From: "Li, Zhijian" <lizhijian@cn.fujitsu.com>
To: Jason Gunthorpe <jgg@ziepe.ca>
Cc: <linux-rdma@vger.kernel.org>, <zyjzyj2000@gmail.com>,
<aharonl@nvidia.com>, <leon@kernel.org>,
<linux-kernel@vger.kernel.org>, <mbloch@nvidia.com>,
<liangwenpeng@huawei.com>, <yangx.jy@cn.fujitsu.com>,
<rpearsonhpe@gmail.com>, <y-goto@fujitsu.com>,
<dan.j.williams@intel.com>,
"nvdimm@lists.linux.dev" <nvdimm@lists.linux.dev>
Subject: Re: [RFC PATCH rdma-next 01/10] RDMA: mr: Introduce is_pmem
Date: Fri, 14 Jan 2022 16:10:33 +0800 [thread overview]
Message-ID: <4e679df5-633d-cd0c-9de3-16348b2cef35@cn.fujitsu.com> (raw)
In-Reply-To: <bf038e6c-66db-50ca-0126-3ad4ac1371e7@fujitsu.com>
Copied to nvdimm list
Thanks
Zhijian
on 2022/1/6 14:12, Li Zhijian wrote:
>
> Add Dan to the party :)
>
> May i know whether there is any existing APIs to check whether
> a va/page backs to a nvdimm/pmem ?
>
>
>
> On 06/01/2022 08:21, Jason Gunthorpe wrote:
>> On Tue, Dec 28, 2021 at 04:07:08PM +0800, Li Zhijian wrote:
>>> We can use it to indicate whether the registering mr is associated with
>>> a pmem/nvdimm or not.
>>>
>>> Currently, we only assign it in rxe driver, for other device/drivers,
>>> they should implement it if needed.
>>>
>>> RDMA FLUSH will support the persistence feature for a pmem/nvdimm.
>>>
>>> Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
>>> drivers/infiniband/sw/rxe/rxe_mr.c | 47
>>> ++++++++++++++++++++++++++++++
>>> include/rdma/ib_verbs.h | 1 +
>>> 2 files changed, 48 insertions(+)
>>>
>>> diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c
>>> b/drivers/infiniband/sw/rxe/rxe_mr.c
>>> index 7c4cd19a9db2..bcd5e7afa475 100644
>>> +++ b/drivers/infiniband/sw/rxe/rxe_mr.c
>>> @@ -162,6 +162,50 @@ void rxe_mr_init_dma(struct rxe_pd *pd, int
>>> access, struct rxe_mr *mr)
>>> mr->type = IB_MR_TYPE_DMA;
>>> }
>>> +// XXX: the logic is similar with mm/memory-failure.c
>>> +static bool page_in_dev_pagemap(struct page *page)
>>> +{
>>> + unsigned long pfn;
>>> + struct page *p;
>>> + struct dev_pagemap *pgmap = NULL;
>>> +
>>> + pfn = page_to_pfn(page);
>>> + if (!pfn) {
>>> + pr_err("no such pfn for page %p\n", page);
>>> + return false;
>>> + }
>>> +
>>> + p = pfn_to_online_page(pfn);
>>> + if (!p) {
>>> + if (pfn_valid(pfn)) {
>>> + pgmap = get_dev_pagemap(pfn, NULL);
>>> + if (pgmap)
>>> + put_dev_pagemap(pgmap);
>>> + }
>>> + }
>>> +
>>> + return !!pgmap;
>> You need to get Dan to check this out, but I'm pretty sure this should
>> be more like this:
>>
>> if (is_zone_device_page(page) && page->pgmap->type ==
>> MEMORY_DEVICE_FS_DAX)
>
> Great, i have added him.
>
>
>
>>
>>
>>> +static bool iova_in_pmem(struct rxe_mr *mr, u64 iova, int length)
>>> +{
>>> + struct page *page = NULL;
>>> + char *vaddr = iova_to_vaddr(mr, iova, length);
>>> +
>>> + if (!vaddr) {
>>> + pr_err("not a valid iova %llu\n", iova);
>>> + return false;
>>> + }
>>> +
>>> + page = virt_to_page(vaddr);
>> And obviously this isn't uniform for the entire umem, so I don't even
>> know what this is supposed to mean.
>
> My intention is to check if a memory region belongs to a nvdimm/pmem.
> The approach is like that:
> iova(user space)-+ +-> page -> page_in_dev_pagemap()
> | |
> +-> va(kernel space) -+
> Since current MR's va is associated with map_set where it record the
> relations
> between iova and va and page. Do do you mean we should travel map_set to
> get its page ? or by any other ways.
>
>
>
>
>
>
>
>>> diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
>>> index 6e9ad656ecb7..822ebb3425dc 100644
>>> +++ b/include/rdma/ib_verbs.h
>>> @@ -1807,6 +1807,7 @@ struct ib_mr {
>>> unsigned int page_size;
>>> enum ib_mr_type type;
>>> bool need_inval;
>>> + bool is_pmem;
>> Or why it is being stored in the global struct?
>
> Indeed, it's not strong necessary. but i think is_pmem should belongs
> to a ib_mr
> so that it can be checked by other general code when they needed even
> though no
> one does such checking so far.
>
>
> Thanks
> Zhijian
>
>
>
>>
>> Jason
>
next prev parent reply other threads:[~2022-01-14 8:10 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 [this message]
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
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=4e679df5-633d-cd0c-9de3-16348b2cef35@cn.fujitsu.com \
--to=lizhijian@cn.fujitsu.com \
--cc=aharonl@nvidia.com \
--cc=dan.j.williams@intel.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=mbloch@nvidia.com \
--cc=nvdimm@lists.linux.dev \
--cc=rpearsonhpe@gmail.com \
--cc=y-goto@fujitsu.com \
--cc=yangx.jy@cn.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).