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/arch/x86/util/perf_regs.c | 314 +++++++++++++++++++++++++++++++++++ 1 file changed, 314 insertions(+) create mode 100644 tools/perf/arch/x86/util/perf_regs.c (limited to 'tools/perf/arch/x86/util/perf_regs.c') diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c new file mode 100644 index 000000000..0ed177991 --- /dev/null +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include + +#include "../../../perf-sys.h" +#include "../../../util/perf_regs.h" +#include "../../../util/debug.h" +#include "../../../util/event.h" +#include "../../../util/pmu.h" +#include "../../../util/pmu-hybrid.h" + +const struct sample_reg sample_reg_masks[] = { + SMPL_REG(AX, PERF_REG_X86_AX), + SMPL_REG(BX, PERF_REG_X86_BX), + SMPL_REG(CX, PERF_REG_X86_CX), + SMPL_REG(DX, PERF_REG_X86_DX), + SMPL_REG(SI, PERF_REG_X86_SI), + SMPL_REG(DI, PERF_REG_X86_DI), + SMPL_REG(BP, PERF_REG_X86_BP), + SMPL_REG(SP, PERF_REG_X86_SP), + SMPL_REG(IP, PERF_REG_X86_IP), + SMPL_REG(FLAGS, PERF_REG_X86_FLAGS), + SMPL_REG(CS, PERF_REG_X86_CS), + SMPL_REG(SS, PERF_REG_X86_SS), +#ifdef HAVE_ARCH_X86_64_SUPPORT + SMPL_REG(R8, PERF_REG_X86_R8), + SMPL_REG(R9, PERF_REG_X86_R9), + SMPL_REG(R10, PERF_REG_X86_R10), + SMPL_REG(R11, PERF_REG_X86_R11), + SMPL_REG(R12, PERF_REG_X86_R12), + SMPL_REG(R13, PERF_REG_X86_R13), + SMPL_REG(R14, PERF_REG_X86_R14), + SMPL_REG(R15, PERF_REG_X86_R15), +#endif + SMPL_REG2(XMM0, PERF_REG_X86_XMM0), + SMPL_REG2(XMM1, PERF_REG_X86_XMM1), + SMPL_REG2(XMM2, PERF_REG_X86_XMM2), + SMPL_REG2(XMM3, PERF_REG_X86_XMM3), + SMPL_REG2(XMM4, PERF_REG_X86_XMM4), + SMPL_REG2(XMM5, PERF_REG_X86_XMM5), + SMPL_REG2(XMM6, PERF_REG_X86_XMM6), + SMPL_REG2(XMM7, PERF_REG_X86_XMM7), + SMPL_REG2(XMM8, PERF_REG_X86_XMM8), + SMPL_REG2(XMM9, PERF_REG_X86_XMM9), + SMPL_REG2(XMM10, PERF_REG_X86_XMM10), + SMPL_REG2(XMM11, PERF_REG_X86_XMM11), + SMPL_REG2(XMM12, PERF_REG_X86_XMM12), + SMPL_REG2(XMM13, PERF_REG_X86_XMM13), + SMPL_REG2(XMM14, PERF_REG_X86_XMM14), + SMPL_REG2(XMM15, PERF_REG_X86_XMM15), + SMPL_REG_END +}; + +struct sdt_name_reg { + const char *sdt_name; + const char *uprobe_name; +}; +#define SDT_NAME_REG(n, m) {.sdt_name = "%" #n, .uprobe_name = "%" #m} +#define SDT_NAME_REG_END {.sdt_name = NULL, .uprobe_name = NULL} + +static const struct sdt_name_reg sdt_reg_tbl[] = { + SDT_NAME_REG(eax, ax), + SDT_NAME_REG(rax, ax), + SDT_NAME_REG(al, ax), + SDT_NAME_REG(ah, ax), + SDT_NAME_REG(ebx, bx), + SDT_NAME_REG(rbx, bx), + SDT_NAME_REG(bl, bx), + SDT_NAME_REG(bh, bx), + SDT_NAME_REG(ecx, cx), + SDT_NAME_REG(rcx, cx), + SDT_NAME_REG(cl, cx), + SDT_NAME_REG(ch, cx), + SDT_NAME_REG(edx, dx), + SDT_NAME_REG(rdx, dx), + SDT_NAME_REG(dl, dx), + SDT_NAME_REG(dh, dx), + SDT_NAME_REG(esi, si), + SDT_NAME_REG(rsi, si), + SDT_NAME_REG(sil, si), + SDT_NAME_REG(edi, di), + SDT_NAME_REG(rdi, di), + SDT_NAME_REG(dil, di), + SDT_NAME_REG(ebp, bp), + SDT_NAME_REG(rbp, bp), + SDT_NAME_REG(bpl, bp), + SDT_NAME_REG(rsp, sp), + SDT_NAME_REG(esp, sp), + SDT_NAME_REG(spl, sp), + + /* rNN registers */ + SDT_NAME_REG(r8b, r8), + SDT_NAME_REG(r8w, r8), + SDT_NAME_REG(r8d, r8), + SDT_NAME_REG(r9b, r9), + SDT_NAME_REG(r9w, r9), + SDT_NAME_REG(r9d, r9), + SDT_NAME_REG(r10b, r10), + SDT_NAME_REG(r10w, r10), + SDT_NAME_REG(r10d, r10), + SDT_NAME_REG(r11b, r11), + SDT_NAME_REG(r11w, r11), + SDT_NAME_REG(r11d, r11), + SDT_NAME_REG(r12b, r12), + SDT_NAME_REG(r12w, r12), + SDT_NAME_REG(r12d, r12), + SDT_NAME_REG(r13b, r13), + SDT_NAME_REG(r13w, r13), + SDT_NAME_REG(r13d, r13), + SDT_NAME_REG(r14b, r14), + SDT_NAME_REG(r14w, r14), + SDT_NAME_REG(r14d, r14), + SDT_NAME_REG(r15b, r15), + SDT_NAME_REG(r15w, r15), + SDT_NAME_REG(r15d, r15), + SDT_NAME_REG_END, +}; + +/* + * Perf only supports OP which is in +/-NUM(REG) form. + * Here plus-minus sign, NUM and parenthesis are optional, + * only REG is mandatory. + * + * SDT events also supports indirect addressing mode with a + * symbol as offset, scaled mode and constants in OP. But + * perf does not support them yet. Below are few examples. + * + * OP with scaled mode: + * (%rax,%rsi,8) + * 10(%ras,%rsi,8) + * + * OP with indirect addressing mode: + * check_action(%rip) + * mp_+52(%rip) + * 44+mp_(%rip) + * + * OP with constant values: + * $0 + * $123 + * $-1 + */ +#define SDT_OP_REGEX "^([+\\-]?)([0-9]*)(\\(?)(%[a-z][a-z0-9]+)(\\)?)$" + +static regex_t sdt_op_regex; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex, SDT_OP_REGEX, REG_EXTENDED); + if (ret < 0) { + pr_debug4("Regex compilation error.\n"); + return ret; + } + + initialized = 1; + return 0; +} + +/* + * Max x86 register name length is 5(ex: %r15d). So, 6th char + * should always contain NULL. This helps to find register name + * length using strlen, instead of maintaining one more variable. + */ +#define SDT_REG_NAME_SIZE 6 + +/* + * The uprobe parser does not support all gas register names; + * so, we have to replace them (ex. for x86_64: %rax -> %ax). + * Note: If register does not require renaming, just copy + * paste as it is, but don't leave it empty. + */ +static void sdt_rename_register(char *sdt_reg, int sdt_len, char *uprobe_reg) +{ + int i = 0; + + for (i = 0; sdt_reg_tbl[i].sdt_name != NULL; i++) { + if (!strncmp(sdt_reg_tbl[i].sdt_name, sdt_reg, sdt_len)) { + strcpy(uprobe_reg, sdt_reg_tbl[i].uprobe_name); + return; + } + } + + strncpy(uprobe_reg, sdt_reg, sdt_len); +} + +int arch_sdt_arg_parse_op(char *old_op, char **new_op) +{ + char new_reg[SDT_REG_NAME_SIZE] = {0}; + int new_len = 0, ret; + /* + * rm[0]: +/-NUM(REG) + * rm[1]: +/- + * rm[2]: NUM + * rm[3]: ( + * rm[4]: REG + * rm[5]: ) + */ + regmatch_t rm[6]; + /* + * Max prefix length is 2 as it may contains sign(+/-) + * and displacement 0 (Both sign and displacement 0 are + * optional so it may be empty). Use one more character + * to hold last NULL so that strlen can be used to find + * prefix length, instead of maintaining one more variable. + */ + char prefix[3] = {0}; + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + /* + * If unsupported OR does not match with regex OR + * register name too long, skip it. + */ + if (strchr(old_op, ',') || strchr(old_op, '$') || + regexec(&sdt_op_regex, old_op, 6, rm, 0) || + rm[4].rm_eo - rm[4].rm_so > SDT_REG_NAME_SIZE) { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + /* + * Prepare prefix. + * If SDT OP has parenthesis but does not provide + * displacement, add 0 for displacement. + * SDT Uprobe Prefix + * ----------------------------- + * +24(%rdi) +24(%di) + + * 24(%rdi) +24(%di) + + * %rdi %di + * (%rdi) +0(%di) +0 + * -80(%rbx) -80(%bx) - + */ + if (rm[3].rm_so != rm[3].rm_eo) { + if (rm[1].rm_so != rm[1].rm_eo) + prefix[0] = *(old_op + rm[1].rm_so); + else if (rm[2].rm_so != rm[2].rm_eo) + prefix[0] = '+'; + else + scnprintf(prefix, sizeof(prefix), "+0"); + } + + /* Rename register */ + sdt_rename_register(old_op + rm[4].rm_so, rm[4].rm_eo - rm[4].rm_so, + new_reg); + + /* Prepare final OP which should be valid for uprobe_events */ + new_len = strlen(prefix) + + (rm[2].rm_eo - rm[2].rm_so) + + (rm[3].rm_eo - rm[3].rm_so) + + strlen(new_reg) + + (rm[5].rm_eo - rm[5].rm_so) + + 1; /* NULL */ + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%.*s%.*s%.*s%.*s%.*s", + strlen(prefix), prefix, + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so, + (int)(rm[3].rm_eo - rm[3].rm_so), old_op + rm[3].rm_so, + strlen(new_reg), new_reg, + (int)(rm[5].rm_eo - rm[5].rm_so), old_op + rm[5].rm_so); + + return SDT_ARG_VALID; +} + +uint64_t arch__intr_reg_mask(void) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .sample_type = PERF_SAMPLE_REGS_INTR, + .sample_regs_intr = PERF_REG_EXTENDED_MASK, + .precise_ip = 1, + .disabled = 1, + .exclude_kernel = 1, + }; + struct perf_pmu *pmu; + int fd; + /* + * In an unnamed union, init it here to build on older gcc versions + */ + attr.sample_period = 1; + + if (perf_pmu__has_hybrid()) { + /* + * The same register set is supported among different hybrid PMUs. + * Only check the first available one. + */ + pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list); + attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; + } + + event_attr_init(&attr); + + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + if (fd != -1) { + close(fd); + return (PERF_REG_EXTENDED_MASK | PERF_REGS_MASK); + } + + return PERF_REGS_MASK; +} -- cgit v1.2.3