* [PATCH bpf-next v2 4/8] bpf: add icsk_retransmits to bpf_tcp_sock
From: Stanislav Fomichev @ 2019-07-02 16:13 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Eric Dumazet,
Priyaranjan Jha, Yuchung Cheng, Soheil Hassas Yeganeh
In-Reply-To: <20190702161403.191066-1-sdf@google.com>
Add some inet_connection_sock fields to bpf_tcp_sock that might be useful
for debugging congestion control issues.
Cc: Eric Dumazet <edumazet@google.com>
Cc: Priyaranjan Jha <priyarjha@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
include/uapi/linux/bpf.h | 1 +
net/core/filter.c | 20 +++++++++++++++++++-
2 files changed, 20 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index bfb0b1a76684..ead27aebf491 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3078,6 +3078,7 @@ struct bpf_tcp_sock {
*/
__u32 delivered; /* Total data packets delivered incl. rexmits */
__u32 delivered_ce; /* Like the above but only ECE marked packets */
+ __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */
};
struct bpf_sock_tuple {
diff --git a/net/core/filter.c b/net/core/filter.c
index 3da4b6c38b46..089aaea0ccc6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5544,7 +5544,8 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
- if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, delivered_ce))
+ if (off < 0 || off >= offsetofend(struct bpf_tcp_sock,
+ icsk_retransmits))
return false;
if (off % size != 0)
@@ -5575,6 +5576,20 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
offsetof(struct tcp_sock, FIELD)); \
} while (0)
+#define BPF_INET_SOCK_GET_COMMON(FIELD) \
+ do { \
+ BUILD_BUG_ON(FIELD_SIZEOF(struct inet_connection_sock, \
+ FIELD) > \
+ FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \
+ struct inet_connection_sock, \
+ FIELD), \
+ si->dst_reg, si->src_reg, \
+ offsetof( \
+ struct inet_connection_sock, \
+ FIELD)); \
+ } while (0)
+
if (insn > insn_buf)
return insn - insn_buf;
@@ -5661,6 +5676,9 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
case offsetof(struct bpf_tcp_sock, delivered_ce):
BPF_TCP_SOCK_GET_COMMON(delivered_ce);
break;
+ case offsetof(struct bpf_tcp_sock, icsk_retransmits):
+ BPF_INET_SOCK_GET_COMMON(icsk_retransmits);
+ break;
}
return insn - insn_buf;
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v2 3/8] bpf: add dsack_dups/delivered{,_ce} to bpf_tcp_sock
From: Stanislav Fomichev @ 2019-07-02 16:13 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Eric Dumazet,
Priyaranjan Jha, Yuchung Cheng, Soheil Hassas Yeganeh
In-Reply-To: <20190702161403.191066-1-sdf@google.com>
Add more fields to bpf_tcp_sock that might be useful for debugging
congestion control issues.
Cc: Eric Dumazet <edumazet@google.com>
Cc: Priyaranjan Jha <priyarjha@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
include/uapi/linux/bpf.h | 5 +++++
net/core/filter.c | 11 ++++++++++-
2 files changed, 15 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9cdd0aaeba06..bfb0b1a76684 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3073,6 +3073,11 @@ struct bpf_tcp_sock {
* sum(delta(snd_una)), or how many bytes
* were acked.
*/
+ __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups
+ * total number of DSACK blocks received
+ */
+ __u32 delivered; /* Total data packets delivered incl. rexmits */
+ __u32 delivered_ce; /* Like the above but only ECE marked packets */
};
struct bpf_sock_tuple {
diff --git a/net/core/filter.c b/net/core/filter.c
index ad908526545d..3da4b6c38b46 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5544,7 +5544,7 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
- if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, bytes_acked))
+ if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, delivered_ce))
return false;
if (off % size != 0)
@@ -5652,6 +5652,15 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
case offsetof(struct bpf_tcp_sock, bytes_acked):
BPF_TCP_SOCK_GET_COMMON(bytes_acked);
break;
+ case offsetof(struct bpf_tcp_sock, dsack_dups):
+ BPF_TCP_SOCK_GET_COMMON(dsack_dups);
+ break;
+ case offsetof(struct bpf_tcp_sock, delivered):
+ BPF_TCP_SOCK_GET_COMMON(delivered);
+ break;
+ case offsetof(struct bpf_tcp_sock, delivered_ce):
+ BPF_TCP_SOCK_GET_COMMON(delivered_ce);
+ break;
}
return insn - insn_buf;
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v2 2/8] bpf: split shared bpf_tcp_sock and bpf_sock_ops implementation
From: Stanislav Fomichev @ 2019-07-02 16:13 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Eric Dumazet,
Priyaranjan Jha, Yuchung Cheng, Soheil Hassas Yeganeh
In-Reply-To: <20190702161403.191066-1-sdf@google.com>
We've added bpf_tcp_sock member to bpf_sock_ops and don't expect
any new tcp_sock fields in bpf_sock_ops. Let's remove
CONVERT_COMMON_TCP_SOCK_FIELDS so bpf_tcp_sock can be independently
extended.
Cc: Eric Dumazet <edumazet@google.com>
Cc: Priyaranjan Jha <priyarjha@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
net/core/filter.c | 180 ++++++++++++++++++++++++++++++++--------------
1 file changed, 126 insertions(+), 54 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index 4836264f82ee..ad908526545d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5194,54 +5194,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
};
#endif /* CONFIG_IPV6_SEG6_BPF */
-#define CONVERT_COMMON_TCP_SOCK_FIELDS(md_type, CONVERT) \
-do { \
- switch (si->off) { \
- case offsetof(md_type, snd_cwnd): \
- CONVERT(snd_cwnd); break; \
- case offsetof(md_type, srtt_us): \
- CONVERT(srtt_us); break; \
- case offsetof(md_type, snd_ssthresh): \
- CONVERT(snd_ssthresh); break; \
- case offsetof(md_type, rcv_nxt): \
- CONVERT(rcv_nxt); break; \
- case offsetof(md_type, snd_nxt): \
- CONVERT(snd_nxt); break; \
- case offsetof(md_type, snd_una): \
- CONVERT(snd_una); break; \
- case offsetof(md_type, mss_cache): \
- CONVERT(mss_cache); break; \
- case offsetof(md_type, ecn_flags): \
- CONVERT(ecn_flags); break; \
- case offsetof(md_type, rate_delivered): \
- CONVERT(rate_delivered); break; \
- case offsetof(md_type, rate_interval_us): \
- CONVERT(rate_interval_us); break; \
- case offsetof(md_type, packets_out): \
- CONVERT(packets_out); break; \
- case offsetof(md_type, retrans_out): \
- CONVERT(retrans_out); break; \
- case offsetof(md_type, total_retrans): \
- CONVERT(total_retrans); break; \
- case offsetof(md_type, segs_in): \
- CONVERT(segs_in); break; \
- case offsetof(md_type, data_segs_in): \
- CONVERT(data_segs_in); break; \
- case offsetof(md_type, segs_out): \
- CONVERT(segs_out); break; \
- case offsetof(md_type, data_segs_out): \
- CONVERT(data_segs_out); break; \
- case offsetof(md_type, lost_out): \
- CONVERT(lost_out); break; \
- case offsetof(md_type, sacked_out): \
- CONVERT(sacked_out); break; \
- case offsetof(md_type, bytes_received): \
- CONVERT(bytes_received); break; \
- case offsetof(md_type, bytes_acked): \
- CONVERT(bytes_acked); break; \
- } \
-} while (0)
-
#ifdef CONFIG_INET
static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
int dif, int sdif, u8 family, u8 proto)
@@ -5623,9 +5575,6 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
offsetof(struct tcp_sock, FIELD)); \
} while (0)
- CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_tcp_sock,
- BPF_TCP_SOCK_GET_COMMON);
-
if (insn > insn_buf)
return insn - insn_buf;
@@ -5640,6 +5589,69 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
offsetof(struct tcp_sock, rtt_min) +
offsetof(struct minmax_sample, v));
break;
+ case offsetof(struct bpf_tcp_sock, snd_cwnd):
+ BPF_TCP_SOCK_GET_COMMON(snd_cwnd);
+ break;
+ case offsetof(struct bpf_tcp_sock, srtt_us):
+ BPF_TCP_SOCK_GET_COMMON(srtt_us);
+ break;
+ case offsetof(struct bpf_tcp_sock, snd_ssthresh):
+ BPF_TCP_SOCK_GET_COMMON(snd_ssthresh);
+ break;
+ case offsetof(struct bpf_tcp_sock, rcv_nxt):
+ BPF_TCP_SOCK_GET_COMMON(rcv_nxt);
+ break;
+ case offsetof(struct bpf_tcp_sock, snd_nxt):
+ BPF_TCP_SOCK_GET_COMMON(snd_nxt);
+ break;
+ case offsetof(struct bpf_tcp_sock, snd_una):
+ BPF_TCP_SOCK_GET_COMMON(snd_una);
+ break;
+ case offsetof(struct bpf_tcp_sock, mss_cache):
+ BPF_TCP_SOCK_GET_COMMON(mss_cache);
+ break;
+ case offsetof(struct bpf_tcp_sock, ecn_flags):
+ BPF_TCP_SOCK_GET_COMMON(ecn_flags);
+ break;
+ case offsetof(struct bpf_tcp_sock, rate_delivered):
+ BPF_TCP_SOCK_GET_COMMON(rate_delivered);
+ break;
+ case offsetof(struct bpf_tcp_sock, rate_interval_us):
+ BPF_TCP_SOCK_GET_COMMON(rate_interval_us);
+ break;
+ case offsetof(struct bpf_tcp_sock, packets_out):
+ BPF_TCP_SOCK_GET_COMMON(packets_out);
+ break;
+ case offsetof(struct bpf_tcp_sock, retrans_out):
+ BPF_TCP_SOCK_GET_COMMON(retrans_out);
+ break;
+ case offsetof(struct bpf_tcp_sock, total_retrans):
+ BPF_TCP_SOCK_GET_COMMON(total_retrans);
+ break;
+ case offsetof(struct bpf_tcp_sock, segs_in):
+ BPF_TCP_SOCK_GET_COMMON(segs_in);
+ break;
+ case offsetof(struct bpf_tcp_sock, data_segs_in):
+ BPF_TCP_SOCK_GET_COMMON(data_segs_in);
+ break;
+ case offsetof(struct bpf_tcp_sock, segs_out):
+ BPF_TCP_SOCK_GET_COMMON(segs_out);
+ break;
+ case offsetof(struct bpf_tcp_sock, data_segs_out):
+ BPF_TCP_SOCK_GET_COMMON(data_segs_out);
+ break;
+ case offsetof(struct bpf_tcp_sock, lost_out):
+ BPF_TCP_SOCK_GET_COMMON(lost_out);
+ break;
+ case offsetof(struct bpf_tcp_sock, sacked_out):
+ BPF_TCP_SOCK_GET_COMMON(sacked_out);
+ break;
+ case offsetof(struct bpf_tcp_sock, bytes_received):
+ BPF_TCP_SOCK_GET_COMMON(bytes_received);
+ break;
+ case offsetof(struct bpf_tcp_sock, bytes_acked):
+ BPF_TCP_SOCK_GET_COMMON(bytes_acked);
+ break;
}
return insn - insn_buf;
@@ -7913,9 +7925,6 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \
} while (0)
- CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_sock_ops,
- SOCK_OPS_GET_TCP_SOCK_FIELD);
-
if (insn > insn_buf)
return insn - insn_buf;
@@ -8085,6 +8094,69 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash,
struct sock, type);
break;
+ case offsetof(struct bpf_sock_ops, snd_cwnd):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(snd_cwnd);
+ break;
+ case offsetof(struct bpf_sock_ops, srtt_us):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(srtt_us);
+ break;
+ case offsetof(struct bpf_sock_ops, snd_ssthresh):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(snd_ssthresh);
+ break;
+ case offsetof(struct bpf_sock_ops, rcv_nxt):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(rcv_nxt);
+ break;
+ case offsetof(struct bpf_sock_ops, snd_nxt):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(snd_nxt);
+ break;
+ case offsetof(struct bpf_sock_ops, snd_una):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(snd_una);
+ break;
+ case offsetof(struct bpf_sock_ops, mss_cache):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(mss_cache);
+ break;
+ case offsetof(struct bpf_sock_ops, ecn_flags):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(ecn_flags);
+ break;
+ case offsetof(struct bpf_sock_ops, rate_delivered):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(rate_delivered);
+ break;
+ case offsetof(struct bpf_sock_ops, rate_interval_us):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(rate_interval_us);
+ break;
+ case offsetof(struct bpf_sock_ops, packets_out):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(packets_out);
+ break;
+ case offsetof(struct bpf_sock_ops, retrans_out):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(retrans_out);
+ break;
+ case offsetof(struct bpf_sock_ops, total_retrans):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(total_retrans);
+ break;
+ case offsetof(struct bpf_sock_ops, segs_in):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(segs_in);
+ break;
+ case offsetof(struct bpf_sock_ops, data_segs_in):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_in);
+ break;
+ case offsetof(struct bpf_sock_ops, segs_out):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(segs_out);
+ break;
+ case offsetof(struct bpf_sock_ops, data_segs_out):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_out);
+ break;
+ case offsetof(struct bpf_sock_ops, lost_out):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(lost_out);
+ break;
+ case offsetof(struct bpf_sock_ops, sacked_out):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(sacked_out);
+ break;
+ case offsetof(struct bpf_sock_ops, bytes_received):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_received);
+ break;
+ case offsetof(struct bpf_sock_ops, bytes_acked):
+ SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked);
+ break;
case offsetof(struct bpf_sock_ops, sk):
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
struct bpf_sock_ops_kern,
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v2 1/8] bpf: add BPF_CGROUP_SOCK_OPS callback that is executed on every RTT
From: Stanislav Fomichev @ 2019-07-02 16:13 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Eric Dumazet,
Priyaranjan Jha, Yuchung Cheng, Soheil Hassas Yeganeh
In-Reply-To: <20190702161403.191066-1-sdf@google.com>
Performance impact should be minimal because it's under a new
BPF_SOCK_OPS_RTT_CB_FLAG flag that has to be explicitly enabled.
Suggested-by: Eric Dumazet <edumazet@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Priyaranjan Jha <priyarjha@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
include/net/tcp.h | 8 ++++++++
include/uapi/linux/bpf.h | 6 +++++-
net/ipv4/tcp_input.c | 4 ++++
3 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9d36cc88d043..e16d8a3fd3b4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2221,6 +2221,14 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1);
}
+static inline void tcp_bpf_rtt(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTT_CB_FLAG))
+ tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL);
+}
+
#if IS_ENABLED(CONFIG_SMC)
extern struct static_key_false tcp_have_smc;
#endif
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index cffea1826a1f..9cdd0aaeba06 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1770,6 +1770,7 @@ union bpf_attr {
* * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
* * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
* * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
+ * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT)
*
* Therefore, this function can be used to clear a callback flag by
* setting the appropriate bit to zero. e.g. to disable the RTO
@@ -3314,7 +3315,8 @@ struct bpf_sock_ops {
#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0)
#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1)
#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2)
-#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently
+#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently
* supported cb flags
*/
@@ -3369,6 +3371,8 @@ enum {
BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after
* socket transition to LISTEN state.
*/
+ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT.
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b71efeb0ae5b..c21e8a22fb3b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -778,6 +778,8 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2;
tp->rtt_seq = tp->snd_nxt;
tp->mdev_max_us = tcp_rto_min_us(sk);
+
+ tcp_bpf_rtt(sk);
}
} else {
/* no previous measure. */
@@ -786,6 +788,8 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk));
tp->mdev_max_us = tp->rttvar_us;
tp->rtt_seq = tp->snd_nxt;
+
+ tcp_bpf_rtt(sk);
}
tp->srtt_us = max(1U, srtt);
}
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v2 0/8] bpf: TCP RTT sock_ops bpf callback
From: Stanislav Fomichev @ 2019-07-02 16:13 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Eric Dumazet,
Priyaranjan Jha, Yuchung Cheng, Soheil Hassas Yeganeh
Congestion control team would like to have a periodic callback to
track some TCP statistics. Let's add a sock_ops callback that can be
selectively enabled on a socket by socket basis and is executed for
every RTT. BPF program frequency can be further controlled by calling
bpf_ktime_get_ns and bailing out early.
I run neper tcp_stream and tcp_rr tests with the sample program
from the last patch and didn't observe any noticeable performance
difference.
v2:
* add a comment about second accept() in selftest (Yonghong Song)
* refer to tcp_bpf.readme in sample program (Yonghong Song)
Suggested-by: Eric Dumazet <edumazet@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Priyaranjan Jha <priyarjha@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Stanislav Fomichev (8):
bpf: add BPF_CGROUP_SOCK_OPS callback that is executed on every RTT
bpf: split shared bpf_tcp_sock and bpf_sock_ops implementation
bpf: add dsack_dups/delivered{,_ce} to bpf_tcp_sock
bpf: add icsk_retransmits to bpf_tcp_sock
bpf/tools: sync bpf.h
selftests/bpf: test BPF_SOCK_OPS_RTT_CB
samples/bpf: add sample program that periodically dumps TCP stats
samples/bpf: fix tcp_bpf.readme detach command
include/net/tcp.h | 8 +
include/uapi/linux/bpf.h | 12 +-
net/core/filter.c | 207 +++++++++++-----
net/ipv4/tcp_input.c | 4 +
samples/bpf/Makefile | 1 +
samples/bpf/tcp_bpf.readme | 2 +-
samples/bpf/tcp_dumpstats_kern.c | 68 ++++++
tools/include/uapi/linux/bpf.h | 12 +-
tools/testing/selftests/bpf/Makefile | 3 +-
tools/testing/selftests/bpf/progs/tcp_rtt.c | 61 +++++
tools/testing/selftests/bpf/test_tcp_rtt.c | 254 ++++++++++++++++++++
11 files changed, 574 insertions(+), 58 deletions(-)
create mode 100644 samples/bpf/tcp_dumpstats_kern.c
create mode 100644 tools/testing/selftests/bpf/progs/tcp_rtt.c
create mode 100644 tools/testing/selftests/bpf/test_tcp_rtt.c
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply
* Re: [PATCH net-next 1/1] devlink: Add APIs to publish/unpublish the port parameters.
From: Andrew Lunn @ 2019-07-02 16:11 UTC (permalink / raw)
To: Sudarsana Reddy Kalluru; +Cc: davem, netdev, mkalderon, aelior, jiri
In-Reply-To: <20190702152056.31728-1-skalluru@marvell.com>
On Tue, Jul 02, 2019 at 08:20:56AM -0700, Sudarsana Reddy Kalluru wrote:
> The patch adds devlink interfaces for drivers to publish/unpublish the
> devlink port parameters.
Hi Sudarsana
A good commit message says more about 'why' than 'what'. I can see the
'what' by reading the code. But the 'why' is often not so clear.
Why would i want to unpublish port parameters?
Thanks
Andrew
^ permalink raw reply
* Re: [PATCH v2 bpf-next] libbpf: fix GCC8 warning for strncpy
From: Y Song @ 2019-07-02 16:10 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: andrii.nakryiko, bpf, netdev, Alexei Starovoitov, Daniel Borkmann,
Magnus Karlsson
In-Reply-To: <20190702151620.3382559-1-andriin@fb.com>
On Tue, Jul 2, 2019 at 8:17 AM Andrii Nakryiko <andriin@fb.com> wrote:
>
> GCC8 started emitting warning about using strncpy with number of bytes
> exactly equal destination size, which is generally unsafe, as can lead
> to non-zero terminated string being copied. Use IFNAMSIZ - 1 as number
> of bytes to ensure name is always zero-terminated.
>
> Cc: Magnus Karlsson <magnus.karlsson@intel.com>
> Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
> ---
> tools/lib/bpf/xsk.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
> index bf15a80a37c2..b33740221b7e 100644
> --- a/tools/lib/bpf/xsk.c
> +++ b/tools/lib/bpf/xsk.c
> @@ -327,7 +327,8 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
>
> channels.cmd = ETHTOOL_GCHANNELS;
> ifr.ifr_data = (void *)&channels;
> - strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ);
> + strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
> + ifr.ifr_name[IFNAMSIZ - 1] = '\0';
> err = ioctl(fd, SIOCETHTOOL, &ifr);
> if (err && errno != EOPNOTSUPP) {
> ret = -errno;
> --
> 2.17.1
>
^ permalink raw reply
* Re: [PATCH bpf] xdp: fix race on generic receive path
From: Ilya Maximets @ 2019-07-02 16:11 UTC (permalink / raw)
To: Magnus Karlsson
Cc: Network Development, linux-kernel, bpf, xdp-newbies,
David S. Miller, Björn Töpel, Magnus Karlsson,
Jonathan Lemon, Jakub Kicinski, Alexei Starovoitov,
Daniel Borkmann
In-Reply-To: <CAJ8uoz34wS-Ut=TiULN32Zs-terBkzSiEws65jsd=f4S_rp43Q@mail.gmail.com>
On 02.07.2019 18:01, Magnus Karlsson wrote:
> On Tue, Jul 2, 2019 at 4:36 PM Ilya Maximets <i.maximets@samsung.com> wrote:
>>
>> Unlike driver mode, generic xdp receive could be triggered
>> by different threads on different CPU cores at the same time
>> leading to the fill and rx queue breakage. For example, this
>> could happen while sending packets from two processes to the
>> first interface of veth pair while the second part of it is
>> open with AF_XDP socket.
>>
>> Need to take a lock for each generic receive to avoid race.
>
> Thanks for this catch Ilya. Do you have any performance numbers you
> could share of the impact of adding this spin lock? The reason I ask
> is that if the impact is negligible, then let us just add it. But if
> it is too large, we might want to brain storm about some other
> possible solutions.
Hi. Unfortunately, I don't have a hardware for performance tests right
now, so I could run only tests over virtual interfaces like veth pair.
It'll be good if someone could check the performance with real HW.
Best regards, Ilya Maximets.
>
> Thanks: Magnus
>
>> Fixes: c497176cb2e4 ("xsk: add Rx receive functions and poll support")
>> Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
>> ---
>> include/net/xdp_sock.h | 2 ++
>> net/xdp/xsk.c | 32 +++++++++++++++++++++++---------
>> 2 files changed, 25 insertions(+), 9 deletions(-)
>>
>> diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
>> index d074b6d60f8a..ac3c047d058c 100644
>> --- a/include/net/xdp_sock.h
>> +++ b/include/net/xdp_sock.h
>> @@ -67,6 +67,8 @@ struct xdp_sock {
>> * in the SKB destructor callback.
>> */
>> spinlock_t tx_completion_lock;
>> + /* Protects generic receive. */
>> + spinlock_t rx_lock;
>> u64 rx_dropped;
>> };
>>
>> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
>> index a14e8864e4fa..19f41d2b670c 100644
>> --- a/net/xdp/xsk.c
>> +++ b/net/xdp/xsk.c
>> @@ -119,17 +119,22 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
>> {
>> u32 metalen = xdp->data - xdp->data_meta;
>> u32 len = xdp->data_end - xdp->data;
>> + unsigned long flags;
>> void *buffer;
>> u64 addr;
>> int err;
>>
>> - if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
>> - return -EINVAL;
>> + spin_lock_irqsave(&xs->rx_lock, flags);
>> +
>> + if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) {
>> + err = -EINVAL;
>> + goto out_unlock;
>> + }
>>
>> if (!xskq_peek_addr(xs->umem->fq, &addr) ||
>> len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
>> - xs->rx_dropped++;
>> - return -ENOSPC;
>> + err = -ENOSPC;
>> + goto out_drop;
>> }
>>
>> addr += xs->umem->headroom;
>> @@ -138,13 +143,21 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
>> memcpy(buffer, xdp->data_meta, len + metalen);
>> addr += metalen;
>> err = xskq_produce_batch_desc(xs->rx, addr, len);
>> - if (!err) {
>> - xskq_discard_addr(xs->umem->fq);
>> - xsk_flush(xs);
>> - return 0;
>> - }
>> + if (err)
>> + goto out_drop;
>> +
>> + xskq_discard_addr(xs->umem->fq);
>> + xskq_produce_flush_desc(xs->rx);
>>
>> + spin_unlock_irqrestore(&xs->rx_lock, flags);
>> +
>> + xs->sk.sk_data_ready(&xs->sk);
>> + return 0;
>> +
>> +out_drop:
>> xs->rx_dropped++;
>> +out_unlock:
>> + spin_unlock_irqrestore(&xs->rx_lock, flags);
>> return err;
>> }
>>
>> @@ -765,6 +778,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
>>
>> xs = xdp_sk(sk);
>> mutex_init(&xs->mutex);
>> + spin_lock_init(&xs->rx_lock);
>> spin_lock_init(&xs->tx_completion_lock);
>>
>> mutex_lock(&net->xdp.lock);
>> --
>> 2.17.1
^ permalink raw reply
* Re: [PATCH bpf-next] bpf: cgroup: Fix build error without CONFIG_NET
From: Yonghong Song @ 2019-07-02 16:04 UTC (permalink / raw)
To: YueHaibing
Cc: Stanislav Fomichev, ast@kernel.org, daniel@iogearbox.net,
Martin Lau, Song Liu, sdf@google.com,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
bpf@vger.kernel.org
In-Reply-To: <20190702155316.GJ6757@mini-arch>
On 7/2/19 8:53 AM, Stanislav Fomichev wrote:
> On 07/02, YueHaibing wrote:
>> If CONFIG_NET is not set, gcc building fails:
>>
>> kernel/bpf/cgroup.o: In function `cg_sockopt_func_proto':
>> cgroup.c:(.text+0x237e): undefined reference to `bpf_sk_storage_get_proto'
>> cgroup.c:(.text+0x2394): undefined reference to `bpf_sk_storage_delete_proto'
>> kernel/bpf/cgroup.o: In function `__cgroup_bpf_run_filter_getsockopt':
>> (.text+0x2a1f): undefined reference to `lock_sock_nested'
>> (.text+0x2ca2): undefined reference to `release_sock'
>> kernel/bpf/cgroup.o: In function `__cgroup_bpf_run_filter_setsockopt':
>> (.text+0x3006): undefined reference to `lock_sock_nested'
>> (.text+0x32bb): undefined reference to `release_sock'
>>
>> Add CONFIG_NET dependency to fix this.
> Can you share the config? Do I understand correctly that you have
> CONFIG_NET=n and CONFIG_BPF=y? What parts of BPF do you expect to
> work in this case?
>
> Less invasive fix would be something along the lines:
>
> diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
> index 76fa0076f20d..0a00eaca6fae 100644
> --- a/kernel/bpf/cgroup.c
> +++ b/kernel/bpf/cgroup.c
> @@ -939,6 +939,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
> }
> EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
>
> +#ifdef CONFIG_NET
> static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
> enum bpf_attach_type attach_type)
> {
> @@ -1120,6 +1121,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
> return ret;
> }
> EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
> +#endif
>
> static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
> size_t *lenp)
> @@ -1386,10 +1388,12 @@ static const struct bpf_func_proto *
> cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
> {
> switch (func_id) {
> +#ifdef CONFIG_NET
> case BPF_FUNC_sk_storage_get:
> return &bpf_sk_storage_get_proto;
> case BPF_FUNC_sk_storage_delete:
> return &bpf_sk_storage_delete_proto;
> +#endif
> #ifdef CONFIG_INET
> case BPF_FUNC_tcp_sock:
> return &bpf_tcp_sock_proto;
Ah. Just send another email without checking inbox.
Looks like the above change is preferred.
YueHaibing, could you make change and resubmit your patch?
>
>> Reported-by: Hulk Robot <hulkci@huawei.com>
>> Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks")
>> Signed-off-by: YueHaibing <yuehaibing@huawei.com>
>> ---
>> init/Kconfig | 1 +
>> 1 file changed, 1 insertion(+)
>>
>> diff --git a/init/Kconfig b/init/Kconfig
>> index e2e51b5..341cf2a 100644
>> --- a/init/Kconfig
>> +++ b/init/Kconfig
>> @@ -998,6 +998,7 @@ config CGROUP_PERF
>> config CGROUP_BPF
>> bool "Support for eBPF programs attached to cgroups"
>> depends on BPF_SYSCALL
>> + depends on NET
>> select SOCK_CGROUP_DATA
>> help
>> Allow attaching eBPF programs to a cgroup using the bpf(2)
>> --
>> 2.7.4
>>
>>
^ permalink raw reply
* Re: [PATCH bpf-next] bpf: cgroup: Fix build error without CONFIG_NET
From: Yonghong Song @ 2019-07-02 16:01 UTC (permalink / raw)
To: YueHaibing, ast@kernel.org, daniel@iogearbox.net, Martin Lau,
Song Liu, sdf@google.com
Cc: linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
bpf@vger.kernel.org
In-Reply-To: <20190702132913.26060-1-yuehaibing@huawei.com>
On 7/2/19 6:29 AM, YueHaibing wrote:
> If CONFIG_NET is not set, gcc building fails:
>
> kernel/bpf/cgroup.o: In function `cg_sockopt_func_proto':
> cgroup.c:(.text+0x237e): undefined reference to `bpf_sk_storage_get_proto'
> cgroup.c:(.text+0x2394): undefined reference to `bpf_sk_storage_delete_proto'
> kernel/bpf/cgroup.o: In function `__cgroup_bpf_run_filter_getsockopt':
> (.text+0x2a1f): undefined reference to `lock_sock_nested'
> (.text+0x2ca2): undefined reference to `release_sock'
> kernel/bpf/cgroup.o: In function `__cgroup_bpf_run_filter_setsockopt':
> (.text+0x3006): undefined reference to `lock_sock_nested'
> (.text+0x32bb): undefined reference to `release_sock'
>
> Add CONFIG_NET dependency to fix this.
>
> Reported-by: Hulk Robot <hulkci@huawei.com>
> Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks")
> Signed-off-by: YueHaibing <yuehaibing@huawei.com>
> ---
> init/Kconfig | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/init/Kconfig b/init/Kconfig
> index e2e51b5..341cf2a 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -998,6 +998,7 @@ config CGROUP_PERF
> config CGROUP_BPF
> bool "Support for eBPF programs attached to cgroups"
> depends on BPF_SYSCALL
> + depends on NET
> select SOCK_CGROUP_DATA
> help
> Allow attaching eBPF programs to a cgroup using the bpf(2)
Adding CGROUP_BPF depending on CONFIG_NET is not a good idea.
There should be really independent.
How about the following change?
-bash-4.4$ git diff
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 76fa0076f20d..0a00eaca6fae 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -939,6 +939,7 @@ int __cgroup_bpf_run_filter_sysctl(struct
ctl_table_header *head,
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
+#ifdef CONFIG_NET
static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
enum bpf_attach_type
attach_type)
{
@@ -1120,6 +1121,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock
*sk, int level,
return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
+#endif
static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
size_t *lenp)
@@ -1386,10 +1388,12 @@ static const struct bpf_func_proto *
cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog
*prog)
{
switch (func_id) {
+#ifdef CONFIG_NET
case BPF_FUNC_sk_storage_get:
return &bpf_sk_storage_get_proto;
case BPF_FUNC_sk_storage_delete:
return &bpf_sk_storage_delete_proto;
+#endif
#ifdef CONFIG_INET
case BPF_FUNC_tcp_sock:
return &bpf_tcp_sock_proto;
Stanislav, you introduced getsockopt and setsockopt hooks which
have this compilation issues if CONFIG_NET=n.
What do you think for the above change?
^ permalink raw reply related
* Re: [PATCH bpf-next] bpf: cgroup: Fix build error without CONFIG_NET
From: Stanislav Fomichev @ 2019-07-02 15:53 UTC (permalink / raw)
To: YueHaibing
Cc: ast, daniel, kafai, songliubraving, yhs, sdf, linux-kernel,
netdev, bpf
In-Reply-To: <20190702132913.26060-1-yuehaibing@huawei.com>
On 07/02, YueHaibing wrote:
> If CONFIG_NET is not set, gcc building fails:
>
> kernel/bpf/cgroup.o: In function `cg_sockopt_func_proto':
> cgroup.c:(.text+0x237e): undefined reference to `bpf_sk_storage_get_proto'
> cgroup.c:(.text+0x2394): undefined reference to `bpf_sk_storage_delete_proto'
> kernel/bpf/cgroup.o: In function `__cgroup_bpf_run_filter_getsockopt':
> (.text+0x2a1f): undefined reference to `lock_sock_nested'
> (.text+0x2ca2): undefined reference to `release_sock'
> kernel/bpf/cgroup.o: In function `__cgroup_bpf_run_filter_setsockopt':
> (.text+0x3006): undefined reference to `lock_sock_nested'
> (.text+0x32bb): undefined reference to `release_sock'
>
> Add CONFIG_NET dependency to fix this.
Can you share the config? Do I understand correctly that you have
CONFIG_NET=n and CONFIG_BPF=y? What parts of BPF do you expect to
work in this case?
Less invasive fix would be something along the lines:
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 76fa0076f20d..0a00eaca6fae 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -939,6 +939,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
+#ifdef CONFIG_NET
static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
enum bpf_attach_type attach_type)
{
@@ -1120,6 +1121,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
+#endif
static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
size_t *lenp)
@@ -1386,10 +1388,12 @@ static const struct bpf_func_proto *
cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
+#ifdef CONFIG_NET
case BPF_FUNC_sk_storage_get:
return &bpf_sk_storage_get_proto;
case BPF_FUNC_sk_storage_delete:
return &bpf_sk_storage_delete_proto;
+#endif
#ifdef CONFIG_INET
case BPF_FUNC_tcp_sock:
return &bpf_tcp_sock_proto;
> Reported-by: Hulk Robot <hulkci@huawei.com>
> Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks")
> Signed-off-by: YueHaibing <yuehaibing@huawei.com>
> ---
> init/Kconfig | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/init/Kconfig b/init/Kconfig
> index e2e51b5..341cf2a 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -998,6 +998,7 @@ config CGROUP_PERF
> config CGROUP_BPF
> bool "Support for eBPF programs attached to cgroups"
> depends on BPF_SYSCALL
> + depends on NET
> select SOCK_CGROUP_DATA
> help
> Allow attaching eBPF programs to a cgroup using the bpf(2)
> --
> 2.7.4
>
>
^ permalink raw reply related
* Re: mlxsw: spectrum: PTP: Support timestamping on Spectrum-1 - potential null ptr dereference
From: Colin Ian King @ 2019-07-02 15:52 UTC (permalink / raw)
To: Petr Machata
Cc: Jiri Pirko, Ido Schimmel, David S. Miller, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
In-Reply-To: <87r278sado.fsf@mellanox.com>
On 02/07/2019 16:51, Petr Machata wrote:
>
> Colin Ian King <colin.king@canonical.com> writes:
>
>> Hi,
>>
>> Static analysis with Coverity on today's linux-next has found a
>> potential null pointer dereference bug with the following commit:
>>
>> commit d92e4e6e33c8b19635be70fb8935b627d2e4f8fe
>> Author: Petr Machata <petrm@mellanox.com>
>> Date: Sun Jun 30 09:04:56 2019 +0300
>>
>> mlxsw: spectrum: PTP: Support timestamping on Spectrum-1
>>
>>
>> In function: mlxsw_sp1_ptp_packet_finish the offending code is as follows:
>>
>> /* Between capturing the packet and finishing it, there is a
>> window of
>> * opportunity for the originating port to go away (e.g. due to a
>> * split). Also make sure the SKB device reference is still valid.
>> */
>> mlxsw_sp_port = mlxsw_sp->ports[local_port];
>> if (!mlxsw_sp_port && (!skb->dev || skb->dev == mlxsw_sp_port->dev)) {
>> dev_kfree_skb_any(skb);
>> return;
>> }
>>
>> If mlxsw_sp_port is null and skb->dev is not-null then the comparison
>> "skb->dev == mlxsw_sp_port->dev" ends up with a null pointer dereference.
>>
>> I think the if statement should be:
>>
>> if (mlxsw_sp_port && (!skb->dev || skb->dev == mlxsw_sp_port->dev))
>>
>> ..but I'm not 100% sure as I may be missing something a bit more subtle
>> here.
>
> Yes, that line is wrong. It's missing a pair of parens, it should be:
>
> if (!(mlxsw_sp_port && (!skb->dev || skb->dev == mlxsw_sp_port->dev))) {
>
> I.e. I need a port && I need the skb->dev to still refer to that port
> (or else be NULL). If that doesn't hold, bail out.
Ah, that makes sense.
>
> Thanks for the report, I'll spin a fix!
>
OK, thanks!
^ permalink raw reply
* [PATCH ipsec v2] xfrm interface: fix memory leak on creation
From: Nicolas Dichtel @ 2019-07-02 15:51 UTC (permalink / raw)
To: steffen.klassert, davem
Cc: netdev, Nicolas Dichtel, Lorenzo Colitti, Benedict Wong,
Shannon Nelson, Antony Antony, Eyal Birger, Julien Floret
The following commands produce a backtrace and return an error but the xfrm
interface is created (in the wrong netns):
$ ip netns add foo
$ ip netns add bar
$ ip -n foo netns set bar 0
$ ip -n foo link add xfrmi0 link-netnsid 0 type xfrm dev lo if_id 23
RTNETLINK answers: Invalid argument
$ ip -n bar link ls xfrmi0
2: xfrmi0@lo: <NOARP,M-DOWN> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
link/none 00:00:00:00:00:00 brd 00:00:00:00:00:00
Here is the backtrace:
[ 79.879174] WARNING: CPU: 0 PID: 1178 at net/core/dev.c:8172 rollback_registered_many+0x86/0x3c1
[ 79.880260] Modules linked in: xfrm_interface nfsv3 nfs_acl auth_rpcgss nfsv4 nfs lockd grace sunrpc fscache button parport_pc parport serio_raw evdev pcspkr loop ext4 crc16 mbcache jbd2 crc32c_generic ide_cd_mod ide_gd_mod cdrom ata_$
eneric ata_piix libata scsi_mod 8139too piix psmouse i2c_piix4 ide_core 8139cp mii i2c_core floppy
[ 79.883698] CPU: 0 PID: 1178 Comm: ip Not tainted 5.2.0-rc6+ #106
[ 79.884462] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[ 79.885447] RIP: 0010:rollback_registered_many+0x86/0x3c1
[ 79.886120] Code: 01 e8 d7 7d c6 ff 0f 0b 48 8b 45 00 4c 8b 20 48 8d 58 90 49 83 ec 70 48 8d 7b 70 48 39 ef 74 44 8a 83 d0 04 00 00 84 c0 75 1f <0f> 0b e8 61 cd ff ff 48 b8 00 01 00 00 00 00 ad de 48 89 43 70 66
[ 79.888667] RSP: 0018:ffffc900015ab740 EFLAGS: 00010246
[ 79.889339] RAX: ffff8882353e5700 RBX: ffff8882353e56a0 RCX: ffff8882353e5710
[ 79.890174] RDX: ffffc900015ab7e0 RSI: ffffc900015ab7e0 RDI: ffff8882353e5710
[ 79.891029] RBP: ffffc900015ab7e0 R08: ffffc900015ab7e0 R09: ffffc900015ab7e0
[ 79.891866] R10: ffffc900015ab7a0 R11: ffffffff82233fec R12: ffffc900015ab770
[ 79.892728] R13: ffffffff81eb7ec0 R14: ffff88822ed6cf00 R15: 00000000ffffffea
[ 79.893557] FS: 00007ff350f31740(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000
[ 79.894581] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 79.895317] CR2: 00000000006c8580 CR3: 000000022c272000 CR4: 00000000000006f0
[ 79.896137] Call Trace:
[ 79.896464] unregister_netdevice_many+0x12/0x6c
[ 79.896998] __rtnl_newlink+0x6e2/0x73b
[ 79.897446] ? __kmalloc_node_track_caller+0x15e/0x185
[ 79.898039] ? pskb_expand_head+0x5f/0x1fe
[ 79.898556] ? stack_access_ok+0xd/0x2c
[ 79.899009] ? deref_stack_reg+0x12/0x20
[ 79.899462] ? stack_access_ok+0xd/0x2c
[ 79.899927] ? stack_access_ok+0xd/0x2c
[ 79.900404] ? __module_text_address+0x9/0x4f
[ 79.900910] ? is_bpf_text_address+0x5/0xc
[ 79.901390] ? kernel_text_address+0x67/0x7b
[ 79.901884] ? __kernel_text_address+0x1a/0x25
[ 79.902397] ? unwind_get_return_address+0x12/0x23
[ 79.903122] ? __cmpxchg_double_slab.isra.37+0x46/0x77
[ 79.903772] rtnl_newlink+0x43/0x56
[ 79.904217] rtnetlink_rcv_msg+0x200/0x24c
In fact, each time a xfrm interface was created, a netdev was allocated
by __rtnl_newlink()/rtnl_create_link() and then another one by
xfrmi_newlink()/xfrmi_create(). Only the second one was registered, it's
why the previous commands produce a backtrace: dev_change_net_namespace()
was called on a netdev with reg_state set to NETREG_UNINITIALIZED (the
first one).
CC: Lorenzo Colitti <lorenzo@google.com>
CC: Benedict Wong <benedictwong@google.com>
CC: Steffen Klassert <steffen.klassert@secunet.com>
CC: Shannon Nelson <shannon.nelson@oracle.com>
CC: Antony Antony <antony@phenome.org>
CC: Eyal Birger <eyal.birger@gmail.com>
Fixes: f203b76d7809 ("xfrm: Add virtual xfrm interfaces")
Reported-by: Julien Floret <julien.floret@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
v1 -> v2:
- fix typos in commit log
net/xfrm/xfrm_interface.c | 98 +++++++++++----------------------------
1 file changed, 28 insertions(+), 70 deletions(-)
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index ad3a2555c517..7dbe0c608df5 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -133,7 +133,7 @@ static void xfrmi_dev_free(struct net_device *dev)
free_percpu(dev->tstats);
}
-static int xfrmi_create2(struct net_device *dev)
+static int xfrmi_create(struct net_device *dev)
{
struct xfrm_if *xi = netdev_priv(dev);
struct net *net = dev_net(dev);
@@ -156,54 +156,7 @@ static int xfrmi_create2(struct net_device *dev)
return err;
}
-static struct xfrm_if *xfrmi_create(struct net *net, struct xfrm_if_parms *p)
-{
- struct net_device *dev;
- struct xfrm_if *xi;
- char name[IFNAMSIZ];
- int err;
-
- if (p->name[0]) {
- strlcpy(name, p->name, IFNAMSIZ);
- } else {
- err = -EINVAL;
- goto failed;
- }
-
- dev = alloc_netdev(sizeof(*xi), name, NET_NAME_UNKNOWN, xfrmi_dev_setup);
- if (!dev) {
- err = -EAGAIN;
- goto failed;
- }
-
- dev_net_set(dev, net);
-
- xi = netdev_priv(dev);
- xi->p = *p;
- xi->net = net;
- xi->dev = dev;
- xi->phydev = dev_get_by_index(net, p->link);
- if (!xi->phydev) {
- err = -ENODEV;
- goto failed_free;
- }
-
- err = xfrmi_create2(dev);
- if (err < 0)
- goto failed_dev_put;
-
- return xi;
-
-failed_dev_put:
- dev_put(xi->phydev);
-failed_free:
- free_netdev(dev);
-failed:
- return ERR_PTR(err);
-}
-
-static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p,
- int create)
+static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p)
{
struct xfrm_if __rcu **xip;
struct xfrm_if *xi;
@@ -211,17 +164,11 @@ static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p,
for (xip = &xfrmn->xfrmi[0];
(xi = rtnl_dereference(*xip)) != NULL;
- xip = &xi->next) {
- if (xi->p.if_id == p->if_id) {
- if (create)
- return ERR_PTR(-EEXIST);
-
+ xip = &xi->next)
+ if (xi->p.if_id == p->if_id)
return xi;
- }
- }
- if (!create)
- return ERR_PTR(-ENODEV);
- return xfrmi_create(net, p);
+
+ return NULL;
}
static void xfrmi_dev_uninit(struct net_device *dev)
@@ -686,21 +633,33 @@ static int xfrmi_newlink(struct net *src_net, struct net_device *dev,
struct netlink_ext_ack *extack)
{
struct net *net = dev_net(dev);
- struct xfrm_if_parms *p;
+ struct xfrm_if_parms p;
struct xfrm_if *xi;
+ int err;
- xi = netdev_priv(dev);
- p = &xi->p;
-
- xfrmi_netlink_parms(data, p);
+ xfrmi_netlink_parms(data, &p);
if (!tb[IFLA_IFNAME])
return -EINVAL;
- nla_strlcpy(p->name, tb[IFLA_IFNAME], IFNAMSIZ);
+ nla_strlcpy(p.name, tb[IFLA_IFNAME], IFNAMSIZ);
- xi = xfrmi_locate(net, p, 1);
- return PTR_ERR_OR_ZERO(xi);
+ xi = xfrmi_locate(net, &p);
+ if (xi)
+ return -EEXIST;
+
+ xi = netdev_priv(dev);
+ xi->p = p;
+ xi->net = net;
+ xi->dev = dev;
+ xi->phydev = dev_get_by_index(net, p.link);
+ if (!xi->phydev)
+ return -ENODEV;
+
+ err = xfrmi_create(dev);
+ if (err < 0)
+ dev_put(xi->phydev);
+ return err;
}
static void xfrmi_dellink(struct net_device *dev, struct list_head *head)
@@ -717,9 +676,8 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
xfrmi_netlink_parms(data, &xi->p);
- xi = xfrmi_locate(net, &xi->p, 0);
-
- if (IS_ERR_OR_NULL(xi)) {
+ xi = xfrmi_locate(net, &xi->p);
+ if (!xi) {
xi = netdev_priv(dev);
} else {
if (xi->dev != dev)
--
2.21.0
^ permalink raw reply related
* Re: mlxsw: spectrum: PTP: Support timestamping on Spectrum-1 - potential null ptr dereference
From: Petr Machata @ 2019-07-02 15:51 UTC (permalink / raw)
To: Colin Ian King
Cc: Jiri Pirko, Ido Schimmel, David S. Miller, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
In-Reply-To: <4fb676a6-1de8-8bcf-5f2e-3157827546c8@canonical.com>
Colin Ian King <colin.king@canonical.com> writes:
> Hi,
>
> Static analysis with Coverity on today's linux-next has found a
> potential null pointer dereference bug with the following commit:
>
> commit d92e4e6e33c8b19635be70fb8935b627d2e4f8fe
> Author: Petr Machata <petrm@mellanox.com>
> Date: Sun Jun 30 09:04:56 2019 +0300
>
> mlxsw: spectrum: PTP: Support timestamping on Spectrum-1
>
>
> In function: mlxsw_sp1_ptp_packet_finish the offending code is as follows:
>
> /* Between capturing the packet and finishing it, there is a
> window of
> * opportunity for the originating port to go away (e.g. due to a
> * split). Also make sure the SKB device reference is still valid.
> */
> mlxsw_sp_port = mlxsw_sp->ports[local_port];
> if (!mlxsw_sp_port && (!skb->dev || skb->dev == mlxsw_sp_port->dev)) {
> dev_kfree_skb_any(skb);
> return;
> }
>
> If mlxsw_sp_port is null and skb->dev is not-null then the comparison
> "skb->dev == mlxsw_sp_port->dev" ends up with a null pointer dereference.
>
> I think the if statement should be:
>
> if (mlxsw_sp_port && (!skb->dev || skb->dev == mlxsw_sp_port->dev))
>
> ..but I'm not 100% sure as I may be missing something a bit more subtle
> here.
Yes, that line is wrong. It's missing a pair of parens, it should be:
if (!(mlxsw_sp_port && (!skb->dev || skb->dev == mlxsw_sp_port->dev))) {
I.e. I need a port && I need the skb->dev to still refer to that port
(or else be NULL). If that doesn't hold, bail out.
Thanks for the report, I'll spin a fix!
^ permalink raw reply
* [PATCH bpf-next] selftests/bpf: fix compiling loop{1,2,3}.c on s390
From: Ilya Leoshkevich @ 2019-07-02 15:39 UTC (permalink / raw)
To: bpf, netdev; +Cc: Ilya Leoshkevich
Use PT_REGS_RC(ctx) instead of ctx->rax, which is not present on s390.
Pass -D__TARGET_ARCH_$(ARCH) to selftests in order to choose a proper
PT_REGS_RC variant.
Fix s930 -> s390 typo.
On s390, provide the forward declaration of struct pt_regs and cast it
to user_pt_regs in PT_REGS_* macros. This is necessary, because instead
of the full struct pt_regs, s390 exposes only its first field
user_pt_regs to userspace, and bpf_helpers.h is used with both userspace
(in selftests) and kernel (in samples) headers.
On x86, provide userspace versions of PT_REGS_* macros. Unlike s390, x86
provides struct pt_regs to both userspace and kernel, however, with
different field names.
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
---
tools/testing/selftests/bpf/Makefile | 4 +-
tools/testing/selftests/bpf/bpf_helpers.h | 46 +++++++++++++++--------
tools/testing/selftests/bpf/progs/loop1.c | 2 +-
tools/testing/selftests/bpf/progs/loop2.c | 2 +-
tools/testing/selftests/bpf/progs/loop3.c | 2 +-
5 files changed, 37 insertions(+), 19 deletions(-)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index d60fee59fbd1..599b320bef65 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
include ../../../../scripts/Kbuild.include
+include ../../../scripts/Makefile.arch
LIBDIR := ../../../lib
BPFDIR := $(LIBDIR)/bpf
@@ -138,7 +139,8 @@ CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
$(CLANG_SYS_INCLUDES) \
- -Wno-compare-distinct-pointer-types
+ -Wno-compare-distinct-pointer-types \
+ -D__TARGET_ARCH_$(ARCH)
$(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
$(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 1a5b1accf091..faf86d83301a 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -312,8 +312,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
#if defined(__TARGET_ARCH_x86)
#define bpf_target_x86
#define bpf_target_defined
-#elif defined(__TARGET_ARCH_s930x)
- #define bpf_target_s930x
+#elif defined(__TARGET_ARCH_s390)
+ #define bpf_target_s390
#define bpf_target_defined
#elif defined(__TARGET_ARCH_arm)
#define bpf_target_arm
@@ -338,8 +338,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
#ifndef bpf_target_defined
#if defined(__x86_64__)
#define bpf_target_x86
-#elif defined(__s390x__)
- #define bpf_target_s930x
+#elif defined(__s390__)
+ #define bpf_target_s390
#elif defined(__arm__)
#define bpf_target_arm
#elif defined(__aarch64__)
@@ -355,6 +355,7 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
#if defined(bpf_target_x86)
+#ifdef __KERNEL__
#define PT_REGS_PARM1(x) ((x)->di)
#define PT_REGS_PARM2(x) ((x)->si)
#define PT_REGS_PARM3(x) ((x)->dx)
@@ -365,19 +366,34 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
#define PT_REGS_RC(x) ((x)->ax)
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->ip)
+#else
+#define PT_REGS_PARM1(x) ((x)->rdi)
+#define PT_REGS_PARM2(x) ((x)->rsi)
+#define PT_REGS_PARM3(x) ((x)->rdx)
+#define PT_REGS_PARM4(x) ((x)->rcx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->rsp)
+#define PT_REGS_FP(x) ((x)->rbp)
+#define PT_REGS_RC(x) ((x)->rax)
+#define PT_REGS_SP(x) ((x)->rsp)
+#define PT_REGS_IP(x) ((x)->rip)
+#endif
-#elif defined(bpf_target_s390x)
+#elif defined(bpf_target_s390)
-#define PT_REGS_PARM1(x) ((x)->gprs[2])
-#define PT_REGS_PARM2(x) ((x)->gprs[3])
-#define PT_REGS_PARM3(x) ((x)->gprs[4])
-#define PT_REGS_PARM4(x) ((x)->gprs[5])
-#define PT_REGS_PARM5(x) ((x)->gprs[6])
-#define PT_REGS_RET(x) ((x)->gprs[14])
-#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->gprs[2])
-#define PT_REGS_SP(x) ((x)->gprs[15])
-#define PT_REGS_IP(x) ((x)->psw.addr)
+/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_PARM1(x) (((const volatile user_pt_regs *)(x))->gprs[2])
+#define PT_REGS_PARM2(x) (((const volatile user_pt_regs *)(x))->gprs[3])
+#define PT_REGS_PARM3(x) (((const volatile user_pt_regs *)(x))->gprs[4])
+#define PT_REGS_PARM4(x) (((const volatile user_pt_regs *)(x))->gprs[5])
+#define PT_REGS_PARM5(x) (((const volatile user_pt_regs *)(x))->gprs[6])
+#define PT_REGS_RET(x) (((const volatile user_pt_regs *)(x))->gprs[14])
+/* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_FP(x) (((const volatile user_pt_regs *)(x))->gprs[11])
+#define PT_REGS_RC(x) (((const volatile user_pt_regs *)(x))->gprs[2])
+#define PT_REGS_SP(x) (((const volatile user_pt_regs *)(x))->gprs[15])
+#define PT_REGS_IP(x) (((const volatile user_pt_regs *)(x))->psw.addr)
#elif defined(bpf_target_arm)
diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c
index dea395af9ea9..7cdb7f878310 100644
--- a/tools/testing/selftests/bpf/progs/loop1.c
+++ b/tools/testing/selftests/bpf/progs/loop1.c
@@ -18,7 +18,7 @@ int nested_loops(volatile struct pt_regs* ctx)
for (j = 0; j < 300; j++)
for (i = 0; i < j; i++) {
if (j & 1)
- m = ctx->rax;
+ m = PT_REGS_RC(ctx);
else
m = j;
sum += i * m;
diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c
index 0637bd8e8bcf..9b2f808a2863 100644
--- a/tools/testing/selftests/bpf/progs/loop2.c
+++ b/tools/testing/selftests/bpf/progs/loop2.c
@@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx)
int i = 0;
while (true) {
- if (ctx->rax & 1)
+ if (PT_REGS_RC(ctx) & 1)
i += 3;
else
i += 7;
diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c
index 30a0f6cba080..d727657d51e2 100644
--- a/tools/testing/selftests/bpf/progs/loop3.c
+++ b/tools/testing/selftests/bpf/progs/loop3.c
@@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx)
__u64 i = 0, sum = 0;
do {
i++;
- sum += ctx->rax;
+ sum += PT_REGS_RC(ctx);
} while (i < 0x100000000ULL);
return sum;
}
--
2.21.0
^ permalink raw reply related
* Re: [PATCH] bpf, libbpf: Smatch: Fix potential NULL pointer dereference
From: Yonghong Song @ 2019-07-02 15:34 UTC (permalink / raw)
To: Leo Yan, Alexei Starovoitov, Daniel Borkmann, Martin Lau,
Song Liu, netdev@vger.kernel.org, bpf@vger.kernel.org,
linux-kernel@vger.kernel.org, Dan Carpenter
In-Reply-To: <20190702102531.23512-1-leo.yan@linaro.org>
On 7/2/19 3:25 AM, Leo Yan wrote:
> Based on the following report from Smatch, fix the potential
> NULL pointer dereference check.
>
> tools/lib/bpf/libbpf.c:3493
> bpf_prog_load_xattr() warn: variable dereferenced before check 'attr'
> (see line 3483)
>
> 3479 int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
> 3480 struct bpf_object **pobj, int *prog_fd)
> 3481 {
> 3482 struct bpf_object_open_attr open_attr = {
> 3483 .file = attr->file,
> 3484 .prog_type = attr->prog_type,
> ^^^^^^
> 3485 };
>
> At the head of function, it directly access 'attr' without checking if
> it's NULL pointer. This patch moves the values assignment after
> validating 'attr' and 'attr->file'.
>
> Signed-off-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Yonghong Song <yhs@fb.com>
^ permalink raw reply
* Re: [PATCH] User mode linux bump maximum MTU tuntap interface [RESAND]
From: Anton Ivanov @ 2019-07-02 14:47 UTC (permalink / raw)
To: Richard Weinberger,
Алексей
Cc: netdev, linux-um
In-Reply-To: <CAFLxGvytDC1TFdT0m9vvijz_93B8TziWURcR-3mskWB-7TzFag@mail.gmail.com>
On 02/07/2019 15:40, Richard Weinberger wrote:
> CC'ing um folks.
>
> On Tue, Jul 2, 2019 at 3:01 PM Алексей <ne-vlezay80@yandex.ru> wrote:
>>
>> Hello, the parameter ETH_MAX_PACKET limited to 1500 bytes is the not
>> support jumbo frames.
>>
>> This patch change ETH_MAX_PACKET the 65535 bytes to jumbo frame support
>> with user mode linux tuntap driver.
>>
>>
>> PATCH:
>>
>> -------------------
>>
>>
>> diff -ruNP ../linux_orig/linux-5.1/arch/um/include/shared/net_user.h
>> ./arch/um/include/shared/net_user.h
>> --- a/arch/um/include/shared/net_user.h 2019-05-06 00:42:58.000000000
>> +0000
>> +++ b/arch/um/include/shared/net_user.h 2019-07-02 07:14:13.593333356
>> +0000
>> @@ -9,7 +9,7 @@
>> #define ETH_ADDR_LEN (6)
>> #define ETH_HEADER_ETHERTAP (16)
>> #define ETH_HEADER_OTHER (26) /* 14 for ethernet + VLAN + MPLS for
>> crazy people */
>> -#define ETH_MAX_PACKET (1500)
>> +#define ETH_MAX_PACKET (65535)
>>
>> #define UML_NET_VERSION (4)
>>
>> -------------------
>>
>>
>
>
The vector version for tap already allows mtu > 1500. It does not have a
check to limit it to 65535 max though and it should.
I will add this one to the queue of stuff for the network drivers. IMHO
we should start migrating some of the older ones to vector IO.
--
Anton R. Ivanov
https://www.kot-begemot.co.uk/
^ permalink raw reply
* !!!Klientskie bazy. Email: prodawez@armyspy.com Uznajte podrobnee.
From: netdev @ 2019-07-02 3:23 UTC (permalink / raw)
To: netdev
!!!Klientskie bazy. Email: prodawez@armyspy.com Uznajte podrobnee.
^ permalink raw reply
* [PATCH net 6/6] gtp: add missing gtp_encap_disable_sock() in gtp_encap_enable()
From: Taehee Yoo @ 2019-07-02 15:24 UTC (permalink / raw)
To: davem, pablo, laforge, osmocom-net-gprs, netdev; +Cc: ap420073
If an invalid role is sent from user space, gtp_encap_enable() will fail.
Then, it should call gtp_encap_disable_sock() but current code doesn't.
It makes memory leak.
Fixes: 91ed81f9abc7 ("gtp: support SGSN-side tunnels")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
---
drivers/net/gtp.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index b3ccac54e204..ecfe26215935 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -857,8 +857,13 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[])
if (data[IFLA_GTP_ROLE]) {
role = nla_get_u32(data[IFLA_GTP_ROLE]);
- if (role > GTP_ROLE_SGSN)
+ if (role > GTP_ROLE_SGSN) {
+ if (sk0)
+ gtp_encap_disable_sock(sk0);
+ if (sk1u)
+ gtp_encap_disable_sock(sk1u);
return -EINVAL;
+ }
}
gtp->sk0 = sk0;
--
2.17.1
^ permalink raw reply related
* [PATCH net 5/6] gtp: fix use-after-free in gtp_newlink()
From: Taehee Yoo @ 2019-07-02 15:23 UTC (permalink / raw)
To: davem, pablo, laforge, osmocom-net-gprs, netdev; +Cc: ap420073
Current gtp_newlink() could be called after unregister_pernet_subsys().
gtp_newlink() uses gtp_net but it can be destroyed by
unregister_pernet_subsys().
So unregister_pernet_subsys() should be called after
rtnl_link_unregister().
Test commands:
#SHELL 1
while :
do
for i in {1..5}
do
./gtp-link add gtp$i &
done
killall gtp-link
done
#SHELL 2
while :
do
modprobe -rv gtp
done
Splat looks like:
[ 753.176631] BUG: KASAN: use-after-free in gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.177722] Read of size 8 at addr ffff8880d48f2458 by task gtp-link/7126
[ 753.179082] CPU: 0 PID: 7126 Comm: gtp-link Tainted: G W 5.2.0-rc6+ #50
[ 753.185801] Call Trace:
[ 753.186264] dump_stack+0x7c/0xbb
[ 753.186863] ? gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.187583] print_address_description+0xc7/0x240
[ 753.188382] ? gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.189097] ? gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.189846] __kasan_report+0x12a/0x16f
[ 753.190542] ? gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.191298] kasan_report+0xe/0x20
[ 753.191893] gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.192580] ? __netlink_ns_capable+0xc3/0xf0
[ 753.193370] __rtnl_newlink+0xb9f/0x11b0
[ ... ]
[ 753.241201] Allocated by task 7186:
[ 753.241844] save_stack+0x19/0x80
[ 753.242399] __kasan_kmalloc.constprop.3+0xa0/0xd0
[ 753.243192] __kmalloc+0x13e/0x300
[ 753.243764] ops_init+0xd6/0x350
[ 753.244314] register_pernet_operations+0x249/0x6f0
[ ... ]
[ 753.251770] Freed by task 7178:
[ 753.252288] save_stack+0x19/0x80
[ 753.252833] __kasan_slab_free+0x111/0x150
[ 753.253962] kfree+0xc7/0x280
[ 753.254509] ops_free_list.part.11+0x1c4/0x2d0
[ 753.255241] unregister_pernet_operations+0x262/0x390
[ ... ]
[ 753.285883] list_add corruption. next->prev should be prev (ffff8880d48f2458), but was ffff8880d497d878. (next.
[ 753.287241] ------------[ cut here ]------------
[ 753.287794] kernel BUG at lib/list_debug.c:25!
[ 753.288364] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 753.289099] CPU: 0 PID: 7126 Comm: gtp-link Tainted: G B W 5.2.0-rc6+ #50
[ 753.291036] RIP: 0010:__list_add_valid+0x74/0xd0
[ 753.291589] Code: 48 39 da 75 27 48 39 f5 74 36 48 39 dd 74 31 48 83 c4 08 b8 01 00 00 00 5b 5d c3 48 89 d9 48b
[ 753.293779] RSP: 0018:ffff8880cae8f398 EFLAGS: 00010286
[ 753.294401] RAX: 0000000000000075 RBX: ffff8880d497d878 RCX: 0000000000000000
[ 753.296260] RDX: 0000000000000075 RSI: 0000000000000008 RDI: ffffed10195d1e69
[ 753.297070] RBP: ffff8880cd250ae0 R08: ffffed101b4bff21 R09: ffffed101b4bff21
[ 753.297899] R10: 0000000000000001 R11: ffffed101b4bff20 R12: ffff8880d497d878
[ 753.298703] R13: 0000000000000000 R14: ffff8880cd250ae0 R15: ffff8880d48f2458
[ 753.299564] FS: 00007f5f79805740(0000) GS:ffff8880da400000(0000) knlGS:0000000000000000
[ 753.300533] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 753.301231] CR2: 00007fe8c7ef4f10 CR3: 00000000b71a6006 CR4: 00000000000606f0
[ 753.302183] Call Trace:
[ 753.302530] gtp_newlink+0x5f6/0xa5c [gtp]
[ 753.303037] ? __netlink_ns_capable+0xc3/0xf0
[ 753.303576] __rtnl_newlink+0xb9f/0x11b0
[ 753.304092] ? rtnl_link_unregister+0x230/0x230
Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
---
drivers/net/gtp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 52f35cbeb1dc..b3ccac54e204 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1376,9 +1376,9 @@ late_initcall(gtp_init);
static void __exit gtp_fini(void)
{
- unregister_pernet_subsys(>p_net_ops);
genl_unregister_family(>p_genl_family);
rtnl_link_unregister(>p_link_ops);
+ unregister_pernet_subsys(>p_net_ops);
pr_info("GTP module unloaded\n");
}
--
2.17.1
^ permalink raw reply related
* [PATCH net 4/6] gtp: fix Illegal context switch in RCU read-side critical section.
From: Taehee Yoo @ 2019-07-02 15:23 UTC (permalink / raw)
To: davem, pablo, laforge, osmocom-net-gprs, netdev; +Cc: ap420073
ipv4_pdp_add() is called in RCU read-side critical section.
So GFP_KERNEL should not be used in the function.
This patch make ipv4_pdp_add() to use GFP_ATOMIC instead of GFP_KERNEL.
Test commands:
gtp-link add gtp1 &
gtp-tunnel add gtp1 v1 100 200 1.1.1.1 2.2.2.2
Splat looks like:
[ 130.618881] =============================
[ 130.626382] WARNING: suspicious RCU usage
[ 130.626994] 5.2.0-rc6+ #50 Not tainted
[ 130.627622] -----------------------------
[ 130.628223] ./include/linux/rcupdate.h:266 Illegal context switch in RCU read-side critical section!
[ 130.629684]
[ 130.629684] other info that might help us debug this:
[ 130.629684]
[ 130.631022]
[ 130.631022] rcu_scheduler_active = 2, debug_locks = 1
[ 130.632136] 4 locks held by gtp-tunnel/1025:
[ 130.632925] #0: 000000002b93c8b7 (cb_lock){++++}, at: genl_rcv+0x15/0x40
[ 130.634159] #1: 00000000f17bc999 (genl_mutex){+.+.}, at: genl_rcv_msg+0xfb/0x130
[ 130.635487] #2: 00000000c644ed8e (rtnl_mutex){+.+.}, at: gtp_genl_new_pdp+0x18c/0x1150 [gtp]
[ 130.636936] #3: 0000000007a1cde7 (rcu_read_lock){....}, at: gtp_genl_new_pdp+0x187/0x1150 [gtp]
[ 130.638348]
[ 130.638348] stack backtrace:
[ 130.639062] CPU: 1 PID: 1025 Comm: gtp-tunnel Not tainted 5.2.0-rc6+ #50
[ 130.641318] Call Trace:
[ 130.641707] dump_stack+0x7c/0xbb
[ 130.642252] ___might_sleep+0x2c0/0x3b0
[ 130.642862] kmem_cache_alloc_trace+0x1cd/0x2b0
[ 130.643591] gtp_genl_new_pdp+0x6c5/0x1150 [gtp]
[ 130.644371] genl_family_rcv_msg+0x63a/0x1030
[ 130.645074] ? mutex_lock_io_nested+0x1090/0x1090
[ 130.645845] ? genl_unregister_family+0x630/0x630
[ 130.646592] ? debug_show_all_locks+0x2d0/0x2d0
[ 130.647293] ? check_flags.part.40+0x440/0x440
[ 130.648099] genl_rcv_msg+0xa3/0x130
[ ... ]
Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
---
drivers/net/gtp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 92ef777a757f..52f35cbeb1dc 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -959,7 +959,7 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
}
- pctx = kmalloc(sizeof(struct pdp_ctx), GFP_KERNEL);
+ pctx = kmalloc(sizeof(*pctx), GFP_ATOMIC);
if (pctx == NULL)
return -ENOMEM;
--
2.17.1
^ permalink raw reply related
* [PATCH net 3/6] gtp: remove duplicate code in gtp_dellink()
From: Taehee Yoo @ 2019-07-02 15:22 UTC (permalink / raw)
To: davem, pablo, laforge, osmocom-net-gprs, netdev; +Cc: ap420073
gtp_encap_disable() in gtp_dellink() is unnecessary because it will be
called by unregister_netdevice().
unregister_netdevice() internally calls gtp_dev_uninit() by ->ndo_uninit().
And gtp_dev_uninit() calls gtp_encap_disable().
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
---
drivers/net/gtp.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 5101f8c3c99c..92ef777a757f 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -694,7 +694,6 @@ static void gtp_dellink(struct net_device *dev, struct list_head *head)
{
struct gtp_dev *gtp = netdev_priv(dev);
- gtp_encap_disable(gtp);
gtp_hashtable_free(gtp);
list_del_rcu(>p->list);
unregister_netdevice_queue(dev, head);
--
2.17.1
^ permalink raw reply related
* [PATCH net 2/6] gtp: fix use-after-free in gtp_encap_destroy()
From: Taehee Yoo @ 2019-07-02 15:22 UTC (permalink / raw)
To: davem, pablo, laforge, osmocom-net-gprs, netdev; +Cc: ap420073
gtp_encap_destroy() is called twice.
1. When interface is deleted.
2. When udp socket is destroyed.
either gtp->sk0 or gtp->sk1u could be freed by sock_put() in
gtp_encap_destroy(). so, when gtp_encap_destroy() is called again,
it would uses freed sk pointer.
patch makes gtp_encap_destroy() to set either gtp->sk0 or gtp->sk1u to
null. in addition, both gtp->sk0 and gtp->sk1u pointer are protected
by rtnl_lock. so, rtnl_lock() is added.
Test command:
gtp-link add gtp1 &
killall gtp-link
ip link del gtp1
Splat looks like:
[ 83.182767] BUG: KASAN: use-after-free in __lock_acquire+0x3a20/0x46a0
[ 83.184128] Read of size 8 at addr ffff8880cc7d5360 by task ip/1008
[ 83.185567] CPU: 1 PID: 1008 Comm: ip Not tainted 5.2.0-rc6+ #50
[ 83.188469] Call Trace:
[ ... ]
[ 83.200126] lock_acquire+0x141/0x380
[ 83.200575] ? lock_sock_nested+0x3a/0xf0
[ 83.201069] _raw_spin_lock_bh+0x38/0x70
[ 83.201551] ? lock_sock_nested+0x3a/0xf0
[ 83.202044] lock_sock_nested+0x3a/0xf0
[ 83.202520] gtp_encap_destroy+0x18/0xe0 [gtp]
[ 83.203065] gtp_encap_disable.isra.14+0x13/0x50 [gtp]
[ 83.203687] gtp_dellink+0x56/0x170 [gtp]
[ 83.204190] rtnl_delete_link+0xb4/0x100
[ ... ]
[ 83.236513] Allocated by task 976:
[ 83.236925] save_stack+0x19/0x80
[ 83.237332] __kasan_kmalloc.constprop.3+0xa0/0xd0
[ 83.237894] kmem_cache_alloc+0xd8/0x280
[ 83.238360] sk_prot_alloc.isra.42+0x50/0x200
[ 83.238874] sk_alloc+0x32/0x940
[ 83.239264] inet_create+0x283/0xc20
[ 83.239684] __sock_create+0x2dd/0x540
[ 83.240136] __sys_socket+0xca/0x1a0
[ 83.240550] __x64_sys_socket+0x6f/0xb0
[ 83.240998] do_syscall_64+0x9c/0x450
[ 83.241466] entry_SYSCALL_64_after_hwframe+0x49/0xbe
[ 83.242061]
[ 83.242249] Freed by task 0:
[ 83.242616] save_stack+0x19/0x80
[ 83.243013] __kasan_slab_free+0x111/0x150
[ 83.243498] kmem_cache_free+0x89/0x250
[ 83.244444] __sk_destruct+0x38f/0x5a0
[ 83.245366] rcu_core+0x7e9/0x1c20
[ 83.245766] __do_softirq+0x213/0x8fa
Fixes: 1e3a3abd8b28 ("gtp: make GTP sockets in gtp_newlink optional")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
---
drivers/net/gtp.c | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 939da5442f65..5101f8c3c99c 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -285,13 +285,17 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
return gtp_rx(pctx, skb, hdrlen, gtp->role);
}
-static void gtp_encap_destroy(struct sock *sk)
+static void __gtp_encap_destroy(struct sock *sk)
{
struct gtp_dev *gtp;
lock_sock(sk);
gtp = sk->sk_user_data;
if (gtp) {
+ if (gtp->sk0 == sk)
+ gtp->sk0 = NULL;
+ else
+ gtp->sk1u = NULL;
udp_sk(sk)->encap_type = 0;
rcu_assign_sk_user_data(sk, NULL);
sock_put(sk);
@@ -299,12 +303,19 @@ static void gtp_encap_destroy(struct sock *sk)
release_sock(sk);
}
+static void gtp_encap_destroy(struct sock *sk)
+{
+ rtnl_lock();
+ __gtp_encap_destroy(sk);
+ rtnl_unlock();
+}
+
static void gtp_encap_disable_sock(struct sock *sk)
{
if (!sk)
return;
- gtp_encap_destroy(sk);
+ __gtp_encap_destroy(sk);
}
static void gtp_encap_disable(struct gtp_dev *gtp)
@@ -1038,6 +1049,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
}
+ rtnl_lock();
rcu_read_lock();
gtp = gtp_find_dev(sock_net(skb->sk), info->attrs);
@@ -1062,6 +1074,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
out_unlock:
rcu_read_unlock();
+ rtnl_unlock();
return err;
}
--
2.17.1
^ permalink raw reply related
* Re: [PATCH] net: core: page_pool: add user refcnt and reintroduce page_pool_destroy
From: Ivan Khoronzhuk @ 2019-07-02 15:21 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: netdev, Ilias Apalodimas, grygorii.strashko, jakub.kicinski,
daniel, john.fastabend, ast, linux-kernel, linux-omap
In-Reply-To: <20190702171029.76c60538@carbon>
On Tue, Jul 02, 2019 at 05:10:29PM +0200, Jesper Dangaard Brouer wrote:
>On Tue, 2 Jul 2019 17:56:13 +0300
>Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:
>
>> On Tue, Jul 02, 2019 at 04:52:30PM +0200, Jesper Dangaard Brouer wrote:
>> >On Tue, 2 Jul 2019 17:44:27 +0300
>> >Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:
>> >
>> >> On Tue, Jul 02, 2019 at 04:31:39PM +0200, Jesper Dangaard Brouer wrote:
>> >> >From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
>> >> >
>> >> >Jesper recently removed page_pool_destroy() (from driver invocation) and
>> >> >moved shutdown and free of page_pool into xdp_rxq_info_unreg(), in-order to
>> >> >handle in-flight packets/pages. This created an asymmetry in drivers
>> >> >create/destroy pairs.
>> >> >
>> >> >This patch add page_pool user refcnt and reintroduce page_pool_destroy.
>> >> >This serves two purposes, (1) simplify drivers error handling as driver now
>> >> >drivers always calls page_pool_destroy() and don't need to track if
>> >> >xdp_rxq_info_reg_mem_model() was unsuccessful. (2) allow special cases
>> >> >where a single RX-queue (with a single page_pool) provides packets for two
>> >> >net_device'es, and thus needs to register the same page_pool twice with two
>> >> >xdp_rxq_info structures.
>> >>
>> >> As I tend to use xdp level patch there is no more reason to mention (2) case
>> >> here. XDP patch serves it better and can prevent not only obj deletion but also
>> >> pool flush, so, this one patch I could better leave only for (1) case.
>> >
>> >I don't understand what you are saying.
>> >
>> >Do you approve this patch, or do you reject this patch?
>> >
>> It's not reject, it's proposition to use both, XDP and page pool patches,
>> each having its goal.
>
>Just to be clear, if you want this patch to get accepted you have to
>reply with your Signed-off-by (as I wrote).
>
>Maybe we should discuss it in another thread, about why you want two
>solutions to the same problem.
If it solves same problem I propose to reject this one and use this:
https://lkml.org/lkml/2019/7/2/651
--
Regards,
Ivan Khoronzhuk
^ permalink raw reply
* [PATCH net-next 1/1] devlink: Add APIs to publish/unpublish the port parameters.
From: Sudarsana Reddy Kalluru @ 2019-07-02 15:20 UTC (permalink / raw)
To: davem; +Cc: netdev, mkalderon, aelior, jiri
The patch adds devlink interfaces for drivers to publish/unpublish the
devlink port parameters.
Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
---
include/net/devlink.h | 2 ++
net/core/devlink.c | 42 ++++++++++++++++++++++++++++++++++++++++++
2 files changed, 44 insertions(+)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 6c51e86..2e2d7fc 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -651,6 +651,8 @@ int devlink_port_params_register(struct devlink_port *devlink_port,
void devlink_port_params_unregister(struct devlink_port *devlink_port,
const struct devlink_param *params,
size_t params_count);
+void devlink_port_params_publish(struct devlink_port *devlink_port);
+void devlink_port_params_unpublish(struct devlink_port *ddevlink_port);
int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
union devlink_param_value *init_val);
int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 4baf716..c06c23f 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -6378,6 +6378,48 @@ void devlink_port_params_unregister(struct devlink_port *devlink_port,
}
EXPORT_SYMBOL_GPL(devlink_port_params_unregister);
+/**
+ * devlink_port_params_publish - publish port configuration parameters
+ *
+ * @devlink_port: devlink port
+ *
+ * Publish previously registered port configuration parameters.
+ */
+void devlink_port_params_publish(struct devlink_port *devlink_port)
+{
+ struct devlink_param_item *param_item;
+
+ list_for_each_entry(param_item, &devlink_port->param_list, list) {
+ if (param_item->published)
+ continue;
+ param_item->published = true;
+ devlink_param_notify(devlink_port->devlink, devlink_port->index,
+ param_item, DEVLINK_CMD_PORT_PARAM_NEW);
+ }
+}
+EXPORT_SYMBOL_GPL(devlink_port_params_publish);
+
+/**
+ * devlink_port_params_unpublish - unpublish port configuration parameters
+ *
+ * @devlink_port: devlink port
+ *
+ * Unpublish previously registered port configuration parameters.
+ */
+void devlink_port_params_unpublish(struct devlink_port *devlink_port)
+{
+ struct devlink_param_item *param_item;
+
+ list_for_each_entry(param_item, &devlink_port->param_list, list) {
+ if (!param_item->published)
+ continue;
+ param_item->published = false;
+ devlink_param_notify(devlink_port->devlink, devlink_port->index,
+ param_item, DEVLINK_CMD_PORT_PARAM_DEL);
+ }
+}
+EXPORT_SYMBOL_GPL(devlink_port_params_unpublish);
+
static int
__devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id,
union devlink_param_value *init_val)
--
1.8.3.1
^ 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