Re: [PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
On 7/31/15 1:50 AM, xiakaixu wrote: 于 2015/7/30 9:44, Alexei Starovoitov 写道: On 7/29/15 4:17 PM, Daniel Borkmann wrote: -if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) +if (map->map_type >= BPF_MAP_TYPE_PROG_ARRAY) /* 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); When we are going to add a new map type to the eBPF framework that is not an fd_array_map thing, this assumption of map->map_type >= BPF_MAP_TYPE_PROG_ARRAY might not hold then ... Also I think here changing == to >= is probably unnecessary. prog_array needs to do it because of circular dependency whereas perf_event_array cannot have it. Even when we attach bpf prog to perf_event and then add it to perf_event_array used by the same prog, right? Please test such scenario just in case. Not sure completely understand what you mean. You know, we can attach bpf_prog to kprobe events. For now, we limit few event types, only PERF_EVENT_RAW & PERF_EVENT_HARDWARE event can be accessed in bpf_perf_event_read(). Seems like the dependency scenario won't happen. ahh, yes, you're correct. There is no circular dependency. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
于 2015/7/30 9:44, Alexei Starovoitov 写道: > On 7/29/15 4:17 PM, Daniel Borkmann wrote: >>> -if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) >>> +if (map->map_type >= BPF_MAP_TYPE_PROG_ARRAY) >>> /* 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); >> >> When we are going to add a new map type to the eBPF framework that is not >> an fd_array_map thing, this assumption of map->map_type >= >> BPF_MAP_TYPE_PROG_ARRAY >> might not hold then ... > > Also I think here changing == to >= is probably unnecessary. > prog_array needs to do it because of circular dependency > whereas perf_event_array cannot have it. > Even when we attach bpf prog to perf_event and then add it to > perf_event_array used by the same prog, right? > Please test such scenario just in case. Not sure completely understand what you mean. You know, we can attach bpf_prog to kprobe events. For now, we limit few event types, only PERF_EVENT_RAW & PERF_EVENT_HARDWARE event can be accessed in bpf_perf_event_read(). Seems like the dependency scenario won't happen. I will add the event decrement refcnt function to map_free in V5. right? > > > . > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
On 7/31/15 1:50 AM, xiakaixu wrote: 于 2015/7/30 9:44, Alexei Starovoitov 写道: On 7/29/15 4:17 PM, Daniel Borkmann wrote: -if (map-map_type == BPF_MAP_TYPE_PROG_ARRAY) +if (map-map_type = BPF_MAP_TYPE_PROG_ARRAY) /* 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); When we are going to add a new map type to the eBPF framework that is not an fd_array_map thing, this assumption of map-map_type = BPF_MAP_TYPE_PROG_ARRAY might not hold then ... Also I think here changing == to = is probably unnecessary. prog_array needs to do it because of circular dependency whereas perf_event_array cannot have it. Even when we attach bpf prog to perf_event and then add it to perf_event_array used by the same prog, right? Please test such scenario just in case. Not sure completely understand what you mean. You know, we can attach bpf_prog to kprobe events. For now, we limit few event types, only PERF_EVENT_RAW PERF_EVENT_HARDWARE event can be accessed in bpf_perf_event_read(). Seems like the dependency scenario won't happen. ahh, yes, you're correct. There is no circular dependency. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
于 2015/7/30 9:44, Alexei Starovoitov 写道: On 7/29/15 4:17 PM, Daniel Borkmann wrote: -if (map-map_type == BPF_MAP_TYPE_PROG_ARRAY) +if (map-map_type = BPF_MAP_TYPE_PROG_ARRAY) /* 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); When we are going to add a new map type to the eBPF framework that is not an fd_array_map thing, this assumption of map-map_type = BPF_MAP_TYPE_PROG_ARRAY might not hold then ... Also I think here changing == to = is probably unnecessary. prog_array needs to do it because of circular dependency whereas perf_event_array cannot have it. Even when we attach bpf prog to perf_event and then add it to perf_event_array used by the same prog, right? Please test such scenario just in case. Not sure completely understand what you mean. You know, we can attach bpf_prog to kprobe events. For now, we limit few event types, only PERF_EVENT_RAW PERF_EVENT_HARDWARE event can be accessed in bpf_perf_event_read(). Seems like the dependency scenario won't happen. I will add the event decrement refcnt function to map_free in V5. right? . -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
On 7/29/15 4:17 PM, Daniel Borkmann wrote: -if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) +if (map->map_type >= BPF_MAP_TYPE_PROG_ARRAY) /* 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); When we are going to add a new map type to the eBPF framework that is not an fd_array_map thing, this assumption of map->map_type >= BPF_MAP_TYPE_PROG_ARRAY might not hold then ... Also I think here changing == to >= is probably unnecessary. prog_array needs to do it because of circular dependency whereas perf_event_array cannot have it. Even when we attach bpf prog to perf_event and then add it to perf_event_array used by the same prog, right? Please test such scenario just in case. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
On 07/28/2015 01:17 PM, Kaixu Xia wrote:
From: Wang Nan
According to the comments from Daniel, 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.
Tested the samples/bpf/tracex5 after this patch:
$ sudo ./tracex5
...
dd-1051 [000] d...26.682903: : mmap
dd-1051 [000] d...26.698348: : syscall=102 (one of get/set
uid/pid/gid)
dd-1051 [000] d...26.703892: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.705847: : write(fd=1, buf=0078c010,
size=512)
dd-1051 [000] d...26.707914: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.710988: : write(fd=1, buf=0078c010,
size=512)
dd-1051 [000] d...26.711865: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.712704: : write(fd=1, buf=0078c010,
size=512)
...
Signed-off-by: Wang Nan
Signed-off-by: Kaixu Xia
---
include/linux/bpf.h | 6 ++-
kernel/bpf/arraymap.c | 104 +++---
kernel/bpf/syscall.c | 4 +-
3 files changed, 80 insertions(+), 34 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4383476..610b730 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -130,6 +130,8 @@ struct bpf_prog_aux {
};
};
+struct fd_array_map_ops;
+
struct bpf_array {
struct bpf_map map;
u32 elem_size;
@@ -140,15 +142,17 @@ struct bpf_array {
*/
enum bpf_prog_type owner_prog_type;
bool owner_jited;
+ const struct fd_array_map_ops* fd_ops;
union {
char value[0] __aligned(8);
+ void *ptrs[0] __aligned(8);
struct bpf_prog *prog[0] __aligned(8);
After your conversion, prog member from the union is not used here anymore
(only as offsetof(...) in JITs). We should probably get rid of it then.
};
};
#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..4784cdc 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -150,15 +150,62 @@ static int __init register_array_map(void)
}
late_initcall(register_array_map);
-static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+struct fd_array_map_ops {
+ void *(*get_ptr)(struct bpf_array *array, int fd);
+ void (*put_ptr)(struct bpf_array *array, void *ptr);
+};
+
+static void *prog_fd_array_get_ptr(struct bpf_array *array, int fd)
+{
+ 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(struct bpf_array *array __maybe_unused,
+ void *ptr)
array member seems not to be used in both implementations. It should then
probably not be part of the API?
+{
+ struct bpf_prog *prog = (struct bpf_prog *)ptr;
No cast on void * needed.
+
+ bpf_prog_put_rcu(prog);
+}
+
+static const struct fd_array_map_ops prog_fd_array_map_ops = {
+ .get_ptr= prog_fd_array_get_ptr,
+ .put_ptr= prog_fd_array_put_ptr,
+};
+
+static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr,
+ const struct fd_array_map_ops *ops)
{
- /* only bpf_prog file descriptors can be stored in prog_array map */
+ struct bpf_map *map;
+ struct bpf_array *array;
+
+ /* 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);
+
+ map = array_map_alloc(attr);
+ if (IS_ERR(map))
+ return map;
+
+ array = container_of(map, struct bpf_array, map);
+ array->fd_ops = ops;
+ return map;
+}
+
+static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+{
+ return fd_array_map_alloc(attr, _fd_array_map_ops);
}
-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 +214,21 @@ static void prog_array_map_free(struct bpf_map *map)
/* make sure it's empty */
for (i = 0; i < array->map.max_entries; i++)
-
Re: [PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
On 07/28/2015 01:17 PM, Kaixu Xia wrote:
From: Wang Nan wangn...@huawei.com
According to the comments from Daniel, 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.
Tested the samples/bpf/tracex5 after this patch:
$ sudo ./tracex5
...
dd-1051 [000] d...26.682903: : mmap
dd-1051 [000] d...26.698348: : syscall=102 (one of get/set
uid/pid/gid)
dd-1051 [000] d...26.703892: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.705847: : write(fd=1, buf=0078c010,
size=512)
dd-1051 [000] d...26.707914: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.710988: : write(fd=1, buf=0078c010,
size=512)
dd-1051 [000] d...26.711865: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.712704: : write(fd=1, buf=0078c010,
size=512)
...
Signed-off-by: Wang Nan wangn...@huawei.com
Signed-off-by: Kaixu Xia xiaka...@huawei.com
---
include/linux/bpf.h | 6 ++-
kernel/bpf/arraymap.c | 104 +++---
kernel/bpf/syscall.c | 4 +-
3 files changed, 80 insertions(+), 34 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4383476..610b730 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -130,6 +130,8 @@ struct bpf_prog_aux {
};
};
+struct fd_array_map_ops;
+
struct bpf_array {
struct bpf_map map;
u32 elem_size;
@@ -140,15 +142,17 @@ struct bpf_array {
*/
enum bpf_prog_type owner_prog_type;
bool owner_jited;
+ const struct fd_array_map_ops* fd_ops;
union {
char value[0] __aligned(8);
+ void *ptrs[0] __aligned(8);
struct bpf_prog *prog[0] __aligned(8);
After your conversion, prog member from the union is not used here anymore
(only as offsetof(...) in JITs). We should probably get rid of it then.
};
};
#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..4784cdc 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -150,15 +150,62 @@ static int __init register_array_map(void)
}
late_initcall(register_array_map);
-static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+struct fd_array_map_ops {
+ void *(*get_ptr)(struct bpf_array *array, int fd);
+ void (*put_ptr)(struct bpf_array *array, void *ptr);
+};
+
+static void *prog_fd_array_get_ptr(struct bpf_array *array, int fd)
+{
+ 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(struct bpf_array *array __maybe_unused,
+ void *ptr)
array member seems not to be used in both implementations. It should then
probably not be part of the API?
+{
+ struct bpf_prog *prog = (struct bpf_prog *)ptr;
No cast on void * needed.
+
+ bpf_prog_put_rcu(prog);
+}
+
+static const struct fd_array_map_ops prog_fd_array_map_ops = {
+ .get_ptr= prog_fd_array_get_ptr,
+ .put_ptr= prog_fd_array_put_ptr,
+};
+
+static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr,
+ const struct fd_array_map_ops *ops)
{
- /* only bpf_prog file descriptors can be stored in prog_array map */
+ struct bpf_map *map;
+ struct bpf_array *array;
+
+ /* 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);
+
+ map = array_map_alloc(attr);
+ if (IS_ERR(map))
+ return map;
+
+ array = container_of(map, struct bpf_array, map);
+ array-fd_ops = ops;
+ return map;
+}
+
+static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+{
+ return fd_array_map_alloc(attr, prog_fd_array_map_ops);
}
-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 +214,21 @@ static void prog_array_map_free(struct bpf_map *map)
/* make sure it's empty */
Re: [PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
On 7/29/15 4:17 PM, Daniel Borkmann wrote: -if (map-map_type == BPF_MAP_TYPE_PROG_ARRAY) +if (map-map_type = BPF_MAP_TYPE_PROG_ARRAY) /* 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); When we are going to add a new map type to the eBPF framework that is not an fd_array_map thing, this assumption of map-map_type = BPF_MAP_TYPE_PROG_ARRAY might not hold then ... Also I think here changing == to = is probably unnecessary. prog_array needs to do it because of circular dependency whereas perf_event_array cannot have it. Even when we attach bpf prog to perf_event and then add it to perf_event_array used by the same prog, right? Please test such scenario just in case. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
From: Wang Nan
According to the comments from Daniel, 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.
Tested the samples/bpf/tracex5 after this patch:
$ sudo ./tracex5
...
dd-1051 [000] d...26.682903: : mmap
dd-1051 [000] d...26.698348: : syscall=102 (one of get/set
uid/pid/gid)
dd-1051 [000] d...26.703892: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.705847: : write(fd=1, buf=0078c010,
size=512)
dd-1051 [000] d...26.707914: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.710988: : write(fd=1, buf=0078c010,
size=512)
dd-1051 [000] d...26.711865: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.712704: : write(fd=1, buf=0078c010,
size=512)
...
Signed-off-by: Wang Nan
Signed-off-by: Kaixu Xia
---
include/linux/bpf.h | 6 ++-
kernel/bpf/arraymap.c | 104 +++---
kernel/bpf/syscall.c | 4 +-
3 files changed, 80 insertions(+), 34 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4383476..610b730 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -130,6 +130,8 @@ struct bpf_prog_aux {
};
};
+struct fd_array_map_ops;
+
struct bpf_array {
struct bpf_map map;
u32 elem_size;
@@ -140,15 +142,17 @@ struct bpf_array {
*/
enum bpf_prog_type owner_prog_type;
bool owner_jited;
+ const struct fd_array_map_ops* fd_ops;
union {
char value[0] __aligned(8);
+ void *ptrs[0] __aligned(8);
struct bpf_prog *prog[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..4784cdc 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -150,15 +150,62 @@ static int __init register_array_map(void)
}
late_initcall(register_array_map);
-static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+struct fd_array_map_ops {
+ void *(*get_ptr)(struct bpf_array *array, int fd);
+ void (*put_ptr)(struct bpf_array *array, void *ptr);
+};
+
+static void *prog_fd_array_get_ptr(struct bpf_array *array, int fd)
+{
+ 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(struct bpf_array *array __maybe_unused,
+ void *ptr)
+{
+ struct bpf_prog *prog = (struct bpf_prog *)ptr;
+
+ bpf_prog_put_rcu(prog);
+}
+
+static const struct fd_array_map_ops prog_fd_array_map_ops = {
+ .get_ptr= prog_fd_array_get_ptr,
+ .put_ptr= prog_fd_array_put_ptr,
+};
+
+static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr,
+ const struct fd_array_map_ops *ops)
{
- /* only bpf_prog file descriptors can be stored in prog_array map */
+ struct bpf_map *map;
+ struct bpf_array *array;
+
+ /* 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);
+
+ map = array_map_alloc(attr);
+ if (IS_ERR(map))
+ return map;
+
+ array = container_of(map, struct bpf_array, map);
+ array->fd_ops = ops;
+ return map;
+}
+
+static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+{
+ return fd_array_map_alloc(attr, _fd_array_map_ops);
}
-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 +214,21 @@ 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
[PATCH v4 1/4] bpf: Make the bpf_prog_array_map more generic
From: Wang Nan wangn...@huawei.com
According to the comments from Daniel, 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.
Tested the samples/bpf/tracex5 after this patch:
$ sudo ./tracex5
...
dd-1051 [000] d...26.682903: : mmap
dd-1051 [000] d...26.698348: : syscall=102 (one of get/set
uid/pid/gid)
dd-1051 [000] d...26.703892: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.705847: : write(fd=1, buf=0078c010,
size=512)
dd-1051 [000] d...26.707914: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.710988: : write(fd=1, buf=0078c010,
size=512)
dd-1051 [000] d...26.711865: : read(fd=0, buf=0078c010,
size=512)
dd-1051 [000] d...26.712704: : write(fd=1, buf=0078c010,
size=512)
...
Signed-off-by: Wang Nan wangn...@huawei.com
Signed-off-by: Kaixu Xia xiaka...@huawei.com
---
include/linux/bpf.h | 6 ++-
kernel/bpf/arraymap.c | 104 +++---
kernel/bpf/syscall.c | 4 +-
3 files changed, 80 insertions(+), 34 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4383476..610b730 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -130,6 +130,8 @@ struct bpf_prog_aux {
};
};
+struct fd_array_map_ops;
+
struct bpf_array {
struct bpf_map map;
u32 elem_size;
@@ -140,15 +142,17 @@ struct bpf_array {
*/
enum bpf_prog_type owner_prog_type;
bool owner_jited;
+ const struct fd_array_map_ops* fd_ops;
union {
char value[0] __aligned(8);
+ void *ptrs[0] __aligned(8);
struct bpf_prog *prog[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..4784cdc 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -150,15 +150,62 @@ static int __init register_array_map(void)
}
late_initcall(register_array_map);
-static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+struct fd_array_map_ops {
+ void *(*get_ptr)(struct bpf_array *array, int fd);
+ void (*put_ptr)(struct bpf_array *array, void *ptr);
+};
+
+static void *prog_fd_array_get_ptr(struct bpf_array *array, int fd)
+{
+ 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(struct bpf_array *array __maybe_unused,
+ void *ptr)
+{
+ struct bpf_prog *prog = (struct bpf_prog *)ptr;
+
+ bpf_prog_put_rcu(prog);
+}
+
+static const struct fd_array_map_ops prog_fd_array_map_ops = {
+ .get_ptr= prog_fd_array_get_ptr,
+ .put_ptr= prog_fd_array_put_ptr,
+};
+
+static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr,
+ const struct fd_array_map_ops *ops)
{
- /* only bpf_prog file descriptors can be stored in prog_array map */
+ struct bpf_map *map;
+ struct bpf_array *array;
+
+ /* 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);
+
+ map = array_map_alloc(attr);
+ if (IS_ERR(map))
+ return map;
+
+ array = container_of(map, struct bpf_array, map);
+ array-fd_ops = ops;
+ return map;
+}
+
+static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+{
+ return fd_array_map_alloc(attr, prog_fd_array_map_ops);
}
-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 +214,21 @@ 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;
}
