From: Yafang Shao <laoar.shao@gmail.com>
To: ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
kafai@fb.com, songliubraving@fb.com, yhs@fb.com,
john.fastabend@gmail.com, kpsingh@kernel.org, sdf@google.com,
haoluo@google.com, jolsa@kernel.org, hannes@cmpxchg.org,
mhocko@kernel.org, roman.gushchin@linux.dev, shakeelb@google.com,
songmuchun@bytedance.com, akpm@linux-foundation.org,
tj@kernel.org, lizefan.x@bytedance.com
Cc: cgroups@vger.kernel.org, netdev@vger.kernel.org,
bpf@vger.kernel.org, linux-mm@kvack.org,
Yafang Shao <laoar.shao@gmail.com>
Subject: [PATCH bpf-next v3 07/13] bpf: Introduce new helpers bpf_ringbuf_pages_{alloc,free}
Date: Fri, 2 Sep 2022 02:29:57 +0000 [thread overview]
Message-ID: <20220902023003.47124-8-laoar.shao@gmail.com> (raw)
In-Reply-To: <20220902023003.47124-1-laoar.shao@gmail.com>
Allocate pages related memory into the new helper
bpf_ringbuf_pages_alloc(), then it can be handled as a single unit.
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
---
kernel/bpf/ringbuf.c | 80 ++++++++++++++++++++++++++++++++++++----------------
1 file changed, 56 insertions(+), 24 deletions(-)
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 5eb7820..1e7284c 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -59,6 +59,57 @@ struct bpf_ringbuf_hdr {
u32 pg_off;
};
+static void bpf_ringbuf_pages_free(struct page **pages, int nr_pages)
+{
+ int i;
+
+ for (i = 0; i < nr_pages; i++)
+ __free_page(pages[i]);
+ bpf_map_area_free(pages, NULL);
+}
+
+static struct page **bpf_ringbuf_pages_alloc(struct bpf_map *map,
+ int nr_meta_pages,
+ int nr_data_pages,
+ int numa_node,
+ const gfp_t flags)
+{
+ int nr_pages = nr_meta_pages + nr_data_pages;
+ struct mem_cgroup *memcg, *old_memcg;
+ struct page **pages, *page;
+ int array_size;
+ int i;
+
+ memcg = bpf_map_get_memcg(map);
+ old_memcg = set_active_memcg(memcg);
+ array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages);
+ pages = bpf_map_area_alloc(array_size, numa_node, NULL);
+ if (!pages)
+ goto err;
+
+ for (i = 0; i < nr_pages; i++) {
+ page = alloc_pages_node(numa_node, flags, 0);
+ if (!page) {
+ nr_pages = i;
+ goto err_free_pages;
+ }
+ pages[i] = page;
+ if (i >= nr_meta_pages)
+ pages[nr_data_pages + i] = page;
+ }
+ set_active_memcg(old_memcg);
+ bpf_map_put_memcg(memcg);
+
+ return pages;
+
+err_free_pages:
+ bpf_ringbuf_pages_free(pages, nr_pages);
+err:
+ set_active_memcg(old_memcg);
+ bpf_map_put_memcg(memcg);
+ return NULL;
+}
+
static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node,
struct bpf_map *map)
{
@@ -67,10 +118,8 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node,
int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES;
int nr_data_pages = data_sz >> PAGE_SHIFT;
int nr_pages = nr_meta_pages + nr_data_pages;
- struct page **pages, *page;
struct bpf_ringbuf *rb;
- size_t array_size;
- int i;
+ struct page **pages;
/* Each data page is mapped twice to allow "virtual"
* continuous read of samples wrapping around the end of ring
@@ -89,22 +138,11 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node,
* when mmap()'ed in user-space, simplifying both kernel and
* user-space implementations significantly.
*/
- array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages);
- pages = bpf_map_area_alloc(array_size, numa_node, map);
+ pages = bpf_ringbuf_pages_alloc(map, nr_meta_pages, nr_data_pages,
+ numa_node, flags);
if (!pages)
return NULL;
- for (i = 0; i < nr_pages; i++) {
- page = alloc_pages_node(numa_node, flags, 0);
- if (!page) {
- nr_pages = i;
- goto err_free_pages;
- }
- pages[i] = page;
- if (i >= nr_meta_pages)
- pages[nr_data_pages + i] = page;
- }
-
rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages,
VM_MAP | VM_USERMAP, PAGE_KERNEL);
if (rb) {
@@ -114,10 +152,6 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node,
return rb;
}
-err_free_pages:
- for (i = 0; i < nr_pages; i++)
- __free_page(pages[i]);
- bpf_map_area_free(pages, NULL);
return NULL;
}
@@ -188,12 +222,10 @@ static void bpf_ringbuf_free(struct bpf_ringbuf *rb)
* to unmap rb itself with vunmap() below
*/
struct page **pages = rb->pages;
- int i, nr_pages = rb->nr_pages;
+ int nr_pages = rb->nr_pages;
vunmap(rb);
- for (i = 0; i < nr_pages; i++)
- __free_page(pages[i]);
- bpf_map_area_free(pages, NULL);
+ bpf_ringbuf_pages_free(pages, nr_pages);
}
static void ringbuf_map_free(struct bpf_map *map)
--
1.8.3.1
next prev parent reply other threads:[~2022-09-02 2:30 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-02 2:29 [PATCH bpf-next v3 00/13] bpf: Introduce selectable memcg for bpf map Yafang Shao
2022-09-02 2:29 ` [PATCH bpf-next v3 01/13] cgroup: Update the comment on cgroup_get_from_fd Yafang Shao
2022-09-02 2:29 ` [PATCH bpf-next v3 02/13] bpf: Introduce new helper bpf_map_put_memcg() Yafang Shao
2022-09-02 2:29 ` [PATCH bpf-next v3 03/13] bpf: Define bpf_map_{get,put}_memcg for !CONFIG_MEMCG_KMEM Yafang Shao
2022-09-02 2:29 ` [PATCH bpf-next v3 04/13] bpf: Call bpf_map_init_from_attr() immediately after map creation Yafang Shao
2022-09-02 2:29 ` [PATCH bpf-next v3 05/13] bpf: Save memcg in bpf_map_init_from_attr() Yafang Shao
2022-09-02 2:29 ` [PATCH bpf-next v3 06/13] bpf: Use scoped-based charge in bpf_map_area_alloc Yafang Shao
2022-09-02 2:29 ` Yafang Shao [this message]
2022-09-02 2:29 ` [PATCH bpf-next v3 08/13] bpf: Use bpf_map_kzalloc in arraymap Yafang Shao
2022-09-02 2:29 ` [PATCH bpf-next v3 09/13] bpf: Use bpf_map_kvcalloc in bpf_local_storage Yafang Shao
2022-09-02 2:30 ` [PATCH bpf-next v3 10/13] mm, memcg: Add new helper get_obj_cgroup_from_cgroup Yafang Shao
2022-09-02 2:30 ` [PATCH bpf-next v3 11/13] mm, memcg: Add new helper task_under_memcg_hierarchy Yafang Shao
2022-09-02 2:30 ` [PATCH bpf-next v3 12/13] bpf: Add return value for bpf_map_init_from_attr Yafang Shao
2022-09-02 2:30 ` [PATCH bpf-next v3 13/13] bpf: Introduce selectable memcg for bpf map Yafang Shao
2022-09-07 15:43 ` [PATCH bpf-next v3 00/13] " Tejun Heo
2022-09-07 15:45 ` Tejun Heo
2022-09-07 16:13 ` Alexei Starovoitov
2022-09-07 16:18 ` Tejun Heo
2022-09-07 16:27 ` Alexei Starovoitov
2022-09-07 17:01 ` Tejun Heo
2022-09-08 2:44 ` Yafang Shao
2022-09-07 22:28 ` Roman Gushchin
2022-09-08 2:37 ` Yafang Shao
2022-09-08 2:43 ` Alexei Starovoitov
2022-09-08 2:48 ` Yafang Shao
2022-09-08 16:13 ` Roman Gushchin
2022-09-13 6:15 ` Yafang Shao
2022-09-16 16:53 ` Roman Gushchin
2022-09-18 3:44 ` Yafang Shao
2022-09-20 2:40 ` Roman Gushchin
2022-09-20 12:42 ` Yafang Shao
2022-09-20 23:15 ` Roman Gushchin
2022-09-21 9:36 ` Yafang Shao
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=20220902023003.47124-8-laoar.shao@gmail.com \
--to=laoar.shao@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=cgroups@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=hannes@cmpxchg.org \
--cc=haoluo@google.com \
--cc=john.fastabend@gmail.com \
--cc=jolsa@kernel.org \
--cc=kafai@fb.com \
--cc=kpsingh@kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizefan.x@bytedance.com \
--cc=mhocko@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=roman.gushchin@linux.dev \
--cc=sdf@google.com \
--cc=shakeelb@google.com \
--cc=songliubraving@fb.com \
--cc=songmuchun@bytedance.com \
--cc=tj@kernel.org \
--cc=yhs@fb.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).