summaryrefslogtreecommitdiff
path: root/net/sched/sch_netem.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-08-15 15:04:25 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-08-15 15:04:25 -0700
commit9a76aba02a37718242d7cdc294f0a3901928aa57 (patch)
tree2040d038f85d2120f21af83b0793efd5af1864e3 /net/sched/sch_netem.c
parent0a957467c5fd46142bc9c52758ffc552d4c5e2f7 (diff)
parent26a1ccc6c117be8e33e0410fce8c5298b0015b99 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Highlights: - Gustavo A. R. Silva keeps working on the implicit switch fallthru changes. - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From Luca Coelho. - Re-enable ASPM in r8169, from Kai-Heng Feng. - Add virtual XFRM interfaces, which avoids all of the limitations of existing IPSEC tunnels. From Steffen Klassert. - Convert GRO over to use a hash table, so that when we have many flows active we don't traverse a long list during accumluation. - Many new self tests for routing, TC, tunnels, etc. Too many contributors to mention them all, but I'm really happy to keep seeing this stuff. - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu. - Lots of cleanups and fixes in L2TP code from Guillaume Nault. - Add IPSEC offload support to netdevsim, from Shannon Nelson. - Add support for slotting with non-uniform distribution to netem packet scheduler, from Yousuk Seung. - Add UDP GSO support to mlx5e, from Boris Pismenny. - Support offloading of Team LAG in NFP, from John Hurley. - Allow to configure TX queue selection based upon RX queue, from Amritha Nambiar. - Support ethtool ring size configuration in aquantia, from Anton Mikaev. - Support DSCP and flowlabel per-transport in SCTP, from Xin Long. - Support list based batching and stack traversal of SKBs, this is very exciting work. From Edward Cree. - Busyloop optimizations in vhost_net, from Toshiaki Makita. - Introduce the ETF qdisc, which allows time based transmissions. IGB can offload this in hardware. From Vinicius Costa Gomes. - Add parameter support to devlink, from Moshe Shemesh. - Several multiplication and division optimizations for BPF JIT in nfp driver, from Jiong Wang. - Lots of prepatory work to make more of the packet scheduler layer lockless, when possible, from Vlad Buslov. - Add ACK filter and NAT awareness to sch_cake packet scheduler, from Toke Høiland-Jørgensen. - Support regions and region snapshots in devlink, from Alex Vesker. - Allow to attach XDP programs to both HW and SW at the same time on a given device, with initial support in nfp. From Jakub Kicinski. - Add TLS RX offload and support in mlx5, from Ilya Lesokhin. - Use PHYLIB in r8169 driver, from Heiner Kallweit. - All sorts of changes to support Spectrum 2 in mlxsw driver, from Ido Schimmel. - PTP support in mv88e6xxx DSA driver, from Andrew Lunn. - Make TCP_USER_TIMEOUT socket option more accurate, from Jon Maxwell. - Support for templates in packet scheduler classifier, from Jiri Pirko. - IPV6 support in RDS, from Ka-Cheong Poon. - Native tproxy support in nf_tables, from Máté Eckl. - Maintain IP fragment queue in an rbtree, but optimize properly for in-order frags. From Peter Oskolkov. - Improvde handling of ACKs on hole repairs, from Yuchung Cheng" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits) bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT" hv/netvsc: Fix NULL dereference at single queue mode fallback net: filter: mark expected switch fall-through xen-netfront: fix warn message as irq device name has '/' cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0 net: dsa: mv88e6xxx: missing unlock on error path rds: fix building with IPV6=m inet/connection_sock: prefer _THIS_IP_ to current_text_addr net: dsa: mv88e6xxx: bitwise vs logical bug net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd() ieee802154: hwsim: using right kind of iteration net: hns3: Add vlan filter setting by ethtool command -K net: hns3: Set tx ring' tc info when netdev is up net: hns3: Remove tx ring BD len register in hns3_enet net: hns3: Fix desc num set to default when setting channel net: hns3: Fix for phy link issue when using marvell phy driver net: hns3: Fix for information of phydev lost problem when down/up net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero net: hns3: Add support for serdes loopback selftest bnxt_en: take coredump_record structure off stack ...
Diffstat (limited to 'net/sched/sch_netem.c')
-rw-r--r--net/sched/sch_netem.c73
1 files changed, 49 insertions, 24 deletions
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 7d6801fc5340..ad18a2052416 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -68,6 +68,11 @@
Fabio Ludovici <fabio.ludovici at yahoo.it>
*/
+struct disttable {
+ u32 size;
+ s16 table[0];
+};
+
struct netem_sched_data {
/* internal t(ime)fifo qdisc uses t_root and sch->limit */
struct rb_root t_root;
@@ -99,10 +104,7 @@ struct netem_sched_data {
u32 rho;
} delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor;
- struct disttable {
- u32 size;
- s16 table[0];
- } *delay_dist;
+ struct disttable *delay_dist;
enum {
CLG_RANDOM,
@@ -142,6 +144,7 @@ struct netem_sched_data {
s32 bytes_left;
} slot;
+ struct disttable *slot_dist;
};
/* Time stamp put into socket buffer control block
@@ -180,7 +183,7 @@ static u32 get_crandom(struct crndstate *state)
u64 value, rho;
unsigned long answer;
- if (state->rho == 0) /* no correlation */
+ if (!state || state->rho == 0) /* no correlation */
return prandom_u32();
value = prandom_u32();
@@ -601,10 +604,19 @@ finish_segs:
static void get_slot_next(struct netem_sched_data *q, u64 now)
{
- q->slot.slot_next = now + q->slot_config.min_delay +
- (prandom_u32() *
- (q->slot_config.max_delay -
- q->slot_config.min_delay) >> 32);
+ s64 next_delay;
+
+ if (!q->slot_dist)
+ next_delay = q->slot_config.min_delay +
+ (prandom_u32() *
+ (q->slot_config.max_delay -
+ q->slot_config.min_delay) >> 32);
+ else
+ next_delay = tabledist(q->slot_config.dist_delay,
+ (s32)(q->slot_config.dist_jitter),
+ NULL, q->slot_dist);
+
+ q->slot.slot_next = now + next_delay;
q->slot.packets_left = q->slot_config.max_packets;
q->slot.bytes_left = q->slot_config.max_bytes;
}
@@ -721,9 +733,9 @@ static void dist_free(struct disttable *d)
* signed 16 bit values.
*/
-static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
+static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
+ const struct nlattr *attr)
{
- struct netem_sched_data *q = qdisc_priv(sch);
size_t n = nla_len(attr)/sizeof(__s16);
const __s16 *data = nla_data(attr);
spinlock_t *root_lock;
@@ -744,7 +756,7 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
root_lock = qdisc_root_sleeping_lock(sch);
spin_lock_bh(root_lock);
- swap(q->delay_dist, d);
+ swap(*tbl, d);
spin_unlock_bh(root_lock);
dist_free(d);
@@ -762,7 +774,8 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr)
q->slot_config.max_bytes = INT_MAX;
q->slot.packets_left = q->slot_config.max_packets;
q->slot.bytes_left = q->slot_config.max_bytes;
- if (q->slot_config.min_delay | q->slot_config.max_delay)
+ if (q->slot_config.min_delay | q->slot_config.max_delay |
+ q->slot_config.dist_jitter)
q->slot.slot_next = ktime_get_ns();
else
q->slot.slot_next = 0;
@@ -926,16 +939,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
}
if (tb[TCA_NETEM_DELAY_DIST]) {
- ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]);
- if (ret) {
- /* recover clg and loss_model, in case of
- * q->clg and q->loss_model were modified
- * in get_loss_clg()
- */
- q->clg = old_clg;
- q->loss_model = old_loss_model;
- return ret;
- }
+ ret = get_dist_table(sch, &q->delay_dist,
+ tb[TCA_NETEM_DELAY_DIST]);
+ if (ret)
+ goto get_table_failure;
+ }
+
+ if (tb[TCA_NETEM_SLOT_DIST]) {
+ ret = get_dist_table(sch, &q->slot_dist,
+ tb[TCA_NETEM_SLOT_DIST]);
+ if (ret)
+ goto get_table_failure;
}
sch->limit = qopt->limit;
@@ -983,6 +997,15 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
get_slot(q, tb[TCA_NETEM_SLOT]);
return ret;
+
+get_table_failure:
+ /* recover clg and loss_model, in case of
+ * q->clg and q->loss_model were modified
+ * in get_loss_clg()
+ */
+ q->clg = old_clg;
+ q->loss_model = old_loss_model;
+ return ret;
}
static int netem_init(struct Qdisc *sch, struct nlattr *opt,
@@ -1011,6 +1034,7 @@ static void netem_destroy(struct Qdisc *sch)
if (q->qdisc)
qdisc_destroy(q->qdisc);
dist_free(q->delay_dist);
+ dist_free(q->slot_dist);
}
static int dump_loss_model(const struct netem_sched_data *q,
@@ -1127,7 +1151,8 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
if (dump_loss_model(q, skb) != 0)
goto nla_put_failure;
- if (q->slot_config.min_delay | q->slot_config.max_delay) {
+ if (q->slot_config.min_delay | q->slot_config.max_delay |
+ q->slot_config.dist_jitter) {
slot = q->slot_config;
if (slot.max_packets == INT_MAX)
slot.max_packets = 0;