* [PATCH v3 net-next 5/8] bpf: Add BPF_MAP_GET_FD_BY_ID
From: Martin KaFai Lau @ 2017-06-05 19:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <cover.1496686606.git.kafai@fb.com>
Add BPF_MAP_GET_FD_BY_ID command to allow user to get a fd
from a bpf_map's ID.
bpf_map_inc_not_zero() is added and is called with map_idr_lock
held.
__bpf_map_put() is also added which has the 'bool do_idr_lock'
param to decide if the map_idr_lock should be acquired when
freeing the map->id.
In the error path of bpf_map_inc_not_zero(), it may have to
call __bpf_map_put(map, false) which does not need
to take the map_idr_lock when freeing the map->id.
It is currently limited to CAP_SYS_ADMIN which we can
consider to lift it in followup patches.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
include/uapi/linux/bpf.h | 2 +
kernel/bpf/syscall.c | 95 +++++++++++++++++++++++++++++++++++++++++++-----
2 files changed, 87 insertions(+), 10 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d70cfed19d5e..dd23f47ff00c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -85,6 +85,7 @@ enum bpf_cmd {
BPF_PROG_GET_NEXT_ID,
BPF_MAP_GET_NEXT_ID,
BPF_PROG_GET_FD_BY_ID,
+ BPF_MAP_GET_FD_BY_ID,
};
enum bpf_map_type {
@@ -217,6 +218,7 @@ union bpf_attr {
union {
__u32 start_id;
__u32 prog_id;
+ __u32 map_id;
};
__u32 next_id;
};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index dc6253bb8ebb..1802bb9c47d9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -135,11 +135,19 @@ static int bpf_map_alloc_id(struct bpf_map *map)
return id > 0 ? 0 : id;
}
-static void bpf_map_free_id(struct bpf_map *map)
+static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
{
- spin_lock_bh(&map_idr_lock);
+ if (do_idr_lock)
+ spin_lock_bh(&map_idr_lock);
+ else
+ __acquire(&map_idr_lock);
+
idr_remove(&map_idr, map->id);
- spin_unlock_bh(&map_idr_lock);
+
+ if (do_idr_lock)
+ spin_unlock_bh(&map_idr_lock);
+ else
+ __release(&map_idr_lock);
}
/* called from workqueue */
@@ -163,16 +171,21 @@ static void bpf_map_put_uref(struct bpf_map *map)
/* decrement map refcnt and schedule it for freeing via workqueue
* (unrelying map implementation ops->map_free() might sleep)
*/
-void bpf_map_put(struct bpf_map *map)
+static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
{
if (atomic_dec_and_test(&map->refcnt)) {
/* bpf_map_free_id() must be called first */
- bpf_map_free_id(map);
+ bpf_map_free_id(map, do_idr_lock);
INIT_WORK(&map->work, bpf_map_free_deferred);
schedule_work(&map->work);
}
}
+void bpf_map_put(struct bpf_map *map)
+{
+ __bpf_map_put(map, true);
+}
+
void bpf_map_put_with_uref(struct bpf_map *map)
{
bpf_map_put_uref(map);
@@ -271,15 +284,20 @@ static int map_create(union bpf_attr *attr)
goto free_map;
err = bpf_map_new_fd(map);
- if (err < 0)
- /* failed to allocate fd */
- goto free_id;
+ if (err < 0) {
+ /* failed to allocate fd.
+ * bpf_map_put() is needed because the above
+ * bpf_map_alloc_id() has published the map
+ * to the userspace and the userspace may
+ * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID.
+ */
+ bpf_map_put(map);
+ return err;
+ }
trace_bpf_map_create(map, err);
return err;
-free_id:
- bpf_map_free_id(map);
free_map:
bpf_map_uncharge_memlock(map);
free_map_nouncharge:
@@ -331,6 +349,28 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
return map;
}
+/* map_idr_lock should have been held */
+static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
+ bool uref)
+{
+ int refold;
+
+ refold = __atomic_add_unless(&map->refcnt, 1, 0);
+
+ if (refold >= BPF_MAX_REFCNT) {
+ __bpf_map_put(map, false);
+ return ERR_PTR(-EBUSY);
+ }
+
+ if (!refold)
+ return ERR_PTR(-ENOENT);
+
+ if (uref)
+ atomic_inc(&map->usercnt);
+
+ return map;
+}
+
int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
{
return -ENOTSUPP;
@@ -1167,6 +1207,38 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr)
return fd;
}
+#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id
+
+static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
+{
+ struct bpf_map *map;
+ u32 id = attr->map_id;
+ int fd;
+
+ if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ spin_lock_bh(&map_idr_lock);
+ map = idr_find(&map_idr, id);
+ if (map)
+ map = bpf_map_inc_not_zero(map, true);
+ else
+ map = ERR_PTR(-ENOENT);
+ spin_unlock_bh(&map_idr_lock);
+
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ fd = bpf_map_new_fd(map);
+ if (fd < 0)
+ bpf_map_put(map);
+
+ return fd;
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@@ -1255,6 +1327,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_PROG_GET_FD_BY_ID:
err = bpf_prog_get_fd_by_id(&attr);
break;
+ case BPF_MAP_GET_FD_BY_ID:
+ err = bpf_map_get_fd_by_id(&attr);
+ break;
default:
err = -EINVAL;
break;
--
2.9.3
^ permalink raw reply related
* [PATCH v3 net-next 4/8] bpf: Add BPF_PROG_GET_FD_BY_ID
From: Martin KaFai Lau @ 2017-06-05 19:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <cover.1496686606.git.kafai@fb.com>
Add BPF_PROG_GET_FD_BY_ID command to allow user to get a fd
from a bpf_prog's ID.
bpf_prog_inc_not_zero() is added and is called with prog_idr_lock
held.
__bpf_prog_put() is also added which has the 'bool do_idr_lock'
param to decide if the prog_idr_lock should be acquired when
freeing the prog->id.
In the error path of bpf_prog_inc_not_zero(), it may have to
call __bpf_prog_put(map, false) which does not need
to take the prog_idr_lock when freeing the prog->id.
It is currently limited to CAP_SYS_ADMIN which we can
consider to lift it in followup patches.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
include/uapi/linux/bpf.h | 8 +++--
kernel/bpf/syscall.c | 91 ++++++++++++++++++++++++++++++++++++++++++------
2 files changed, 87 insertions(+), 12 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 629747a3f273..d70cfed19d5e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -84,6 +84,7 @@ enum bpf_cmd {
BPF_PROG_TEST_RUN,
BPF_PROG_GET_NEXT_ID,
BPF_MAP_GET_NEXT_ID,
+ BPF_PROG_GET_FD_BY_ID,
};
enum bpf_map_type {
@@ -212,8 +213,11 @@ union bpf_attr {
__u32 duration;
} test;
- struct { /* anonymous struct used by BPF_*_GET_NEXT_ID */
- __u32 start_id;
+ struct { /* anonymous struct used by BPF_*_GET_*_ID */
+ union {
+ __u32 start_id;
+ __u32 prog_id;
+ };
__u32 next_id;
};
} __attribute__((aligned(8)));
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2405feedb8c1..dc6253bb8ebb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -703,15 +703,23 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog)
return id > 0 ? 0 : id;
}
-static void bpf_prog_free_id(struct bpf_prog *prog)
+static void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
{
/* cBPF to eBPF migrations are currently not in the idr store. */
if (!prog->aux->id)
return;
- spin_lock_bh(&prog_idr_lock);
+ if (do_idr_lock)
+ spin_lock_bh(&prog_idr_lock);
+ else
+ __acquire(&prog_idr_lock);
+
idr_remove(&prog_idr, prog->aux->id);
- spin_unlock_bh(&prog_idr_lock);
+
+ if (do_idr_lock)
+ spin_unlock_bh(&prog_idr_lock);
+ else
+ __release(&prog_idr_lock);
}
static void __bpf_prog_put_rcu(struct rcu_head *rcu)
@@ -723,16 +731,21 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
bpf_prog_free(aux->prog);
}
-void bpf_prog_put(struct bpf_prog *prog)
+static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
trace_bpf_prog_put_rcu(prog);
/* bpf_prog_free_id() must be called first */
- bpf_prog_free_id(prog);
+ bpf_prog_free_id(prog, do_idr_lock);
bpf_prog_kallsyms_del(prog);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
}
+
+void bpf_prog_put(struct bpf_prog *prog)
+{
+ __bpf_prog_put(prog, true);
+}
EXPORT_SYMBOL_GPL(bpf_prog_put);
static int bpf_prog_release(struct inode *inode, struct file *filp)
@@ -814,6 +827,24 @@ struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
}
EXPORT_SYMBOL_GPL(bpf_prog_inc);
+/* prog_idr_lock should have been held */
+static struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
+{
+ int refold;
+
+ refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+
+ if (refold >= BPF_MAX_REFCNT) {
+ __bpf_prog_put(prog, false);
+ return ERR_PTR(-EBUSY);
+ }
+
+ if (!refold)
+ return ERR_PTR(-ENOENT);
+
+ return prog;
+}
+
static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
{
struct fd f = fdget(ufd);
@@ -928,16 +959,21 @@ static int bpf_prog_load(union bpf_attr *attr)
goto free_used_maps;
err = bpf_prog_new_fd(prog);
- if (err < 0)
- /* failed to allocate fd */
- goto free_id;
+ if (err < 0) {
+ /* failed to allocate fd.
+ * bpf_prog_put() is needed because the above
+ * bpf_prog_alloc_id() has published the prog
+ * to the userspace and the userspace may
+ * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID.
+ */
+ bpf_prog_put(prog);
+ return err;
+ }
bpf_prog_kallsyms_add(prog);
trace_bpf_prog_load(prog, err);
return err;
-free_id:
- bpf_prog_free_id(prog);
free_used_maps:
free_used_maps(prog->aux);
free_prog:
@@ -1099,6 +1135,38 @@ static int bpf_obj_get_next_id(const union bpf_attr *attr,
return err;
}
+#define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id
+
+static int bpf_prog_get_fd_by_id(const union bpf_attr *attr)
+{
+ struct bpf_prog *prog;
+ u32 id = attr->prog_id;
+ int fd;
+
+ if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ spin_lock_bh(&prog_idr_lock);
+ prog = idr_find(&prog_idr, id);
+ if (prog)
+ prog = bpf_prog_inc_not_zero(prog);
+ else
+ prog = ERR_PTR(-ENOENT);
+ spin_unlock_bh(&prog_idr_lock);
+
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ fd = bpf_prog_new_fd(prog);
+ if (fd < 0)
+ bpf_prog_put(prog);
+
+ return fd;
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@@ -1184,6 +1252,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
err = bpf_obj_get_next_id(&attr, uattr,
&map_idr, &map_idr_lock);
break;
+ case BPF_PROG_GET_FD_BY_ID:
+ err = bpf_prog_get_fd_by_id(&attr);
+ break;
default:
err = -EINVAL;
break;
--
2.9.3
^ permalink raw reply related
* [PATCH v3 net-next 2/8] bpf: Introduce bpf_map ID
From: Martin KaFai Lau @ 2017-06-05 19:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <cover.1496686606.git.kafai@fb.com>
This patch generates an unique ID for each created bpf_map.
The approach is similar to the earlier patch for bpf_prog ID.
It is worth to note that the bpf_map's ID and bpf_prog's ID
are in two independent ID spaces and both have the same valid range:
[1, INT_MAX).
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
include/linux/bpf.h | 1 +
kernel/bpf/syscall.c | 34 +++++++++++++++++++++++++++++++++-
2 files changed, 34 insertions(+), 1 deletion(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c5946d19f2ca..c32bace66d3d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -46,6 +46,7 @@ struct bpf_map {
u32 max_entries;
u32 map_flags;
u32 pages;
+ u32 id;
struct user_struct *user;
const struct bpf_map_ops *ops;
struct work_struct work;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2a1b32b470f1..4c3075b5d840 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -27,6 +27,8 @@
DEFINE_PER_CPU(int, bpf_prog_active);
static DEFINE_IDR(prog_idr);
static DEFINE_SPINLOCK(prog_idr_lock);
+static DEFINE_IDR(map_idr);
+static DEFINE_SPINLOCK(map_idr_lock);
int sysctl_unprivileged_bpf_disabled __read_mostly;
@@ -117,6 +119,29 @@ static void bpf_map_uncharge_memlock(struct bpf_map *map)
free_uid(user);
}
+static int bpf_map_alloc_id(struct bpf_map *map)
+{
+ int id;
+
+ spin_lock_bh(&map_idr_lock);
+ id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC);
+ if (id > 0)
+ map->id = id;
+ spin_unlock_bh(&map_idr_lock);
+
+ if (WARN_ON_ONCE(!id))
+ return -ENOSPC;
+
+ return id > 0 ? 0 : id;
+}
+
+static void bpf_map_free_id(struct bpf_map *map)
+{
+ spin_lock_bh(&map_idr_lock);
+ idr_remove(&map_idr, map->id);
+ spin_unlock_bh(&map_idr_lock);
+}
+
/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work)
{
@@ -141,6 +166,7 @@ static void bpf_map_put_uref(struct bpf_map *map)
void bpf_map_put(struct bpf_map *map)
{
if (atomic_dec_and_test(&map->refcnt)) {
+ bpf_map_free_id(map);
INIT_WORK(&map->work, bpf_map_free_deferred);
schedule_work(&map->work);
}
@@ -239,14 +265,20 @@ static int map_create(union bpf_attr *attr)
if (err)
goto free_map_nouncharge;
+ err = bpf_map_alloc_id(map);
+ if (err)
+ goto free_map;
+
err = bpf_map_new_fd(map);
if (err < 0)
/* failed to allocate fd */
- goto free_map;
+ goto free_id;
trace_bpf_map_create(map, err);
return err;
+free_id:
+ bpf_map_free_id(map);
free_map:
bpf_map_uncharge_memlock(map);
free_map_nouncharge:
--
2.9.3
^ permalink raw reply related
* [PATCH v3 net-next 7/8] bpf: Add BPF_OBJ_GET_INFO_BY_FD
From: Martin KaFai Lau @ 2017-06-05 19:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <cover.1496686606.git.kafai@fb.com>
A single BPF_OBJ_GET_INFO_BY_FD cmd is used to obtain the info
for both bpf_prog and bpf_map. The kernel can figure out the
fd is associated with a bpf_prog or bpf_map.
The suggested struct bpf_prog_info and struct bpf_map_info are
not meant to be a complete list and it is not the goal of this patch.
New fields can be added in the future patch.
The focus of this patch is to create the interface,
BPF_OBJ_GET_INFO_BY_FD cmd for exposing the bpf_prog's and
bpf_map's info.
The obj's info, which will be extended (and get bigger) over time, is
separated from the bpf_attr to avoid bloating the bpf_attr.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
include/linux/filter.h | 2 -
include/uapi/linux/bpf.h | 28 ++++++++
kernel/bpf/syscall.c | 163 ++++++++++++++++++++++++++++++++++++++++++-----
3 files changed, 174 insertions(+), 19 deletions(-)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1e2dddf21f3b..1fa26dc562ce 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -69,8 +69,6 @@ struct bpf_prog_aux;
/* BPF program can access up to 512 bytes of stack space. */
#define MAX_BPF_STACK 512
-#define BPF_TAG_SIZE 8
-
/* Helper macros for filter block array initializers. */
/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index dd23f47ff00c..9b2c10b45733 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -86,6 +86,7 @@ enum bpf_cmd {
BPF_MAP_GET_NEXT_ID,
BPF_PROG_GET_FD_BY_ID,
BPF_MAP_GET_FD_BY_ID,
+ BPF_OBJ_GET_INFO_BY_FD,
};
enum bpf_map_type {
@@ -222,6 +223,12 @@ union bpf_attr {
};
__u32 next_id;
};
+
+ struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
+ __u32 bpf_fd;
+ __u32 info_len;
+ __aligned_u64 info;
+ } info;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -686,4 +693,25 @@ struct xdp_md {
__u32 data_end;
};
+#define BPF_TAG_SIZE 8
+
+struct bpf_prog_info {
+ __u32 type;
+ __u32 id;
+ __u8 tag[BPF_TAG_SIZE];
+ __u32 jited_prog_len;
+ __u32 xlated_prog_len;
+ __aligned_u64 jited_prog_insns;
+ __aligned_u64 xlated_prog_insns;
+} __attribute__((aligned(8)));
+
+struct bpf_map_info {
+ __u32 type;
+ __u32 id;
+ __u32 key_size;
+ __u32 value_size;
+ __u32 max_entries;
+ __u32 map_flags;
+} __attribute__((aligned(8)));
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1802bb9c47d9..8942c820d620 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1239,6 +1239,145 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
return fd;
}
+static int check_uarg_tail_zero(void __user *uaddr,
+ size_t expected_size,
+ size_t actual_size)
+{
+ unsigned char __user *addr;
+ unsigned char __user *end;
+ unsigned char val;
+ int err;
+
+ if (actual_size <= expected_size)
+ return 0;
+
+ addr = uaddr + expected_size;
+ end = uaddr + actual_size;
+
+ for (; addr < end; addr++) {
+ err = get_user(val, addr);
+ if (err)
+ return err;
+ if (val)
+ return -E2BIG;
+ }
+
+ return 0;
+}
+
+static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ struct bpf_prog_info info = {};
+ u32 info_len = attr->info.info_len;
+ char __user *uinsns;
+ u32 ulen;
+ int err;
+
+ err = check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+ if (err)
+ return err;
+ info_len = min_t(u32, sizeof(info), info_len);
+
+ if (copy_from_user(&info, uinfo, info_len))
+ return err;
+
+ info.type = prog->type;
+ info.id = prog->aux->id;
+
+ memcpy(info.tag, prog->tag, sizeof(prog->tag));
+
+ if (!capable(CAP_SYS_ADMIN)) {
+ info.jited_prog_len = 0;
+ info.xlated_prog_len = 0;
+ goto done;
+ }
+
+ ulen = info.jited_prog_len;
+ info.jited_prog_len = prog->jited_len;
+ if (info.jited_prog_len && ulen) {
+ uinsns = u64_to_user_ptr(info.jited_prog_insns);
+ ulen = min_t(u32, info.jited_prog_len, ulen);
+ if (copy_to_user(uinsns, prog->bpf_func, ulen))
+ return -EFAULT;
+ }
+
+ ulen = info.xlated_prog_len;
+ info.xlated_prog_len = bpf_prog_size(prog->len);
+ if (info.xlated_prog_len && ulen) {
+ uinsns = u64_to_user_ptr(info.xlated_prog_insns);
+ ulen = min_t(u32, info.xlated_prog_len, ulen);
+ if (copy_to_user(uinsns, prog->insnsi, ulen))
+ return -EFAULT;
+ }
+
+done:
+ if (copy_to_user(uinfo, &info, info_len) ||
+ put_user(info_len, &uattr->info.info_len))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int bpf_map_get_info_by_fd(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ struct bpf_map_info info = {};
+ u32 info_len = attr->info.info_len;
+ int err;
+
+ err = check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+ if (err)
+ return err;
+ info_len = min_t(u32, sizeof(info), info_len);
+
+ info.type = map->map_type;
+ info.id = map->id;
+ info.key_size = map->key_size;
+ info.value_size = map->value_size;
+ info.max_entries = map->max_entries;
+ info.map_flags = map->map_flags;
+
+ if (copy_to_user(uinfo, &info, info_len) ||
+ put_user(info_len, &uattr->info.info_len))
+ return -EFAULT;
+
+ return 0;
+}
+
+#define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
+
+static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ int ufd = attr->info.bpf_fd;
+ struct fd f;
+ int err;
+
+ if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD))
+ return -EINVAL;
+
+ f = fdget(ufd);
+ if (!f.file)
+ return -EBADFD;
+
+ if (f.file->f_op == &bpf_prog_fops)
+ err = bpf_prog_get_info_by_fd(f.file->private_data, attr,
+ uattr);
+ else if (f.file->f_op == &bpf_map_fops)
+ err = bpf_map_get_info_by_fd(f.file->private_data, attr,
+ uattr);
+ else
+ err = -EINVAL;
+
+ fdput(f);
+ return err;
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@@ -1258,23 +1397,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
* user-space does not rely on any kernel feature
* extensions we dont know about yet.
*/
- if (size > sizeof(attr)) {
- unsigned char __user *addr;
- unsigned char __user *end;
- unsigned char val;
-
- addr = (void __user *)uattr + sizeof(attr);
- end = (void __user *)uattr + size;
-
- for (; addr < end; addr++) {
- err = get_user(val, addr);
- if (err)
- return err;
- if (val)
- return -E2BIG;
- }
- size = sizeof(attr);
- }
+ err = check_uarg_tail_zero(uattr, sizeof(attr), size);
+ if (err)
+ return err;
+ size = min_t(u32, size, sizeof(attr));
/* copy attributes from user space, may be less than sizeof(bpf_attr) */
if (copy_from_user(&attr, uattr, size) != 0)
@@ -1330,6 +1456,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_MAP_GET_FD_BY_ID:
err = bpf_map_get_fd_by_id(&attr);
break;
+ case BPF_OBJ_GET_INFO_BY_FD:
+ err = bpf_obj_get_info_by_fd(&attr, uattr);
+ break;
default:
err = -EINVAL;
break;
--
2.9.3
^ permalink raw reply related
* [PATCH v3 net-next 6/8] bpf: Add jited_len to struct bpf_prog
From: Martin KaFai Lau @ 2017-06-05 19:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <cover.1496686606.git.kafai@fb.com>
Add jited_len to struct bpf_prog. It will be
useful for the struct bpf_prog_info which will
be added in the later patch.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
arch/arm64/net/bpf_jit_comp.c | 1 +
arch/powerpc/net/bpf_jit_comp64.c | 1 +
arch/s390/net/bpf_jit_comp.c | 1 +
arch/sparc/net/bpf_jit_comp_64.c | 1 +
arch/x86/net/bpf_jit_comp.c | 1 +
include/linux/filter.h | 1 +
6 files changed, 6 insertions(+)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index b1d38eeb24f6..4f95873d7142 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -900,6 +900,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
bpf_jit_binary_lock_ro(header);
prog->bpf_func = (void *)ctx.image;
prog->jited = 1;
+ prog->jited_len = image_size;
out_off:
kfree(ctx.offset);
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index a01366584a4b..861c5af1c9c4 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -1052,6 +1052,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
fp->bpf_func = (void *)image;
fp->jited = 1;
+ fp->jited_len = alloclen;
bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE));
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 42ad3832586c..01c6fbc3e85b 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1329,6 +1329,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
bpf_jit_binary_lock_ro(header);
fp->bpf_func = (void *) jit.prg_buf;
fp->jited = 1;
+ fp->jited_len = jit.size;
free_addrs:
kfree(jit.addrs);
out:
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 098874a81f6e..8799ae9a8788 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -1560,6 +1560,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
prog->bpf_func = (void *)ctx.image;
prog->jited = 1;
+ prog->jited_len = image_size;
out_off:
kfree(ctx.offset);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 617eac9c4511..e1324f280e06 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1167,6 +1167,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
bpf_jit_binary_lock_ro(header);
prog->bpf_func = (void *)image;
prog->jited = 1;
+ prog->jited_len = proglen;
} else {
prog = orig_prog;
}
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a20ba40fcb73..1e2dddf21f3b 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -432,6 +432,7 @@ struct bpf_prog {
kmemcheck_bitfield_end(meta);
enum bpf_prog_type type; /* Type of BPF program */
u32 len; /* Number of filter blocks */
+ u32 jited_len; /* Size of jited insns in bytes */
u8 tag[BPF_TAG_SIZE];
struct bpf_prog_aux *aux; /* Auxiliary fields */
struct sock_fprog_kern *orig_prog; /* Original BPF program */
--
2.9.3
^ permalink raw reply related
* [PATCH v3 net-next 0/8] Introduce bpf ID
From: Martin KaFai Lau @ 2017-06-05 19:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexei Starovoitov, Daniel Borkmann, kernel-team
This patch series:
1) Introduce ID for both bpf_prog and bpf_map.
2) Add bpf commands to iterate the prog IDs and map
IDs of the system.
3) Add bpf commands to get a prog/map fd from an ID
4) Add bpf command to get prog/map info from a fd.
The prog/map info is a jump start in this patchset
and it is not meant to be a complete list. They can
be extended in the future patches.
v3:
- I suspect v2 may not have applied cleanly.
In particular, patch 1 has conflict with a recent
change in struct bpf_prog_aux introduced at a similar time frame:
8726679a0fa3 ("bpf: teach verifier to track stack depth")
v3 should have fixed it.
v2:
Compiler warning fixes:
- Remove lockdep_is_held() usage. Add comment
to explain the lock situation instead.
- Add static for idr related variables
- Add __user to the uattr param in bpf_prog_get_info_by_fd()
and bpf_map_get_info_by_fd().
Martin KaFai Lau (8):
bpf: Introduce bpf_prog ID
bpf: Introduce bpf_map ID
bpf: Add BPF_(PROG|MAP)_GET_NEXT_ID command
bpf: Add BPF_PROG_GET_FD_BY_ID
bpf: Add BPF_MAP_GET_FD_BY_ID
bpf: Add jited_len to struct bpf_prog
bpf: Add BPF_OBJ_GET_INFO_BY_FD
bpf: Test for bpf ID
arch/arm64/net/bpf_jit_comp.c | 1 +
arch/powerpc/net/bpf_jit_comp64.c | 1 +
arch/s390/net/bpf_jit_comp.c | 1 +
arch/sparc/net/bpf_jit_comp_64.c | 1 +
arch/x86/net/bpf_jit_comp.c | 1 +
include/linux/bpf.h | 2 +
include/linux/filter.h | 3 +-
include/uapi/linux/bpf.h | 41 +++
kernel/bpf/syscall.c | 433 ++++++++++++++++++++++++++++--
tools/include/uapi/linux/bpf.h | 41 +++
tools/lib/bpf/bpf.c | 68 +++++
tools/lib/bpf/bpf.h | 5 +
tools/testing/selftests/bpf/Makefile | 2 +-
tools/testing/selftests/bpf/test_obj_id.c | 35 +++
tools/testing/selftests/bpf/test_progs.c | 191 +++++++++++++
15 files changed, 798 insertions(+), 28 deletions(-)
create mode 100644 tools/testing/selftests/bpf/test_obj_id.c
--
2.9.3
^ permalink raw reply
* [PATCH v3 net-next 8/8] bpf: Test for bpf ID
From: Martin KaFai Lau @ 2017-06-05 19:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <cover.1496686606.git.kafai@fb.com>
Add test to exercise the bpf_prog/map id generation,
bpf_(prog|map)_get_next_id(), bpf_(prog|map)_get_fd_by_id() and
bpf_get_obj_info_by_fd().
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
tools/include/uapi/linux/bpf.h | 41 +++++++
tools/lib/bpf/bpf.c | 68 +++++++++++
tools/lib/bpf/bpf.h | 5 +
tools/testing/selftests/bpf/Makefile | 2 +-
tools/testing/selftests/bpf/test_obj_id.c | 35 ++++++
tools/testing/selftests/bpf/test_progs.c | 191 ++++++++++++++++++++++++++++++
6 files changed, 341 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/test_obj_id.c
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e78aece03628..9b2c10b45733 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -82,6 +82,11 @@ enum bpf_cmd {
BPF_PROG_ATTACH,
BPF_PROG_DETACH,
BPF_PROG_TEST_RUN,
+ BPF_PROG_GET_NEXT_ID,
+ BPF_MAP_GET_NEXT_ID,
+ BPF_PROG_GET_FD_BY_ID,
+ BPF_MAP_GET_FD_BY_ID,
+ BPF_OBJ_GET_INFO_BY_FD,
};
enum bpf_map_type {
@@ -209,6 +214,21 @@ union bpf_attr {
__u32 repeat;
__u32 duration;
} test;
+
+ struct { /* anonymous struct used by BPF_*_GET_*_ID */
+ union {
+ __u32 start_id;
+ __u32 prog_id;
+ __u32 map_id;
+ };
+ __u32 next_id;
+ };
+
+ struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
+ __u32 bpf_fd;
+ __u32 info_len;
+ __aligned_u64 info;
+ } info;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -673,4 +693,25 @@ struct xdp_md {
__u32 data_end;
};
+#define BPF_TAG_SIZE 8
+
+struct bpf_prog_info {
+ __u32 type;
+ __u32 id;
+ __u8 tag[BPF_TAG_SIZE];
+ __u32 jited_prog_len;
+ __u32 xlated_prog_len;
+ __aligned_u64 jited_prog_insns;
+ __aligned_u64 xlated_prog_insns;
+} __attribute__((aligned(8)));
+
+struct bpf_map_info {
+ __u32 type;
+ __u32 id;
+ __u32 key_size;
+ __u32 value_size;
+ __u32 max_entries;
+ __u32 map_flags;
+} __attribute__((aligned(8)));
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 6e178987af8e..7e0405e1651d 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -257,3 +257,71 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
*duration = attr.test.duration;
return ret;
}
+
+int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
+{
+ union bpf_attr attr;
+ int err;
+
+ bzero(&attr, sizeof(attr));
+ attr.start_id = start_id;
+
+ err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr));
+ if (!err)
+ *next_id = attr.next_id;
+
+ return err;
+}
+
+int bpf_map_get_next_id(__u32 start_id, __u32 *next_id)
+{
+ union bpf_attr attr;
+ int err;
+
+ bzero(&attr, sizeof(attr));
+ attr.start_id = start_id;
+
+ err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr));
+ if (!err)
+ *next_id = attr.next_id;
+
+ return err;
+}
+
+int bpf_prog_get_fd_by_id(__u32 id)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.prog_id = id;
+
+ return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+}
+
+int bpf_map_get_fd_by_id(__u32 id)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.map_id = id;
+
+ return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+}
+
+int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
+{
+ union bpf_attr attr;
+ int err;
+
+ bzero(&attr, sizeof(attr));
+ bzero(info, *info_len);
+ attr.info.bpf_fd = prog_fd;
+ attr.info.info_len = *info_len;
+ attr.info.info = ptr_to_u64(info);
+
+ err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr));
+ if (!err)
+ *info_len = attr.info.info_len;
+
+ return err;
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 972bd8333eb7..16de44a14b48 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -54,5 +54,10 @@ int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
void *data_out, __u32 *size_out, __u32 *retval,
__u32 *duration);
+int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
+int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
+int bpf_prog_get_fd_by_id(__u32 id);
+int bpf_map_get_fd_by_id(__u32 id);
+int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
#endif
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f389b02d43a0..9f0e07ba5334 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -14,7 +14,7 @@ LDLIBS += -lcap -lelf
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_align
-TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o
+TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o
TEST_PROGS := test_kmod.sh
diff --git a/tools/testing/selftests/bpf/test_obj_id.c b/tools/testing/selftests/bpf/test_obj_id.c
new file mode 100644
index 000000000000..d8723aaf827a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_obj_id.c
@@ -0,0 +1,35 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include "bpf_helpers.h"
+
+/* It is a dumb bpf program such that it must have no
+ * issue to be loaded since testing the verifier is
+ * not the focus here.
+ */
+
+int _version SEC("version") = 1;
+
+struct bpf_map_def SEC("maps") test_map_id = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u64),
+ .max_entries = 1,
+};
+
+SEC("test_prog_id")
+int test_prog_id(struct __sk_buff *skb)
+{
+ __u32 key = 0;
+ __u64 *value;
+
+ value = bpf_map_lookup_elem(&test_map_id, &key);
+
+ return TC_ACT_OK;
+}
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index b59f5ed4ae40..8189bfc7e277 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -22,6 +22,8 @@ typedef __u16 __sum16;
#include <sys/wait.h>
#include <sys/resource.h>
+#include <sys/types.h>
+#include <pwd.h>
#include <linux/bpf.h>
#include <linux/err.h>
@@ -70,6 +72,7 @@ static struct {
pass_cnt++; \
printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\
} \
+ __ret; \
})
static int bpf_prog_load(const char *file, enum bpf_prog_type type,
@@ -283,6 +286,193 @@ static void test_tcp_estats(void)
bpf_object__close(obj);
}
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+ return (__u64) (unsigned long) ptr;
+}
+
+static void test_bpf_obj_id(void)
+{
+ const __u64 array_magic_value = 0xfaceb00c;
+ const __u32 array_key = 0;
+ const int nr_iters = 2;
+ const char *file = "./test_obj_id.o";
+
+ struct bpf_object *objs[nr_iters];
+ int prog_fds[nr_iters], map_fds[nr_iters];
+ /* +1 to test for the info_len returned by kernel */
+ struct bpf_prog_info prog_infos[nr_iters + 1];
+ struct bpf_map_info map_infos[nr_iters + 1];
+ char jited_insns[128], xlated_insns[128];
+ __u32 i, next_id, info_len, nr_id_found, duration = 0;
+ int err = 0;
+ __u64 array_value;
+
+ err = bpf_prog_get_fd_by_id(0);
+ CHECK(err >= 0 || errno != ENOENT,
+ "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
+
+ err = bpf_map_get_fd_by_id(0);
+ CHECK(err >= 0 || errno != ENOENT,
+ "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno);
+
+ for (i = 0; i < nr_iters; i++)
+ objs[i] = NULL;
+
+ /* Check bpf_obj_get_info_by_fd() */
+ for (i = 0; i < nr_iters; i++) {
+ err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER,
+ &objs[i], &prog_fds[i]);
+ /* test_obj_id.o is a dumb prog. It should never fail
+ * to load.
+ */
+ assert(!err);
+
+ /* Check getting prog info */
+ info_len = sizeof(struct bpf_prog_info) * 2;
+ prog_infos[i].jited_prog_insns = ptr_to_u64(jited_insns);
+ prog_infos[i].jited_prog_len = sizeof(jited_insns);
+ prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns);
+ prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
+ err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i],
+ &info_len);
+ if (CHECK(err ||
+ prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
+ info_len != sizeof(struct bpf_prog_info) ||
+ !prog_infos[i].jited_prog_len ||
+ !prog_infos[i].xlated_prog_len,
+ "get-prog-info(fd)",
+ "err %d errno %d i %d type %d(%d) info_len %u(%lu) jited_prog_len %u xlated_prog_len %u\n",
+ err, errno, i,
+ prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
+ info_len, sizeof(struct bpf_prog_info),
+ prog_infos[i].jited_prog_len,
+ prog_infos[i].xlated_prog_len))
+ goto done;
+
+ map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
+ assert(map_fds[i] >= 0);
+ err = bpf_map_update_elem(map_fds[i], &array_key,
+ &array_magic_value, 0);
+ assert(!err);
+
+ /* Check getting map info */
+ info_len = sizeof(struct bpf_map_info) * 2;
+ err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
+ &info_len);
+ if (CHECK(err ||
+ map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
+ map_infos[i].key_size != sizeof(__u32) ||
+ map_infos[i].value_size != sizeof(__u64) ||
+ map_infos[i].max_entries != 1 ||
+ map_infos[i].map_flags != 0 ||
+ info_len != sizeof(struct bpf_map_info),
+ "get-map-info(fd)",
+ "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n",
+ err, errno,
+ map_infos[i].type, BPF_MAP_TYPE_ARRAY,
+ info_len, sizeof(struct bpf_map_info),
+ map_infos[i].key_size,
+ map_infos[i].value_size,
+ map_infos[i].max_entries,
+ map_infos[i].map_flags))
+ goto done;
+ }
+
+ /* Check bpf_prog_get_next_id() */
+ nr_id_found = 0;
+ next_id = 0;
+ while (!bpf_prog_get_next_id(next_id, &next_id)) {
+ struct bpf_prog_info prog_info;
+ int prog_fd;
+
+ info_len = sizeof(prog_info);
+
+ prog_fd = bpf_prog_get_fd_by_id(next_id);
+ if (prog_fd < 0 && errno == ENOENT)
+ /* The bpf_prog is in the dead row */
+ continue;
+ if (CHECK(prog_fd < 0, "get-prog-fd(next_id)",
+ "prog_fd %d next_id %d errno %d\n",
+ prog_fd, next_id, errno))
+ break;
+
+ for (i = 0; i < nr_iters; i++)
+ if (prog_infos[i].id == next_id)
+ break;
+
+ if (i == nr_iters)
+ continue;
+
+ nr_id_found++;
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+ CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
+ memcmp(&prog_info, &prog_infos[i], info_len),
+ "get-prog-info(next_id->fd)",
+ "err %d errno %d info_len %u(%lu) memcmp %d\n",
+ err, errno, info_len, sizeof(struct bpf_prog_info),
+ memcmp(&prog_info, &prog_infos[i], info_len));
+
+ close(prog_fd);
+ }
+ CHECK(nr_id_found != nr_iters,
+ "check total prog id found by get_next_id",
+ "nr_id_found %u(%u)\n",
+ nr_id_found, nr_iters);
+
+ /* Check bpf_map_get_next_id() */
+ nr_id_found = 0;
+ next_id = 0;
+ while (!bpf_map_get_next_id(next_id, &next_id)) {
+ struct bpf_map_info map_info;
+ int map_fd;
+
+ info_len = sizeof(map_info);
+
+ map_fd = bpf_map_get_fd_by_id(next_id);
+ if (map_fd < 0 && errno == ENOENT)
+ /* The bpf_map is in the dead row */
+ continue;
+ if (CHECK(map_fd < 0, "get-map-fd(next_id)",
+ "map_fd %d next_id %u errno %d\n",
+ map_fd, next_id, errno))
+ break;
+
+ for (i = 0; i < nr_iters; i++)
+ if (map_infos[i].id == next_id)
+ break;
+
+ if (i == nr_iters)
+ continue;
+
+ nr_id_found++;
+
+ err = bpf_map_lookup_elem(map_fd, &array_key, &array_value);
+ assert(!err);
+
+ err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+ CHECK(err || info_len != sizeof(struct bpf_map_info) ||
+ memcmp(&map_info, &map_infos[i], info_len) ||
+ array_value != array_magic_value,
+ "check get-map-info(next_id->fd)",
+ "err %d errno %d info_len %u(%lu) memcmp %d array_value %llu(%llu)\n",
+ err, errno, info_len, sizeof(struct bpf_map_info),
+ memcmp(&map_info, &map_infos[i], info_len),
+ array_value, array_magic_value);
+
+ close(map_fd);
+ }
+ CHECK(nr_id_found != nr_iters,
+ "check total map id found by get_next_id",
+ "nr_id_found %u(%u)\n",
+ nr_id_found, nr_iters);
+
+done:
+ for (i = 0; i < nr_iters; i++)
+ bpf_object__close(objs[i]);
+}
+
int main(void)
{
struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
@@ -293,6 +483,7 @@ int main(void)
test_xdp();
test_l4lb();
test_tcp_estats();
+ test_bpf_obj_id();
printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
return 0;
--
2.9.3
^ permalink raw reply related
* [PATCH v3 net-next 3/8] bpf: Add BPF_(PROG|MAP)_GET_NEXT_ID command
From: Martin KaFai Lau @ 2017-06-05 19:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <cover.1496686606.git.kafai@fb.com>
This patch adds BPF_PROG_GET_NEXT_ID and BPF_MAP_GET_NEXT_ID
to allow userspace to iterate all bpf_prog IDs and bpf_map IDs.
The API is trying to be consistent with the existing
BPF_MAP_GET_NEXT_KEY.
It is currently limited to CAP_SYS_ADMIN which we can
consider to lift it in followup patches.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
include/uapi/linux/bpf.h | 7 +++++++
kernel/bpf/syscall.c | 38 ++++++++++++++++++++++++++++++++++++++
2 files changed, 45 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e78aece03628..629747a3f273 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -82,6 +82,8 @@ enum bpf_cmd {
BPF_PROG_ATTACH,
BPF_PROG_DETACH,
BPF_PROG_TEST_RUN,
+ BPF_PROG_GET_NEXT_ID,
+ BPF_MAP_GET_NEXT_ID,
};
enum bpf_map_type {
@@ -209,6 +211,11 @@ union bpf_attr {
__u32 repeat;
__u32 duration;
} test;
+
+ struct { /* anonymous struct used by BPF_*_GET_NEXT_ID */
+ __u32 start_id;
+ __u32 next_id;
+ };
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4c3075b5d840..2405feedb8c1 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -166,6 +166,7 @@ static void bpf_map_put_uref(struct bpf_map *map)
void bpf_map_put(struct bpf_map *map)
{
if (atomic_dec_and_test(&map->refcnt)) {
+ /* bpf_map_free_id() must be called first */
bpf_map_free_id(map);
INIT_WORK(&map->work, bpf_map_free_deferred);
schedule_work(&map->work);
@@ -726,6 +727,7 @@ void bpf_prog_put(struct bpf_prog *prog)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
trace_bpf_prog_put_rcu(prog);
+ /* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog);
bpf_prog_kallsyms_del(prog);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
@@ -1069,6 +1071,34 @@ static int bpf_prog_test_run(const union bpf_attr *attr,
return ret;
}
+#define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id
+
+static int bpf_obj_get_next_id(const union bpf_attr *attr,
+ union bpf_attr __user *uattr,
+ struct idr *idr,
+ spinlock_t *lock)
+{
+ u32 next_id = attr->start_id;
+ int err = 0;
+
+ if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX)
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ next_id++;
+ spin_lock_bh(lock);
+ if (!idr_get_next(idr, &next_id))
+ err = -ENOENT;
+ spin_unlock_bh(lock);
+
+ if (!err)
+ err = put_user(next_id, &uattr->next_id);
+
+ return err;
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@@ -1146,6 +1176,14 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
+ case BPF_PROG_GET_NEXT_ID:
+ err = bpf_obj_get_next_id(&attr, uattr,
+ &prog_idr, &prog_idr_lock);
+ break;
+ case BPF_MAP_GET_NEXT_ID:
+ err = bpf_obj_get_next_id(&attr, uattr,
+ &map_idr, &map_idr_lock);
+ break;
default:
err = -EINVAL;
break;
--
2.9.3
^ permalink raw reply related
* [PATCH v3 net-next 1/8] bpf: Introduce bpf_prog ID
From: Martin KaFai Lau @ 2017-06-05 19:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <cover.1496686606.git.kafai@fb.com>
This patch generates an unique ID for each BPF_PROG_LOAD-ed prog.
It is worth to note that each BPF_PROG_LOAD-ed prog will have
a different ID even they have the same bpf instructions.
The ID is generated by the existing idr_alloc_cyclic().
The ID is ranged from [1, INT_MAX). It is allocated in cyclic manner,
so an ID will get reused every 2 billion BPF_PROG_LOAD.
The bpf_prog_alloc_id() is done after bpf_prog_select_runtime()
because the jit process may have allocated a new prog. Hence,
we need to ensure the value of pointer 'prog' will not be changed
any more before storing the prog to the prog_idr.
After bpf_prog_select_runtime(), the prog is read-only. Hence,
the id is stored in 'struct bpf_prog_aux'.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
include/linux/bpf.h | 1 +
kernel/bpf/syscall.c | 40 +++++++++++++++++++++++++++++++++++++++-
2 files changed, 40 insertions(+), 1 deletion(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fcc80ca11045..c5946d19f2ca 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -172,6 +172,7 @@ struct bpf_prog_aux {
u32 used_map_cnt;
u32 max_ctx_offset;
u32 stack_depth;
+ u32 id;
struct latch_tree_node ksym_tnode;
struct list_head ksym_lnode;
const struct bpf_verifier_ops *ops;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 59da103adb85..2a1b32b470f1 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -22,8 +22,11 @@
#include <linux/filter.h>
#include <linux/version.h>
#include <linux/kernel.h>
+#include <linux/idr.h>
DEFINE_PER_CPU(int, bpf_prog_active);
+static DEFINE_IDR(prog_idr);
+static DEFINE_SPINLOCK(prog_idr_lock);
int sysctl_unprivileged_bpf_disabled __read_mostly;
@@ -650,6 +653,34 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
free_uid(user);
}
+static int bpf_prog_alloc_id(struct bpf_prog *prog)
+{
+ int id;
+
+ spin_lock_bh(&prog_idr_lock);
+ id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC);
+ if (id > 0)
+ prog->aux->id = id;
+ spin_unlock_bh(&prog_idr_lock);
+
+ /* id is in [1, INT_MAX) */
+ if (WARN_ON_ONCE(!id))
+ return -ENOSPC;
+
+ return id > 0 ? 0 : id;
+}
+
+static void bpf_prog_free_id(struct bpf_prog *prog)
+{
+ /* cBPF to eBPF migrations are currently not in the idr store. */
+ if (!prog->aux->id)
+ return;
+
+ spin_lock_bh(&prog_idr_lock);
+ idr_remove(&prog_idr, prog->aux->id);
+ spin_unlock_bh(&prog_idr_lock);
+}
+
static void __bpf_prog_put_rcu(struct rcu_head *rcu)
{
struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
@@ -663,6 +694,7 @@ void bpf_prog_put(struct bpf_prog *prog)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
trace_bpf_prog_put_rcu(prog);
+ bpf_prog_free_id(prog);
bpf_prog_kallsyms_del(prog);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
@@ -857,15 +889,21 @@ static int bpf_prog_load(union bpf_attr *attr)
if (err < 0)
goto free_used_maps;
+ err = bpf_prog_alloc_id(prog);
+ if (err)
+ goto free_used_maps;
+
err = bpf_prog_new_fd(prog);
if (err < 0)
/* failed to allocate fd */
- goto free_used_maps;
+ goto free_id;
bpf_prog_kallsyms_add(prog);
trace_bpf_prog_load(prog, err);
return err;
+free_id:
+ bpf_prog_free_id(prog);
free_used_maps:
free_used_maps(prog->aux);
free_prog:
--
2.9.3
^ permalink raw reply related
* Re: [PATCH] ip: link add vxcan support
From: Stephen Hemminger @ 2017-06-05 19:28 UTC (permalink / raw)
To: Oliver Hartkopp; +Cc: linux-can, mkl, netdev
In-Reply-To: <20170602170447.2913-1-socketcan@hartkopp.net>
On Fri, 2 Jun 2017 19:04:47 +0200
Oliver Hartkopp <socketcan@hartkopp.net> wrote:
> Since commit a8f820a380a2a06 ('can: add Virtual CAN Tunnel driver (vxcan)')
> for Linux 4.12 a virtual CAN tunnel driver analogue to veth is available in
> Linux.
>
> This patch adds the ability to create vxcan device pairs.
>
> Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Applied, with minor header cleanup so that sanitized headers are used.
diff --git a/include/linux/can/vxcan.h b/include/linux/can/vxcan.h
index ffb0b7156f7e..5b29e8a7bc27 100644
--- a/include/linux/can/vxcan.h
+++ b/include/linux/can/vxcan.h
@@ -1,5 +1,5 @@
-#ifndef _UAPI_CAN_VXCAN_H
-#define _UAPI_CAN_VXCAN_H
+#ifndef _CAN_VXCAN_H
+#define _CAN_VXCAN_H
enum {
VXCAN_INFO_UNSPEC,
^ permalink raw reply related
* Re: [PATCH iproute2 V2] iplink: Update usage in help message
From: Stephen Hemminger @ 2017-06-05 19:30 UTC (permalink / raw)
To: Tariq Toukan; +Cc: netdev, Eran Ben Elisha, Or Gerlitz, Eli Cohen
In-Reply-To: <1496579808-31933-1-git-send-email-tariqt@mellanox.com>
On Sun, 4 Jun 2017 15:36:48 +0300
Tariq Toukan <tariqt@mellanox.com> wrote:
> From: Eli Cohen <eli@mellanox.com>
>
> Add to usage message a description of how to configure Infiniband node
> and port GUIDs. Also modify the man page to emphasize the GUIDs are
> configured for Infiniband VFs.
>
> Fixes: d91fb3f4c7e4 ("Add support for configuring Infiniband GUIDs")
> Signed-off-by: Eli Cohen <eli@mellanox.com>
> Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Looks good, applied
^ permalink raw reply
* Re: [PATCH iproute2] iproute: extend route get to return matching fib route
From: Stephen Hemminger @ 2017-06-05 19:34 UTC (permalink / raw)
To: Roopa Prabhu; +Cc: netdev, dsahern, nikolay
In-Reply-To: <1496379208-30573-1-git-send-email-roopa@cumulusnetworks.com>
On Thu, 1 Jun 2017 21:53:28 -0700
Roopa Prabhu <roopa@cumulusnetworks.com> wrote:
> From: Roopa Prabhu <roopa@cumulusnetworks.com>
>
> Uses newly introduced RTM_GETROUTE flag RTM_F_FIB_MATCH
> to return a matching fib route. Introduces 'fibmatch'
> keyword to ip route get.
>
> ipv4:
> ----
> $ip route show
> default via 192.168.0.2 dev eth0
> 10.0.14.0/24
> nexthop via 172.16.0.3 dev dummy0 weight 1
> nexthop via 172.16.1.3 dev dummy1 weight 1
>
> $ip route get 10.0.14.2
> 10.0.14.2 via 172.16.1.3 dev dummy1 src 172.16.1.1
> cache
>
> $ip route get fibmatch 10.0.14.2
> 10.0.14.0/24
> nexthop via 172.16.0.3 dev dummy0 weight 1
> nexthop via 172.16.1.3 dev dummy1 weight 1
>
> ipv6:
> ----
> $ip -6 route show
> 2001:db9:100::/120 metric 1024
> nexthop via 2001:db8:2::2 dev dummy0 weight 1
> nexthop via 2001:db8:12::2 dev dummy1 weight 1
>
> $ip -6 route get 2001:db9:100::1
> 2001:db9:100::1 from :: via 2001:db8:12::2 dev dummy1 \
> src 2001:db8:12::1 metric 1024 pref medium
>
> $ip -6 route get fibmatch 2001:db9:100::1
> 2001:db9:100::/120 metric 1024
> nexthop via 2001:db8:12::2 dev dummy1 weight 1
> nexthop via 2001:db8:2::2 dev dummy0 weight 1
>
> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Applied to net-next branch
^ permalink raw reply
* Re: [PATCH] virtio_net: lower limit on buffer size
From: J. Bruce Fields @ 2017-06-05 19:36 UTC (permalink / raw)
To: Sergei Shtylyov
Cc: Michael S. Tsirkin, linux-kernel, Mikulas Patocka, Jason Wang,
virtualization, netdev
In-Reply-To: <aafb81af-54f2-06b0-3b5c-2713bc28184b@cogentembedded.com>
On Sat, Jun 03, 2017 at 11:17:30PM +0300, Sergei Shtylyov wrote:
> On 06/02/2017 11:25 PM, J. Bruce Fields wrote:
>
> >>>commit d85b758f72b0 "virtio_net: fix support for small rings"
> >>
> >> Commit d85b758f72b0 ("virtio_net: fix support for small rings")
> >>
> >>>was supposed to increase the buffer size for small rings
> >>>but had an unintentional side effect of decreasing
> >>>it for large rings. This seems to break some setups -
> >>>it's not yet clear why, but increasing buffer size
> >>>back to what it was before helps.
> >>>
> >>>Fixes: d85b758f72b0 "virtio_net: fix support for small rings"
> >>
> >>Fixes: d85b758f72b0 ("virtio_net: fix support for small rings")
> >
> >I may be bikeshedding, but, personally I never do the parens--they're
> >redundant given the quotes, and space is often tight.
>
> Just see Documetation/process/submitting-patches.rst.
Yeah, I know, I claim it's a bad rule (but I'm too lazy to send a patch,
so, weight my opinion accordingly).
--b.
^ permalink raw reply
* Re: [PATCH V7 net-next iproute] ip: Add IFLA_EVENT output to ip monitor
From: Stephen Hemminger @ 2017-06-05 19:38 UTC (permalink / raw)
To: Vladislav Yasevich; +Cc: netdev, dsahern
In-Reply-To: <1496329276-31106-1-git-send-email-vyasevic@redhat.com>
On Thu, 1 Jun 2017 11:01:16 -0400
Vladislav Yasevich <vyasevic@redhat.com> wrote:
> Add IFLA_EVENT output so that event types can be viewed with
> 'monitor' command. This gives a little more information for why
> a given message was received.
>
> Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Applied to net-next.
^ permalink raw reply
* Re: [patch net-next 0/6] introduce trap control action to tc and offload it
From: Jiri Pirko @ 2017-06-05 19:43 UTC (permalink / raw)
To: Andrew Lunn
Cc: netdev, davem, jhs, xiyou.wangcong, edumazet, alexander.h.duyck,
stephen, daniel, mlxsw
In-Reply-To: <20170605154651.GE11772@lunn.ch>
Mon, Jun 05, 2017 at 05:46:51PM CEST, andrew@lunn.ch wrote:
>On Mon, Jun 05, 2017 at 04:38:26PM +0200, Jiri Pirko wrote:
>> From: Jiri Pirko <jiri@mellanox.com>
>>
>> This patchset introduces a control action dedicated to indicate
>> to trap the matched packet to CPU. This is specific action for
>> HW offloads. Also, the patchset offloads the action to mlxsw driver.
>>
>> Example usage:
>> $ tc filter add dev enp3s0np19 parent ffff: protocol ip prio 20 flower skip_sw dst_ip 192.168.10.1 action trap
>
>Hi Jiri
>
>So i assume this means a frame ingressing on the switch port
>enp3s0np19 matching the filter is now visible on the linux enp3s0np19
Yes.
>interface? How do you avoid Linux processing it? If enp3s0np19 is a
On contrary. I want Linux to process it. The packet was stolen from the
offloaded fastpath to kernel.
>member of a bridge, we don't want the software bridge processing it
>and forwarding it out another port, since i assume the hardware has
>already done this. Or does the trap stop further processing of the
>frame by the hardware?
Exactly the latter :) Thanks!
>
>Thanks
> Andrew
^ permalink raw reply
* Re: [patch net-next 0/6] introduce trap control action to tc and offload it
From: Jiri Pirko @ 2017-06-05 19:56 UTC (permalink / raw)
To: Andrew Lunn
Cc: netdev, davem, jhs, xiyou.wangcong, edumazet, alexander.h.duyck,
stephen, daniel, mlxsw
In-Reply-To: <20170605194317.GA1986@nanopsycho>
Mon, Jun 05, 2017 at 09:43:17PM CEST, jiri@resnulli.us wrote:
>Mon, Jun 05, 2017 at 05:46:51PM CEST, andrew@lunn.ch wrote:
>>On Mon, Jun 05, 2017 at 04:38:26PM +0200, Jiri Pirko wrote:
>>> From: Jiri Pirko <jiri@mellanox.com>
>>>
>>> This patchset introduces a control action dedicated to indicate
>>> to trap the matched packet to CPU. This is specific action for
>>> HW offloads. Also, the patchset offloads the action to mlxsw driver.
>>>
>>> Example usage:
>>> $ tc filter add dev enp3s0np19 parent ffff: protocol ip prio 20 flower skip_sw dst_ip 192.168.10.1 action trap
>>
>>Hi Jiri
>>
>>So i assume this means a frame ingressing on the switch port
>>enp3s0np19 matching the filter is now visible on the linux enp3s0np19
>
>Yes.
>
>
>>interface? How do you avoid Linux processing it? If enp3s0np19 is a
>
>On contrary. I want Linux to process it. The packet was stolen from the
>offloaded fastpath to kernel.
>
>
>>member of a bridge, we don't want the software bridge processing it
>>and forwarding it out another port, since i assume the hardware has
>>already done this. Or does the trap stop further processing of the
>>frame by the hardware?
>
>Exactly the latter :) Thanks!
Btw, if you would like to just sample the traffic and not really
influence it in any way, there is a special action "sample" for that.
mlxsw offloads that.
^ permalink raw reply
* Re: [patch net-next 1/6] net: sched: introduce a TRAP control action
From: Andrew Lunn @ 2017-06-05 19:56 UTC (permalink / raw)
To: Jiri Pirko
Cc: netdev, davem, jhs, xiyou.wangcong, edumazet, alexander.h.duyck,
stephen, daniel, mlxsw
In-Reply-To: <20170605143832.7025-2-jiri@resnulli.us>
> On Mon, Jun 05, 2017 at 04:38:27PM +0200, Jiri Pirko wrote:
> From: Jiri Pirko <jiri@mellanox.com>
>
> There is need to instruct the HW offloaded path to push certain matched
> packets to cpu/kernel for further analysis. So this patch introduces a
> new TRAP control action to TC.
>
> For kernel datapath, this action does not make much sense. So with the
> same logic as in HW, new TRAP behaves similar to STOLEN. The skb is just
> dropped in the datapath (and virtually ejected to an upper level, which
> does not exist in case of kernel).
>
> Signed-off-by: Jiri Pirko <jiri@mellanox.com>
> Reviewed-by: Yotam Gigi <yotamg@mellanox.com>
> ---
> include/uapi/linux/pkt_cls.h | 5 +++++
> net/core/dev.c | 2 ++
> net/sched/cls_bpf.c | 1 +
> net/sched/sch_atm.c | 1 +
> net/sched/sch_cbq.c | 1 +
> net/sched/sch_drr.c | 1 +
> net/sched/sch_dsmark.c | 1 +
> net/sched/sch_fq_codel.c | 1 +
> net/sched/sch_hfsc.c | 1 +
> net/sched/sch_htb.c | 1 +
> net/sched/sch_multiq.c | 1 +
> net/sched/sch_prio.c | 1 +
> net/sched/sch_qfq.c | 1 +
> net/sched/sch_sfb.c | 1 +
> net/sched/sch_sfq.c | 1 +
> 15 files changed, 20 insertions(+)
>
> diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
> index edf43dd..5d6f711 100644
> --- a/include/uapi/linux/pkt_cls.h
> +++ b/include/uapi/linux/pkt_cls.h
> @@ -37,6 +37,11 @@ enum {
> #define TC_ACT_QUEUED 5
> #define TC_ACT_REPEAT 6
> #define TC_ACT_REDIRECT 7
> +#define TC_ACT_TRAP 8 /* For hw path, this means "trap to cpu",
> + * for sw path, this is equivalent of
> + * TC_ACT_STOLEN - drop the skb and act
> + * like everything is allright.
> + */
Hi Jiri
Given my question and your answer, can we please extend this
description.
"For hw path, this means "trap to cpu" and don't further process the
frame in hardware."
Oh, and s/allright/alright.
Andrew
^ permalink raw reply
* Re: [patch net-next 1/6] net: sched: introduce a TRAP control action
From: Jiri Pirko @ 2017-06-05 19:59 UTC (permalink / raw)
To: Andrew Lunn
Cc: netdev, davem, jhs, xiyou.wangcong, edumazet, alexander.h.duyck,
stephen, daniel, mlxsw
In-Reply-To: <20170605195632.GA9339@lunn.ch>
Mon, Jun 05, 2017 at 09:56:32PM CEST, andrew@lunn.ch wrote:
>> On Mon, Jun 05, 2017 at 04:38:27PM +0200, Jiri Pirko wrote:
>> From: Jiri Pirko <jiri@mellanox.com>
>>
>> There is need to instruct the HW offloaded path to push certain matched
>> packets to cpu/kernel for further analysis. So this patch introduces a
>> new TRAP control action to TC.
>>
>> For kernel datapath, this action does not make much sense. So with the
>> same logic as in HW, new TRAP behaves similar to STOLEN. The skb is just
>> dropped in the datapath (and virtually ejected to an upper level, which
>> does not exist in case of kernel).
>>
>> Signed-off-by: Jiri Pirko <jiri@mellanox.com>
>> Reviewed-by: Yotam Gigi <yotamg@mellanox.com>
>> ---
>> include/uapi/linux/pkt_cls.h | 5 +++++
>> net/core/dev.c | 2 ++
>> net/sched/cls_bpf.c | 1 +
>> net/sched/sch_atm.c | 1 +
>> net/sched/sch_cbq.c | 1 +
>> net/sched/sch_drr.c | 1 +
>> net/sched/sch_dsmark.c | 1 +
>> net/sched/sch_fq_codel.c | 1 +
>> net/sched/sch_hfsc.c | 1 +
>> net/sched/sch_htb.c | 1 +
>> net/sched/sch_multiq.c | 1 +
>> net/sched/sch_prio.c | 1 +
>> net/sched/sch_qfq.c | 1 +
>> net/sched/sch_sfb.c | 1 +
>> net/sched/sch_sfq.c | 1 +
>> 15 files changed, 20 insertions(+)
>>
>> diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
>> index edf43dd..5d6f711 100644
>> --- a/include/uapi/linux/pkt_cls.h
>> +++ b/include/uapi/linux/pkt_cls.h
>> @@ -37,6 +37,11 @@ enum {
>> #define TC_ACT_QUEUED 5
>> #define TC_ACT_REPEAT 6
>> #define TC_ACT_REDIRECT 7
>> +#define TC_ACT_TRAP 8 /* For hw path, this means "trap to cpu",
>> + * for sw path, this is equivalent of
>> + * TC_ACT_STOLEN - drop the skb and act
>> + * like everything is allright.
>> + */
>
>Hi Jiri
>
>Given my question and your answer, can we please extend this
>description.
>
>"For hw path, this means "trap to cpu" and don't further process the
>frame in hardware."
Okay :)
>
>Oh, and s/allright/alright.
English is an odd language :) Thanks!
^ permalink raw reply
* [PATCH v1 1/2] net: emac: fix reset timeout with AR8035 phy
From: Christian Lamparter @ 2017-06-05 20:49 UTC (permalink / raw)
To: netdev; +Cc: David S . Miller, Ivan Mikhaylov, Chris Blake
This patch fixes a problem where the AR8035 PHY can't be
detected on an Cisco Meraki MR24, if the ethernet cable is
not connected on boot.
Russell Senior provided steps to reproduce the issue:
|Disconnect ethernet cable, apply power, wait until device has booted,
|plug in ethernet, check for interfaces, no eth0 is listed.
|
|This appears to be a problem during probing of the AR8035 Phy chip.
|When ethernet has no link, the phy detection fails, and eth0 is not
|created. Plugging ethernet later has no effect, because there is no
|interface as far as the kernel is concerned. The relevant part of
|the boot log looks like this:
|this is the failing case:
|
|[ 0.876611] /plb/opb/emac-rgmii@ef601500: input 0 in RGMII mode
|[ 0.882532] /plb/opb/ethernet@ef600c00: reset timeout
|[ 0.888546] /plb/opb/ethernet@ef600c00: can't find PHY!
|and the succeeding case:
|
|[ 0.876672] /plb/opb/emac-rgmii@ef601500: input 0 in RGMII mode
|[ 0.883952] eth0: EMAC-0 /plb/opb/ethernet@ef600c00, MAC 00:01:..
|[ 0.890822] eth0: found Atheros 8035 Gigabit Ethernet PHY (0x01)
Based on the comment and the commit message of
commit 23fbb5a87c56 ("emac: Fix EMAC soft reset on 460EX/GT").
This is because the AR8035 PHY of the Meraki MR24 does not
provide the TX Clk, if the ethernet cable is not attached.
This causes the reset to timeout and the PHY detection code
in emac_init_phy() is unable to detect the AR8035 PHY.
As a result, the emac driver bails out early and the user
has no ethernet.
In order to stay compatible with existing configurations, the
driver will try the normal reset first and only falls back to
to the internal clock, after the first reset fails. If the
second reset fails as well, it will give up as before.
LEDE-Bug: #687 <https://bugs.lede-project.org/index.php?do=details&task_id=687>
Cc: Chris Blake <chrisrblake93@gmail.com>
Reported-by: Russell Senior <russell@personaltelco.net>
Fixes: 23fbb5a87c56e98 ("emac: Fix EMAC soft reset on 460EX/GT")
Signed-off-by: Christian Lamparter <chunkeey@googlemail.com>
---
drivers/net/ethernet/ibm/emac/core.c | 32 +++++++++++++++++++++++++-------
1 file changed, 25 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 508923f39ccf..18af1116fa1d 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -343,6 +343,7 @@ static int emac_reset(struct emac_instance *dev)
{
struct emac_regs __iomem *p = dev->emacp;
int n = 20;
+ bool try_internal_clock = false;
DBG(dev, "reset" NL);
@@ -355,6 +356,7 @@ static int emac_reset(struct emac_instance *dev)
}
#ifdef CONFIG_PPC_DCR_NATIVE
+do_retry:
/*
* PPC460EX/GT Embedded Processor Advanced User's Manual
* section 28.10.1 Mode Register 0 (EMACx_MR0) states:
@@ -362,10 +364,19 @@ static int emac_reset(struct emac_instance *dev)
* of the EMAC. If none is present, select the internal clock
* (SDR0_ETH_CFG[EMACx_PHY_CLK] = 1).
* After a soft reset, select the external clock.
+ *
+ * The AR8035-A PHY Meraki MR24 does not provide a TX Clk if the
+ * ethernet cable is not attached. This causes the reset to timeout
+ * and the PHY detection code in emac_init_phy() is unable to
+ * communicate and detect the AR8035-A PHY. As a result, the emac
+ * driver bails out early and the user has no ethernet.
+ * In order to stay compatible with existing configurations, the
+ * driver will fall back to and switch to the internal clock, after
+ * the first reset fails.
*/
if (emac_has_feature(dev, EMAC_FTR_460EX_PHY_CLK_FIX)) {
- if (dev->phy_address == 0xffffffff &&
- dev->phy_map == 0xffffffff) {
+ if (try_internal_clock || (dev->phy_address == 0xffffffff &&
+ dev->phy_map == 0xffffffff)) {
/* No PHY: select internal loop clock before reset */
dcri_clrset(SDR0, SDR0_ETH_CFG,
0, SDR0_ETH_CFG_ECS << dev->cell_index);
@@ -383,8 +394,8 @@ static int emac_reset(struct emac_instance *dev)
#ifdef CONFIG_PPC_DCR_NATIVE
if (emac_has_feature(dev, EMAC_FTR_460EX_PHY_CLK_FIX)) {
- if (dev->phy_address == 0xffffffff &&
- dev->phy_map == 0xffffffff) {
+ if (try_internal_clock || (dev->phy_address == 0xffffffff &&
+ dev->phy_map == 0xffffffff)) {
/* No PHY: restore external clock source after reset */
dcri_clrset(SDR0, SDR0_ETH_CFG,
SDR0_ETH_CFG_ECS << dev->cell_index, 0);
@@ -396,9 +407,16 @@ static int emac_reset(struct emac_instance *dev)
dev->reset_failed = 0;
return 0;
} else {
- emac_report_timeout_error(dev, "reset timeout");
- dev->reset_failed = 1;
- return -ETIMEDOUT;
+ if (emac_has_feature(dev, EMAC_FTR_460EX_PHY_CLK_FIX) &&
+ !try_internal_clock) {
+ /* do a retry with the internal clock */
+ try_internal_clock = true;
+ goto do_retry;
+ } else {
+ emac_report_timeout_error(dev, "reset timeout");
+ dev->reset_failed = 1;
+ return -ETIMEDOUT;
+ }
}
}
--
2.11.0
^ permalink raw reply related
* [PATCH v1 2/2] net: emac: fix and unify emac_mdio functions
From: Christian Lamparter @ 2017-06-05 20:49 UTC (permalink / raw)
To: netdev; +Cc: David S . Miller, Ivan Mikhaylov
In-Reply-To: <635dd014238af6f48c4169439b7ac161e80de1b7.1496695540.git.chunkeey@googlemail.com>
emac_mdio_read_link() was not copying the requested phy settings
back into the emac driver's own phy api. This has caused a link
speed mismatch issue for the AR8035 as the emac driver kept
trying to connect with 10/100MBps on a 1GBit/s link.
This patch also unifies shared code between emac_setup_aneg()
and emac_mdio_setup_forced(). And furthermore it removes
a chunk of emac_mdio_init_phy(), that was copying the same
data into itself.
Signed-off-by: Christian Lamparter <chunkeey@googlemail.com>
---
drivers/net/ethernet/ibm/emac/core.c | 41 ++++++++++++++++--------------------
1 file changed, 18 insertions(+), 23 deletions(-)
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 18af1116fa1d..8cfb148cfdb0 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2478,20 +2478,24 @@ static int emac_mii_bus_reset(struct mii_bus *bus)
return emac_reset(dev);
}
+static int emac_mdio_phy_start_aneg(struct mii_phy *phy,
+ struct phy_device *phy_dev)
+{
+ phy_dev->autoneg = phy->autoneg;
+ phy_dev->speed = phy->speed;
+ phy_dev->duplex = phy->duplex;
+ phy_dev->advertising = phy->advertising;
+ return phy_start_aneg(phy_dev);
+}
+
static int emac_mdio_setup_aneg(struct mii_phy *phy, u32 advertise)
{
struct net_device *ndev = phy->dev;
struct emac_instance *dev = netdev_priv(ndev);
- dev->phy.autoneg = AUTONEG_ENABLE;
- dev->phy.speed = SPEED_1000;
- dev->phy.duplex = DUPLEX_FULL;
- dev->phy.advertising = advertise;
phy->autoneg = AUTONEG_ENABLE;
- phy->speed = dev->phy.speed;
- phy->duplex = dev->phy.duplex;
phy->advertising = advertise;
- return phy_start_aneg(dev->phy_dev);
+ return emac_mdio_phy_start_aneg(phy, dev->phy_dev);
}
static int emac_mdio_setup_forced(struct mii_phy *phy, int speed, int fd)
@@ -2499,13 +2503,10 @@ static int emac_mdio_setup_forced(struct mii_phy *phy, int speed, int fd)
struct net_device *ndev = phy->dev;
struct emac_instance *dev = netdev_priv(ndev);
- dev->phy.autoneg = AUTONEG_DISABLE;
- dev->phy.speed = speed;
- dev->phy.duplex = fd;
phy->autoneg = AUTONEG_DISABLE;
phy->speed = speed;
phy->duplex = fd;
- return phy_start_aneg(dev->phy_dev);
+ return emac_mdio_phy_start_aneg(phy, dev->phy_dev);
}
static int emac_mdio_poll_link(struct mii_phy *phy)
@@ -2527,16 +2528,17 @@ static int emac_mdio_read_link(struct mii_phy *phy)
{
struct net_device *ndev = phy->dev;
struct emac_instance *dev = netdev_priv(ndev);
+ struct phy_device *phy_dev = dev->phy_dev;
int res;
- res = phy_read_status(dev->phy_dev);
+ res = phy_read_status(phy_dev);
if (res)
return res;
- dev->phy.speed = phy->speed;
- dev->phy.duplex = phy->duplex;
- dev->phy.pause = phy->pause;
- dev->phy.asym_pause = phy->asym_pause;
+ phy->speed = phy_dev->speed;
+ phy->duplex = phy_dev->duplex;
+ phy->pause = phy_dev->pause;
+ phy->asym_pause = phy_dev->asym_pause;
return 0;
}
@@ -2546,13 +2548,6 @@ static int emac_mdio_init_phy(struct mii_phy *phy)
struct emac_instance *dev = netdev_priv(ndev);
phy_start(dev->phy_dev);
- dev->phy.autoneg = phy->autoneg;
- dev->phy.speed = phy->speed;
- dev->phy.duplex = phy->duplex;
- dev->phy.advertising = phy->advertising;
- dev->phy.pause = phy->pause;
- dev->phy.asym_pause = phy->asym_pause;
-
return phy_init_hw(dev->phy_dev);
}
--
2.11.0
^ permalink raw reply related
* Re: [PATCH 7/7] mlx5: Do not build eswitch_offloads if CONFIG_MLX5_EN_ESWITCH_OFFLOADS is set
From: Jes Sorensen @ 2017-06-05 20:51 UTC (permalink / raw)
To: Or Gerlitz
Cc: Jes Sorensen, Linux Netdev List, Kernel Team, Saeed Mahameed,
Ilan Tayari
In-Reply-To: <CAJ3xEMhKjPwg75hO8af7XDL5JPoxkq2AtpL61CtOLb-T4aACWQ@mail.gmail.com>
On 06/03/2017 03:37 PM, Or Gerlitz wrote:
> On Fri, Jun 2, 2017 at 11:22 PM, Jes Sorensen <jsorensen@fb.com> wrote:
>> On 05/28/2017 02:03 AM, Or Gerlitz wrote:
>>>
>>> On Sun, May 28, 2017 at 5:23 AM, Jes Sorensen <jes.sorensen@gmail.com>
>>> wrote:
>>>>
>>>> On 05/27/2017 05:02 PM, Or Gerlitz wrote:
>>>>>
>>>>>
>>>>> On Sat, May 27, 2017 at 12:16 AM, Jes Sorensen <jes.sorensen@gmail.com>
>>>>> wrote:
>>>>>>
>>>>>>
>>>>>> This gets rid of the temporary #ifdef spaghetti and allows the code to
>>>>>> compile without offload support enabled.
>>>
>>>
>>>>> I am pretty sure we can do that exercise you're up to without any
>>>>> spaghetti cooking and even put more code under that CONFIG directive
>>>>> (en_rep.c), I'll take that with Saeed.
>>>
>>>
>>>> I want to avoid adding #ifdef CONFIG_foo to the main code in order to
>>>> keep
>>>> it readable. I did it gradually to make sure I didn't break anything and
>>>> to
>>>> allow for it to be bisected in case something did break. If we can move
>>>> out
>>>> more code from places like en_rep.c into eswitch_offload.c and get it
>>>> disabled that way that would be great, but I like to limit the number of
>>>> #ifdefs we add to the actual code.
>>>
>>>
>>> FWIW (see below), squashing your seven patches to one resulted in a
>>> fairly simple/clear
>>> patch, so if we go that way, no need to have seven commits just for this
>>> piece.
>>
>>
>> Squashing patches into jumbo patches is inherently broken and bad coding
>> practice! It makes it way more complicated to debug and bisect in case a
>> minor detail broke in the process.
>
> Not that pure LOC ##-s is the only/deep measurement, but your overall
> changes in the the seven patch series account to:
>
> 5 files changed, 94 insertions(+), 3 deletions(-)
>
> and by no mean this is jumbo or inherently broken and bad coded, so
> please slow down please, I looked with care on the resulted patch and
> said it's basically ok.
Squashing patches for the sake of squashing patches is inherently broken
and bad. So please calm down and stop this mangling of other peoples'
patches.
If you want an alternative, put up a proposal and look at it for
comparison somewhere.
Jes
^ permalink raw reply
* [PATCH 0/1] Allow TC support to be disabled
From: Jes Sorensen @ 2017-06-05 20:53 UTC (permalink / raw)
To: netdev; +Cc: kernel-team, saeedm, ilant, Jes Sorensen
Hi,
Here is the follow-on patch which allows for TC support to be compiled
out.
It builds on top of my patch set from last week.
Jes
Jes Sorensen (1):
mlx5: Allow TC support to be disabled in the build
drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 10 ++++++
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 4 ++-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 39 ++++++-----------------
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 12 +++++++
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 29 +++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 1 +
6 files changed, 65 insertions(+), 30 deletions(-)
--
2.13.0
^ permalink raw reply
* [PATCH 1/1] mlx5: Allow TC support to be disabled in the build
From: Jes Sorensen @ 2017-06-05 20:53 UTC (permalink / raw)
To: netdev; +Cc: kernel-team, saeedm, ilant, Jes Sorensen
In-Reply-To: <20170605205358.20211-1-jsorensen@fb.com>
This provides the option for TC offload support to be disabled in the
driver.
Signed-off-by: Jes Sorensen <jsorensen@fb.com>
---
drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 10 ++++++
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 4 ++-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 39 ++++++-----------------
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 12 +++++++
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 29 +++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 1 +
6 files changed, 65 insertions(+), 30 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index d91272d437bf..6c2607e2866d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -52,6 +52,16 @@ config MLX5_CORE_EN_ESWITCH_OFFLOADS
If unsure, set to Y
+config MLX5_CORE_EN_TC
+ bool "Enable support for TC Filtering Offload Support"
+ default y
+ depends on MLX5_CORE_EN && MLX5_CORE_EN_ESWITCH_OFFLOADS
+ ---help---
+ Say Y here if you want to use Mellanox TC offload support.
+ If set to N, the driver will use the kernel's software implementation.
+
+ If unsure, set to Y
+
config MLX5_CORE_IPOIB
bool "Mellanox Technologies ConnectX-4 IPoIB offloads support"
depends on MLX5_CORE_EN
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 615b33693cc2..72d7d58e9823 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -11,10 +11,12 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o
mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o \
en_main.o en_common.o en_fs.o en_ethtool.o en_tx.o \
en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \
- en_tc.o en_arfs.o en_rep.o en_fs_ethtool.o en_selftest.o
+ en_arfs.o en_rep.o en_fs_ethtool.o en_selftest.o
mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o
+mlx5_core-$(CONFIG_MLX5_CORE_EN_TC) += en_tc.o
+
mlx5_core-$(CONFIG_MLX5_EN_ESWITCH_OFFLOADS) += en_eswitch_offloads.o
mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cdff04b2aea1..9abdd4189edf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2961,38 +2961,10 @@ static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
return 0;
}
-static int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
-{
- struct mlx5e_priv *priv = netdev_priv(netdev);
- struct mlx5e_channels new_channels = {};
- int err = 0;
-
- if (tc && tc != MLX5E_MAX_NUM_TC)
- return -EINVAL;
-
- mutex_lock(&priv->state_lock);
-
- new_channels.params = priv->channels.params;
- new_channels.params.num_tc = tc ? tc : 1;
-
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
- priv->channels.params = new_channels.params;
- goto out;
- }
-
- err = mlx5e_open_channels(priv, &new_channels);
- if (err)
- goto out;
-
- mlx5e_switch_priv_channels(priv, &new_channels, NULL);
-out:
- mutex_unlock(&priv->state_lock);
- return err;
-}
-
static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle,
__be16 proto, struct tc_to_netdev *tc)
{
+#ifdef CONFIG_MLX5_CORE_EN_TC
struct mlx5e_priv *priv = netdev_priv(dev);
if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS))
@@ -3019,6 +2991,9 @@ static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle,
tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
return mlx5e_setup_tc(dev, tc->mqprio->num_tc);
+#else
+ return -EOPNOTSUPP;
+#endif
}
static void
@@ -4085,14 +4060,18 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
goto err_destroy_direct_tirs;
}
+#ifdef CONFIG_MLX5_CORE_EN_TC
err = mlx5e_tc_init(priv);
if (err)
goto err_destroy_flow_steering;
+#endif
return 0;
+#ifdef CONFIG_MLX5_CORE_EN_TC
err_destroy_flow_steering:
mlx5e_destroy_flow_steering(priv);
+#endif
err_destroy_direct_tirs:
mlx5e_destroy_direct_tirs(priv);
err_destroy_indirect_tirs:
@@ -4106,7 +4085,9 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
{
+#ifdef CONFIG_MLX5_CORE_EN_TC
mlx5e_tc_cleanup(priv);
+#endif
mlx5e_destroy_flow_steering(priv);
mlx5e_destroy_direct_tirs(priv);
mlx5e_destroy_indirect_tirs(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 79462c0368a0..514f190b3f3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -256,6 +256,7 @@ void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv)
static void mlx5e_rep_neigh_stats_work(struct work_struct *work)
{
+#ifdef CONFIG_MLX5_CORE_EN_TC
struct mlx5e_rep_priv *rpriv = container_of(work, struct mlx5e_rep_priv,
neigh_update.neigh_stats_work.work);
struct net_device *netdev = rpriv->rep->netdev;
@@ -270,6 +271,7 @@ static void mlx5e_rep_neigh_stats_work(struct work_struct *work)
mlx5e_tc_update_neigh_used_value(nhe);
rtnl_unlock();
+#endif
}
static void mlx5e_rep_neigh_entry_hold(struct mlx5e_neigh_hash_entry *nhe)
@@ -288,6 +290,7 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
bool neigh_connected,
unsigned char ha[ETH_ALEN])
{
+#ifdef CONFIG_MLX5_CORE_EN_TC
struct ethhdr *eth = (struct ethhdr *)e->encap_header;
ASSERT_RTNL();
@@ -302,6 +305,7 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
mlx5e_tc_encap_flows_add(priv, e);
}
+#endif
}
static void mlx5e_rep_neigh_update(struct work_struct *work)
@@ -859,14 +863,18 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
}
rep->vport_rx_rule = flow_rule;
+#ifdef CONFIG_MLX5_CORE_EN_TC
err = mlx5e_tc_init(priv);
if (err)
goto err_del_flow_rule;
+#endif
return 0;
+#ifdef CONFIG_MLX5_CORE_EN_TC
err_del_flow_rule:
mlx5_del_flow_rules(rep->vport_rx_rule);
+#endif
err_destroy_direct_tirs:
mlx5e_destroy_direct_tirs(priv);
err_destroy_direct_rqts:
@@ -879,7 +887,9 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep = rpriv->rep;
+#ifdef CONFIG_MLX5_CORE_EN_TC
mlx5e_tc_cleanup(priv);
+#endif
mlx5_del_flow_rules(rep->vport_rx_rule);
mlx5e_destroy_direct_tirs(priv);
mlx5e_destroy_direct_rqts(priv);
@@ -953,8 +963,10 @@ mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
mlx5e_remove_sqs_fwd_rules(priv);
/* clean (and re-init) existing uplink offloaded TC rules */
+#ifdef CONFIG_MLX5_CORE_EN_TC
mlx5e_tc_cleanup(priv);
mlx5e_tc_init(priv);
+#endif
mlx5e_rep_neigh_cleanup(rpriv);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 8ec13f9be660..2eba4c74ed97 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1966,3 +1966,32 @@ void mlx5e_tc_cleanup(struct mlx5e_priv *priv)
tc->t = NULL;
}
}
+
+int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct mlx5e_channels new_channels = {};
+ int err = 0;
+
+ if (tc && tc != MLX5E_MAX_NUM_TC)
+ return -EINVAL;
+
+ mutex_lock(&priv->state_lock);
+
+ new_channels.params = priv->channels.params;
+ new_channels.params.num_tc = tc ? tc : 1;
+
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ goto out;
+ }
+
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err)
+ goto out;
+
+ mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+out:
+ mutex_unlock(&priv->state_lock);
+ return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index ecbe30d808ae..c1562fa77f35 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -37,6 +37,7 @@
int mlx5e_tc_init(struct mlx5e_priv *priv);
void mlx5e_tc_cleanup(struct mlx5e_priv *priv);
+int mlx5e_setup_tc(struct net_device *netdev, u8 tc);
int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
struct tc_cls_flower_offload *f);
--
2.13.0
^ permalink raw reply related
* [PATCH net 0/3] netvsc bug fixes
From: Stephen Hemminger @ 2017-06-05 21:10 UTC (permalink / raw)
To: davem; +Cc: netdev, Stephen Hemminger
These are non-critical bug fixes to the 4.12 version of netvsc
network driver. Two fix RCU splat warnings, and the other fixes
long standing issue with net poll. I don't think anyone has run
into the net poll issue before, so not worth incorporating into
stable.
Stephen Hemminger (3):
netvsc: fix rcu dereference warning from ethtool
netvsc: fix net poll mode
netvsc: fix RCU warning from set_multicast
drivers/net/hyperv/netvsc_drv.c | 55 +++++++++++++++++++++++++----------------
1 file changed, 34 insertions(+), 21 deletions(-)
--
2.11.0
^ permalink raw reply
* [PATCH net 1/3] netvsc: fix rcu dereference warning from ethtool
From: Stephen Hemminger @ 2017-06-05 21:10 UTC (permalink / raw)
To: davem; +Cc: netdev, Stephen Hemminger
In-Reply-To: <20170605211010.9571-1-sthemmin@microsoft.com>
The ethtool info command calls the netvsc get_sset_count with RTNL
but not with RCU. Which causes warning:
drivers/net/hyperv/netvsc_drv.c:1010 suspicious rcu_dereference_check() usage!
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
---
drivers/net/hyperv/netvsc_drv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 4421a6d00375..d93e4da25fd2 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1028,7 +1028,7 @@ static const struct {
static int netvsc_get_sset_count(struct net_device *dev, int string_set)
{
struct net_device_context *ndc = netdev_priv(dev);
- struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
+ struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
if (!nvdev)
return -ENODEV;
--
2.11.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox