2020-05-17 01:27:31

by John Hubbard

Subject: [PATCH] rds: convert get_user_pages() --> pin_user_pages()

This code was using get_user_pages_fast(), in a "Case 2" scenario
(DMA/RDMA), using the categorization from [1]. That means that it's
time to convert the get_user_pages_fast() + put_page() calls to
pin_user_pages_fast() + unpin_user_pages() calls.

There is some helpful background in [2]: basically, this is a small
part of fixing a long-standing disconnect between pinning pages, and
file systems' use of those pages.

[1] Documentation/core-api/pin_user_pages.rst

[2] "Explicit pinning of user-space pages":
https://lwn.net/Articles/807108/

Cc: David S. Miller <[email protected]>
Cc: Jakub Kicinski <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Signed-off-by: John Hubbard <[email protected]>
---
net/rds/info.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/rds/info.c b/net/rds/info.c
index 03f6fd56d237..e1d63563e81c 100644
--- a/net/rds/info.c
+++ b/net/rds/info.c
@@ -162,7 +162,6 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
struct rds_info_lengths lens;
unsigned long nr_pages = 0;
unsigned long start;
- unsigned long i;
rds_info_func func;
struct page **pages = NULL;
int ret;
@@ -193,7 +192,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
ret = -ENOMEM;
goto out;
}
- ret = get_user_pages_fast(start, nr_pages, FOLL_WRITE, pages);
+ ret = pin_user_pages_fast(start, nr_pages, FOLL_WRITE, pages);
if (ret != nr_pages) {
if (ret > 0)
nr_pages = ret;
@@ -235,8 +234,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
ret = -EFAULT;

out:
- for (i = 0; pages && i < nr_pages; i++)
- put_page(pages[i]);
+ unpin_user_pages(pages, nr_pages);
kfree(pages);

return ret;

base-commit: 3d1c1e5931ce45b3a3f309385bbc00c78e9951c6
--
2.26.2

2020-05-17 19:41:53

by David Miller

Subject: Re: [PATCH] rds: convert get_user_pages() --> pin_user_pages()

From: John Hubbard <[email protected]>
Date: Sat, 16 May 2020 18:23:36 -0700

> This code was using get_user_pages_fast(), in a "Case 2" scenario
> (DMA/RDMA), using the categorization from [1]. That means that it's
> time to convert the get_user_pages_fast() + put_page() calls to
> pin_user_pages_fast() + unpin_user_pages() calls.
>
> There is some helpful background in [2]: basically, this is a small
> part of fixing a long-standing disconnect between pinning pages, and
> file systems' use of those pages.
>
> [1] Documentation/core-api/pin_user_pages.rst
>
> [2] "Explicit pinning of user-space pages":
> https://lwn.net/Articles/807108/
>
> Cc: David S. Miller <[email protected]>
> Cc: Jakub Kicinski <[email protected]>
> Cc: [email protected]
> Cc: [email protected]
> Cc: [email protected]
> Signed-off-by: John Hubbard <[email protected]>

Applied to net-next, thanks.