* [PATCH v2 iproute2 2/2] tc: Add support for the ETF Qdisc
From: Jesus Sanchez-Palencia @ 2018-07-03 22:52 UTC (permalink / raw)
To: netdev
Cc: jhs, kurt.kanzenbach, xiyou.wangcong, jiri, vinicius.gomes,
Jesus Sanchez-Palencia
In-Reply-To: <20180703225219.25526-1-jesus.sanchez-palencia@intel.com>
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
The "Earliest TxTime First" (ETF) queueing discipline allows precise
control of the transmission time of packets by providing a sorted
time-based scheduling of packets.
The syntax is:
tc qdisc add dev DEV parent NODE etf delta <DELTA>
clockid <CLOCKID> [offload] [deadline_mode]
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
tc/Makefile | 1 +
tc/q_etf.c | 168 ++++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 169 insertions(+)
create mode 100644 tc/q_etf.c
diff --git a/tc/Makefile b/tc/Makefile
index dfd00267..4525c0fb 100644
--- a/tc/Makefile
+++ b/tc/Makefile
@@ -71,6 +71,7 @@ TCMODULES += q_clsact.o
TCMODULES += e_bpf.o
TCMODULES += f_matchall.o
TCMODULES += q_cbs.o
+TCMODULES += q_etf.o
TCSO :=
ifeq ($(TC_CONFIG_ATM),y)
diff --git a/tc/q_etf.c b/tc/q_etf.c
new file mode 100644
index 00000000..5db1dd6f
--- /dev/null
+++ b/tc/q_etf.c
@@ -0,0 +1,168 @@
+/*
+ * q_etf.c Earliest TxTime First (ETF).
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com>
+ * Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+#define CLOCKID_INVALID (-1)
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... etf delta NANOS clockid CLOCKID [offload] [deadline_mode]\n");
+ fprintf(stderr, "CLOCKID must be a valid SYS-V id (i.e. CLOCK_TAI)\n");
+}
+
+static void explain1(const char *arg, const char *val)
+{
+ fprintf(stderr, "etf: illegal value for \"%s\": \"%s\"\n", arg, val);
+}
+
+static void explain_clockid(const char *val)
+{
+ fprintf(stderr, "etf: illegal value for \"clockid\": \"%s\".\n", val);
+ fprintf(stderr, "It must be a valid SYS-V id (i.e. CLOCK_TAI)");
+}
+
+static int get_clockid(__s32 *val, const char *arg)
+{
+ const struct static_clockid {
+ const char *name;
+ clockid_t clockid;
+ } clockids_sysv[] = {
+ { "CLOCK_REALTIME", CLOCK_REALTIME },
+ { "CLOCK_TAI", CLOCK_TAI },
+ { "CLOCK_BOOTTIME", CLOCK_BOOTTIME },
+ { "CLOCK_MONOTONIC", CLOCK_MONOTONIC },
+ { NULL }
+ };
+
+ const struct static_clockid *c;
+
+ for (c = clockids_sysv; c->name; c++) {
+ if (strncasecmp(c->name, arg, 25) == 0) {
+ *val = c->clockid;
+
+ return 0;
+ }
+ }
+
+ return -1;
+}
+
+
+static int etf_parse_opt(struct qdisc_util *qu, int argc,
+ char **argv, struct nlmsghdr *n, const char *dev)
+{
+ struct tc_etf_qopt opt = {
+ .clockid = CLOCKID_INVALID,
+ };
+ struct rtattr *tail;
+
+ while (argc > 0) {
+ if (matches(*argv, "offload") == 0) {
+ if (opt.flags & TC_ETF_OFFLOAD_ON) {
+ fprintf(stderr, "etf: duplicate \"offload\" specification\n");
+ return -1;
+ }
+
+ opt.flags |= TC_ETF_OFFLOAD_ON;
+ } else if (matches(*argv, "deadline_mode") == 0) {
+ if (opt.flags & TC_ETF_DEADLINE_MODE_ON) {
+ fprintf(stderr, "etf: duplicate \"deadline_mode\" specification\n");
+ return -1;
+ }
+
+ opt.flags |= TC_ETF_DEADLINE_MODE_ON;
+ } else if (matches(*argv, "delta") == 0) {
+ NEXT_ARG();
+ if (opt.delta) {
+ fprintf(stderr, "etf: duplicate \"delta\" specification\n");
+ return -1;
+ }
+ if (get_s32(&opt.delta, *argv, 0)) {
+ explain1("delta", *argv);
+ return -1;
+ }
+ } else if (matches(*argv, "clockid") == 0) {
+ NEXT_ARG();
+ if (opt.clockid != CLOCKID_INVALID) {
+ fprintf(stderr, "etf: duplicate \"clockid\" specification\n");
+ return -1;
+ }
+ if (get_clockid(&opt.clockid, *argv)) {
+ explain_clockid(*argv);
+ return -1;
+ }
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "etf: unknown parameter \"%s\"\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ addattr_l(n, 2024, TCA_ETF_PARMS, &opt, sizeof(opt));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int etf_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_ETF_MAX+1];
+ struct tc_etf_qopt *qopt;
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_ETF_MAX, opt);
+
+ if (tb[TCA_ETF_PARMS] == NULL)
+ return -1;
+
+ qopt = RTA_DATA(tb[TCA_ETF_PARMS]);
+ if (RTA_PAYLOAD(tb[TCA_ETF_PARMS]) < sizeof(*qopt))
+ return -1;
+
+ if (qopt->clockid == CLOCKID_INVALID)
+ print_string(PRINT_ANY, "clockid", "clockid %s ", "invalid");
+ else
+ print_uint(PRINT_ANY, "clockid", "clockid %d ", qopt->clockid);
+
+ print_uint(PRINT_ANY, "delta", "delta %d ", qopt->delta);
+ print_string(PRINT_ANY, "offload", "offload %s ",
+ (qopt->flags & TC_ETF_OFFLOAD_ON) ? "on" : "off");
+ print_string(PRINT_ANY, "deadline_mode", "deadline_mode %s",
+ (qopt->flags & TC_ETF_DEADLINE_MODE_ON) ? "on" : "off");
+
+ return 0;
+}
+
+struct qdisc_util etf_qdisc_util = {
+ .id = "etf",
+ .parse_qopt = etf_parse_opt,
+ .print_qopt = etf_print_opt,
+};
--
2.17.1
^ permalink raw reply related
* [PATCH v2 iproute2 1/2] uapi pkt_sched: Add etf info - DO NOT COMMIT
From: Jesus Sanchez-Palencia @ 2018-07-03 22:52 UTC (permalink / raw)
To: netdev
Cc: jhs, kurt.kanzenbach, xiyou.wangcong, jiri, vinicius.gomes,
Jesus Sanchez-Palencia
This should come from the next uapi headers update.
Sending it now just as a convenience so anyone can build tc with etf
and taprio support.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
include/uapi/linux/pkt_sched.h | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 37b5096a..94911846 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -539,6 +539,7 @@ enum {
TCA_NETEM_LATENCY64,
TCA_NETEM_JITTER64,
TCA_NETEM_SLOT,
+ TCA_NETEM_SLOT_DIST,
__TCA_NETEM_MAX,
};
@@ -581,6 +582,8 @@ struct tc_netem_slot {
__s64 max_delay;
__s32 max_packets;
__s32 max_bytes;
+ __s64 dist_delay; /* nsec */
+ __s64 dist_jitter; /* nsec */
};
enum {
@@ -934,4 +937,22 @@ enum {
#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
+/* ETF */
+struct tc_etf_qopt {
+ __s32 delta;
+ __s32 clockid;
+ __u32 flags;
+#define TC_ETF_DEADLINE_MODE_ON BIT(0)
+#define TC_ETF_OFFLOAD_ON BIT(1)
+};
+
+enum {
+ TCA_ETF_UNSPEC,
+ TCA_ETF_PARMS,
+ __TCA_ETF_MAX,
+};
+
+#define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
+
#endif
--
2.17.1
^ permalink raw reply related
* [PATCH v2 net-next 14/14] net/sched: Make etf report drops on error_queue
From: Jesus Sanchez-Palencia @ 2018-07-03 22:43 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
Use the socket error queue for reporting dropped packets if the
socket has enabled that feature through the SO_TXTIME API.
Packets are dropped either on enqueue() if they aren't accepted by the
qdisc or on dequeue() if the system misses their deadline. Those are
reported as different errors so applications can react accordingly.
Userspace can retrieve the errors through the socket error queue and the
corresponding cmsg interfaces. A struct sock_extended_err* is used for
returning the error data, and the packet's timestamp can be retrieved by
adding both ee_data and ee_info fields as e.g.:
((__u64) serr->ee_data << 32) + serr->ee_info
This feature is disabled by default and must be explicitly enabled by
applications. Enabling it can bring some overhead for the Tx cycles
of the application.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
include/net/sock.h | 3 ++-
include/uapi/linux/errqueue.h | 4 ++++
include/uapi/linux/net_tstamp.h | 5 ++++-
net/core/sock.c | 4 ++++
net/sched/sch_etf.c | 35 +++++++++++++++++++++++++++++++--
5 files changed, 47 insertions(+), 4 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index 68347b9821c6..e0eac9ef44b5 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -481,7 +481,8 @@ struct sock {
u8 sk_clockid;
u8 sk_txtime_deadline_mode : 1,
- sk_txtime_unused : 7;
+ sk_txtime_report_errors : 1,
+ sk_txtime_unused : 6;
struct socket *sk_socket;
void *sk_user_data;
diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h
index dc64cfaf13da..c0151200f7d1 100644
--- a/include/uapi/linux/errqueue.h
+++ b/include/uapi/linux/errqueue.h
@@ -20,12 +20,16 @@ struct sock_extended_err {
#define SO_EE_ORIGIN_ICMP6 3
#define SO_EE_ORIGIN_TXSTATUS 4
#define SO_EE_ORIGIN_ZEROCOPY 5
+#define SO_EE_ORIGIN_TXTIME 6
#define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS
#define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1))
#define SO_EE_CODE_ZEROCOPY_COPIED 1
+#define SO_EE_CODE_TXTIME_INVALID_PARAM 1
+#define SO_EE_CODE_TXTIME_MISSED 2
+
/**
* struct scm_timestamping - timestamps exposed through cmsg
*
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index c9a77c353b98..f8f4539f1135 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -147,8 +147,11 @@ struct scm_ts_pktinfo {
*/
enum txtime_flags {
SOF_TXTIME_DEADLINE_MODE = (1 << 0),
+ SOF_TXTIME_REPORT_ERRORS = (1 << 1),
- SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_DEADLINE_MODE)
+ SOF_TXTIME_FLAGS_LAST = SOF_TXTIME_REPORT_ERRORS,
+ SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_FLAGS_LAST - 1) |
+ SOF_TXTIME_FLAGS_LAST
};
struct sock_txtime {
diff --git a/net/core/sock.c b/net/core/sock.c
index fe64b839f1b2..03fdea5b0f57 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1087,6 +1087,8 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
sk->sk_clockid = sk_txtime.clockid;
sk->sk_txtime_deadline_mode =
!!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
+ sk->sk_txtime_report_errors =
+ !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS);
}
break;
@@ -1429,6 +1431,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.txtime.clockid = sk->sk_clockid;
v.txtime.flags |= sk->sk_txtime_deadline_mode ?
SOF_TXTIME_DEADLINE_MODE : 0;
+ v.txtime.flags |= sk->sk_txtime_report_errors ?
+ SOF_TXTIME_REPORT_ERRORS : 0;
break;
default:
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 932a136db568..1538d6fa8165 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
+#include <linux/errqueue.h>
#include <linux/rbtree.h>
#include <linux/skbuff.h>
#include <linux/posix-timers.h>
@@ -123,6 +124,32 @@ static void reset_watchdog(struct Qdisc *sch)
qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
}
+static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
+{
+ struct sock_exterr_skb *serr;
+ struct sk_buff *clone;
+ ktime_t txtime = skb->tstamp;
+
+ if (!skb->sk || !(skb->sk->sk_txtime_report_errors))
+ return;
+
+ clone = skb_clone(skb, GFP_ATOMIC);
+ if (!clone)
+ return;
+
+ serr = SKB_EXT_ERR(clone);
+ serr->ee.ee_errno = err;
+ serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME;
+ serr->ee.ee_type = 0;
+ serr->ee.ee_code = code;
+ serr->ee.ee_pad = 0;
+ serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
+ serr->ee.ee_info = txtime; /* low part of tstamp */
+
+ if (sock_queue_err_skb(skb->sk, clone))
+ kfree_skb(clone);
+}
+
static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
struct sk_buff **to_free)
{
@@ -130,8 +157,11 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
struct rb_node **p = &q->head.rb_node, *parent = NULL;
ktime_t txtime = nskb->tstamp;
- if (!is_packet_valid(sch, nskb))
+ if (!is_packet_valid(sch, nskb)) {
+ report_sock_error(nskb, EINVAL,
+ SO_EE_CODE_TXTIME_INVALID_PARAM);
return qdisc_drop(nskb, sch, to_free);
+ }
while (*p) {
struct sk_buff *skb;
@@ -174,6 +204,8 @@ static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
if (drop) {
struct sk_buff *to_free = NULL;
+ report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
+
qdisc_drop(skb, sch, &to_free);
kfree_skb_list(to_free);
qdisc_qstats_overlimit(sch);
@@ -199,7 +231,6 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
now = q->get_time();
/* Drop if packet has expired while in queue. */
- /* FIXME: Must return error on the socket's error queue */
if (ktime_before(skb->tstamp, now)) {
timesortedlist_erase(sch, skb, true);
skb = NULL;
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 13/14] igb: Add support for ETF offload
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
Implement HW offload support for SO_TXTIME through igb's Launchtime
feature. This is done by extending igb_setup_tc() so it supports
TC_SETUP_QDISC_ETF and configuring i210 so time based transmit
arbitration is enabled.
The FQTSS transmission mode added before is extended so strict
priority (SP) queues wait for stream reservation (SR) ones.
igb_config_tx_modes() is extended so it can support enabling/disabling
Launchtime following the previous approach used for the credit-based
shaper (CBS).
As the previous flow, FQTSS transmission mode is enabled automatically
by the driver once Launchtime (or CBS, as before) is enabled.
Similarly, it's automatically disabled when the feature is disabled
for the last queue that had it setup on.
The driver just consumes the transmit times from the skbuffs directly,
so no special handling is done in case an 'invalid' time is provided.
We assume this has been handled by the ETF qdisc already.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
.../net/ethernet/intel/igb/e1000_defines.h | 16 ++
drivers/net/ethernet/intel/igb/igb.h | 1 +
drivers/net/ethernet/intel/igb/igb_main.c | 138 +++++++++++++++---
3 files changed, 138 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 252440a418dc..8a28f3388f69 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -1048,6 +1048,22 @@
#define E1000_TQAVCTRL_XMIT_MODE BIT(0)
#define E1000_TQAVCTRL_DATAFETCHARB BIT(4)
#define E1000_TQAVCTRL_DATATRANARB BIT(8)
+#define E1000_TQAVCTRL_DATATRANTIM BIT(9)
+#define E1000_TQAVCTRL_SP_WAIT_SR BIT(10)
+/* Fetch Time Delta - bits 31:16
+ *
+ * This field holds the value to be reduced from the launch time for
+ * fetch time decision. The FetchTimeDelta value is defined in 32 ns
+ * granularity.
+ *
+ * This field is 16 bits wide, and so the maximum value is:
+ *
+ * 65535 * 32 = 2097120 ~= 2.1 msec
+ *
+ * XXX: We are configuring the max value here since we couldn't come up
+ * with a reason for not doing so.
+ */
+#define E1000_TQAVCTRL_FETCHTIME_DELTA (0xFFFF << 16)
/* TX Qav Credit Control fields */
#define E1000_TQAVCC_IDLESLOPE_MASK 0xFFFF
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 9643b5b3d444..ca54e268d157 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -262,6 +262,7 @@ struct igb_ring {
u16 count; /* number of desc. in the ring */
u8 queue_index; /* logical index of the ring*/
u8 reg_idx; /* physical index of the ring */
+ bool launchtime_enable; /* true if LaunchTime is enabled */
bool cbs_enable; /* indicates if CBS is enabled */
s32 idleslope; /* idleSlope in kbps */
s32 sendslope; /* sendSlope in kbps */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 445da8285d9b..e3a0c02721c9 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1666,13 +1666,26 @@ static bool is_any_cbs_enabled(struct igb_adapter *adapter)
return false;
}
+static bool is_any_txtime_enabled(struct igb_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ if (adapter->tx_ring[i]->launchtime_enable)
+ return true;
+ }
+
+ return false;
+}
+
/**
* igb_config_tx_modes - Configure "Qav Tx mode" features on igb
* @adapter: pointer to adapter struct
* @queue: queue number
*
- * Configure CBS for a given hardware queue. Parameters are retrieved
- * from the correct Tx ring, so igb_save_cbs_params() should be used
+ * Configure CBS and Launchtime for a given hardware queue.
+ * Parameters are retrieved from the correct Tx ring, so
+ * igb_save_cbs_params() and igb_save_txtime_params() should be used
* for setting those correctly prior to this function being called.
**/
static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
@@ -1686,6 +1699,19 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
WARN_ON(hw->mac.type != e1000_i210);
WARN_ON(queue < 0 || queue > 1);
+ /* If any of the Qav features is enabled, configure queues as SR and
+ * with HIGH PRIO. If none is, then configure them with LOW PRIO and
+ * as SP.
+ */
+ if (ring->cbs_enable || ring->launchtime_enable) {
+ set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
+ set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+ } else {
+ set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
+ set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
+ }
+
+ /* If CBS is enabled, set DataTranARB and config its parameters. */
if (ring->cbs_enable || queue == 0) {
/* i210 does not allow the queue 0 to be in the Strict
* Priority mode while the Qav mode is enabled, so,
@@ -1702,9 +1728,6 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
ring->hicredit = ETH_FRAME_LEN;
}
- set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
- set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
-
/* Always set data transfer arbitration to credit-based
* shaper algorithm on TQAVCTRL if CBS is enabled for any of
* the queues.
@@ -1780,8 +1803,6 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
wr32(E1000_I210_TQAVHC(queue),
0x80000000 + ring->hicredit * 0x7735);
} else {
- set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
- set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
/* Set idleSlope to zero. */
tqavcc = rd32(E1000_I210_TQAVCC(queue));
@@ -1802,17 +1823,61 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
}
}
+ /* If LaunchTime is enabled, set DataTranTIM. */
+ if (ring->launchtime_enable) {
+ /* Always set DataTranTIM on TQAVCTRL if LaunchTime is enabled
+ * for any of the SR queues, and configure fetchtime delta.
+ * XXX NOTE:
+ * - LaunchTime will be enabled for all SR queues.
+ * - A fixed offset can be added relative to the launch
+ * time of all packets if configured at reg LAUNCH_OS0.
+ * We are keeping it as 0 for now (default value).
+ */
+ tqavctrl = rd32(E1000_I210_TQAVCTRL);
+ tqavctrl |= E1000_TQAVCTRL_DATATRANTIM |
+ E1000_TQAVCTRL_FETCHTIME_DELTA;
+ wr32(E1000_I210_TQAVCTRL, tqavctrl);
+ } else {
+ /* If Launchtime is not enabled for any SR queues anymore,
+ * then clear DataTranTIM on TQAVCTRL and clear fetchtime delta,
+ * effectively disabling Launchtime.
+ */
+ if (!is_any_txtime_enabled(adapter)) {
+ tqavctrl = rd32(E1000_I210_TQAVCTRL);
+ tqavctrl &= ~E1000_TQAVCTRL_DATATRANTIM;
+ tqavctrl &= ~E1000_TQAVCTRL_FETCHTIME_DELTA;
+ wr32(E1000_I210_TQAVCTRL, tqavctrl);
+ }
+ }
+
/* XXX: In i210 controller the sendSlope and loCredit parameters from
* CBS are not configurable by software so we don't do any 'controller
* configuration' in respect to these parameters.
*/
- netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
- (ring->cbs_enable) ? "enabled" : "disabled", queue,
+ netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d \
+ idleslope %d sendslope %d hiCredit %d \
+ locredit %d\n",
+ (ring->cbs_enable) ? "enabled" : "disabled",
+ (ring->launchtime_enable) ? "enabled" : "disabled", queue,
ring->idleslope, ring->sendslope, ring->hicredit,
ring->locredit);
}
+static int igb_save_txtime_params(struct igb_adapter *adapter, int queue,
+ bool enable)
+{
+ struct igb_ring *ring;
+
+ if (queue < 0 || queue > adapter->num_tx_queues)
+ return -EINVAL;
+
+ ring = adapter->tx_ring[queue];
+ ring->launchtime_enable = enable;
+
+ return 0;
+}
+
static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
bool enable, int idleslope, int sendslope,
int hicredit, int locredit)
@@ -1856,10 +1921,11 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
int i, max_queue;
/* Configure TQAVCTRL register: set transmit mode to 'Qav',
- * set data fetch arbitration to 'round robin'.
+ * set data fetch arbitration to 'round robin', set SP_WAIT_SR
+ * so SP queues wait for SR ones.
*/
val = rd32(E1000_I210_TQAVCTRL);
- val |= E1000_TQAVCTRL_XMIT_MODE;
+ val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_SP_WAIT_SR;
val &= ~E1000_TQAVCTRL_DATAFETCHARB;
wr32(E1000_I210_TQAVCTRL, val);
@@ -2483,7 +2549,7 @@ static void igb_offload_apply(struct igb_adapter *adapter, s32 queue)
igb_config_tx_modes(adapter, queue);
- if (!is_any_cbs_enabled(adapter))
+ if (!is_any_cbs_enabled(adapter) && !is_any_txtime_enabled(adapter))
enable_fqtss(adapter, false);
}
@@ -2756,6 +2822,29 @@ static int igb_setup_tc_block(struct igb_adapter *adapter,
}
}
+static int igb_offload_txtime(struct igb_adapter *adapter,
+ struct tc_etf_qopt_offload *qopt)
+{
+ struct e1000_hw *hw = &adapter->hw;
+ int err;
+
+ /* Launchtime offloading is only supported by i210 controller. */
+ if (hw->mac.type != e1000_i210)
+ return -EOPNOTSUPP;
+
+ /* Launchtime offloading is only supported by queues 0 and 1. */
+ if (qopt->queue < 0 || qopt->queue > 1)
+ return -EINVAL;
+
+ err = igb_save_txtime_params(adapter, qopt->queue, qopt->enable);
+ if (err)
+ return err;
+
+ igb_offload_apply(adapter, qopt->queue);
+
+ return 0;
+}
+
static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
@@ -2766,6 +2855,8 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
return igb_offload_cbs(adapter, type_data);
case TC_SETUP_BLOCK:
return igb_setup_tc_block(adapter, type_data);
+ case TC_SETUP_QDISC_ETF:
+ return igb_offload_txtime(adapter, type_data);
default:
return -EOPNOTSUPP;
@@ -5586,11 +5677,14 @@ static void igb_set_itr(struct igb_q_vector *q_vector)
}
}
-static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
- u32 type_tucmd, u32 mss_l4len_idx)
+static void igb_tx_ctxtdesc(struct igb_ring *tx_ring,
+ struct igb_tx_buffer *first,
+ u32 vlan_macip_lens, u32 type_tucmd,
+ u32 mss_l4len_idx)
{
struct e1000_adv_tx_context_desc *context_desc;
u16 i = tx_ring->next_to_use;
+ struct timespec64 ts;
context_desc = IGB_TX_CTXTDESC(tx_ring, i);
@@ -5605,9 +5699,18 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
mss_l4len_idx |= tx_ring->reg_idx << 4;
context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens);
- context_desc->seqnum_seed = 0;
context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd);
context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);
+
+ /* We assume there is always a valid tx time available. Invalid times
+ * should have been handled by the upper layers.
+ */
+ if (tx_ring->launchtime_enable) {
+ ts = ns_to_timespec64(first->skb->tstamp);
+ context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
+ } else {
+ context_desc->seqnum_seed = 0;
+ }
}
static int igb_tso(struct igb_ring *tx_ring,
@@ -5690,7 +5793,8 @@ static int igb_tso(struct igb_ring *tx_ring,
vlan_macip_lens |= (ip.hdr - skb->data) << E1000_ADVTXD_MACLEN_SHIFT;
vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
- igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx);
+ igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens,
+ type_tucmd, mss_l4len_idx);
return 1;
}
@@ -5745,7 +5849,7 @@ static void igb_tx_csum(struct igb_ring *tx_ring, struct igb_tx_buffer *first)
vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT;
vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
- igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, 0);
+ igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, type_tucmd, 0);
}
#define IGB_SET_FLAG(_input, _flag, _result) \
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 12/14] igb: Only call skb_tx_timestamp after descriptors are ready
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
Currently, skb_tx_timestamp() is being called before the Tx
descriptors are prepared in igb_xmit_frame_ring(), which happens
during either the igb_tso() or igb_tx_csum() calls.
Given that now the skb->tstamp might be used to carry the timestamp
for SO_TXTIME, we must only call skb_tx_timestamp() after the
information has been copied into the Tx descriptors.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
drivers/net/ethernet/intel/igb/igb_main.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index c30ab7b260cc..445da8285d9b 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6033,8 +6033,6 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
}
}
- skb_tx_timestamp(skb);
-
if (skb_vlan_tag_present(skb)) {
tx_flags |= IGB_TX_FLAGS_VLAN;
tx_flags |= (skb_vlan_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
@@ -6050,6 +6048,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
else if (!tso)
igb_tx_csum(tx_ring, first);
+ skb_tx_timestamp(skb);
+
if (igb_tx_map(tx_ring, first, hdr_len))
goto cleanup_tx_tstamp;
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 11/14] igb: Refactor igb_offload_cbs()
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
Split code into a separate function (igb_offload_apply()) that will be
used by ETF offload implementation.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
drivers/net/ethernet/intel/igb/igb_main.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 8c90f1e51add..c30ab7b260cc 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2474,6 +2474,19 @@ igb_features_check(struct sk_buff *skb, struct net_device *dev,
return features;
}
+static void igb_offload_apply(struct igb_adapter *adapter, s32 queue)
+{
+ if (!is_fqtss_enabled(adapter)) {
+ enable_fqtss(adapter, true);
+ return;
+ }
+
+ igb_config_tx_modes(adapter, queue);
+
+ if (!is_any_cbs_enabled(adapter))
+ enable_fqtss(adapter, false);
+}
+
static int igb_offload_cbs(struct igb_adapter *adapter,
struct tc_cbs_qopt_offload *qopt)
{
@@ -2494,15 +2507,7 @@ static int igb_offload_cbs(struct igb_adapter *adapter,
if (err)
return err;
- if (is_fqtss_enabled(adapter)) {
- igb_config_tx_modes(adapter, qopt->queue);
-
- if (!is_any_cbs_enabled(adapter))
- enable_fqtss(adapter, false);
-
- } else {
- enable_fqtss(adapter, true);
- }
+ igb_offload_apply(adapter, qopt->queue);
return 0;
}
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 09/14] igb: Refactor igb_configure_cbs()
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
Make this function retrieve what it needs from the Tx ring being
addressed since it already relies on what had been saved on it before.
Also, since this function will be used by the upcoming Launchtime
patches rename it to better reflect its intention. Note that
Launchtime is not part of what 802.1Qav specifies, but the i210
datasheet refers to this set of functionality as "Qav Transmission
Mode".
Here we also perform a tiny refactor at is_any_cbs_enabled(), and add
further documentation to igb_setup_tx_mode().
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
drivers/net/ethernet/intel/igb/igb_main.c | 60 +++++++++++------------
1 file changed, 28 insertions(+), 32 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f1e3397bd405..15f6b9c57ccf 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1655,23 +1655,17 @@ static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode)
}
/**
- * igb_configure_cbs - Configure Credit-Based Shaper (CBS)
+ * igb_config_tx_modes - Configure "Qav Tx mode" features on igb
* @adapter: pointer to adapter struct
* @queue: queue number
- * @enable: true = enable CBS, false = disable CBS
- * @idleslope: idleSlope in kbps
- * @sendslope: sendSlope in kbps
- * @hicredit: hiCredit in bytes
- * @locredit: loCredit in bytes
*
- * Configure CBS for a given hardware queue. When disabling, idleslope,
- * sendslope, hicredit, locredit arguments are ignored. Returns 0 if
- * success. Negative otherwise.
+ * Configure CBS for a given hardware queue. Parameters are retrieved
+ * from the correct Tx ring, so igb_save_cbs_params() should be used
+ * for setting those correctly prior to this function being called.
**/
-static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
- bool enable, int idleslope, int sendslope,
- int hicredit, int locredit)
+static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
{
+ struct igb_ring *ring = adapter->tx_ring[queue];
struct net_device *netdev = adapter->netdev;
struct e1000_hw *hw = &adapter->hw;
u32 tqavcc;
@@ -1680,7 +1674,7 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
WARN_ON(hw->mac.type != e1000_i210);
WARN_ON(queue < 0 || queue > 1);
- if (enable || queue == 0) {
+ if (ring->cbs_enable || queue == 0) {
/* i210 does not allow the queue 0 to be in the Strict
* Priority mode while the Qav mode is enabled, so,
* instead of disabling strict priority mode, we give
@@ -1690,10 +1684,10 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
* Queue0 QueueMode must be set to 1b when
* TransmitMode is set to Qav."
*/
- if (queue == 0 && !enable) {
+ if (queue == 0 && !ring->cbs_enable) {
/* max "linkspeed" idleslope in kbps */
- idleslope = 1000000;
- hicredit = ETH_FRAME_LEN;
+ ring->idleslope = 1000000;
+ ring->hicredit = ETH_FRAME_LEN;
}
set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
@@ -1756,14 +1750,15 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
* calculated value, so the resulting bandwidth might
* be slightly higher for some configurations.
*/
- value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000);
+ value = DIV_ROUND_UP_ULL(ring->idleslope * 61034ULL, 1000000);
tqavcc = rd32(E1000_I210_TQAVCC(queue));
tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK;
tqavcc |= value;
wr32(E1000_I210_TQAVCC(queue), tqavcc);
- wr32(E1000_I210_TQAVHC(queue), 0x80000000 + hicredit * 0x7735);
+ wr32(E1000_I210_TQAVHC(queue),
+ 0x80000000 + ring->hicredit * 0x7735);
} else {
set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
@@ -1783,8 +1778,9 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
*/
netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
- (enable) ? "enabled" : "disabled", queue,
- idleslope, sendslope, hicredit, locredit);
+ (ring->cbs_enable) ? "enabled" : "disabled", queue,
+ ring->idleslope, ring->sendslope, ring->hicredit,
+ ring->locredit);
}
static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
@@ -1809,19 +1805,25 @@ static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
static bool is_any_cbs_enabled(struct igb_adapter *adapter)
{
- struct igb_ring *ring;
int i;
for (i = 0; i < adapter->num_tx_queues; i++) {
- ring = adapter->tx_ring[i];
-
- if (ring->cbs_enable)
+ if (adapter->tx_ring[i]->cbs_enable)
return true;
}
return false;
}
+/**
+ * igb_setup_tx_mode - Switch to/from Qav Tx mode when applicable
+ * @adapter: pointer to adapter struct
+ *
+ * Configure TQAVCTRL register switching the controller's Tx mode
+ * if FQTSS mode is enabled or disabled. Additionally, will issue
+ * a call to igb_config_tx_modes() per queue so any previously saved
+ * Tx parameters are applied.
+ **/
static void igb_setup_tx_mode(struct igb_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
@@ -1881,11 +1883,7 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
adapter->num_tx_queues : I210_SR_QUEUES_NUM;
for (i = 0; i < max_queue; i++) {
- struct igb_ring *ring = adapter->tx_ring[i];
-
- igb_configure_cbs(adapter, i, ring->cbs_enable,
- ring->idleslope, ring->sendslope,
- ring->hicredit, ring->locredit);
+ igb_config_tx_modes(adapter, i);
}
} else {
wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT);
@@ -2480,9 +2478,7 @@ static int igb_offload_cbs(struct igb_adapter *adapter,
return err;
if (is_fqtss_enabled(adapter)) {
- igb_configure_cbs(adapter, qopt->queue, qopt->enable,
- qopt->idleslope, qopt->sendslope,
- qopt->hicredit, qopt->locredit);
+ igb_config_tx_modes(adapter, qopt->queue);
if (!is_any_cbs_enabled(adapter))
enable_fqtss(adapter, false);
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 10/14] igb: Only change Tx arbitration when CBS is on
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
Currently the data transmission arbitration algorithm - DataTranARB
field on TQAVCTRL reg - is always set to CBS when the Tx mode is
changed from legacy to 'Qav' mode.
Make that configuration a bit more granular in preparation for the
upcoming Launchtime enabling patches, since CBS and Launchtime can be
enabled separately. That is achieved by moving the DataTranARB setup
to igb_config_tx_modes() instead.
Similarly, when disabling CBS we must check if it has been disabled
for all queues, and clear the DataTranARB accordingly.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
drivers/net/ethernet/intel/igb/igb_main.c | 49 +++++++++++++++--------
1 file changed, 33 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 15f6b9c57ccf..8c90f1e51add 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1654,6 +1654,18 @@ static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode)
wr32(E1000_I210_TQAVCC(queue), val);
}
+static bool is_any_cbs_enabled(struct igb_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ if (adapter->tx_ring[i]->cbs_enable)
+ return true;
+ }
+
+ return false;
+}
+
/**
* igb_config_tx_modes - Configure "Qav Tx mode" features on igb
* @adapter: pointer to adapter struct
@@ -1668,7 +1680,7 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
struct igb_ring *ring = adapter->tx_ring[queue];
struct net_device *netdev = adapter->netdev;
struct e1000_hw *hw = &adapter->hw;
- u32 tqavcc;
+ u32 tqavcc, tqavctrl;
u16 value;
WARN_ON(hw->mac.type != e1000_i210);
@@ -1693,6 +1705,14 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+ /* Always set data transfer arbitration to credit-based
+ * shaper algorithm on TQAVCTRL if CBS is enabled for any of
+ * the queues.
+ */
+ tqavctrl = rd32(E1000_I210_TQAVCTRL);
+ tqavctrl |= E1000_TQAVCTRL_DATATRANARB;
+ wr32(E1000_I210_TQAVCTRL, tqavctrl);
+
/* According to i210 datasheet section 7.2.7.7, we should set
* the 'idleSlope' field from TQAVCC register following the
* equation:
@@ -1770,6 +1790,16 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
/* Set hiCredit to zero. */
wr32(E1000_I210_TQAVHC(queue), 0);
+
+ /* If CBS is not enabled for any queues anymore, then return to
+ * the default state of Data Transmission Arbitration on
+ * TQAVCTRL.
+ */
+ if (!is_any_cbs_enabled(adapter)) {
+ tqavctrl = rd32(E1000_I210_TQAVCTRL);
+ tqavctrl &= ~E1000_TQAVCTRL_DATATRANARB;
+ wr32(E1000_I210_TQAVCTRL, tqavctrl);
+ }
}
/* XXX: In i210 controller the sendSlope and loCredit parameters from
@@ -1803,18 +1833,6 @@ static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
return 0;
}
-static bool is_any_cbs_enabled(struct igb_adapter *adapter)
-{
- int i;
-
- for (i = 0; i < adapter->num_tx_queues; i++) {
- if (adapter->tx_ring[i]->cbs_enable)
- return true;
- }
-
- return false;
-}
-
/**
* igb_setup_tx_mode - Switch to/from Qav Tx mode when applicable
* @adapter: pointer to adapter struct
@@ -1838,11 +1856,10 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
int i, max_queue;
/* Configure TQAVCTRL register: set transmit mode to 'Qav',
- * set data fetch arbitration to 'round robin' and set data
- * transfer arbitration to 'credit shaper algorithm.
+ * set data fetch arbitration to 'round robin'.
*/
val = rd32(E1000_I210_TQAVCTRL);
- val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_DATATRANARB;
+ val |= E1000_TQAVCTRL_XMIT_MODE;
val &= ~E1000_TQAVCTRL_DATAFETCHARB;
wr32(E1000_I210_TQAVCTRL, val);
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 08/14] net/sched: Add HW offloading capability to ETF
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
Add infra so etf qdisc supports HW offload of time-based transmission.
For hw offload, the time sorted list is still used, so packets are
dequeued always in order of txtime.
Example:
$ tc qdisc replace dev enp2s0 parent root handle 100 mqprio num_tc 3 \
map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 0
$ tc qdisc add dev enp2s0 parent 100:1 etf offload delta 100000 \
clockid CLOCK_REALTIME
In this example, the Qdisc will use HW offload for the control of the
transmission time through the network adapter. The hrtimer used for
packets scheduling inside the qdisc will use the clockid CLOCK_REALTIME
as reference and packets leave the Qdisc "delta" (100000) nanoseconds
before their transmission time. Because this will be using HW offload and
since dynamic clocks are not supported by the hrtimer, the system clock
and the PHC clock must be synchronized for this mode to behave as
expected.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
include/net/pkt_sched.h | 5 +++
include/uapi/linux/pkt_sched.h | 1 +
net/sched/sch_etf.c | 71 +++++++++++++++++++++++++++++++++-
3 files changed, 76 insertions(+), 1 deletion(-)
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 2466ea143d01..7dc769e5452b 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -155,4 +155,9 @@ struct tc_cbs_qopt_offload {
s32 sendslope;
};
+struct tc_etf_qopt_offload {
+ u8 enable;
+ s32 queue;
+};
+
#endif
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index d5e933ce1447..949118461009 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -944,6 +944,7 @@ struct tc_etf_qopt {
__s32 clockid;
__u32 flags;
#define TC_ETF_DEADLINE_MODE_ON BIT(0)
+#define TC_ETF_OFFLOAD_ON BIT(1)
};
enum {
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 4b7f4903ac17..932a136db568 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -20,8 +20,10 @@
#include <net/sock.h>
#define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON)
+#define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON)
struct etf_sched_data {
+ bool offload;
bool deadline_mode;
int clockid;
int queue;
@@ -45,6 +47,9 @@ static inline int validate_input_params(struct tc_etf_qopt *qopt,
* * Dynamic clockids are not supported.
*
* * Delta must be a positive integer.
+ *
+ * Also note that for the HW offload case, we must
+ * expect that system clocks have been synchronized to PHC.
*/
if (qopt->clockid < 0) {
NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported");
@@ -225,6 +230,56 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
return skb;
}
+static void etf_disable_offload(struct net_device *dev,
+ struct etf_sched_data *q)
+{
+ struct tc_etf_qopt_offload etf = { };
+ const struct net_device_ops *ops;
+ int err;
+
+ if (!q->offload)
+ return;
+
+ ops = dev->netdev_ops;
+ if (!ops->ndo_setup_tc)
+ return;
+
+ etf.queue = q->queue;
+ etf.enable = 0;
+
+ err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
+ if (err < 0)
+ pr_warn("Couldn't disable ETF offload for queue %d\n",
+ etf.queue);
+}
+
+static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q,
+ struct netlink_ext_ack *extack)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct tc_etf_qopt_offload etf = { };
+ int err;
+
+ if (q->offload)
+ return 0;
+
+ if (!ops->ndo_setup_tc) {
+ NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload");
+ return -EOPNOTSUPP;
+ }
+
+ etf.queue = q->queue;
+ etf.enable = 1;
+
+ err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
+ if (err < 0) {
+ NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload");
+ return err;
+ }
+
+ return 0;
+}
+
static int etf_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
@@ -251,8 +306,9 @@ static int etf_init(struct Qdisc *sch, struct nlattr *opt,
qopt = nla_data(tb[TCA_ETF_PARMS]);
- pr_debug("delta %d clockid %d deadline %s\n",
+ pr_debug("delta %d clockid %d offload %s deadline %s\n",
qopt->delta, qopt->clockid,
+ OFFLOAD_IS_ON(qopt) ? "on" : "off",
DEADLINE_MODE_IS_ON(qopt) ? "on" : "off");
err = validate_input_params(qopt, extack);
@@ -261,9 +317,16 @@ static int etf_init(struct Qdisc *sch, struct nlattr *opt,
q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
+ if (OFFLOAD_IS_ON(qopt)) {
+ err = etf_enable_offload(dev, q, extack);
+ if (err < 0)
+ return err;
+ }
+
/* Everything went OK, save the parameters used. */
q->delta = qopt->delta;
q->clockid = qopt->clockid;
+ q->offload = OFFLOAD_IS_ON(qopt);
q->deadline_mode = DEADLINE_MODE_IS_ON(qopt);
switch (q->clockid) {
@@ -326,10 +389,13 @@ static void etf_reset(struct Qdisc *sch)
static void etf_destroy(struct Qdisc *sch)
{
struct etf_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
/* Only cancel watchdog if it's been initialized. */
if (q->watchdog.qdisc == sch)
qdisc_watchdog_cancel(&q->watchdog);
+
+ etf_disable_offload(dev, q);
}
static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -344,6 +410,9 @@ static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
opt.delta = q->delta;
opt.clockid = q->clockid;
+ if (q->offload)
+ opt.flags |= TC_ETF_OFFLOAD_ON;
+
if (q->deadline_mode)
opt.flags |= TC_ETF_DEADLINE_MODE_ON;
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 07/14] net/sched: Introduce the ETF Qdisc
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
The ETF (Earliest TxTime First) qdisc uses the information added
earlier in this series (the socket option SO_TXTIME and the new
role of sk_buff->tstamp) to schedule packets transmission based
on absolute time.
For some workloads, just bandwidth enforcement is not enough, and
precise control of the transmission of packets is necessary.
Example:
$ tc qdisc replace dev enp2s0 parent root handle 100 mqprio num_tc 3 \
map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 0
$ tc qdisc add dev enp2s0 parent 100:1 etf delta 100000 \
clockid CLOCK_TAI
In this example, the Qdisc will provide SW best-effort for the control
of the transmission time to the network adapter, the time stamp in the
socket will be in reference to the clockid CLOCK_TAI and packets
will leave the qdisc "delta" (100000) nanoseconds before its transmission
time.
The ETF qdisc will buffer packets sorted by their txtime. It will drop
packets on enqueue() if their skbuff clockid does not match the clock
reference of the Qdisc. Moreover, on dequeue(), a packet will be dropped
if it expires while being enqueued.
The qdisc also supports the SO_TXTIME deadline mode. For this mode, it
will dequeue a packet as soon as possible and change the skb timestamp
to 'now' during etf_dequeue().
Note that both the qdisc's and the SO_TXTIME ABIs allow for a clockid
to be configured, but it's been decided that usage of CLOCK_TAI should
be enforced until we decide to allow for other clockids to be used.
The rationale here is that PTP times are usually in the TAI scale, thus
no other clocks should be necessary. For now, the qdisc will return
EINVAL if any clocks other than CLOCK_TAI are used.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
---
include/linux/netdevice.h | 1 +
include/uapi/linux/pkt_sched.h | 17 ++
net/sched/Kconfig | 11 +
net/sched/Makefile | 1 +
net/sched/sch_etf.c | 384 +++++++++++++++++++++++++++++++++
5 files changed, 414 insertions(+)
create mode 100644 net/sched/sch_etf.c
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 64480a0f2c16..610df79b9845 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -798,6 +798,7 @@ enum tc_setup_type {
TC_SETUP_QDISC_RED,
TC_SETUP_QDISC_PRIO,
TC_SETUP_QDISC_MQ,
+ TC_SETUP_QDISC_ETF,
};
/* These structures hold the attributes of bpf state that are being passed
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index bad3c03bcf43..d5e933ce1447 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -937,4 +937,21 @@ enum {
#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
+/* ETF */
+struct tc_etf_qopt {
+ __s32 delta;
+ __s32 clockid;
+ __u32 flags;
+#define TC_ETF_DEADLINE_MODE_ON BIT(0)
+};
+
+enum {
+ TCA_ETF_UNSPEC,
+ TCA_ETF_PARMS,
+ __TCA_ETF_MAX,
+};
+
+#define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
+
#endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a01169fb5325..fcc89706745b 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -183,6 +183,17 @@ config NET_SCH_CBS
To compile this code as a module, choose M here: the
module will be called sch_cbs.
+config NET_SCH_ETF
+ tristate "Earliest TxTime First (ETF)"
+ help
+ Say Y here if you want to use the Earliest TxTime First (ETF) packet
+ scheduling algorithm.
+
+ See the top of <file:net/sched/sch_etf.c> for more details.
+
+ To compile this code as a module, choose M here: the
+ module will be called sch_etf.
+
config NET_SCH_GRED
tristate "Generic Random Early Detection (GRED)"
---help---
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 8811d3804878..9a5a7077d217 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -54,6 +54,7 @@ obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o
obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o
obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o
obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o
+obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o
obj-$(CONFIG_NET_CLS_U32) += cls_u32.o
obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
new file mode 100644
index 000000000000..4b7f4903ac17
--- /dev/null
+++ b/net/sched/sch_etf.c
@@ -0,0 +1,384 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* net/sched/sch_etf.c Earliest TxTime First queueing discipline.
+ *
+ * Authors: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
+ * Vinicius Costa Gomes <vinicius.gomes@intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/rbtree.h>
+#include <linux/skbuff.h>
+#include <linux/posix-timers.h>
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
+#include <net/sock.h>
+
+#define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON)
+
+struct etf_sched_data {
+ bool deadline_mode;
+ int clockid;
+ int queue;
+ s32 delta; /* in ns */
+ ktime_t last; /* The txtime of the last skb sent to the netdevice. */
+ struct rb_root head;
+ struct qdisc_watchdog watchdog;
+ ktime_t (*get_time)(void);
+};
+
+static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = {
+ [TCA_ETF_PARMS] = { .len = sizeof(struct tc_etf_qopt) },
+};
+
+static inline int validate_input_params(struct tc_etf_qopt *qopt,
+ struct netlink_ext_ack *extack)
+{
+ /* Check if params comply to the following rules:
+ * * Clockid and delta must be valid.
+ *
+ * * Dynamic clockids are not supported.
+ *
+ * * Delta must be a positive integer.
+ */
+ if (qopt->clockid < 0) {
+ NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported");
+ return -ENOTSUPP;
+ }
+
+ if (qopt->clockid != CLOCK_TAI) {
+ NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used");
+ return -EINVAL;
+ }
+
+ if (qopt->delta < 0) {
+ NL_SET_ERR_MSG(extack, "Delta must be positive");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ ktime_t txtime = nskb->tstamp;
+ struct sock *sk = nskb->sk;
+ ktime_t now;
+
+ if (!sk)
+ return false;
+
+ if (!sock_flag(sk, SOCK_TXTIME))
+ return false;
+
+ /* We don't perform crosstimestamping.
+ * Drop if packet's clockid differs from qdisc's.
+ */
+ if (sk->sk_clockid != q->clockid)
+ return false;
+
+ if (sk->sk_txtime_deadline_mode != q->deadline_mode)
+ return false;
+
+ now = q->get_time();
+ if (ktime_before(txtime, now) || ktime_before(txtime, q->last))
+ return false;
+
+ return true;
+}
+
+static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct rb_node *p;
+
+ p = rb_first(&q->head);
+ if (!p)
+ return NULL;
+
+ return rb_to_skb(p);
+}
+
+static void reset_watchdog(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb = etf_peek_timesortedlist(sch);
+ ktime_t next;
+
+ if (!skb)
+ return;
+
+ next = ktime_sub_ns(skb->tstamp, q->delta);
+ qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
+}
+
+static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
+ struct sk_buff **to_free)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct rb_node **p = &q->head.rb_node, *parent = NULL;
+ ktime_t txtime = nskb->tstamp;
+
+ if (!is_packet_valid(sch, nskb))
+ return qdisc_drop(nskb, sch, to_free);
+
+ while (*p) {
+ struct sk_buff *skb;
+
+ parent = *p;
+ skb = rb_to_skb(parent);
+ if (ktime_after(txtime, skb->tstamp))
+ p = &parent->rb_right;
+ else
+ p = &parent->rb_left;
+ }
+ rb_link_node(&nskb->rbnode, parent, p);
+ rb_insert_color(&nskb->rbnode, &q->head);
+
+ qdisc_qstats_backlog_inc(sch, nskb);
+ sch->q.qlen++;
+
+ /* Now we may need to re-arm the qdisc watchdog for the next packet. */
+ reset_watchdog(sch);
+
+ return NET_XMIT_SUCCESS;
+}
+
+static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
+ bool drop)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+
+ rb_erase(&skb->rbnode, &q->head);
+
+ /* The rbnode field in the skb re-uses these fields, now that
+ * we are done with the rbnode, reset them.
+ */
+ skb->next = NULL;
+ skb->prev = NULL;
+ skb->dev = qdisc_dev(sch);
+
+ qdisc_qstats_backlog_dec(sch, skb);
+
+ if (drop) {
+ struct sk_buff *to_free = NULL;
+
+ qdisc_drop(skb, sch, &to_free);
+ kfree_skb_list(to_free);
+ qdisc_qstats_overlimit(sch);
+ } else {
+ qdisc_bstats_update(sch, skb);
+
+ q->last = skb->tstamp;
+ }
+
+ sch->q.qlen--;
+}
+
+static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb;
+ ktime_t now, next;
+
+ skb = etf_peek_timesortedlist(sch);
+ if (!skb)
+ return NULL;
+
+ now = q->get_time();
+
+ /* Drop if packet has expired while in queue. */
+ /* FIXME: Must return error on the socket's error queue */
+ if (ktime_before(skb->tstamp, now)) {
+ timesortedlist_erase(sch, skb, true);
+ skb = NULL;
+ goto out;
+ }
+
+ /* When in deadline mode, dequeue as soon as possible and change the
+ * txtime from deadline to (now + delta).
+ */
+ if (q->deadline_mode) {
+ timesortedlist_erase(sch, skb, false);
+ skb->tstamp = now;
+ goto out;
+ }
+
+ next = ktime_sub_ns(skb->tstamp, q->delta);
+
+ /* Dequeue only if now is within the [txtime - delta, txtime] range. */
+ if (ktime_after(now, next))
+ timesortedlist_erase(sch, skb, false);
+ else
+ skb = NULL;
+
+out:
+ /* Now we may need to re-arm the qdisc watchdog for the next packet. */
+ reset_watchdog(sch);
+
+ return skb;
+}
+
+static int etf_init(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+ struct nlattr *tb[TCA_ETF_MAX + 1];
+ struct tc_etf_qopt *qopt;
+ int err;
+
+ if (!opt) {
+ NL_SET_ERR_MSG(extack,
+ "Missing ETF qdisc options which are mandatory");
+ return -EINVAL;
+ }
+
+ err = nla_parse_nested(tb, TCA_ETF_MAX, opt, etf_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_ETF_PARMS]) {
+ NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters");
+ return -EINVAL;
+ }
+
+ qopt = nla_data(tb[TCA_ETF_PARMS]);
+
+ pr_debug("delta %d clockid %d deadline %s\n",
+ qopt->delta, qopt->clockid,
+ DEADLINE_MODE_IS_ON(qopt) ? "on" : "off");
+
+ err = validate_input_params(qopt, extack);
+ if (err < 0)
+ return err;
+
+ q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
+
+ /* Everything went OK, save the parameters used. */
+ q->delta = qopt->delta;
+ q->clockid = qopt->clockid;
+ q->deadline_mode = DEADLINE_MODE_IS_ON(qopt);
+
+ switch (q->clockid) {
+ case CLOCK_REALTIME:
+ q->get_time = ktime_get_real;
+ break;
+ case CLOCK_MONOTONIC:
+ q->get_time = ktime_get;
+ break;
+ case CLOCK_BOOTTIME:
+ q->get_time = ktime_get_boottime;
+ break;
+ case CLOCK_TAI:
+ q->get_time = ktime_get_clocktai;
+ break;
+ default:
+ NL_SET_ERR_MSG(extack, "Clockid is not supported");
+ return -ENOTSUPP;
+ }
+
+ qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid);
+
+ return 0;
+}
+
+static void timesortedlist_clear(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct rb_node *p = rb_first(&q->head);
+
+ while (p) {
+ struct sk_buff *skb = rb_to_skb(p);
+
+ p = rb_next(p);
+
+ rb_erase(&skb->rbnode, &q->head);
+ rtnl_kfree_skbs(skb, skb);
+ sch->q.qlen--;
+ }
+}
+
+static void etf_reset(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+
+ /* Only cancel watchdog if it's been initialized. */
+ if (q->watchdog.qdisc == sch)
+ qdisc_watchdog_cancel(&q->watchdog);
+
+ /* No matter which mode we are on, it's safe to clear both lists. */
+ timesortedlist_clear(sch);
+ __qdisc_reset_queue(&sch->q);
+
+ sch->qstats.backlog = 0;
+ sch->q.qlen = 0;
+
+ q->last = 0;
+}
+
+static void etf_destroy(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+
+ /* Only cancel watchdog if it's been initialized. */
+ if (q->watchdog.qdisc == sch)
+ qdisc_watchdog_cancel(&q->watchdog);
+}
+
+static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct tc_etf_qopt opt = { };
+ struct nlattr *nest;
+
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (!nest)
+ goto nla_put_failure;
+
+ opt.delta = q->delta;
+ opt.clockid = q->clockid;
+ if (q->deadline_mode)
+ opt.flags |= TC_ETF_DEADLINE_MODE_ON;
+
+ if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt))
+ goto nla_put_failure;
+
+ return nla_nest_end(skb, nest);
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -1;
+}
+
+static struct Qdisc_ops etf_qdisc_ops __read_mostly = {
+ .id = "etf",
+ .priv_size = sizeof(struct etf_sched_data),
+ .enqueue = etf_enqueue_timesortedlist,
+ .dequeue = etf_dequeue_timesortedlist,
+ .peek = etf_peek_timesortedlist,
+ .init = etf_init,
+ .reset = etf_reset,
+ .destroy = etf_destroy,
+ .dump = etf_dump,
+ .owner = THIS_MODULE,
+};
+
+static int __init etf_module_init(void)
+{
+ return register_qdisc(&etf_qdisc_ops);
+}
+
+static void __exit etf_module_exit(void)
+{
+ unregister_qdisc(&etf_qdisc_ops);
+}
+module_init(etf_module_init)
+module_exit(etf_module_exit)
+MODULE_LICENSE("GPL");
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 06/14] net/sched: Allow creating a Qdisc watchdog with other clocks
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
This adds 'qdisc_watchdog_init_clockid()' that allows a clockid to be
passed, this allows other time references to be used when scheduling
the Qdisc to run.
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
---
include/net/pkt_sched.h | 2 ++
net/sched/sch_api.c | 11 +++++++++--
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 815b92a23936..2466ea143d01 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -72,6 +72,8 @@ struct qdisc_watchdog {
struct Qdisc *qdisc;
};
+void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
+ clockid_t clockid);
void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 54eca685420f..98541c6399db 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -596,12 +596,19 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
return HRTIMER_NORESTART;
}
-void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
+void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
+ clockid_t clockid)
{
- hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_init(&wd->timer, clockid, HRTIMER_MODE_ABS_PINNED);
wd->timer.function = qdisc_watchdog;
wd->qdisc = qdisc;
}
+EXPORT_SYMBOL(qdisc_watchdog_init_clockid);
+
+void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
+{
+ qdisc_watchdog_init_clockid(wd, qdisc, CLOCK_MONOTONIC);
+}
EXPORT_SYMBOL(qdisc_watchdog_init);
void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 05/14] net: packet: Hook into time based transmission.
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
From: Richard Cochran <rcochran@linutronix.de>
For raw layer-2 packets, copy the desired future transmit time from
the CMSG cookie into the skb.
Signed-off-by: Richard Cochran <rcochran@linutronix.de>
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
net/packet/af_packet.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 57634bc3da74..3428f7739ae9 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1951,6 +1951,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
goto out_unlock;
}
+ sockc.transmit_time = 0;
sockc.tsflags = sk->sk_tsflags;
if (msg->msg_controllen) {
err = sock_cmsg_send(sk, msg, &sockc);
@@ -1962,6 +1963,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
skb->dev = dev;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = sockc.transmit_time;
sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags);
@@ -2457,6 +2459,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
skb->dev = dev;
skb->priority = po->sk.sk_priority;
skb->mark = po->sk.sk_mark;
+ skb->tstamp = sockc->transmit_time;
sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
skb_shinfo(skb)->destructor_arg = ph.raw;
@@ -2633,6 +2636,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
+ sockc.transmit_time = 0;
sockc.tsflags = po->sk.sk_tsflags;
if (msg->msg_controllen) {
err = sock_cmsg_send(&po->sk, msg, &sockc);
@@ -2829,6 +2833,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
if (unlikely(!(dev->flags & IFF_UP)))
goto out_unlock;
+ sockc.transmit_time = 0;
sockc.tsflags = sk->sk_tsflags;
sockc.mark = sk->sk_mark;
if (msg->msg_controllen) {
@@ -2903,6 +2908,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
skb->dev = dev;
skb->priority = sk->sk_priority;
skb->mark = sockc.mark;
+ skb->tstamp = sockc.transmit_time;
if (has_vnet_hdr) {
err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 04/14] net: ipv6: Hook into time based transmission
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
Add a struct sockcm_cookie parameter to ip6_setup_cork() so
we can easily re-use the transmit_time field from struct inet_cork
for most paths, by copying the timestamp from the CMSG cookie.
This is later copied into the skb during __ip6_make_skb().
For the raw fast path, also pass the sockcm_cookie as a parameter
so we can just perform the copy at rawv6_send_hdrinc() directly.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
net/ipv6/ip6_output.c | 11 ++++++++---
net/ipv6/raw.c | 7 +++++--
net/ipv6/udp.c | 1 +
3 files changed, 14 insertions(+), 5 deletions(-)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a14fb4fcdf18..f48af7e62f12 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1158,7 +1158,8 @@ static void ip6_append_data_mtu(unsigned int *mtu,
static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6,
- struct rt6_info *rt, struct flowi6 *fl6)
+ struct rt6_info *rt, struct flowi6 *fl6,
+ const struct sockcm_cookie *sockc)
{
struct ipv6_pinfo *np = inet6_sk(sk);
unsigned int mtu;
@@ -1226,6 +1227,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
cork->base.flags |= IPCORK_ALLFRAG;
cork->base.length = 0;
+ cork->base.transmit_time = sockc->transmit_time;
+
return 0;
}
@@ -1575,7 +1578,7 @@ int ip6_append_data(struct sock *sk,
* setup for corking
*/
err = ip6_setup_cork(sk, &inet->cork, &np->cork,
- ipc6, rt, fl6);
+ ipc6, rt, fl6, sockc);
if (err)
return err;
@@ -1673,6 +1676,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = cork->base.transmit_time;
+
skb_dst_set(skb, dst_clone(&rt->dst));
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
if (proto == IPPROTO_ICMPV6) {
@@ -1765,7 +1770,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
cork->base.opt = NULL;
cork->base.dst = NULL;
v6_cork.opt = NULL;
- err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6);
+ err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6, sockc);
if (err) {
ip6_cork_release(cork, &v6_cork);
return ERR_PTR(err);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index afc307c89d1a..5737c50f16eb 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -620,7 +620,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
struct flowi6 *fl6, struct dst_entry **dstp,
- unsigned int flags)
+ unsigned int flags, const struct sockcm_cookie *sockc)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
@@ -650,6 +650,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
skb->protocol = htons(ETH_P_IPV6);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = sockc->transmit_time;
skb_dst_set(skb, &rt->dst);
*dstp = NULL;
@@ -848,6 +849,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_oif = sk->sk_bound_dev_if;
sockc.tsflags = sk->sk_tsflags;
+ sockc.transmit_time = 0;
if (msg->msg_controllen) {
opt = &opt_space;
memset(opt, 0, sizeof(struct ipv6_txoptions));
@@ -921,7 +923,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
back_from_confirm:
if (inet->hdrincl)
- err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags);
+ err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst,
+ msg->msg_flags, &sockc);
else {
ipc6.opt = opt;
lock_sock(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e6645cae403e..ac6fc6728903 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1148,6 +1148,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc6.dontfrag = -1;
ipc6.gso_size = up->gso_size;
sockc.tsflags = sk->sk_tsflags;
+ sockc.transmit_time = 0;
/* destination address check */
if (sin6) {
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 03/14] net: ipv4: Hook into time based transmission
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
Add a transmit_time field to struct inet_cork, then copy the
timestamp from the CMSG cookie at ip_setup_cork() so we can
safely copy it into the skb later during __ip_make_skb().
For the raw fast path, just perform the copy at raw_send_hdrinc().
Signed-off-by: Richard Cochran <rcochran@linutronix.de>
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
include/net/inet_sock.h | 1 +
net/ipv4/icmp.c | 2 ++
net/ipv4/ip_output.c | 3 +++
net/ipv4/ping.c | 1 +
net/ipv4/raw.c | 2 ++
net/ipv4/udp.c | 1 +
6 files changed, 10 insertions(+)
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 83d5b3c2ac42..314be484c696 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -148,6 +148,7 @@ struct inet_cork {
__s16 tos;
char priority;
__u16 gso_size;
+ u64 transmit_time;
};
struct inet_cork_full {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 1617604c9284..937239afd68d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -437,6 +437,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
ipc.tx_flags = 0;
ipc.ttl = 0;
ipc.tos = -1;
+ ipc.sockc.transmit_time = 0;
if (icmp_param->replyopts.opt.opt.optlen) {
ipc.opt = &icmp_param->replyopts.opt;
@@ -715,6 +716,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
ipc.tx_flags = 0;
ipc.ttl = 0;
ipc.tos = -1;
+ ipc.sockc.transmit_time = 0;
rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
type, code, &icmp_param);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b3308e9d9762..135fb5036d18 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1153,6 +1153,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
cork->tos = ipc->tos;
cork->priority = ipc->priority;
cork->tx_flags = ipc->tx_flags;
+ cork->transmit_time = ipc->sockc.transmit_time;
return 0;
}
@@ -1413,6 +1414,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = cork->transmit_time;
/*
* Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
* on dst refcount
@@ -1550,6 +1552,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
ipc.tx_flags = 0;
ipc.ttl = 0;
ipc.tos = -1;
+ ipc.sockc.transmit_time = 0;
if (replyopts.opt.opt.optlen) {
ipc.opt = &replyopts.opt;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2ed64bca54e3..b47492205507 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -746,6 +746,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc.tx_flags = 0;
ipc.ttl = 0;
ipc.tos = -1;
+ ipc.sockc.transmit_time = 0;
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index abb3c9490c55..446af7be2b55 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -381,6 +381,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = sockc->transmit_time;
skb_dst_set(skb, &rt->dst);
*rtp = NULL;
@@ -562,6 +563,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
ipc.sockc.tsflags = sk->sk_tsflags;
+ ipc.sockc.transmit_time = 0;
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 24e116ddae79..5c76ba0666ec 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -930,6 +930,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc.tx_flags = 0;
ipc.ttl = 0;
ipc.tos = -1;
+ ipc.sockc.transmit_time = 0;
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 02/14] net: Add a new socket option for a future transmit time.
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
From: Richard Cochran <rcochran@linutronix.de>
This patch introduces SO_TXTIME. User space enables this option in
order to pass a desired future transmit time in a CMSG when calling
sendmsg(2). The argument to this socket option is a 8-bytes long struct
provided by the uapi header net_tstamp.h defined as:
struct sock_txtime {
clockid_t clockid;
u32 flags;
};
Note that new fields were added to struct sock by filling a 2-bytes
hole found in the struct. For that reason, neither the struct size or
number of cachelines were altered.
Signed-off-by: Richard Cochran <rcochran@linutronix.de>
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
arch/alpha/include/uapi/asm/socket.h | 3 +++
arch/ia64/include/uapi/asm/socket.h | 3 +++
arch/mips/include/uapi/asm/socket.h | 3 +++
arch/parisc/include/uapi/asm/socket.h | 3 +++
arch/s390/include/uapi/asm/socket.h | 3 +++
arch/sparc/include/uapi/asm/socket.h | 3 +++
arch/xtensa/include/uapi/asm/socket.h | 3 +++
include/net/sock.h | 10 ++++++++
include/uapi/asm-generic/socket.h | 3 +++
include/uapi/linux/net_tstamp.h | 15 ++++++++++++
net/core/sock.c | 35 +++++++++++++++++++++++++++
11 files changed, 84 insertions(+)
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index be14f16149d5..065fb372e355 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -112,4 +112,7 @@
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 3efba40adc54..c872c4e6bafb 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -114,4 +114,7 @@
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 49c3d4795963..71370fb3ceef 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -123,4 +123,7 @@
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 1d0fdc3b5d22..061b9cf2a779 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -104,4 +104,7 @@
#define SO_ZEROCOPY 0x4035
+#define SO_TXTIME 0x4036
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 3510c0fd06f4..39d901476ee5 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -111,4 +111,7 @@
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index d58520c2e6ff..7ea35e5601b6 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -101,6 +101,9 @@
#define SO_ZEROCOPY 0x003e
+#define SO_TXTIME 0x003f
+#define SCM_TXTIME SO_TXTIME
+
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 75a07b8119a9..1de07a7f7680 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -116,4 +116,7 @@
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _XTENSA_SOCKET_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 2ed99bfa4595..68347b9821c6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -319,6 +319,9 @@ struct sock_common {
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
* @sk_reuseport_cb: reuseport group container
* @sk_rcu: used during RCU grace period
+ * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
+ * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+ * @sk_txtime_unused: unused txtime flags
*/
struct sock {
/*
@@ -475,6 +478,11 @@ struct sock {
u8 sk_shutdown;
u32 sk_tskey;
atomic_t sk_zckey;
+
+ u8 sk_clockid;
+ u8 sk_txtime_deadline_mode : 1,
+ sk_txtime_unused : 7;
+
struct socket *sk_socket;
void *sk_user_data;
#ifdef CONFIG_SECURITY
@@ -790,6 +798,7 @@ enum sock_flags {
SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
+ SOCK_TXTIME,
};
#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -1585,6 +1594,7 @@ void sock_kzfree_s(struct sock *sk, void *mem, int size);
void sk_send_sigurg(struct sock *sk);
struct sockcm_cookie {
+ u64 transmit_time;
u32 mark;
u16 tsflags;
};
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 0ae758c90e54..a12692e5f7a8 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -107,4 +107,7 @@
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index 4fe104b2411f..c9a77c353b98 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -141,4 +141,19 @@ struct scm_ts_pktinfo {
__u32 reserved[2];
};
+/*
+ * SO_TXTIME gets a struct sock_txtime with flags being an integer bit
+ * field comprised of these values.
+ */
+enum txtime_flags {
+ SOF_TXTIME_DEADLINE_MODE = (1 << 0),
+
+ SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_DEADLINE_MODE)
+};
+
+struct sock_txtime {
+ clockid_t clockid; /* reference clockid */
+ u32 flags; /* flags defined by enum txtime_flags */
+};
+
#endif /* _NET_TIMESTAMPING_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index 6429982eb976..fe64b839f1b2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -91,6 +91,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <asm/unaligned.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
@@ -697,6 +698,7 @@ EXPORT_SYMBOL(sk_mc_loop);
int sock_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
+ struct sock_txtime sk_txtime;
struct sock *sk = sock->sk;
int val;
int valbool;
@@ -1070,6 +1072,24 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
}
break;
+ case SO_TXTIME:
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+ ret = -EPERM;
+ } else if (optlen != sizeof(struct sock_txtime)) {
+ ret = -EINVAL;
+ } else if (copy_from_user(&sk_txtime, optval,
+ sizeof(struct sock_txtime))) {
+ ret = -EFAULT;
+ } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) {
+ ret = -EINVAL;
+ } else {
+ sock_valbool_flag(sk, SOCK_TXTIME, true);
+ sk->sk_clockid = sk_txtime.clockid;
+ sk->sk_txtime_deadline_mode =
+ !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
+ }
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1115,6 +1135,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
u64 val64;
struct linger ling;
struct timeval tm;
+ struct sock_txtime txtime;
} v;
int lv = sizeof(int);
@@ -1403,6 +1424,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sock_flag(sk, SOCK_ZEROCOPY);
break;
+ case SO_TXTIME:
+ lv = sizeof(v.txtime);
+ v.txtime.clockid = sk->sk_clockid;
+ v.txtime.flags |= sk->sk_txtime_deadline_mode ?
+ SOF_TXTIME_DEADLINE_MODE : 0;
+ break;
+
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
@@ -2137,6 +2165,13 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK;
sockc->tsflags |= tsflags;
break;
+ case SCM_TXTIME:
+ if (!sock_flag(sk, SOCK_TXTIME))
+ return -EINVAL;
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64)))
+ return -EINVAL;
+ sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
+ break;
/* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
case SCM_RIGHTS:
case SCM_CREDENTIALS:
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 01/14] net: Clear skb->tstamp only on the forwarding path
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
In-Reply-To: <20180703224300.25300-1-jesus.sanchez-palencia@intel.com>
This is done in preparation for the upcoming time based transmission
patchset. Now that skb->tstamp will be used to hold packet's txtime,
we must ensure that it is being cleared when traversing namespaces.
Also, doing that from skb_scrub_packet() before the early return would
break our feature when tunnels are used.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
net/core/skbuff.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1357f36c8a5e..c4e24ac27464 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4898,7 +4898,6 @@ EXPORT_SYMBOL(skb_try_coalesce);
*/
void skb_scrub_packet(struct sk_buff *skb, bool xnet)
{
- skb->tstamp = 0;
skb->pkt_type = PACKET_HOST;
skb->skb_iif = 0;
skb->ignore_df = 0;
@@ -4912,6 +4911,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
ipvs_reset(skb);
skb->mark = 0;
+ skb->tstamp = 0;
}
EXPORT_SYMBOL_GPL(skb_scrub_packet);
--
2.18.0
^ permalink raw reply related
* [PATCH v2 net-next 00/14] Scheduled packet Transmission: ETF
From: Jesus Sanchez-Palencia @ 2018-07-03 22:42 UTC (permalink / raw)
To: netdev
Cc: tglx, jan.altenberg, vinicius.gomes, kurt.kanzenbach, henrik,
richardcochran, ilias.apalodimas, ivan.khoronzhuk, mlichvar,
willemb, jhs, xiyou.wangcong, jiri, eric.dumazet,
jeffrey.t.kirsher
Changes since v1:
- moved struct sock_txtime from socket.h to uapi net_tstamp.h;
- sk_clockid was changed from u16 to u8;
- sk_txtime_flags was changed from u16 to a u8 bit field in struct sock;
- the socket option flags are now validated in sock_setsockopt();
- added SO_EE_ORIGIN_TXTIME;
- sockc.transmit_time is now initialized from all IPv4 Tx paths;
- added support for the IPv6 Tx path;
Overview
========
This work consists of a set of kernel interfaces that can be used by
applications that require (time-based) Scheduled Tx of packets.
It is comprised by 3 new components to the kernel:
- SO_TXTIME: socket option + cmsg programming interfaces.
- etf: the "earliest txtime first" qdisc, that provides per-queue
TxTime-based scheduling. This has been renamed from 'tbs' to
'etf' to better describe its functionality.
- taprio: the "time-aware priority scheduler" qdisc, that provides
per-port Time-Aware scheduling;
This patchset is providing the first 2 components, which have been
developed for longer. The taprio qdisc will be shared as an RFC separately
(shortly).
Note that this series is a follow up of the "Time based packet
transmission" RFCv3 [1].
etf (formerly known as 'tbs')
=============================
For applications/systems that the concept of time slices isn't precise
enough, the etf qdisc allows applications to control the instant when
a packet should leave the network controller. When used in conjunction
with taprio, it can also be used in case the application needs to
control with greater guarantee the offset into each time slice a packet
will be sent. Another use case of etf, is when only a small number of
applications on a system are time sensitive, so it can then be used
with a more traditional root qdisc (like mqprio).
The etf qdisc is designed so it buffers packets until a configurable
time before their deadline (Tx time). The qdisc uses a rbtree internally
so the buffered packets are always 'ordered' by their txtime (deadline)
and will be dequeued following the earliest txtime first.
It relies on the SO_TXTIME API set for receiving the per-packet timestamp
(txtime) as well as the config flags for each socket: the clockid to be
used as a reference, if the expected mode of txtime for that socket is
deadline or strict mode, and if packet drops should be reported on the
socket's error queue or not.
The qdisc will drop any packets with a Tx time in the past, or if a
packet expires while waiting for being dequeued. Drops can be reported
as errors back to userspace through the socket's error queue.
Example configuration:
$ tc qdisc add dev enp2s0 parent 100:1 etf offload delta 200000 \
clockid CLOCK_TAI
Here, the Qdisc will use HW offload for the txtime control.
Packets will be dequeued by the qdisc "delta" (200000) nanoseconds before
their transmission time. Because this will be using HW offload and
since dynamic clocks are not supported by hrtimers, the system clock
and the PHC clock must be synchronized for this mode to behave as expected.
A more complete example can be found here, with instructions of how to
test it:
https://gist.github.com/jeez/bd3afeff081ba64a695008dd8215866f [2]
Note that we haven't modified the qdisc so it uses a timerqueue because
the modification needed was increasing the number of cachelines of a sk_buff.
This series is also hosted on github and can be found at [3].
The companion iproute2 patches can be found at [4].
[1] https://patchwork.ozlabs.org/cover/882342/
[2] github doesn't make it clear, but the gist can be cloned like this:
$ git clone https://gist.github.com/jeez/bd3afeff081ba64a695008dd8215866f scheduled-tx-tests
[3] https://github.com/jeez/linux/tree/etf-v2
[4] https://github.com/jeez/iproute2/tree/etf-v2
Jesus Sanchez-Palencia (10):
net: Clear skb->tstamp only on the forwarding path
net: ipv4: Hook into time based transmission
net: ipv6: Hook into time based transmission
net/sched: Add HW offloading capability to ETF
igb: Refactor igb_configure_cbs()
igb: Only change Tx arbitration when CBS is on
igb: Refactor igb_offload_cbs()
igb: Only call skb_tx_timestamp after descriptors are ready
igb: Add support for ETF offload
net/sched: Make etf report drops on error_queue
Richard Cochran (2):
net: Add a new socket option for a future transmit time.
net: packet: Hook into time based transmission.
Vinicius Costa Gomes (2):
net/sched: Allow creating a Qdisc watchdog with other clocks
net/sched: Introduce the ETF Qdisc
arch/alpha/include/uapi/asm/socket.h | 3 +
arch/ia64/include/uapi/asm/socket.h | 3 +
arch/mips/include/uapi/asm/socket.h | 3 +
arch/parisc/include/uapi/asm/socket.h | 3 +
arch/s390/include/uapi/asm/socket.h | 3 +
arch/sparc/include/uapi/asm/socket.h | 3 +
arch/xtensa/include/uapi/asm/socket.h | 3 +
.../net/ethernet/intel/igb/e1000_defines.h | 16 +
drivers/net/ethernet/intel/igb/igb.h | 1 +
drivers/net/ethernet/intel/igb/igb_main.c | 256 ++++++---
include/linux/netdevice.h | 1 +
include/net/inet_sock.h | 1 +
include/net/pkt_sched.h | 7 +
include/net/sock.h | 11 +
include/uapi/asm-generic/socket.h | 3 +
include/uapi/linux/errqueue.h | 4 +
include/uapi/linux/net_tstamp.h | 18 +
include/uapi/linux/pkt_sched.h | 18 +
net/core/skbuff.c | 2 +-
net/core/sock.c | 39 ++
net/ipv4/icmp.c | 2 +
net/ipv4/ip_output.c | 3 +
net/ipv4/ping.c | 1 +
net/ipv4/raw.c | 2 +
net/ipv4/udp.c | 1 +
net/ipv6/ip6_output.c | 11 +-
net/ipv6/raw.c | 7 +-
net/ipv6/udp.c | 1 +
net/packet/af_packet.c | 6 +
net/sched/Kconfig | 11 +
net/sched/Makefile | 1 +
net/sched/sch_api.c | 11 +-
net/sched/sch_etf.c | 484 ++++++++++++++++++
33 files changed, 864 insertions(+), 75 deletions(-)
create mode 100644 net/sched/sch_etf.c
--
2.18.0
^ permalink raw reply
* Re: [PATCH bpf-next v2 2/3] bpf: btf: add btf print functionality
From: Jakub Kicinski @ 2018-07-03 22:38 UTC (permalink / raw)
To: Okash Khawaja, Martin KaFai Lau
Cc: Daniel Borkmann, Alexei Starovoitov, Yonghong Song,
Quentin Monnet, David S. Miller, netdev, kernel-team,
linux-kernel
In-Reply-To: <20180703152331.151d1c4b@cakuba.netronome.com>
On Tue, 3 Jul 2018 15:23:31 -0700, Jakub Kicinski wrote:
> > > > + else
> > > > + jsonw_printf(jw, "%hhd", *((char *)data));
> > >
> > > ... I think you need to always print a string, and express it as
> > > \u00%02hhx for non-printable.
> > Okay that makes sense
>
> Yeah, IDK, char can be used as a byte as well as a string. In eBPF
> it may actually be more likely to just be used as a raw byte buffer...
Actually, what is the definition/purpose of BTF_INT_CHAR? There seems
to be no BTF_INT_SHORT and BTF_INT_SIGNED can simply be of size 8...
Is normal int only used for bitfields of size 8 and BTF_INT_CHAR for
char variables?
The kernel seems to be rejecting combinations of those flags, is
unsigned char going to not be marked as char then?
> Either way I think it may be nice to keep it consistent, at least for
> the JSON output could we do either always ints or always characters?
^ permalink raw reply
* Re: [PATCH bpf-next v2 2/3] bpf: btf: add btf print functionality
From: Jakub Kicinski @ 2018-07-03 22:23 UTC (permalink / raw)
To: Okash Khawaja
Cc: Daniel Borkmann, Martin KaFai Lau, Alexei Starovoitov,
Yonghong Song, Quentin Monnet, David S. Miller, netdev,
kernel-team, linux-kernel
In-Reply-To: <20180703214559.GA4448@w1t1fb>
On Tue, 3 Jul 2018 22:46:00 +0100, Okash Khawaja wrote:
> On Mon, Jul 02, 2018 at 10:06:59PM -0700, Jakub Kicinski wrote:
> > On Mon, 2 Jul 2018 11:39:15 -0700, Okash Khawaja wrote:
> > > +#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
> > > +#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
> >
> > Perhaps it's just me but BIT_OFFSET or BIT_COUNT as a name of this macro
> > would make it more obvious to parse in the code below.
> I don't mind either. However these macro names are also used inside
> kernel for same purpose. For sake of consistency, I'd recommend we keep
> them :)
Ugh, okay :)
> > > + } print_num;
> > > +
> > > + total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
> > > + data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
> > > + bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
> > > + bits_to_copy = bits + bit_offset;
> > > + bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy);
> > > +
> > > + print_num.u64_num = 0;
> > > + memcpy(&print_num.u64_num, data, bytes_to_copy);
> >
> > This scheme is unlikely to work on big endian machines...
> Can you give an example how?
On BE:
Input: [0x01, 0x82]
Bit length: 15
Bytes to copy: 2
bit_offset: 0
upper_bits: 7
print_num.u64_num = 0;
# [0, 0, 0, 0, 0, 0, 0, 0]
memcpy(&print_num.u64_num, data, bytes_to_copy);
# [0x01, 0x82, 0, 0, 0, 0, 0, 0]
mask = (1 << upper_bits) - 1;
# mask = 0x7f
print_num.u8_nums[bytes_to_copy - 1] &= mask;
# [0x01, 0x02, 0, 0, 0, 0, 0, 0]
printf("0x%llx", print_num.u64_num);
# 0x0102000000000000 AKA 72620543991349248
# expected:
# 0x0102 AKA 258
Am I missing something?
> > > + upper_bits = BITS_PER_BYTE_MASKED(bits_to_copy);
> > > + if (upper_bits) {
> > > + uint8_t mask = (1 << upper_bits) - 1;
> > > +
> > > + print_num.u8_nums[bytes_to_copy - 1] &= mask;
> > > + }
> > > +
> > > + print_num.u64_num >>= bit_offset;
> > > +
> > > + if (is_plain_text)
> > > + jsonw_printf(jw, "0x%llx", print_num.u64_num);
> > > + else
> > > + jsonw_printf(jw, "%llu", print_num.u64_num);
> > > +}
> > > +
> > > +static int btf_dumper_int(const struct btf_type *t, uint8_t bit_offset,
> > > + const void *data, json_writer_t *jw,
> > > + bool is_plain_text)
> > > +{
> > > + uint32_t *int_type = (uint32_t *)(t + 1);
> > > + uint32_t bits = BTF_INT_BITS(*int_type);
> > > + int ret = 0;
> > > +
> > > + /* if this is bit field */
> > > + if (bit_offset || BTF_INT_OFFSET(*int_type) ||
> > > + BITS_PER_BYTE_MASKED(bits)) {
> > > + btf_dumper_int_bits(*int_type, bit_offset, data, jw,
> > > + is_plain_text);
> > > + return ret;
> > > + }
> > > +
> > > + switch (BTF_INT_ENCODING(*int_type)) {
> > > + case 0:
> > > + if (BTF_INT_BITS(*int_type) == 64)
> > > + jsonw_printf(jw, "%lu", *((uint64_t *)data));
> > > + else if (BTF_INT_BITS(*int_type) == 32)
> > > + jsonw_printf(jw, "%u", *((uint32_t *)data));
> > > + else if (BTF_INT_BITS(*int_type) == 16)
> > > + jsonw_printf(jw, "%hu", *((uint16_t *)data));
> > > + else if (BTF_INT_BITS(*int_type) == 8)
> > > + jsonw_printf(jw, "%hhu", *((uint8_t *)data));
> > > + else
> > > + btf_dumper_int_bits(*int_type, bit_offset, data, jw,
> > > + is_plain_text);
> > > + break;
> > > + case BTF_INT_SIGNED:
> > > + if (BTF_INT_BITS(*int_type) == 64)
> > > + jsonw_printf(jw, "%ld", *((int64_t *)data));
> > > + else if (BTF_INT_BITS(*int_type) == 32)
> > > + jsonw_printf(jw, "%d", *((int32_t *)data));
> > > + else if (BTF_INT_BITS(*int_type) == 16)
> >
> > Please drop the double space. Both for 16 where it makes no sense and
> > for 8 where it's marginally useful but not really.
> >
> > > + jsonw_printf(jw, "%hd", *((int16_t *)data));
> > > + else if (BTF_INT_BITS(*int_type) == 8)
> > > + jsonw_printf(jw, "%hhd", *((int8_t *)data));
> > > + else
> > > + btf_dumper_int_bits(*int_type, bit_offset, data, jw,
> > > + is_plain_text);
> > > + break;
> > > + case BTF_INT_CHAR:
> > > + if (*((char *)data) == '\0')
> > > + jsonw_null(jw);
> >
> > Mm.. I don't think 0 char is equivalent to null.
> Yes, thanks. Will fix.
>
> >
> > > + else if (isprint(*((char *)data)))
> > > + jsonw_printf(jw, "\"%c\"", *((char *)data));
> >
> > This looks very suspicious. So if I see a "6" for a char field it's
> > either a 6 ('\u0006') or a 54 ('6')...
> It will always be 54. May be I missed your point. Could you explain why
> it would be other than 54?
Ah, I think I missed that %c is in quotes...
> > > + else
> > > + if (is_plain_text)
> > > + jsonw_printf(jw, "%hhx", *((char *)data));
This seems to be missing a "0x" prefix?
> > > + else
> > > + jsonw_printf(jw, "%hhd", *((char *)data));
> >
> > ... I think you need to always print a string, and express it as
> > \u00%02hhx for non-printable.
> Okay that makes sense
Yeah, IDK, char can be used as a byte as well as a string. In eBPF
it may actually be more likely to just be used as a raw byte buffer...
Either way I think it may be nice to keep it consistent, at least for
the JSON output could we do either always ints or always characters?
^ permalink raw reply
* Re: [PATCH bpf-next v2 2/3] bpf: btf: add btf print functionality
From: Okash Khawaja @ 2018-07-03 21:46 UTC (permalink / raw)
To: Jakub Kicinski
Cc: Daniel Borkmann, Martin KaFai Lau, Alexei Starovoitov,
Yonghong Song, Quentin Monnet, David S. Miller, netdev,
kernel-team, linux-kernel
In-Reply-To: <20180702220659.6baa77ba@cakuba.netronome.com>
On Mon, Jul 02, 2018 at 10:06:59PM -0700, Jakub Kicinski wrote:
> On Mon, 2 Jul 2018 11:39:15 -0700, Okash Khawaja wrote:
[...]
>
> > +#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
> > +#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
>
> Perhaps it's just me but BIT_OFFSET or BIT_COUNT as a name of this macro
> would make it more obvious to parse in the code below.
I don't mind either. However these macro names are also used inside
kernel for same purpose. For sake of consistency, I'd recommend we keep
them :)
>
> > +#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
> > +#define BITS_ROUNDUP_BYTES(bits) \
> > + (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
> > +
> > +static int btf_dumper_do_type(const struct btf_dumper *d, uint32_t type_id,
> > + uint8_t bit_offset, const void *data);
> > +
> > +static void btf_dumper_ptr(const void *data, json_writer_t *jw,
> > + bool is_plain_text)
> > +{
> > + if (is_plain_text)
> > + jsonw_printf(jw, "%p", *((uintptr_t *)data));
> > + else
> > + jsonw_printf(jw, "%u", *((uintptr_t *)data));
> > +}
> > +
> > +static int btf_dumper_modifier(const struct btf_dumper *d, uint32_t type_id,
> > + const void *data)
> > +{
> > + int32_t actual_type_id = btf__resolve_type(d->btf, type_id);
>
> Please prefer kernel types like __u32 wherever possible.
>
> > + int ret;
> > +
> > + if (actual_type_id < 0)
> > + return actual_type_id;
> > +
> > + ret = btf_dumper_do_type(d, actual_type_id, 0, data);
> > +
> > + return ret;
>
> ret is unnecessary.
>
> > +}
> > +
> > +static void btf_dumper_enum(const void *data, json_writer_t *jw)
> > +{
> > + jsonw_printf(jw, "%d", *((int32_t *)data));
>
> Unnecessary parenthesis. There is a lot of those, please remove them
> all.
>
> > +}
> > +
> > +static int btf_dumper_array(const struct btf_dumper *d, uint32_t type_id,
> > + const void *data)
> > +{
> > + const struct btf_type *t = btf__type_by_id(d->btf, type_id);
> > + struct btf_array *arr = (struct btf_array *)(t + 1);
> > + int64_t elem_size;
> > + int ret = 0;
> > + uint32_t i;
> > +
> > + elem_size = btf__resolve_size(d->btf, arr->type);
> > + if (elem_size < 0)
> > + return elem_size;
> > +
> > + jsonw_start_array(d->jw);
> > + for (i = 0; i < arr->nelems; i++) {
> > + ret = btf_dumper_do_type(d, arr->type, 0,
> > + data + (i * elem_size));
>
> Unnecessary parenthesis.
>
> > + if (ret)
> > + break;
> > + }
> > +
> > + jsonw_end_array(d->jw);
> > + return ret;
> > +}
> > +
> > +static void btf_dumper_int_bits(uint32_t int_type, uint8_t bit_offset,
> > + const void *data, json_writer_t *jw,
> > + bool is_plain_text)
> > +{
> > + uint32_t bits = BTF_INT_BITS(int_type);
> > + uint16_t total_bits_offset;
> > + uint16_t bytes_to_copy;
> > + uint16_t bits_to_copy;
>
> Please use normal int types for things which don't have to be
> explicitly sized. Using explicitly sized variables is bad style,
> and ALU operations other than on word or byte quantities are usually
> slower on modern CPUs.
>
> > + uint8_t upper_bits;
> > + union {
> > + uint64_t u64_num;
> > + uint8_t u8_nums[8];
>
> Are the int types in BTF constrained to 64bit at most?
>
> > + } print_num;
> > +
> > + total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
> > + data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
> > + bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
> > + bits_to_copy = bits + bit_offset;
> > + bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy);
> > +
> > + print_num.u64_num = 0;
> > + memcpy(&print_num.u64_num, data, bytes_to_copy);
>
> This scheme is unlikely to work on big endian machines...
Can you give an example how?
>
> > + upper_bits = BITS_PER_BYTE_MASKED(bits_to_copy);
> > + if (upper_bits) {
> > + uint8_t mask = (1 << upper_bits) - 1;
> > +
> > + print_num.u8_nums[bytes_to_copy - 1] &= mask;
> > + }
> > +
> > + print_num.u64_num >>= bit_offset;
> > +
> > + if (is_plain_text)
> > + jsonw_printf(jw, "0x%llx", print_num.u64_num);
> > + else
> > + jsonw_printf(jw, "%llu", print_num.u64_num);
> > +}
> > +
> > +static int btf_dumper_int(const struct btf_type *t, uint8_t bit_offset,
> > + const void *data, json_writer_t *jw,
> > + bool is_plain_text)
> > +{
> > + uint32_t *int_type = (uint32_t *)(t + 1);
> > + uint32_t bits = BTF_INT_BITS(*int_type);
> > + int ret = 0;
> > +
> > + /* if this is bit field */
> > + if (bit_offset || BTF_INT_OFFSET(*int_type) ||
> > + BITS_PER_BYTE_MASKED(bits)) {
> > + btf_dumper_int_bits(*int_type, bit_offset, data, jw,
> > + is_plain_text);
> > + return ret;
> > + }
> > +
> > + switch (BTF_INT_ENCODING(*int_type)) {
> > + case 0:
> > + if (BTF_INT_BITS(*int_type) == 64)
> > + jsonw_printf(jw, "%lu", *((uint64_t *)data));
> > + else if (BTF_INT_BITS(*int_type) == 32)
> > + jsonw_printf(jw, "%u", *((uint32_t *)data));
> > + else if (BTF_INT_BITS(*int_type) == 16)
> > + jsonw_printf(jw, "%hu", *((uint16_t *)data));
> > + else if (BTF_INT_BITS(*int_type) == 8)
> > + jsonw_printf(jw, "%hhu", *((uint8_t *)data));
> > + else
> > + btf_dumper_int_bits(*int_type, bit_offset, data, jw,
> > + is_plain_text);
> > + break;
> > + case BTF_INT_SIGNED:
> > + if (BTF_INT_BITS(*int_type) == 64)
> > + jsonw_printf(jw, "%ld", *((int64_t *)data));
> > + else if (BTF_INT_BITS(*int_type) == 32)
> > + jsonw_printf(jw, "%d", *((int32_t *)data));
> > + else if (BTF_INT_BITS(*int_type) == 16)
>
> Please drop the double space. Both for 16 where it makes no sense and
> for 8 where it's marginally useful but not really.
>
> > + jsonw_printf(jw, "%hd", *((int16_t *)data));
> > + else if (BTF_INT_BITS(*int_type) == 8)
> > + jsonw_printf(jw, "%hhd", *((int8_t *)data));
> > + else
> > + btf_dumper_int_bits(*int_type, bit_offset, data, jw,
> > + is_plain_text);
> > + break;
> > + case BTF_INT_CHAR:
> > + if (*((char *)data) == '\0')
> > + jsonw_null(jw);
>
> Mm.. I don't think 0 char is equivalent to null.
Yes, thanks. Will fix.
>
> > + else if (isprint(*((char *)data)))
> > + jsonw_printf(jw, "\"%c\"", *((char *)data));
>
> This looks very suspicious. So if I see a "6" for a char field it's
> either a 6 ('\u0006') or a 54 ('6')...
It will always be 54. May be I missed your point. Could you explain why
it would be other than 54?
>
> > + else
> > + if (is_plain_text)
> > + jsonw_printf(jw, "%hhx", *((char *)data));
> > + else
> > + jsonw_printf(jw, "%hhd", *((char *)data));
>
> ... I think you need to always print a string, and express it as
> \u00%02hhx for non-printable.
Okay that makes sense
>
> > + break;
> > + case BTF_INT_BOOL:
> > + jsonw_bool(jw, *((int *)data));
> > + break;
> > + default:
> > + /* shouldn't happen */
> > + ret = -EINVAL;
>
> You only set ret to something else than 0 here just to break and
> immediately return. Please remove the ret variable.
>
> > + break;
> > + }
> > +
> > + return ret;
> > +}
> > +
> > +static int btf_dumper_struct(const struct btf_dumper *d, uint32_t type_id,
> > + const void *data)
> > +{
> > + const struct btf_type *t = btf__type_by_id(d->btf, type_id);
>
> Please don't call functions which need error checking as initialized
> the if below looks very awkward..
>
> > + struct btf_member *m;
> > + int ret = 0;
> > +
> > + int i, vlen;
> > +
> > + if (!t)
> > + return -EINVAL;
> > +
> > + vlen = BTF_INFO_VLEN(t->info);
> > + jsonw_start_object(d->jw);
> > + m = (struct btf_member *)(t + 1);
> > +
> > + for (i = 0; i < vlen; i++) {
> > + jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off));
> > + ret = btf_dumper_do_type(d, m[i].type,
> > + BITS_PER_BYTE_MASKED(m[i].offset), data
> > + + BITS_ROUNDDOWN_BYTES(m[i].offset));
>
> Please use a temp variable to avoid this awkward multi-line sum.
>
> > + if (ret)
> > + return ret;
>
> You can't return without jsonw_end_object().
>
> > + }
> > +
> > + jsonw_end_object(d->jw);
> > +
> > + return 0;
> > +}
> > +
> > +static int btf_dumper_do_type(const struct btf_dumper *d, uint32_t type_id,
> > + uint8_t bit_offset, const void *data)
> > +{
> > + const struct btf_type *t = btf__type_by_id(d->btf, type_id);
> > + int ret = 0;
> > +
> > + switch (BTF_INFO_KIND(t->info)) {
> > + case BTF_KIND_INT:
> > + ret = btf_dumper_int(t, bit_offset, data, d->jw,
> > + d->is_plain_text);
> > + break;
> > + case BTF_KIND_STRUCT:
> > + case BTF_KIND_UNION:
> > + ret = btf_dumper_struct(d, type_id, data);
> > + break;
> > + case BTF_KIND_ARRAY:
> > + ret = btf_dumper_array(d, type_id, data);
> > + break;
> > + case BTF_KIND_ENUM:
> > + btf_dumper_enum(data, d->jw);
> > + break;
> > + case BTF_KIND_PTR:
> > + btf_dumper_ptr(data, d->jw, d->is_plain_text);
> > + break;
> > + case BTF_KIND_UNKN:
> > + jsonw_printf(d->jw, "(unknown)");
> > + break;
> > + case BTF_KIND_FWD:
> > + /* map key or value can't be forward */
>
> Right, but you have to print _something_, otherwise we would have a
> name without a value, which would break JSON, no?
>
> > + ret = -EINVAL;
> > + break;
> > + case BTF_KIND_TYPEDEF:
> > + case BTF_KIND_VOLATILE:
> > + case BTF_KIND_CONST:
> > + case BTF_KIND_RESTRICT:
> > + ret = btf_dumper_modifier(d, type_id, data);
> > + break;
> > + default:
> > + jsonw_printf(d->jw, "(unsupported-kind");
> > + ret = -EINVAL;
> > + break;
> > + }
> > +
> > + return ret;
>
> Why return ret; at all, there is no code after the switch just return
> directly from cases and save 9 LOC.
>
> > +}
> > +
> > +int32_t btf_dumper_type(const struct btf_dumper *d, uint32_t type_id,
> > + const void *data)
> > +{
> > + if (!d)
> > + return -EINVAL;
>
> No need for defensive programming.
>
> > + return btf_dumper_do_type(d, type_id, 0, data);
> > +}
> > --- /dev/null
> > +++ b/tools/bpf/bpftool/btf_dumper.h
> > @@ -0,0 +1,23 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +/* Copyright (c) 2018 Facebook */
> > +
> > +#ifndef BTF_DUMPER_H
> > +#define BTF_DUMPER_H
> > +
> > +struct btf_dumper {
> > + const struct btf *btf;
> > + json_writer_t *jw;
> > + bool is_plain_text;
> > +};
> > +
> > +/* btf_dumper_type - print data along with type information
> > + * @d: an instance containing context for dumping types
> > + * @type_id: index in btf->types array. this points to the type to be dumped
> > + * @data: pointer the actual data, i.e. the values to be printed
> > + *
> > + * Returns zero on success and negative error code otherwise
> > + */
> > +int32_t btf_dumper_type(const struct btf_dumper *d, uint32_t type_id,
> > + const void *data);
> > +
> > +#endif
>
> Please don't add header files for a single struct and single function.
> Just put this in main.h.
Thanks for your feedback. I'll reply with v3.
Okash
^ permalink raw reply
* [PATCH v2 net] net/ipv6: Revert attempt to simplify route replace and append
From: dsahern @ 2018-07-03 21:36 UTC (permalink / raw)
To: netdev; +Cc: idosch, sharpd, Thomas.Winter, petrm, David Ahern
From: David Ahern <dsahern@gmail.com>
NetworkManager likes to manage linklocal prefix routes and does so with
the NLM_F_APPEND flag, breaking attempts to simplify the IPv6 route
code and by extension enable multipath routes with device only nexthops.
Revert f34436a43092 and these followup patches:
6eba08c3626b ("ipv6: Only emit append events for appended routes").
ce45bded6435 ("mlxsw: spectrum_router: Align with new route replace logic")
53b562df8c20 ("mlxsw: spectrum_router: Allow appending to dev-only routes")
Update the fib_tests cases to reflect the old behavior.
Fixes: f34436a43092 ("net/ipv6: Simplify route replace and appending into multipath route")
Signed-off-by: David Ahern <dsahern@gmail.com>
---
The gre_multipath tests only exist in net-next. Those will need to be
updated separately.
.../net/ethernet/mellanox/mlxsw/spectrum_router.c | 48 +++----
include/net/ip6_route.h | 6 +
net/ipv6/ip6_fib.c | 156 ++++++++++++---------
net/ipv6/route.c | 3 +-
tools/testing/selftests/net/fib_tests.sh | 41 ------
5 files changed, 117 insertions(+), 137 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 6aaaf3d9ba31..77b2adb29341 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4756,6 +4756,12 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
kfree(mlxsw_sp_rt6);
}
+static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
+{
+ /* RTF_CACHE routes are ignored */
+ return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY;
+}
+
static struct fib6_info *
mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
{
@@ -4765,11 +4771,11 @@ mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
- const struct fib6_info *nrt, bool append)
+ const struct fib6_info *nrt, bool replace)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
- if (!append)
+ if (!mlxsw_sp_fib6_rt_can_mp(nrt) || replace)
return NULL;
list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
@@ -4784,7 +4790,8 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
break;
if (rt->fib6_metric < nrt->fib6_metric)
continue;
- if (rt->fib6_metric == nrt->fib6_metric)
+ if (rt->fib6_metric == nrt->fib6_metric &&
+ mlxsw_sp_fib6_rt_can_mp(rt))
return fib6_entry;
if (rt->fib6_metric > nrt->fib6_metric)
break;
@@ -5163,7 +5170,7 @@ static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
const struct fib6_info *nrt, bool replace)
{
- struct mlxsw_sp_fib6_entry *fib6_entry;
+ struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL;
list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
@@ -5172,13 +5179,18 @@ mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
continue;
if (rt->fib6_table->tb6_id != nrt->fib6_table->tb6_id)
break;
- if (replace && rt->fib6_metric == nrt->fib6_metric)
- return fib6_entry;
+ if (replace && rt->fib6_metric == nrt->fib6_metric) {
+ if (mlxsw_sp_fib6_rt_can_mp(rt) ==
+ mlxsw_sp_fib6_rt_can_mp(nrt))
+ return fib6_entry;
+ if (mlxsw_sp_fib6_rt_can_mp(nrt))
+ fallback = fallback ?: fib6_entry;
+ }
if (rt->fib6_metric > nrt->fib6_metric)
- return fib6_entry;
+ return fallback ?: fib6_entry;
}
- return NULL;
+ return fallback;
}
static int
@@ -5304,8 +5316,7 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp,
}
static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
- struct fib6_info *rt, bool replace,
- bool append)
+ struct fib6_info *rt, bool replace)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_node *fib_node;
@@ -5331,7 +5342,7 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
/* Before creating a new entry, try to append route to an existing
* multipath entry.
*/
- fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, append);
+ fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, replace);
if (fib6_entry) {
err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt);
if (err)
@@ -5339,14 +5350,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
return 0;
}
- /* We received an append event, yet did not find any route to
- * append to.
- */
- if (WARN_ON(append)) {
- err = -EINVAL;
- goto err_fib6_entry_append;
- }
-
fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt);
if (IS_ERR(fib6_entry)) {
err = PTR_ERR(fib6_entry);
@@ -5364,7 +5367,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
err_fib6_node_entry_link:
mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry);
err_fib6_entry_create:
-err_fib6_entry_append:
err_fib6_entry_nexthop_add:
mlxsw_sp_fib_node_put(mlxsw_sp, fib_node);
return err;
@@ -5715,7 +5717,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
struct mlxsw_sp_fib_event_work *fib_work =
container_of(work, struct mlxsw_sp_fib_event_work, work);
struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
- bool replace, append;
+ bool replace;
int err;
rtnl_lock();
@@ -5726,10 +5728,8 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
case FIB_EVENT_ENTRY_APPEND: /* fall through */
case FIB_EVENT_ENTRY_ADD:
replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
- append = fib_work->event == FIB_EVENT_ENTRY_APPEND;
err = mlxsw_sp_router_fib6_add(mlxsw_sp,
- fib_work->fen6_info.rt, replace,
- append);
+ fib_work->fen6_info.rt, replace);
if (err)
mlxsw_sp_router_fib_abort(mlxsw_sp);
mlxsw_sp_rt6_release(fib_work->fen6_info.rt);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 59656fc580df..7b9c82de11cc 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -66,6 +66,12 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
}
+static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
+{
+ return (f6i->fib6_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
+ RTF_GATEWAY;
+}
+
void ip6_route_input(struct sk_buff *skb);
struct dst_entry *ip6_route_input_lookup(struct net *net,
struct net_device *dev,
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1fb2f3118d60..d212738e9d10 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -935,20 +935,19 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
{
struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&rt->fib6_table->tb6_lock));
- enum fib_event_type event = FIB_EVENT_ENTRY_ADD;
- struct fib6_info *iter = NULL, *match = NULL;
+ struct fib6_info *iter = NULL;
struct fib6_info __rcu **ins;
+ struct fib6_info __rcu **fallback_ins = NULL;
int replace = (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_REPLACE));
- int append = (info->nlh &&
- (info->nlh->nlmsg_flags & NLM_F_APPEND));
int add = (!info->nlh ||
(info->nlh->nlmsg_flags & NLM_F_CREATE));
int found = 0;
+ bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
u16 nlflags = NLM_F_EXCL;
int err;
- if (append)
+ if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND))
nlflags |= NLM_F_APPEND;
ins = &fn->leaf;
@@ -970,8 +969,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
nlflags &= ~NLM_F_EXCL;
if (replace) {
- found++;
- break;
+ if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
+ found++;
+ break;
+ }
+ if (rt_can_ecmp)
+ fallback_ins = fallback_ins ?: ins;
+ goto next_iter;
}
if (rt6_duplicate_nexthop(iter, rt)) {
@@ -986,51 +990,71 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
return -EEXIST;
}
-
- /* first route that matches */
- if (!match)
- match = iter;
+ /* If we have the same destination and the same metric,
+ * but not the same gateway, then the route we try to
+ * add is sibling to this route, increment our counter
+ * of siblings, and later we will add our route to the
+ * list.
+ * Only static routes (which don't have flag
+ * RTF_EXPIRES) are used for ECMPv6.
+ *
+ * To avoid long list, we only had siblings if the
+ * route have a gateway.
+ */
+ if (rt_can_ecmp &&
+ rt6_qualify_for_ecmp(iter))
+ rt->fib6_nsiblings++;
}
if (iter->fib6_metric > rt->fib6_metric)
break;
+next_iter:
ins = &iter->fib6_next;
}
+ if (fallback_ins && !found) {
+ /* No ECMP-able route found, replace first non-ECMP one */
+ ins = fallback_ins;
+ iter = rcu_dereference_protected(*ins,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
+ found++;
+ }
+
/* Reset round-robin state, if necessary */
if (ins == &fn->leaf)
fn->rr_ptr = NULL;
/* Link this route to others same route. */
- if (append && match) {
+ if (rt->fib6_nsiblings) {
+ unsigned int fib6_nsiblings;
struct fib6_info *sibling, *temp_sibling;
- if (rt->fib6_flags & RTF_REJECT) {
- NL_SET_ERR_MSG(extack,
- "Can not append a REJECT route");
- return -EINVAL;
- } else if (match->fib6_flags & RTF_REJECT) {
- NL_SET_ERR_MSG(extack,
- "Can not append to a REJECT route");
- return -EINVAL;
+ /* Find the first route that have the same metric */
+ sibling = leaf;
+ while (sibling) {
+ if (sibling->fib6_metric == rt->fib6_metric &&
+ rt6_qualify_for_ecmp(sibling)) {
+ list_add_tail(&rt->fib6_siblings,
+ &sibling->fib6_siblings);
+ break;
+ }
+ sibling = rcu_dereference_protected(sibling->fib6_next,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
}
- event = FIB_EVENT_ENTRY_APPEND;
- rt->fib6_nsiblings = match->fib6_nsiblings;
- list_add_tail(&rt->fib6_siblings, &match->fib6_siblings);
- match->fib6_nsiblings++;
-
/* For each sibling in the list, increment the counter of
* siblings. BUG() if counters does not match, list of siblings
* is broken!
*/
+ fib6_nsiblings = 0;
list_for_each_entry_safe(sibling, temp_sibling,
- &match->fib6_siblings, fib6_siblings) {
+ &rt->fib6_siblings, fib6_siblings) {
sibling->fib6_nsiblings++;
- BUG_ON(sibling->fib6_nsiblings != match->fib6_nsiblings);
+ BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings);
+ fib6_nsiblings++;
}
-
- rt6_multipath_rebalance(match);
+ BUG_ON(fib6_nsiblings != rt->fib6_nsiblings);
+ rt6_multipath_rebalance(temp_sibling);
}
/*
@@ -1043,8 +1067,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
add:
nlflags |= NLM_F_CREATE;
- err = call_fib6_entry_notifiers(info->nl_net, event, rt,
- extack);
+ err = call_fib6_entry_notifiers(info->nl_net,
+ FIB_EVENT_ENTRY_ADD,
+ rt, extack);
if (err)
return err;
@@ -1062,7 +1087,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
}
} else {
- struct fib6_info *tmp;
+ int nsiblings;
if (!found) {
if (add)
@@ -1077,57 +1102,48 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
if (err)
return err;
- /* if route being replaced has siblings, set tmp to
- * last one, otherwise tmp is current route. this is
- * used to set fib6_next for new route
- */
- if (iter->fib6_nsiblings)
- tmp = list_last_entry(&iter->fib6_siblings,
- struct fib6_info,
- fib6_siblings);
- else
- tmp = iter;
-
- /* insert new route */
atomic_inc(&rt->fib6_ref);
rcu_assign_pointer(rt->fib6_node, fn);
- rt->fib6_next = tmp->fib6_next;
+ rt->fib6_next = iter->fib6_next;
rcu_assign_pointer(*ins, rt);
-
if (!info->skip_notify)
inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
if (!(fn->fn_flags & RTN_RTINFO)) {
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
+ nsiblings = iter->fib6_nsiblings;
+ iter->fib6_node = NULL;
+ fib6_purge_rt(iter, fn, info->nl_net);
+ if (rcu_access_pointer(fn->rr_ptr) == iter)
+ fn->rr_ptr = NULL;
+ fib6_info_release(iter);
- /* delete old route */
- rt = iter;
-
- if (rt->fib6_nsiblings) {
- struct fib6_info *tmp;
-
+ if (nsiblings) {
/* Replacing an ECMP route, remove all siblings */
- list_for_each_entry_safe(iter, tmp, &rt->fib6_siblings,
- fib6_siblings) {
- iter->fib6_node = NULL;
- fib6_purge_rt(iter, fn, info->nl_net);
- if (rcu_access_pointer(fn->rr_ptr) == iter)
- fn->rr_ptr = NULL;
- fib6_info_release(iter);
-
- rt->fib6_nsiblings--;
- info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
+ ins = &rt->fib6_next;
+ iter = rcu_dereference_protected(*ins,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
+ while (iter) {
+ if (iter->fib6_metric > rt->fib6_metric)
+ break;
+ if (rt6_qualify_for_ecmp(iter)) {
+ *ins = iter->fib6_next;
+ iter->fib6_node = NULL;
+ fib6_purge_rt(iter, fn, info->nl_net);
+ if (rcu_access_pointer(fn->rr_ptr) == iter)
+ fn->rr_ptr = NULL;
+ fib6_info_release(iter);
+ nsiblings--;
+ info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
+ } else {
+ ins = &iter->fib6_next;
+ }
+ iter = rcu_dereference_protected(*ins,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
}
+ WARN_ON(nsiblings != 0);
}
-
- WARN_ON(rt->fib6_nsiblings != 0);
-
- rt->fib6_node = NULL;
- fib6_purge_rt(rt, fn, info->nl_net);
- if (rcu_access_pointer(fn->rr_ptr) == rt)
- fn->rr_ptr = NULL;
- fib6_info_release(rt);
}
return 0;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 86a0e4333d42..63f99411f0de 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3842,7 +3842,7 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
lockdep_is_held(&rt->fib6_table->tb6_lock));
while (iter) {
if (iter->fib6_metric == rt->fib6_metric &&
- iter->fib6_nsiblings)
+ rt6_qualify_for_ecmp(iter))
return iter;
iter = rcu_dereference_protected(iter->fib6_next,
lockdep_is_held(&rt->fib6_table->tb6_lock));
@@ -4439,7 +4439,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
*/
cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
NLM_F_REPLACE);
- cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_APPEND;
nhn++;
}
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 78245d60d8bc..0f45633bd634 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -740,13 +740,6 @@ ipv6_rt_add()
run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
log_test $? 2 "Attempt to add duplicate route - reject route"
- # iproute2 prepend only sets NLM_F_CREATE
- # - adds a new route; does NOT convert existing route to ECMP
- add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
- run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2"
- check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
- log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)"
-
# route append with same prefix adds a new route
# - iproute2 sets NLM_F_CREATE | NLM_F_APPEND
add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
@@ -754,27 +747,6 @@ ipv6_rt_add()
check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
log_test $? 0 "Append nexthop to existing route - gw"
- add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
- run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
- check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1"
- log_test $? 0 "Append nexthop to existing route - dev only"
-
- # multipath route can not have a nexthop that is a reject route
- add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
- run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64"
- log_test $? 2 "Append nexthop to existing route - reject route"
-
- # reject route can not be converted to multipath route
- run_cmd "$IP -6 ro flush 2001:db8:104::/64"
- run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
- run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2"
- log_test $? 2 "Append nexthop to existing reject route - gw"
-
- run_cmd "$IP -6 ro flush 2001:db8:104::/64"
- run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
- run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
- log_test $? 2 "Append nexthop to existing reject route - dev only"
-
# insert mpath directly
add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
@@ -819,13 +791,6 @@ ipv6_rt_replace_single()
check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
log_test $? 0 "Single path with multipath"
- # single path with reject
- #
- add_initial_route6 "nexthop via 2001:db8:101::2"
- run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
- check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
- log_test $? 0 "Single path with reject route"
-
# single path with single path using MULTIPATH attribute
#
add_initial_route6 "via 2001:db8:101::2"
@@ -873,12 +838,6 @@ ipv6_rt_replace_mpath()
check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
log_test $? 0 "Multipath with single path via multipath attribute"
- # multipath with reject
- add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
- run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
- check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
- log_test $? 0 "Multipath with reject route"
-
# route replace fails - invalid nexthop 1
add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
--
2.11.0
^ permalink raw reply related
* Re: BUG: unable to handle kernel (3)
From: syzbot @ 2018-07-03 21:30 UTC (permalink / raw)
To: akpm, bridge, coreteam, davem, fw, gregkh, hmclauchlan, kadlec,
kstewart, linux-kernel, linux-mm, netdev, netfilter-devel, pablo,
pombredanne, stephen, syzkaller-bugs, tglx
In-Reply-To: <000000000000e46d0a056d4c70ce@google.com>
syzbot has found a reproducer for the following crash on:
HEAD commit: 4ca559bbdeaf kmsan: fix assertions in IRQ entry/exit hooks.
git tree: https://github.com/google/kmsan.git/master
console output: https://syzkaller.appspot.com/x/log.txt?x=13dafb20400000
kernel config: https://syzkaller.appspot.com/x/.config?x=848e40757852af3e
dashboard link: https://syzkaller.appspot.com/bug?extid=adfeaaee641dd4fdac43
compiler: clang version 7.0.0 (trunk 334104)
syzkaller repro:https://syzkaller.appspot.com/x/repro.syz?x=15497384400000
C reproducer: https://syzkaller.appspot.com/x/repro.c?x=123a42a4400000
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+adfeaaee641dd4fdac43@syzkaller.appspotmail.com
RDX: 0000000020000140 RSI: 0000000020000100 RDI: 00000000200000c0
RBP: 0000000000000000 R08: 00000000fffffffc R09: 0000000000000039
R10: 0000000000000311 R11: 0000000000000246 R12: 00007f00bc56bd80
R13: 00000000006dbc38 R14: 0000000000000006 R15: 0079656b5f676962
CPU: 1 PID: 4528 Comm: syz-executor237 Not tainted 4.17.0+ #17
BUG: unable to handle kernel
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
NULL pointer dereference at 0000000000000008
Call Trace:
PGD 800000019f3d5067 P4D 800000019f3d5067
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:113
PUD 19ce9d067
fail_dump lib/fault-inject.c:51 [inline]
should_fail+0x87b/0xab0 lib/fault-inject.c:149
PMD 0
__should_failslab+0x278/0x2a0 mm/failslab.c:32
Oops: 0000 [#1] SMP PTI
should_failslab+0x29/0x70 mm/slab_common.c:1522
Dumping ftrace buffer:
slab_pre_alloc_hook mm/slab.h:423 [inline]
slab_alloc_node mm/slub.c:2679 [inline]
__kmalloc_node+0x22f/0x1200 mm/slub.c:3859
(ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 4533 Comm: syz-executor237 Not tainted 4.17.0+ #17
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:map_vm_area+0x69/0x1f0 mm/vmalloc.c:1353
RSP: 0018:ffff8801c07df8b8 EFLAGS: 00010046
kmalloc_node include/linux/slab.h:554 [inline]
alloc_vmap_area+0x1e6/0x15a0 mm/vmalloc.c:420
RAX: ffffffff81b1e4bc RBX: 0000000000000000 RCX: ffff8801a8e58000
RDX: 0000000000000000 RSI: 8000000000000063 RDI: 0000000000000000
__get_vm_area_node+0x3a6/0x810 mm/vmalloc.c:1410
RBP: ffff8801c07df930 R08: 0000000000000000 R09: 0000000000000000
R10: ffffc900019fffff R11: 0000000000000000 R12: ffffffff8b58d000
get_vm_area_caller+0xdb/0xf0 mm/vmalloc.c:1456
R13: 0000000000000000 R14: 0000000000000008 R15: 0000000000000000
FS: 00007f00bc56c700(0000) GS:ffff88021fc00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000008 CR3: 000000019e7d2000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
kmsan_vmap+0x79/0x1e0 mm/kmsan/kmsan.c:875
Call Trace:
vmap+0x3b2/0x4b0 mm/vmalloc.c:1661
kmsan_vmap+0x137/0x1e0 mm/kmsan/kmsan.c:888
vmap+0x3b2/0x4b0 mm/vmalloc.c:1661
big_key_alloc_buffer+0x638/0xa30 security/keys/big_key.c:188
big_key_preparse+0x20a/0xed0 security/keys/big_key.c:228
big_key_alloc_buffer+0x638/0xa30 security/keys/big_key.c:188
big_key_preparse+0x20a/0xed0 security/keys/big_key.c:228
key_create_or_update+0x7a6/0x1a80 security/keys/key.c:849
__do_sys_add_key security/keys/keyctl.c:122 [inline]
__se_sys_add_key+0x741/0x980 security/keys/keyctl.c:62
key_create_or_update+0x7a6/0x1a80 security/keys/key.c:849
__do_sys_add_key security/keys/keyctl.c:122 [inline]
__se_sys_add_key+0x741/0x980 security/keys/keyctl.c:62
__x64_sys_add_key+0x15d/0x1b0 security/keys/keyctl.c:62
__x64_sys_add_key+0x15d/0x1b0 security/keys/keyctl.c:62
do_syscall_64+0x15b/0x230 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x63/0xe7
do_syscall_64+0x15b/0x230 arch/x86/entry/common.c:287
RIP: 0033:0x445dc9
entry_SYSCALL_64_after_hwframe+0x63/0xe7
RSP: 002b:00007f00bc58cd78 EFLAGS: 00000246
RIP: 0033:0x445dc9
RSP: 002b:00007f00bc56bd78 EFLAGS: 00000246
ORIG_RAX: 00000000000000f8
ORIG_RAX: 00000000000000f8
RAX: ffffffffffffffda RBX: 00000000006dbc24 RCX: 0000000000445dc9
RAX: ffffffffffffffda RBX: 00000000006dbc3c RCX: 0000000000445dc9
RDX: 0000000020000140 RSI: 0000000020000100 RDI: 00000000200000c0
RDX: 0000000020000140 RSI: 0000000020000100 RDI: 00000000200000c0
RBP: 0000000000000000 R08: 00000000fffffffc R09: 0000000000000039
RBP: 0000000000000000 R08: 00000000fffffffc R09: 0000000000000039
R10: 0000000000000311 R11: 0000000000000246 R12: 00007f00bc56bd80
R13: 00000000006dbc38 R14: 0000000000000006 R15: 0079656b5f676962
R10: 0000000000000311 R11: 0000000000000246 R12: 00007f00bc58cd80
Code:
R13: 00000000006dbc20 R14: 0000000000000005 R15: 0079656b5f676962
24
FAULT_INJECTION: forcing a failure.
name failslab, interval 1, probability 0, space 0, times 0
08 48 89 45 a0 41 8b 84 24 90 0c 00 00 89 45 cc 45 8b bc 24 88 0c 00 00 e8
54 fa b3 ff 4d 8d 75 08 48 85 db 0f 85 5b 01 00 00 <49> 8b 45 08 48 89 45
CPU: 1 PID: 4530 Comm: syz-executor237 Not tainted 4.17.0+ #17
a8 4c
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
89
Call Trace:
f7 e8
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x185/0x1d0 lib/dump_stack.c:113
57
fail_dump lib/fault-inject.c:51 [inline]
should_fail+0x87b/0xab0 lib/fault-inject.c:149
bd
__should_failslab+0x278/0x2a0 mm/failslab.c:32
0e 00
should_failslab+0x29/0x70 mm/slab_common.c:1522
4d
slab_pre_alloc_hook mm/slab.h:423 [inline]
slab_alloc_node mm/slub.c:2679 [inline]
__kmalloc_node+0x22f/0x1200 mm/slub.c:3859
8d
75 18
48
RIP: map_vm_area+0x69/0x1f0 mm/vmalloc.c:1353 RSP: ffff8801c07df8b8
kmalloc_node include/linux/slab.h:554 [inline]
alloc_vmap_area+0x1e6/0x15a0 mm/vmalloc.c:420
CR2: 0000000000000008
---[ end trace 6c00f5bb0b95940c ]---
__get_vm_area_node+0x3a6/0x810 mm/vmalloc.c:1410
^ permalink raw reply
* Re: [PATCH bpf] bpf: hash_map: decrement counter on error
From: Daniel Borkmann @ 2018-07-03 21:28 UTC (permalink / raw)
To: Alexei Starovoitov, Mauricio Vasquez; +Cc: Alexei Starovoitov, netdev
In-Reply-To: <20180703202849.dydvuwcc6bcvy57i@ast-mbp.dhcp.thefacebook.com>
On 07/03/2018 10:28 PM, Alexei Starovoitov wrote:
> On Sun, Jul 01, 2018 at 11:33:58AM -0500, Mauricio Vasquez wrote:
>> On 06/30/2018 06:20 PM, Daniel Borkmann wrote:
>>> On 06/29/2018 02:48 PM, Mauricio Vasquez B wrote:
>>>> Decrement the number of elements in the map in case the allocation
>>>> of a new node fails.
>>>>
>>>> Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
>>> Thanks for the fix, Mauricio!
>>>
>>> Could you reply with a Fixes: tag in order to track the commit originally
>>> introducing this bug?
>>
>> Sure Daniel,
>>
>> Fixes: 6c9059817432 ("bpf: pre-allocate hash map elements")
>
> Good catch. Thanks for the fix.
> Acked-by: Alexei Starovoitov <ast@kernel.org>
Applied to bpf, thanks Mauricio!
^ permalink raw reply
* pull-request: bpf-next 2018-07-03
From: Daniel Borkmann @ 2018-07-03 21:18 UTC (permalink / raw)
To: davem; +Cc: daniel, ast, netdev
Hi David,
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Various improvements to bpftool and libbpf, that is, bpftool build
speed improvements, missing BPF program types added for detection
by section name, ability to load programs from '.text' section is
made to work again, and better bash completion handling, from Jakub.
2) Improvements to nfp JIT's map read handling which allows for optimizing
memcpy from map to packet, from Jiong.
3) New BPF sample is added which demonstrates XDP in combination with
bpf_perf_event_output() helper to sample packets on all CPUs, from Toke.
4) Add a new BPF kselftest case for tracking connect(2) BPF hooks
infrastructure in combination with TFO, from Andrey.
5) Extend the XDP/BPF xdp_rxq_info sample code with a cmdline option to
read payload from packet data in order to use it for benchmarking.
Also for '--action XDP_TX' option implement swapping of MAC addresses
to avoid drops on some hardware seen during testing, from Jesper.
Please consider pulling these changes from:
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
Thanks a lot!
----------------------------------------------------------------
The following changes since commit b1a5046b2497e39cea9eb585358f3749442fb3f7:
Merge branch 'Multipath-tests-for-tunnel-devices' (2018-06-27 10:42:13 +0900)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
for you to fetch changes up to 0b9e3d543f9fa6a8abdac04f974176ee02312860:
Merge branch 'bpf-bpftool-libbpf-improvements' (2018-07-01 01:01:52 +0200)
----------------------------------------------------------------
Andrey Ignatov (1):
selftests/bpf: Test sys_connect BPF hooks with TFO
Daniel Borkmann (1):
Merge branch 'bpf-bpftool-libbpf-improvements'
Jakub Kicinski (8):
tools: bpftool: use correct make variable type to improve compilation time
tools: libbpf: add section names for missing program types
tools: libbpf: allow setting ifindex for programs and maps
tools: libbpf: restore the ability to load programs from .text section
tools: libbpf: don't return '.text' as a program for multi-function programs
tools: bpftool: drop unnecessary Author comments
tools: bpftool: add missing --bpffs to completions
tools: bpftool: deal with options upfront
Jesper Dangaard Brouer (2):
samples/bpf: extend xdp_rxq_info to read packet payload
samples/bpf: xdp_rxq_info action XDP_TX must adjust MAC-addrs
Jiong Wang (1):
nfp: bpf: allow source ptr type be map ptr in memcpy optimization
Toke Høiland-Jørgensen (2):
trace_helpers.c: Add helpers to poll multiple perf FDs for events
samples/bpf: Add xdp_sample_pkts example
drivers/net/ethernet/netronome/nfp/bpf/jit.c | 5 +-
samples/bpf/Makefile | 4 +
samples/bpf/xdp_rxq_info_kern.c | 43 +++++++
samples/bpf/xdp_rxq_info_user.c | 45 ++++++-
samples/bpf/xdp_sample_pkts_kern.c | 66 +++++++++++
samples/bpf/xdp_sample_pkts_user.c | 169 +++++++++++++++++++++++++++
tools/bpf/bpftool/Makefile | 2 +-
tools/bpf/bpftool/bash-completion/bpftool | 32 +++--
tools/bpf/bpftool/common.c | 2 -
tools/bpf/bpftool/main.c | 4 +-
tools/bpf/bpftool/main.h | 2 -
tools/bpf/bpftool/map.c | 2 -
tools/bpf/bpftool/prog.c | 4 +-
tools/lib/bpf/libbpf.c | 49 ++++++--
tools/lib/bpf/libbpf.h | 2 +
tools/testing/selftests/bpf/test_sock_addr.c | 37 +++++-
tools/testing/selftests/bpf/trace_helpers.c | 48 +++++++-
tools/testing/selftests/bpf/trace_helpers.h | 4 +
18 files changed, 471 insertions(+), 49 deletions(-)
create mode 100644 samples/bpf/xdp_sample_pkts_kern.c
create mode 100644 samples/bpf/xdp_sample_pkts_user.c
^ permalink raw reply
* [PATCH] isdn: mark expected switch fall-throughs
From: Gustavo A. R. Silva @ 2018-07-03 21:17 UTC (permalink / raw)
To: Paul Bolle, Karsten Keil
Cc: gigaset307x-common, netdev, linux-kernel, Gustavo A. R. Silva
In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Warning level 2 was used: -Wimplicit-fallthrough=2
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
---
drivers/isdn/gigaset/bas-gigaset.c | 3 +++
drivers/isdn/hardware/mISDN/avmfritz.c | 1 +
drivers/isdn/hardware/mISDN/hfcpci.c | 1 +
drivers/isdn/hardware/mISDN/mISDNinfineon.c | 1 +
drivers/isdn/hardware/mISDN/mISDNisar.c | 4 ++++
drivers/isdn/hisax/avm_pci.c | 1 +
drivers/isdn/hisax/callc.c | 1 +
drivers/isdn/hisax/config.c | 1 +
drivers/isdn/hisax/gazel.c | 4 ++++
drivers/isdn/hisax/isar.c | 2 ++
drivers/isdn/hisax/l3_1tr6.c | 1 +
drivers/isdn/hisax/l3dss1.c | 1 +
drivers/isdn/hysdn/hysdn_boot.c | 2 ++
drivers/isdn/i4l/isdn_v110.c | 9 +++++++++
drivers/isdn/mISDN/stack.c | 1 +
15 files changed, 33 insertions(+)
diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index 40c1411..ecdeb89 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -739,6 +739,7 @@ static void read_int_callback(struct urb *urb)
case HD_OPEN_B2CHANNEL_ACK:
++channel;
+ /* fall through */
case HD_OPEN_B1CHANNEL_ACK:
bcs = cs->bcs + channel;
update_basstate(ucs, BS_B1OPEN << channel, 0);
@@ -752,6 +753,7 @@ static void read_int_callback(struct urb *urb)
case HD_CLOSE_B2CHANNEL_ACK:
++channel;
+ /* fall through */
case HD_CLOSE_B1CHANNEL_ACK:
bcs = cs->bcs + channel;
update_basstate(ucs, 0, BS_B1OPEN << channel);
@@ -765,6 +767,7 @@ static void read_int_callback(struct urb *urb)
case HD_B2_FLOW_CONTROL:
++channel;
+ /* fall through */
case HD_B1_FLOW_CONTROL:
bcs = cs->bcs + channel;
atomic_add((l - BAS_NORMFRAME) * BAS_CORRFRAMES,
diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c
index ae2b266..8eb28a8 100644
--- a/drivers/isdn/hardware/mISDN/avmfritz.c
+++ b/drivers/isdn/hardware/mISDN/avmfritz.c
@@ -361,6 +361,7 @@ modehdlc(struct bchannel *bch, int protocol)
switch (protocol) {
case -1: /* used for init */
bch->state = -1;
+ /* fall through */
case ISDN_P_NONE:
if (bch->state == ISDN_P_NONE)
break;
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 34c9387..72a271b 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -1296,6 +1296,7 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol)
case (-1): /* used for init */
bch->state = -1;
bch->nr = bc;
+ /* fall through */
case (ISDN_P_NONE):
if (bch->state == ISDN_P_NONE)
return 0;
diff --git a/drivers/isdn/hardware/mISDN/mISDNinfineon.c b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
index 1fc2906..3e01012 100644
--- a/drivers/isdn/hardware/mISDN/mISDNinfineon.c
+++ b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
@@ -887,6 +887,7 @@ release_card(struct inf_hw *card) {
release_card(card->sc[i]);
card->sc[i] = NULL;
}
+ /* fall through */
default:
pci_disable_device(card->pdev);
pci_set_drvdata(card->pdev, NULL);
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index b791688..386731e 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -972,6 +972,7 @@ isar_pump_statev_fax(struct isar_ch *ch, u8 devt) {
break;
case PCTRL_CMD_FTM:
p1 = 2;
+ /* fall through */
case PCTRL_CMD_FTH:
send_mbox(ch->is, dps | ISAR_HIS_PUMPCTRL,
PCTRL_CMD_SILON, 1, &p1);
@@ -1177,6 +1178,7 @@ setup_pump(struct isar_ch *ch) {
send_mbox(ch->is, dps | ISAR_HIS_PUMPCFG,
PMOD_DTMF, 1, param);
}
+ /* fall through */
case ISDN_P_B_MODEM_ASYNC:
ctrl = PMOD_DATAMODEM;
if (test_bit(FLG_ORIGIN, &ch->bch.Flags)) {
@@ -1268,6 +1270,7 @@ setup_iom2(struct isar_ch *ch) {
case ISDN_P_B_MODEM_ASYNC:
case ISDN_P_B_T30_FAX:
cmsb |= IOM_CTRL_RCV;
+ /* fall through */
case ISDN_P_B_L2DTMF:
if (test_bit(FLG_DTMFSEND, &ch->bch.Flags))
cmsb |= IOM_CTRL_RCV;
@@ -1560,6 +1563,7 @@ isar_l2l1(struct mISDNchannel *ch, struct sk_buff *skb)
ich->is->name, hh->id);
ret = -EINVAL;
}
+ /* fall through */
default:
pr_info("%s: %s unknown prim(%x,%x)\n",
ich->is->name, __func__, hh->prim, hh->id);
diff --git a/drivers/isdn/hisax/avm_pci.c b/drivers/isdn/hisax/avm_pci.c
index a18b605..b161456 100644
--- a/drivers/isdn/hisax/avm_pci.c
+++ b/drivers/isdn/hisax/avm_pci.c
@@ -207,6 +207,7 @@ modehdlc(struct BCState *bcs, int mode, int bc)
bcs->mode = 1;
bcs->channel = bc;
bc = 0;
+ /* fall through */
case (L1_MODE_NULL):
if (bcs->mode == L1_MODE_NULL)
return;
diff --git a/drivers/isdn/hisax/callc.c b/drivers/isdn/hisax/callc.c
index ddec47a..5f43783 100644
--- a/drivers/isdn/hisax/callc.c
+++ b/drivers/isdn/hisax/callc.c
@@ -1369,6 +1369,7 @@ leased_l1l2(struct PStack *st, int pr, void *arg)
case (PH_ACTIVATE | INDICATION):
case (PH_ACTIVATE | CONFIRM):
event = EV_LEASED;
+ /* fall through */
case (PH_DEACTIVATE | INDICATION):
case (PH_DEACTIVATE | CONFIRM):
if (test_bit(FLG_TWO_DCHAN, &chanp->cs->HW_Flags))
diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c
index 7108bdb8..fcc9c46 100644
--- a/drivers/isdn/hisax/config.c
+++ b/drivers/isdn/hisax/config.c
@@ -1843,6 +1843,7 @@ static void hisax_b_l2l1(struct PStack *st, int pr, void *arg)
case PH_DEACTIVATE | REQUEST:
test_and_clear_bit(BC_FLG_BUSY, &bcs->Flag);
skb_queue_purge(&bcs->squeue);
+ /* fall through */
default:
B_L2L1(b_if, pr, arg);
break;
diff --git a/drivers/isdn/hisax/gazel.c b/drivers/isdn/hisax/gazel.c
index 35c6df6..a6d8af0 100644
--- a/drivers/isdn/hisax/gazel.c
+++ b/drivers/isdn/hisax/gazel.c
@@ -108,6 +108,7 @@ ReadISAC(struct IsdnCardState *cs, u_char offset)
switch (cs->subtyp) {
case R647:
off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+ /* fall through */
case R685:
return (readreg(cs->hw.gazel.isac, off2));
case R753:
@@ -125,6 +126,7 @@ WriteISAC(struct IsdnCardState *cs, u_char offset, u_char value)
switch (cs->subtyp) {
case R647:
off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+ /* fall through */
case R685:
writereg(cs->hw.gazel.isac, off2, value);
break;
@@ -203,6 +205,7 @@ ReadHSCX(struct IsdnCardState *cs, int hscx, u_char offset)
switch (cs->subtyp) {
case R647:
off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+ /* fall through */
case R685:
return (readreg(cs->hw.gazel.hscx[hscx], off2));
case R753:
@@ -220,6 +223,7 @@ WriteHSCX(struct IsdnCardState *cs, int hscx, u_char offset, u_char value)
switch (cs->subtyp) {
case R647:
off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+ /* fall through */
case R685:
writereg(cs->hw.gazel.hscx[hscx], off2, value);
break;
diff --git a/drivers/isdn/hisax/isar.c b/drivers/isdn/hisax/isar.c
index d01ff11..82c1879 100644
--- a/drivers/isdn/hisax/isar.c
+++ b/drivers/isdn/hisax/isar.c
@@ -1089,6 +1089,7 @@ isar_pump_statev_fax(struct BCState *bcs, u_char devt) {
break;
case PCTRL_CMD_FTM:
p1 = 2;
+ /* fall through */
case PCTRL_CMD_FTH:
sendmsg(cs, dps | ISAR_HIS_PUMPCTRL,
PCTRL_CMD_SILON, 1, &p1);
@@ -1097,6 +1098,7 @@ isar_pump_statev_fax(struct BCState *bcs, u_char devt) {
case PCTRL_CMD_FRM:
if (frm_extra_delay)
mdelay(frm_extra_delay);
+ /* fall through */
case PCTRL_CMD_FRH:
p1 = bcs->hw.isar.mod = bcs->hw.isar.newmod;
bcs->hw.isar.newmod = 0;
diff --git a/drivers/isdn/hisax/l3_1tr6.c b/drivers/isdn/hisax/l3_1tr6.c
index da0a1c6..98f60d1 100644
--- a/drivers/isdn/hisax/l3_1tr6.c
+++ b/drivers/isdn/hisax/l3_1tr6.c
@@ -88,6 +88,7 @@ l3_1tr6_setup_req(struct l3_process *pc, u_char pr, void *arg)
break;
case 'C':
channel = 0x08;
+ /* fall through */
case 'P':
channel |= 0x80;
teln++;
diff --git a/drivers/isdn/hisax/l3dss1.c b/drivers/isdn/hisax/l3dss1.c
index 18a3484..368d152 100644
--- a/drivers/isdn/hisax/l3dss1.c
+++ b/drivers/isdn/hisax/l3dss1.c
@@ -1282,6 +1282,7 @@ l3dss1_setup_req(struct l3_process *pc, u_char pr,
switch (0x5f & *teln) {
case 'C':
channel = 0x08;
+ /* fall through */
case 'P':
channel |= 0x80;
teln++;
diff --git a/drivers/isdn/hysdn/hysdn_boot.c b/drivers/isdn/hysdn/hysdn_boot.c
index 4a04253..ba177c3 100644
--- a/drivers/isdn/hysdn/hysdn_boot.c
+++ b/drivers/isdn/hysdn/hysdn_boot.c
@@ -99,6 +99,7 @@ pof_handle_data(hysdn_card *card, int datlen)
case TAG_CBOOTDTA:
DecryptBuf(boot, datlen); /* we need to encrypt the buffer */
+ /* fall through */
case TAG_BOOTDTA:
if (card->debug_flags & LOG_POF_RECORD)
hysdn_addlog(card, "POF got %s len=%d offs=0x%lx",
@@ -137,6 +138,7 @@ pof_handle_data(hysdn_card *card, int datlen)
case TAG_CABSDATA:
DecryptBuf(boot, datlen); /* we need to encrypt the buffer */
+ /* fall through */
case TAG_ABSDATA:
if (card->debug_flags & LOG_POF_RECORD)
hysdn_addlog(card, "POF got %s len=%d offs=0x%lx",
diff --git a/drivers/isdn/i4l/isdn_v110.c b/drivers/isdn/i4l/isdn_v110.c
index 8b74ce4..2a5f666 100644
--- a/drivers/isdn/i4l/isdn_v110.c
+++ b/drivers/isdn/i4l/isdn_v110.c
@@ -354,6 +354,7 @@ EncodeMatrix(unsigned char *buf, int len, unsigned char *m, int mlen)
printk(KERN_WARNING "isdn_v110 (EncodeMatrix): buffer full!\n");
return line;
}
+ /* else: fall through */
case 128:
m[line] = 128; /* leftmost -> set byte to 1000000 */
mbit = 64; /* current bit in the matrix line */
@@ -386,20 +387,28 @@ EncodeMatrix(unsigned char *buf, int len, unsigned char *m, int mlen)
switch (++line % 10) {
case 1:
m[line++] = 0xfe;
+ /* fall through */
case 2:
m[line++] = 0xfe;
+ /* fall through */
case 3:
m[line++] = 0xfe;
+ /* fall through */
case 4:
m[line++] = 0xfe;
+ /* fall through */
case 5:
m[line++] = 0xbf;
+ /* fall through */
case 6:
m[line++] = 0xfe;
+ /* fall through */
case 7:
m[line++] = 0xfe;
+ /* fall through */
case 8:
m[line++] = 0xfe;
+ /* fall through */
case 9:
m[line++] = 0xfe;
}
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index 422dced..d97c6dd 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -539,6 +539,7 @@ create_l2entity(struct mISDNdevice *dev, struct mISDNchannel *ch,
rq.protocol = ISDN_P_NT_S0;
if (dev->Dprotocols & (1 << ISDN_P_NT_E1))
rq.protocol = ISDN_P_NT_E1;
+ /* fall through */
case ISDN_P_LAPD_TE:
ch->recv = mISDN_queue_message;
ch->peer = &dev->D.st->own;
--
2.7.4
^ 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