aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/tests/expr.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /tools/perf/tests/expr.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'tools/perf/tests/expr.c')
-rw-r--r--tools/perf/tests/expr.c224
1 files changed, 224 insertions, 0 deletions
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
new file mode 100644
index 000000000..a9eb1ed6b
--- /dev/null
+++ b/tools/perf/tests/expr.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "util/cputopo.h"
+#include "util/debug.h"
+#include "util/expr.h"
+#include "util/hashmap.h"
+#include "util/header.h"
+#include "util/smt.h"
+#include "tests.h"
+#include <math.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/zalloc.h>
+
+static int test_ids_union(void)
+{
+ struct hashmap *ids1, *ids2;
+
+ /* Empty union. */
+ ids1 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids1);
+ ids2 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids2);
+
+ ids1 = ids__union(ids1, ids2);
+ TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 0);
+
+ /* Union {foo, bar} against {}. */
+ ids2 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids2);
+
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("foo")), 0);
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("bar")), 0);
+
+ ids1 = ids__union(ids1, ids2);
+ TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2);
+
+ /* Union {foo, bar} against {foo}. */
+ ids2 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids2);
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("foo")), 0);
+
+ ids1 = ids__union(ids1, ids2);
+ TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2);
+
+ /* Union {foo, bar} against {bar,baz}. */
+ ids2 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids2);
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("bar")), 0);
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("baz")), 0);
+
+ ids1 = ids__union(ids1, ids2);
+ TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 3);
+
+ ids__free(ids1);
+
+ return 0;
+}
+
+static int test(struct expr_parse_ctx *ctx, const char *e, double val2)
+{
+ double val;
+
+ if (expr__parse(&val, ctx, e))
+ TEST_ASSERT_VAL("parse test failed", 0);
+ TEST_ASSERT_VAL("unexpected value", val == val2);
+ return 0;
+}
+
+static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_unused)
+{
+ struct expr_id_data *val_ptr;
+ const char *p;
+ double val, num_cpus, num_cores, num_dies, num_packages;
+ int ret;
+ struct expr_parse_ctx *ctx;
+ bool is_intel = false;
+ char buf[128];
+
+ if (!get_cpuid(buf, sizeof(buf)))
+ is_intel = strstr(buf, "Intel") != NULL;
+
+ TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0);
+
+ ctx = expr__ctx_new();
+ TEST_ASSERT_VAL("expr__ctx_new", ctx);
+ expr__add_id_val(ctx, strdup("FOO"), 1);
+ expr__add_id_val(ctx, strdup("BAR"), 2);
+
+ ret = test(ctx, "1+1", 2);
+ ret |= test(ctx, "FOO+BAR", 3);
+ ret |= test(ctx, "(BAR/2)%2", 1);
+ ret |= test(ctx, "1 - -4", 5);
+ ret |= test(ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5);
+ ret |= test(ctx, "1-1 | 1", 1);
+ ret |= test(ctx, "1-1 & 1", 0);
+ ret |= test(ctx, "min(1,2) + 1", 2);
+ ret |= test(ctx, "max(1,2) + 1", 3);
+ ret |= test(ctx, "1+1 if 3*4 else 0", 2);
+ ret |= test(ctx, "100 if 1 else 200 if 1 else 300", 100);
+ ret |= test(ctx, "100 if 0 else 200 if 1 else 300", 200);
+ ret |= test(ctx, "100 if 1 else 200 if 0 else 300", 100);
+ ret |= test(ctx, "100 if 0 else 200 if 0 else 300", 300);
+ ret |= test(ctx, "1.1 + 2.1", 3.2);
+ ret |= test(ctx, ".1 + 2.", 2.1);
+ ret |= test(ctx, "d_ratio(1, 2)", 0.5);
+ ret |= test(ctx, "d_ratio(2.5, 0)", 0);
+ ret |= test(ctx, "1.1 < 2.2", 1);
+ ret |= test(ctx, "2.2 > 1.1", 1);
+ ret |= test(ctx, "1.1 < 1.1", 0);
+ ret |= test(ctx, "2.2 > 2.2", 0);
+ ret |= test(ctx, "2.2 < 1.1", 0);
+ ret |= test(ctx, "1.1 > 2.2", 0);
+ ret |= test(ctx, "1.1e10 < 1.1e100", 1);
+ ret |= test(ctx, "1.1e2 > 1.1e-2", 1);
+
+ if (ret) {
+ expr__ctx_free(ctx);
+ return ret;
+ }
+
+ p = "FOO/0";
+ ret = expr__parse(&val, ctx, p);
+ TEST_ASSERT_VAL("division by zero", ret == -1);
+
+ p = "BAR/";
+ ret = expr__parse(&val, ctx, p);
+ TEST_ASSERT_VAL("missing operand", ret == -1);
+
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("FOO + BAR + BAZ + BOZO", "FOO",
+ ctx) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 3);
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR", &val_ptr));
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ", &val_ptr));
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO", &val_ptr));
+
+ expr__ctx_clear(ctx);
+ ctx->sctx.runtime = 3;
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@",
+ NULL, ctx) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2);
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3@", &val_ptr));
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@", &val_ptr));
+
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("dash\\-event1 - dash\\-event2",
+ NULL, ctx) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2);
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1", &val_ptr));
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2", &val_ptr));
+
+ /* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */
+ {
+ struct cpu_topology *topology = cpu_topology__new();
+ bool smton = smt_on(topology);
+ bool corewide = core_wide(/*system_wide=*/false,
+ /*user_requested_cpus=*/false,
+ topology);
+
+ cpu_topology__delete(topology);
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("EVENT1 if #smt_on else EVENT2",
+ NULL, ctx) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1);
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids,
+ smton ? "EVENT1" : "EVENT2",
+ &val_ptr));
+
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("EVENT1 if #core_wide else EVENT2",
+ NULL, ctx) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1);
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids,
+ corewide ? "EVENT1" : "EVENT2",
+ &val_ptr));
+
+ }
+ /* The expression is a constant 1.0 without needing to evaluate EVENT1. */
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("1.0 if EVENT1 > 100.0 else 1.0",
+ NULL, ctx) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 0);
+
+ /* Test toplogy constants appear well ordered. */
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0);
+ TEST_ASSERT_VAL("#num_cores", expr__parse(&num_cores, ctx, "#num_cores") == 0);
+ TEST_ASSERT_VAL("#num_cpus >= #num_cores", num_cpus >= num_cores);
+ TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0);
+ TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies);
+ TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0);
+
+ if (num_dies) // Some platforms do not have CPU die support, for example s390
+ TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
+
+ TEST_ASSERT_VAL("#system_tsc_freq", expr__parse(&val, ctx, "#system_tsc_freq") == 0);
+ if (is_intel)
+ TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0);
+ else
+ TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO);
+
+ /*
+ * Source count returns the number of events aggregating in a leader
+ * event including the leader. Check parsing yields an id.
+ */
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("source count",
+ expr__find_ids("source_count(EVENT1)",
+ NULL, ctx) == 0);
+ TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1);
+ TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", &val_ptr));
+
+ expr__ctx_free(ctx);
+
+ return 0;
+}
+
+DEFINE_SUITE("Simple expression parser", expr);