &dest, 1);
if (IS_ERR(ai->rule)) {
netdev_err(priv->netdev, "%s: add l2 rule(mac:%pM) failed\n",
__func__, mv_dmac);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index d17c242..cf52c06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -36,7 +36,7 @@
struct mlx5e_ethtool_rule {
struct list_head list;
struct ethtool_rx_flow_spec flow_spec;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
struct mlx5e_ethtool_table *eth_ft;
};
@@ -284,13 +284,14 @@ static bool outer_header_zero(u32 *match_criteria)
size - 1);
}
-static struct mlx5_flow_rule *add_ethtool_flow_rule(struct mlx5e_priv *priv,
- struct mlx5_flow_table *ft,
- struct ethtool_rx_flow_spec *fs)
+static struct mlx5_flow_handle *
+add_ethtool_flow_rule(struct mlx5e_priv *priv,
+ struct mlx5_flow_table *ft,
+ struct ethtool_rx_flow_spec *fs)
{
struct mlx5_flow_destination *dst = NULL;
struct mlx5_flow_spec *spec;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
int err = 0;
u32 action;
@@ -317,8 +318,8 @@ static struct mlx5_flow_rule *add_ethtool_flow_rule(struct mlx5e_priv *priv,
}
spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria));
- rule = mlx5_add_flow_rule(ft, spec, action,
- MLX5_FS_DEFAULT_FLOW_TAG, dst);
+ rule = mlx5_add_flow_rules(ft, spec, action,
+ MLX5_FS_DEFAULT_FLOW_TAG, dst, 1);
if (IS_ERR(rule)) {
err = PTR_ERR(rule);
netdev_err(priv->netdev, "%s: failed to add ethtool steering rule: %d\n",
@@ -335,7 +336,7 @@ static void del_ethtool_rule(struct mlx5e_priv *priv,
struct mlx5e_ethtool_rule *eth_rule)
{
if (eth_rule->rule)
- mlx5_del_flow_rule(eth_rule->rule);
+ mlx5_del_flow_rules(eth_rule->rule);
list_del(ð_rule->list);
priv->fs.ethtool.tot_num_rules--;
put_flow_table(eth_rule->eth_ft);
@@ -475,7 +476,7 @@ int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
{
struct mlx5e_ethtool_table *eth_ft;
struct mlx5e_ethtool_rule *eth_rule;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
int num_tuples;
int err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3c97da1..88d3fd1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -328,7 +328,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5_eswitch_rep *rep = priv->ppriv;
struct mlx5_core_dev *mdev = priv->mdev;
- struct mlx5_flow_rule *flow_rule;
+ struct mlx5_flow_handle *flow_rule;
int err;
int i;
@@ -360,7 +360,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
return 0;
err_del_flow_rule:
- mlx5_del_flow_rule(rep->vport_rx_rule);
+ mlx5_del_flow_rules(rep->vport_rx_rule);
err_destroy_direct_tirs:
mlx5e_destroy_direct_tirs(priv);
err_destroy_direct_rqts:
@@ -375,7 +375,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
int i;
mlx5e_tc_cleanup(priv);
- mlx5_del_flow_rule(rep->vport_rx_rule);
+ mlx5_del_flow_rules(rep->vport_rx_rule);
mlx5e_destroy_direct_tirs(priv);
for (i = 0; i < priv->params.num_channels; i++)
mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index ce8c54d..5d9ac0d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -47,21 +47,22 @@
struct mlx5e_tc_flow {
struct rhash_head node;
u64 cookie;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
struct mlx5_esw_flow_attr *attr;
};
#define MLX5E_TC_TABLE_NUM_ENTRIES 1024
#define MLX5E_TC_TABLE_NUM_GROUPS 4
-static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
- struct mlx5_flow_spec *spec,
- u32 action, u32 flow_tag)
+static struct mlx5_flow_handle *
+mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec,
+ u32 action, u32 flow_tag)
{
struct mlx5_core_dev *dev = priv->mdev;
struct mlx5_flow_destination dest = { 0 };
struct mlx5_fc *counter = NULL;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
bool table_created = false;
if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
@@ -94,9 +95,9 @@ static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
}
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
- rule = mlx5_add_flow_rule(priv->fs.tc.t, spec,
- action, flow_tag,
- &dest);
+ rule = mlx5_add_flow_rules(priv->fs.tc.t, spec,
+ action, flow_tag,
+ &dest, 1);
if (IS_ERR(rule))
goto err_add_rule;
@@ -114,9 +115,10 @@ static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
return rule;
}
-static struct mlx5_flow_rule *mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
- struct mlx5_flow_spec *spec,
- struct mlx5_esw_flow_attr *attr)
+static struct mlx5_flow_handle *
+mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_esw_flow_attr *attr)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
int err;
@@ -129,7 +131,7 @@ static struct mlx5_flow_rule *mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
}
static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
- struct mlx5_flow_rule *rule,
+ struct mlx5_flow_handle *rule,
struct mlx5_esw_flow_attr *attr)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -140,7 +142,7 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
if (esw && esw->mode == SRIOV_OFFLOADS)
mlx5_eswitch_del_vlan_action(esw, attr);
- mlx5_del_flow_rule(rule);
+ mlx5_del_flow_rules(rule);
mlx5_fc_destroy(priv->mdev, counter);
@@ -450,7 +452,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
u32 flow_tag, action;
struct mlx5e_tc_flow *flow;
struct mlx5_flow_spec *spec;
- struct mlx5_flow_rule *old = NULL;
+ struct mlx5_flow_handle *old = NULL;
struct mlx5_esw_flow_attr *old_attr = NULL;
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -511,7 +513,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
goto out;
err_del_rule:
- mlx5_del_flow_rule(flow->rule);
+ mlx5_del_flow_rules(flow->rule);
err_free:
if (!old)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 9ef01d1..fcd8b15 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -56,7 +56,7 @@ struct esw_uc_addr {
/* E-Switch MC FDB table hash node */
struct esw_mc_addr { /* SRIOV only */
struct l2addr_node node;
- struct mlx5_flow_rule *uplink_rule; /* Forward to uplink rule */
+ struct mlx5_flow_handle *uplink_rule; /* Forward to uplink rule */
u32 refcnt;
};
@@ -65,7 +65,7 @@ struct vport_addr {
struct l2addr_node node;
u8 action;
u32 vport;
- struct mlx5_flow_rule *flow_rule; /* SRIOV only */
+ struct mlx5_flow_handle *flow_rule; /* SRIOV only */
/* A flag indicating that mac was added due to mc promiscuous vport */
bool mc_promisc;
};
@@ -237,13 +237,13 @@ static void del_l2_table_entry(struct mlx5_core_dev *dev, u32 index)
}
/* E-Switch FDB */
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN])
{
int match_header = (is_zero_ether_addr(mac_c) ? 0 :
MLX5_MATCH_OUTER_HEADERS);
- struct mlx5_flow_rule *flow_rule = NULL;
+ struct mlx5_flow_handle *flow_rule = NULL;
struct mlx5_flow_destination dest;
struct mlx5_flow_spec *spec;
void *mv_misc = NULL;
@@ -286,9 +286,9 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
dmac_v, dmac_c, vport);
spec->match_criteria_enable = match_header;
flow_rule =
- mlx5_add_flow_rule(esw->fdb_table.fdb, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- 0, &dest);
+ mlx5_add_flow_rules(esw->fdb_table.fdb, spec,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ 0, &dest, 1);
if (IS_ERR(flow_rule)) {
esw_warn(esw->dev,
"FDB: Failed to add flow rule: dmac_v(%pM) dmac_c(%pM) -> vport(%d), err(%ld)\n",
@@ -300,7 +300,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
return flow_rule;
}
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
{
u8 mac_c[ETH_ALEN];
@@ -309,7 +309,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
return __esw_fdb_set_vport_rule(esw, vport, false, mac_c, mac);
}
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
{
u8 mac_c[ETH_ALEN];
@@ -322,7 +322,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
return __esw_fdb_set_vport_rule(esw, vport, false, mac_c, mac_v);
}
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
{
u8 mac_c[ETH_ALEN];
@@ -515,7 +515,7 @@ static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
del_l2_table_entry(esw->dev, esw_uc->table_index);
if (vaddr->flow_rule)
- mlx5_del_flow_rule(vaddr->flow_rule);
+ mlx5_del_flow_rules(vaddr->flow_rule);
vaddr->flow_rule = NULL;
l2addr_hash_del(esw_uc);
@@ -562,7 +562,7 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
case MLX5_ACTION_DEL:
if (!iter_vaddr)
continue;
- mlx5_del_flow_rule(iter_vaddr->flow_rule);
+ mlx5_del_flow_rules(iter_vaddr->flow_rule);
l2addr_hash_del(iter_vaddr);
break;
}
@@ -632,7 +632,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
esw_mc->uplink_rule);
if (vaddr->flow_rule)
- mlx5_del_flow_rule(vaddr->flow_rule);
+ mlx5_del_flow_rules(vaddr->flow_rule);
vaddr->flow_rule = NULL;
/* If the multicast mac is added as a result of mc promiscuous vport,
@@ -645,7 +645,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
update_allmulti_vports(esw, vaddr, esw_mc);
if (esw_mc->uplink_rule)
- mlx5_del_flow_rule(esw_mc->uplink_rule);
+ mlx5_del_flow_rules(esw_mc->uplink_rule);
l2addr_hash_del(esw_mc);
return 0;
@@ -828,14 +828,14 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
UPLINK_VPORT);
allmulti_addr->refcnt++;
} else if (vport->allmulti_rule) {
- mlx5_del_flow_rule(vport->allmulti_rule);
+ mlx5_del_flow_rules(vport->allmulti_rule);
vport->allmulti_rule = NULL;
if (--allmulti_addr->refcnt > 0)
goto promisc;
if (allmulti_addr->uplink_rule)
- mlx5_del_flow_rule(allmulti_addr->uplink_rule);
+ mlx5_del_flow_rules(allmulti_addr->uplink_rule);
allmulti_addr->uplink_rule = NULL;
}
@@ -847,7 +847,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
vport->promisc_rule = esw_fdb_set_vport_promisc_rule(esw,
vport_num);
} else if (vport->promisc_rule) {
- mlx5_del_flow_rule(vport->promisc_rule);
+ mlx5_del_flow_rules(vport->promisc_rule);
vport->promisc_rule = NULL;
}
}
@@ -1015,10 +1015,10 @@ static void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan))
- mlx5_del_flow_rule(vport->egress.allowed_vlan);
+ mlx5_del_flow_rules(vport->egress.allowed_vlan);
if (!IS_ERR_OR_NULL(vport->egress.drop_rule))
- mlx5_del_flow_rule(vport->egress.drop_rule);
+ mlx5_del_flow_rules(vport->egress.drop_rule);
vport->egress.allowed_vlan = NULL;
vport->egress.drop_rule = NULL;
@@ -1173,10 +1173,10 @@ static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
if (!IS_ERR_OR_NULL(vport->ingress.drop_rule))
- mlx5_del_flow_rule(vport->ingress.drop_rule);
+ mlx5_del_flow_rules(vport->ingress.drop_rule);
if (!IS_ERR_OR_NULL(vport->ingress.allow_rule))
- mlx5_del_flow_rule(vport->ingress.allow_rule);
+ mlx5_del_flow_rules(vport->ingress.allow_rule);
vport->ingress.drop_rule = NULL;
vport->ingress.allow_rule = NULL;
@@ -1253,9 +1253,9 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
vport->ingress.allow_rule =
- mlx5_add_flow_rule(vport->ingress.acl, spec,
- MLX5_FLOW_CONTEXT_ACTION_ALLOW,
- 0, NULL);
+ mlx5_add_flow_rules(vport->ingress.acl, spec,
+ MLX5_FLOW_CONTEXT_ACTION_ALLOW,
+ 0, NULL, 0);
if (IS_ERR(vport->ingress.allow_rule)) {
err = PTR_ERR(vport->ingress.allow_rule);
esw_warn(esw->dev,
@@ -1267,9 +1267,9 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
memset(spec, 0, sizeof(*spec));
vport->ingress.drop_rule =
- mlx5_add_flow_rule(vport->ingress.acl, spec,
- MLX5_FLOW_CONTEXT_ACTION_DROP,
- 0, NULL);
+ mlx5_add_flow_rules(vport->ingress.acl, spec,
+ MLX5_FLOW_CONTEXT_ACTION_DROP,
+ 0, NULL, 0);
if (IS_ERR(vport->ingress.drop_rule)) {
err = PTR_ERR(vport->ingress.drop_rule);
esw_warn(esw->dev,
@@ -1321,9 +1321,9 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
vport->egress.allowed_vlan =
- mlx5_add_flow_rule(vport->egress.acl, spec,
- MLX5_FLOW_CONTEXT_ACTION_ALLOW,
- 0, NULL);
+ mlx5_add_flow_rules(vport->egress.acl, spec,
+ MLX5_FLOW_CONTEXT_ACTION_ALLOW,
+ 0, NULL, 0);
if (IS_ERR(vport->egress.allowed_vlan)) {
err = PTR_ERR(vport->egress.allowed_vlan);
esw_warn(esw->dev,
@@ -1336,9 +1336,9 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
/* Drop others rule (star rule) */
memset(spec, 0, sizeof(*spec));
vport->egress.drop_rule =
- mlx5_add_flow_rule(vport->egress.acl, spec,
- MLX5_FLOW_CONTEXT_ACTION_DROP,
- 0, NULL);
+ mlx5_add_flow_rules(vport->egress.acl, spec,
+ MLX5_FLOW_CONTEXT_ACTION_DROP,
+ 0, NULL, 0);
if (IS_ERR(vport->egress.drop_rule)) {
err = PTR_ERR(vport->egress.drop_rule);
esw_warn(esw->dev,
@@ -1667,7 +1667,7 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
esw_disable_vport(esw, i);
if (mc_promisc && mc_promisc->uplink_rule)
- mlx5_del_flow_rule(mc_promisc->uplink_rule);
+ mlx5_del_flow_rules(mc_promisc->uplink_rule);
esw_destroy_tsar(esw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ddae90c..6d414cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -97,16 +97,16 @@ struct vport_ingress {
struct mlx5_flow_group *allow_spoofchk_only_grp;
struct mlx5_flow_group *allow_untagged_only_grp;
struct mlx5_flow_group *drop_grp;
- struct mlx5_flow_rule *allow_rule;
- struct mlx5_flow_rule *drop_rule;
+ struct mlx5_flow_handle *allow_rule;
+ struct mlx5_flow_handle *drop_rule;
};
struct vport_egress {
struct mlx5_flow_table *acl;
struct mlx5_flow_group *allowed_vlans_grp;
struct mlx5_flow_group *drop_grp;
- struct mlx5_flow_rule *allowed_vlan;
- struct mlx5_flow_rule *drop_rule;
+ struct mlx5_flow_handle *allowed_vlan;
+ struct mlx5_flow_handle *drop_rule;
};
struct mlx5_vport_info {
@@ -125,8 +125,8 @@ struct mlx5_vport {
int vport;
struct hlist_head uc_list[MLX5_L2_ADDR_HASH_SIZE];
struct hlist_head mc_list[MLX5_L2_ADDR_HASH_SIZE];
- struct mlx5_flow_rule *promisc_rule;
- struct mlx5_flow_rule *allmulti_rule;
+ struct mlx5_flow_handle *promisc_rule;
+ struct mlx5_flow_handle *allmulti_rule;
struct work_struct vport_change_handler;
struct vport_ingress ingress;
@@ -162,7 +162,7 @@ struct mlx5_eswitch_fdb {
struct mlx5_flow_table *fdb;
struct mlx5_flow_group *send_to_vport_grp;
struct mlx5_flow_group *miss_grp;
- struct mlx5_flow_rule *miss_rule;
+ struct mlx5_flow_handle *miss_rule;
int vlan_push_pop_refcount;
} offloads;
};
@@ -175,7 +175,7 @@ enum {
};
struct mlx5_esw_sq {
- struct mlx5_flow_rule *send_to_vport_rule;
+ struct mlx5_flow_handle *send_to_vport_rule;
struct list_head list;
};
@@ -188,7 +188,7 @@ struct mlx5_eswitch_rep {
u8 hw_id[ETH_ALEN];
void *priv_data;
- struct mlx5_flow_rule *vport_rx_rule;
+ struct mlx5_flow_handle *vport_rx_rule;
struct list_head vport_sqs_list;
u16 vlan;
u32 vlan_refcount;
@@ -257,11 +257,11 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
struct mlx5_flow_spec;
struct mlx5_esw_flow_attr;
-struct mlx5_flow_rule *
+struct mlx5_flow_handle *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
struct mlx5_esw_flow_attr *attr);
-struct mlx5_flow_rule *
+struct mlx5_flow_handle *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn);
enum {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index c55ad8d..8b2a383 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -43,14 +43,14 @@ enum {
FDB_SLOW_PATH
};
-struct mlx5_flow_rule *
+struct mlx5_flow_handle *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
struct mlx5_esw_flow_attr *attr)
{
struct mlx5_flow_destination dest = { 0 };
struct mlx5_fc *counter = NULL;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
void *misc;
int action;
@@ -80,8 +80,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
MLX5_MATCH_MISC_PARAMETERS;
- rule = mlx5_add_flow_rule((struct mlx5_flow_table *)esw->fdb_table.fdb,
- spec, action, 0, &dest);
+ rule = mlx5_add_flow_rules((struct mlx5_flow_table *)esw->fdb_table.fdb,
+ spec, action, 0, &dest, 1);
if (IS_ERR(rule))
mlx5_fc_destroy(esw->dev, counter);
@@ -269,11 +269,11 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
return err;
}
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn)
{
struct mlx5_flow_destination dest;
- struct mlx5_flow_rule *flow_rule;
+ struct mlx5_flow_handle *flow_rule;
struct mlx5_flow_spec *spec;
void *misc;
@@ -296,9 +296,9 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest.vport_num = vport;
- flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- 0, &dest);
+ flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ 0, &dest, 1);
if (IS_ERR(flow_rule))
esw_warn(esw->dev, "FDB: Failed to add send to vport rule err %ld\n", PTR_ERR(flow_rule));
out:
@@ -315,7 +315,7 @@ void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw,
return;
list_for_each_entry_safe(esw_sq, tmp, &rep->vport_sqs_list, list) {
- mlx5_del_flow_rule(esw_sq->send_to_vport_rule);
+ mlx5_del_flow_rules(esw_sq->send_to_vport_rule);
list_del(&esw_sq->list);
kfree(esw_sq);
}
@@ -325,7 +325,7 @@ int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep,
u16 *sqns_array, int sqns_num)
{
- struct mlx5_flow_rule *flow_rule;
+ struct mlx5_flow_handle *flow_rule;
struct mlx5_esw_sq *esw_sq;
int err;
int i;
@@ -362,7 +362,7 @@ int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
{
struct mlx5_flow_destination dest;
- struct mlx5_flow_rule *flow_rule = NULL;
+ struct mlx5_flow_handle *flow_rule = NULL;
struct mlx5_flow_spec *spec;
int err = 0;
@@ -376,9 +376,9 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest.vport_num = 0;
- flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- 0, &dest);
+ flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ 0, &dest, 1);
if (IS_ERR(flow_rule)) {
err = PTR_ERR(flow_rule);
esw_warn(esw->dev, "FDB: Failed to add miss flow rule err %d\n", err);
@@ -501,7 +501,7 @@ static void esw_destroy_offloads_fdb_table(struct mlx5_eswitch *esw)
return;
esw_debug(esw->dev, "Destroy offloads FDB Table\n");
- mlx5_del_flow_rule(esw->fdb_table.offloads.miss_rule);
+ mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule);
mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
@@ -585,11 +585,11 @@ static void esw_destroy_vport_rx_group(struct mlx5_eswitch *esw)
mlx5_destroy_flow_group(esw->offloads.vport_rx_group);
}
-struct mlx5_flow_rule *
+struct mlx5_flow_handle *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn)
{
struct mlx5_flow_destination dest;
- struct mlx5_flow_rule *flow_rule;
+ struct mlx5_flow_handle *flow_rule;
struct mlx5_flow_spec *spec;
void *misc;
@@ -610,9 +610,9 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn)
dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dest.tir_num = tirn;
- flow_rule = mlx5_add_flow_rule(esw->offloads.ft_offloads, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- 0, &dest);
+ flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ 0, &dest, 1);
if (IS_ERR(flow_rule)) {
esw_warn(esw->dev, "fs offloads: Failed to add vport rx rule err %ld\n", PTR_ERR(flow_rule));
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 43d7052..6732287 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -155,6 +155,9 @@ static void del_flow_group(struct fs_node *node);
static void del_fte(struct fs_node *node);
static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
struct mlx5_flow_destination *d2);
+static struct mlx5_flow_rule *
+find_flow_rule(struct fs_fte *fte,
+ struct mlx5_flow_destination *dest);
static void tree_init_node(struct fs_node *node,
unsigned int refcount,
@@ -640,8 +643,8 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
return err;
}
-int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
- struct mlx5_flow_destination *dest)
+static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
+ struct mlx5_flow_destination *dest)
{
struct mlx5_flow_table *ft;
struct mlx5_flow_group *fg;
@@ -666,6 +669,28 @@ int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
return err;
}
+int mlx5_modify_rule_destination(struct mlx5_flow_handle *handle,
+ struct mlx5_flow_destination *new_dest,
+ struct mlx5_flow_destination *old_dest)
+{
+ int i;
+
+ if (!old_dest) {
+ if (handle->num_rules != 1)
+ return -EINVAL;
+ return _mlx5_modify_rule_destination(handle->rule[0],
+ new_dest);
+ }
+
+ for (i = 0; i < handle->num_rules; i++) {
+ if (mlx5_flow_dests_cmp(new_dest, &handle->rule[i]->dest_attr))
+ return _mlx5_modify_rule_destination(handle->rule[i],
+ new_dest);
+ }
+
+ return -EINVAL;
+}
+
/* Modify/set FWD rules that point on old_next_ft to point on new_next_ft */
static int connect_fwd_rules(struct mlx5_core_dev *dev,
struct mlx5_flow_table *new_next_ft,
@@ -688,7 +713,7 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev,
list_splice_init(&old_next_ft->fwd_rules, &new_next_ft->fwd_rules);
mutex_unlock(&old_next_ft->lock);
list_for_each_entry(iter, &new_next_ft->fwd_rules, next_ft) {
- err = mlx5_modify_rule_destination(iter, &dest);
+ err = _mlx5_modify_rule_destination(iter, &dest);
if (err)
pr_err("mlx5_core: failed to modify rule to point on flow table %d\n",
new_next_ft->id);
@@ -917,41 +942,117 @@ static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest)
return rule;
}
-/* fte should not be deleted while calling this function */
-static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte,
- struct mlx5_flow_group *fg,
- struct mlx5_flow_destination *dest,
- bool update_action)
+static struct mlx5_flow_handle *alloc_handle(int num_rules)
{
+ struct mlx5_flow_handle *handle;
+
+ handle = kzalloc(sizeof(*handle) + sizeof(handle->rule[0]) *
+ num_rules, GFP_KERNEL);
+ if (!handle)
+ return NULL;
+
+ handle->num_rules = num_rules;
+
+ return handle;
+}
+
+static void destroy_flow_handle(struct fs_fte *fte,
+ struct mlx5_flow_handle *handle,
+ struct mlx5_flow_destination *dest,
+ int i)
+{
+ for (; --i >= 0;) {
+ if (atomic_dec_and_test(&handle->rule[i]->node.refcount)) {
+ fte->dests_size--;
+ list_del(&handle->rule[i]->node.list);
+ kfree(handle->rule[i]);
+ }
+ }
+ kfree(handle);
+}
+
+static struct mlx5_flow_handle *
+create_flow_handle(struct fs_fte *fte,
+ struct mlx5_flow_destination *dest,
+ int dest_num,
+ int *modify_mask,
+ bool *new_rule)
+{
+ struct mlx5_flow_handle *handle;
+ struct mlx5_flow_rule *rule = NULL;
+ static int count = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
+ static int dst = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
+ int type;
+ int i = 0;
+
+ handle = alloc_handle((dest_num) ? dest_num : 1);
+ if (!handle)
+ return ERR_PTR(-ENOMEM);
+
+ do {
+ if (dest) {
+ rule = find_flow_rule(fte, dest + i);
+ if (rule) {
+ atomic_inc(&rule->node.refcount);
+ goto rule_found;
+ }
+ }
+
+ *new_rule = true;
+ rule = alloc_rule(dest + i);
+ if (!rule)
+ goto free_rules;
+
+ /* Add dest to dests list- we need flow tables to be in the
+ * end of the list for forward to next prio rules.
+ */
+ tree_init_node(&rule->node, 1, del_rule);
+ if (dest &&
+ dest[i].type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
+ list_add(&rule->node.list, &fte->node.children);
+ else
+ list_add_tail(&rule->node.list, &fte->node.children);
+ if (dest) {
+ fte->dests_size++;
+
+ type = dest[i].type ==
+ MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+ *modify_mask |= type ? count : dst;
+ }
+rule_found:
+ handle->rule[i] = rule;
+ } while (++i < dest_num);
+
+ return handle;
+
+free_rules:
+ destroy_flow_handle(fte, handle, dest, i);
+ return ERR_PTR(-ENOMEM);
+}
+
+/* fte should not be deleted while calling this function */
+static struct mlx5_flow_handle *
+add_rule_fte(struct fs_fte *fte,
+ struct mlx5_flow_group *fg,
+ struct mlx5_flow_destination *dest,
+ int dest_num,
+ bool update_action)
+{
+ struct mlx5_flow_handle *handle;
struct mlx5_flow_table *ft;
- struct mlx5_flow_rule *rule;
int modify_mask = 0;
int err;
+ bool new_rule = false;
- rule = alloc_rule(dest);
- if (!rule)
- return ERR_PTR(-ENOMEM);
+ handle = create_flow_handle(fte, dest, dest_num, &modify_mask,
+ &new_rule);
+ if (IS_ERR(handle) || !new_rule)
+ goto out;
if (update_action)
modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
fs_get_obj(ft, fg->node.parent);
- /* Add dest to dests list- we need flow tables to be in the
- * end of the list for forward to next prio rules.
- */
- tree_init_node(&rule->node, 1, del_rule);
- if (dest && dest->type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
- list_add(&rule->node.list, &fte->node.children);
- else
- list_add_tail(&rule->node.list, &fte->node.children);
- if (dest) {
- fte->dests_size++;
-
- modify_mask |= dest->type == MLX5_FLOW_DESTINATION_TYPE_COUNTER ?
- BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS) :
- BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
- }
-
if (!(fte->status & FS_FTE_STATUS_EXISTING))
err = mlx5_cmd_create_fte(get_dev(&ft->node),
ft, fg->id, fte);
@@ -959,17 +1060,15 @@ static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte,
err = mlx5_cmd_update_fte(get_dev(&ft->node),
ft, fg->id, modify_mask, fte);
if (err)
- goto free_rule;
+ goto free_handle;
fte->status |= FS_FTE_STATUS_EXISTING;
- return rule;
+out:
+ return handle;
-free_rule:
- list_del(&rule->node.list);
- kfree(rule);
- if (dest)
- fte->dests_size--;
+free_handle:
+ destroy_flow_handle(fte, handle, dest, handle->num_rules);
return ERR_PTR(err);
}
@@ -1098,16 +1197,18 @@ static struct mlx5_flow_rule *find_flow_rule(struct fs_fte *fte,
return NULL;
}
-static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
- u32 *match_value,
- u8 action,
- u32 flow_tag,
- struct mlx5_flow_destination *dest)
+static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
+ u32 *match_value,
+ u8 action,
+ u32 flow_tag,
+ struct mlx5_flow_destination *dest,
+ int dest_num)
{
- struct fs_fte *fte;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *handle;
struct mlx5_flow_table *ft;
struct list_head *prev;
+ struct fs_fte *fte;
+ int i;
nested_lock_ref_node(&fg->node, FS_MUTEX_PARENT);
fs_for_each_fte(fte, fg) {
@@ -1116,40 +1217,33 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
(action & fte->action) && flow_tag == fte->flow_tag) {
int old_action = fte->action;
- rule = find_flow_rule(fte, dest);
- if (rule) {
- atomic_inc(&rule->node.refcount);
- unlock_ref_node(&fte->node);
- unlock_ref_node(&fg->node);
- return rule;
- }
fte->action |= action;
- rule = add_rule_fte(fte, fg, dest,
- old_action != action);
- if (IS_ERR(rule)) {
+ handle = add_rule_fte(fte, fg, dest, dest_num,
+ old_action != action);
+ if (IS_ERR(handle)) {
fte->action = old_action;
goto unlock_fte;
} else {
- goto add_rule;
+ goto add_rules;
}
}
unlock_ref_node(&fte->node);
}
fs_get_obj(ft, fg->node.parent);
if (fg->num_ftes >= fg->max_ftes) {
- rule = ERR_PTR(-ENOSPC);
+ handle = ERR_PTR(-ENOSPC);
goto unlock_fg;
}
fte = create_fte(fg, match_value, action, flow_tag, &prev);
if (IS_ERR(fte)) {
- rule = (void *)fte;
+ handle = (void *)fte;
goto unlock_fg;
}
tree_init_node(&fte->node, 0, del_fte);
nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
- rule = add_rule_fte(fte, fg, dest, false);
- if (IS_ERR(rule)) {
+ handle = add_rule_fte(fte, fg, dest, dest_num, false);
+ if (IS_ERR(handle)) {
kfree(fte);
goto unlock_fg;
}
@@ -1158,21 +1252,24 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
tree_add_node(&fte->node, &fg->node);
list_add(&fte->node.list, prev);
-add_rule:
- tree_add_node(&rule->node, &fte->node);
+add_rules:
+ for (i = 0; i < handle->num_rules; i++) {
+ if (atomic_read(&handle->rule[i]->node.refcount) == 1)
+ tree_add_node(&handle->rule[i]->node, &fte->node);
+ }
unlock_fte:
unlock_ref_node(&fte->node);
unlock_fg:
unlock_ref_node(&fg->node);
- return rule;
+ return handle;
}
-struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_rule *rule)
+struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handle)
{
struct mlx5_flow_rule *dst;
struct fs_fte *fte;
- fs_get_obj(fte, rule->node.parent);
+ fs_get_obj(fte, handle->rule[0]->node.parent);
fs_for_each_dst(dst, fte) {
if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
@@ -1211,18 +1308,22 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest,
return true;
}
-static struct mlx5_flow_rule *
-_mlx5_add_flow_rule(struct mlx5_flow_table *ft,
- struct mlx5_flow_spec *spec,
- u32 action,
- u32 flow_tag,
- struct mlx5_flow_destination *dest)
+static struct mlx5_flow_handle *
+_mlx5_add_flow_rules(struct mlx5_flow_table *ft,
+ struct mlx5_flow_spec *spec,
+ u32 action,
+ u32 flow_tag,
+ struct mlx5_flow_destination *dest,
+ int dest_num)
{
struct mlx5_flow_group *g;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
+ int i;
- if (!dest_is_valid(dest, action, ft))
- return ERR_PTR(-EINVAL);
+ for (i = 0; i < dest_num; i++) {
+ if (!dest_is_valid(&dest[i], action, ft))
+ return ERR_PTR(-EINVAL);
+ }
nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT);
fs_for_each_fg(g, ft)
@@ -1231,7 +1332,7 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft,
g->mask.match_criteria,
spec->match_criteria)) {
rule = add_rule_fg(g, spec->match_value,
- action, flow_tag, dest);
+ action, flow_tag, dest, dest_num);
if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC)
goto unlock;
}
@@ -1244,7 +1345,7 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft,
}
rule = add_rule_fg(g, spec->match_value,
- action, flow_tag, dest);
+ action, flow_tag, dest, dest_num);
if (IS_ERR(rule)) {
/* Remove assumes refcount > 0 and autogroup creates a group
* with a refcount = 0.
@@ -1265,17 +1366,18 @@ static bool fwd_next_prio_supported(struct mlx5_flow_table *ft)
(MLX5_CAP_FLOWTABLE(get_dev(&ft->node), nic_rx_multi_path_tirs)));
}
-struct mlx5_flow_rule *
-mlx5_add_flow_rule(struct mlx5_flow_table *ft,
- struct mlx5_flow_spec *spec,
- u32 action,
- u32 flow_tag,
- struct mlx5_flow_destination *dest)
+struct mlx5_flow_handle *
+mlx5_add_flow_rules(struct mlx5_flow_table *ft,
+ struct mlx5_flow_spec *spec,
+ u32 action,
+ u32 flow_tag,
+ struct mlx5_flow_destination *dest,
+ int dest_num)
{
struct mlx5_flow_root_namespace *root = find_root(&ft->node);
struct mlx5_flow_destination gen_dest;
struct mlx5_flow_table *next_ft = NULL;
- struct mlx5_flow_rule *rule = NULL;
+ struct mlx5_flow_handle *handle = NULL;
u32 sw_action = action;
struct fs_prio *prio;
@@ -1291,6 +1393,7 @@ mlx5_add_flow_rule(struct mlx5_flow_table *ft,
gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
gen_dest.ft = next_ft;
dest = &gen_dest;
+ dest_num = 1;
action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
} else {
mutex_unlock(&root->chain_lock);
@@ -1298,27 +1401,33 @@ mlx5_add_flow_rule(struct mlx5_flow_table *ft,
}
}
- rule = _mlx5_add_flow_rule(ft, spec, action, flow_tag, dest);
+ handle = _mlx5_add_flow_rules(ft, spec, action, flow_tag, dest,
+ dest_num);
if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
- if (!IS_ERR_OR_NULL(rule) &&
- (list_empty(&rule->next_ft))) {
+ if (!IS_ERR_OR_NULL(handle) &&
+ (list_empty(&handle->rule[0]->next_ft))) {
mutex_lock(&next_ft->lock);
- list_add(&rule->next_ft, &next_ft->fwd_rules);
+ list_add(&handle->rule[0]->next_ft,
+ &next_ft->fwd_rules);
mutex_unlock(&next_ft->lock);
- rule->sw_action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+ handle->rule[0]->sw_action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
}
mutex_unlock(&root->chain_lock);
}
- return rule;
+ return handle;
}
-EXPORT_SYMBOL(mlx5_add_flow_rule);
+EXPORT_SYMBOL(mlx5_add_flow_rules);
-void mlx5_del_flow_rule(struct mlx5_flow_rule *rule)
+void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
{
- tree_remove_node(&rule->node);
+ int i;
+
+ for (i = handle->num_rules - 1; i >= 0; i--)
+ tree_remove_node(&handle->rule[i]->node);
+ kfree(handle);
}
-EXPORT_SYMBOL(mlx5_del_flow_rule);
+EXPORT_SYMBOL(mlx5_del_flow_rules);
/* Assuming prio->node.children(flow tables) is sorted by level */
static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 71ff03b..d515088 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -94,6 +94,11 @@ struct mlx5_flow_rule {
u32 sw_action;
};
+struct mlx5_flow_handle {
+ int num_rules;
+ struct mlx5_flow_rule *rule[];
+};
+
/* Type of children is mlx5_flow_group */
struct mlx5_flow_table {
struct fs_node node;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 93ebc5e..0dcd287 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -69,8 +69,8 @@ enum mlx5_flow_namespace_type {
struct mlx5_flow_table;
struct mlx5_flow_group;
-struct mlx5_flow_rule;
struct mlx5_flow_namespace;
+struct mlx5_flow_handle;
struct mlx5_flow_spec {
u8 match_criteria_enable;
@@ -127,18 +127,20 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg);
/* Single destination per rule.
* Group ID is implied by the match criteria.
*/
-struct mlx5_flow_rule *
-mlx5_add_flow_rule(struct mlx5_flow_table *ft,
- struct mlx5_flow_spec *spec,
- u32 action,
- u32 flow_tag,
- struct mlx5_flow_destination *dest);
-void mlx5_del_flow_rule(struct mlx5_flow_rule *fr);
-
-int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
- struct mlx5_flow_destination *dest);
-
-struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_rule *rule);
+struct mlx5_flow_handle *
+mlx5_add_flow_rules(struct mlx5_flow_table *ft,
+ struct mlx5_flow_spec *spec,
+ u32 action,
+ u32 flow_tag,
+ struct mlx5_flow_destination *dest,
+ int dest_num);
+void mlx5_del_flow_rules(struct mlx5_flow_handle *fr);
+
+int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler,
+ struct mlx5_flow_destination *new_dest,
+ struct mlx5_flow_destination *old_dest);
+
+struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handler);
struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
void mlx5_fc_query_cached(struct mlx5_fc *counter,
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH for-next V2 12/15] net/mlx5: Group similer rules under the same fte
From: Saeed Mahameed @ 2016-10-30 21:22 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Or Gerlitz, Leon Romanovsky, Tal Alon, Matan Barak, Mark Bloch,
Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
When adding a new rule, if we can match it with compare_match_value and
flow tag we might be able to insert the rule to the same fte.
In order to do that, there must be an overlap between the actions of the
fte and the new rule.
When updating the action of an existing fte, we must tell the firmware
we are doing so.
Signed-off-by: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 22 ++++++++++++++++------
1 file changed, 16 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index fca6937..43d7052 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -920,7 +920,8 @@ static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest)
/* fte should not be deleted while calling this function */
static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte,
struct mlx5_flow_group *fg,
- struct mlx5_flow_destination *dest)
+ struct mlx5_flow_destination *dest,
+ bool update_action)
{
struct mlx5_flow_table *ft;
struct mlx5_flow_rule *rule;
@@ -931,6 +932,9 @@ static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte,
if (!rule)
return ERR_PTR(-ENOMEM);
+ if (update_action)
+ modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+
fs_get_obj(ft, fg->node.parent);
/* Add dest to dests list- we need flow tables to be in the
* end of the list for forward to next prio rules.
@@ -1109,7 +1113,9 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
fs_for_each_fte(fte, fg) {
nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
if (compare_match_value(&fg->mask, match_value, &fte->val) &&
- action == fte->action && flow_tag == fte->flow_tag) {
+ (action & fte->action) && flow_tag == fte->flow_tag) {
+ int old_action = fte->action;
+
rule = find_flow_rule(fte, dest);
if (rule) {
atomic_inc(&rule->node.refcount);
@@ -1117,11 +1123,15 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
unlock_ref_node(&fg->node);
return rule;
}
- rule = add_rule_fte(fte, fg, dest);
- if (IS_ERR(rule))
+ fte->action |= action;
+ rule = add_rule_fte(fte, fg, dest,
+ old_action != action);
+ if (IS_ERR(rule)) {
+ fte->action = old_action;
goto unlock_fte;
- else
+ } else {
goto add_rule;
+ }
}
unlock_ref_node(&fte->node);
}
@@ -1138,7 +1148,7 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
}
tree_init_node(&fte->node, 0, del_fte);
nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
- rule = add_rule_fte(fte, fg, dest);
+ rule = add_rule_fte(fte, fg, dest, false);
if (IS_ERR(rule)) {
kfree(fte);
goto unlock_fg;
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH for-next V2 11/15] net/mlx5: Refactor find_flow_rule
From: Saeed Mahameed @ 2016-10-30 21:22 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Or Gerlitz, Leon Romanovsky, Tal Alon, Matan Barak, Mark Bloch,
Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
The way we compare between two dests will need to be used in other
places in the future, so we factor out the comparison logic
between two dests into a separate function.
Signed-off-by: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 29 ++++++++++++++++-------
1 file changed, 20 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index e2bab9d..fca6937 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -153,6 +153,8 @@ static void del_rule(struct fs_node *node);
static void del_flow_table(struct fs_node *node);
static void del_flow_group(struct fs_node *node);
static void del_fte(struct fs_node *node);
+static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
+ struct mlx5_flow_destination *d2);
static void tree_init_node(struct fs_node *node,
unsigned int refcount,
@@ -1064,21 +1066,30 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft,
return fg;
}
+static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
+ struct mlx5_flow_destination *d2)
+{
+ if (d1->type == d2->type) {
+ if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+ d1->vport_num == d2->vport_num) ||
+ (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
+ d1->ft == d2->ft) ||
+ (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
+ d1->tir_num == d2->tir_num))
+ return true;
+ }
+
+ return false;
+}
+
static struct mlx5_flow_rule *find_flow_rule(struct fs_fte *fte,
struct mlx5_flow_destination *dest)
{
struct mlx5_flow_rule *rule;
list_for_each_entry(rule, &fte->node.children, node.list) {
- if (rule->dest_attr.type == dest->type) {
- if ((dest->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
- dest->vport_num == rule->dest_attr.vport_num) ||
- (dest->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
- dest->ft == rule->dest_attr.ft) ||
- (dest->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
- dest->tir_num == rule->dest_attr.tir_num))
- return rule;
- }
+ if (mlx5_flow_dests_cmp(&rule->dest_attr, dest))
+ return rule;
}
return NULL;
}
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH for-next V2 10/15] net/mlx5: Use fte status to decide on firmware command
From: Saeed Mahameed @ 2016-10-30 21:22 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Or Gerlitz, Leon Romanovsky, Tal Alon, Matan Barak, Mark Bloch,
Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
An fte status becomes FS_FTE_STATUS_EXISTING only after it was
created in HW. We can use this in order to simplify the logic on
what firmware command to use. If the status isn't FS_FTE_STATUS_EXISTING
we need to create the fte, otherwise we need only to update it.
Signed-off-by: Mark Bloch <markb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index a07ff30..e2bab9d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -946,7 +946,7 @@ static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte,
BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
}
- if (fte->dests_size == 1 || !dest)
+ if (!(fte->status & FS_FTE_STATUS_EXISTING))
err = mlx5_cmd_create_fte(get_dev(&ft->node),
ft, fg->id, fte);
else
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH for-next V2 09/15] net/mlx5: Don't unlock fte while still using it
From: Saeed Mahameed @ 2016-10-30 21:22 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Or Gerlitz, Leon Romanovsky, Tal Alon,
Matan Barak, Mark Bloch, Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm@mellanox.com>
From: Mark Bloch <markb@mellanox.com>
When adding a new rule to an fte, we need to hold the fte lock
until we add that rule to the fte and increase the fte ref count.
Fixes: 0c56b97503fd ("net/mlx5_core: Introduce flow steering API")
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 5da2cc8..a07ff30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1107,9 +1107,8 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
return rule;
}
rule = add_rule_fte(fte, fg, dest);
- unlock_ref_node(&fte->node);
if (IS_ERR(rule))
- goto unlock_fg;
+ goto unlock_fte;
else
goto add_rule;
}
@@ -1127,6 +1126,7 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
goto unlock_fg;
}
tree_init_node(&fte->node, 0, del_fte);
+ nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
rule = add_rule_fte(fte, fg, dest);
if (IS_ERR(rule)) {
kfree(fte);
@@ -1139,6 +1139,8 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
list_add(&fte->node.list, prev);
add_rule:
tree_add_node(&rule->node, &fte->node);
+unlock_fte:
+ unlock_ref_node(&fte->node);
unlock_fg:
unlock_ref_node(&fg->node);
return rule;
--
2.7.4
^ permalink raw reply related
* [PATCH for-next V2 08/15] net/mlx5: Add SRIOV VF max rate configuration support
From: Saeed Mahameed @ 2016-10-30 21:22 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Or Gerlitz, Leon Romanovsky, Tal Alon,
Matan Barak, Mohamad Haj Yahia, Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm@mellanox.com>
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Implement the vf set rate ndo by modifying the TSAR vport rate limit.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 ++++++
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 63 +++++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 2 +
3 files changed, 80 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7eaf380..7f763d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2945,6 +2945,20 @@ static int mlx5e_set_vf_trust(struct net_device *dev, int vf, bool setting)
return mlx5_eswitch_set_vport_trust(mdev->priv.eswitch, vf + 1, setting);
}
+
+static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
+ int max_tx_rate)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5_core_dev *mdev = priv->mdev;
+
+ if (min_tx_rate)
+ return -EOPNOTSUPP;
+
+ return mlx5_eswitch_set_vport_rate(mdev->priv.eswitch, vf + 1,
+ max_tx_rate);
+}
+
static int mlx5_vport_link2ifla(u8 esw_link)
{
switch (esw_link) {
@@ -3252,6 +3266,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
.ndo_set_vf_vlan = mlx5e_set_vf_vlan,
.ndo_set_vf_spoofchk = mlx5e_set_vf_spoofchk,
.ndo_set_vf_trust = mlx5e_set_vf_trust,
+ .ndo_set_vf_rate = mlx5e_set_vf_rate,
.ndo_get_vf_config = mlx5e_get_vf_config,
.ndo_set_vf_link_state = mlx5e_set_vf_link_state,
.ndo_get_vf_stats = mlx5e_get_vf_stats,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 2e11a94..9ef01d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1451,6 +1451,47 @@ static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
vport->qos.enabled = false;
}
+static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num,
+ u32 max_rate)
+{
+ u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+ struct mlx5_vport *vport = &esw->vports[vport_num];
+ struct mlx5_core_dev *dev = esw->dev;
+ void *vport_elem;
+ u32 bitmask = 0;
+ int err = 0;
+
+ if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+ return -EOPNOTSUPP;
+
+ if (!vport->qos.enabled)
+ return -EIO;
+
+ MLX5_SET(scheduling_context, &sched_ctx, element_type,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+ vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx,
+ element_attributes);
+ MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+ MLX5_SET(scheduling_context, &sched_ctx, parent_element_id,
+ esw->qos.root_tsar_id);
+ MLX5_SET(scheduling_context, &sched_ctx, max_average_bw,
+ max_rate);
+ bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
+
+ err = mlx5_modify_scheduling_element_cmd(dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ &sched_ctx,
+ vport->qos.esw_tsar_ix,
+ bitmask);
+ if (err) {
+ esw_warn(esw->dev, "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n",
+ vport_num, err);
+ return err;
+ }
+
+ return 0;
+}
+
static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
{
((u8 *)node_guid)[7] = mac[0];
@@ -1888,6 +1929,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
ivi->qos = evport->info.qos;
ivi->spoofchk = evport->info.spoofchk;
ivi->trusted = evport->info.trusted;
+ ivi->max_tx_rate = evport->info.max_rate;
mutex_unlock(&esw->state_lock);
return 0;
@@ -1981,6 +2023,27 @@ int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
return 0;
}
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw,
+ int vport, u32 max_rate)
+{
+ struct mlx5_vport *evport;
+ int err = 0;
+
+ if (!ESW_ALLOWED(esw))
+ return -EPERM;
+ if (!LEGAL_VPORT(esw, vport))
+ return -EINVAL;
+
+ mutex_lock(&esw->state_lock);
+ evport = &esw->vports[vport];
+ err = esw_vport_qos_config(esw, vport, max_rate);
+ if (!err)
+ evport->info.max_rate = max_rate;
+
+ mutex_unlock(&esw->state_lock);
+ return err;
+}
+
int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
int vport,
struct ifla_vf_stats *vf_stats)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index fb8de34..ddae90c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -246,6 +246,8 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
int vport, bool spoofchk);
int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
int vport_num, bool setting);
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw,
+ int vport, u32 max_rate);
int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
int vport, struct ifla_vf_info *ivi);
int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
--
2.7.4
^ permalink raw reply related
* [PATCH for-next V2 07/15] net/mlx5: Introduce E-switch QoS management
From: Saeed Mahameed @ 2016-10-30 21:22 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Or Gerlitz, Leon Romanovsky, Tal Alon,
Matan Barak, Mohamad Haj Yahia, Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm@mellanox.com>
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Add TSAR to the eswitch which will act as the vports rate limiter.
Create/Destroy TSAR on Enable/Dsiable SRIOV.
Attach/Detach vport to eswitch TSAR on Enable/Disable vport.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 113 +++++++++++++++++++++-
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 12 +++
2 files changed, 124 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index abbf2c3..2e11a94 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1351,6 +1351,106 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
return err;
}
+/* Vport QoS management */
+static int esw_create_tsar(struct mlx5_eswitch *esw)
+{
+ u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+ struct mlx5_core_dev *dev = esw->dev;
+ int err;
+
+ if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+ return 0;
+
+ if (esw->qos.enabled)
+ return -EEXIST;
+
+ err = mlx5_create_scheduling_element_cmd(dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ &tsar_ctx,
+ &esw->qos.root_tsar_id);
+ if (err) {
+ esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err);
+ return err;
+ }
+
+ esw->qos.enabled = true;
+ return 0;
+}
+
+static void esw_destroy_tsar(struct mlx5_eswitch *esw)
+{
+ int err;
+
+ if (!esw->qos.enabled)
+ return;
+
+ err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ esw->qos.root_tsar_id);
+ if (err)
+ esw_warn(esw->dev, "E-Switch destroy TSAR failed (%d)\n", err);
+
+ esw->qos.enabled = false;
+}
+
+static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
+ u32 initial_max_rate)
+{
+ u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+ struct mlx5_vport *vport = &esw->vports[vport_num];
+ struct mlx5_core_dev *dev = esw->dev;
+ void *vport_elem;
+ int err = 0;
+
+ if (!esw->qos.enabled || !MLX5_CAP_GEN(dev, qos) ||
+ !MLX5_CAP_QOS(dev, esw_scheduling))
+ return 0;
+
+ if (vport->qos.enabled)
+ return -EEXIST;
+
+ MLX5_SET(scheduling_context, &sched_ctx, element_type,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+ vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx,
+ element_attributes);
+ MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+ MLX5_SET(scheduling_context, &sched_ctx, parent_element_id,
+ esw->qos.root_tsar_id);
+ MLX5_SET(scheduling_context, &sched_ctx, max_average_bw,
+ initial_max_rate);
+
+ err = mlx5_create_scheduling_element_cmd(dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ &sched_ctx,
+ &vport->qos.esw_tsar_ix);
+ if (err) {
+ esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n",
+ vport_num, err);
+ return err;
+ }
+
+ vport->qos.enabled = true;
+ return 0;
+}
+
+static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
+{
+ struct mlx5_vport *vport = &esw->vports[vport_num];
+ int err = 0;
+
+ if (!vport->qos.enabled)
+ return;
+
+ err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ vport->qos.esw_tsar_ix);
+ if (err)
+ esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n",
+ vport_num, err);
+
+ vport->qos.enabled = false;
+}
+
static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
{
((u8 *)node_guid)[7] = mac[0];
@@ -1386,6 +1486,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
esw_vport_egress_config(esw, vport);
}
}
+
static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
int enable_events)
{
@@ -1399,6 +1500,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
/* Restore old vport configuration */
esw_apply_vport_conf(esw, vport);
+ /* Attach vport to the eswitch rate limiter */
+ if (esw_vport_enable_qos(esw, vport_num, vport->info.max_rate))
+ esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num);
+
/* Sync with current vport context */
vport->enabled_events = enable_events;
vport->enabled = true;
@@ -1437,7 +1542,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
*/
esw_vport_change_handle_locked(vport);
vport->enabled_events = 0;
-
+ esw_vport_disable_qos(esw, vport_num);
if (vport_num && esw->mode == SRIOV_LEGACY) {
mlx5_modify_vport_admin_state(esw->dev,
MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
@@ -1483,6 +1588,10 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
if (err)
goto abort;
+ err = esw_create_tsar(esw);
+ if (err)
+ esw_warn(esw->dev, "Failed to create eswitch TSAR");
+
enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : UC_ADDR_CHANGE;
for (i = 0; i <= nvfs; i++)
esw_enable_vport(esw, i, enabled_events);
@@ -1519,6 +1628,8 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
if (mc_promisc && mc_promisc->uplink_rule)
mlx5_del_flow_rule(mc_promisc->uplink_rule);
+ esw_destroy_tsar(esw);
+
if (esw->mode == SRIOV_LEGACY)
esw_destroy_legacy_fdb_table(esw);
else if (esw->mode == SRIOV_OFFLOADS)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 2e2938e..fb8de34 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -115,6 +115,7 @@ struct mlx5_vport_info {
u8 qos;
u64 node_guid;
int link_state;
+ u32 max_rate;
bool spoofchk;
bool trusted;
};
@@ -133,6 +134,11 @@ struct mlx5_vport {
struct mlx5_vport_info info;
+ struct {
+ bool enabled;
+ u32 esw_tsar_ix;
+ } qos;
+
bool enabled;
u16 enabled_events;
};
@@ -209,6 +215,12 @@ struct mlx5_eswitch {
*/
struct mutex state_lock;
struct esw_mc_addr *mc_promisc;
+
+ struct {
+ bool enabled;
+ u32 root_tsar_id;
+ } qos;
+
struct mlx5_esw_offload offloads;
int mode;
};
--
2.7.4
^ permalink raw reply related
* [PATCH for-next V2 06/15] net/mlx5: Introduce TSAR manipulation firmware commands
From: Saeed Mahameed @ 2016-10-30 21:21 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Or Gerlitz, Leon Romanovsky, Tal Alon, Matan Barak,
Mohamad Haj Yahia, Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Mohamad Haj Yahia <mohamad-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
TSAR (stands for Transmit Scheduling ARbiter) is a hardware component
that is responsible for selecting the next entity to serve on the
transmit path.
The arbitration defines the QoS policy between the agents connected to
the TSAR.
The TSAR is a consist two main features:
1) BW Allocation between agents:
The TSAR implements a defecit weighted round robin between the agents.
Each agent attached to the TSAR is assigned with a weight and it is
awarded transmission tokens according to this weight.
2) Rate limer per agent:
Each agent attached to the TSAR is (optionally) assigned with a rate
limit.
TSAR will not allow scheduling for an agent exceeding its defined rate
limit.
In this patch we implement the API of manipulating the TSAR.
Signed-off-by: Mohamad Haj Yahia <mohamad-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 13 +-
.../net/ethernet/mellanox/mlx5/core/mlx5_core.h | 7 +
drivers/net/ethernet/mellanox/mlx5/core/rl.c | 65 +++++++
include/linux/mlx5/mlx5_ifc.h | 199 ++++++++++++++++++++-
4 files changed, 279 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 1e639f8..8561102 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -318,6 +318,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
case MLX5_CMD_OP_DEALLOC_ENCAP_HEADER:
+ case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT:
return MLX5_CMD_STAT_OK;
case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -419,11 +421,14 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_QUERY_FLOW_TABLE:
case MLX5_CMD_OP_CREATE_FLOW_GROUP:
case MLX5_CMD_OP_QUERY_FLOW_GROUP:
-
case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY:
case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
case MLX5_CMD_OP_ALLOC_ENCAP_HEADER:
+ case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_CREATE_QOS_PARA_VPORT:
*status = MLX5_DRIVER_STATUS_ABORTED;
*synd = MLX5_DRIVER_SYND;
return -EIO;
@@ -580,6 +585,12 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE);
MLX5_COMMAND_STR_CASE(ALLOC_ENCAP_HEADER);
MLX5_COMMAND_STR_CASE(DEALLOC_ENCAP_HEADER);
+ MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(QUERY_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(MODIFY_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(CREATE_QOS_PARA_VPORT);
+ MLX5_COMMAND_STR_CASE(DESTROY_QOS_PARA_VPORT);
default: return "unknown command opcode";
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 3d0cfb9..bf43171 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -91,6 +91,13 @@ int mlx5_core_sriov_configure(struct pci_dev *dev, int num_vfs);
bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev);
int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id);
int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id);
+int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ void *context, u32 *element_id);
+int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ void *context, u32 element_id,
+ u32 modify_bitmask);
+int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ u32 element_id);
int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev);
u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index 104902a..e651e4c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -36,6 +36,71 @@
#include <linux/mlx5/cmd.h>
#include "mlx5_core.h"
+/* Scheduling element fw management */
+int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ void *ctx, u32 *element_id)
+{
+ u32 in[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {0};
+ void *schedc;
+ int err;
+
+ schedc = MLX5_ADDR_OF(create_scheduling_element_in, in,
+ scheduling_context);
+ MLX5_SET(create_scheduling_element_in, in, opcode,
+ MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT);
+ MLX5_SET(create_scheduling_element_in, in, scheduling_hierarchy,
+ hierarchy);
+ memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context));
+
+ err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+ if (err)
+ return err;
+
+ *element_id = MLX5_GET(create_scheduling_element_out, out,
+ scheduling_element_id);
+ return 0;
+}
+
+int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ void *ctx, u32 element_id,
+ u32 modify_bitmask)
+{
+ u32 in[MLX5_ST_SZ_DW(modify_scheduling_element_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(modify_scheduling_element_in)] = {0};
+ void *schedc;
+
+ schedc = MLX5_ADDR_OF(modify_scheduling_element_in, in,
+ scheduling_context);
+ MLX5_SET(modify_scheduling_element_in, in, opcode,
+ MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT);
+ MLX5_SET(modify_scheduling_element_in, in, scheduling_element_id,
+ element_id);
+ MLX5_SET(modify_scheduling_element_in, in, modify_bitmask,
+ modify_bitmask);
+ MLX5_SET(modify_scheduling_element_in, in, scheduling_hierarchy,
+ hierarchy);
+ memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context));
+
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ u32 element_id)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_scheduling_element_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(destroy_scheduling_element_in)] = {0};
+
+ MLX5_SET(destroy_scheduling_element_in, in, opcode,
+ MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT);
+ MLX5_SET(destroy_scheduling_element_in, in, scheduling_element_id,
+ element_id);
+ MLX5_SET(destroy_scheduling_element_in, in, scheduling_hierarchy,
+ hierarchy);
+
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
/* Finds an entry where we can register the given rate
* If the rate already exists, return the entry where it is registered,
* otherwise return the first available entry.
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 12f72e4..2632cb2 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -145,6 +145,12 @@ enum {
MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773,
MLX5_CMD_OP_SET_RATE_LIMIT = 0x780,
MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781,
+ MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782,
+ MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT = 0x783,
+ MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT = 0x784,
+ MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT = 0x785,
+ MLX5_CMD_OP_CREATE_QOS_PARA_VPORT = 0x786,
+ MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT = 0x787,
MLX5_CMD_OP_ALLOC_PD = 0x800,
MLX5_CMD_OP_DEALLOC_PD = 0x801,
MLX5_CMD_OP_ALLOC_UAR = 0x802,
@@ -537,13 +543,27 @@ struct mlx5_ifc_e_switch_cap_bits {
struct mlx5_ifc_qos_cap_bits {
u8 packet_pacing[0x1];
- u8 reserved_0[0x1f];
- u8 reserved_1[0x20];
+ u8 esw_scheduling[0x1];
+ u8 reserved_at_2[0x1e];
+
+ u8 reserved_at_20[0x20];
+
u8 packet_pacing_max_rate[0x20];
+
u8 packet_pacing_min_rate[0x20];
- u8 reserved_2[0x10];
+
+ u8 reserved_at_80[0x10];
u8 packet_pacing_rate_table_size[0x10];
- u8 reserved_3[0x760];
+
+ u8 esw_element_type[0x10];
+ u8 esw_tsar_type[0x10];
+
+ u8 reserved_at_c0[0x10];
+ u8 max_qos_para_vport[0x10];
+
+ u8 max_tsar_bw_share[0x20];
+
+ u8 reserved_at_100[0x700];
};
struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
@@ -2333,6 +2353,30 @@ struct mlx5_ifc_sqc_bits {
struct mlx5_ifc_wq_bits wq;
};
+enum {
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR = 0x0,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT = 0x1,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC = 0x2,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3,
+};
+
+struct mlx5_ifc_scheduling_context_bits {
+ u8 element_type[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 element_attributes[0x20];
+
+ u8 parent_element_id[0x20];
+
+ u8 reserved_at_60[0x40];
+
+ u8 bw_share[0x20];
+
+ u8 max_average_bw[0x20];
+
+ u8 reserved_at_e0[0x120];
+};
+
struct mlx5_ifc_rqtc_bits {
u8 reserved_at_0[0xa0];
@@ -2920,6 +2964,29 @@ struct mlx5_ifc_register_loopback_control_bits {
u8 reserved_at_20[0x60];
};
+struct mlx5_ifc_vport_tc_element_bits {
+ u8 traffic_class[0x4];
+ u8 reserved_at_4[0xc];
+ u8 vport_number[0x10];
+};
+
+struct mlx5_ifc_vport_element_bits {
+ u8 reserved_at_0[0x10];
+ u8 vport_number[0x10];
+};
+
+enum {
+ TSAR_ELEMENT_TSAR_TYPE_DWRR = 0x0,
+ TSAR_ELEMENT_TSAR_TYPE_ROUND_ROBIN = 0x1,
+ TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2,
+};
+
+struct mlx5_ifc_tsar_element_bits {
+ u8 reserved_at_0[0x8];
+ u8 tsar_type[0x8];
+ u8 reserved_at_10[0x10];
+};
+
struct mlx5_ifc_teardown_hca_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -3540,6 +3607,39 @@ struct mlx5_ifc_query_special_contexts_in_bits {
u8 reserved_at_40[0x40];
};
+struct mlx5_ifc_query_scheduling_element_out_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_at_40[0xc0];
+
+ struct mlx5_ifc_scheduling_context_bits scheduling_context;
+
+ u8 reserved_at_300[0x100];
+};
+
+enum {
+ SCHEDULING_HIERARCHY_E_SWITCH = 0x2,
+};
+
+struct mlx5_ifc_query_scheduling_element_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 scheduling_hierarchy[0x8];
+ u8 reserved_at_48[0x18];
+
+ u8 scheduling_element_id[0x20];
+
+ u8 reserved_at_80[0x180];
+};
+
struct mlx5_ifc_query_rqt_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -4725,6 +4825,43 @@ struct mlx5_ifc_modify_sq_in_bits {
struct mlx5_ifc_sqc_bits ctx;
};
+struct mlx5_ifc_modify_scheduling_element_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x1c0];
+};
+
+enum {
+ MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE = 0x1,
+ MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW = 0x2,
+};
+
+struct mlx5_ifc_modify_scheduling_element_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 scheduling_hierarchy[0x8];
+ u8 reserved_at_48[0x18];
+
+ u8 scheduling_element_id[0x20];
+
+ u8 reserved_at_80[0x20];
+
+ u8 modify_bitmask[0x20];
+
+ u8 reserved_at_c0[0x40];
+
+ struct mlx5_ifc_scheduling_context_bits scheduling_context;
+
+ u8 reserved_at_300[0x100];
+};
+
struct mlx5_ifc_modify_rqt_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -5390,6 +5527,30 @@ struct mlx5_ifc_destroy_sq_in_bits {
u8 reserved_at_60[0x20];
};
+struct mlx5_ifc_destroy_scheduling_element_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x1c0];
+};
+
+struct mlx5_ifc_destroy_scheduling_element_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 scheduling_hierarchy[0x8];
+ u8 reserved_at_48[0x18];
+
+ u8 scheduling_element_id[0x20];
+
+ u8 reserved_at_80[0x180];
+};
+
struct mlx5_ifc_destroy_rqt_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -6017,6 +6178,36 @@ struct mlx5_ifc_create_sq_in_bits {
struct mlx5_ifc_sqc_bits ctx;
};
+struct mlx5_ifc_create_scheduling_element_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+
+ u8 scheduling_element_id[0x20];
+
+ u8 reserved_at_a0[0x160];
+};
+
+struct mlx5_ifc_create_scheduling_element_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 scheduling_hierarchy[0x8];
+ u8 reserved_at_48[0x18];
+
+ u8 reserved_at_60[0xa0];
+
+ struct mlx5_ifc_scheduling_context_bits scheduling_context;
+
+ u8 reserved_at_300[0x100];
+};
+
struct mlx5_ifc_create_rqt_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH for-next V2 05/15] net/mlx5: Add ConnectX-5 PCIe 4.0 VF device ID
From: Saeed Mahameed @ 2016-10-30 21:21 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Or Gerlitz, Leon Romanovsky, Tal Alon,
Matan Barak, Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm@mellanox.com>
For the mlx5 driver to support ConnectX-5 PCIe 4.0 VFs, we add the
device ID "0x101a" to mlx5_core_pci_table.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d9c3c70..197e04c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1422,6 +1422,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
{ PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5, PCIe 3.0 */
{ PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */
{ PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5, PCIe 4.0 */
+ { PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5, PCIe 4.0 VF */
{ 0, }
};
--
2.7.4
^ permalink raw reply related
* [PATCH for-next V2 04/15] net/mlx5: Fix length of async_event_mask
From: Saeed Mahameed @ 2016-10-30 21:21 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Or Gerlitz, Leon Romanovsky, Tal Alon, Matan Barak,
Eugenia Emantayev, Saeed Mahameed, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Eugenia Emantayev <eugenia-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
According to PRM async_event_mask have to be 64 bits long.
Signed-off-by: Eugenia Emantayev <eugenia-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index aaca090..e74a73b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -469,7 +469,7 @@ void mlx5_eq_cleanup(struct mlx5_core_dev *dev)
int mlx5_start_eqs(struct mlx5_core_dev *dev)
{
struct mlx5_eq_table *table = &dev->priv.eq_table;
- u32 async_event_mask = MLX5_ASYNC_EVENT_MASK;
+ u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
int err;
if (MLX5_CAP_GEN(dev, pg))
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH for-next V2 03/15] net/mlx5: Ensure SRQ physical address structure endianness
From: Saeed Mahameed @ 2016-10-30 21:21 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Or Gerlitz, Leon Romanovsky, Tal Alon,
Matan Barak, Artemy Kovalyov, Leon Romanovsky, Saeed Mahameed
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm@mellanox.com>
From: Artemy Kovalyov <artemyko@mellanox.com>
SRQ physical address structure field should be in big-endian format.
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
include/linux/mlx5/srq.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h
index 33c97dc..1cde0fd 100644
--- a/include/linux/mlx5/srq.h
+++ b/include/linux/mlx5/srq.h
@@ -55,7 +55,7 @@ struct mlx5_srq_attr {
u32 lwm;
u32 user_index;
u64 db_record;
- u64 *pas;
+ __be64 *pas;
};
struct mlx5_core_dev;
--
2.7.4
^ permalink raw reply related
* [PATCH for-next V2 02/15] net/mlx5: Update struct mlx5_ifc_xrqc_bits
From: Saeed Mahameed @ 2016-10-30 21:21 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev, linux-rdma, Or Gerlitz, Leon Romanovsky, Tal Alon,
Matan Barak, Artemy Kovalyov, Leon Romanovsky, Saeed Mahameed
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm@mellanox.com>
From: Artemy Kovalyov <artemyko@mellanox.com>
Update struct mlx5_ifc_xrqc_bits according to last specification
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
include/linux/mlx5/mlx5_ifc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6045d4d..12f72e4 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -2844,7 +2844,7 @@ struct mlx5_ifc_xrqc_bits {
struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context;
- u8 reserved_at_180[0x200];
+ u8 reserved_at_180[0x880];
struct mlx5_ifc_wq_bits wq;
};
--
2.7.4
^ permalink raw reply related
* [PATCH for-next V2 01/15] IB/mlx5: Skip handling unknown events
From: Saeed Mahameed @ 2016-10-30 21:21 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Or Gerlitz, Leon Romanovsky, Tal Alon, Matan Barak,
Saeed Mahameed, Eugenia Emantayev, Leon Romanovsky
In-Reply-To: <1477862528-4328-1-git-send-email-saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Do not dispatch unknown mlx5 core events on mlx5_ib_event.
Signed-off-by: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Eugenia Emantayev <eugenia-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
drivers/infiniband/hw/mlx5/main.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 2217477..d02341e 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2358,6 +2358,8 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
ibev.event = IB_EVENT_CLIENT_REREGISTER;
port = (u8)param;
break;
+ default:
+ return;
}
ibev.device = &ibdev->ib_dev;
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH for-next V2 00/15][PULL request] Mellanox mlx5 core driver updates 2016-10-25
From: Saeed Mahameed @ 2016-10-30 21:21 UTC (permalink / raw)
To: David S. Miller, Doug Ledford
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Or Gerlitz, Leon Romanovsky, Tal Alon, Matan Barak,
Saeed Mahameed
Hi Dave and Doug,
This series contains some updates and fixes of mlx5 core and
IB drivers with the addition of two features that demand
new low level commands and infrastructure updates.
- SRIOV VF max rate limit support
- mlx5e tc support for FWD rules with counter.
Needed for both net and rdma subsystems.
Updates and Fixes:
>From Saeed Mahameed (2):
- mlx5 IB: Skip handling unknown mlx5 events
- Add ConnectX-5 PCIe 4.0 VF device ID
>From Artemy Kovalyov (2):
- Update struct mlx5_ifc_xrqc_bits
- Ensure SRQ physical address structure endianness
>From Eugenia Emantayev (1):
- Fix length of async_event_mask
New Features:
>From Mohamad Haj Yahia (3): mlx5 SRIOV VF max rate limit support
- Introduce TSAR manipulation firmware commands
- Introduce E-switch QoS management
- Add SRIOV VF max rate configuration support
>From Mark Bloch (7): mlx5e Tc support for FWD rule with counter
- Don't unlock fte while still using it
- Use fte status to decide on firmware command
- Refactor find_flow_rule
- Group similar rules under the same fte
- Add multi dest support
- Add option to add fwd rule with counter
- mlx5e tc support for FWD rule with counter
Mark here fixed two trivial issues with the flow steering core, and did
some refactoring in the flow steering API to support adding mulit destination
rules to the same hardware flow table entry at once. In the last two patches
added the ability to populate a flow rule with a flow counter to the same flow entry.
V2: Dropped some patches that added new structures without adding any usage of them.
Added SRIOV VF max rate configuration support patch that introduces
the usage of the TSAR infrastructure.
Added flow steering fixes and refactoring in addition to mlx5 tc
support for forward rule with counter.
The following changes since commit a909d3e636995ba7c349e2ca5dbb528154d4ac30
Linux 4.9-rc3
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma.git tags/shared-for-4.10-1
for you to fetch changes up to e37a79e5d4cac3831fac3d4afbf2461f56b4b7bd
net/mlx5e: Add tc support for FWD rule with counter
Thanks,
Saeed & Leon.
Artemy Kovalyov (2):
net/mlx5: Update struct mlx5_ifc_xrqc_bits
net/mlx5: Ensure SRQ physical address structure endianness
Eugenia Emantayev (1):
net/mlx5: Fix length of async_event_mask
Mark Bloch (7):
net/mlx5: Don't unlock fte while still using it
net/mlx5: Use fte status to decide on firmware command
net/mlx5: Refactor find_flow_rule
net/mlx5: Group similer rules under the same fte
net/mlx5: Add multi dest support
net/mlx5: Add option to add fwd rule with counter
net/mlx5e: Add tc support for FWD rule with counter
Mohamad Haj Yahia (3):
net/mlx5: Introduce TSAR manipulation firmware commands
net/mlx5: Introduce E-switch QoS management
net/mlx5: Add SRIOV VF max rate configuration support
Saeed Mahameed (2):
IB/mlx5: Skip handling unknown events
net/mlx5: Add ConnectX-5 PCIe 4.0 VF device ID
drivers/infiniband/hw/mlx5/main.c | 16 +-
drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 13 +-
drivers/net/ethernet/mellanox/mlx5/core/en.h | 14 +-
drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 38 +--
drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 49 +--
.../ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 19 +-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 6 +-
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 35 +-
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 244 ++++++++++++--
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 36 ++-
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 60 ++--
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 358 +++++++++++++++------
drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 5 +
drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
.../net/ethernet/mellanox/mlx5/core/mlx5_core.h | 7 +
drivers/net/ethernet/mellanox/mlx5/core/rl.c | 65 ++++
include/linux/mlx5/fs.h | 28 +-
include/linux/mlx5/mlx5_ifc.h | 201 +++++++++++-
include/linux/mlx5/srq.h | 2 +-
22 files changed, 927 insertions(+), 289 deletions(-)
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH v4 10/10] IB/mlx5: Simplify completion into a wait_event
From: Sagi Grimberg @ 2016-10-30 21:17 UTC (permalink / raw)
To: Binoy Jayan, Doug Ledford, Sean Hefty, Hal Rosenstock
Cc: Arnd Bergmann, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1477551554-30349-11-git-send-email-binoy.jayan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
On 27/10/16 09:59, Binoy Jayan wrote:
> Convert the completion 'mlx5_ib_umr_context:done' to a wait_event as it
> just waits for the return value to be filled.
>
> Signed-off-by: Binoy Jayan <binoy.jayan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
> ---
> drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 +-
> drivers/infiniband/hw/mlx5/mr.c | 9 +++++----
> include/rdma/ib_verbs.h | 1 +
> 3 files changed, 7 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
> index de31b5f..cf496b5 100644
> --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
> +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
> @@ -524,7 +524,7 @@ struct mlx5_ib_mw {
> struct mlx5_ib_umr_context {
> struct ib_cqe cqe;
> enum ib_wc_status status;
> - struct completion done;
> + wait_queue_head_t wq;
> };
>
> struct umr_common {
> diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
> index dfaf6f6..49ff2af 100644
> --- a/drivers/infiniband/hw/mlx5/mr.c
> +++ b/drivers/infiniband/hw/mlx5/mr.c
> @@ -846,14 +846,14 @@ static void mlx5_ib_umr_done(struct ib_cq *cq, struct ib_wc *wc)
> container_of(wc->wr_cqe, struct mlx5_ib_umr_context, cqe);
>
> context->status = wc->status;
> - complete(&context->done);
> + wake_up(&context->wq);
> }
>
> static inline void mlx5_ib_init_umr_context(struct mlx5_ib_umr_context *context)
> {
> context->cqe.done = mlx5_ib_umr_done;
> - context->status = -1;
> - init_completion(&context->done);
> + context->status = IB_WC_STATUS_NONE;
> + init_waitqueue_head(&context->wq);
> }
>
> static inline int mlx5_ib_post_send_wait(struct mlx5_ib_dev *dev,
> @@ -873,7 +873,8 @@ static inline int mlx5_ib_post_send_wait(struct mlx5_ib_dev *dev,
> if (err) {
> mlx5_ib_warn(dev, "UMR post send failed, err %d\n", err);
> } else {
> - wait_for_completion(&umr_context.done);
> + wait_event(umr_context.wq,
> + umr_context.status != IB_WC_STATUS_NONE);
How is this simpler?
> enum ib_wc_status {
> + IB_WC_STATUS_NONE = -1,
> IB_WC_SUCCESS,
> IB_WC_LOC_LEN_ERR,
> IB_WC_LOC_QP_OP_ERR,
>
Huh? Where did this bogus status came from? IMHO, this is polluting
the verbs interface for no good reason at all, sorry.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH v4 05/10] IB/isert: Replace semaphore sem with completion
From: Sagi Grimberg @ 2016-10-30 21:12 UTC (permalink / raw)
To: Binoy Jayan, Doug Ledford, Sean Hefty, Hal Rosenstock
Cc: Arnd Bergmann, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1477551554-30349-6-git-send-email-binoy.jayan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
> The semaphore 'sem' in isert_device is used as completion, so convert
> it to struct completion. Semaphores are going away in the future.
Umm, this is 100% *not* true. np->sem is designed as a counting to
sync the iscsi login thread with the connect requests coming from the
initiators. So this is actually a reliable bug insertion :(
NAK from me...
Also, I would appreciate if you include get_maintainer.pl in your
patch submissions so I won't need to fish these in the Linux-rdma
patch traffic.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox