[PATCH v7 2/5] bpf: Make the bpf_prog_array_map more generic

From: Kaixu Xia
Date: Thu Aug 06 2015 - 03:05:21 EST


From: Wang Nan <wangnan0@xxxxxxxxxx>

All the map backends are of generic nature. In order to avoid
adding much special code into the eBPF core, rewrite part of
the bpf_prog_array map code and make it more generic. So the
new perf_event_array map type can reuse most of code with
bpf_prog_array map and add fewer lines of special code.

Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
Signed-off-by: Kaixu Xia <xiakaixu@xxxxxxxxxx>
---
arch/x86/net/bpf_jit_comp.c | 6 ++--
include/linux/bpf.h | 8 +++--
kernel/bpf/arraymap.c | 80 +++++++++++++++++++++++++++------------------
kernel/bpf/core.c | 2 +-
kernel/bpf/syscall.c | 2 +-
5 files changed, 60 insertions(+), 38 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index ec5214f..70efcd0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -246,7 +246,7 @@ static void emit_prologue(u8 **pprog)
* goto out;
* if (++tail_call_cnt > MAX_TAIL_CALL_CNT)
* goto out;
- * prog = array->prog[index];
+ * prog = array->ptrs[index];
* if (prog == NULL)
* goto out;
* goto *(prog->bpf_func + prologue_size);
@@ -284,9 +284,9 @@ static void emit_bpf_tail_call(u8 **pprog)
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */

- /* prog = array->prog[index]; */
+ /* prog = array->ptrs[index]; */
EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */
- offsetof(struct bpf_array, prog));
+ offsetof(struct bpf_array, ptrs));
EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */

/* if (prog == NULL)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 139d6d2..d495211 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -24,6 +24,10 @@ struct bpf_map_ops {
void *(*map_lookup_elem)(struct bpf_map *map, void *key);
int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
int (*map_delete_elem)(struct bpf_map *map, void *key);
+
+ /* funcs called by prog_array and perf_event_array map */
+ void *(*map_fd_get_ptr) (struct bpf_map *map, int fd);
+ void (*map_fd_put_ptr) (void *ptr);
};

struct bpf_map {
@@ -142,13 +146,13 @@ struct bpf_array {
bool owner_jited;
union {
char value[0] __aligned(8);
- struct bpf_prog *prog[0] __aligned(8);
+ void *ptrs[0] __aligned(8);
};
};
#define MAX_TAIL_CALL_CNT 32

u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
-void bpf_prog_array_map_clear(struct bpf_map *map);
+void bpf_fd_array_map_clear(struct bpf_map *map);
bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cb31229..45df657 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -150,15 +150,15 @@ static int __init register_array_map(void)
}
late_initcall(register_array_map);

-static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr)
{
- /* only bpf_prog file descriptors can be stored in prog_array map */
+ /* only file descriptors can be stored in this type of map */
if (attr->value_size != sizeof(u32))
return ERR_PTR(-EINVAL);
return array_map_alloc(attr);
}

-static void prog_array_map_free(struct bpf_map *map)
+static void fd_array_map_free(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
@@ -167,21 +167,21 @@ static void prog_array_map_free(struct bpf_map *map)

/* make sure it's empty */
for (i = 0; i < array->map.max_entries; i++)
- BUG_ON(array->prog[i] != NULL);
+ BUG_ON(array->ptrs[i] != NULL);
kvfree(array);
}

-static void *prog_array_map_lookup_elem(struct bpf_map *map, void *key)
+static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
{
return NULL;
}

/* only called from syscall */
-static int prog_array_map_update_elem(struct bpf_map *map, void *key,
- void *value, u64 map_flags)
+static int fd_array_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
- struct bpf_prog *prog, *old_prog;
+ void *new_ptr, *old_ptr;
u32 index = *(u32 *)key, ufd;

if (map_flags != BPF_ANY)
@@ -191,57 +191,75 @@ static int prog_array_map_update_elem(struct bpf_map *map, void *key,
return -E2BIG;

ufd = *(u32 *)value;
- prog = bpf_prog_get(ufd);
- if (IS_ERR(prog))
- return PTR_ERR(prog);
-
- if (!bpf_prog_array_compatible(array, prog)) {
- bpf_prog_put(prog);
- return -EINVAL;
- }
+ new_ptr = map->ops->map_fd_get_ptr(map, ufd);
+ if (IS_ERR(new_ptr))
+ return PTR_ERR(new_ptr);

- old_prog = xchg(array->prog + index, prog);
- if (old_prog)
- bpf_prog_put_rcu(old_prog);
+ old_ptr = xchg(array->ptrs + index, new_ptr);
+ if (old_ptr)
+ map->ops->map_fd_put_ptr(old_ptr);

return 0;
}

-static int prog_array_map_delete_elem(struct bpf_map *map, void *key)
+static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
- struct bpf_prog *old_prog;
+ void *old_ptr;
u32 index = *(u32 *)key;

if (index >= array->map.max_entries)
return -E2BIG;

- old_prog = xchg(array->prog + index, NULL);
- if (old_prog) {
- bpf_prog_put_rcu(old_prog);
+ old_ptr = xchg(array->ptrs + index, NULL);
+ if (old_ptr) {
+ map->ops->map_fd_put_ptr(old_ptr);
return 0;
} else {
return -ENOENT;
}
}

+static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ struct bpf_prog *prog = bpf_prog_get(fd);
+ if (IS_ERR(prog))
+ return prog;
+
+ if (!bpf_prog_array_compatible(array, prog)) {
+ bpf_prog_put(prog);
+ return ERR_PTR(-EINVAL);
+ }
+ return prog;
+}
+
+static void prog_fd_array_put_ptr(void *ptr)
+{
+ struct bpf_prog *prog = ptr;
+
+ bpf_prog_put_rcu(prog);
+}
+
/* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_prog_array_map_clear(struct bpf_map *map)
+void bpf_fd_array_map_clear(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;

for (i = 0; i < array->map.max_entries; i++)
- prog_array_map_delete_elem(map, &i);
+ fd_array_map_delete_elem(map, &i);
}

static const struct bpf_map_ops prog_array_ops = {
- .map_alloc = prog_array_map_alloc,
- .map_free = prog_array_map_free,
+ .map_alloc = fd_array_map_alloc,
+ .map_free = fd_array_map_free,
.map_get_next_key = array_map_get_next_key,
- .map_lookup_elem = prog_array_map_lookup_elem,
- .map_update_elem = prog_array_map_update_elem,
- .map_delete_elem = prog_array_map_delete_elem,
+ .map_lookup_elem = fd_array_map_lookup_elem,
+ .map_update_elem = fd_array_map_update_elem,
+ .map_delete_elem = fd_array_map_delete_elem,
+ .map_fd_get_ptr = prog_fd_array_get_ptr,
+ .map_fd_put_ptr = prog_fd_array_put_ptr,
};

static struct bpf_map_type_list prog_array_type __read_mostly = {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index fafa741..67c380c 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -450,7 +450,7 @@ select_insn:

tail_call_cnt++;

- prog = READ_ONCE(array->prog[index]);
+ prog = READ_ONCE(array->ptrs[index]);
if (unlikely(!prog))
goto out;

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a1b14d1..dc9b464 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -72,7 +72,7 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
/* prog_array stores refcnt-ed bpf_prog pointers
* release them all when user space closes prog_array_fd
*/
- bpf_prog_array_map_clear(map);
+ bpf_fd_array_map_clear(map);

bpf_map_put(map);
return 0;
--
1.8.3.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/