| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 29 Jul 2022 15:23:11 +0000
From: Yafang Shao <laoar.shao@...il.com>
To: ast@...nel.org, daniel@...earbox.net, andrii@...nel.org,
kafai@...com, songliubraving@...com, yhs@...com,
john.fastabend@...il.com, kpsingh@...nel.org, sdf@...gle.com,
haoluo@...gle.com, jolsa@...nel.org, hannes@...xchg.org,
mhocko@...nel.org, roman.gushchin@...ux.dev, shakeelb@...gle.com,
songmuchun@...edance.com, akpm@...ux-foundation.org
Cc: netdev@...r.kernel.org, bpf@...r.kernel.org, linux-mm@...ck.org,
Yafang Shao <laoar.shao@...il.com>
Subject: [RFC PATCH bpf-next 10/15] bpf: Use bpf_map_pages_alloc in ringbuf
Introduce new helper bpf_map_pages_alloc() for this memory allocation.
Signed-off-by: Yafang Shao <laoar.shao@...il.com>
---
include/linux/bpf.h | 4 ++++
kernel/bpf/ringbuf.c | 27 +++++++++------------------
kernel/bpf/syscall.c | 41 +++++++++++++++++++++++++++++++++++++++++
3 files changed, 54 insertions(+), 18 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 711d9b1829d4..4af72d2b6d73 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1638,8 +1638,12 @@ void *bpf_map_container_alloc(u64 size, int numa_node);
void *bpf_map_container_mmapable_alloc(u64 size, int numa_node,
u32 align, u32 offset);
void *bpf_map_area_alloc(struct bpf_map *map, u64 size, int numa_node);
+void *bpf_map_pages_alloc(struct bpf_map *map, struct page **pages,
+ int nr_meta_pages, int nr_data_pages, int nid,
+ gfp_t flags, unsigned int order);
void bpf_map_area_free(void *base);
void bpf_map_container_free(void *base);
+void bpf_map_pages_free(struct page **pages, int nr_pages);
bool bpf_map_write_active(const struct bpf_map *map);
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
int generic_map_lookup_batch(struct bpf_map *map,
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 7c875d4d5b2f..25973cab251d 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -63,15 +63,15 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(struct bpf_map *map,
size_t data_sz,
int numa_node)
{
- const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL |
+ const gfp_t flags = GFP_KERNEL | __GFP_RETRY_MAYFAIL |
__GFP_NOWARN | __GFP_ZERO;
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;
+ struct page **pages;
size_t array_size;
- int i;
+ void *ptr;
/* Each data page is mapped twice to allow "virtual"
* continuous read of samples wrapping around the end of ring
@@ -95,16 +95,10 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(struct bpf_map *map,
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;
- }
+ ptr = bpf_map_pages_alloc(map, pages, nr_meta_pages, nr_data_pages,
+ numa_node, flags, 0);
+ if (!ptr)
+ goto err_free_pages;
rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages,
VM_MAP | VM_USERMAP, PAGE_KERNEL);
@@ -116,8 +110,6 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(struct bpf_map *map,
}
err_free_pages:
- for (i = 0; i < nr_pages; i++)
- __free_page(pages[i]);
bpf_map_area_free(pages);
return NULL;
}
@@ -189,11 +181,10 @@ 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_pages_free(pages, nr_pages);
bpf_map_area_free(pages);
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4f893d2ac4fd..5c13782839f3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -559,6 +559,47 @@ void bpf_map_container_free(void *container)
kvfree(container);
}
+void *bpf_map_pages_alloc(struct bpf_map *map, struct page **pages,
+ int nr_meta_pages, int nr_data_pages, int nid,
+ gfp_t flags, unsigned int order)
+{
+ int nr_pages = nr_meta_pages + nr_data_pages;
+ struct mem_cgroup *memcg, *old_memcg;
+ struct page *page;
+ int i;
+
+ memcg = bpf_map_get_memcg(map);
+ old_memcg = set_active_memcg(memcg);
+ for (i = 0; i < nr_pages; i++) {
+ page = alloc_pages_node(nid, flags | __GFP_ACCOUNT, order);
+ if (!page) {
+ nr_pages = i;
+ set_active_memcg(old_memcg);
+ goto err_free_pages;
+ }
+ pages[i] = page;
+ if (i >= nr_meta_pages)
+ pages[nr_data_pages + i] = page;
+ }
+ set_active_memcg(old_memcg);
+
+ return pages;
+
+err_free_pages:
+ for (i = 0; i < nr_pages; i++)
+ __free_page(pages[i]);
+
+ return NULL;
+}
+
+void bpf_map_pages_free(struct page **pages, int nr_pages)
+{
+ int i;
+
+ for (i = 0; i < nr_pages; i++)
+ __free_page(pages[i]);
+}
+
static int bpf_map_kptr_off_cmp(const void *a, const void *b)
{
const struct bpf_map_value_off_desc *off_desc1 = a, *off_desc2 = b;
--
2.17.1
Powered by blists - more mailing lists