summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-07-11 10:55:49 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-11 10:55:49 -0700
commit237f83dfbe668443b5e31c3c7576125871cca674 (patch)
tree11848a8d0aa414a1d3ce2024e181071b1d9dea08 /lib
parent8f6ccf6159aed1f04c6d179f61f6fb2691261e84 (diff)
parent1ff2f0fa450ea4e4f87793d9ed513098ec6e12be (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Some highlights from this development cycle: 1) Big refactoring of ipv6 route and neigh handling to support nexthop objects configurable as units from userspace. From David Ahern. 2) Convert explored_states in BPF verifier into a hash table, significantly decreased state held for programs with bpf2bpf calls, from Alexei Starovoitov. 3) Implement bpf_send_signal() helper, from Yonghong Song. 4) Various classifier enhancements to mvpp2 driver, from Maxime Chevallier. 5) Add aRFS support to hns3 driver, from Jian Shen. 6) Fix use after free in inet frags by allocating fqdirs dynamically and reworking how rhashtable dismantle occurs, from Eric Dumazet. 7) Add act_ctinfo packet classifier action, from Kevin Darbyshire-Bryant. 8) Add TFO key backup infrastructure, from Jason Baron. 9) Remove several old and unused ISDN drivers, from Arnd Bergmann. 10) Add devlink notifications for flash update status to mlxsw driver, from Jiri Pirko. 11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski. 12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes. 13) Various enhancements to ipv6 flow label handling, from Eric Dumazet and Willem de Bruijn. 14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van der Merwe, and others. 15) Various improvements to axienet driver including converting it to phylink, from Robert Hancock. 16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean. 17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana Radulescu. 18) Add devlink health reporting to mlx5, from Moshe Shemesh. 19) Convert stmmac over to phylink, from Jose Abreu. 20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from Shalom Toledo. 21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera. 22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel. 23) Track spill/fill of constants in BPF verifier, from Alexei Starovoitov. 24) Support bounded loops in BPF, from Alexei Starovoitov. 25) Various page_pool API fixes and improvements, from Jesper Dangaard Brouer. 26) Just like ipv4, support ref-countless ipv6 route handling. From Wei Wang. 27) Support VLAN offloading in aquantia driver, from Igor Russkikh. 28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy. 29) Add flower GRE encap/decap support to nfp driver, from Pieter Jansen van Vuuren. 30) Protect against stack overflow when using act_mirred, from John Hurley. 31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen. 32) Use page_pool API in netsec driver, Ilias Apalodimas. 33) Add Google gve network driver, from Catherine Sullivan. 34) More indirect call avoidance, from Paolo Abeni. 35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan. 36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek. 37) Add MPLS manipulation actions to TC, from John Hurley. 38) Add sending a packet to connection tracking from TC actions, and then allow flower classifier matching on conntrack state. From Paul Blakey. 39) Netfilter hw offload support, from Pablo Neira Ayuso" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits) net/mlx5e: Return in default case statement in tx_post_resync_params mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync(). net: dsa: add support for BRIDGE_MROUTER attribute pkt_sched: Include const.h net: netsec: remove static declaration for netsec_set_tx_de() net: netsec: remove superfluous if statement netfilter: nf_tables: add hardware offload support net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload net: flow_offload: add flow_block_cb_is_busy() and use it net: sched: remove tcf block API drivers: net: use flow block API net: sched: use flow block API net: flow_offload: add flow_block_cb_{priv, incref, decref}() net: flow_offload: add list handling functions net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free() net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_* net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND net: flow_offload: add flow_block_cb_setup_simple() net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC ...
Diffstat (limited to 'lib')
-rw-r--r--lib/Kconfig8
-rw-r--r--lib/Kconfig.debug9
-rw-r--r--lib/Makefile2
-rw-r--r--lib/dim/Makefile9
-rw-r--r--lib/dim/dim.c83
-rw-r--r--lib/dim/net_dim.c190
-rw-r--r--lib/objagg.c6
-rw-r--r--lib/test_blackhole_dev.c100
8 files changed, 403 insertions, 4 deletions
diff --git a/lib/Kconfig b/lib/Kconfig
index 8c8eefc5e54c..52a7b2e6fb74 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -562,6 +562,14 @@ config SIGNATURE
Digital signature verification. Currently only RSA is supported.
Implementation is done using GnuPG MPI library
+config DIMLIB
+ bool "DIM library"
+ default y
+ help
+ Dynamic Interrupt Moderation library.
+ Implements an algorithm for dynamically change CQ modertion values
+ according to run time performance.
+
#
# libfdt files, only selected if needed.
#
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b0c5f6ca9a5c..d4c8c9323aa4 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1929,6 +1929,15 @@ config TEST_BPF
If unsure, say N.
+config TEST_BLACKHOLE_DEV
+ tristate "Test blackhole netdev functionality"
+ depends on m && NET
+ help
+ This builds the "test_blackhole_dev" module that validates the
+ data path through this blackhole netdev.
+
+ If unsure, say N.
+
config FIND_BIT_BENCHMARK
tristate "Test find_bit functions"
help
diff --git a/lib/Makefile b/lib/Makefile
index d3daedf93c5a..fdd56bc219b8 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -91,6 +91,7 @@ obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o
obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o
obj-$(CONFIG_TEST_STACKINIT) += test_stackinit.o
+obj-$(CONFIG_TEST_BLACKHOLE_DEV) += test_blackhole_dev.o
obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/
@@ -202,6 +203,7 @@ obj-$(CONFIG_GLOB) += glob.o
obj-$(CONFIG_GLOB_SELFTEST) += globtest.o
obj-$(CONFIG_MPILIB) += mpi/
+obj-$(CONFIG_DIMLIB) += dim/
obj-$(CONFIG_SIGNATURE) += digsig.o
lib-$(CONFIG_CLZ_TAB) += clz_tab.o
diff --git a/lib/dim/Makefile b/lib/dim/Makefile
new file mode 100644
index 000000000000..160afe288df0
--- /dev/null
+++ b/lib/dim/Makefile
@@ -0,0 +1,9 @@
+#
+# DIM Dynamic Interrupt Moderation library
+#
+
+obj-$(CONFIG_DIMLIB) = net_dim.o
+
+net_dim-y = \
+ dim.o \
+ net_dim.o
diff --git a/lib/dim/dim.c b/lib/dim/dim.c
new file mode 100644
index 000000000000..439d641ec796
--- /dev/null
+++ b/lib/dim/dim.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2019, Mellanox Technologies inc. All rights reserved.
+ */
+
+#include <linux/dim.h>
+
+bool dim_on_top(struct dim *dim)
+{
+ switch (dim->tune_state) {
+ case DIM_PARKING_ON_TOP:
+ case DIM_PARKING_TIRED:
+ return true;
+ case DIM_GOING_RIGHT:
+ return (dim->steps_left > 1) && (dim->steps_right == 1);
+ default: /* DIM_GOING_LEFT */
+ return (dim->steps_right > 1) && (dim->steps_left == 1);
+ }
+}
+EXPORT_SYMBOL(dim_on_top);
+
+void dim_turn(struct dim *dim)
+{
+ switch (dim->tune_state) {
+ case DIM_PARKING_ON_TOP:
+ case DIM_PARKING_TIRED:
+ break;
+ case DIM_GOING_RIGHT:
+ dim->tune_state = DIM_GOING_LEFT;
+ dim->steps_left = 0;
+ break;
+ case DIM_GOING_LEFT:
+ dim->tune_state = DIM_GOING_RIGHT;
+ dim->steps_right = 0;
+ break;
+ }
+}
+EXPORT_SYMBOL(dim_turn);
+
+void dim_park_on_top(struct dim *dim)
+{
+ dim->steps_right = 0;
+ dim->steps_left = 0;
+ dim->tired = 0;
+ dim->tune_state = DIM_PARKING_ON_TOP;
+}
+EXPORT_SYMBOL(dim_park_on_top);
+
+void dim_park_tired(struct dim *dim)
+{
+ dim->steps_right = 0;
+ dim->steps_left = 0;
+ dim->tune_state = DIM_PARKING_TIRED;
+}
+EXPORT_SYMBOL(dim_park_tired);
+
+void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
+ struct dim_stats *curr_stats)
+{
+ /* u32 holds up to 71 minutes, should be enough */
+ u32 delta_us = ktime_us_delta(end->time, start->time);
+ u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr);
+ u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr,
+ start->byte_ctr);
+ u32 ncomps = BIT_GAP(BITS_PER_TYPE(u32), end->comp_ctr,
+ start->comp_ctr);
+
+ if (!delta_us)
+ return;
+
+ curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us);
+ curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us);
+ curr_stats->epms = DIV_ROUND_UP(DIM_NEVENTS * USEC_PER_MSEC,
+ delta_us);
+ curr_stats->cpms = DIV_ROUND_UP(ncomps * USEC_PER_MSEC, delta_us);
+ if (curr_stats->epms != 0)
+ curr_stats->cpe_ratio =
+ (curr_stats->cpms * 100) / curr_stats->epms;
+ else
+ curr_stats->cpe_ratio = 0;
+
+}
+EXPORT_SYMBOL(dim_calc_stats);
diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c
new file mode 100644
index 000000000000..5bcc902c5388
--- /dev/null
+++ b/lib/dim/net_dim.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2018, Mellanox Technologies inc. All rights reserved.
+ */
+
+#include <linux/dim.h>
+
+struct dim_cq_moder
+net_dim_get_rx_moderation(u8 cq_period_mode, int ix)
+{
+ struct dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix];
+
+ cq_moder.cq_period_mode = cq_period_mode;
+ return cq_moder;
+}
+EXPORT_SYMBOL(net_dim_get_rx_moderation);
+
+struct dim_cq_moder
+net_dim_get_def_rx_moderation(u8 cq_period_mode)
+{
+ u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
+ NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE;
+
+ return net_dim_get_rx_moderation(cq_period_mode, profile_ix);
+}
+EXPORT_SYMBOL(net_dim_get_def_rx_moderation);
+
+struct dim_cq_moder
+net_dim_get_tx_moderation(u8 cq_period_mode, int ix)
+{
+ struct dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix];
+
+ cq_moder.cq_period_mode = cq_period_mode;
+ return cq_moder;
+}
+EXPORT_SYMBOL(net_dim_get_tx_moderation);
+
+struct dim_cq_moder
+net_dim_get_def_tx_moderation(u8 cq_period_mode)
+{
+ u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
+ NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE;
+
+ return net_dim_get_tx_moderation(cq_period_mode, profile_ix);
+}
+EXPORT_SYMBOL(net_dim_get_def_tx_moderation);
+
+static int net_dim_step(struct dim *dim)
+{
+ if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2))
+ return DIM_TOO_TIRED;
+
+ switch (dim->tune_state) {
+ case DIM_PARKING_ON_TOP:
+ case DIM_PARKING_TIRED:
+ break;
+ case DIM_GOING_RIGHT:
+ if (dim->profile_ix == (NET_DIM_PARAMS_NUM_PROFILES - 1))
+ return DIM_ON_EDGE;
+ dim->profile_ix++;
+ dim->steps_right++;
+ break;
+ case DIM_GOING_LEFT:
+ if (dim->profile_ix == 0)
+ return DIM_ON_EDGE;
+ dim->profile_ix--;
+ dim->steps_left++;
+ break;
+ }
+
+ dim->tired++;
+ return DIM_STEPPED;
+}
+
+static void net_dim_exit_parking(struct dim *dim)
+{
+ dim->tune_state = dim->profile_ix ? DIM_GOING_LEFT : DIM_GOING_RIGHT;
+ net_dim_step(dim);
+}
+
+static int net_dim_stats_compare(struct dim_stats *curr,
+ struct dim_stats *prev)
+{
+ if (!prev->bpms)
+ return curr->bpms ? DIM_STATS_BETTER : DIM_STATS_SAME;
+
+ if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms))
+ return (curr->bpms > prev->bpms) ? DIM_STATS_BETTER :
+ DIM_STATS_WORSE;
+
+ if (!prev->ppms)
+ return curr->ppms ? DIM_STATS_BETTER :
+ DIM_STATS_SAME;
+
+ if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms))
+ return (curr->ppms > prev->ppms) ? DIM_STATS_BETTER :
+ DIM_STATS_WORSE;
+
+ if (!prev->epms)
+ return DIM_STATS_SAME;
+
+ if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms))
+ return (curr->epms < prev->epms) ? DIM_STATS_BETTER :
+ DIM_STATS_WORSE;
+
+ return DIM_STATS_SAME;
+}
+
+static bool net_dim_decision(struct dim_stats *curr_stats, struct dim *dim)
+{
+ int prev_state = dim->tune_state;
+ int prev_ix = dim->profile_ix;
+ int stats_res;
+ int step_res;
+
+ switch (dim->tune_state) {
+ case DIM_PARKING_ON_TOP:
+ stats_res = net_dim_stats_compare(curr_stats,
+ &dim->prev_stats);
+ if (stats_res != DIM_STATS_SAME)
+ net_dim_exit_parking(dim);
+ break;
+
+ case DIM_PARKING_TIRED:
+ dim->tired--;
+ if (!dim->tired)
+ net_dim_exit_parking(dim);
+ break;
+
+ case DIM_GOING_RIGHT:
+ case DIM_GOING_LEFT:
+ stats_res = net_dim_stats_compare(curr_stats,
+ &dim->prev_stats);
+ if (stats_res != DIM_STATS_BETTER)
+ dim_turn(dim);
+
+ if (dim_on_top(dim)) {
+ dim_park_on_top(dim);
+ break;
+ }
+
+ step_res = net_dim_step(dim);
+ switch (step_res) {
+ case DIM_ON_EDGE:
+ dim_park_on_top(dim);
+ break;
+ case DIM_TOO_TIRED:
+ dim_park_tired(dim);
+ break;
+ }
+
+ break;
+ }
+
+ if (prev_state != DIM_PARKING_ON_TOP ||
+ dim->tune_state != DIM_PARKING_ON_TOP)
+ dim->prev_stats = *curr_stats;
+
+ return dim->profile_ix != prev_ix;
+}
+
+void net_dim(struct dim *dim, struct dim_sample end_sample)
+{
+ struct dim_stats curr_stats;
+ u16 nevents;
+
+ switch (dim->state) {
+ case DIM_MEASURE_IN_PROGRESS:
+ nevents = BIT_GAP(BITS_PER_TYPE(u16),
+ end_sample.event_ctr,
+ dim->start_sample.event_ctr);
+ if (nevents < DIM_NEVENTS)
+ break;
+ dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats);
+ if (net_dim_decision(&curr_stats, dim)) {
+ dim->state = DIM_APPLY_NEW_PROFILE;
+ schedule_work(&dim->work);
+ break;
+ }
+ /* fall through */
+ case DIM_START_MEASURE:
+ dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr,
+ end_sample.byte_ctr, &dim->start_sample);
+ dim->state = DIM_MEASURE_IN_PROGRESS;
+ break;
+ case DIM_APPLY_NEW_PROFILE:
+ break;
+ }
+}
+EXPORT_SYMBOL(net_dim);
diff --git a/lib/objagg.c b/lib/objagg.c
index 576be22e86de..55621fb82e0a 100644
--- a/lib/objagg.c
+++ b/lib/objagg.c
@@ -605,12 +605,10 @@ const struct objagg_stats *objagg_stats_get(struct objagg *objagg)
{
struct objagg_stats *objagg_stats;
struct objagg_obj *objagg_obj;
- size_t alloc_size;
int i;
- alloc_size = sizeof(*objagg_stats) +
- sizeof(objagg_stats->stats_info[0]) * objagg->obj_count;
- objagg_stats = kzalloc(alloc_size, GFP_KERNEL);
+ objagg_stats = kzalloc(struct_size(objagg_stats, stats_info,
+ objagg->obj_count), GFP_KERNEL);
if (!objagg_stats)
return ERR_PTR(-ENOMEM);
diff --git a/lib/test_blackhole_dev.c b/lib/test_blackhole_dev.c
new file mode 100644
index 000000000000..4c40580a99a3
--- /dev/null
+++ b/lib/test_blackhole_dev.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This module tests the blackhole_dev that is created during the
+ * net subsystem initialization. The test this module performs is
+ * by injecting an skb into the stack with skb->dev as the
+ * blackhole_dev and expects kernel to behave in a sane manner
+ * (in other words, *not crash*)!
+ *
+ * Copyright (c) 2018, Mahesh Bandewar <maheshb@google.com>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/udp.h>
+#include <linux/ipv6.h>
+
+#include <net/dst.h>
+
+#define SKB_SIZE 256
+#define HEAD_SIZE (14+40+8) /* Ether + IPv6 + UDP */
+#define TAIL_SIZE 32 /* random tail-room */
+
+#define UDP_PORT 1234
+
+static int __init test_blackholedev_init(void)
+{
+ struct ipv6hdr *ip6h;
+ struct sk_buff *skb;
+ struct ethhdr *ethh;
+ struct udphdr *uh;
+ int data_len;
+ int ret;
+
+ skb = alloc_skb(SKB_SIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ /* Reserve head-room for the headers */
+ skb_reserve(skb, HEAD_SIZE);
+
+ /* Add data to the skb */
+ data_len = SKB_SIZE - (HEAD_SIZE + TAIL_SIZE);
+ memset(__skb_put(skb, data_len), 0xf, data_len);
+
+ /* Add protocol data */
+ /* (Transport) UDP */
+ uh = (struct udphdr *)skb_push(skb, sizeof(struct udphdr));
+ skb_set_transport_header(skb, 0);
+ uh->source = uh->dest = htons(UDP_PORT);
+ uh->len = htons(data_len);
+ uh->check = 0;
+ /* (Network) IPv6 */
+ ip6h = (struct ipv6hdr *)skb_push(skb, sizeof(struct ipv6hdr));
+ skb_set_network_header(skb, 0);
+ ip6h->hop_limit = 32;
+ ip6h->payload_len = data_len + sizeof(struct udphdr);
+ ip6h->nexthdr = IPPROTO_UDP;
+ ip6h->saddr = in6addr_loopback;
+ ip6h->daddr = in6addr_loopback;
+ /* Ether */
+ ethh = (struct ethhdr *)skb_push(skb, sizeof(struct ethhdr));
+ skb_set_mac_header(skb, 0);
+
+ skb->protocol = htons(ETH_P_IPV6);
+ skb->pkt_type = PACKET_HOST;
+ skb->dev = blackhole_netdev;
+
+ /* Now attempt to send the packet */
+ ret = dev_queue_xmit(skb);
+
+ switch (ret) {
+ case NET_XMIT_SUCCESS:
+ pr_warn("dev_queue_xmit() returned NET_XMIT_SUCCESS\n");
+ break;
+ case NET_XMIT_DROP:
+ pr_warn("dev_queue_xmit() returned NET_XMIT_DROP\n");
+ break;
+ case NET_XMIT_CN:
+ pr_warn("dev_queue_xmit() returned NET_XMIT_CN\n");
+ break;
+ default:
+ pr_err("dev_queue_xmit() returned UNKNOWN(%d)\n", ret);
+ }
+
+ return 0;
+}
+
+static void __exit test_blackholedev_exit(void)
+{
+ pr_warn("test_blackholedev module terminating.\n");
+}
+
+module_init(test_blackholedev_init);
+module_exit(test_blackholedev_exit);
+
+MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>");
+MODULE_LICENSE("GPL");