From: "lizhijian@fujitsu.com" <lizhijian@fujitsu.com>
To: Tom Talpey <tom@talpey.com>,
"lizhijian@fujitsu.com" <lizhijian@fujitsu.com>,
"linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>,
"zyjzyj2000@gmail.com" <zyjzyj2000@gmail.com>,
"jgg@ziepe.ca" <jgg@ziepe.ca>,
"aharonl@nvidia.com" <aharonl@nvidia.com>,
"leon@kernel.org" <leon@kernel.org>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"mbloch@nvidia.com" <mbloch@nvidia.com>,
"liweihang@huawei.com" <liweihang@huawei.com>,
"liangwenpeng@huawei.com" <liangwenpeng@huawei.com>,
"yangx.jy@fujitsu.com" <yangx.jy@fujitsu.com>,
"rpearsonhpe@gmail.com" <rpearsonhpe@gmail.com>,
"y-goto@fujitsu.com" <y-goto@fujitsu.com>
Subject: Re: [RFC PATCH rdma-next 05/10] RDMA/rxe: Allow registering persistent flag for pmem MR only
Date: Fri, 31 Dec 2021 03:34:49 +0000 [thread overview]
Message-ID: <15ad4285-7a74-2b3f-1c1e-823b36cfcf82@fujitsu.com> (raw)
In-Reply-To: <45bfd837-a784-5ea2-7ae0-46e7e557b030@talpey.com>
delete unreachable liweihang@huawei.com from recipients
On 31/12/2021 06:25, Tom Talpey wrote:
> On 12/28/2021 3:07 AM, Li Zhijian wrote:
>> Memory region should support 2 placement types: IB_ACCESS_FLUSH_PERSISTENT
>> and IB_ACCESS_FLUSH_GLOBAL_VISIBILITY, and only pmem/nvdimm has ability to
>> persist data(IB_ACCESS_FLUSH_PERSISTENT).
>>
>> Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
>> ---
>> drivers/infiniband/sw/rxe/rxe_mr.c | 12 ++++++++++++
>> 1 file changed, 12 insertions(+)
>>
>> diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
>> index bcd5e7afa475..21616d058f29 100644
>> --- a/drivers/infiniband/sw/rxe/rxe_mr.c
>> +++ b/drivers/infiniband/sw/rxe/rxe_mr.c
>> @@ -206,6 +206,11 @@ static bool iova_in_pmem(struct rxe_mr *mr, u64 iova, int length)
>> return page_in_dev_pagemap(page);
>> }
>> +static bool ib_check_flush_access_flags(struct ib_mr *mr, u32 flags)
>> +{
>> + return mr->is_pmem || !(flags & IB_ACCESS_FLUSH_PERSISTENT);
>> +}
>
> It is perfectly allowed to flush ordinary memory, persistence is
> another matter entirely.
It did, but only allows for the MRs that registered FLUSH access flags.
> Is this subroutine checking for flush,
> or persistence?
both, but it should be called in registering MR stage.
we have to 2 checking points, here is the 1st gate, where it prevent
local user from registering a persistent access flag to an ordinary memory.
2nd is in [RFC PATCH rdma-next 08/10] RDMA/rxe: Implement flush execution in responder side
where it prevent remote user to requesting persist data into an ordinary memory.
> Its name is confusing and needs to be clarified.
Err, let me see.... a more suitable name is very welcome.
Thanks
>
>> +
>> int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
>> int access, struct rxe_mr *mr)
>> {
>> @@ -282,6 +287,13 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
>> // iova_in_pmem must be called after set is updated
>> mr->ibmr.is_pmem = iova_in_pmem(mr, iova, length);
>> + if (!ib_check_flush_access_flags(&mr->ibmr, access)) {
>> + pr_err("Cannot set IB_ACCESS_FLUSH_PERSISTENT for non-pmem memory\n");
>> + mr->state = RXE_MR_STATE_INVALID;
>> + mr->umem = NULL;
>> + err = -EINVAL;
>> + goto err_release_umem;
>> + }
>
> Setting is_pmem is reasonable, but again, this is confusing with respect
> to the region being flushable. In general, all memory is flushable,
> provided the platform supports any kind of cache flush (i.e. all of them).
>
> Tom.
next prev parent reply other threads:[~2021-12-31 3:34 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-28 8:07 [RFC PATCH rdma-next 00/10] RDMA/rxe: Add RDMA FLUSH operation Li Zhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 01/10] RDMA: mr: Introduce is_pmem Li Zhijian
2022-01-06 0:21 ` Jason Gunthorpe
2022-01-06 6:12 ` lizhijian
2022-01-14 8:10 ` Li, Zhijian
2022-01-27 22:30 ` Jeff Moyer
2022-01-16 18:11 ` Dan Williams
2022-01-18 8:55 ` lizhijian
2022-01-18 15:28 ` Dan Williams
2022-01-19 2:01 ` lizhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 02/10] RDMA: Allow registering MR with flush access flags Li Zhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 03/10] RDMA/rxe: Allow registering FLUSH flags for supported device only Li Zhijian
2022-01-06 0:22 ` Jason Gunthorpe
2022-01-06 6:20 ` lizhijian
2022-01-13 6:43 ` lizhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 04/10] RDMA/rxe: Enable IB_DEVICE_RDMA_FLUSH for rxe device Li Zhijian
2022-01-06 0:22 ` Jason Gunthorpe
2022-01-06 6:26 ` lizhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 05/10] RDMA/rxe: Allow registering persistent flag for pmem MR only Li Zhijian
2021-12-30 22:25 ` Tom Talpey
2021-12-31 3:34 ` lizhijian [this message]
2021-12-31 14:40 ` Tom Talpey
2022-01-04 1:32 ` lizhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 06/10] RDMA/rxe: Implement RC RDMA FLUSH service in requester side Li Zhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 07/10] RDMA/rxe: Set BTH's SE to zero for FLUSH packet Li Zhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 08/10] RDMA/rxe: Implement flush execution in responder side Li Zhijian
2021-12-30 22:18 ` Tom Talpey
2021-12-31 1:37 ` lizhijian
2021-12-31 2:32 ` Tom Talpey
2022-01-04 8:51 ` lizhijian
2022-01-04 16:02 ` Tom Talpey
2022-01-06 0:35 ` Jason Gunthorpe
2022-01-04 16:40 ` Tom Talpey
2022-01-05 1:43 ` lizhijian
2022-01-06 0:28 ` Jason Gunthorpe
2022-01-06 6:42 ` lizhijian
2022-01-06 17:33 ` Jason Gunthorpe
2022-01-10 5:45 ` lizhijian
2022-01-10 14:34 ` Jason Gunthorpe
2022-01-11 5:34 ` lizhijian
2022-01-11 20:48 ` Jason Gunthorpe
2022-01-12 9:50 ` lizhijian
2022-01-12 13:12 ` Jason Gunthorpe
2022-01-13 6:29 ` lizhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 09/10] RDMA/rxe: Implement flush completion Li Zhijian
2021-12-28 8:07 ` [RFC PATCH rdma-next 10/10] RDMA/rxe: Add RD FLUSH service support Li Zhijian
2021-12-29 8:49 ` [RFC PATCH rdma-next 00/10] RDMA/rxe: Add RDMA FLUSH operation Gromadzki, Tomasz
2021-12-29 14:35 ` Tom Talpey
2021-12-31 1:10 ` lizhijian
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=15ad4285-7a74-2b3f-1c1e-823b36cfcf82@fujitsu.com \
--to=lizhijian@fujitsu.com \
--cc=aharonl@nvidia.com \
--cc=jgg@ziepe.ca \
--cc=leon@kernel.org \
--cc=liangwenpeng@huawei.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=liweihang@huawei.com \
--cc=mbloch@nvidia.com \
--cc=rpearsonhpe@gmail.com \
--cc=tom@talpey.com \
--cc=y-goto@fujitsu.com \
--cc=yangx.jy@fujitsu.com \
--cc=zyjzyj2000@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).