* [v2,for-rc] RDMA/qedr: qedr crash while running rdma-tool
@ 2021-10-23 16:45 Alok Prasad
2021-10-24 10:46 ` Kamal Heib
0 siblings, 1 reply; 4+ messages in thread
From: Alok Prasad @ 2021-10-23 16:45 UTC (permalink / raw)
To: jgg, dledford
Cc: michal.kalderon, ariel.elior, linux-rdma, smalin, aelior, palok,
alok.prasad7, Michal Kalderon
This patch fixes crash caused by querying qp.
Also corrects the state of gsi qp.
Below call trace is generated while using iproute2 utility
"rdma res show -dd qp" on rdma interface.
==========================================================================
[ 302.569794] BUG: kernel NULL pointer dereference, address: 0000000000000034
..
[ 302.570378] Hardware name: Dell Inc. PowerEdge R720/0M1GCR, BIOS 1.2.6 05/10/2012
[ 302.570500] RIP: 0010:qed_rdma_query_qp+0x33/0x1a0 [qed]
[ 302.570861] RSP: 0018:ffffba560a08f580 EFLAGS: 00010206
[ 302.570979] RAX: 0000000200000000 RBX: ffffba560a08f5b8 RCX: 0000000000000000
[ 302.571100] RDX: ffffba560a08f5b8 RSI: 0000000000000000 RDI: ffff9807ee458090
[ 302.571221] RBP: ffffba560a08f5a0 R08: 0000000000000000 R09: ffff9807890e7048
[ 302.571342] R10: ffffba560a08f658 R11: 0000000000000000 R12: 0000000000000000
[ 302.571462] R13: ffff9807ee458090 R14: ffff9807f0afb000 R15: ffffba560a08f7ec
[ 302.571583] FS: 00007fbbf8bfe740(0000) GS:ffff980aafa00000(0000) knlGS:0000000000000000
[ 302.571729] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 302.571847] CR2: 0000000000000034 CR3: 00000001720ba001 CR4: 00000000000606f0
[ 302.571968] Call Trace:
[ 302.572083] qedr_query_qp+0x82/0x360 [qedr]
[ 302.572211] ib_query_qp+0x34/0x40 [ib_core]
[ 302.572361] ? ib_query_qp+0x34/0x40 [ib_core]
[ 302.572503] fill_res_qp_entry_query.isra.26+0x47/0x1d0 [ib_core]
[ 302.572670] ? __nla_put+0x20/0x30
[ 302.572788] ? nla_put+0x33/0x40
[ 302.572901] fill_res_qp_entry+0xe3/0x120 [ib_core]
[ 302.573058] res_get_common_dumpit+0x3f8/0x5d0 [ib_core]
[ 302.573213] ? fill_res_cm_id_entry+0x1f0/0x1f0 [ib_core]
[ 302.573377] nldev_res_get_qp_dumpit+0x1a/0x20 [ib_core]
[ 302.573529] netlink_dump+0x156/0x2f0
[ 302.573648] __netlink_dump_start+0x1ab/0x260
[ 302.573765] rdma_nl_rcv+0x1de/0x330 [ib_core]
[ 302.573918] ? nldev_res_get_cm_id_dumpit+0x20/0x20 [ib_core]
[ 302.574074] netlink_unicast+0x1b8/0x270
[ 302.574191] netlink_sendmsg+0x33e/0x470
[ 302.574307] sock_sendmsg+0x63/0x70
[ 302.574421] __sys_sendto+0x13f/0x180
[ 302.574536] ? setup_sgl.isra.12+0x70/0xc0
[ 302.574655] __x64_sys_sendto+0x28/0x30
[ 302.574769] do_syscall_64+0x3a/0xb0
[ 302.574884] entry_SYSCALL_64_after_hwframe+0x44/0xae
==========================================================================
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: Michal Kalderon <mkalderon@marvell.com>
Signed-off-by: Shai Malin <smalin@marvell.com>
Signed-off-by: Alok Prasad <palok@marvell.com>
---
v2 (from [1]):
- Change description.
- Corrected enum type.
[1] https://patchwork.kernel.org/project/linux-rdma/patch/20210821074339.16614-1-palok@marvell.com/
---
drivers/infiniband/hw/qedr/verbs.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index dcb3653db72d..85baa4f730df 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -2744,15 +2744,20 @@ int qedr_query_qp(struct ib_qp *ibqp,
int rc = 0;
memset(¶ms, 0, sizeof(params));
+ memset(qp_attr, 0, sizeof(*qp_attr));
+ memset(qp_init_attr, 0, sizeof(*qp_init_attr));
- rc = dev->ops->rdma_query_qp(dev->rdma_ctx, qp->qed_qp, ¶ms);
+ if (qp->qed_qp)
+ rc = dev->ops->rdma_query_qp(dev->rdma_ctx,
+ qp->qed_qp, ¶ms);
if (rc)
goto err;
- memset(qp_attr, 0, sizeof(*qp_attr));
- memset(qp_init_attr, 0, sizeof(*qp_init_attr));
+ if (qp->qp_type == IB_QPT_GSI)
+ qp_attr->qp_state = qedr_get_ibqp_state(QED_ROCE_QP_STATE_RTS);
+ else
+ qp_attr->qp_state = qedr_get_ibqp_state(params.state);
- qp_attr->qp_state = qedr_get_ibqp_state(params.state);
qp_attr->cur_qp_state = qedr_get_ibqp_state(params.state);
qp_attr->path_mtu = ib_mtu_int_to_enum(params.mtu);
qp_attr->path_mig_state = IB_MIG_MIGRATED;
--
2.17.1
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [v2,for-rc] RDMA/qedr: qedr crash while running rdma-tool
2021-10-23 16:45 [v2,for-rc] RDMA/qedr: qedr crash while running rdma-tool Alok Prasad
@ 2021-10-24 10:46 ` Kamal Heib
2021-10-27 17:00 ` Jason Gunthorpe
0 siblings, 1 reply; 4+ messages in thread
From: Kamal Heib @ 2021-10-24 10:46 UTC (permalink / raw)
To: Alok Prasad
Cc: michal.kalderon, ariel.elior, linux-rdma, smalin, aelior,
alok.prasad7, Michal Kalderon, dledford, jgg
On 10/23/21 19:45, Alok Prasad wrote:
> This patch fixes crash caused by querying qp.
> Also corrects the state of gsi qp.
>
> Below call trace is generated while using iproute2 utility
> "rdma res show -dd qp" on rdma interface.
> ==========================================================================
> [ 302.569794] BUG: kernel NULL pointer dereference, address: 0000000000000034
> ..
> [ 302.570378] Hardware name: Dell Inc. PowerEdge R720/0M1GCR, BIOS 1.2.6 05/10/2012
> [ 302.570500] RIP: 0010:qed_rdma_query_qp+0x33/0x1a0 [qed]
> [ 302.570861] RSP: 0018:ffffba560a08f580 EFLAGS: 00010206
> [ 302.570979] RAX: 0000000200000000 RBX: ffffba560a08f5b8 RCX: 0000000000000000
> [ 302.571100] RDX: ffffba560a08f5b8 RSI: 0000000000000000 RDI: ffff9807ee458090
> [ 302.571221] RBP: ffffba560a08f5a0 R08: 0000000000000000 R09: ffff9807890e7048
> [ 302.571342] R10: ffffba560a08f658 R11: 0000000000000000 R12: 0000000000000000
> [ 302.571462] R13: ffff9807ee458090 R14: ffff9807f0afb000 R15: ffffba560a08f7ec
> [ 302.571583] FS: 00007fbbf8bfe740(0000) GS:ffff980aafa00000(0000) knlGS:0000000000000000
> [ 302.571729] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 302.571847] CR2: 0000000000000034 CR3: 00000001720ba001 CR4: 00000000000606f0
> [ 302.571968] Call Trace:
> [ 302.572083] qedr_query_qp+0x82/0x360 [qedr]
> [ 302.572211] ib_query_qp+0x34/0x40 [ib_core]
> [ 302.572361] ? ib_query_qp+0x34/0x40 [ib_core]
> [ 302.572503] fill_res_qp_entry_query.isra.26+0x47/0x1d0 [ib_core]
> [ 302.572670] ? __nla_put+0x20/0x30
> [ 302.572788] ? nla_put+0x33/0x40
> [ 302.572901] fill_res_qp_entry+0xe3/0x120 [ib_core]
> [ 302.573058] res_get_common_dumpit+0x3f8/0x5d0 [ib_core]
> [ 302.573213] ? fill_res_cm_id_entry+0x1f0/0x1f0 [ib_core]
> [ 302.573377] nldev_res_get_qp_dumpit+0x1a/0x20 [ib_core]
> [ 302.573529] netlink_dump+0x156/0x2f0
> [ 302.573648] __netlink_dump_start+0x1ab/0x260
> [ 302.573765] rdma_nl_rcv+0x1de/0x330 [ib_core]
> [ 302.573918] ? nldev_res_get_cm_id_dumpit+0x20/0x20 [ib_core]
> [ 302.574074] netlink_unicast+0x1b8/0x270
> [ 302.574191] netlink_sendmsg+0x33e/0x470
> [ 302.574307] sock_sendmsg+0x63/0x70
> [ 302.574421] __sys_sendto+0x13f/0x180
> [ 302.574536] ? setup_sgl.isra.12+0x70/0xc0
> [ 302.574655] __x64_sys_sendto+0x28/0x30
> [ 302.574769] do_syscall_64+0x3a/0xb0
> [ 302.574884] entry_SYSCALL_64_after_hwframe+0x44/0xae
> ==========================================================================
> Signed-off-by: Ariel Elior <aelior@marvell.com>
> Signed-off-by: Michal Kalderon <mkalderon@marvell.com>
> Signed-off-by: Shai Malin <smalin@marvell.com>
> Signed-off-by: Alok Prasad <palok@marvell.com>
> ---
> v2 (from [1]):
> - Change description.
> - Corrected enum type.
> [1] https://patchwork.kernel.org/project/linux-rdma/patch/20210821074339.16614-1-palok@marvell.com/
> ---
> drivers/infiniband/hw/qedr/verbs.c | 13 +++++++++----
> 1 file changed, 9 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
> index dcb3653db72d..85baa4f730df 100644
> --- a/drivers/infiniband/hw/qedr/verbs.c
> +++ b/drivers/infiniband/hw/qedr/verbs.c
> @@ -2744,15 +2744,20 @@ int qedr_query_qp(struct ib_qp *ibqp,
> int rc = 0;
>
> memset(¶ms, 0, sizeof(params));
> + memset(qp_attr, 0, sizeof(*qp_attr));
> + memset(qp_init_attr, 0, sizeof(*qp_init_attr));
>
> - rc = dev->ops->rdma_query_qp(dev->rdma_ctx, qp->qed_qp, ¶ms);
> + if (qp->qed_qp)
I suggest to use "if (qp->qp_type != IB_QPT_GSI)" to match the handling
of GSI QPs in the QEDR driver.
Thanks,
Kamal
> + rc = dev->ops->rdma_query_qp(dev->rdma_ctx,
> + qp->qed_qp, ¶ms);
> if (rc)
> goto err;
>
> - memset(qp_attr, 0, sizeof(*qp_attr));
> - memset(qp_init_attr, 0, sizeof(*qp_init_attr));
> + if (qp->qp_type == IB_QPT_GSI)
> + qp_attr->qp_state = qedr_get_ibqp_state(QED_ROCE_QP_STATE_RTS);
> + else
> + qp_attr->qp_state = qedr_get_ibqp_state(params.state);
>
> - qp_attr->qp_state = qedr_get_ibqp_state(params.state);
> qp_attr->cur_qp_state = qedr_get_ibqp_state(params.state);
> qp_attr->path_mtu = ib_mtu_int_to_enum(params.mtu);
> qp_attr->path_mig_state = IB_MIG_MIGRATED;
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [v2,for-rc] RDMA/qedr: qedr crash while running rdma-tool
2021-10-24 10:46 ` Kamal Heib
@ 2021-10-27 17:00 ` Jason Gunthorpe
2021-10-27 18:45 ` [EXT] " Alok Prasad
0 siblings, 1 reply; 4+ messages in thread
From: Jason Gunthorpe @ 2021-10-27 17:00 UTC (permalink / raw)
To: Kamal Heib
Cc: Alok Prasad, michal.kalderon, ariel.elior, linux-rdma, smalin,
aelior, alok.prasad7, Michal Kalderon, dledford
On Sun, Oct 24, 2021 at 01:46:03PM +0300, Kamal Heib wrote:
> > diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
> > index dcb3653db72d..85baa4f730df 100644
> > +++ b/drivers/infiniband/hw/qedr/verbs.c
> > @@ -2744,15 +2744,20 @@ int qedr_query_qp(struct ib_qp *ibqp,
> > int rc = 0;
> > memset(¶ms, 0, sizeof(params));
> > + memset(qp_attr, 0, sizeof(*qp_attr));
> > + memset(qp_init_attr, 0, sizeof(*qp_init_attr));
> > - rc = dev->ops->rdma_query_qp(dev->rdma_ctx, qp->qed_qp, ¶ms);
> > + if (qp->qed_qp)
>
> I suggest to use "if (qp->qp_type != IB_QPT_GSI)" to match the handling of
> GSI QPs in the QEDR driver.
Alok? Time is closing to get this in before the merge window.
Jason
^ permalink raw reply [flat|nested] 4+ messages in thread
* RE: [EXT] Re: [v2,for-rc] RDMA/qedr: qedr crash while running rdma-tool
2021-10-27 17:00 ` Jason Gunthorpe
@ 2021-10-27 18:45 ` Alok Prasad
0 siblings, 0 replies; 4+ messages in thread
From: Alok Prasad @ 2021-10-27 18:45 UTC (permalink / raw)
To: Jason Gunthorpe, Kamal Heib
Cc: Michal Kalderon, Ariel Elior, linux-rdma, Shai Malin,
Ariel Elior, alok.prasad7, Michal Kalderon, dledford
> -----Original Message-----
> From: Jason Gunthorpe <jgg@nvidia.com>
> Sent: 27 October 2021 22:31
> To: Kamal Heib <kheib@redhat.com>
> Cc: Alok Prasad <palok@marvell.com>; Michal Kalderon <mkalderon@marvell.com>; Ariel Elior
> <aelior@marvell.com>; linux-rdma@vger.kernel.org; Shai Malin <smalin@marvell.com>; Ariel
> Elior <aelior@marvell.com>; alok.prasad7@gmail.com; Michal Kalderon
> <mkalderon@marvell.com>; dledford@redhat.com
> Subject: [EXT] Re: [v2,for-rc] RDMA/qedr: qedr crash while running rdma-tool
>
> External Email
>
> ----------------------------------------------------------------------
> On Sun, Oct 24, 2021 at 01:46:03PM +0300, Kamal Heib wrote:
>
> > > diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
> > > index dcb3653db72d..85baa4f730df 100644
> > > +++ b/drivers/infiniband/hw/qedr/verbs.c
> > > @@ -2744,15 +2744,20 @@ int qedr_query_qp(struct ib_qp *ibqp,
> > > int rc = 0;
> > > memset(¶ms, 0, sizeof(params));
> > > + memset(qp_attr, 0, sizeof(*qp_attr));
> > > + memset(qp_init_attr, 0, sizeof(*qp_init_attr));
> > > - rc = dev->ops->rdma_query_qp(dev->rdma_ctx, qp->qed_qp, ¶ms);
> > > + if (qp->qed_qp)
> >
> > I suggest to use "if (qp->qp_type != IB_QPT_GSI)" to match the handling of
> > GSI QPs in the QEDR driver.
>
> Alok? Time is closing to get this in before the merge window.
>
> Jason
Done now with v3, Sorry for delaying on this.
- Alok
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2021-10-27 18:46 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-10-23 16:45 [v2,for-rc] RDMA/qedr: qedr crash while running rdma-tool Alok Prasad
2021-10-24 10:46 ` Kamal Heib
2021-10-27 17:00 ` Jason Gunthorpe
2021-10-27 18:45 ` [EXT] " Alok Prasad
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).