From: Roman Gushchin <guro@fb.com>
To: <bpf@vger.kernel.org>
Cc: <ast@kernel.org>, <daniel@iogearbox.net>,
<netdev@vger.kernel.org>, <andrii@kernel.org>,
<akpm@linux-foundation.org>, <linux-mm@kvack.org>,
<linux-kernel@vger.kernel.org>, <kernel-team@fb.com>
Subject: [PATCH bpf-next v9 32/34] bpf: eliminate rlimit-based memory accounting infra for bpf maps
Date: Tue, 1 Dec 2020 13:58:58 -0800 [thread overview]
Message-ID: <20201201215900.3569844-33-guro@fb.com> (raw)
In-Reply-To: <20201201215900.3569844-1-guro@fb.com>
Remove rlimit-based accounting infrastructure code, which is not used
anymore.
To provide a backward compatibility, use an approximation of the
bpf map memory footprint as a "memlock" value, available to a user
via map info. The approximation is based on the maximal number of
elements and key and value sizes.
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
---
include/linux/bpf.h | 12 ---
kernel/bpf/syscall.c | 96 ++++---------------
.../selftests/bpf/progs/bpf_iter_bpf_map.c | 2 +-
.../selftests/bpf/progs/map_ptr_kern.c | 7 --
4 files changed, 17 insertions(+), 100 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e1f2c95c15ec..61331a148cde 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -138,11 +138,6 @@ struct bpf_map_ops {
const struct bpf_iter_seq_info *iter_seq_info;
};
-struct bpf_map_memory {
- u32 pages;
- struct user_struct *user;
-};
-
struct bpf_map {
/* The first two cachelines with read-mostly members of which some
* are also accessed in fast-path (e.g. ops, max_entries).
@@ -163,7 +158,6 @@ struct bpf_map {
u32 btf_key_type_id;
u32 btf_value_type_id;
struct btf *btf;
- struct bpf_map_memory memory;
#ifdef CONFIG_MEMCG_KMEM
struct mem_cgroup *memcg;
#endif
@@ -1224,12 +1218,6 @@ void bpf_map_inc_with_uref(struct bpf_map *map);
struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map);
void bpf_map_put_with_uref(struct bpf_map *map);
void bpf_map_put(struct bpf_map *map);
-int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
-void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
-int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size);
-void bpf_map_charge_finish(struct bpf_map_memory *mem);
-void bpf_map_charge_move(struct bpf_map_memory *dst,
- struct bpf_map_memory *src);
void *bpf_map_area_alloc(u64 size, int numa_node);
void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
void bpf_map_area_free(void *base);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index dff3a5f62d7a..29096d96d989 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -128,7 +128,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
-static u32 bpf_map_value_size(struct bpf_map *map)
+static u32 bpf_map_value_size(const struct bpf_map *map)
{
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
@@ -346,77 +346,6 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
map->numa_node = bpf_map_attr_numa_node(attr);
}
-static int bpf_charge_memlock(struct user_struct *user, u32 pages)
-{
- unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
- if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) {
- atomic_long_sub(pages, &user->locked_vm);
- return -EPERM;
- }
- return 0;
-}
-
-static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
-{
- if (user)
- atomic_long_sub(pages, &user->locked_vm);
-}
-
-int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size)
-{
- u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT;
- struct user_struct *user;
- int ret;
-
- if (size >= U32_MAX - PAGE_SIZE)
- return -E2BIG;
-
- user = get_current_user();
- ret = bpf_charge_memlock(user, pages);
- if (ret) {
- free_uid(user);
- return ret;
- }
-
- mem->pages = pages;
- mem->user = user;
-
- return 0;
-}
-
-void bpf_map_charge_finish(struct bpf_map_memory *mem)
-{
- bpf_uncharge_memlock(mem->user, mem->pages);
- free_uid(mem->user);
-}
-
-void bpf_map_charge_move(struct bpf_map_memory *dst,
- struct bpf_map_memory *src)
-{
- *dst = *src;
-
- /* Make sure src will not be used for the redundant uncharging. */
- memset(src, 0, sizeof(struct bpf_map_memory));
-}
-
-int bpf_map_charge_memlock(struct bpf_map *map, u32 pages)
-{
- int ret;
-
- ret = bpf_charge_memlock(map->memory.user, pages);
- if (ret)
- return ret;
- map->memory.pages += pages;
- return ret;
-}
-
-void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages)
-{
- bpf_uncharge_memlock(map->memory.user, pages);
- map->memory.pages -= pages;
-}
-
static int bpf_map_alloc_id(struct bpf_map *map)
{
int id;
@@ -524,14 +453,11 @@ static void bpf_map_release_memcg(struct bpf_map *map)
static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
- struct bpf_map_memory mem;
- bpf_map_charge_move(&mem, &map->memory);
security_bpf_map_free(map);
bpf_map_release_memcg(map);
/* implementation dependent freeing */
map->ops->map_free(map);
- bpf_map_charge_finish(&mem);
}
static void bpf_map_put_uref(struct bpf_map *map)
@@ -592,6 +518,19 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f)
}
#ifdef CONFIG_PROC_FS
+/* Provides an approximation of the map's memory footprint.
+ * Used only to provide a backward compatibility and display
+ * a reasonable "memlock" info.
+ */
+static unsigned long bpf_map_memory_footprint(const struct bpf_map *map)
+{
+ unsigned long size;
+
+ size = round_up(map->key_size + bpf_map_value_size(map), 8);
+
+ return round_up(map->max_entries * size, PAGE_SIZE);
+}
+
static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_map *map = filp->private_data;
@@ -610,7 +549,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
"value_size:\t%u\n"
"max_entries:\t%u\n"
"map_flags:\t%#x\n"
- "memlock:\t%llu\n"
+ "memlock:\t%lu\n"
"map_id:\t%u\n"
"frozen:\t%u\n",
map->map_type,
@@ -618,7 +557,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
map->value_size,
map->max_entries,
map->map_flags,
- map->memory.pages * 1ULL << PAGE_SHIFT,
+ bpf_map_memory_footprint(map),
map->id,
READ_ONCE(map->frozen));
if (type) {
@@ -861,7 +800,6 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
static int map_create(union bpf_attr *attr)
{
int numa_node = bpf_map_attr_numa_node(attr);
- struct bpf_map_memory mem;
struct bpf_map *map;
int f_flags;
int err;
@@ -960,9 +898,7 @@ static int map_create(union bpf_attr *attr)
security_bpf_map_free(map);
free_map:
btf_put(map->btf);
- bpf_map_charge_move(&mem, &map->memory);
map->ops->map_free(map);
- bpf_map_charge_finish(&mem);
return err;
}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
index 08651b23edba..b83b5d2e17dc 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
@@ -23,6 +23,6 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter,
map->usercnt.counter,
- map->memory.user->locked_vm.counter);
+ 0LLU);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index c325405751e2..d8850bc6a9f1 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -26,17 +26,12 @@ __u32 g_line = 0;
return 0; \
})
-struct bpf_map_memory {
- __u32 pages;
-} __attribute__((preserve_access_index));
-
struct bpf_map {
enum bpf_map_type map_type;
__u32 key_size;
__u32 value_size;
__u32 max_entries;
__u32 id;
- struct bpf_map_memory memory;
} __attribute__((preserve_access_index));
static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size,
@@ -47,7 +42,6 @@ static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size,
VERIFY(map->value_size == value_size);
VERIFY(map->max_entries == max_entries);
VERIFY(map->id > 0);
- VERIFY(map->memory.pages > 0);
return 1;
}
@@ -60,7 +54,6 @@ static inline int check_bpf_map_ptr(struct bpf_map *indirect,
VERIFY(indirect->value_size == direct->value_size);
VERIFY(indirect->max_entries == direct->max_entries);
VERIFY(indirect->id == direct->id);
- VERIFY(indirect->memory.pages == direct->memory.pages);
return 1;
}
--
2.26.2
next prev parent reply other threads:[~2020-12-01 22:02 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-01 21:58 [PATCH bpf-next v9 00/34] bpf: switch to memcg-based memory accounting Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 01/34] mm: memcontrol: use helpers to read page's memcg data Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 02/34] mm: memcontrol/slab: use helpers to access slab page's memcg_data Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 03/34] mm: introduce page memcg flags Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 04/34] mm: convert page kmemcg type to a page memcg flag Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 05/34] bpf: memcg-based memory accounting for bpf progs Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 06/34] bpf: prepare for memcg-based memory accounting for bpf maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 07/34] bpf: " Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 08/34] bpf: refine memcg-based memory accounting for arraymap maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 09/34] bpf: refine memcg-based memory accounting for cpumap maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 10/34] bpf: memcg-based memory accounting for cgroup storage maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 11/34] bpf: refine memcg-based memory accounting for devmap maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 12/34] bpf: refine memcg-based memory accounting for hashtab maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 13/34] bpf: memcg-based memory accounting for lpm_trie maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 14/34] bpf: memcg-based memory accounting for bpf ringbuffer Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 15/34] bpf: memcg-based memory accounting for bpf local storage maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 16/34] bpf: refine memcg-based memory accounting for sockmap and sockhash maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 17/34] bpf: refine memcg-based memory accounting for xskmap maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 18/34] bpf: eliminate rlimit-based memory accounting for arraymap maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 19/34] bpf: eliminate rlimit-based memory accounting for bpf_struct_ops maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 20/34] bpf: eliminate rlimit-based memory accounting for cpumap maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 21/34] bpf: eliminate rlimit-based memory accounting for cgroup storage maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 22/34] bpf: eliminate rlimit-based memory accounting for devmap maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 23/34] bpf: eliminate rlimit-based memory accounting for hashtab maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 24/34] bpf: eliminate rlimit-based memory accounting for lpm_trie maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 25/34] bpf: eliminate rlimit-based memory accounting for queue_stack_maps maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 26/34] bpf: eliminate rlimit-based memory accounting for reuseport_array maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 27/34] bpf: eliminate rlimit-based memory accounting for bpf ringbuffer Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 28/34] bpf: eliminate rlimit-based memory accounting for sockmap and sockhash maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 29/34] bpf: eliminate rlimit-based memory accounting for stackmap maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 30/34] bpf: eliminate rlimit-based memory accounting for xskmap maps Roman Gushchin
2020-12-01 21:58 ` [PATCH bpf-next v9 31/34] bpf: eliminate rlimit-based memory accounting for bpf local storage maps Roman Gushchin
2020-12-01 21:58 ` Roman Gushchin [this message]
2020-12-01 21:58 ` [PATCH bpf-next v9 33/34] bpf: eliminate rlimit-based memory accounting for bpf progs Roman Gushchin
2020-12-01 21:59 ` [PATCH bpf-next v9 34/34] bpf: samples: do not touch RLIMIT_MEMLOCK Roman Gushchin
2020-12-03 2:50 ` [PATCH bpf-next v9 00/34] bpf: switch to memcg-based memory accounting patchwork-bot+netdevbpf
2020-12-03 2:54 ` Alexei Starovoitov
2020-12-03 3:26 ` Roman Gushchin
2020-12-05 0:37 ` Daniel Borkmann
2020-12-08 2:53 ` Andrii Nakryiko
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=20201201215900.3569844-33-guro@fb.com \
--to=guro@fb.com \
--cc=akpm@linux-foundation.org \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
/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).