aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/util/values.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/util/values.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 '')
-rw-r--r--tools/perf/util/values.c305
1 files changed, 305 insertions, 0 deletions
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
new file mode 100644
index 000000000..b9823f414
--- /dev/null
+++ b/tools/perf/util/values.c
@@ -0,0 +1,305 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/zalloc.h>
+
+#include "values.h"
+#include "debug.h"
+
+int perf_read_values_init(struct perf_read_values *values)
+{
+ values->threads_max = 16;
+ values->pid = malloc(values->threads_max * sizeof(*values->pid));
+ values->tid = malloc(values->threads_max * sizeof(*values->tid));
+ values->value = zalloc(values->threads_max * sizeof(*values->value));
+ if (!values->pid || !values->tid || !values->value) {
+ pr_debug("failed to allocate read_values threads arrays");
+ goto out_free_pid;
+ }
+ values->threads = 0;
+
+ values->counters_max = 16;
+ values->counterrawid = malloc(values->counters_max
+ * sizeof(*values->counterrawid));
+ values->countername = malloc(values->counters_max
+ * sizeof(*values->countername));
+ if (!values->counterrawid || !values->countername) {
+ pr_debug("failed to allocate read_values counters arrays");
+ goto out_free_counter;
+ }
+ values->counters = 0;
+
+ return 0;
+
+out_free_counter:
+ zfree(&values->counterrawid);
+ zfree(&values->countername);
+out_free_pid:
+ zfree(&values->pid);
+ zfree(&values->tid);
+ zfree(&values->value);
+ return -ENOMEM;
+}
+
+void perf_read_values_destroy(struct perf_read_values *values)
+{
+ int i;
+
+ if (!values->threads_max || !values->counters_max)
+ return;
+
+ for (i = 0; i < values->threads; i++)
+ zfree(&values->value[i]);
+ zfree(&values->value);
+ zfree(&values->pid);
+ zfree(&values->tid);
+ zfree(&values->counterrawid);
+ for (i = 0; i < values->counters; i++)
+ zfree(&values->countername[i]);
+ zfree(&values->countername);
+}
+
+static int perf_read_values__enlarge_threads(struct perf_read_values *values)
+{
+ int nthreads_max = values->threads_max * 2;
+ void *npid = realloc(values->pid, nthreads_max * sizeof(*values->pid)),
+ *ntid = realloc(values->tid, nthreads_max * sizeof(*values->tid)),
+ *nvalue = realloc(values->value, nthreads_max * sizeof(*values->value));
+
+ if (!npid || !ntid || !nvalue)
+ goto out_err;
+
+ values->threads_max = nthreads_max;
+ values->pid = npid;
+ values->tid = ntid;
+ values->value = nvalue;
+ return 0;
+out_err:
+ free(npid);
+ free(ntid);
+ free(nvalue);
+ pr_debug("failed to enlarge read_values threads arrays");
+ return -ENOMEM;
+}
+
+static int perf_read_values__findnew_thread(struct perf_read_values *values,
+ u32 pid, u32 tid)
+{
+ int i;
+
+ for (i = 0; i < values->threads; i++)
+ if (values->pid[i] == pid && values->tid[i] == tid)
+ return i;
+
+ if (values->threads == values->threads_max) {
+ i = perf_read_values__enlarge_threads(values);
+ if (i < 0)
+ return i;
+ }
+
+ i = values->threads;
+
+ values->value[i] = zalloc(values->counters_max * sizeof(**values->value));
+ if (!values->value[i]) {
+ pr_debug("failed to allocate read_values counters array");
+ return -ENOMEM;
+ }
+ values->pid[i] = pid;
+ values->tid[i] = tid;
+ values->threads = i + 1;
+
+ return i;
+}
+
+static int perf_read_values__enlarge_counters(struct perf_read_values *values)
+{
+ char **countername;
+ int i, counters_max = values->counters_max * 2;
+ u64 *counterrawid = realloc(values->counterrawid, counters_max * sizeof(*values->counterrawid));
+
+ if (!counterrawid) {
+ pr_debug("failed to enlarge read_values rawid array");
+ goto out_enomem;
+ }
+
+ countername = realloc(values->countername, counters_max * sizeof(*values->countername));
+ if (!countername) {
+ pr_debug("failed to enlarge read_values rawid array");
+ goto out_free_rawid;
+ }
+
+ for (i = 0; i < values->threads; i++) {
+ u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value));
+ int j;
+
+ if (!value) {
+ pr_debug("failed to enlarge read_values ->values array");
+ goto out_free_name;
+ }
+
+ for (j = values->counters_max; j < counters_max; j++)
+ value[j] = 0;
+
+ values->value[i] = value;
+ }
+
+ values->counters_max = counters_max;
+ values->counterrawid = counterrawid;
+ values->countername = countername;
+
+ return 0;
+out_free_name:
+ free(countername);
+out_free_rawid:
+ free(counterrawid);
+out_enomem:
+ return -ENOMEM;
+}
+
+static int perf_read_values__findnew_counter(struct perf_read_values *values,
+ u64 rawid, const char *name)
+{
+ int i;
+
+ for (i = 0; i < values->counters; i++)
+ if (values->counterrawid[i] == rawid)
+ return i;
+
+ if (values->counters == values->counters_max) {
+ i = perf_read_values__enlarge_counters(values);
+ if (i)
+ return i;
+ }
+
+ i = values->counters++;
+ values->counterrawid[i] = rawid;
+ values->countername[i] = strdup(name);
+
+ return i;
+}
+
+int perf_read_values_add_value(struct perf_read_values *values,
+ u32 pid, u32 tid,
+ u64 rawid, const char *name, u64 value)
+{
+ int tindex, cindex;
+
+ tindex = perf_read_values__findnew_thread(values, pid, tid);
+ if (tindex < 0)
+ return tindex;
+ cindex = perf_read_values__findnew_counter(values, rawid, name);
+ if (cindex < 0)
+ return cindex;
+
+ values->value[tindex][cindex] += value;
+ return 0;
+}
+
+static void perf_read_values__display_pretty(FILE *fp,
+ struct perf_read_values *values)
+{
+ int i, j;
+ int pidwidth, tidwidth;
+ int *counterwidth;
+
+ counterwidth = malloc(values->counters * sizeof(*counterwidth));
+ if (!counterwidth) {
+ fprintf(fp, "INTERNAL ERROR: Failed to allocate counterwidth array\n");
+ return;
+ }
+ tidwidth = 3;
+ pidwidth = 3;
+ for (j = 0; j < values->counters; j++)
+ counterwidth[j] = strlen(values->countername[j]);
+ for (i = 0; i < values->threads; i++) {
+ int width;
+
+ width = snprintf(NULL, 0, "%d", values->pid[i]);
+ if (width > pidwidth)
+ pidwidth = width;
+ width = snprintf(NULL, 0, "%d", values->tid[i]);
+ if (width > tidwidth)
+ tidwidth = width;
+ for (j = 0; j < values->counters; j++) {
+ width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]);
+ if (width > counterwidth[j])
+ counterwidth[j] = width;
+ }
+ }
+
+ fprintf(fp, "# %*s %*s", pidwidth, "PID", tidwidth, "TID");
+ for (j = 0; j < values->counters; j++)
+ fprintf(fp, " %*s", counterwidth[j], values->countername[j]);
+ fprintf(fp, "\n");
+
+ for (i = 0; i < values->threads; i++) {
+ fprintf(fp, " %*d %*d", pidwidth, values->pid[i],
+ tidwidth, values->tid[i]);
+ for (j = 0; j < values->counters; j++)
+ fprintf(fp, " %*" PRIu64,
+ counterwidth[j], values->value[i][j]);
+ fprintf(fp, "\n");
+ }
+ free(counterwidth);
+}
+
+static void perf_read_values__display_raw(FILE *fp,
+ struct perf_read_values *values)
+{
+ int width, pidwidth, tidwidth, namewidth, rawwidth, countwidth;
+ int i, j;
+
+ tidwidth = 3; /* TID */
+ pidwidth = 3; /* PID */
+ namewidth = 4; /* "Name" */
+ rawwidth = 3; /* "Raw" */
+ countwidth = 5; /* "Count" */
+
+ for (i = 0; i < values->threads; i++) {
+ width = snprintf(NULL, 0, "%d", values->pid[i]);
+ if (width > pidwidth)
+ pidwidth = width;
+ width = snprintf(NULL, 0, "%d", values->tid[i]);
+ if (width > tidwidth)
+ tidwidth = width;
+ }
+ for (j = 0; j < values->counters; j++) {
+ width = strlen(values->countername[j]);
+ if (width > namewidth)
+ namewidth = width;
+ width = snprintf(NULL, 0, "%" PRIx64, values->counterrawid[j]);
+ if (width > rawwidth)
+ rawwidth = width;
+ }
+ for (i = 0; i < values->threads; i++) {
+ for (j = 0; j < values->counters; j++) {
+ width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]);
+ if (width > countwidth)
+ countwidth = width;
+ }
+ }
+
+ fprintf(fp, "# %*s %*s %*s %*s %*s\n",
+ pidwidth, "PID", tidwidth, "TID",
+ namewidth, "Name", rawwidth, "Raw",
+ countwidth, "Count");
+ for (i = 0; i < values->threads; i++)
+ for (j = 0; j < values->counters; j++)
+ fprintf(fp, " %*d %*d %*s %*" PRIx64 " %*" PRIu64,
+ pidwidth, values->pid[i],
+ tidwidth, values->tid[i],
+ namewidth, values->countername[j],
+ rawwidth, values->counterrawid[j],
+ countwidth, values->value[i][j]);
+}
+
+void perf_read_values_display(FILE *fp, struct perf_read_values *values, int raw)
+{
+ if (raw)
+ perf_read_values__display_raw(fp, values);
+ else
+ perf_read_values__display_pretty(fp, values);
+}