Re: [PATCH for-next 2/3] RDMA/rtrs: Fix rxe_dealloc_pd warning
From: Zhijian Li (Fujitsu)
Date: Thu Apr 13 2023 - 04:13:37 EST
On 13/04/2023 15:35, Guoqing Jiang wrote:
> Hi,
>
> I take a closer look today.
>
> On 4/12/23 09:15, Zhijian Li (Fujitsu) wrote:
>>
>> On 11/04/2023 20:26, Leon Romanovsky wrote:
>>> On Tue, Apr 11, 2023 at 02:43:46AM +0000, Zhijian Li (Fujitsu) wrote:
>>>>
>>>> On 10/04/2023 21:10, Guoqing Jiang wrote:
>>>>>
>>>>> On 4/10/23 20:08, Leon Romanovsky wrote:
>>>>>> On Mon, Apr 10, 2023 at 06:43:03AM +0000, Li Zhijian wrote:
>>>>>>> The warning occurs when destroying PD whose reference count is not zero.
>>>>>>>
>>>>>>> Precodition: clt_path->s.con_num is 2.
>>>>>>> So 2 cm connection will be created as below:
>>>>>>> CPU0 CPU1
>>>>>>> init_conns { |
>>>>>>> create_cm() // a. con[0] created |
>>>>>>> | a'. rtrs_clt_rdma_cm_handler() {
>>>>>>> | rtrs_rdma_addr_resolved()
>>>>>>> | create_con_cq_qp(con); << con[0]
>>>>>>> | }
>>>>>>> | in this moment, refcnt of PD was increased to 2+
>
> What do you mean "refcnt of PD"? usecnt in struct ib_pd or dev_ref.
I mean usecnt in struct ib_pd
>
>>>>>>> |
>>>>>>> create_cm() // b. cid = 1, failed |
>>>>>>> destroy_con_cq_qp() |
>>>>>>> rtrs_ib_dev_put() |
>>>>>>> dev_free() |
>>>>>>> ib_dealloc_pd(dev->ib_pd) << PD |
>>>>>>> is destroyed, but refcnt is |
>>>>>>> still greater than 0 |
>
> Assuming you mean "pd->usecnt". We only allocate pd in con[0] by rtrs_ib_dev_find_or_add,
> if con[1] failed to create cm, then alloc_path_reqs -> ib_alloc_mr -> atomic_inc(&pd->usecnt)
> can't be triggered. Is there other places could increase the refcnt?
Yes, when create a qp, it will also associate to this PD, that also mean refcnt of PD will be increased.
When con[0](create_con_cq_qp) succeeded, refcnt of PD will be 2. and then when con[1] failed, since
QP didn't create, refcnt of PD is still 2. con[1]'s cleanup will destroy the PD(ib_dealloc_pd) since dev_ref = 1, after that its
refcnt is still 1.
> Then what is the appropriate time to call destroy_con_cq_qp for this scenario?
> Otherwise there could be memory leak.
we must ensure QP in con[0] is closed before destroying the PD.
Currently destroy_con_cq_qp() subroutine will close the opened QP first.
Thanks
>
>>>>>>> }
>>>>>>>
>>>>>>> Simply, Here we can avoid this warning by introducing conn own flag to
>>>>>>> track if its cleanup should drop the PD.
>>>>>>>
>>>>>>> -----------------------------------------------
>>>>>>> rnbd_client L597: Mapping device /dev/nvme0n1 on session client, (access_mode: rw, nr_poll_queues: 0)
>>>>>>> ------------[ cut here ]------------
>>>>>>> WARNING: CPU: 0 PID: 26407 at drivers/infiniband/sw/rxe/rxe_pool.c:256 __rxe_cleanup+0x13a/0x170 [rdma_rxe]
>>>>>>> Modules linked in: rpcrdma rdma_ucm ib_iser rnbd_client libiscsi rtrs_client scsi_transport_iscsi rtrs_core rdma_cm iw_cm ib_cm crc32_generic rdma_rxe udp_tunnel ib_uverbs ib_core kmem device_dax nd_pmem dax_pmem nd_
>>>>>>> vme crc32c_intel fuse nvme_core nfit libnvdimm dm_multipath scsi_dh_rdac scsi_dh_emc scsi_dh_alua dm_mirror dm_region_hash dm_log dm_mod
>>>>>>> CPU: 0 PID: 26407 Comm: rnbd-client.sh Kdump: loaded Not tainted 6.2.0-rc6-roce-flush+ #53
>>>>>>> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
>>>>>>> RIP: 0010:__rxe_cleanup+0x13a/0x170 [rdma_rxe]
>>>>>>> Code: 45 84 e4 0f 84 5a ff ff ff 48 89 ef e8 5f 18 71 f9 84 c0 75 90 be c8 00 00 00 48 89 ef e8 be 89 1f fa 85 c0 0f 85 7b ff ff ff <0f> 0b 41 bc ea ff ff ff e9 71 ff ff ff e8 84 7f 1f fa e9 d0 fe ff
>>>>>>> RSP: 0018:ffffb09880b6f5f0 EFLAGS: 00010246
>>>>>>> RAX: 0000000000000000 RBX: ffff99401f15d6a8 RCX: 0000000000000000
>>>>>>> RDX: 0000000000000001 RSI: ffffffffbac8234b RDI: 00000000ffffffff
>>>>>>> RBP: ffff99401f15d6d0 R08: 0000000000000001 R09: 0000000000000001
>>>>>>> R10: 0000000000002d82 R11: 0000000000000000 R12: 0000000000000001
>>>>>>> R13: ffff994101eff208 R14: ffffb09880b6f6a0 R15: 00000000fffffe00
>>>>>>> FS: 00007fe113904740(0000) GS:ffff99413bc00000(0000) knlGS:0000000000000000
>>>>>>> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>>>>>>> CR2: 00007ff6cde656c8 CR3: 000000001f108004 CR4: 00000000001706f0
>>>>>>> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
>>>>>>> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
>>>>>>> Call Trace:
>>>>>>> <TASK>
>>>>>>> rxe_dealloc_pd+0x16/0x20 [rdma_rxe]
>>>>>>> ib_dealloc_pd_user+0x4b/0x80 [ib_core]
>>>>>>> rtrs_ib_dev_put+0x79/0xd0 [rtrs_core]
>>>>>>> destroy_con_cq_qp+0x8a/0xa0 [rtrs_client]
>>>>>>> init_path+0x1e7/0x9a0 [rtrs_client]
>>>>>>> ? __pfx_autoremove_wake_function+0x10/0x10
>>>>>>> ? lock_is_held_type+0xd7/0x130
>>>>>>> ? rcu_read_lock_sched_held+0x43/0x80
>>>>>>> ? pcpu_alloc+0x3dd/0x7d0
>>>>>>> ? rtrs_clt_init_stats+0x18/0x40 [rtrs_client]
>>>>>>> rtrs_clt_open+0x24f/0x5a0 [rtrs_client]
>>>>>>> ? __pfx_rnbd_clt_link_ev+0x10/0x10 [rnbd_client]
>>>>>>> rnbd_clt_map_device+0x6a5/0xe10 [rnbd_client]
>>>>>>>
>>>>>>> Signed-off-by: Li Zhijian <lizhijian@xxxxxxxxxxx>
>>>>>>> ---
>>>>>>> drivers/infiniband/ulp/rtrs/rtrs-clt.c | 4 ++++
>>>>>>> drivers/infiniband/ulp/rtrs/rtrs-clt.h | 1 +
>>>>>>> 2 files changed, 5 insertions(+)
>>>>>>>
>>>>>>> diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
>>>>>>> index c2065fc33a56..4c8f42e46e2f 100644
>>>>>>> --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
>>>>>>> +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
>>>>>>> @@ -1664,6 +1664,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
>>>>>>> return -ENOMEM;
>>>>>>> }
>>>>>>> clt_path->s.dev_ref = 1;
>>>>>>> + con->has_dev = true;
>>>>>>> query_fast_reg_mode(clt_path);
>>>>>>> wr_limit = clt_path->s.dev->ib_dev->attrs.max_qp_wr;
>>>>>>> /*
>>>>>>> @@ -1690,6 +1691,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
>>>>>>> wr_limit = clt_path->s.dev->ib_dev->attrs.max_qp_wr;
>>>>>>> /* Shared between connections */
>>>>>>> clt_path->s.dev_ref++;
>>>>>> Without looking in the code, I would expect dev_ref from the line above
>>>>>> to perform PD protection.
>>>>> Agreed.
>>>> Sorry, i didn't get your point. Do you mean something like this:
>>>>
>>>> + con->has_dev = true;
>>>> clt_path->s.dev_ref++;
>>> No, my point was that clt_path->s.dev_ref > 0 means that has_dev is
>>> equal to true, and dev_ref is supposed to protect from early PD
>>> destruction.
>>>
>>
>>> + if (!con->has_dev)
>>> + return;
>> We have already done such protection VVVV
>>
>>> if (clt_path->s.dev_ref && !--clt_path->s.dev_ref) { <<< each cleanup will decrease clt_path->s.dev_ref
>>> rtrs_ib_dev_put(clt_path->s.dev); <<< when it becomes to 0, PD will be destructed.
>>> clt_path->s.dev = NULL;
>>
>> But they are not equal, clt_path->s.dev_ref could be shared by multiple connections.
>> So in the case con[0] successed and con[1] failed(clt_path->s.dev_ref is 1),
>> the con[1]'s cleanup path(destroy_con_cq_qp) will destroy PD while conn[0] still associates this PD.
>
> Then what is the appropriate time to call destroy_con_cq_qp for this scenario?
> Otherwise there could be memory leak.
>
> Thanks,
> Guoqing