From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- tools/perf/util/vdso.c | 363 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 363 insertions(+) create mode 100644 tools/perf/util/vdso.c (limited to 'tools/perf/util/vdso.c') diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c new file mode 100644 index 000000000..43beb1696 --- /dev/null +++ b/tools/perf/util/vdso.c @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "vdso.h" +#include "dso.h" +#include +#include "map.h" +#include "symbol.h" +#include "machine.h" +#include "thread.h" +#include "linux/string.h" +#include +#include "debug.h" + +/* + * Include definition of find_map() also used in perf-read-vdso.c for + * building perf-read-vdso32 and perf-read-vdsox32. + */ +#include "find-map.c" + +#define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX" + +struct vdso_file { + bool found; + bool error; + char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)]; + const char *dso_name; + const char *read_prog; +}; + +struct vdso_info { + struct vdso_file vdso; +#if BITS_PER_LONG == 64 + struct vdso_file vdso32; + struct vdso_file vdsox32; +#endif +}; + +static struct vdso_info *vdso_info__new(void) +{ + static const struct vdso_info vdso_info_init = { + .vdso = { + .temp_file_name = VDSO__TEMP_FILE_NAME, + .dso_name = DSO__NAME_VDSO, + }, +#if BITS_PER_LONG == 64 + .vdso32 = { + .temp_file_name = VDSO__TEMP_FILE_NAME, + .dso_name = DSO__NAME_VDSO32, + .read_prog = "perf-read-vdso32", + }, + .vdsox32 = { + .temp_file_name = VDSO__TEMP_FILE_NAME, + .dso_name = DSO__NAME_VDSOX32, + .read_prog = "perf-read-vdsox32", + }, +#endif + }; + + return memdup(&vdso_info_init, sizeof(vdso_info_init)); +} + +static char *get_file(struct vdso_file *vdso_file) +{ + char *vdso = NULL; + char *buf = NULL; + void *start, *end; + size_t size; + int fd; + + if (vdso_file->found) + return vdso_file->temp_file_name; + + if (vdso_file->error || find_map(&start, &end, VDSO__MAP_NAME)) + return NULL; + + size = end - start; + + buf = memdup(start, size); + if (!buf) + return NULL; + + fd = mkstemp(vdso_file->temp_file_name); + if (fd < 0) + goto out; + + if (size == (size_t) write(fd, buf, size)) + vdso = vdso_file->temp_file_name; + + close(fd); + + out: + free(buf); + + vdso_file->found = (vdso != NULL); + vdso_file->error = !vdso_file->found; + return vdso; +} + +void machine__exit_vdso(struct machine *machine) +{ + struct vdso_info *vdso_info = machine->vdso_info; + + if (!vdso_info) + return; + + if (vdso_info->vdso.found) + unlink(vdso_info->vdso.temp_file_name); +#if BITS_PER_LONG == 64 + if (vdso_info->vdso32.found) + unlink(vdso_info->vdso32.temp_file_name); + if (vdso_info->vdsox32.found) + unlink(vdso_info->vdsox32.temp_file_name); +#endif + + zfree(&machine->vdso_info); +} + +static struct dso *__machine__addnew_vdso(struct machine *machine, const char *short_name, + const char *long_name) +{ + struct dso *dso; + + dso = dso__new(short_name); + if (dso != NULL) { + __dsos__add(&machine->dsos, dso); + dso__set_long_name(dso, long_name, false); + /* Put dso here because __dsos_add already got it */ + dso__put(dso); + } + + return dso; +} + +static enum dso_type machine__thread_dso_type(struct machine *machine, + struct thread *thread) +{ + enum dso_type dso_type = DSO__TYPE_UNKNOWN; + struct map *map; + + maps__for_each_entry(thread->maps, map) { + struct dso *dso = map->dso; + if (!dso || dso->long_name[0] != '/') + continue; + dso_type = dso__type(dso, machine); + if (dso_type != DSO__TYPE_UNKNOWN) + break; + } + + return dso_type; +} + +#if BITS_PER_LONG == 64 + +static int vdso__do_copy_compat(FILE *f, int fd) +{ + char buf[4096]; + size_t count; + + while (1) { + count = fread(buf, 1, sizeof(buf), f); + if (ferror(f)) + return -errno; + if (feof(f)) + break; + if (count && writen(fd, buf, count) != (ssize_t)count) + return -errno; + } + + return 0; +} + +static int vdso__copy_compat(const char *prog, int fd) +{ + FILE *f; + int err; + + f = popen(prog, "r"); + if (!f) + return -errno; + + err = vdso__do_copy_compat(f, fd); + + if (pclose(f) == -1) + return -errno; + + return err; +} + +static int vdso__create_compat_file(const char *prog, char *temp_name) +{ + int fd, err; + + fd = mkstemp(temp_name); + if (fd < 0) + return -errno; + + err = vdso__copy_compat(prog, fd); + + if (close(fd) == -1) + return -errno; + + return err; +} + +static const char *vdso__get_compat_file(struct vdso_file *vdso_file) +{ + int err; + + if (vdso_file->found) + return vdso_file->temp_file_name; + + if (vdso_file->error) + return NULL; + + err = vdso__create_compat_file(vdso_file->read_prog, + vdso_file->temp_file_name); + if (err) { + pr_err("%s failed, error %d\n", vdso_file->read_prog, err); + vdso_file->error = true; + return NULL; + } + + vdso_file->found = true; + + return vdso_file->temp_file_name; +} + +static struct dso *__machine__findnew_compat(struct machine *machine, + struct vdso_file *vdso_file) +{ + const char *file_name; + struct dso *dso; + + dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true); + if (dso) + goto out; + + file_name = vdso__get_compat_file(vdso_file); + if (!file_name) + goto out; + + dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name); +out: + return dso; +} + +static int __machine__findnew_vdso_compat(struct machine *machine, + struct thread *thread, + struct vdso_info *vdso_info, + struct dso **dso) +{ + enum dso_type dso_type; + + dso_type = machine__thread_dso_type(machine, thread); + +#ifndef HAVE_PERF_READ_VDSO32 + if (dso_type == DSO__TYPE_32BIT) + return 0; +#endif +#ifndef HAVE_PERF_READ_VDSOX32 + if (dso_type == DSO__TYPE_X32BIT) + return 0; +#endif + + switch (dso_type) { + case DSO__TYPE_32BIT: + *dso = __machine__findnew_compat(machine, &vdso_info->vdso32); + return 1; + case DSO__TYPE_X32BIT: + *dso = __machine__findnew_compat(machine, &vdso_info->vdsox32); + return 1; + case DSO__TYPE_UNKNOWN: + case DSO__TYPE_64BIT: + default: + return 0; + } +} + +#endif + +static struct dso *machine__find_vdso(struct machine *machine, + struct thread *thread) +{ + struct dso *dso = NULL; + enum dso_type dso_type; + + dso_type = machine__thread_dso_type(machine, thread); + switch (dso_type) { + case DSO__TYPE_32BIT: + dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO32, true); + if (!dso) { + dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, + true); + if (dso && dso_type != dso__type(dso, machine)) + dso = NULL; + } + break; + case DSO__TYPE_X32BIT: + dso = __dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true); + break; + case DSO__TYPE_64BIT: + case DSO__TYPE_UNKNOWN: + default: + dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true); + break; + } + + return dso; +} + +struct dso *machine__findnew_vdso(struct machine *machine, + struct thread *thread) +{ + struct vdso_info *vdso_info; + struct dso *dso = NULL; + + down_write(&machine->dsos.lock); + if (!machine->vdso_info) + machine->vdso_info = vdso_info__new(); + + vdso_info = machine->vdso_info; + if (!vdso_info) + goto out_unlock; + + dso = machine__find_vdso(machine, thread); + if (dso) + goto out_unlock; + +#if BITS_PER_LONG == 64 + if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso)) + goto out_unlock; +#endif + + dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true); + if (!dso) { + char *file; + + file = get_file(&vdso_info->vdso); + if (file) + dso = __machine__addnew_vdso(machine, DSO__NAME_VDSO, file); + } + +out_unlock: + dso__get(dso); + up_write(&machine->dsos.lock); + return dso; +} + +bool dso__is_vdso(struct dso *dso) +{ + return !strcmp(dso->short_name, DSO__NAME_VDSO) || + !strcmp(dso->short_name, DSO__NAME_VDSO32) || + !strcmp(dso->short_name, DSO__NAME_VDSOX32); +} -- cgit v1.2.3