diff options
Diffstat (limited to '')
1850 files changed, 193887 insertions, 83181 deletions
diff --git a/tools/Makefile b/tools/Makefile index db2f7b8ebed5..c074e42fd92f 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -24,6 +24,7 @@ help: @echo ' intel-speed-select - Intel Speed Select tool' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' + @echo ' nolibc - nolibc headers testing and installation' @echo ' objtool - an ELF object analysis tool' @echo ' pci - PCI tools' @echo ' perf - Linux performance measurement and analysis tool' @@ -31,6 +32,9 @@ help: @echo ' bootconfig - boot config tool' @echo ' spi - spi tools' @echo ' tmon - thermal monitoring and tuning tool' + @echo ' thermometer - temperature capture tool' + @echo ' thermal-engine - thermal monitoring tool' + @echo ' thermal - thermal library' @echo ' tracing - misc tracing tools' @echo ' turbostat - Intel CPU idle stats and freq reporting tool' @echo ' usb - USB testing tools' @@ -74,6 +78,9 @@ bpf/%: FORCE libapi: FORCE $(call descend,lib/api) +nolibc_%: FORCE + $(call descend,include/nolibc,$(patsubst nolibc_%,%,$@)) + # The perf build does not follow the descend function setup, # invoking it via it's own make rule. PERF_O = $(if $(O),$(O)/tools/perf,) @@ -85,12 +92,21 @@ perf: FORCE selftests: FORCE $(call descend,testing/$@) +thermal: FORCE + $(call descend,lib/$@) + turbostat x86_energy_perf_policy intel-speed-select: FORCE $(call descend,power/x86/$@) tmon: FORCE $(call descend,thermal/$@) +thermometer: FORCE + $(call descend,thermal/$@) + +thermal-engine: FORCE thermal + $(call descend,thermal/$@) + freefall: FORCE $(call descend,laptop/$@) @@ -101,7 +117,7 @@ all: acpi cgroup counter cpupower gpio hv firewire \ perf selftests bootconfig spi turbostat usb \ virtio vm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat wmi \ - pci debugging tracing + pci debugging tracing thermal thermometer thermal-engine acpi_install: $(call descend,power/$(@:_install=),install) @@ -115,12 +131,21 @@ cgroup_install counter_install firewire_install gpio_install hv_install iio_inst selftests_install: $(call descend,testing/$(@:_install=),install) +thermal_install: + $(call descend,lib/$(@:_install=),install) + turbostat_install x86_energy_perf_policy_install intel-speed-select_install: $(call descend,power/x86/$(@:_install=),install) tmon_install: $(call descend,thermal/$(@:_install=),install) +thermometer_install: + $(call descend,thermal/$(@:_install=),install) + +thermal-engine_install: + $(call descend,thermal/$(@:_install=),install) + freefall_install: $(call descend,laptop/$(@:_install=),install) @@ -133,7 +158,7 @@ install: acpi_install cgroup_install counter_install cpupower_install gpio_insta virtio_install vm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install \ wmi_install pci_install debugging_install intel-speed-select_install \ - tracing_install + tracing_install thermometer_install thermal-engine_install acpi_clean: $(call descend,power/acpi,clean) @@ -160,9 +185,18 @@ perf_clean: selftests_clean: $(call descend,testing/$(@:_clean=),clean) +thermal_clean: + $(call descend,lib/thermal,clean) + turbostat_clean x86_energy_perf_policy_clean intel-speed-select_clean: $(call descend,power/x86/$(@:_clean=),clean) +thermometer_clean: + $(call descend,thermal/thermometer,clean) + +thermal-engine_clean: + $(call descend,thermal/thermal-engine,clean) + tmon_clean: $(call descend,thermal/tmon,clean) @@ -177,6 +211,6 @@ clean: acpi_clean cgroup_clean counter_clean cpupower_clean hv_clean firewire_cl vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean \ gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \ - intel-speed-select_clean tracing_clean + intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean .PHONY: FORCE diff --git a/tools/accounting/.gitignore b/tools/accounting/.gitignore index c45fb4ed4309..522a690aaf3d 100644 --- a/tools/accounting/.gitignore +++ b/tools/accounting/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only getdelays +procacct diff --git a/tools/accounting/Makefile b/tools/accounting/Makefile index 03687f19cbb1..11def1ad046c 100644 --- a/tools/accounting/Makefile +++ b/tools/accounting/Makefile @@ -2,7 +2,7 @@ CC := $(CROSS_COMPILE)gcc CFLAGS := -I../../usr/include -PROGS := getdelays +PROGS := getdelays procacct all: $(PROGS) diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 5ef1c15e88ad..e83e6e47a21e 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -205,6 +205,10 @@ static void print_delayacct(struct taskstats *t) "RECLAIM %12s%15s%15s\n" " %15llu%15llu%15llums\n" "THRASHING%12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "COMPACT %12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "WPCOPY %12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -228,7 +232,15 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->thrashing_count, (unsigned long long)t->thrashing_delay_total, - average_ms(t->thrashing_delay_total, t->thrashing_count)); + average_ms(t->thrashing_delay_total, t->thrashing_count), + "count", "delay total", "delay average", + (unsigned long long)t->compact_count, + (unsigned long long)t->compact_delay_total, + average_ms(t->compact_delay_total, t->compact_count), + "count", "delay total", "delay average", + (unsigned long long)t->wpcopy_count, + (unsigned long long)t->wpcopy_delay_total, + average_ms(t->wpcopy_delay_total, t->wpcopy_count)); } static void task_context_switch_counts(struct taskstats *t) diff --git a/tools/accounting/procacct.c b/tools/accounting/procacct.c new file mode 100644 index 000000000000..8353d3237e50 --- /dev/null +++ b/tools/accounting/procacct.c @@ -0,0 +1,417 @@ +// SPDX-License-Identifier: GPL-2.0 +/* procacct.c + * + * Demonstrator of fetching resource data on task exit, as a way + * to accumulate accurate program resource usage statistics, without + * prior identification of the programs. For that, the fields for + * device and inode of the program executable binary file are also + * extracted in addition to the command string. + * + * The TGID together with the PID and the AGROUP flag allow + * identification of threads in a process and single-threaded processes. + * The ac_tgetime field gives proper whole-process walltime. + * + * Written (changed) by Thomas Orgis, University of Hamburg in 2022 + * + * This is a cheap derivation (inheriting the style) of getdelays.c: + * + * Utility to get per-pid and per-tgid delay accounting statistics + * Also illustrates usage of the taskstats interface + * + * Copyright (C) Shailabh Nagar, IBM Corp. 2005 + * Copyright (C) Balbir Singh, IBM Corp. 2006 + * Copyright (c) Jay Lan, SGI. 2006 + */ + +#include <stdio.h> +#include <stdlib.h> +#include <errno.h> +#include <unistd.h> +#include <poll.h> +#include <string.h> +#include <fcntl.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/socket.h> +#include <sys/wait.h> +#include <signal.h> + +#include <linux/genetlink.h> +#include <linux/acct.h> +#include <linux/taskstats.h> +#include <linux/kdev_t.h> + +/* + * Generic macros for dealing with netlink sockets. Might be duplicated + * elsewhere. It is recommended that commercial grade applications use + * libnl or libnetlink and use the interfaces provided by the library + */ +#define GENLMSG_DATA(glh) ((void *)(NLMSG_DATA(glh) + GENL_HDRLEN)) +#define GENLMSG_PAYLOAD(glh) (NLMSG_PAYLOAD(glh, 0) - GENL_HDRLEN) +#define NLA_DATA(na) ((void *)((char *)(na) + NLA_HDRLEN)) +#define NLA_PAYLOAD(len) (len - NLA_HDRLEN) + +#define err(code, fmt, arg...) \ + do { \ + fprintf(stderr, fmt, ##arg); \ + exit(code); \ + } while (0) + +int rcvbufsz; +char name[100]; +int dbg; +int print_delays; +int print_io_accounting; +int print_task_context_switch_counts; + +#define PRINTF(fmt, arg...) { \ + if (dbg) { \ + printf(fmt, ##arg); \ + } \ + } + +/* Maximum size of response requested or message sent */ +#define MAX_MSG_SIZE 1024 +/* Maximum number of cpus expected to be specified in a cpumask */ +#define MAX_CPUS 32 + +struct msgtemplate { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[MAX_MSG_SIZE]; +}; + +char cpumask[100+6*MAX_CPUS]; + +static void usage(void) +{ + fprintf(stderr, "procacct [-v] [-w logfile] [-r bufsize] [-m cpumask]\n"); + fprintf(stderr, " -v: debug on\n"); +} + +/* + * Create a raw netlink socket and bind + */ +static int create_nl_socket(int protocol) +{ + int fd; + struct sockaddr_nl local; + + fd = socket(AF_NETLINK, SOCK_RAW, protocol); + if (fd < 0) + return -1; + + if (rcvbufsz) + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, + &rcvbufsz, sizeof(rcvbufsz)) < 0) { + fprintf(stderr, "Unable to set socket rcv buf size to %d\n", + rcvbufsz); + goto error; + } + + memset(&local, 0, sizeof(local)); + local.nl_family = AF_NETLINK; + + if (bind(fd, (struct sockaddr *) &local, sizeof(local)) < 0) + goto error; + + return fd; +error: + close(fd); + return -1; +} + + +static int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid, + __u8 genl_cmd, __u16 nla_type, + void *nla_data, int nla_len) +{ + struct nlattr *na; + struct sockaddr_nl nladdr; + int r, buflen; + char *buf; + + struct msgtemplate msg; + + msg.n.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + msg.n.nlmsg_type = nlmsg_type; + msg.n.nlmsg_flags = NLM_F_REQUEST; + msg.n.nlmsg_seq = 0; + msg.n.nlmsg_pid = nlmsg_pid; + msg.g.cmd = genl_cmd; + msg.g.version = 0x1; + na = (struct nlattr *) GENLMSG_DATA(&msg); + na->nla_type = nla_type; + na->nla_len = nla_len + 1 + NLA_HDRLEN; + memcpy(NLA_DATA(na), nla_data, nla_len); + msg.n.nlmsg_len += NLMSG_ALIGN(na->nla_len); + + buf = (char *) &msg; + buflen = msg.n.nlmsg_len; + memset(&nladdr, 0, sizeof(nladdr)); + nladdr.nl_family = AF_NETLINK; + while ((r = sendto(sd, buf, buflen, 0, (struct sockaddr *) &nladdr, + sizeof(nladdr))) < buflen) { + if (r > 0) { + buf += r; + buflen -= r; + } else if (errno != EAGAIN) + return -1; + } + return 0; +} + + +/* + * Probe the controller in genetlink to find the family id + * for the TASKSTATS family + */ +static int get_family_id(int sd) +{ + struct { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[256]; + } ans; + + int id = 0, rc; + struct nlattr *na; + int rep_len; + + strcpy(name, TASKSTATS_GENL_NAME); + rc = send_cmd(sd, GENL_ID_CTRL, getpid(), CTRL_CMD_GETFAMILY, + CTRL_ATTR_FAMILY_NAME, (void *)name, + strlen(TASKSTATS_GENL_NAME)+1); + if (rc < 0) + return 0; /* sendto() failure? */ + + rep_len = recv(sd, &ans, sizeof(ans), 0); + if (ans.n.nlmsg_type == NLMSG_ERROR || + (rep_len < 0) || !NLMSG_OK((&ans.n), rep_len)) + return 0; + + na = (struct nlattr *) GENLMSG_DATA(&ans); + na = (struct nlattr *) ((char *) na + NLA_ALIGN(na->nla_len)); + if (na->nla_type == CTRL_ATTR_FAMILY_ID) + id = *(__u16 *) NLA_DATA(na); + + return id; +} + +#define average_ms(t, c) (t / 1000000ULL / (c ? c : 1)) + +static void print_procacct(struct taskstats *t) +{ + /* First letter: T is a mere thread, G the last in a group, U unknown. */ + printf( + "%c pid=%lu tgid=%lu uid=%lu wall=%llu gwall=%llu cpu=%llu vmpeak=%llu rsspeak=%llu dev=%lu:%lu inode=%llu comm=%s\n" + , t->version >= 12 ? (t->ac_flag & AGROUP ? 'P' : 'T') : '?' + , (unsigned long)t->ac_pid + , (unsigned long)(t->version >= 12 ? t->ac_tgid : 0) + , (unsigned long)t->ac_uid + , (unsigned long long)t->ac_etime + , (unsigned long long)(t->version >= 12 ? t->ac_tgetime : 0) + , (unsigned long long)(t->ac_utime+t->ac_stime) + , (unsigned long long)t->hiwater_vm + , (unsigned long long)t->hiwater_rss + , (unsigned long)(t->version >= 12 ? MAJOR(t->ac_exe_dev) : 0) + , (unsigned long)(t->version >= 12 ? MINOR(t->ac_exe_dev) : 0) + , (unsigned long long)(t->version >= 12 ? t->ac_exe_inode : 0) + , t->ac_comm + ); +} + +void handle_aggr(int mother, struct nlattr *na, int fd) +{ + int aggr_len = NLA_PAYLOAD(na->nla_len); + int len2 = 0; + pid_t rtid = 0; + + na = (struct nlattr *) NLA_DATA(na); + while (len2 < aggr_len) { + switch (na->nla_type) { + case TASKSTATS_TYPE_PID: + rtid = *(int *) NLA_DATA(na); + PRINTF("PID\t%d\n", rtid); + break; + case TASKSTATS_TYPE_TGID: + rtid = *(int *) NLA_DATA(na); + PRINTF("TGID\t%d\n", rtid); + break; + case TASKSTATS_TYPE_STATS: + if (mother == TASKSTATS_TYPE_AGGR_PID) + print_procacct((struct taskstats *) NLA_DATA(na)); + if (fd) { + if (write(fd, NLA_DATA(na), na->nla_len) < 0) + err(1, "write error\n"); + } + break; + case TASKSTATS_TYPE_NULL: + break; + default: + fprintf(stderr, "Unknown nested nla_type %d\n", + na->nla_type); + break; + } + len2 += NLA_ALIGN(na->nla_len); + na = (struct nlattr *)((char *)na + + NLA_ALIGN(na->nla_len)); + } +} + +int main(int argc, char *argv[]) +{ + int c, rc, rep_len, aggr_len, len2; + int cmd_type = TASKSTATS_CMD_ATTR_UNSPEC; + __u16 id; + __u32 mypid; + + struct nlattr *na; + int nl_sd = -1; + int len = 0; + pid_t tid = 0; + + int fd = 0; + int write_file = 0; + int maskset = 0; + char *logfile = NULL; + int containerset = 0; + char *containerpath = NULL; + int cfd = 0; + int forking = 0; + sigset_t sigset; + + struct msgtemplate msg; + + while (!forking) { + c = getopt(argc, argv, "m:vr:"); + if (c < 0) + break; + + switch (c) { + case 'w': + logfile = strdup(optarg); + printf("write to file %s\n", logfile); + write_file = 1; + break; + case 'r': + rcvbufsz = atoi(optarg); + printf("receive buf size %d\n", rcvbufsz); + if (rcvbufsz < 0) + err(1, "Invalid rcv buf size\n"); + break; + case 'm': + strncpy(cpumask, optarg, sizeof(cpumask)); + cpumask[sizeof(cpumask) - 1] = '\0'; + maskset = 1; + break; + case 'v': + printf("debug on\n"); + dbg = 1; + break; + default: + usage(); + exit(-1); + } + } + if (!maskset) { + maskset = 1; + strncpy(cpumask, "1", sizeof(cpumask)); + cpumask[sizeof(cpumask) - 1] = '\0'; + } + printf("cpumask %s maskset %d\n", cpumask, maskset); + + if (write_file) { + fd = open(logfile, O_WRONLY | O_CREAT | O_TRUNC, 0644); + if (fd == -1) { + perror("Cannot open output file\n"); + exit(1); + } + } + + nl_sd = create_nl_socket(NETLINK_GENERIC); + if (nl_sd < 0) + err(1, "error creating Netlink socket\n"); + + mypid = getpid(); + id = get_family_id(nl_sd); + if (!id) { + fprintf(stderr, "Error getting family id, errno %d\n", errno); + goto err; + } + PRINTF("family id %d\n", id); + + if (maskset) { + rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET, + TASKSTATS_CMD_ATTR_REGISTER_CPUMASK, + &cpumask, strlen(cpumask) + 1); + PRINTF("Sent register cpumask, retval %d\n", rc); + if (rc < 0) { + fprintf(stderr, "error sending register cpumask\n"); + goto err; + } + } + + do { + rep_len = recv(nl_sd, &msg, sizeof(msg), 0); + PRINTF("received %d bytes\n", rep_len); + + if (rep_len < 0) { + fprintf(stderr, "nonfatal reply error: errno %d\n", + errno); + continue; + } + if (msg.n.nlmsg_type == NLMSG_ERROR || + !NLMSG_OK((&msg.n), rep_len)) { + struct nlmsgerr *err = NLMSG_DATA(&msg); + + fprintf(stderr, "fatal reply error, errno %d\n", + err->error); + goto done; + } + + PRINTF("nlmsghdr size=%zu, nlmsg_len=%d, rep_len=%d\n", + sizeof(struct nlmsghdr), msg.n.nlmsg_len, rep_len); + + + rep_len = GENLMSG_PAYLOAD(&msg.n); + + na = (struct nlattr *) GENLMSG_DATA(&msg); + len = 0; + while (len < rep_len) { + len += NLA_ALIGN(na->nla_len); + int mother = na->nla_type; + + PRINTF("mother=%i\n", mother); + switch (na->nla_type) { + case TASKSTATS_TYPE_AGGR_PID: + case TASKSTATS_TYPE_AGGR_TGID: + /* For nested attributes, na follows */ + handle_aggr(mother, na, fd); + break; + default: + fprintf(stderr, "Unexpected nla_type %d\n", + na->nla_type); + case TASKSTATS_TYPE_NULL: + break; + } + na = (struct nlattr *) (GENLMSG_DATA(&msg) + len); + } + } while (1); +done: + if (maskset) { + rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET, + TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK, + &cpumask, strlen(cpumask) + 1); + printf("Sent deregister mask, retval %d\n", rc); + if (rc < 0) + err(rc, "error sending deregister cpumask\n"); + } +err: + close(nl_sd); + if (fd) + close(fd); + if (cfd) + close(cfd); + return 0; +} diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h new file mode 100644 index 000000000000..8aa0d276a636 --- /dev/null +++ b/tools/arch/arm64/include/asm/cputype.h @@ -0,0 +1,268 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 ARM Ltd. + */ +#ifndef __ASM_CPUTYPE_H +#define __ASM_CPUTYPE_H + +#define INVALID_HWID ULONG_MAX + +#define MPIDR_UP_BITMASK (0x1 << 30) +#define MPIDR_MT_BITMASK (0x1 << 24) +#define MPIDR_HWID_BITMASK UL(0xff00ffffff) + +#define MPIDR_LEVEL_BITS_SHIFT 3 +#define MPIDR_LEVEL_BITS (1 << MPIDR_LEVEL_BITS_SHIFT) +#define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1) + +#define MPIDR_LEVEL_SHIFT(level) \ + (((1 << level) >> 1) << MPIDR_LEVEL_BITS_SHIFT) + +#define MPIDR_AFFINITY_LEVEL(mpidr, level) \ + ((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK) + +#define MIDR_REVISION_MASK 0xf +#define MIDR_REVISION(midr) ((midr) & MIDR_REVISION_MASK) +#define MIDR_PARTNUM_SHIFT 4 +#define MIDR_PARTNUM_MASK (0xfff << MIDR_PARTNUM_SHIFT) +#define MIDR_PARTNUM(midr) \ + (((midr) & MIDR_PARTNUM_MASK) >> MIDR_PARTNUM_SHIFT) +#define MIDR_ARCHITECTURE_SHIFT 16 +#define MIDR_ARCHITECTURE_MASK (0xf << MIDR_ARCHITECTURE_SHIFT) +#define MIDR_ARCHITECTURE(midr) \ + (((midr) & MIDR_ARCHITECTURE_MASK) >> MIDR_ARCHITECTURE_SHIFT) +#define MIDR_VARIANT_SHIFT 20 +#define MIDR_VARIANT_MASK (0xf << MIDR_VARIANT_SHIFT) +#define MIDR_VARIANT(midr) \ + (((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT) +#define MIDR_IMPLEMENTOR_SHIFT 24 +#define MIDR_IMPLEMENTOR_MASK (0xffU << MIDR_IMPLEMENTOR_SHIFT) +#define MIDR_IMPLEMENTOR(midr) \ + (((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT) + +#define MIDR_CPU_MODEL(imp, partnum) \ + (((imp) << MIDR_IMPLEMENTOR_SHIFT) | \ + (0xf << MIDR_ARCHITECTURE_SHIFT) | \ + ((partnum) << MIDR_PARTNUM_SHIFT)) + +#define MIDR_CPU_VAR_REV(var, rev) \ + (((var) << MIDR_VARIANT_SHIFT) | (rev)) + +#define MIDR_CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \ + MIDR_ARCHITECTURE_MASK) + +#define ARM_CPU_IMP_ARM 0x41 +#define ARM_CPU_IMP_APM 0x50 +#define ARM_CPU_IMP_CAVIUM 0x43 +#define ARM_CPU_IMP_BRCM 0x42 +#define ARM_CPU_IMP_QCOM 0x51 +#define ARM_CPU_IMP_NVIDIA 0x4E +#define ARM_CPU_IMP_FUJITSU 0x46 +#define ARM_CPU_IMP_HISI 0x48 +#define ARM_CPU_IMP_APPLE 0x61 + +#define ARM_CPU_PART_AEM_V8 0xD0F +#define ARM_CPU_PART_FOUNDATION 0xD00 +#define ARM_CPU_PART_CORTEX_A57 0xD07 +#define ARM_CPU_PART_CORTEX_A72 0xD08 +#define ARM_CPU_PART_CORTEX_A53 0xD03 +#define ARM_CPU_PART_CORTEX_A73 0xD09 +#define ARM_CPU_PART_CORTEX_A75 0xD0A +#define ARM_CPU_PART_CORTEX_A35 0xD04 +#define ARM_CPU_PART_CORTEX_A55 0xD05 +#define ARM_CPU_PART_CORTEX_A76 0xD0B +#define ARM_CPU_PART_NEOVERSE_N1 0xD0C +#define ARM_CPU_PART_CORTEX_A77 0xD0D +#define ARM_CPU_PART_NEOVERSE_V1 0xD40 +#define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 +#define ARM_CPU_PART_CORTEX_X1 0xD44 +#define ARM_CPU_PART_CORTEX_A510 0xD46 +#define ARM_CPU_PART_CORTEX_A710 0xD47 +#define ARM_CPU_PART_CORTEX_X2 0xD48 +#define ARM_CPU_PART_NEOVERSE_N2 0xD49 +#define ARM_CPU_PART_CORTEX_A78C 0xD4B + +#define APM_CPU_PART_POTENZA 0x000 + +#define CAVIUM_CPU_PART_THUNDERX 0x0A1 +#define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2 +#define CAVIUM_CPU_PART_THUNDERX_83XX 0x0A3 +#define CAVIUM_CPU_PART_THUNDERX2 0x0AF +/* OcteonTx2 series */ +#define CAVIUM_CPU_PART_OCTX2_98XX 0x0B1 +#define CAVIUM_CPU_PART_OCTX2_96XX 0x0B2 +#define CAVIUM_CPU_PART_OCTX2_95XX 0x0B3 +#define CAVIUM_CPU_PART_OCTX2_95XXN 0x0B4 +#define CAVIUM_CPU_PART_OCTX2_95XXMM 0x0B5 +#define CAVIUM_CPU_PART_OCTX2_95XXO 0x0B6 + +#define BRCM_CPU_PART_BRAHMA_B53 0x100 +#define BRCM_CPU_PART_VULCAN 0x516 + +#define QCOM_CPU_PART_FALKOR_V1 0x800 +#define QCOM_CPU_PART_FALKOR 0xC00 +#define QCOM_CPU_PART_KRYO 0x200 +#define QCOM_CPU_PART_KRYO_2XX_GOLD 0x800 +#define QCOM_CPU_PART_KRYO_2XX_SILVER 0x801 +#define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 +#define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804 +#define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 + +#define NVIDIA_CPU_PART_DENVER 0x003 +#define NVIDIA_CPU_PART_CARMEL 0x004 + +#define FUJITSU_CPU_PART_A64FX 0x001 + +#define HISI_CPU_PART_TSV110 0xD01 + +#define APPLE_CPU_PART_M1_ICESTORM 0x022 +#define APPLE_CPU_PART_M1_FIRESTORM 0x023 +#define APPLE_CPU_PART_M1_ICESTORM_PRO 0x024 +#define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025 +#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 +#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 + +#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) +#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) +#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) +#define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73) +#define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75) +#define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35) +#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55) +#define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76) +#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1) +#define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) +#define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) +#define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) +#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) +#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) +#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) +#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) +#define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) +#define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) +#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) +#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) +#define MIDR_OCTX2_98XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_98XX) +#define MIDR_OCTX2_96XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_96XX) +#define MIDR_OCTX2_95XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XX) +#define MIDR_OCTX2_95XXN MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XXN) +#define MIDR_OCTX2_95XXMM MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XXMM) +#define MIDR_OCTX2_95XXO MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XXO) +#define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2) +#define MIDR_BRAHMA_B53 MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_BRAHMA_B53) +#define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN) +#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) +#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) +#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) +#define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD) +#define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER) +#define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) +#define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD) +#define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER) +#define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER) +#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) +#define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX) +#define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110) +#define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM) +#define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM) +#define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO) +#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) +#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) +#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) + +/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ +#define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX +#define MIDR_FUJITSU_ERRATUM_010001_MASK (~MIDR_CPU_VAR_REV(1, 0)) +#define TCR_CLEAR_FUJITSU_ERRATUM_010001 (TCR_NFD1 | TCR_NFD0) + +#ifndef __ASSEMBLY__ + +#include <asm/sysreg.h> + +#define read_cpuid(reg) read_sysreg_s(SYS_ ## reg) + +/* + * Represent a range of MIDR values for a given CPU model and a + * range of variant/revision values. + * + * @model - CPU model as defined by MIDR_CPU_MODEL + * @rv_min - Minimum value for the revision/variant as defined by + * MIDR_CPU_VAR_REV + * @rv_max - Maximum value for the variant/revision for the range. + */ +struct midr_range { + u32 model; + u32 rv_min; + u32 rv_max; +}; + +#define MIDR_RANGE(m, v_min, r_min, v_max, r_max) \ + { \ + .model = m, \ + .rv_min = MIDR_CPU_VAR_REV(v_min, r_min), \ + .rv_max = MIDR_CPU_VAR_REV(v_max, r_max), \ + } + +#define MIDR_REV_RANGE(m, v, r_min, r_max) MIDR_RANGE(m, v, r_min, v, r_max) +#define MIDR_REV(m, v, r) MIDR_RANGE(m, v, r, v, r) +#define MIDR_ALL_VERSIONS(m) MIDR_RANGE(m, 0, 0, 0xf, 0xf) + +static inline bool midr_is_cpu_model_range(u32 midr, u32 model, u32 rv_min, + u32 rv_max) +{ + u32 _model = midr & MIDR_CPU_MODEL_MASK; + u32 rv = midr & (MIDR_REVISION_MASK | MIDR_VARIANT_MASK); + + return _model == model && rv >= rv_min && rv <= rv_max; +} + +static inline bool is_midr_in_range(u32 midr, struct midr_range const *range) +{ + return midr_is_cpu_model_range(midr, range->model, + range->rv_min, range->rv_max); +} + +static inline bool +is_midr_in_range_list(u32 midr, struct midr_range const *ranges) +{ + while (ranges->model) + if (is_midr_in_range(midr, ranges++)) + return true; + return false; +} + +/* + * The CPU ID never changes at run time, so we might as well tell the + * compiler that it's constant. Use this function to read the CPU ID + * rather than directly reading processor_id or read_cpuid() directly. + */ +static inline u32 __attribute_const__ read_cpuid_id(void) +{ + return read_cpuid(MIDR_EL1); +} + +static inline u64 __attribute_const__ read_cpuid_mpidr(void) +{ + return read_cpuid(MPIDR_EL1); +} + +static inline unsigned int __attribute_const__ read_cpuid_implementor(void) +{ + return MIDR_IMPLEMENTOR(read_cpuid_id()); +} + +static inline unsigned int __attribute_const__ read_cpuid_part_number(void) +{ + return MIDR_PARTNUM(read_cpuid_id()); +} + +static inline u32 __attribute_const__ read_cpuid_cachetype(void) +{ + return read_cpuid(CTR_EL0); +} +#endif /* __ASSEMBLY__ */ + +#endif diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index b3edde68bc3e..3bb134355874 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -139,8 +139,10 @@ struct kvm_guest_debug_arch { __u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS]; }; +#define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0) struct kvm_debug_exit_arch { __u32 hsr; + __u32 hsr_high; /* ESR_EL2[61:32] */ __u64 far; /* used for watchpoints */ }; @@ -281,6 +283,11 @@ struct kvm_arm_copy_mte_tags { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 KVM_REG_ARM_FW_REG(3) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED 2 + /* SVE registers */ #define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) @@ -327,6 +334,40 @@ struct kvm_arm_copy_mte_tags { #define KVM_ARM64_SVE_VLS_WORDS \ ((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1) +/* Bitmap feature firmware registers */ +#define KVM_REG_ARM_FW_FEAT_BMAP (0x0016 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_FEAT_BMAP_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW_FEAT_BMAP | \ + ((r) & 0xffff)) + +#define KVM_REG_ARM_STD_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(0) + +enum { + KVM_REG_ARM_STD_BIT_TRNG_V1_0 = 0, +#ifdef __KERNEL__ + KVM_REG_ARM_STD_BMAP_BIT_COUNT, +#endif +}; + +#define KVM_REG_ARM_STD_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(1) + +enum { + KVM_REG_ARM_STD_HYP_BIT_PV_TIME = 0, +#ifdef __KERNEL__ + KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT, +#endif +}; + +#define KVM_REG_ARM_VENDOR_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(2) + +enum { + KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT = 0, + KVM_REG_ARM_VENDOR_HYP_BIT_PTP = 1, +#ifdef __KERNEL__ + KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT, +#endif +}; + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 @@ -362,6 +403,7 @@ struct kvm_arm_copy_mte_tags { #define KVM_ARM_VCPU_PMU_V3_IRQ 0 #define KVM_ARM_VCPU_PMU_V3_INIT 1 #define KVM_ARM_VCPU_PMU_V3_FILTER 2 +#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3 #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 @@ -413,6 +455,16 @@ struct kvm_arm_copy_mte_tags { #define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS #define KVM_PSCI_RET_DENIED PSCI_RET_DENIED +/* arm64-specific kvm_run::system_event flags */ +/* + * Reset caused by a PSCI v1.1 SYSTEM_RESET2 call. + * Valid only when the system event has a type of KVM_SYSTEM_EVENT_RESET. + */ +#define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (1ULL << 0) + +/* run->fail_entry.hardware_entry_failure_reason codes. */ +#define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/tools/arch/arm64/include/uapi/asm/perf_regs.h b/tools/arch/arm64/include/uapi/asm/perf_regs.h index d54daafa89e3..fd157f46727e 100644 --- a/tools/arch/arm64/include/uapi/asm/perf_regs.h +++ b/tools/arch/arm64/include/uapi/asm/perf_regs.h @@ -36,6 +36,11 @@ enum perf_event_arm_regs { PERF_REG_ARM64_LR, PERF_REG_ARM64_SP, PERF_REG_ARM64_PC, - PERF_REG_ARM64_MAX, + + /* Extended/pseudo registers */ + PERF_REG_ARM64_VG = 46, // SVE Vector Granule + + PERF_REG_ARM64_MAX = PERF_REG_ARM64_PC + 1, + PERF_REG_ARM64_EXTENDED_MAX = PERF_REG_ARM64_VG + 1 }; #endif /* _ASM_ARM64_PERF_REGS_H */ diff --git a/tools/arch/h8300/include/asm/bitsperlong.h b/tools/arch/h8300/include/asm/bitsperlong.h deleted file mode 100644 index fa1508337ffc..000000000000 --- a/tools/arch/h8300/include/asm/bitsperlong.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_H8300_BITS_PER_LONG -#define __ASM_H8300_BITS_PER_LONG - -#include <asm-generic/bitsperlong.h> - -#if !defined(__ASSEMBLY__) -/* h8300-unknown-linux required long */ -#define __kernel_size_t __kernel_size_t -typedef unsigned long __kernel_size_t; -typedef long __kernel_ssize_t; -typedef long __kernel_ptrdiff_t; -#endif - -#endif /* __ASM_H8300_BITS_PER_LONG */ diff --git a/tools/arch/h8300/include/uapi/asm/mman.h b/tools/arch/h8300/include/uapi/asm/mman.h deleted file mode 100644 index be7bbe0528d1..000000000000 --- a/tools/arch/h8300/include/uapi/asm/mman.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef TOOLS_ARCH_H8300_UAPI_ASM_MMAN_FIX_H -#define TOOLS_ARCH_H8300_UAPI_ASM_MMAN_FIX_H -#include <uapi/asm-generic/mman.h> -/* MAP_32BIT is undefined on h8300, fix it for perf */ -#define MAP_32BIT 0 -#endif diff --git a/tools/arch/x86/include/asm/amd-ibs.h b/tools/arch/x86/include/asm/amd-ibs.h index 174e7d83fcbd..765e9e752d03 100644 --- a/tools/arch/x86/include/asm/amd-ibs.h +++ b/tools/arch/x86/include/asm/amd-ibs.h @@ -49,7 +49,7 @@ union ibs_op_ctl { }; }; -/* MSR 0xc0011035: IBS Op Data 2 */ +/* MSR 0xc0011035: IBS Op Data 1 */ union ibs_op_data { __u64 val; struct { diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index d5b5f2ab87a0..03acc823838a 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -201,17 +201,17 @@ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -/* FREE! ( 7*32+10) */ +#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ #define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -/* FREE! ( 7*32+20) */ +#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ @@ -238,6 +238,7 @@ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ #define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ #define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -299,7 +300,6 @@ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ -#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ @@ -315,6 +315,8 @@ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ +#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -327,6 +329,7 @@ #define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ #define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ #define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ +#define X86_FEATURE_HFI (14*32+19) /* Hardware Feedback Interface */ /* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */ #define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ @@ -387,7 +390,11 @@ #define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ +#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */ +#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */ #define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ +#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ +#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ @@ -400,6 +407,7 @@ #define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ /* @@ -438,5 +446,6 @@ #define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ +#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 8f28fafa98b3..36369e76cc63 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -10,12 +10,6 @@ * cpu_feature_enabled(). */ -#ifdef CONFIG_X86_SMAP -# define DISABLE_SMAP 0 -#else -# define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31)) -#endif - #ifdef CONFIG_X86_UMIP # define DISABLE_UMIP 0 #else @@ -56,8 +50,11 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif -/* Force disable because it's broken beyond repair */ -#define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) +#ifdef CONFIG_INTEL_IOMMU_SVM +# define DISABLE_ENQCMD 0 +#else +# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) +#endif #ifdef CONFIG_X86_SGX # define DISABLE_SGX 0 @@ -65,6 +62,12 @@ # define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31)) #endif +#ifdef CONFIG_INTEL_TDX_GUEST +# define DISABLE_TDX_GUEST 0 +#else +# define DISABLE_TDX_GUEST (1 << (X86_FEATURE_TDX_GUEST & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -76,8 +79,8 @@ #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) -#define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX) +#define DISABLED_MASK8 (DISABLE_TDX_GUEST) +#define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index dc632b41f135..65c0d9ce1e29 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -124,7 +124,7 @@ struct insn { #define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ #define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ /* VEX bit fields */ -#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */ +#define X86_EVEX_M(vex) ((vex) & 0x07) /* EVEX Byte1 */ #define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ #define X86_VEX2_M 1 /* VEX2.M always 1 */ #define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 01e2650b9585..d27e0581b777 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -76,6 +76,8 @@ /* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */ #define MSR_IA32_CORE_CAPS 0x000000cf +#define MSR_IA32_CORE_CAPS_INTEGRITY_CAPS_BIT 2 +#define MSR_IA32_CORE_CAPS_INTEGRITY_CAPS BIT(MSR_IA32_CORE_CAPS_INTEGRITY_CAPS_BIT) #define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT 5 #define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT) @@ -114,6 +116,30 @@ * Not susceptible to * TSX Async Abort (TAA) vulnerabilities. */ +#define ARCH_CAP_SBDR_SSDP_NO BIT(13) /* + * Not susceptible to SBDR and SSDP + * variants of Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_FBSDP_NO BIT(14) /* + * Not susceptible to FBSDP variant of + * Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_PSDP_NO BIT(15) /* + * Not susceptible to PSDP variant of + * Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_FB_CLEAR BIT(17) /* + * VERW clears CPU fill buffer + * even on MDS_NO CPUs. + */ +#define ARCH_CAP_FB_CLEAR_CTRL BIT(18) /* + * MSR_IA32_MCU_OPT_CTRL[FB_CLEAR_DIS] + * bit available to control VERW + * behavior. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -128,9 +154,10 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ -/* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 -#define RNGDS_MITG_DIS BIT(0) +#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ +#define RTM_ALLOW BIT(1) /* TSX development mode */ +#define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 @@ -154,6 +181,11 @@ #define MSR_IA32_POWER_CTL 0x000001fc #define MSR_IA32_POWER_CTL_BIT_EE 19 +/* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ +#define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 +#define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) + #define MSR_LBR_NHM_FROM 0x00000680 #define MSR_LBR_NHM_TO 0x000006c0 #define MSR_LBR_CORE_FROM 0x00000040 @@ -205,6 +237,8 @@ #define RTIT_CTL_DISRETC BIT(11) #define RTIT_CTL_PTW_EN BIT(12) #define RTIT_CTL_BRANCH_EN BIT(13) +#define RTIT_CTL_EVENT_EN BIT(31) +#define RTIT_CTL_NOTNT BIT_ULL(55) #define RTIT_CTL_MTC_RANGE_OFFSET 14 #define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) #define RTIT_CTL_CYC_THRESH_OFFSET 19 @@ -310,6 +344,7 @@ /* Run Time Average Power Limiting (RAPL) Interface */ +#define MSR_VR_CURRENT_CONFIG 0x00000601 #define MSR_RAPL_POWER_UNIT 0x00000606 #define MSR_PKG_POWER_LIMIT 0x00000610 @@ -360,11 +395,29 @@ #define MSR_ATOM_CORE_TURBO_RATIOS 0x0000066c #define MSR_ATOM_CORE_TURBO_VIDS 0x0000066d - #define MSR_CORE_PERF_LIMIT_REASONS 0x00000690 #define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 #define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 +/* Control-flow Enforcement Technology MSRs */ +#define MSR_IA32_U_CET 0x000006a0 /* user mode cet */ +#define MSR_IA32_S_CET 0x000006a2 /* kernel mode cet */ +#define CET_SHSTK_EN BIT_ULL(0) +#define CET_WRSS_EN BIT_ULL(1) +#define CET_ENDBR_EN BIT_ULL(2) +#define CET_LEG_IW_EN BIT_ULL(3) +#define CET_NO_TRACK_EN BIT_ULL(4) +#define CET_SUPPRESS_DISABLE BIT_ULL(5) +#define CET_RESERVED (BIT_ULL(6) | BIT_ULL(7) | BIT_ULL(8) | BIT_ULL(9)) +#define CET_SUPPRESS BIT_ULL(10) +#define CET_WAIT_ENDBR BIT_ULL(11) + +#define MSR_IA32_PL0_SSP 0x000006a4 /* ring-0 shadow stack pointer */ +#define MSR_IA32_PL1_SSP 0x000006a5 /* ring-1 shadow stack pointer */ +#define MSR_IA32_PL2_SSP 0x000006a6 /* ring-2 shadow stack pointer */ +#define MSR_IA32_PL3_SSP 0x000006a7 /* ring-3 shadow stack pointer */ +#define MSR_IA32_INT_SSP_TAB 0x000006a8 /* exception shadow stack table */ + /* Hardware P state interface */ #define MSR_PPERF 0x0000064e #define MSR_PERF_LIMIT_REASONS 0x0000064f @@ -476,16 +529,41 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 #define MSR_AMD64_SEV_ES_ENABLED_BIT 1 +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +/* AMD Collaborative Processor Performance Control MSRs */ +#define MSR_AMD_CPPC_CAP1 0xc00102b0 +#define MSR_AMD_CPPC_ENABLE 0xc00102b1 +#define MSR_AMD_CPPC_CAP2 0xc00102b2 +#define MSR_AMD_CPPC_REQ 0xc00102b3 +#define MSR_AMD_CPPC_STATUS 0xc00102b4 + +#define AMD_CPPC_LOWEST_PERF(x) (((x) >> 0) & 0xff) +#define AMD_CPPC_LOWNONLIN_PERF(x) (((x) >> 8) & 0xff) +#define AMD_CPPC_NOMINAL_PERF(x) (((x) >> 16) & 0xff) +#define AMD_CPPC_HIGHEST_PERF(x) (((x) >> 24) & 0xff) + +#define AMD_CPPC_MAX_PERF(x) (((x) & 0xff) << 0) +#define AMD_CPPC_MIN_PERF(x) (((x) & 0xff) << 8) +#define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16) +#define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24) + +/* AMD Performance Counter Global Status and Control MSRs */ +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS 0xc0000300 +#define MSR_AMD64_PERF_CNTR_GLOBAL_CTL 0xc0000301 +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR 0xc0000302 + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 @@ -650,6 +728,10 @@ #define MSR_IA32_PERF_CTL 0x00000199 #define INTEL_PERF_CTL_MASK 0xffff +/* AMD Branch Sampling configuration */ +#define MSR_AMD_DBG_EXTN_CFG 0xc000010f +#define MSR_AMD_SAMP_BR_FROM 0xc0010300 + #define MSR_IA32_MPERF 0x000000e7 #define MSR_IA32_APERF 0x000000e8 @@ -687,12 +769,14 @@ #define PACKAGE_THERM_STATUS_PROCHOT (1 << 0) #define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10) +#define PACKAGE_THERM_STATUS_HFI_UPDATED (1 << 26) #define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2 #define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0) #define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1) #define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24) +#define PACKAGE_THERM_INT_HFI_ENABLE (1 << 25) /* Thermal Thresholds Support */ #define THERM_INT_THRESHOLD0_ENABLE (1 << 15) @@ -941,4 +1025,8 @@ #define MSR_VM_IGNNE 0xc0010115 #define MSR_VM_HSAVE_PA 0xc0010117 +/* Hardware Feedback Interface */ +#define MSR_IA32_HW_FEEDBACK_PTR 0x17d0 +#define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1 + #endif /* _ASM_X86_MSR_INDEX_H */ diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index b2d504f11937..aff774775c67 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -35,11 +35,7 @@ # define NEED_CMOV 0 #endif -#ifdef CONFIG_X86_USE_3DNOW -# define NEED_3DNOW (1<<(X86_FEATURE_3DNOW & 31)) -#else # define NEED_3DNOW 0 -#endif #if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64) # define NEED_NOPL (1<<(X86_FEATURE_NOPL & 31)) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 5a776a08f78c..21614807a2cb 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -373,9 +373,23 @@ struct kvm_debugregs { __u64 reserved[9]; }; -/* for KVM_CAP_XSAVE */ +/* for KVM_CAP_XSAVE and KVM_CAP_XSAVE2 */ struct kvm_xsave { + /* + * KVM_GET_XSAVE2 and KVM_SET_XSAVE write and read as many bytes + * as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) + * respectively, when invoked on the vm file descriptor. + * + * The size value returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) + * will always be at least 4096. Currently, it is only greater + * than 4096 if a dynamic feature has been enabled with + * ``arch_prctl()``, but this may change in the future. + * + * The offsets of the state save areas in struct kvm_xsave follow + * the contents of CPUID leaf 0xD on the host. + */ __u32 region[1024]; + __u32 extra[0]; }; #define KVM_MAX_XCRS 16 @@ -414,11 +428,12 @@ struct kvm_sync_regs { struct kvm_vcpu_events events; }; -#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) -#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) -#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) -#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) -#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) +#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) +#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) +#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) +#define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 @@ -438,6 +453,9 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 +/* attributes for system fd (group 0) */ +#define KVM_X86_XCOMP_GUEST_SUPP 0 + struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h index 754a07856817..500b96e71f18 100644 --- a/tools/arch/x86/include/uapi/asm/prctl.h +++ b/tools/arch/x86/include/uapi/asm/prctl.h @@ -2,20 +2,22 @@ #ifndef _ASM_X86_PRCTL_H #define _ASM_X86_PRCTL_H -#define ARCH_SET_GS 0x1001 -#define ARCH_SET_FS 0x1002 -#define ARCH_GET_FS 0x1003 -#define ARCH_GET_GS 0x1004 +#define ARCH_SET_GS 0x1001 +#define ARCH_SET_FS 0x1002 +#define ARCH_GET_FS 0x1003 +#define ARCH_GET_GS 0x1004 -#define ARCH_GET_CPUID 0x1011 -#define ARCH_SET_CPUID 0x1012 +#define ARCH_GET_CPUID 0x1011 +#define ARCH_SET_CPUID 0x1012 -#define ARCH_GET_XCOMP_SUPP 0x1021 -#define ARCH_GET_XCOMP_PERM 0x1022 -#define ARCH_REQ_XCOMP_PERM 0x1023 +#define ARCH_GET_XCOMP_SUPP 0x1021 +#define ARCH_GET_XCOMP_PERM 0x1022 +#define ARCH_REQ_XCOMP_PERM 0x1023 +#define ARCH_GET_XCOMP_GUEST_PERM 0x1024 +#define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 -#define ARCH_MAP_VDSO_X32 0x2001 -#define ARCH_MAP_VDSO_32 0x2002 -#define ARCH_MAP_VDSO_64 0x2003 +#define ARCH_MAP_VDSO_X32 0x2001 +#define ARCH_MAP_VDSO_32 0x2002 +#define ARCH_MAP_VDSO_64 0x2003 #endif /* _ASM_X86_PRCTL_H */ diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index efa969325ede..f69c168391aa 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -108,6 +108,14 @@ #define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 +#define SVM_VMGEXIT_PSC 0x80000010 +#define SVM_VMGEXIT_GUEST_REQUEST 0x80000011 +#define SVM_VMGEXIT_EXT_GUEST_REQUEST 0x80000012 +#define SVM_VMGEXIT_AP_CREATION 0x80000013 +#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0 +#define SVM_VMGEXIT_AP_CREATE 1 +#define SVM_VMGEXIT_AP_DESTROY 2 +#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ @@ -218,6 +226,11 @@ { SVM_VMGEXIT_NMI_COMPLETE, "vmgexit_nmi_complete" }, \ { SVM_VMGEXIT_AP_HLT_LOOP, "vmgexit_ap_hlt_loop" }, \ { SVM_VMGEXIT_AP_JUMP_TABLE, "vmgexit_ap_jump_table" }, \ + { SVM_VMGEXIT_PSC, "vmgexit_page_state_change" }, \ + { SVM_VMGEXIT_GUEST_REQUEST, "vmgexit_guest_request" }, \ + { SVM_VMGEXIT_EXT_GUEST_REQUEST, "vmgexit_ext_guest_request" }, \ + { SVM_VMGEXIT_AP_CREATION, "vmgexit_ap_creation" }, \ + { SVM_VMGEXIT_HV_FEATURES, "vmgexit_hypervisor_feature" }, \ { SVM_EXIT_ERR, "invalid_guest_state" } diff --git a/tools/arch/x86/intel_sdsi/Makefile b/tools/arch/x86/intel_sdsi/Makefile new file mode 100644 index 000000000000..5de2288cda79 --- /dev/null +++ b/tools/arch/x86/intel_sdsi/Makefile @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for Intel Software Defined Silicon provisioning tool + +intel_sdsi: intel_sdsi.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +override CFLAGS += -O2 -Wall + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f intel_sdsi + +install : intel_sdsi + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p intel_sdsi $(DESTDIR)$(BINDIR)/intel_sdsi diff --git a/tools/arch/x86/intel_sdsi/intel_sdsi.c b/tools/arch/x86/intel_sdsi/intel_sdsi.c new file mode 100644 index 000000000000..c0e2f2349db4 --- /dev/null +++ b/tools/arch/x86/intel_sdsi/intel_sdsi.c @@ -0,0 +1,558 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * sdsi: Intel Software Defined Silicon tool for provisioning certificates + * and activation payloads on supported cpus. + * + * See https://github.com/intel/intel-sdsi/blob/master/os-interface.rst + * for register descriptions. + * + * Copyright (C) 2022 Intel Corporation. All rights reserved. + */ + +#include <dirent.h> +#include <errno.h> +#include <fcntl.h> +#include <getopt.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include <sys/types.h> + +#define SDSI_DEV "intel_vsec.sdsi" +#define AUX_DEV_PATH "/sys/bus/auxiliary/devices/" +#define SDSI_PATH (AUX_DEV_DIR SDSI_DEV) +#define GUID 0x6dd191 +#define REGISTERS_MIN_SIZE 72 + +#define __round_mask(x, y) ((__typeof__(x))((y) - 1)) +#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1) + +struct enabled_features { + uint64_t reserved:3; + uint64_t sdsi:1; + uint64_t reserved1:60; +}; + +struct auth_fail_count { + uint64_t key_failure_count:3; + uint64_t key_failure_threshold:3; + uint64_t auth_failure_count:3; + uint64_t auth_failure_threshold:3; + uint64_t reserved:52; +}; + +struct availability { + uint64_t reserved:48; + uint64_t available:3; + uint64_t threshold:3; +}; + +struct sdsi_regs { + uint64_t ppin; + uint64_t reserved; + struct enabled_features en_features; + uint64_t reserved1; + struct auth_fail_count auth_fail_count; + struct availability prov_avail; + uint64_t reserved2; + uint64_t reserved3; + uint64_t socket_id; +}; + +struct sdsi_dev { + struct sdsi_regs regs; + char *dev_name; + char *dev_path; + int guid; +}; + +enum command { + CMD_NONE, + CMD_SOCKET_INFO, + CMD_DUMP_CERT, + CMD_PROV_AKC, + CMD_PROV_CAP, +}; + +static void sdsi_list_devices(void) +{ + struct dirent *entry; + DIR *aux_dir; + bool found = false; + + aux_dir = opendir(AUX_DEV_PATH); + if (!aux_dir) { + fprintf(stderr, "Cannot open directory %s\n", AUX_DEV_PATH); + return; + } + + while ((entry = readdir(aux_dir))) { + if (!strncmp(SDSI_DEV, entry->d_name, strlen(SDSI_DEV))) { + found = true; + printf("%s\n", entry->d_name); + } + } + + if (!found) + fprintf(stderr, "No sdsi devices found.\n"); +} + +static int sdsi_update_registers(struct sdsi_dev *s) +{ + FILE *regs_ptr; + int ret; + + memset(&s->regs, 0, sizeof(s->regs)); + + /* Open the registers file */ + ret = chdir(s->dev_path); + if (ret == -1) { + perror("chdir"); + return ret; + } + + regs_ptr = fopen("registers", "r"); + if (!regs_ptr) { + perror("Could not open 'registers' file"); + return -1; + } + + if (s->guid != GUID) { + fprintf(stderr, "Unrecognized guid, 0x%x\n", s->guid); + fclose(regs_ptr); + return -1; + } + + /* Update register info for this guid */ + ret = fread(&s->regs, sizeof(uint8_t), sizeof(s->regs), regs_ptr); + if (ret != sizeof(s->regs)) { + fprintf(stderr, "Could not read 'registers' file\n"); + fclose(regs_ptr); + return -1; + } + + fclose(regs_ptr); + + return 0; +} + +static int sdsi_read_reg(struct sdsi_dev *s) +{ + int ret; + + ret = sdsi_update_registers(s); + if (ret) + return ret; + + /* Print register info for this guid */ + printf("\n"); + printf("Socket information for device %s\n", s->dev_name); + printf("\n"); + printf("PPIN: 0x%lx\n", s->regs.ppin); + printf("Enabled Features\n"); + printf(" SDSi: %s\n", !!s->regs.en_features.sdsi ? "Enabled" : "Disabled"); + printf("Authorization Failure Count\n"); + printf(" AKC Failure Count: %d\n", s->regs.auth_fail_count.key_failure_count); + printf(" AKC Failure Threshold: %d\n", s->regs.auth_fail_count.key_failure_threshold); + printf(" CAP Failure Count: %d\n", s->regs.auth_fail_count.auth_failure_count); + printf(" CAP Failure Threshold: %d\n", s->regs.auth_fail_count.auth_failure_threshold); + printf("Provisioning Availability\n"); + printf(" Updates Available: %d\n", s->regs.prov_avail.available); + printf(" Updates Threshold: %d\n", s->regs.prov_avail.threshold); + printf("Socket ID: %ld\n", s->regs.socket_id & 0xF); + + return 0; +} + +static int sdsi_certificate_dump(struct sdsi_dev *s) +{ + uint64_t state_certificate[512] = {0}; + bool first_instance; + uint64_t previous; + FILE *cert_ptr; + int i, ret, size; + + ret = sdsi_update_registers(s); + if (ret) + return ret; + + if (!s->regs.en_features.sdsi) { + fprintf(stderr, "SDSi feature is present but not enabled."); + fprintf(stderr, " Unable to read state certificate"); + return -1; + } + + ret = chdir(s->dev_path); + if (ret == -1) { + perror("chdir"); + return ret; + } + + cert_ptr = fopen("state_certificate", "r"); + if (!cert_ptr) { + perror("Could not open 'state_certificate' file"); + return -1; + } + + size = fread(state_certificate, 1, sizeof(state_certificate), cert_ptr); + if (!size) { + fprintf(stderr, "Could not read 'state_certificate' file\n"); + fclose(cert_ptr); + return -1; + } + + printf("%3d: 0x%lx\n", 0, state_certificate[0]); + previous = state_certificate[0]; + first_instance = true; + + for (i = 1; i < (int)(round_up(size, sizeof(uint64_t))/sizeof(uint64_t)); i++) { + if (state_certificate[i] == previous) { + if (first_instance) { + puts("*"); + first_instance = false; + } + continue; + } + printf("%3d: 0x%lx\n", i, state_certificate[i]); + previous = state_certificate[i]; + first_instance = true; + } + printf("%3d\n", i); + + fclose(cert_ptr); + + return 0; +} + +static int sdsi_provision(struct sdsi_dev *s, char *bin_file, enum command command) +{ + int bin_fd, prov_fd, size, ret; + char buf[4096] = { 0 }; + char cap[] = "provision_cap"; + char akc[] = "provision_akc"; + char *prov_file; + + if (!bin_file) { + fprintf(stderr, "No binary file provided\n"); + return -1; + } + + /* Open the binary */ + bin_fd = open(bin_file, O_RDONLY); + if (bin_fd == -1) { + fprintf(stderr, "Could not open file %s: %s\n", bin_file, strerror(errno)); + return bin_fd; + } + + prov_file = (command == CMD_PROV_AKC) ? akc : cap; + + ret = chdir(s->dev_path); + if (ret == -1) { + perror("chdir"); + close(bin_fd); + return ret; + } + + /* Open the provision file */ + prov_fd = open(prov_file, O_WRONLY); + if (prov_fd == -1) { + fprintf(stderr, "Could not open file %s: %s\n", prov_file, strerror(errno)); + close(bin_fd); + return prov_fd; + } + + /* Read the binary file into the buffer */ + size = read(bin_fd, buf, 4096); + if (size == -1) { + close(bin_fd); + close(prov_fd); + return -1; + } + + ret = write(prov_fd, buf, size); + if (ret == -1) { + close(bin_fd); + close(prov_fd); + perror("Provisioning failed"); + return ret; + } + + printf("Provisioned %s file %s successfully\n", prov_file, bin_file); + + close(bin_fd); + close(prov_fd); + + return 0; +} + +static int sdsi_provision_akc(struct sdsi_dev *s, char *bin_file) +{ + int ret; + + ret = sdsi_update_registers(s); + if (ret) + return ret; + + if (!s->regs.en_features.sdsi) { + fprintf(stderr, "SDSi feature is present but not enabled. Unable to provision"); + return -1; + } + + if (!s->regs.prov_avail.available) { + fprintf(stderr, "Maximum number of updates (%d) has been reached.\n", + s->regs.prov_avail.threshold); + return -1; + } + + if (s->regs.auth_fail_count.key_failure_count == + s->regs.auth_fail_count.key_failure_threshold) { + fprintf(stderr, "Maximum number of AKC provision failures (%d) has been reached.\n", + s->regs.auth_fail_count.key_failure_threshold); + fprintf(stderr, "Power cycle the system to reset the counter\n"); + return -1; + } + + return sdsi_provision(s, bin_file, CMD_PROV_AKC); +} + +static int sdsi_provision_cap(struct sdsi_dev *s, char *bin_file) +{ + int ret; + + ret = sdsi_update_registers(s); + if (ret) + return ret; + + if (!s->regs.en_features.sdsi) { + fprintf(stderr, "SDSi feature is present but not enabled. Unable to provision"); + return -1; + } + + if (!s->regs.prov_avail.available) { + fprintf(stderr, "Maximum number of updates (%d) has been reached.\n", + s->regs.prov_avail.threshold); + return -1; + } + + if (s->regs.auth_fail_count.auth_failure_count == + s->regs.auth_fail_count.auth_failure_threshold) { + fprintf(stderr, "Maximum number of CAP provision failures (%d) has been reached.\n", + s->regs.auth_fail_count.auth_failure_threshold); + fprintf(stderr, "Power cycle the system to reset the counter\n"); + return -1; + } + + return sdsi_provision(s, bin_file, CMD_PROV_CAP); +} + +static int read_sysfs_data(const char *file, int *value) +{ + char buff[16]; + FILE *fp; + + fp = fopen(file, "r"); + if (!fp) { + perror(file); + return -1; + } + + if (!fgets(buff, 16, fp)) { + fprintf(stderr, "Failed to read file '%s'", file); + fclose(fp); + return -1; + } + + fclose(fp); + *value = strtol(buff, NULL, 0); + + return 0; +} + +static struct sdsi_dev *sdsi_create_dev(char *dev_no) +{ + int dev_name_len = sizeof(SDSI_DEV) + strlen(dev_no) + 1; + struct sdsi_dev *s; + int guid; + DIR *dir; + + s = (struct sdsi_dev *)malloc(sizeof(*s)); + if (!s) { + perror("malloc"); + return NULL; + } + + s->dev_name = (char *)malloc(sizeof(SDSI_DEV) + strlen(dev_no) + 1); + if (!s->dev_name) { + perror("malloc"); + free(s); + return NULL; + } + + snprintf(s->dev_name, dev_name_len, "%s.%s", SDSI_DEV, dev_no); + + s->dev_path = (char *)malloc(sizeof(AUX_DEV_PATH) + dev_name_len); + if (!s->dev_path) { + perror("malloc"); + free(s->dev_name); + free(s); + return NULL; + } + + snprintf(s->dev_path, sizeof(AUX_DEV_PATH) + dev_name_len, "%s%s", AUX_DEV_PATH, + s->dev_name); + dir = opendir(s->dev_path); + if (!dir) { + fprintf(stderr, "Could not open directory '%s': %s\n", s->dev_path, + strerror(errno)); + free(s->dev_path); + free(s->dev_name); + free(s); + return NULL; + } + + if (chdir(s->dev_path) == -1) { + perror("chdir"); + free(s->dev_path); + free(s->dev_name); + free(s); + return NULL; + } + + if (read_sysfs_data("guid", &guid)) { + free(s->dev_path); + free(s->dev_name); + free(s); + return NULL; + } + + s->guid = guid; + + return s; +} + +static void sdsi_free_dev(struct sdsi_dev *s) +{ + free(s->dev_path); + free(s->dev_name); + free(s); +} + +static void usage(char *prog) +{ + printf("Usage: %s [-l] [-d DEVNO [-iD] [-a FILE] [-c FILE]]\n", prog); +} + +static void show_help(void) +{ + printf("Commands:\n"); + printf(" %-18s\t%s\n", "-l, --list", "list available sdsi devices"); + printf(" %-18s\t%s\n", "-d, --devno DEVNO", "sdsi device number"); + printf(" %-18s\t%s\n", "-i --info", "show socket information"); + printf(" %-18s\t%s\n", "-D --dump", "dump state certificate data"); + printf(" %-18s\t%s\n", "-a --akc FILE", "provision socket with AKC FILE"); + printf(" %-18s\t%s\n", "-c --cap FILE>", "provision socket with CAP FILE"); +} + +int main(int argc, char *argv[]) +{ + char bin_file[PATH_MAX], *dev_no = NULL; + char *progname; + enum command command = CMD_NONE; + struct sdsi_dev *s; + int ret = 0, opt; + int option_index = 0; + + static struct option long_options[] = { + {"akc", required_argument, 0, 'a'}, + {"cap", required_argument, 0, 'c'}, + {"devno", required_argument, 0, 'd'}, + {"dump", no_argument, 0, 'D'}, + {"help", no_argument, 0, 'h'}, + {"info", no_argument, 0, 'i'}, + {"list", no_argument, 0, 'l'}, + {0, 0, 0, 0 } + }; + + + progname = argv[0]; + + while ((opt = getopt_long_only(argc, argv, "+a:c:d:Da:c:h", long_options, + &option_index)) != -1) { + switch (opt) { + case 'd': + dev_no = optarg; + break; + case 'l': + sdsi_list_devices(); + return 0; + case 'i': + command = CMD_SOCKET_INFO; + break; + case 'D': + command = CMD_DUMP_CERT; + break; + case 'a': + case 'c': + if (!access(optarg, F_OK) == 0) { + fprintf(stderr, "Could not open file '%s': %s\n", optarg, + strerror(errno)); + return -1; + } + + if (!realpath(optarg, bin_file)) { + perror("realpath"); + return -1; + } + + command = (opt == 'a') ? CMD_PROV_AKC : CMD_PROV_CAP; + break; + case 'h': + usage(progname); + show_help(); + return 0; + default: + usage(progname); + return -1; + } + } + + if (!dev_no) { + if (command != CMD_NONE) + fprintf(stderr, "Missing device number, DEVNO, for this command\n"); + usage(progname); + return -1; + } + + s = sdsi_create_dev(dev_no); + if (!s) + return -1; + + /* Run the command */ + switch (command) { + case CMD_NONE: + fprintf(stderr, "Missing command for device %s\n", dev_no); + usage(progname); + break; + case CMD_SOCKET_INFO: + ret = sdsi_read_reg(s); + break; + case CMD_DUMP_CERT: + ret = sdsi_certificate_dump(s); + break; + case CMD_PROV_AKC: + ret = sdsi_provision_akc(s, bin_file); + break; + case CMD_PROV_CAP: + ret = sdsi_provision_cap(s, bin_file); + break; + } + + + sdsi_free_dev(s); + + return ret; +} diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 1cc9da6e29c7..d0d7b9bc6cad 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -27,8 +27,7 @@ * Output: * rax original destination */ -SYM_FUNC_START_ALIAS(__memcpy) -SYM_FUNC_START_WEAK(memcpy) +SYM_FUNC_START(__memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS @@ -39,12 +38,13 @@ SYM_FUNC_START_WEAK(memcpy) rep movsq movl %edx, %ecx rep movsb - ret -SYM_FUNC_END(memcpy) -SYM_FUNC_END_ALIAS(__memcpy) -EXPORT_SYMBOL(memcpy) + RET +SYM_FUNC_END(__memcpy) EXPORT_SYMBOL(__memcpy) +SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy) +EXPORT_SYMBOL(memcpy) + /* * memcpy_erms() - enhanced fast string memcpy. This is faster and * simpler than memcpy. Use memcpy_erms when possible. @@ -53,7 +53,7 @@ SYM_FUNC_START_LOCAL(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb - ret + RET SYM_FUNC_END(memcpy_erms) SYM_FUNC_START_LOCAL(memcpy_orig) @@ -137,7 +137,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movq %r9, 1*8(%rdi) movq %r10, -2*8(%rdi, %rdx) movq %r11, -1*8(%rdi, %rdx) - retq + RET .p2align 4 .Lless_16bytes: cmpl $8, %edx @@ -149,7 +149,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movq -1*8(%rsi, %rdx), %r9 movq %r8, 0*8(%rdi) movq %r9, -1*8(%rdi, %rdx) - retq + RET .p2align 4 .Lless_8bytes: cmpl $4, %edx @@ -162,7 +162,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movl -4(%rsi, %rdx), %r8d movl %ecx, (%rdi) movl %r8d, -4(%rdi, %rdx) - retq + RET .p2align 4 .Lless_3bytes: subl $1, %edx @@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movb %cl, (%rdi) .Lend: - retq + RET SYM_FUNC_END(memcpy_orig) .popsection diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 9827ae267f96..fc9ffd3ff3b2 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -17,7 +17,6 @@ * * rax original destination */ -SYM_FUNC_START_WEAK(memset) SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended @@ -40,12 +39,13 @@ SYM_FUNC_START(__memset) movl %edx,%ecx rep stosb movq %r9,%rax - ret + RET SYM_FUNC_END(__memset) -SYM_FUNC_END_ALIAS(memset) -EXPORT_SYMBOL(memset) EXPORT_SYMBOL(__memset) +SYM_FUNC_ALIAS_WEAK(memset, __memset) +EXPORT_SYMBOL(memset) + /* * ISO C memset - set a memory block to a byte value. This function uses * enhanced rep stosb to override the fast string function. @@ -63,7 +63,7 @@ SYM_FUNC_START_LOCAL(memset_erms) movq %rdx,%rcx rep stosb movq %r9,%rax - ret + RET SYM_FUNC_END(memset_erms) SYM_FUNC_START_LOCAL(memset_orig) @@ -125,7 +125,7 @@ SYM_FUNC_START_LOCAL(memset_orig) .Lende: movq %r10,%rax - ret + RET .Lbad_alignment: cmpq $7,%rdx diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt index ec31f5b60323..d12d1358f96d 100644 --- a/tools/arch/x86/lib/x86-opcode-map.txt +++ b/tools/arch/x86/lib/x86-opcode-map.txt @@ -690,7 +690,10 @@ AVXcode: 2 45: vpsrlvd/q Vx,Hx,Wx (66),(v) 46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo) 47: vpsllvd/q Vx,Hx,Wx (66),(v) -# Skip 0x48-0x4b +# Skip 0x48 +49: TILERELEASE (v1),(000),(11B) | LDTILECFG Mtc (v1)(000) | STTILECFG Mtc (66),(v1),(000) | TILEZERO Vt (F2),(v1),(11B) +# Skip 0x4a +4b: TILELOADD Vt,Wsm (F2),(v1) | TILELOADDT1 Vt,Wsm (66),(v1) | TILESTORED Wsm,Vt (F3),(v) 4c: vrcp14ps/d Vpd,Wpd (66),(ev) 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) @@ -705,7 +708,10 @@ AVXcode: 2 59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) 5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) 5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) -# Skip 0x5c-0x61 +5c: TDPBF16PS Vt,Wt,Ht (F3),(v1) +# Skip 0x5d +5e: TDPBSSD Vt,Wt,Ht (F2),(v1) | TDPBSUD Vt,Wt,Ht (F3),(v1) | TDPBUSD Vt,Wt,Ht (66),(v1) | TDPBUUD Vt,Wt,Ht (v1) +# Skip 0x5f-0x61 62: vpexpandb/w Vx,Wx (66),(ev) 63: vpcompressb/w Wx,Vx (66),(ev) 64: vpblendmd/q Vx,Hx,Wx (66),(ev) @@ -822,9 +828,9 @@ AVXcode: 3 05: vpermilpd Vx,Wx,Ib (66),(v) 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v) 07: -08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) +08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) | vrndscaleph Vx,Wx,Ib (evo) 09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo) -0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) +0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) | vrndscalesh Vx,Hx,Wx,Ib (evo) 0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo) 0c: vblendps Vx,Hx,Wx,Ib (66) 0d: vblendpd Vx,Hx,Wx,Ib (66) @@ -846,8 +852,8 @@ AVXcode: 3 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1) 23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) 25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev) -26: vgetmantps/d Vx,Wx,Ib (66),(ev) -27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) +26: vgetmantps/d Vx,Wx,Ib (66),(ev) | vgetmantph Vx,Wx,Ib (ev) +27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) | vgetmantsh Vx,Hx,Wx,Ib (ev) 30: kshiftrb/w Vk,Uk,Ib (66),(v) 31: kshiftrd/q Vk,Uk,Ib (66),(v) 32: kshiftlb/w Vk,Uk,Ib (66),(v) @@ -871,23 +877,102 @@ AVXcode: 3 51: vrangess/d Vx,Hx,Wx,Ib (66),(ev) 54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev) 55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev) -56: vreduceps/d Vx,Wx,Ib (66),(ev) -57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) +56: vreduceps/d Vx,Wx,Ib (66),(ev) | vreduceph Vx,Wx,Ib (ev) +57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) | vreducesh Vx,Hx,Wx,Ib (ev) 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1) 61: vpcmpestri Vdq,Wdq,Ib (66),(v1) 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) -66: vfpclassps/d Vk,Wx,Ib (66),(ev) -67: vfpclassss/d Vk,Wx,Ib (66),(ev) +66: vfpclassps/d Vk,Wx,Ib (66),(ev) | vfpclassph Vx,Wx,Ib (ev) +67: vfpclassss/d Vk,Wx,Ib (66),(ev) | vfpclasssh Vx,Wx,Ib (ev) 70: vpshldw Vx,Hx,Wx,Ib (66),(ev) 71: vpshldd/q Vx,Hx,Wx,Ib (66),(ev) 72: vpshrdw Vx,Hx,Wx,Ib (66),(ev) 73: vpshrdd/q Vx,Hx,Wx,Ib (66),(ev) +c2: vcmpph Vx,Hx,Wx,Ib (ev) | vcmpsh Vx,Hx,Wx,Ib (F3),(ev) cc: sha1rnds4 Vdq,Wdq,Ib ce: vgf2p8affineqb Vx,Wx,Ib (66) cf: vgf2p8affineinvqb Vx,Wx,Ib (66) df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) -f0: RORX Gy,Ey,Ib (F2),(v) +f0: RORX Gy,Ey,Ib (F2),(v) | HRESET Gv,Ib (F3),(000),(11B) +EndTable + +Table: EVEX map 5 +Referrer: +AVXcode: 5 +10: vmovsh Vx,Hx,Wx (F3),(ev) | vmovsh Vx,Wx (F3),(ev) +11: vmovsh Wx,Hx,Vx (F3),(ev) | vmovsh Wx,Vx (F3),(ev) +1d: vcvtps2phx Vx,Wx (66),(ev) | vcvtss2sh Vx,Hx,Wx (ev) +2a: vcvtsi2sh Vx,Hx,Wx (F3),(ev) +2c: vcvttsh2si Vx,Wx (F3),(ev) +2d: vcvtsh2si Vx,Wx (F3),(ev) +2e: vucomish Vx,Wx (ev) +2f: vcomish Vx,Wx (ev) +51: vsqrtph Vx,Wx (ev) | vsqrtsh Vx,Hx,Wx (F3),(ev) +58: vaddph Vx,Hx,Wx (ev) | vaddsh Vx,Hx,Wx (F3),(ev) +59: vmulph Vx,Hx,Wx (ev) | vmulsh Vx,Hx,Wx (F3),(ev) +5a: vcvtpd2ph Vx,Wx (66),(ev) | vcvtph2pd Vx,Wx (ev) | vcvtsd2sh Vx,Hx,Wx (F2),(ev) | vcvtsh2sd Vx,Hx,Wx (F3),(ev) +5b: vcvtdq2ph Vx,Wx (ev) | vcvtph2dq Vx,Wx (66),(ev) | vcvtqq2ph Vx,Wx (ev) | vcvttph2dq Vx,Wx (F3),(ev) +5c: vsubph Vx,Hx,Wx (ev) | vsubsh Vx,Hx,Wx (F3),(ev) +5d: vminph Vx,Hx,Wx (ev) | vminsh Vx,Hx,Wx (F3),(ev) +5e: vdivph Vx,Hx,Wx (ev) | vdivsh Vx,Hx,Wx (F3),(ev) +5f: vmaxph Vx,Hx,Wx (ev) | vmaxsh Vx,Hx,Wx (F3),(ev) +6e: vmovw Vx,Wx (66),(ev) +78: vcvttph2udq Vx,Wx (ev) | vcvttph2uqq Vx,Wx (66),(ev) | vcvttsh2usi Vx,Wx (F3),(ev) +79: vcvtph2udq Vx,Wx (ev) | vcvtph2uqq Vx,Wx (66),(ev) | vcvtsh2usi Vx,Wx (F3),(ev) +7a: vcvttph2qq Vx,Wx (66),(ev) | vcvtudq2ph Vx,Wx (F2),(ev) | vcvtuqq2ph Vx,Wx (F2),(ev) +7b: vcvtph2qq Vx,Wx (66),(ev) | vcvtusi2sh Vx,Hx,Wx (F3),(ev) +7c: vcvttph2uw Vx,Wx (ev) | vcvttph2w Vx,Wx (66),(ev) +7d: vcvtph2uw Vx,Wx (ev) | vcvtph2w Vx,Wx (66),(ev) | vcvtuw2ph Vx,Wx (F2),(ev) | vcvtw2ph Vx,Wx (F3),(ev) +7e: vmovw Wx,Vx (66),(ev) +EndTable + +Table: EVEX map 6 +Referrer: +AVXcode: 6 +13: vcvtph2psx Vx,Wx (66),(ev) | vcvtsh2ss Vx,Hx,Wx (ev) +2c: vscalefph Vx,Hx,Wx (66),(ev) +2d: vscalefsh Vx,Hx,Wx (66),(ev) +42: vgetexpph Vx,Wx (66),(ev) +43: vgetexpsh Vx,Hx,Wx (66),(ev) +4c: vrcpph Vx,Wx (66),(ev) +4d: vrcpsh Vx,Hx,Wx (66),(ev) +4e: vrsqrtph Vx,Wx (66),(ev) +4f: vrsqrtsh Vx,Hx,Wx (66),(ev) +56: vfcmaddcph Vx,Hx,Wx (F2),(ev) | vfmaddcph Vx,Hx,Wx (F3),(ev) +57: vfcmaddcsh Vx,Hx,Wx (F2),(ev) | vfmaddcsh Vx,Hx,Wx (F3),(ev) +96: vfmaddsub132ph Vx,Hx,Wx (66),(ev) +97: vfmsubadd132ph Vx,Hx,Wx (66),(ev) +98: vfmadd132ph Vx,Hx,Wx (66),(ev) +99: vfmadd132sh Vx,Hx,Wx (66),(ev) +9a: vfmsub132ph Vx,Hx,Wx (66),(ev) +9b: vfmsub132sh Vx,Hx,Wx (66),(ev) +9c: vfnmadd132ph Vx,Hx,Wx (66),(ev) +9d: vfnmadd132sh Vx,Hx,Wx (66),(ev) +9e: vfnmsub132ph Vx,Hx,Wx (66),(ev) +9f: vfnmsub132sh Vx,Hx,Wx (66),(ev) +a6: vfmaddsub213ph Vx,Hx,Wx (66),(ev) +a7: vfmsubadd213ph Vx,Hx,Wx (66),(ev) +a8: vfmadd213ph Vx,Hx,Wx (66),(ev) +a9: vfmadd213sh Vx,Hx,Wx (66),(ev) +aa: vfmsub213ph Vx,Hx,Wx (66),(ev) +ab: vfmsub213sh Vx,Hx,Wx (66),(ev) +ac: vfnmadd213ph Vx,Hx,Wx (66),(ev) +ad: vfnmadd213sh Vx,Hx,Wx (66),(ev) +ae: vfnmsub213ph Vx,Hx,Wx (66),(ev) +af: vfnmsub213sh Vx,Hx,Wx (66),(ev) +b6: vfmaddsub231ph Vx,Hx,Wx (66),(ev) +b7: vfmsubadd231ph Vx,Hx,Wx (66),(ev) +b8: vfmadd231ph Vx,Hx,Wx (66),(ev) +b9: vfmadd231sh Vx,Hx,Wx (66),(ev) +ba: vfmsub231ph Vx,Hx,Wx (66),(ev) +bb: vfmsub231sh Vx,Hx,Wx (66),(ev) +bc: vfnmadd231ph Vx,Hx,Wx (66),(ev) +bd: vfnmadd231sh Vx,Hx,Wx (66),(ev) +be: vfnmsub231ph Vx,Hx,Wx (66),(ev) +bf: vfnmsub231sh Vx,Hx,Wx (66),(ev) +d6: vfcmulcph Vx,Hx,Wx (F2),(ev) | vfmulcph Vx,Hx,Wx (F3),(ev) +d7: vfcmulcsh Vx,Hx,Wx (F2),(ev) | vfmulcsh Vx,Hx,Wx (F3),(ev) EndTable GrpTable: Grp1 @@ -970,7 +1055,7 @@ GrpTable: Grp7 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv -5: rdpkru (110),(11B) | wrpkru (111),(11B) | SAVEPREVSSP (F3),(010),(11B) | RSTORSSP Mq (F3) | SETSSBSY (F3),(000),(11B) +5: rdpkru (110),(11B) | wrpkru (111),(11B) | SAVEPREVSSP (F3),(010),(11B) | RSTORSSP Mq (F3) | SETSSBSY (F3),(000),(11B) | CLUI (F3),(110),(11B) | SERIALIZE (000),(11B) | STUI (F3),(111),(11B) | TESTUI (F3)(101)(11B) | UIRET (F3),(100),(11B) | XRESLDTRK (F2),(000),(11B) | XSUSLDTRK (F2),(001),(11B) 6: LMSW Ew 7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B) EndTable @@ -987,7 +1072,7 @@ GrpTable: Grp9 3: xrstors 4: xsavec 5: xsaves -6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) +6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) | SENDUIPI Gq (F3) 7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B) EndTable diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst index bc276388f432..68454ef28f58 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -25,6 +25,8 @@ GEN COMMANDS | **bpftool** **gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] | **bpftool** **gen skeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen subskeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] | **bpftool** **gen help** DESCRIPTION @@ -149,6 +151,50 @@ DESCRIPTION (non-read-only) data from userspace, with same simplicity as for BPF side. + **bpftool gen subskeleton** *FILE* + Generate BPF subskeleton C header file for a given *FILE*. + + Subskeletons are similar to skeletons, except they do not own + the corresponding maps, programs, or global variables. They + require that the object file used to generate them is already + loaded into a *bpf_object* by some other means. + + This functionality is useful when a library is included into a + larger BPF program. A subskeleton for the library would have + access to all objects and globals defined in it, without + having to know about the larger program. + + Consequently, there are only two functions defined + for subskeletons: + + - **example__open(bpf_object\*)** + Instantiates a subskeleton from an already opened (but not + necessarily loaded) **bpf_object**. + + - **example__destroy()** + Frees the storage for the subskeleton but *does not* unload + any BPF programs or maps. + + **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] + Generate a minimum BTF file as *OUTPUT*, derived from a given + *INPUT* BTF file, containing all needed BTF types so one, or + more, given eBPF objects CO-RE relocations may be satisfied. + + When kernels aren't compiled with CONFIG_DEBUG_INFO_BTF, + libbpf, when loading an eBPF object, has to rely on external + BTF files to be able to calculate CO-RE relocations. + + Usually, an external BTF file is built from existing kernel + DWARF data using pahole. It contains all the types used by + its respective kernel image and, because of that, is big. + + The min_core_btf feature builds smaller BTF files, customized + to one or multiple eBPF objects, so they can be distributed + together with an eBPF CO-RE based application, turning the + application portable to different kernel versions. + + Check examples bellow for more information how to use it. + **bpftool gen help** Print short help message. @@ -215,7 +261,9 @@ This is example BPF application with two BPF programs and a mix of BPF maps and global variables. Source code is split across two source code files. **$ clang -target bpf -g example1.bpf.c -o example1.bpf.o** + **$ clang -target bpf -g example2.bpf.c -o example2.bpf.o** + **$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o** This set of commands compiles *example1.bpf.c* and *example2.bpf.c* @@ -329,3 +377,70 @@ BPF ELF object file *example.bpf.o*. my_static_var: 7 This is a stripped-out version of skeleton generated for above example code. + +min_core_btf +------------ + +**$ bpftool btf dump file 5.4.0-example.btf format raw** + +:: + + [1] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [2] CONST '(anon)' type_id=1 + [3] VOLATILE '(anon)' type_id=1 + [4] ARRAY '(anon)' type_id=1 index_type_id=21 nr_elems=2 + [5] PTR '(anon)' type_id=8 + [6] CONST '(anon)' type_id=5 + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=(none) + [8] CONST '(anon)' type_id=7 + [9] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + <long output> + +**$ bpftool btf dump file one.bpf.o format raw** + +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=4 + 'ent' type_id=3 bits_offset=0 + 'id' type_id=7 bits_offset=64 + 'args' type_id=9 bits_offset=128 + '__data' type_id=12 bits_offset=512 + [3] STRUCT 'trace_entry' size=8 vlen=4 + 'type' type_id=4 bits_offset=0 + 'flags' type_id=5 bits_offset=16 + 'preempt_count' type_id=5 bits_offset=24 + <long output> + +**$ bpftool gen min_core_btf 5.4.0-example.btf 5.4.0-smaller.btf one.bpf.o** + +**$ bpftool btf dump file 5.4.0-smaller.btf format raw** + +:: + + [1] TYPEDEF 'pid_t' type_id=6 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=1 + 'args' type_id=4 bits_offset=128 + [3] STRUCT 'task_struct' size=9216 vlen=2 + 'pid' type_id=1 bits_offset=17920 + 'real_parent' type_id=7 bits_offset=18048 + [4] ARRAY '(anon)' type_id=5 index_type_id=8 nr_elems=6 + [5] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [6] TYPEDEF '__kernel_pid_t' type_id=8 + [7] PTR '(anon)' type_id=3 + [8] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + <end> + +Now, the "5.4.0-smaller.btf" file may be used by libbpf as an external BTF file +when loading the "one.bpf.o" object into the "5.4.0-example" kernel. Note that +the generated BTF file won't allow other eBPF objects to be loaded, just the +ones given to min_core_btf. + +:: + + LIBBPF_OPTS(bpf_object_open_opts, opts, .btf_custom_path = "5.4.0-smaller.btf"); + struct bpf_object *obj; + + obj = bpf_object__open_file("one.bpf.o", &opts); + + ... diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 7084dd9fa2f8..6965c94dfdaf 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -20,7 +20,8 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** } + *OBJECT* := { **map** | **program** | **link** | **cgroup** | **perf** | **net** | **feature** | + **btf** | **gen** | **struct_ops** | **iter** } *OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } @@ -31,6 +32,8 @@ SYNOPSIS *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | **load** | **attach** | **detach** | **help** } + *LINK-COMMANDS* := { **show** | **list** | **pin** | **detach** | **help** } + *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } *PERF-COMMANDS* := { **show** | **list** | **help** } @@ -39,6 +42,14 @@ SYNOPSIS *FEATURE-COMMANDS* := { **probe** | **help** } + *BTF-COMMANDS* := { **show** | **list** | **dump** | **help** } + + *GEN-COMMANDS* := { **object** | **skeleton** | **min_core_btf** | **help** } + + *STRUCT-OPS-COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } + + *ITER-COMMANDS* := { **pin** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects diff --git a/tools/bpf/bpftool/Documentation/common_options.rst b/tools/bpf/bpftool/Documentation/common_options.rst index 908487b9c2ad..4107a586b68b 100644 --- a/tools/bpf/bpftool/Documentation/common_options.rst +++ b/tools/bpf/bpftool/Documentation/common_options.rst @@ -4,12 +4,13 @@ Print short help message (similar to **bpftool help**). -V, --version - Print version number (similar to **bpftool version**), and optional - features that were included when bpftool was compiled. Optional - features include linking against libbfd to provide the disassembler - for JIT-ted programs (**bpftool prog dump jited**) and usage of BPF - skeletons (some features like **bpftool prog profile** or showing - pids associated to BPF objects may rely on it). + Print bpftool's version number (similar to **bpftool version**), the + number of the libbpf version in use, and optional features that were + included when bpftool was compiled. Optional features include linking + against libbfd to provide the disassembler for JIT-ted programs + (**bpftool prog dump jited**) and usage of BPF skeletons (some + features like **bpftool prog profile** or showing pids associated to + BPF objects may rely on it). -j, --json Generate JSON output. For commands that cannot produce JSON, this diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 83369f55df61..c6d2c77d0252 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -18,37 +18,33 @@ BPF_DIR = $(srctree)/tools/lib/bpf ifneq ($(OUTPUT),) _OUTPUT := $(OUTPUT) else - _OUTPUT := $(CURDIR) + _OUTPUT := $(CURDIR)/ endif -BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/ +BOOTSTRAP_OUTPUT := $(_OUTPUT)bootstrap/ -LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/ +LIBBPF_OUTPUT := $(_OUTPUT)libbpf/ LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) -LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf LIBBPF := $(LIBBPF_OUTPUT)libbpf.a LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/ LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT) -LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)/include +LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)include LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a -# We need to copy hashmap.h and nlattr.h which is not otherwise exported by -# libbpf, but still required by bpftool. -LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h) -LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h) - -ifeq ($(BPFTOOL_VERSION),) -BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion) -endif +# We need to copy hashmap.h, nlattr.h, relo_core.h and libbpf_internal.h +# which are not otherwise exported by libbpf, but still required by bpftool. +LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h relo_core.h libbpf_internal.h) +LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h relo_core.h libbpf_internal.h) $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR): $(QUIET_MKDIR)mkdir -p $@ $(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \ - DESTDIR=$(LIBBPF_DESTDIR) prefix= $(LIBBPF) install_headers + DESTDIR=$(LIBBPF_DESTDIR:/=) prefix= $(LIBBPF) install_headers $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR) $(call QUIET_INSTALL, $@) @@ -56,7 +52,7 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_ $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ - DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR) prefix= \ + DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \ ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) @@ -78,12 +74,14 @@ CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS)) CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ - -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(or $(OUTPUT),.) \ -I$(LIBBPF_INCLUDE) \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi +ifneq ($(BPFTOOL_VERSION),) CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' +endif ifneq ($(EXTRA_CFLAGS),) CFLAGS += $(EXTRA_CFLAGS) endif @@ -95,7 +93,7 @@ INSTALL ?= install RM ?= rm -f FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib libcap \ +FEATURE_TESTS = libbfd disassembler-four-args zlib libcap \ clang-bpf-co-re FEATURE_DISPLAY = libbfd disassembler-four-args zlib libcap \ clang-bpf-co-re @@ -120,10 +118,6 @@ ifeq ($(feature-disassembler-four-args), 1) CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE endif -ifeq ($(feature-reallocarray), 0) -CFLAGS += -DCOMPAT_NEED_REALLOCARRAY -endif - LIBS = $(LIBBPF) -lelf -lz LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz ifeq ($(feature-libcap), 1) @@ -186,7 +180,7 @@ endif $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) $(QUIET_CLANG)$(CLANG) \ - -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(or $(OUTPUT),.) \ -I$(srctree)/tools/include/uapi/ \ -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ -g -O2 -Wall -target bpf -c $< -o $@ diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 493753a4962e..5df8d72c5179 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -1003,9 +1003,25 @@ _bpftool() ;; esac ;; + subskeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; + min_core_btf) + _filedir + return 0 + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'object skeleton help' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'object skeleton subskeleton help min_core_btf' -- "$cur" ) ) ;; esac ;; diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 59833125ac0a..7e6accb9d9f7 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -459,6 +459,51 @@ done: return err; } +static const char sysfs_vmlinux[] = "/sys/kernel/btf/vmlinux"; + +static struct btf *get_vmlinux_btf_from_sysfs(void) +{ + struct btf *base; + + base = btf__parse(sysfs_vmlinux, NULL); + if (libbpf_get_error(base)) { + p_err("failed to parse vmlinux BTF at '%s': %ld\n", + sysfs_vmlinux, libbpf_get_error(base)); + base = NULL; + } + + return base; +} + +#define BTF_NAME_BUFF_LEN 64 + +static bool btf_is_kernel_module(__u32 btf_id) +{ + struct bpf_btf_info btf_info = {}; + char btf_name[BTF_NAME_BUFF_LEN]; + int btf_fd; + __u32 len; + int err; + + btf_fd = bpf_btf_get_fd_by_id(btf_id); + if (btf_fd < 0) { + p_err("can't get BTF object by id (%u): %s", btf_id, strerror(errno)); + return false; + } + + len = sizeof(btf_info); + btf_info.name = ptr_to_u64(btf_name); + btf_info.name_len = sizeof(btf_name); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + close(btf_fd); + if (err) { + p_err("can't get BTF (ID %u) object info: %s", btf_id, strerror(errno)); + return false; + } + + return btf_info.kernel_btf && strncmp(btf_name, "vmlinux", sizeof(btf_name)) != 0; +} + static int do_dump(int argc, char **argv) { struct btf *btf = NULL, *base = NULL; @@ -536,18 +581,11 @@ static int do_dump(int argc, char **argv) NEXT_ARG(); } else if (is_prefix(src, "file")) { const char sysfs_prefix[] = "/sys/kernel/btf/"; - const char sysfs_vmlinux[] = "/sys/kernel/btf/vmlinux"; if (!base_btf && strncmp(*argv, sysfs_prefix, sizeof(sysfs_prefix) - 1) == 0 && - strcmp(*argv, sysfs_vmlinux) != 0) { - base = btf__parse(sysfs_vmlinux, NULL); - if (libbpf_get_error(base)) { - p_err("failed to parse vmlinux BTF at '%s': %ld\n", - sysfs_vmlinux, libbpf_get_error(base)); - base = NULL; - } - } + strcmp(*argv, sysfs_vmlinux) != 0) + base = get_vmlinux_btf_from_sysfs(); btf = btf__parse_split(*argv, base ?: base_btf); err = libbpf_get_error(btf); @@ -591,6 +629,12 @@ static int do_dump(int argc, char **argv) } if (!btf) { + if (!base_btf && btf_is_kernel_module(btf_id)) { + p_info("Warning: valid base BTF was not specified with -B option, falling back to standard base BTF (%s)", + sysfs_vmlinux); + base_btf = get_vmlinux_btf_from_sysfs(); + } + btf = btf__load_from_kernel_by_id_split(btf_id, base_btf); err = libbpf_get_error(btf); if (err) { @@ -902,7 +946,7 @@ static int do_show(int argc, char **argv) equal_fn_for_key_as_id, NULL); btf_map_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!btf_prog_table || !btf_map_table) { + if (IS_ERR(btf_prog_table) || IS_ERR(btf_map_table)) { hashmap__free(btf_prog_table); hashmap__free(btf_map_table); if (fd >= 0) diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 3571a281c43f..effe136119d7 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -50,6 +50,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, const char *attach_flags_str, int level) { + char prog_name[MAX_PROG_FULL_NAME]; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); int prog_fd; @@ -63,6 +64,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, return -1; } + get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name)); if (json_output) { jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info.id); @@ -73,7 +75,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, jsonw_uint_field(json_wtr, "attach_type", attach_type); jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); - jsonw_string_field(json_wtr, "name", info.name); + jsonw_string_field(json_wtr, "name", prog_name); jsonw_end_object(json_wtr); } else { printf("%s%-8u ", level ? " " : "", info.id); @@ -81,7 +83,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, printf("%-15s", attach_type_name[attach_type]); else printf("type %-10u", attach_type); - printf(" %-15s %-15s\n", attach_flags_str, info.name); + printf(" %-15s %-15s\n", attach_flags_str, prog_name); } close(prog_fd); diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index fa8eb8134344..c740142c24d8 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -17,13 +17,13 @@ #include <linux/magic.h> #include <net/if.h> #include <sys/mount.h> -#include <sys/resource.h> #include <sys/stat.h> #include <sys/vfs.h> #include <bpf/bpf.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/btf.h> #include "main.h" @@ -55,7 +55,6 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", [BPF_CGROUP_GETSOCKOPT] = "getsockopt", [BPF_CGROUP_SETSOCKOPT] = "setsockopt", - [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", [BPF_SK_SKB_VERDICT] = "sk_skb_verdict", @@ -75,6 +74,7 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { [BPF_SK_REUSEPORT_SELECT] = "sk_skb_reuseport_select", [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_skb_reuseport_select_or_migrate", [BPF_PERF_EVENT] = "perf_event", + [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", }; void p_err(const char *fmt, ...) @@ -118,13 +118,6 @@ static bool is_bpffs(char *path) return (unsigned long)st_fs.f_type == BPF_FS_MAGIC; } -void set_max_rlimit(void) -{ - struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; - - setrlimit(RLIMIT_MEMLOCK, &rinf); -} - static int mnt_fs(const char *target, const char *type, char *buff, size_t bufflen) { @@ -304,6 +297,49 @@ const char *get_fd_type_name(enum bpf_obj_type type) return names[type]; } +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len) +{ + const char *prog_name = prog_info->name; + const struct btf_type *func_type; + const struct bpf_func_info finfo = {}; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + struct btf *prog_btf = NULL; + + if (buff_len <= BPF_OBJ_NAME_LEN || + strlen(prog_info->name) < BPF_OBJ_NAME_LEN - 1) + goto copy_name; + + if (!prog_info->btf_id || prog_info->nr_func_info == 0) + goto copy_name; + + info.nr_func_info = 1; + info.func_info_rec_size = prog_info->func_info_rec_size; + if (info.func_info_rec_size > sizeof(finfo)) + info.func_info_rec_size = sizeof(finfo); + info.func_info = ptr_to_u64(&finfo); + + if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) + goto copy_name; + + prog_btf = btf__load_from_kernel_by_id(info.btf_id); + if (!prog_btf) + goto copy_name; + + func_type = btf__type_by_id(prog_btf, finfo.type_id); + if (!func_type || !btf_is_func(func_type)) + goto copy_name; + + prog_name = btf__name_by_offset(prog_btf, func_type->name_off); + +copy_name: + snprintf(name_buff, buff_len, "%s", prog_name); + + if (prog_btf) + btf__free(prog_btf); +} + int get_fd_type(int fd) { char path[PATH_MAX]; diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index e999159fa28d..d12f46051aac 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -3,6 +3,7 @@ #include <ctype.h> #include <errno.h> +#include <fcntl.h> #include <string.h> #include <unistd.h> #include <net/if.h> @@ -45,6 +46,11 @@ static bool run_as_unprivileged; /* Miscellaneous utility functions */ +static bool grep(const char *buffer, const char *pattern) +{ + return !!strstr(buffer, pattern); +} + static bool check_procfs(void) { struct statfs st_fs; @@ -135,6 +141,32 @@ static void print_end_section(void) /* Probing functions */ +static int get_vendor_id(int ifindex) +{ + char ifname[IF_NAMESIZE], path[64], buf[8]; + ssize_t len; + int fd; + + if (!if_indextoname(ifindex, ifname)) + return -1; + + snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) + return -1; + + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len < 0) + return -1; + if (len >= (ssize_t)sizeof(buf)) + return -1; + buf[len] = '\0'; + + return strtol(buf, NULL, 0); +} + static int read_procfs(const char *path) { char *endptr, *line = NULL; @@ -175,7 +207,10 @@ static void probe_unprivileged_disabled(void) printf("bpf() syscall for unprivileged users is enabled\n"); break; case 1: - printf("bpf() syscall restricted to privileged users\n"); + printf("bpf() syscall restricted to privileged users (without recovery)\n"); + break; + case 2: + printf("bpf() syscall restricted to privileged users (admin can change)\n"); break; case -1: printf("Unable to retrieve required privileges for bpf() syscall\n"); @@ -478,6 +513,40 @@ static bool probe_bpf_syscall(const char *define_prefix) return res; } +static bool +probe_prog_load_ifindex(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz, + __u32 ifindex) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + .prog_ifindex = ifindex, + ); + int fd; + + errno = 0; + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + if (fd >= 0) + close(fd); + + return fd >= 0 && errno != EINVAL && errno != EOPNOTSUPP; +} + +static bool probe_prog_type_ifindex(enum bpf_prog_type prog_type, __u32 ifindex) +{ + /* nfp returns -EINVAL on exit(0) with TC offload */ + struct bpf_insn insns[2] = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN() + }; + + return probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), + NULL, 0, ifindex); +} + static void probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, const char *define_prefix, __u32 ifindex) @@ -487,8 +556,7 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, size_t maxlen; bool res; - if (ifindex) - /* Only test offload-able program types */ + if (ifindex) { switch (prog_type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_XDP: @@ -497,7 +565,11 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, return; } - res = bpf_probe_prog_type(prog_type, ifindex); + res = probe_prog_type_ifindex(prog_type, ifindex); + } else { + res = libbpf_probe_bpf_prog_type(prog_type, NULL) > 0; + } + #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for unprivileged users * check that we did not fail because of insufficient permissions @@ -526,6 +598,26 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, define_prefix); } +static bool probe_map_type_ifindex(enum bpf_map_type map_type, __u32 ifindex) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; + int fd; + + opts.map_ifindex = ifindex; + + key_size = sizeof(__u32); + value_size = sizeof(__u32); + max_entries = 1; + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, + &opts); + if (fd >= 0) + close(fd); + + return fd >= 0; +} + static void probe_map_type(enum bpf_map_type map_type, const char *define_prefix, __u32 ifindex) @@ -535,7 +627,19 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, size_t maxlen; bool res; - res = bpf_probe_map_type(map_type, ifindex); + if (ifindex) { + switch (map_type) { + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_ARRAY: + break; + default: + return; |