From: Zhu Yanjun <yanjun.zhu@linux.dev>
To: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>,
linux-rdma@vger.kernel.org, leon@kernel.org, jgg@ziepe.ca,
zyjzyj2000@gmail.com
Subject: Re: [PATCH for-next] RDMA/rxe: Improve readability of ODP pagefault interface
Date: Wed, 12 Mar 2025 08:19:00 +0100 [thread overview]
Message-ID: <0fbeb3f2-7074-404c-8915-72fa12f1cbcf@linux.dev> (raw)
In-Reply-To: <20250312065937.1787241-1-matsuda-daisuke@fujitsu.com>
在 2025/3/12 7:59, Daisuke Matsuda 写道:
> Use a meaningful constant explicitly instead of hard-coding a literal.
>
> Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
> ---
> drivers/infiniband/sw/rxe/rxe_odp.c | 12 +++++++-----
> 1 file changed, 7 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/infiniband/sw/rxe/rxe_odp.c b/drivers/infiniband/sw/rxe/rxe_odp.c
> index a82e5011360c..94f7bbe14981 100644
> --- a/drivers/infiniband/sw/rxe/rxe_odp.c
> +++ b/drivers/infiniband/sw/rxe/rxe_odp.c
> @@ -37,8 +37,9 @@ const struct mmu_interval_notifier_ops rxe_mn_ops = {
> .invalidate = rxe_ib_invalidate_range,
> };
>
> -#define RXE_PAGEFAULT_RDONLY BIT(1)
> -#define RXE_PAGEFAULT_SNAPSHOT BIT(2)
> +#define RXE_PAGEFAULT_DEFAULT 0
> +#define RXE_PAGEFAULT_RDONLY BIT(0)
> +#define RXE_PAGEFAULT_SNAPSHOT BIT(1)
> static int rxe_odp_do_pagefault_and_lock(struct rxe_mr *mr, u64 user_va, int bcnt, u32 flags)
> {
> struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
> @@ -222,7 +223,7 @@ int rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
> enum rxe_mr_copy_dir dir)
> {
> struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
> - u32 flags = 0;
> + u32 flags = RXE_PAGEFAULT_DEFAULT;
> int err;
>
> if (length == 0)
> @@ -236,7 +237,7 @@ int rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
> break;
>
> case RXE_FROM_MR_OBJ:
> - flags = RXE_PAGEFAULT_RDONLY;
> + flags |= RXE_PAGEFAULT_RDONLY;
The above "|=" is different from the original "=". I am not sure if it
is correct or not. But in this function, because flags is set 0 at
first. Thus, the result is the same.
Except the above, I am fine with this commit.
Thanks a lot.
Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Zhu Yanjun
> break;
>
> default:
> @@ -312,7 +313,8 @@ int rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
> struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
> int err;
>
> - err = rxe_odp_map_range_and_lock(mr, iova, sizeof(char), 0);
> + err = rxe_odp_map_range_and_lock(mr, iova, sizeof(char),
> + RXE_PAGEFAULT_DEFAULT);
> if (err < 0)
> return err;
>
next prev parent reply other threads:[~2025-03-12 7:19 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-12 6:59 [PATCH for-next] RDMA/rxe: Improve readability of ODP pagefault interface Daisuke Matsuda
2025-03-12 7:19 ` Zhu Yanjun [this message]
2025-03-12 7:58 ` Daisuke Matsuda (Fujitsu)
2025-03-12 18:57 ` Leon Romanovsky
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=0fbeb3f2-7074-404c-8915-72fa12f1cbcf@linux.dev \
--to=yanjun.zhu@linux.dev \
--cc=jgg@ziepe.ca \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=matsuda-daisuke@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 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.