* [PATCH v1 for-rc] RDMA/vmw_pvrdma: Return the correct opcode when creating WR
@ 2019-01-07 23:23 Adit Ranadive
2019-01-07 23:28 ` Jason Gunthorpe
0 siblings, 1 reply; 6+ messages in thread
From: Adit Ranadive @ 2019-01-07 23:23 UTC (permalink / raw)
To: jgg, dledford; +Cc: Adit Ranadive, linux-rdma, Pv-drivers, stable
From: Adit Ranadive <aditr@vmware.com>
Since the IB_WR_REG_MR opcode value changed, let's set the PVRDMA
device opcodes explicitly.
Reported-by: Ruishuang Wang <ruishuangw@vmware.com>
Fixes: 9a59739bd01f ("IB/rxe: Revise the ib_wr_opcode enum")
Cc: stable@vger.kernel.org
Reviewed-by: Bryan Tan <bryantan@vmware.com>
Reviewed-by: Ruishuang Wang <ruishuangw@vmware.com>
Reviewed-by: Vishnu Dasa <vdasa@vmware.com>
Signed-off-by: Adit Ranadive <aditr@vmware.com>
---
drivers/infiniband/hw/vmw_pvrdma/pvrdma.h | 43 +++++++++++++++++++++++++++++++
1 file changed, 43 insertions(+)
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 42b8685c997e..a85d7ba96d55 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -427,6 +427,49 @@ static inline enum ib_qp_state pvrdma_qp_state_to_ib(enum pvrdma_qp_state state)
static inline enum pvrdma_wr_opcode ib_wr_opcode_to_pvrdma(enum ib_wr_opcode op)
{
+ switch (op) {
+ case IB_WR_RDMA_WRITE:
+ return PVRDMA_WR_RDMA_WRITE;
+ case IB_WR_RDMA_WRITE_WITH_IMM:
+ return PVRDMA_WR_RDMA_WRITE_WITH_IMM;
+ case IB_WR_SEND:
+ return PVRDMA_WR_SEND;
+ case IB_WR_SEND_WITH_IMM:
+ return PVRDMA_WR_SEND_WITH_IMM;
+ case IB_WR_RDMA_READ:
+ return PVRDMA_WR_RDMA_READ;
+ case IB_WR_ATOMIC_CMP_AND_SWP:
+ return PVRDMA_WR_ATOMIC_CMP_AND_SWP;
+ case IB_WR_ATOMIC_FETCH_AND_ADD:
+ return PVRDMA_WR_ATOMIC_FETCH_AND_ADD;
+ case IB_WR_LSO:
+ return PVRDMA_WR_LSO;
+ case IB_WR_SEND_WITH_INV:
+ return PVRDMA_WR_SEND_WITH_INV;
+ case IB_WR_RDMA_READ_WITH_INV:
+ return PVRDMA_WR_RDMA_READ_WITH_INV;
+ case IB_WR_LOCAL_INV:
+ return PVRDMA_WR_LOCAL_INV;
+ case IB_WR_REG_MR:
+ return PVRDMA_WR_FAST_REG_MR;
+ case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
+ return PVRDMA_WR_MASKED_ATOMIC_CMP_AND_SWP;
+ case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD:
+ return PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD;
+ case IB_WR_REG_SIG_MR:
+ return PVRDMA_WR_REG_SIG_MR;
+ case IB_WR_RESERVED1:
+ case IB_WR_RESERVED2:
+ case IB_WR_RESERVED3:
+ case IB_WR_RESERVED4:
+ case IB_WR_RESERVED5:
+ case IB_WR_RESERVED6:
+ case IB_WR_RESERVED7:
+ case IB_WR_RESERVED8:
+ case IB_WR_RESERVED9:
+ case IB_WR_RESERVED10:
+ return (enum pvrdma_wr_opcode)op;
+ }
return (enum pvrdma_wr_opcode)op;
}
--
1.8.3.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH v1 for-rc] RDMA/vmw_pvrdma: Return the correct opcode when creating WR
2019-01-07 23:23 [PATCH v1 for-rc] RDMA/vmw_pvrdma: Return the correct opcode when creating WR Adit Ranadive
@ 2019-01-07 23:28 ` Jason Gunthorpe
2019-01-08 0:02 ` Adit Ranadive
0 siblings, 1 reply; 6+ messages in thread
From: Jason Gunthorpe @ 2019-01-07 23:28 UTC (permalink / raw)
To: Adit Ranadive; +Cc: dledford, linux-rdma, Pv-drivers, stable
On Mon, Jan 07, 2019 at 11:23:05PM +0000, Adit Ranadive wrote:
> From: Adit Ranadive <aditr@vmware.com>
>
> Since the IB_WR_REG_MR opcode value changed, let's set the PVRDMA
> device opcodes explicitly.
>
> Reported-by: Ruishuang Wang <ruishuangw@vmware.com>
> Fixes: 9a59739bd01f ("IB/rxe: Revise the ib_wr_opcode enum")
> Cc: stable@vger.kernel.org
> Reviewed-by: Bryan Tan <bryantan@vmware.com>
> Reviewed-by: Ruishuang Wang <ruishuangw@vmware.com>
> Reviewed-by: Vishnu Dasa <vdasa@vmware.com>
> Signed-off-by: Adit Ranadive <aditr@vmware.com>
> drivers/infiniband/hw/vmw_pvrdma/pvrdma.h | 43 +++++++++++++++++++++++++++++++
> 1 file changed, 43 insertions(+)
>
> diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
> index 42b8685c997e..a85d7ba96d55 100644
> +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
> @@ -427,6 +427,49 @@ static inline enum ib_qp_state pvrdma_qp_state_to_ib(enum pvrdma_qp_state state)
>
> static inline enum pvrdma_wr_opcode ib_wr_opcode_to_pvrdma(enum ib_wr_opcode op)
> {
> + switch (op) {
> + case IB_WR_RDMA_WRITE:
> + return PVRDMA_WR_RDMA_WRITE;
> + case IB_WR_RDMA_WRITE_WITH_IMM:
> + return PVRDMA_WR_RDMA_WRITE_WITH_IMM;
> + case IB_WR_SEND:
> + return PVRDMA_WR_SEND;
> + case IB_WR_SEND_WITH_IMM:
> + return PVRDMA_WR_SEND_WITH_IMM;
> + case IB_WR_RDMA_READ:
> + return PVRDMA_WR_RDMA_READ;
> + case IB_WR_ATOMIC_CMP_AND_SWP:
> + return PVRDMA_WR_ATOMIC_CMP_AND_SWP;
> + case IB_WR_ATOMIC_FETCH_AND_ADD:
> + return PVRDMA_WR_ATOMIC_FETCH_AND_ADD;
> + case IB_WR_LSO:
> + return PVRDMA_WR_LSO;
> + case IB_WR_SEND_WITH_INV:
> + return PVRDMA_WR_SEND_WITH_INV;
> + case IB_WR_RDMA_READ_WITH_INV:
> + return PVRDMA_WR_RDMA_READ_WITH_INV;
> + case IB_WR_LOCAL_INV:
> + return PVRDMA_WR_LOCAL_INV;
> + case IB_WR_REG_MR:
> + return PVRDMA_WR_FAST_REG_MR;
> + case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
> + return PVRDMA_WR_MASKED_ATOMIC_CMP_AND_SWP;
> + case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD:
> + return PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD;
> + case IB_WR_REG_SIG_MR:
> + return PVRDMA_WR_REG_SIG_MR;
> + case IB_WR_RESERVED1:
> + case IB_WR_RESERVED2:
> + case IB_WR_RESERVED3:
> + case IB_WR_RESERVED4:
> + case IB_WR_RESERVED5:
> + case IB_WR_RESERVED6:
> + case IB_WR_RESERVED7:
> + case IB_WR_RESERVED8:
> + case IB_WR_RESERVED9:
> + case IB_WR_RESERVED10:
> + return (enum pvrdma_wr_opcode)op;
> + }
> return (enum pvrdma_wr_opcode)op;
I ment it should always translate, not cast like this - if no
translation is available then it should be a posting failure.
Jason
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v1 for-rc] RDMA/vmw_pvrdma: Return the correct opcode when creating WR
2019-01-07 23:28 ` Jason Gunthorpe
@ 2019-01-08 0:02 ` Adit Ranadive
2019-01-08 3:10 ` Jason Gunthorpe
0 siblings, 1 reply; 6+ messages in thread
From: Adit Ranadive @ 2019-01-08 0:02 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: dledford, linux-rdma, Pv-drivers, stable
On 1/7/19 3:28 PM, Jason Gunthorpe wrote:
> On Mon, Jan 07, 2019 at 11:23:05PM +0000, Adit Ranadive wrote:
>> From: Adit Ranadive <aditr@vmware.com>
>>
>> Since the IB_WR_REG_MR opcode value changed, let's set the PVRDMA
>> device opcodes explicitly.
>>
>> Reported-by: Ruishuang Wang <ruishuangw@vmware.com>
>> Fixes: 9a59739bd01f ("IB/rxe: Revise the ib_wr_opcode enum")
>> Cc: stable@vger.kernel.org
>> Reviewed-by: Bryan Tan <bryantan@vmware.com>
>> Reviewed-by: Ruishuang Wang <ruishuangw@vmware.com>
>> Reviewed-by: Vishnu Dasa <vdasa@vmware.com>
>> Signed-off-by: Adit Ranadive <aditr@vmware.com>
>> drivers/infiniband/hw/vmw_pvrdma/pvrdma.h | 43 +++++++++++++++++++++++++++++++
>> 1 file changed, 43 insertions(+)
>>
>> diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
>> index 42b8685c997e..a85d7ba96d55 100644
>> +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
>> @@ -427,6 +427,49 @@ static inline enum ib_qp_state pvrdma_qp_state_to_ib(enum pvrdma_qp_state state)
>>
>> static inline enum pvrdma_wr_opcode ib_wr_opcode_to_pvrdma(enum ib_wr_opcode op)
>> {
>> + switch (op) {
>> + case IB_WR_RDMA_WRITE:
>> + return PVRDMA_WR_RDMA_WRITE;
>> + case IB_WR_RDMA_WRITE_WITH_IMM:
>> + return PVRDMA_WR_RDMA_WRITE_WITH_IMM;
>> + case IB_WR_SEND:
>> + return PVRDMA_WR_SEND;
>> + case IB_WR_SEND_WITH_IMM:
>> + return PVRDMA_WR_SEND_WITH_IMM;
>> + case IB_WR_RDMA_READ:
>> + return PVRDMA_WR_RDMA_READ;
>> + case IB_WR_ATOMIC_CMP_AND_SWP:
>> + return PVRDMA_WR_ATOMIC_CMP_AND_SWP;
>> + case IB_WR_ATOMIC_FETCH_AND_ADD:
>> + return PVRDMA_WR_ATOMIC_FETCH_AND_ADD;
>> + case IB_WR_LSO:
>> + return PVRDMA_WR_LSO;
>> + case IB_WR_SEND_WITH_INV:
>> + return PVRDMA_WR_SEND_WITH_INV;
>> + case IB_WR_RDMA_READ_WITH_INV:
>> + return PVRDMA_WR_RDMA_READ_WITH_INV;
>> + case IB_WR_LOCAL_INV:
>> + return PVRDMA_WR_LOCAL_INV;
>> + case IB_WR_REG_MR:
>> + return PVRDMA_WR_FAST_REG_MR;
>> + case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
>> + return PVRDMA_WR_MASKED_ATOMIC_CMP_AND_SWP;
>> + case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD:
>> + return PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD;
>> + case IB_WR_REG_SIG_MR:
>> + return PVRDMA_WR_REG_SIG_MR;
>> + case IB_WR_RESERVED1:
>> + case IB_WR_RESERVED2:
>> + case IB_WR_RESERVED3:
>> + case IB_WR_RESERVED4:
>> + case IB_WR_RESERVED5:
>> + case IB_WR_RESERVED6:
>> + case IB_WR_RESERVED7:
>> + case IB_WR_RESERVED8:
>> + case IB_WR_RESERVED9:
>> + case IB_WR_RESERVED10:
>> + return (enum pvrdma_wr_opcode)op;
>> + }
>> return (enum pvrdma_wr_opcode)op;
>
> I ment it should always translate, not cast like this - if no
> translation is available then it should be a posting failure.
>
> Jason
>
Not sure if I follow you. We can post a failure but that would be
in pvrdma_qp.c when it looks at the opcode returned from here. We
would have to handle all the IB enums here though if you don't want
a default case (you would get compiler warnings otherwise).
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index 3acf74cbe266..eeb9e9ef4655 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -721,6 +721,12 @@ int pvrdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM)
wqe_hdr->ex.imm_data = wr->ex.imm_data;
+ if (wqe_hdr->opcode > PVRDMA_WR_REG_SIG_MR) {
+ *bad_wr = wr;
+ ret = -EINVAL;
+ goto out;
+ }
+
switch (qp->ibqp.qp_type) {
case IB_QPT_GSI:
case IB_QPT_UD:
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH v1 for-rc] RDMA/vmw_pvrdma: Return the correct opcode when creating WR
2019-01-08 0:02 ` Adit Ranadive
@ 2019-01-08 3:10 ` Jason Gunthorpe
2019-01-08 18:39 ` Adit Ranadive
0 siblings, 1 reply; 6+ messages in thread
From: Jason Gunthorpe @ 2019-01-08 3:10 UTC (permalink / raw)
To: Adit Ranadive; +Cc: dledford, linux-rdma, Pv-drivers, stable
On Tue, Jan 08, 2019 at 12:02:42AM +0000, Adit Ranadive wrote:
> On 1/7/19 3:28 PM, Jason Gunthorpe wrote:
> > On Mon, Jan 07, 2019 at 11:23:05PM +0000, Adit Ranadive wrote:
> >> From: Adit Ranadive <aditr@vmware.com>
> >>
> >> Since the IB_WR_REG_MR opcode value changed, let's set the PVRDMA
> >> device opcodes explicitly.
> >>
> >> Reported-by: Ruishuang Wang <ruishuangw@vmware.com>
> >> Fixes: 9a59739bd01f ("IB/rxe: Revise the ib_wr_opcode enum")
> >> Cc: stable@vger.kernel.org
> >> Reviewed-by: Bryan Tan <bryantan@vmware.com>
> >> Reviewed-by: Ruishuang Wang <ruishuangw@vmware.com>
> >> Reviewed-by: Vishnu Dasa <vdasa@vmware.com>
> >> Signed-off-by: Adit Ranadive <aditr@vmware.com>
> >> drivers/infiniband/hw/vmw_pvrdma/pvrdma.h | 43 +++++++++++++++++++++++++++++++
> >> 1 file changed, 43 insertions(+)
> >>
> >> diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
> >> index 42b8685c997e..a85d7ba96d55 100644
> >> +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
> >> @@ -427,6 +427,49 @@ static inline enum ib_qp_state pvrdma_qp_state_to_ib(enum pvrdma_qp_state state)
> >>
> >> static inline enum pvrdma_wr_opcode ib_wr_opcode_to_pvrdma(enum ib_wr_opcode op)
> >> {
> >> + switch (op) {
> >> + case IB_WR_RDMA_WRITE:
> >> + return PVRDMA_WR_RDMA_WRITE;
> >> + case IB_WR_RDMA_WRITE_WITH_IMM:
> >> + return PVRDMA_WR_RDMA_WRITE_WITH_IMM;
> >> + case IB_WR_SEND:
> >> + return PVRDMA_WR_SEND;
> >> + case IB_WR_SEND_WITH_IMM:
> >> + return PVRDMA_WR_SEND_WITH_IMM;
> >> + case IB_WR_RDMA_READ:
> >> + return PVRDMA_WR_RDMA_READ;
> >> + case IB_WR_ATOMIC_CMP_AND_SWP:
> >> + return PVRDMA_WR_ATOMIC_CMP_AND_SWP;
> >> + case IB_WR_ATOMIC_FETCH_AND_ADD:
> >> + return PVRDMA_WR_ATOMIC_FETCH_AND_ADD;
> >> + case IB_WR_LSO:
> >> + return PVRDMA_WR_LSO;
> >> + case IB_WR_SEND_WITH_INV:
> >> + return PVRDMA_WR_SEND_WITH_INV;
> >> + case IB_WR_RDMA_READ_WITH_INV:
> >> + return PVRDMA_WR_RDMA_READ_WITH_INV;
> >> + case IB_WR_LOCAL_INV:
> >> + return PVRDMA_WR_LOCAL_INV;
> >> + case IB_WR_REG_MR:
> >> + return PVRDMA_WR_FAST_REG_MR;
> >> + case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
> >> + return PVRDMA_WR_MASKED_ATOMIC_CMP_AND_SWP;
> >> + case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD:
> >> + return PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD;
> >> + case IB_WR_REG_SIG_MR:
> >> + return PVRDMA_WR_REG_SIG_MR;
> >> + case IB_WR_RESERVED1:
> >> + case IB_WR_RESERVED2:
> >> + case IB_WR_RESERVED3:
> >> + case IB_WR_RESERVED4:
> >> + case IB_WR_RESERVED5:
> >> + case IB_WR_RESERVED6:
> >> + case IB_WR_RESERVED7:
> >> + case IB_WR_RESERVED8:
> >> + case IB_WR_RESERVED9:
> >> + case IB_WR_RESERVED10:
> >> + return (enum pvrdma_wr_opcode)op;
> >> + }
> >> return (enum pvrdma_wr_opcode)op;
> >
> > I ment it should always translate, not cast like this - if no
> > translation is available then it should be a posting failure.
> >
> > Jason
> >
>
> Not sure if I follow you. We can post a failure but that would be
> in pvrdma_qp.c when it looks at the opcode returned from here. We
> would have to handle all the IB enums here though if you don't want
> a default case (you would get compiler warnings otherwise).
You'd do something like
default:
return PVRDMA_WR_ERROR;
And something, somewhere, should fail the posting.
Jason
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v1 for-rc] RDMA/vmw_pvrdma: Return the correct opcode when creating WR
2019-01-08 3:10 ` Jason Gunthorpe
@ 2019-01-08 18:39 ` Adit Ranadive
2019-01-08 23:48 ` Jason Gunthorpe
0 siblings, 1 reply; 6+ messages in thread
From: Adit Ranadive @ 2019-01-08 18:39 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: dledford, linux-rdma, Pv-drivers, stable
On 1/7/19 7:10 PM, Jason Gunthorpe wrote:
> On Tue, Jan 08, 2019 at 12:02:42AM +0000, Adit Ranadive wrote:
>> On 1/7/19 3:28 PM, Jason Gunthorpe wrote:
>>> On Mon, Jan 07, 2019 at 11:23:05PM +0000, Adit Ranadive wrote:
>>>> From: Adit Ranadive <aditr@vmware.com>
>>>>
>>>> Since the IB_WR_REG_MR opcode value changed, let's set the PVRDMA
>>>> device opcodes explicitly.
>>>>
>>>> Reported-by: Ruishuang Wang <ruishuangw@vmware.com>
>>>> Fixes: 9a59739bd01f ("IB/rxe: Revise the ib_wr_opcode enum")
>>>> Cc: stable@vger.kernel.org
>>>> Reviewed-by: Bryan Tan <bryantan@vmware.com>
>>>> Reviewed-by: Ruishuang Wang <ruishuangw@vmware.com>
>>>> Reviewed-by: Vishnu Dasa <vdasa@vmware.com>
>>>> Signed-off-by: Adit Ranadive <aditr@vmware.com>
>>>> drivers/infiniband/hw/vmw_pvrdma/pvrdma.h | 43 +++++++++++++++++++++++++++++++
>>>> 1 file changed, 43 insertions(+)
>>>>
>>>> diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
>>>> index 42b8685c997e..a85d7ba96d55 100644
>>>> +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
>>>> @@ -427,6 +427,49 @@ static inline enum ib_qp_state pvrdma_qp_state_to_ib(enum pvrdma_qp_state state)
>>>>
>>>> static inline enum pvrdma_wr_opcode ib_wr_opcode_to_pvrdma(enum ib_wr_opcode op)
>>>> {
>>>> + switch (op) {
>>>> + case IB_WR_RDMA_WRITE:
>>>> + return PVRDMA_WR_RDMA_WRITE;
>>>> + case IB_WR_RDMA_WRITE_WITH_IMM:
>>>> + return PVRDMA_WR_RDMA_WRITE_WITH_IMM;
>>>> + case IB_WR_SEND:
>>>> + return PVRDMA_WR_SEND;
>>>> + case IB_WR_SEND_WITH_IMM:
>>>> + return PVRDMA_WR_SEND_WITH_IMM;
>>>> + case IB_WR_RDMA_READ:
>>>> + return PVRDMA_WR_RDMA_READ;
>>>> + case IB_WR_ATOMIC_CMP_AND_SWP:
>>>> + return PVRDMA_WR_ATOMIC_CMP_AND_SWP;
>>>> + case IB_WR_ATOMIC_FETCH_AND_ADD:
>>>> + return PVRDMA_WR_ATOMIC_FETCH_AND_ADD;
>>>> + case IB_WR_LSO:
>>>> + return PVRDMA_WR_LSO;
>>>> + case IB_WR_SEND_WITH_INV:
>>>> + return PVRDMA_WR_SEND_WITH_INV;
>>>> + case IB_WR_RDMA_READ_WITH_INV:
>>>> + return PVRDMA_WR_RDMA_READ_WITH_INV;
>>>> + case IB_WR_LOCAL_INV:
>>>> + return PVRDMA_WR_LOCAL_INV;
>>>> + case IB_WR_REG_MR:
>>>> + return PVRDMA_WR_FAST_REG_MR;
>>>> + case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
>>>> + return PVRDMA_WR_MASKED_ATOMIC_CMP_AND_SWP;
>>>> + case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD:
>>>> + return PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD;
>>>> + case IB_WR_REG_SIG_MR:
>>>> + return PVRDMA_WR_REG_SIG_MR;
>>>> + case IB_WR_RESERVED1:
>>>> + case IB_WR_RESERVED2:
>>>> + case IB_WR_RESERVED3:
>>>> + case IB_WR_RESERVED4:
>>>> + case IB_WR_RESERVED5:
>>>> + case IB_WR_RESERVED6:
>>>> + case IB_WR_RESERVED7:
>>>> + case IB_WR_RESERVED8:
>>>> + case IB_WR_RESERVED9:
>>>> + case IB_WR_RESERVED10:
>>>> + return (enum pvrdma_wr_opcode)op;
>>>> + }
>>>> return (enum pvrdma_wr_opcode)op;
>>>
>>> I ment it should always translate, not cast like this - if no
>>> translation is available then it should be a posting failure.
>>>
>>> Jason
>>>
>>
>> Not sure if I follow you. We can post a failure but that would be
>> in pvrdma_qp.c when it looks at the opcode returned from here. We
>> would have to handle all the IB enums here though if you don't want
>> a default case (you would get compiler warnings otherwise).
>
> You'd do something like
>
> default:
> return PVRDMA_WR_ERROR;
>
> And something, somewhere, should fail the posting.
>
> Jason
>
Okay. So maybe something like this, would work:
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 42b8685c997e..3c633ab58052 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -427,7 +427,40 @@ static inline enum ib_qp_state pvrdma_qp_state_to_ib(enum pvrdma_qp_state state)
static inline enum pvrdma_wr_opcode ib_wr_opcode_to_pvrdma(enum ib_wr_opcode op)
{
- return (enum pvrdma_wr_opcode)op;
+ switch (op) {
+ case IB_WR_RDMA_WRITE:
+ return PVRDMA_WR_RDMA_WRITE;
+ case IB_WR_RDMA_WRITE_WITH_IMM:
+ return PVRDMA_WR_RDMA_WRITE_WITH_IMM;
+ case IB_WR_SEND:
+ return PVRDMA_WR_SEND;
+ case IB_WR_SEND_WITH_IMM:
+ return PVRDMA_WR_SEND_WITH_IMM;
+ case IB_WR_RDMA_READ:
+ return PVRDMA_WR_RDMA_READ;
+ case IB_WR_ATOMIC_CMP_AND_SWP:
+ return PVRDMA_WR_ATOMIC_CMP_AND_SWP;
+ case IB_WR_ATOMIC_FETCH_AND_ADD:
+ return PVRDMA_WR_ATOMIC_FETCH_AND_ADD;
+ case IB_WR_LSO:
+ return PVRDMA_WR_LSO;
+ case IB_WR_SEND_WITH_INV:
+ return PVRDMA_WR_SEND_WITH_INV;
+ case IB_WR_RDMA_READ_WITH_INV:
+ return PVRDMA_WR_RDMA_READ_WITH_INV;
+ case IB_WR_LOCAL_INV:
+ return PVRDMA_WR_LOCAL_INV;
+ case IB_WR_REG_MR:
+ return PVRDMA_WR_FAST_REG_MR;
+ case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
+ return PVRDMA_WR_MASKED_ATOMIC_CMP_AND_SWP;
+ case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD:
+ return PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD;
+ case IB_WR_REG_SIG_MR:
+ return PVRDMA_WR_REG_SIG_MR;
+ default:
+ return PVRDMA_WR_ERROR;
+ }
}
static inline enum ib_wc_status pvrdma_wc_status_to_ib(
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index 3acf74cbe266..1ec3646087ba 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -721,6 +721,12 @@ int pvrdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM)
wqe_hdr->ex.imm_data = wr->ex.imm_data;
+ if (unlikely(wqe_hdr->opcode == PVRDMA_WR_ERROR)) {
+ *bad_wr = wr;
+ ret = -EINVAL;
+ goto out;
+ }
+
switch (qp->ibqp.qp_type) {
case IB_QPT_GSI:
case IB_QPT_UD:
diff --git a/include/uapi/rdma/vmw_pvrdma-abi.h b/include/uapi/rdma/vmw_pvrdma-abi.h
index d13fd490b66d..6e73f0274e41 100644
--- a/include/uapi/rdma/vmw_pvrdma-abi.h
+++ b/include/uapi/rdma/vmw_pvrdma-abi.h
@@ -78,6 +78,7 @@ enum pvrdma_wr_opcode {
PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD,
PVRDMA_WR_BIND_MW,
PVRDMA_WR_REG_SIG_MR,
+ PVRDMA_WR_ERROR,
};
enum pvrdma_wc_status {
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH v1 for-rc] RDMA/vmw_pvrdma: Return the correct opcode when creating WR
2019-01-08 18:39 ` Adit Ranadive
@ 2019-01-08 23:48 ` Jason Gunthorpe
0 siblings, 0 replies; 6+ messages in thread
From: Jason Gunthorpe @ 2019-01-08 23:48 UTC (permalink / raw)
To: Adit Ranadive; +Cc: dledford, linux-rdma, Pv-drivers, stable
On Tue, Jan 08, 2019 at 06:39:02PM +0000, Adit Ranadive wrote:
> >> Not sure if I follow you. We can post a failure but that would be
> >> in pvrdma_qp.c when it looks at the opcode returned from here. We
> >> would have to handle all the IB enums here though if you don't want
> >> a default case (you would get compiler warnings otherwise).
> >
> > You'd do something like
> >
> > default:
> > return PVRDMA_WR_ERROR;
> >
> > And something, somewhere, should fail the posting.
> >
> > Jason
> >
>
> Okay. So maybe something like this, would work:
Yes, this is what I was thinking, please send a patch
Jason
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2019-01-08 23:48 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-01-07 23:23 [PATCH v1 for-rc] RDMA/vmw_pvrdma: Return the correct opcode when creating WR Adit Ranadive
2019-01-07 23:28 ` Jason Gunthorpe
2019-01-08 0:02 ` Adit Ranadive
2019-01-08 3:10 ` Jason Gunthorpe
2019-01-08 18:39 ` Adit Ranadive
2019-01-08 23:48 ` Jason Gunthorpe
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.