From: Lee Duncan <[email protected]>
iSCSI NOPs are sometimes "lost", mistakenly sent to the
user-land iscsid daemon instead of handled in the kernel,
as they should be, resulting in a message from the daemon like:
> iscsid: Got nop in, but kernel supports nop handling.
This can occur because of the forward- and back-locks
in the kernel iSCSI code, and the fact that an iSCSI NOP
response can be processed before processing of the NOP send
is complete. This can result in "conn->ping_task" being NULL
in iscsi_nop_out_rsp(), when the pointer is actually in
the process of being set.
To work around this, we add a new state to the "ping_task"
pointer. In addition to NULL (not assigned) and a pointer
(assigned), we add the state "being set", which is signaled
with an INVALID pointer (using "-1").
Signed-off-by: Lee Duncan <[email protected]>
---
drivers/scsi/libiscsi.c | 13 ++++++++++---
include/scsi/libiscsi.h | 3 +++
2 files changed, 13 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 1e9c3171fa9f..cade108c33b6 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -738,6 +738,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
task->conn->session->age);
}
+ if (unlikely(READ_ONCE(conn->ping_task) == INVALID_SCSI_TASK))
+ WRITE_ONCE(conn->ping_task, task);
+
if (!ihost->workq) {
if (iscsi_prep_mgmt_task(conn, task))
goto free_task;
@@ -941,8 +944,11 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr)
struct iscsi_nopout hdr;
struct iscsi_task *task;
- if (!rhdr && conn->ping_task)
- return -EINVAL;
+ if (!rhdr) {
+ if (READ_ONCE(conn->ping_task))
+ return -EINVAL;
+ WRITE_ONCE(conn->ping_task, INVALID_SCSI_TASK);
+ }
memset(&hdr, 0, sizeof(struct iscsi_nopout));
hdr.opcode = ISCSI_OP_NOOP_OUT | ISCSI_OP_IMMEDIATE;
@@ -957,11 +963,12 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr)
task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)&hdr, NULL, 0);
if (!task) {
+ if (!rhdr)
+ WRITE_ONCE(conn->ping_task, NULL);
iscsi_conn_printk(KERN_ERR, conn, "Could not send nopout\n");
return -EIO;
} else if (!rhdr) {
/* only track our nops */
- conn->ping_task = task;
conn->last_ping = jiffies;
}
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index c25fb86ffae9..b3bbd10eb3f0 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -132,6 +132,9 @@ struct iscsi_task {
void *dd_data; /* driver/transport data */
};
+/* invalid scsi_task pointer */
+#define INVALID_SCSI_TASK (struct iscsi_task *)-1l
+
static inline int iscsi_task_has_unsol_data(struct iscsi_task *task)
{
return task->unsol_r2t.data_length > task->unsol_r2t.sent;
--
2.26.2
On 9/25/20 11:41 AM, [email protected] wrote:
> From: Lee Duncan <[email protected]>
>
> iSCSI NOPs are sometimes "lost", mistakenly sent to the
> user-land iscsid daemon instead of handled in the kernel,
> as they should be, resulting in a message from the daemon like:
>
>> iscsid: Got nop in, but kernel supports nop handling.
>
> This can occur because of the forward- and back-locks
> in the kernel iSCSI code, and the fact that an iSCSI NOP
> response can be processed before processing of the NOP send
> is complete. This can result in "conn->ping_task" being NULL
> in iscsi_nop_out_rsp(), when the pointer is actually in
> the process of being set.
>
> To work around this, we add a new state to the "ping_task"
> pointer. In addition to NULL (not assigned) and a pointer
> (assigned), we add the state "being set", which is signaled
> with an INVALID pointer (using "-1").
>
> Signed-off-by: Lee Duncan <[email protected]>
> ---
> drivers/scsi/libiscsi.c | 13 ++++++++++---
> include/scsi/libiscsi.h | 3 +++
> 2 files changed, 13 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
> index 1e9c3171fa9f..cade108c33b6 100644
> --- a/drivers/scsi/libiscsi.c
> +++ b/drivers/scsi/libiscsi.c
> @@ -738,6 +738,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
> task->conn->session->age);
> }
>
> + if (unlikely(READ_ONCE(conn->ping_task) == INVALID_SCSI_TASK))
> + WRITE_ONCE(conn->ping_task, task);
> +
> if (!ihost->workq) {
> if (iscsi_prep_mgmt_task(conn, task))
> goto free_task;
> @@ -941,8 +944,11 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr)
> struct iscsi_nopout hdr;
> struct iscsi_task *task;
>
> - if (!rhdr && conn->ping_task)
> - return -EINVAL;
> + if (!rhdr) {
> + if (READ_ONCE(conn->ping_task))
> + return -EINVAL;
> + WRITE_ONCE(conn->ping_task, INVALID_SCSI_TASK);
> + }
>
> memset(&hdr, 0, sizeof(struct iscsi_nopout));
> hdr.opcode = ISCSI_OP_NOOP_OUT | ISCSI_OP_IMMEDIATE;
> @@ -957,11 +963,12 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr)
>
> task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)&hdr, NULL, 0);
> if (!task) {
> + if (!rhdr)
> + WRITE_ONCE(conn->ping_task, NULL);
> iscsi_conn_printk(KERN_ERR, conn, "Could not send nopout\n");
> return -EIO;
> } else if (!rhdr) {
> /* only track our nops */
> - conn->ping_task = task;
> conn->last_ping = jiffies;
> }
>
> diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
> index c25fb86ffae9..b3bbd10eb3f0 100644
> --- a/include/scsi/libiscsi.h
> +++ b/include/scsi/libiscsi.h
> @@ -132,6 +132,9 @@ struct iscsi_task {
> void *dd_data; /* driver/transport data */
> };
>
> +/* invalid scsi_task pointer */
> +#define INVALID_SCSI_TASK (struct iscsi_task *)-1l
> +
> static inline int iscsi_task_has_unsol_data(struct iscsi_task *task)
> {
> return task->unsol_r2t.data_length > task->unsol_r2t.sent;
>
Ping?
--
Lee Duncan
On 9/25/20 1:41 PM, [email protected] wrote:
> From: Lee Duncan <[email protected]>
>
> iSCSI NOPs are sometimes "lost", mistakenly sent to the
> user-land iscsid daemon instead of handled in the kernel,
> as they should be, resulting in a message from the daemon like:
>
>> iscsid: Got nop in, but kernel supports nop handling.
>
> This can occur because of the forward- and back-locks
> in the kernel iSCSI code, and the fact that an iSCSI NOP
> response can be processed before processing of the NOP send
> is complete. This can result in "conn->ping_task" being NULL
> in iscsi_nop_out_rsp(), when the pointer is actually in
> the process of being set.
>
> To work around this, we add a new state to the "ping_task"
> pointer. In addition to NULL (not assigned) and a pointer
> (assigned), we add the state "being set", which is signaled
> with an INVALID pointer (using "-1").
>
> Signed-off-by: Lee Duncan <[email protected]>
> ---
> drivers/scsi/libiscsi.c | 13 ++++++++++---
> include/scsi/libiscsi.h | 3 +++
> 2 files changed, 13 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
> index 1e9c3171fa9f..cade108c33b6 100644
> --- a/drivers/scsi/libiscsi.c
> +++ b/drivers/scsi/libiscsi.c
> @@ -738,6 +738,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
> task->conn->session->age);
> }
>
> + if (unlikely(READ_ONCE(conn->ping_task) == INVALID_SCSI_TASK))
> + WRITE_ONCE(conn->ping_task, task);
> +
> if (!ihost->workq) {
> if (iscsi_prep_mgmt_task(conn, task))
> goto free_task;
I think the API gets a little weird now where in some cases
__iscsi_conn_send_pdu checks the opcode to see what type of request
it is but above we the caller sets the ping_task.
For login, tmfs and passthrough, we assume the __iscsi_conn_send_pdu
has sent or cleaned up everything. I think it might be nicer to just
have __iscsi_conn_send_pdu set the ping_task field before doing the
xmit/queue call. It would then work similar to the conn->login_task
case where that function knows about that special task too.
So in __iscsi_conn_send_pdu add a "if (opcode == ISCSI_OP_NOOP_OUT)",
and check if it's a nop we need to track. If so set conn->ping_task.
On 10/8/20 12:11 PM, Mike Christie wrote:
> On 9/25/20 1:41 PM, [email protected] wrote:
>> From: Lee Duncan <[email protected]>
>>
>> iSCSI NOPs are sometimes "lost", mistakenly sent to the
>> user-land iscsid daemon instead of handled in the kernel,
>> as they should be, resulting in a message from the daemon like:
>>
>>> iscsid: Got nop in, but kernel supports nop handling.
>>
>> This can occur because of the forward- and back-locks
>> in the kernel iSCSI code, and the fact that an iSCSI NOP
>> response can be processed before processing of the NOP send
>> is complete. This can result in "conn->ping_task" being NULL
>> in iscsi_nop_out_rsp(), when the pointer is actually in
>> the process of being set.
>>
>> To work around this, we add a new state to the "ping_task"
>> pointer. In addition to NULL (not assigned) and a pointer
>> (assigned), we add the state "being set", which is signaled
>> with an INVALID pointer (using "-1").
>>
>> Signed-off-by: Lee Duncan <[email protected]>
>> ---
>> drivers/scsi/libiscsi.c | 13 ++++++++++---
>> include/scsi/libiscsi.h | 3 +++
>> 2 files changed, 13 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
>> index 1e9c3171fa9f..cade108c33b6 100644
>> --- a/drivers/scsi/libiscsi.c
>> +++ b/drivers/scsi/libiscsi.c
>> @@ -738,6 +738,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
>> task->conn->session->age);
>> }
>>
>> + if (unlikely(READ_ONCE(conn->ping_task) == INVALID_SCSI_TASK))
>> + WRITE_ONCE(conn->ping_task, task);
>> +
>> if (!ihost->workq) {
>> if (iscsi_prep_mgmt_task(conn, task))
>> goto free_task;
>
> I think the API gets a little weird now where in some cases
> __iscsi_conn_send_pdu checks the opcode to see what type of request
> it is but above we the caller sets the ping_task.
>
> For login, tmfs and passthrough, we assume the __iscsi_conn_send_pdu
> has sent or cleaned up everything. I think it might be nicer to just
> have __iscsi_conn_send_pdu set the ping_task field before doing the
> xmit/queue call. It would then work similar to the conn->login_task
> case where that function knows about that special task too.
>
> So in __iscsi_conn_send_pdu add a "if (opcode == ISCSI_OP_NOOP_OUT)",
> and check if it's a nop we need to track. If so set conn->ping_task.
>
Ignore this. It won't work nicely either. To figure out if the nop is
our internal transport test ping vs a userspace ping that also needs
a reply, we would need to do something like you did above so there is
no point.
On 10/8/20 1:54 PM, Mike Christie wrote:
> On 10/8/20 12:11 PM, Mike Christie wrote:
>> On 9/25/20 1:41 PM, [email protected] wrote:
>>> From: Lee Duncan <[email protected]>
>>>
>>> iSCSI NOPs are sometimes "lost", mistakenly sent to the
>>> user-land iscsid daemon instead of handled in the kernel,
>>> as they should be, resulting in a message from the daemon like:
>>>
>>>> iscsid: Got nop in, but kernel supports nop handling.
>>>
>>> This can occur because of the forward- and back-locks
>>> in the kernel iSCSI code, and the fact that an iSCSI NOP
>>> response can be processed before processing of the NOP send
>>> is complete. This can result in "conn->ping_task" being NULL
>>> in iscsi_nop_out_rsp(), when the pointer is actually in
>>> the process of being set.
>>>
>>> To work around this, we add a new state to the "ping_task"
>>> pointer. In addition to NULL (not assigned) and a pointer
>>> (assigned), we add the state "being set", which is signaled
>>> with an INVALID pointer (using "-1").
>>>
>>> Signed-off-by: Lee Duncan <[email protected]>
>>> ---
>>> drivers/scsi/libiscsi.c | 13 ++++++++++---
>>> include/scsi/libiscsi.h | 3 +++
>>> 2 files changed, 13 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
>>> index 1e9c3171fa9f..cade108c33b6 100644
>>> --- a/drivers/scsi/libiscsi.c
>>> +++ b/drivers/scsi/libiscsi.c
>>> @@ -738,6 +738,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
>>> task->conn->session->age);
>>> }
>>>
>>> + if (unlikely(READ_ONCE(conn->ping_task) == INVALID_SCSI_TASK))
>>> + WRITE_ONCE(conn->ping_task, task);
>>> +
>>> if (!ihost->workq) {
>>> if (iscsi_prep_mgmt_task(conn, task))
>>> goto free_task;
>>
>> I think the API gets a little weird now where in some cases
>> __iscsi_conn_send_pdu checks the opcode to see what type of request
>> it is but above we the caller sets the ping_task.
>>
>> For login, tmfs and passthrough, we assume the __iscsi_conn_send_pdu
>> has sent or cleaned up everything. I think it might be nicer to just
>> have __iscsi_conn_send_pdu set the ping_task field before doing the
>> xmit/queue call. It would then work similar to the conn->login_task
>> case where that function knows about that special task too.
>>
>> So in __iscsi_conn_send_pdu add a "if (opcode == ISCSI_OP_NOOP_OUT)",
>> and check if it's a nop we need to track. If so set conn->ping_task.
>>
> Ignore this. It won't work nicely either. To figure out if the nop is
> our internal transport test ping vs a userspace ping that also needs
> a reply, we would need to do something like you did above so there is
> no point.
>
Hi Mike:
I've read this a few times, and I'm still no sure I'm parsing it correctly.
Are you saying that my original patch submission is ok, or are you
saying there's nothing we can do and we're up the proverbial creek?
--
Lee Duncan