diff options
Diffstat (limited to 'tools')
55 files changed, 4499 insertions, 844 deletions
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index a43a6f10b564..359960a8f1de 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -843,9 +843,14 @@ static int handle_perms(void) else p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'", capability_msg(bpf_caps, 0), +#ifdef CAP_BPF capability_msg(bpf_caps, 1), capability_msg(bpf_caps, 2), - capability_msg(bpf_caps, 3)); + capability_msg(bpf_caps, 3) +#else + "", "", "", "", "", "" +#endif /* CAP_BPF */ + ); goto exit_free; } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index d942c1e3372c..acdb2c245f0a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -940,7 +940,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd, } if (*attach_type == BPF_FLOW_DISSECTOR) { - *mapfd = -1; + *mapfd = 0; return 0; } diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index 4e3512f700c0..ce5b65e07ab1 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -70,7 +70,7 @@ int BPF_PROG(fentry_XXX) static inline void fexit_update_maps(u32 id, struct bpf_perf_event_value *after) { - struct bpf_perf_event_value *before, diff, *accum; + struct bpf_perf_event_value *before, diff; before = bpf_map_lookup_elem(&fentry_readings, &id); /* only account samples with a valid fentry_reading */ @@ -95,7 +95,7 @@ int BPF_PROG(fexit_XXX) { struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; u32 cpu = bpf_get_smp_processor_id(); - u32 i, one = 1, zero = 0; + u32 i, zero = 0; int err; u64 *count; diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index d9b385fe808c..10a4c4cd13cf 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -15,6 +15,9 @@ static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) /* LP64 case */ return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); @@ -174,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur; \ cur = cur->next) \ if (map->equal_fn(cur->key, (_key), map->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ if (map->equal_fn(cur->key, (_key), map->ctx)) diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e3c98c007825..9bc537d0b92d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -891,13 +891,16 @@ int xsk_umem__delete(struct xsk_umem *umem) void xsk_socket__delete(struct xsk_socket *xsk) { size_t desc_sz = sizeof(struct xdp_desc); - struct xsk_ctx *ctx = xsk->ctx; struct xdp_mmap_offsets off; + struct xsk_umem *umem; + struct xsk_ctx *ctx; int err; if (!xsk) return; + ctx = xsk->ctx; + umem = ctx->umem; if (ctx->prog_fd != -1) { xsk_delete_bpf_maps(xsk); close(ctx->prog_fd); @@ -917,11 +920,11 @@ void xsk_socket__delete(struct xsk_socket *xsk) xsk_put_ctx(ctx); - ctx->umem->refcount--; + umem->refcount--; /* Do not close an fd that also has an associated umem connected * to it. */ - if (xsk->fd != ctx->umem->fd) + if (xsk->fd != umem->fd) close(xsk->fd); free(xsk); } diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 2b6551269e43..f3e3c94ab9bd 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -12,11 +12,12 @@ turbostat : turbostat.c override CFLAGS += -O2 -Wall -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' +override CFLAGS += -D_FILE_OFFSET_BITS=64 override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) - $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap + $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap -lrt .PHONY : clean clean : diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index a6db83a88e85..f6b7e85b121c 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -335,7 +335,7 @@ that they count at TSC rate, which is true on all processors tested to date. .SH REFERENCES Volume 3B: System Programming Guide" -http://www.intel.com/products/processor/manuals/ +https://www.intel.com/products/processor/manuals/ .SH FILES .ta diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 33b370865d16..f3a1746f7f45 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -79,6 +79,7 @@ unsigned long long gfx_cur_rc6_ms; unsigned long long cpuidle_cur_cpu_lpi_us; unsigned long long cpuidle_cur_sys_lpi_us; unsigned int gfx_cur_mhz; +unsigned int gfx_act_mhz; unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; double rapl_power_units, rapl_time_units; @@ -210,13 +211,14 @@ struct pkg_data { unsigned long long pkg_both_core_gfxe_c0; long long gfx_rc6_ms; unsigned int gfx_mhz; + unsigned int gfx_act_mhz; unsigned int package_id; - unsigned int energy_pkg; /* MSR_PKG_ENERGY_STATUS */ - unsigned int energy_dram; /* MSR_DRAM_ENERGY_STATUS */ - unsigned int energy_cores; /* MSR_PP0_ENERGY_STATUS */ - unsigned int energy_gfx; /* MSR_PP1_ENERGY_STATUS */ - unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ - unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ + unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */ + unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */ + unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */ + unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */ + unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ + unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; unsigned long long counter[MAX_ADDED_COUNTERS]; } *package_even, *package_odd; @@ -259,6 +261,113 @@ struct msr_counter { #define SYSFS_PERCPU (1 << 1) }; +/* + * The accumulated sum of MSR is defined as a monotonic + * increasing MSR, it will be accumulated periodically, + * despite its register's bit width. + */ +enum { + IDX_PKG_ENERGY, + IDX_DRAM_ENERGY, + IDX_PP0_ENERGY, + IDX_PP1_ENERGY, + IDX_PKG_PERF, + IDX_DRAM_PERF, + IDX_COUNT, +}; + +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr); + +struct msr_sum_array { + /* get_msr_sum() = sum + (get_msr() - last) */ + struct { + /*The accumulated MSR value is updated by the timer*/ + unsigned long long sum; + /*The MSR footprint recorded in last timer*/ + unsigned long long last; + } entries[IDX_COUNT]; +}; + +/* The percpu MSR sum array.*/ +struct msr_sum_array *per_cpu_msr_sum; + +int idx_to_offset(int idx) +{ + int offset; + + switch (idx) { + case IDX_PKG_ENERGY: + offset = MSR_PKG_ENERGY_STATUS; + break; + case IDX_DRAM_ENERGY: + offset = MSR_DRAM_ENERGY_STATUS; + break; + case IDX_PP0_ENERGY: + offset = MSR_PP0_ENERGY_STATUS; + break; + case IDX_PP1_ENERGY: + offset = MSR_PP1_ENERGY_STATUS; + break; + case IDX_PKG_PERF: + offset = MSR_PKG_PERF_STATUS; + break; + case IDX_DRAM_PERF: + offset = MSR_DRAM_PERF_STATUS; + break; + default: + offset = -1; + } + return offset; +} + +int offset_to_idx(int offset) +{ + int idx; + + switch (offset) { + case MSR_PKG_ENERGY_STATUS: + idx = IDX_PKG_ENERGY; + break; + case MSR_DRAM_ENERGY_STATUS: + idx = IDX_DRAM_ENERGY; + break; + case MSR_PP0_ENERGY_STATUS: + idx = IDX_PP0_ENERGY; + break; + case MSR_PP1_ENERGY_STATUS: + idx = IDX_PP1_ENERGY; + break; + case MSR_PKG_PERF_STATUS: + idx = IDX_PKG_PERF; + break; + case MSR_DRAM_PERF_STATUS: + idx = IDX_DRAM_PERF; + break; + default: + idx = -1; + } + return idx; +} + +int idx_valid(int idx) +{ + switch (idx) { + case IDX_PKG_ENERGY: + return do_rapl & RAPL_PKG; + case IDX_DRAM_ENERGY: + return do_rapl & RAPL_DRAM; + case IDX_PP0_ENERGY: + return do_rapl & RAPL_CORES_ENERGY_STATUS; + case IDX_PP1_ENERGY: + return do_rapl & RAPL_GFX; + case IDX_PKG_PERF: + return do_rapl & RAPL_PKG_PERF_STATUS; + case IDX_DRAM_PERF: + return do_rapl & RAPL_DRAM_PERF_STATUS; + default: + return 0; + } +} struct sys_counters { unsigned int added_thread_counters; unsigned int added_core_counters; @@ -451,6 +560,7 @@ struct msr_counter bic[] = { { 0x0, "APIC" }, { 0x0, "X2APIC" }, { 0x0, "Die" }, + { 0x0, "GFXAMHz" }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -505,6 +615,7 @@ struct msr_counter bic[] = { #define BIC_APIC (1ULL << 48) #define BIC_X2APIC (1ULL << 49) #define BIC_Die (1ULL << 50) +#define BIC_GFXACTMHz (1ULL << 51) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -724,6 +835,9 @@ void print_header(char *delim) if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); if (DO_BIC(BIC_Any_c0)) @@ -858,13 +972,13 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "pc10: %016llX\n", p->pc10); outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); - outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg); - outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores); - outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx); - outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram); - outp += sprintf(outp, "Throttle PKG: %0X\n", + outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg); + outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores); + outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx); + outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram); + outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status); - outp += sprintf(outp, "Throttle RAM: %0X\n", + outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status); outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); @@ -1062,14 +1176,7 @@ int format_counters(struct thread_data *t, struct core_data *c, } } - /* - * If measurement interval exceeds minimum RAPL Joule Counter range, - * indicate that results are suspect by printing "**" in fraction place. - */ - if (interval_float < rapl_joule_counter_range) - fmt8 = "%s%.2f"; - else - fmt8 = "%6.0f**"; + fmt8 = "%s%.2f"; if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); @@ -1098,6 +1205,10 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz); + /* GFXACTMHz */ + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz); + /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc); @@ -1210,11 +1321,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ } #define DELTA_WRAP32(new, old) \ - if (new > old) { \ - old = new - old; \ - } else { \ - old = 0x100000000 + new - old; \ - } + old = ((((unsigned long long)new << 32) - ((unsigned long long)old << 32)) >> 32); int delta_package(struct pkg_data *new, struct pkg_data *old) @@ -1253,13 +1360,14 @@ delta_package(struct pkg_data *new, struct pkg_data *old) old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms; old->gfx_mhz = new->gfx_mhz; + old->gfx_act_mhz = new->gfx_act_mhz; - DELTA_WRAP32(new->energy_pkg, old->energy_pkg); - DELTA_WRAP32(new->energy_cores, old->energy_cores); - DELTA_WRAP32(new->energy_gfx, old->energy_gfx); - DELTA_WRAP32(new->energy_dram, old->energy_dram); - DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status); - DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status); + old->energy_pkg = new->energy_pkg - old->energy_pkg; + old->energy_cores = new->energy_cores - old->energy_cores; + old->energy_gfx = new->energy_gfx - old->energy_gfx; + old->energy_dram = new->energy_dram - old->energy_dram; + old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status; + old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -1469,6 +1577,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->gfx_rc6_ms = 0; p->gfx_mhz = 0; + p->gfx_act_mhz = 0; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) t->counter[i] = 0; @@ -1564,6 +1673,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.packages.gfx_rc6_ms = p->gfx_rc6_ms; average.packages.gfx_mhz = p->gfx_mhz; + average.packages.gfx_act_mhz = p->gfx_act_mhz; average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c); @@ -1784,7 +1894,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) int i; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu); return -1; } @@ -1966,39 +2076,39 @@ retry: p->sys_lpi = cpuidle_cur_sys_lpi_us; if (do_rapl & RAPL_PKG) { - if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (do_rapl & RAPL_CORES_ENERGY_STATUS) { - if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr)) return -14; - p->energy_cores = msr & 0xFFFFFFFF; + p->energy_cores = msr; } if (do_rapl & RAPL_DRAM) { - if (get_msr(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) return -15; - p->energy_dram = msr & 0xFFFFFFFF; + p->energy_dram = msr; } if (do_rapl & RAPL_GFX) { - if (get_msr(cpu, MSR_PP1_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr)) return -16; - p->energy_gfx = msr & 0xFFFFFFFF; + p->energy_gfx = msr; } if (do_rapl & RAPL_PKG_PERF_STATUS) { - if (get_msr(cpu, MSR_PKG_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr)) return -16; - p->rapl_pkg_perf_status = msr & 0xFFFFFFFF; + p->rapl_pkg_perf_status = msr; } if (do_rapl & RAPL_DRAM_PERF_STATUS) { - if (get_msr(cpu, MSR_DRAM_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr)) return -16; - p->rapl_dram_perf_status = msr & 0xFFFFFFFF; + p->rapl_dram_perf_status = msr; } if (do_rapl & RAPL_AMD_F17H) { - if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) @@ -2012,6 +2122,9 @@ retry: if (DO_BIC(BIC_GFXMHz)) p->gfx_mhz = gfx_cur_mhz; + if (DO_BIC(BIC_GFXACTMHz)) + p->gfx_act_mhz = gfx_act_mhz; + for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &p->counter[i])) return -10; @@ -2173,6 +2286,7 @@ int has_turbo_ratio_group_limits(int family, int model) case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_GOLDMONT_D: + case INTEL_FAM6_ATOM_TREMONT_D: return 1; } return 0; @@ -2650,7 +2764,12 @@ int get_thread_siblings(struct cpu_topology *thiscpu) sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu); - filep = fopen_or_die(path, "r"); + filep = fopen(path, "r"); + + if (!filep) { + warnx("%s: open failed", path); + return -1; + } do { offset -= BITMASK_SIZE; if (fscanf(filep, "%lx%c", &map, &character) != 2) @@ -2763,18 +2882,25 @@ void re_initialize(void) { free_all_buffers(); setup_all_buffers(); - printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); + fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); } void set_max_cpu_num(void) { FILE *filep; + int base_cpu; unsigned long dummy; + char pathname[64]; + + base_cpu = sched_getcpu(); + if (base_cpu < 0) + err(1, "cannot find calling cpu ID"); + sprintf(pathname, + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", + base_cpu); + filep = fopen_or_die(pathname, "r"); topo.max_cpu_num = 0; - filep = fopen_or_die( - "/sys/devices/system/cpu/cpu0/topology/thread_siblings", - "r"); while (fscanf(filep, "%lx,", &dummy) == 1) topo.max_cpu_num += BITMASK_SIZE; fclose(filep); @@ -2916,6 +3042,33 @@ int snapshot_gfx_mhz(void) } /* + * snapshot_gfx_cur_mhz() + * + * record snapshot of + * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz + * + * return 1 if config change requires a restart, else return 0 + */ +int snapshot_gfx_act_mhz(void) +{ + static FILE *fp; + int retval; + + if (fp == NULL) + fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r"); + else { + rewind(fp); + fflush(fp); + } + + retval = fscanf(fp, "%d", &gfx_act_mhz); + if (retval != 1) + err(1, "GFX ACT MHz"); + + return 0; +} + +/* * snapshot_cpu_lpi() * * record snapshot of @@ -2980,6 +3133,9 @@ int snapshot_proc_sysfs_files(void) if (DO_BIC(BIC_GFXMHz)) snapshot_gfx_mhz(); + if (DO_BIC(BIC_GFXACTMHz)) + snapshot_gfx_act_mhz(); + if (DO_BIC(BIC_CPU_LPI)) snapshot_cpu_lpi_us(); @@ -3057,6 +3213,111 @@ void do_sleep(void) } } +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr) +{ + int ret, idx; + unsigned long long msr_cur, msr_last; + + if (!per_cpu_msr_sum) + return 1; + + idx = offset_to_idx(offset); + if (idx < 0) + return idx; + /* get_msr_sum() = sum + (get_msr() - last) */ + ret = get_msr(cpu, offset, &msr_cur); + if (ret) + return ret; + msr_last = per_cpu_msr_sum[cpu].entries[idx].last; + DELTA_WRAP32(msr_cur, msr_last); + *msr = msr_last + per_cpu_msr_sum[cpu].entries[idx].sum; + + return 0; +} + +timer_t timerid; + +/* Timer callback, update the sum of MSRs periodically. */ +static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + int i, ret; + int cpu = t->cpu_id; + + for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) { + unsigned long long msr_cur, msr_last; + int offset; + + if (!idx_valid(i)) + continue; + offset = idx_to_offset(i); + if (offset < 0) + continue; + ret = get_msr(cpu, offset, &msr_cur); + if (ret) { + fprintf(outf, "Can not update msr(0x%x)\n", offset); + continue; + } + + msr_last = per_cpu_msr_sum[cpu].entries[i].last; + per_cpu_msr_sum[cpu].entries[i].last = msr_cur & 0xffffffff; + + DELTA_WRAP32(msr_cur, msr_last); + per_cpu_msr_sum[cpu].entries[i].sum += msr_last; + } + return 0; +} + +static void +msr_record_handler(union sigval v) +{ + for_all_cpus(update_msr_sum, EVEN_COUNTERS); +} + +void msr_sum_record(void) +{ + struct itimerspec its; + struct sigevent sev; + + per_cpu_msr_sum = calloc(topo.max_cpu_num + 1, sizeof(struct msr_sum_array)); + if (!per_cpu_msr_sum) { + fprintf(outf, "Can not allocate memory for long time MSR.\n"); + return; + } + /* + * Signal handler might be restricted, so use thread notifier instead. + */ + memset(&sev, 0, sizeof(struct sigevent)); + sev.sigev_notify = SIGEV_THREAD; + sev.sigev_notify_function = msr_record_handler; + + sev.sigev_value.sival_ptr = &timerid; + if (timer_create(CLOCK_REALTIME, &sev, &timerid) == -1) { + fprintf(outf, "Can not create timer.\n"); + goto release_msr; + } + + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 1; + /* + * A wraparound time has been calculated early. + * Some sources state that the peak power for a + * microprocessor is usually 1.5 times the TDP rating, + * use 2 * TDP for safety. + */ + its.it_interval.tv_sec = rapl_joule_counter_range / 2; + its.it_interval.tv_nsec = 0; + + if (timer_settime(timerid, 0, &its, NULL) == -1) { + fprintf(outf, "Can not set timer.\n"); + goto release_timer; + } + return; + + release_timer: + timer_delete(timerid); + release_msr: + free(per_cpu_msr_sum); +} void turbostat_loop() { @@ -3075,7 +3336,7 @@ restart: if (retval < -1) { exit(retval); } else if (retval == -1) { - if (restarted > 1) { + if (restarted > 10) { exit(retval); } re_initialize(); @@ -3279,6 +3540,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ pkg_cstate_limits = glm_pkg_cstate_limits; break; default: @@ -3361,6 +3623,17 @@ int is_ehl(unsigned int family, unsigned int model) } return 0; } +int is_jvl(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_TREMONT_D: + return 1; + } + return 0; +} int has_turbo_ratio_limit(unsigned int family, unsigned int model) { @@ -3475,6 +3748,20 @@ int has_config_tdp(unsigned int family, unsigned int model) } static void +remove_underbar(char *s) +{ + char *to = s; + + while (*s) { + if (*s != '_') + *to++ = *s; + s++; + } + + *to = 0; +} + +static void dump_cstate_pstate_config_info(unsigned int family, unsigned int model) { if (!do_nhm_platform_info) @@ -3530,9 +3817,6 @@ dump_sysfs_cstate_config(void) int state; char *sp; - if (!DO_BIC(BIC_sysfs)) - return; - if (access("/sys/devices/system/cpu/cpuidle", R_OK)) { fprintf(outf, "cpuidle not loaded\n"); return; @@ -3559,6 +3843,8 @@ dump_sysfs_cstate_config(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc", base_cpu, state); input = fopen(path, "r"); @@ -3645,7 +3931,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_epb: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3689,7 +3975,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_hwp: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3777,7 +4063,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_perf_limit: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3881,13 +4167,8 @@ double get_tdp_intel(unsigned int model) double get_tdp_amd(unsigned int family) { - switch (family) { - case 0x17: - case 0x18: - default: - /* This is the max stock TDP of HEDT/Server Fam17h chips */ - return 250.0; - } + /* This is the max stock TDP of HEDT/Server Fam17h+ chips */ + return 280.0; } /* @@ -3959,6 +4240,14 @@ void rapl_probe_intel(unsigned int family, unsigned int model) BIC_PRESENT(BIC_GFXWatt); } break; + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ + do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + if (rapl_joules) + BIC_PRESENT(BIC_Pkg_J); + else + BIC_PRESENT(BIC_PkgWatt); + break; case INTEL_FAM6_SKYLAKE_L: /* SKL */ case INTEL_FAM6_CANNONLAKE_L: /* CNL */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; @@ -4069,27 +4358,20 @@ void rapl_probe_amd(unsigned int family, unsigned int model) if (max_extended_level >= 0x80000007) { __cpuid(0x80000007, eax, ebx, ecx, edx); - /* RAPL (Fam 17h) */ + /* RAPL (Fam 17h+) */ has_rapl = edx & (1 << 14); } - if (!has_rapl) + if (!has_rapl || family < 0x17) return; - switch (family) { - case 0x17: /* Zen, Zen+ */ - case 0x18: /* Hygon Dhyana */ - do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - } - break; - default: - return; + do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); } if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr)) @@ -4162,7 +4444,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4234,7 +4516,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) cpu = t->cpu_id; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_rapl: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4361,6 +4643,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ return 1; } return 0; @@ -4507,12 +4790,33 @@ double discover_bclk(unsigned int family, unsigned int model) * below this value, including the Digital Thermal Sensor (DTS), * Package Thermal Management Sensor (PTM), and thermal event thresholds. */ -int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int read_tcc_activation_temp() { unsigned long long msr; - unsigned int target_c_local; - int cpu; + unsigned int tcc, target_c, offset_c; + /* Temperature Target MSR is Nehalem and newer only */ + if (!do_nhm_platform_info) + return 0; + + if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) + return 0; + + target_c = (msr >> 16) & 0xFF; + + offset_c = (msr >> 24) & 0xF; + + tcc = target_c - offset_c; + + if (!quiet) + fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n", + base_cpu, msr, tcc, target_c, offset_c); + + return tcc; +} + +int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ /* tcc_activation_temp is used only for dts or ptm */ if (!(do_dts || do_ptm)) return 0; @@ -4521,43 +4825,18 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; - cpu = t->cpu_id; - if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); - return -1; - } - if (tcc_activation_temp_override != 0) { tcc_activation_temp = tcc_activation_temp_override; - fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n", - cpu, tcc_activation_temp); + fprintf(outf, "Using cmdline TCC Target (%d C)\n", tcc_activation_temp); return 0; } - /* Temperature Target MSR is Nehalem and newer only */ - if (!do_nhm_platform_info) - goto guess; - - if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) - goto guess; - - target_c_local = (msr >> 16) & 0xFF; - - if (!quiet) - fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", - cpu, msr, target_c_local); - - if (!target_c_local) - goto guess; - - tcc_activation_temp = target_c_local; - - return 0; + tcc_activation_temp = read_tcc_activation_temp(); + if (tcc_activation_temp) + return 0; -guess: tcc_activation_temp = TJMAX_DEFAULT; - fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n", - cpu, tcc_activation_temp); + fprintf(outf, "Guessing tjMax %d C, Please use -T to specify\n", tcc_activation_temp); return 0; } @@ -4685,19 +4964,46 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_ICELAKE_NNPI: case INTEL_FAM6_TIGERLAKE_L: case INTEL_FAM6_TIGERLAKE: + case INTEL_FAM6_ROCKETLAKE: + case INTEL_FAM6_LAKEFIELD: + case INTEL_FAM6_ALDERLAKE: return INTEL_FAM6_CANNONLAKE_L; - case INTEL_FAM6_ATOM_TREMONT_D: - return INTEL_FAM6_ATOM_GOLDMONT_D; - case INTEL_FAM6_ATOM_TREMONT_L: return INTEL_FAM6_ATOM_TREMONT; case INTEL_FAM6_ICELAKE_X: + case INTEL_FAM6_SAPPHIRERAPIDS_X: return INTEL_FAM6_SKYLAKE_X; } return model; } + +void print_dev_latency(void) +{ + char *path = "/dev/cpu_dma_latency"; + int fd; + int value; + int retval; + + fd = open(path, O_RDONLY); + if (fd < 0) { + warn("fopen %s\n", path); + return; + } + + retval = read(fd, (void *)&value, sizeof(int)); + if (retval != sizeof(int)) { + warn("read %s\n", path); + close(fd); + return; + } + fprintf(outf, "/dev/cpu_dma_latency: %d usec (%s)\n", + value, value == 2000000000 ? "default" : "constrained"); + + close(fd); +} + void process_cpuid() { unsigned int eax, ebx, ecx, edx; @@ -4916,6 +5222,14 @@ void process_cpuid() BIC_PRESENT(BIC_Mod_c6); use_c1_residency_msr = 1; } + if (is_jvl(family, model)) { + BIC_NOT_PRESENT(BIC_CPU_c3); + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc2); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_NOT_PRESENT(BIC_Pkgpc6); + BIC_NOT_PRESENT(BIC_Pkgpc7); + } if (is_dnv(family, model)) { BIC_PRESENT(BIC_CPU_c1); BIC_NOT_PRESENT(BIC_CPU_c3); @@ -4935,9 +5249,12 @@ void process_cpuid() BIC_NOT_PRESENT(BIC_Pkgpc7); } if (has_c8910_msrs(family, model)) { - BIC_PRESENT(BIC_Pkgpc8); - BIC_PRESENT(BIC_Pkgpc9); - BIC_PRESENT(BIC_Pkgpc10); + if (pkg_cstate_limit >= PCL__8) + BIC_PRESENT(BIC_Pkgpc8); + if (pkg_cstate_limit >= PCL__9) + BIC_PRESENT(BIC_Pkgpc9); + if (pkg_cstate_limit >= PCL_10) + BIC_PRESENT(BIC_Pkgpc10); } do_irtl_hsw = has_c8910_msrs(family, model); if (has_skl_msrs(family, model)) { @@ -4967,6 +5284,8 @@ void process_cpuid() dump_cstate_pstate_config_info(family, model); if (!quiet) + print_dev_latency(); + if (!quiet) dump_sysfs_cstate_config(); if (!quiet) dump_sysfs_pstate_config(); @@ -4980,6 +5299,9 @@ void process_cpuid() if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) BIC_PRESENT(BIC_GFXMHz); + if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + BIC_PRESENT(BIC_GFXACTMHz); + if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK)) BIC_PRESENT(BIC_CPU_LPI); else @@ -5390,7 +5712,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 20.03.20" + fprintf(outf, "turbostat version 20.09.30" " - Len Brown <lenb@kernel.org>\n"); } @@ -5597,6 +5919,8 @@ void probe_sysfs(void) *sp = '%'; *(sp + 1) = '\0'; + remove_underbar(name_buf); + fclose(input); sprintf(path, "cpuidle/state%d/time", state); @@ -5624,6 +5948,8 @@ void probe_sysfs(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "cpuidle/state%d/usage", state); if (is_deferred_skip(name_buf)) @@ -5868,6 +6194,7 @@ int main(int argc, char **argv) return 0; } + msr_sum_record(); /* * if any params left, it must be a command to fork */ diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 3fe1eed900d4..ff6c6661f075 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -622,6 +622,57 @@ void cmdline(int argc, char **argv) } } +/* + * Open a file, and exit on failure + */ +FILE *fopen_or_die(const char *path, const char *mode) +{ + FILE *filep = fopen(path, "r"); + + if (!filep) + err(1, "%s: open failed", path); + return filep; +} + +void err_on_hypervisor(void) +{ + FILE *cpuinfo; + char *flags, *hypervisor; + char *buffer; + + /* On VMs /proc/cpuinfo contains a "flags" entry for hypervisor */ + cpuinfo = fopen_or_die("/proc/cpuinfo", "ro"); + + buffer = malloc(4096); + if (!buffer) { + fclose(cpuinfo); + err(-ENOMEM, "buffer malloc fail"); + } + + if (!fread(buffer, 1024, 1, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + + flags = strstr(buffer, "flags"); + rewind(cpuinfo); + fseek(cpuinfo, flags - buffer, SEEK_SET); + if (!fgets(buffer, 4096, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + fclose(cpuinfo); + + hypervisor = strstr(buffer, "hypervisor"); + + free(buffer); + + if (hypervisor) + err(-1, + "not supported on this virtual machine"); +} int get_msr(int cpu, int offset, unsigned long long *msr) { @@ -635,8 +686,10 @@ int get_msr(int cpu, int offset, unsigned long long *msr) err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); retval = pread(fd, msr, sizeof(*msr), offset); - if (retval != sizeof(*msr)) + if (retval != sizeof(*msr)) { + err_on_hypervisor(); err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset); + } if (debug > 1) fprintf(stderr, "get_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, *msr); @@ -1086,18 +1139,6 @@ int update_cpu_msrs(int cpu) return 0; } -/* - * Open a file, and exit on failure - */ -FILE *fopen_or_die(const char *path, const char *mode) -{ - FILE *filep = fopen(path, "r"); - - if (!filep) - err(1, "%s: open failed", path); - return filep; -} - unsigned int get_pkg_num(int cpu) { FILE *fp; diff --git a/tools/testing/selftests/bpf/prog_tests/map_init.c b/tools/testing/selftests/bpf/prog_tests/map_init.c new file mode 100644 index 000000000000..14a31109dd0e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_init.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include <test_progs.h> +#include "test_map_init.skel.h" + +#define TEST_VALUE 0x1234 +#define FILL_VALUE 0xdeadbeef + +static int nr_cpus; +static int duration; + +typedef unsigned long long map_key_t; +typedef unsigned long long map_value_t; +typedef struct { + map_value_t v; /* padding */ +} __bpf_percpu_val_align pcpu_map_value_t; + + +static int map_populate(int map_fd, int num) +{ + pcpu_map_value_t value[nr_cpus]; + int i, err; + map_key_t key; + + for (i = 0; i < nr_cpus; i++) + bpf_percpu(value, i) = FILL_VALUE; + + for (key = 1; key <= num; key++) { + err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + return -1; + } + + return 0; +} + +static struct test_map_init *setup(enum bpf_map_type map_type, int map_sz, + int *map_fd, int populate) +{ + struct test_map_init *skel; + int err; + + skel = test_map_init__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return NULL; + + err = bpf_map__set_type(skel->maps.hashmap1, map_type); + if (!ASSERT_OK(err, "bpf_map__set_type")) + goto error; + + err = bpf_map__set_max_entries(skel->maps.hashmap1, map_sz); + if (!ASSERT_OK(err, "bpf_map__set_max_entries")) + goto error; + + err = test_map_init__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto error; + + *map_fd = bpf_map__fd(skel->maps.hashmap1); + if (CHECK(*map_fd < 0, "bpf_map__fd", "failed\n")) + goto error; + + err = map_populate(*map_fd, populate); + if (!ASSERT_OK(err, "map_populate")) + goto error_map; + + return skel; + +error_map: + close(*map_fd); +error: + test_map_init__destroy(skel); + return NULL; +} + +/* executes bpf program that updates map with key, value */ +static int prog_run_insert_elem(struct test_map_init *skel, map_key_t key, + map_value_t value) +{ + struct test_map_init__bss *bss; + + bss = skel->bss; + + bss->inKey = key; + bss->inValue = value; + bss->inPid = getpid(); + + if (!ASSERT_OK(test_map_init__attach(skel), "skel_attach")) + return -1; + + /* Let tracepoint trigger */ + syscall(__NR_getpgid); + + test_map_init__detach(skel); + + return 0; +} + +static int check_values_one_cpu(pcpu_map_value_t *value, map_value_t expected) +{ + int i, nzCnt = 0; + map_value_t val; + + for (i = 0; i < nr_cpus; i++) { + val = bpf_percpu(value, i); + if (val) { + if (CHECK(val != expected, "map value", + "unexpected for cpu %d: 0x%llx\n", i, val)) + return -1; + nzCnt++; + } + } + + if (CHECK(nzCnt != 1, "map value", "set for %d CPUs instead of 1!\n", + nzCnt)) + return -1; + + return 0; +} + +/* Add key=1 elem with values set for all CPUs + * Delete elem key=1 + * Run bpf prog that inserts new key=1 elem with value=0x1234 + * (bpf prog can only set value for current CPU) + * Lookup Key=1 and check value is as expected for all CPUs: + * value set by bpf prog for one CPU, 0 for all others + */ +static void test_pcpu_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* max 1 elem in map so insertion is forced to reuse freed entry */ + skel = setup(BPF_MAP_TYPE_PERCPU_HASH, 1, &map_fd, 1); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* delete element so the entry can be re-used*/ + key = 1; + err = bpf_map_delete_elem(map_fd, &key); + if (!ASSERT_OK(err, "bpf_map_delete_elem")) + goto cleanup; + + /* run bpf prog that inserts new elem, re-using the slot just freed */ + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=1 was re-created by bpf prog */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +/* Add key=1 and key=2 elems with values set for all CPUs + * Run bpf prog that inserts new key=3 elem + * (only for current cpu; other cpus should have initial value = 0) + * Lookup Key=1 and check value is as expected for all CPUs + */ +static void test_pcpu_lru_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* Set up LRU map with 2 elements, values filled for all CPUs. + * With these 2 elements, the LRU map is full + */ + skel = setup(BPF_MAP_TYPE_LRU_PERCPU_HASH, 2, &map_fd, 2); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* run bpf prog that inserts new key=3 element, re-using LRU slot */ + key = 3; + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=3 replaced one of earlier elements */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +void test_map_init(void) +{ + nr_cpus = bpf_num_possible_cpus(); + if (nr_cpus <= 1) { + printf("%s:SKIP: >1 cpu needed for this test\n", __func__); + test__skip(); + return; + } + + if (test__start_subtest("pcpu_map_init")) + test_pcpu_map_init(); + if (test__start_subtest("pcpu_lru_map_init")) + test_pcpu_lru_map_init(); +} diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 00578311a423..30982a7e4d0f 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -243,7 +243,10 @@ static ino_t get_inode_from_kernfs(struct kernfs_node* node) } } -int pids_cgrp_id = 1; +extern bool CONFIG_CGROUP_PIDS __kconfig __weak; +enum cgroup_subsys_id___local { + pids_cgrp_id___local = 123, /* value doesn't matter */ +}; static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, struct task_struct* task, @@ -253,7 +256,9 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn); struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn); - if (ENABLE_CGROUP_V1_RESOLVER) { + if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) { + int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local, + pids_cgrp_id___local); #ifdef UNROLL #pragma unroll #endif @@ -262,7 +267,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, cgroups, subsys[i]); if (subsys != NULL) { int subsys_id = BPF_CORE_READ(subsys, ss, id); - if (subsys_id == pids_cgrp_id) { + if (subsys_id == cgrp_id) { proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn); root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn); break; diff --git a/tools/testing/selftests/bpf/progs/test_map_init.c b/tools/testing/selftests/bpf/progs/test_map_init.c new file mode 100644 index 000000000000..c89d28ead673 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_init.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u64 inKey = 0; +__u64 inValue = 0; +__u32 inPid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 2); + __type(key, __u64); + __type(value, __u64); +} hashmap1 SEC(".maps"); + + +SEC("tp/syscalls/sys_enter_getpgid") +int sysenter_getpgid(const void *ctx) +{ + /* Just do it for once, when called from our own test prog. This + * ensures the map value is only updated for a single CPU. + */ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + if (cur_pid == inPid) + bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d2c2d6205008..ce8f4ad39684 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,29 +1,33 @@ # SPDX-License-Identifier: GPL-2.0-only +/aarch64/get-reg-list +/aarch64/get-reg-list-sve /s390x/memop /s390x/resets /s390x/sync_regs_test /x86_64/cr4_cpuid_sync_test /x86_64/debug_regs /x86_64/evmcs_test +/x86_64/kvm_pv_test /x86_64/hyperv_cpuid /x86_64/mmio_warning_test /x86_64/platform_info_test /x86_64/set_sregs_test /x86_64/smm_test /x86_64/state_test -/x86_64/user_msr_test -/x86_64/vmx_preemption_timer_test /x86_64/svm_vmcall_test /x86_64/sync_regs_test +/x86_64/tsc_msrs_test +/x86_64/userspace_msr_exit_test /x86_64/vmx_apic_access_test /x86_64/vmx_close_while_nested_test /x86_64/vmx_dirty_log_test +/x86_64/vmx_preemption_timer_test /x86_64/vmx_set_nested_state_test /x86_64/vmx_tsc_adjust_test /x86_64/xss_msr_test -/clear_dirty_log_test /demand_paging_test /dirty_log_test +/dirty_log_perf_test /kvm_create_max_vcpus /set_memory_region_test /steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 1b9c257fca5e..c7ca4faba272 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -34,13 +34,14 @@ ifeq ($(ARCH),s390) endif LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid +TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test @@ -49,6 +50,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test +TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test @@ -57,17 +59,18 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test -TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test -TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test +TEST_GEN_PROGS_x86_64 += dirty_log_perf_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time -TEST_GEN_PROGS_aarch64 += clear_dirty_log_test +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test +TEST_GEN_PROGS_aarch64 += dirty_log_perf_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus TEST_GEN_PROGS_aarch64 += set_memory_region_test TEST_GEN_PROGS_aarch64 += steal_time @@ -111,14 +114,21 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option) include ../lib.mk STATIC_LIBS := $(OUTPUT)/libkvm.a -LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM)) -EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.* +LIBKVM_C := $(filter %.c,$(LIBKVM)) +LIBKVM_S := $(filter %.S,$(LIBKVM)) +LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) +LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) +EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.* + +x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) +$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ)))) -$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c +$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) +LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) +$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS) $(AR) crs $@ $^ x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c new file mode 100644 index 000000000000..efba76682b4b --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define REG_LIST_SVE +#include "get-reg-list.c" diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c new file mode 100644 index 000000000000..33218a395d9f --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -0,0 +1,841 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check for KVM_GET_REG_LIST regressions. + * + * Copyright (C) 2020, Red Hat, Inc. + * + * When attempting to migrate from a host with an older kernel to a host + * with a newer kernel we allow the newer kernel on the destination to + * list new registers with get-reg-list. We assume they'll be unused, at + * least until the guest reboots, and so they're relatively harmless. + * However, if the destination host with the newer kernel is missing + * registers which the source host with the older kernel has, then that's + * a regression in get-reg-list. This test checks for that regression by + * checking the current list against a blessed list. We should never have + * missing registers, but if new ones appear then they can probably be + * added to the blessed list. A completely new blessed list can be created + * by running the test with the --list command line argument. + * + * Note, the blessed list should be created from the oldest possible + * kernel. We can't go older than v4.15, though, because that's the first + * release to expose the ID system registers in KVM_GET_REG_LIST, see + * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features + * from guests"). Also, one must use the --core-reg-fixup command line + * option when running on an older kernel that doesn't include df205b5c6328 + * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST") + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include "kvm_util.h" +#include "test_util.h" +#include "processor.h" + +#ifdef REG_LIST_SVE +#define reg_list_sve() (true) +#else +#define reg_list_sve() (false) +#endif + +#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK) + +#define for_each_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) + +#define for_each_missing_reg(i) \ + for ((i) = 0; (i) < blessed_n; ++(i)) \ + if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) + +#define for_each_new_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) \ + if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i])) + + +static struct kvm_reg_list *reg_list; + +static __u64 base_regs[], vregs[], sve_regs[], rejects_set[]; +static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n; +static __u64 *blessed_reg, blessed_n; + +static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) +{ + int i; + + for (i = 0; i < nr_regs; ++i) + if (reg == regs[i]) + return true; + return false; +} + +static const char *str_with_index(const char *template, __u64 index) +{ + char *str, *p; + int n; + + str = strdup(template); + p = strstr(str, "##"); + n = sprintf(p, "%lld", index); + strcat(p + n, strstr(template, "##") + 2); + + return (const char *)str; +} + +#define CORE_REGS_XX_NR_WORDS 2 +#define CORE_SPSR_XX_NR_WORDS 2 +#define CORE_FPREGS_XX_NR_WORDS 4 + +static const char *core_id_to_str(__u64 id) +{ + __u64 core_off = id & ~REG_MASK, idx; + + /* + * core_off is the offset into struct kvm_regs + */ + switch (core_off) { + case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... + KVM_REG_ARM_CORE_REG(regs.regs[30]): + idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS; + TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx); + case KVM_REG_ARM_CORE_REG(regs.sp): + return "KVM_REG_ARM_CORE_REG(regs.sp)"; + case KVM_REG_ARM_CORE_REG(regs.pc): + return "KVM_REG_ARM_CORE_REG(regs.pc)"; + case KVM_REG_ARM_CORE_REG(regs.pstate): + return "KVM_REG_ARM_CORE_REG(regs.pstate)"; + case KVM_REG_ARM_CORE_REG(sp_el1): + return "KVM_REG_ARM_CORE_REG(sp_el1)"; + case KVM_REG_ARM_CORE_REG(elr_el1): + return "KVM_REG_ARM_CORE_REG(elr_el1)"; + case KVM_REG_ARM_CORE_REG(spsr[0]) ... + KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): + idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS; + TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS; + TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)"; + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)"; + } + + TEST_FAIL("Unknown core reg id: 0x%llx", id); + return NULL; +} + +static const char *sve_id_to_str(__u64 id) +{ + __u64 sve_off, n, i; + + if (id == KVM_REG_ARM64_SVE_VLS) + return "KVM_REG_ARM64_SVE_VLS"; + + sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1)); + i = id & (KVM_ARM64_SVE_MAX_SLICES - 1); + + TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id); + + switch (sve_off) { + case KVM_REG_ARM64_SVE_ZREG_BASE ... + KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0), + "Unexpected bits set in SVE ZREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n); + case KVM_REG_ARM64_SVE_PREG_BASE ... + KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0), + "Unexpected bits set in SVE PREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n); + case KVM_REG_ARM64_SVE_FFR_BASE: + TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0), + "Unexpected bits set in SVE FFR id: 0x%llx", id); + return "KVM_REG_ARM64_SVE_FFR(0)"; + } + + return NULL; +} + +static void print_reg(__u64 id) +{ + unsigned op0, op1, crn, crm, op2; + const char *reg_size = NULL; + + TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64, + "KVM_REG_ARM64 missing in reg id: 0x%llx", id); + + switch (id & KVM_REG_SIZE_MASK) { + case KVM_REG_SIZE_U8: + reg_size = "KVM_REG_SIZE_U8"; + break; + case KVM_REG_SIZE_U16: + reg_size = "KVM_REG_SIZE_U16"; + break; + case KVM_REG_SIZE_U32: + reg_size = "KVM_REG_SIZE_U32"; + break; + case KVM_REG_SIZE_U64: + reg_size = "KVM_REG_SIZE_U64"; + break; + case KVM_REG_SIZE_U128: + reg_size = "KVM_REG_SIZE_U128"; + break; + case KVM_REG_SIZE_U256: + reg_size = "KVM_REG_SIZE_U256"; + break; + case KVM_REG_SIZE_U512: + reg_size = "KVM_REG_SIZE_U512"; + break; + case KVM_REG_SIZE_U1024: + reg_size = "KVM_REG_SIZE_U1024"; + break; + case KVM_REG_SIZE_U2048: + reg_size = "KVM_REG_SIZE_U2048"; + break; + default: + TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id); + } + + switch (id & KVM_REG_ARM_COPROC_MASK) { + case KVM_REG_ARM_CORE: + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id)); + break; + case KVM_REG_ARM_DEMUX: + TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)), + "Unexpected bits set in DEMUX reg id: 0x%llx", id); + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n", + reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK); + break; + case KVM_REG_ARM64_SYSREG: + op0 = (id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT; + op1 = (id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT; + crn = (id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT; + crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT; + op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT; + TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2), + "Unexpected bits set in SYSREG reg id: 0x%llx", id); + printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2); + break; + case KVM_REG_ARM_FW: + TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff), + "Unexpected bits set in FW reg id: 0x%llx", id); + printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff); + break; + case KVM_REG_ARM64_SVE: + if (reg_list_sve()) + printf("\t%s,\n", sve_id_to_str(id)); + else + TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id); + break; + default: + TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id); + } +} + +/* + * Older kernels listed each 32-bit word of CORE registers separately. + * For 64 and 128-bit registers we need to ignore the extra words. We + * also need to fixup the sizes, because the older kernels stated all + * registers were 64-bit, even when they weren't. + */ +static void core_reg_fixup(void) +{ + struct kvm_reg_list *tmp; + __u64 id, core_off; + int i; + + tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64)); + + for (i = 0; i < reg_list->n; ++i) { + id = reg_list->reg[i]; + + if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) { + tmp->reg[tmp->n++] = id; + continue; + } + + core_off = id & ~REG_MASK; + + switch (core_off) { + case 0x52: case 0xd2: case 0xd6: + /* + * These offsets are pointing at padding. + * We need to ignore them too. + */ + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + if (core_off & 3) + continue; + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U128; + tmp->reg[tmp->n++] = id; + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U32; + tmp->reg[tmp->n++] = id; + continue; + default: + if (core_off & 1) + continue; + tmp->reg[tmp->n++] = id; + break; + } + } + + free(reg_list); + reg_list = tmp; +} + +static void prepare_vcpu_init(struct kvm_vcpu_init *init) +{ + if (reg_list_sve()) + init->features[0] |= 1 << KVM_ARM_VCPU_SVE; +} + +static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +{ + int feature; + + if (reg_list_sve()) { + feature = KVM_ARM_VCPU_SVE; + vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature); + } +} + +static void check_supported(void) +{ + if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) { + fprintf(stderr, "SVE not available, skipping tests\n"); + exit(KSFT_SKIP); + } +} + +int main(int ac, char **av) +{ + struct kvm_vcpu_init init = { .target = -1, }; + int new_regs = 0, missing_regs = 0, i; + int failed_get = 0, failed_set = 0, failed_reject = 0; + bool print_list = false, fixup_core_regs = false; + struct kvm_vm *vm; + __u64 *vec_regs; + + check_supported(); + + for (i = 1; i < ac; ++i) { + if (strcmp(av[i], "--core-reg-fixup") == 0) + fixup_core_regs = true; + else if (strcmp(av[i], "--list") == 0) + print_list = true; + else + fprintf(stderr, "Ignoring unknown option: %s\n", av[i]); + } + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + prepare_vcpu_init(&init); + aarch64_vcpu_add_default(vm, 0, &init, NULL); + finalize_vcpu(vm, 0); + + reg_list = vcpu_get_reg_list(vm, 0); + + if (fixup_core_regs) + core_reg_fixup(); + + if (print_list) { + putchar('\n'); + for_each_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + return 0; + } + + /* + * We only test that we can get the register and then write back the + * same value. Some registers may allow other values to be written + * back, but others only allow some bits to be changed, and at least + * for ID registers set will fail if the value does not exactly match + * what was returned by get. If registers that allow other values to + * be written need to have the other values tested, then we should + * create a new set of tests for those in a new independent test + * executable. + */ + for_each_reg(i) { + uint8_t addr[2048 / 8]; + struct kvm_one_reg reg = { + .id = reg_list->reg[i], + .addr = (__u64)&addr, + }; + int ret; + + ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®); + if (ret) { + puts("Failed to get "); + print_reg(reg.id); + putchar('\n'); + ++failed_get; + } + + /* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */ + if (find_reg(rejects_set, rejects_set_n, reg.id)) { + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret != -1 || errno != EPERM) { + printf("Failed to reject (ret=%d, errno=%d) ", ret, errno); + print_reg(reg.id); + putchar('\n'); + ++failed_reject; + } + continue; + } + + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret) { + puts("Failed to set "); + print_reg(reg.id); + putchar('\n'); + ++failed_set; + } + } + + if (reg_list_sve()) { + blessed_n = base_regs_n + sve_regs_n; + vec_regs = sve_regs; + } else { + blessed_n = base_regs_n + vregs_n; + vec_regs = vregs; + } + + blessed_reg = calloc(blessed_n, sizeof(__u64)); + for (i = 0; i < base_regs_n; ++i) + blessed_reg[i] = base_regs[i]; + for (i = 0; i < blessed_n - base_regs_n; ++i) + blessed_reg[base_regs_n + i] = vec_regs[i]; + + for_each_new_reg(i) + ++new_regs; + + for_each_missing_reg(i) + ++missing_regs; + + if (new_regs || missing_regs) { + printf("Number blessed registers: %5lld\n", blessed_n); + printf("Number registers: %5lld\n", reg_list->n); + } + + if (new_regs) { + printf("\nThere are %d new registers.\n" + "Consider adding them to the blessed reg " + "list with the following lines:\n\n", new_regs); + for_each_new_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + } + + if (missing_regs) { + printf("\nThere are %d missing registers.\n" + "The following lines are missing registers:\n\n", missing_regs); + for_each_missing_reg(i) + print_reg(blessed_reg[i]); + putchar('\n'); + } + + TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject, + "There are %d missing registers; " + "%d registers failed get; %d registers failed set; %d registers failed reject", + missing_regs, failed_get, failed_set, failed_reject); + + return 0; +} + +/* + * The current blessed list was primed with the output of kernel version + * v4.15 with --core-reg-fixup and then later updated with new registers. + */ +static __u64 base_regs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.sp), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pc), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pstate), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(sp_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(elr_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr), + KVM_REG_ARM_FW_REG(0), + KVM_REG_ARM_FW_REG(1), + KVM_REG_ARM_FW_REG(2), + ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 0, 2), + ARM64_SYS_REG(3, 0, 0, 0, 0), /* MIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 0, 6), /* REVIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 1), /* CLIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 7), /* AIDR_EL1 */ + ARM64_SYS_REG(3, 3, 0, 0, 1), /* CTR_EL0 */ + ARM64_SYS_REG(2, 0, 0, 0, 4), + ARM64_SYS_REG(2, 0, 0, 0, 5), + ARM64_SYS_REG(2, 0, 0, 0, 6), + ARM64_SYS_REG(2, 0, 0, 0, 7), + ARM64_SYS_REG(2, 0, 0, 1, 4), + ARM64_SYS_REG(2, 0, 0, 1, 5), + ARM64_SYS_REG(2, 0, 0, 1, 6), + ARM64_SYS_REG(2, 0, 0, 1, 7), + ARM64_SYS_REG(2, 0, 0, 2, 0), /* MDCCINT_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 2), /* MDSCR_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 4), + ARM64_SYS_REG(2, 0, 0, 2, 5), + ARM64_SYS_REG(2, 0, 0, 2, 6), + ARM64_SYS_REG(2, 0, 0, 2, 7), + ARM64_SYS_REG(2, 0, 0, 3, 4), + ARM64_SYS_REG(2, 0, 0, 3, 5), + ARM64_SYS_REG(2, 0, 0, 3, 6), + ARM64_SYS_REG(2, 0, 0, 3, 7), + ARM64_SYS_REG(2, 0, 0, 4, 4), + ARM64_SYS_REG(2, 0, 0, 4, 5), + ARM64_SYS_REG(2, 0, 0, 4, 6), + ARM64_SYS_REG(2, 0, 0, 4, 7), + ARM64_SYS_REG(2, 0, 0, 5, 4), + ARM64_SYS_REG(2, 0, 0, 5, 5), + ARM64_SYS_REG(2, 0, 0, 5, 6), + ARM64_SYS_REG(2, 0, 0, 5, 7), + ARM64_SYS_REG(2, 0, 0, 6, 4), + ARM64_SYS_REG(2, 0, 0, 6, 5), + ARM64_SYS_REG(2, 0, 0, 6, 6), + ARM64_SYS_REG(2, 0, 0, 6, 7), + ARM64_SYS_REG(2, 0, 0, 7, 4), + ARM64_SYS_REG(2, 0, 0, 7, 5), + ARM64_SYS_REG(2, 0, 0, 7, 6), + ARM64_SYS_REG(2, 0, 0, 7, 7), + ARM64_SYS_REG(2, 0, 0, 8, 4), + ARM64_SYS_REG(2, 0, 0, 8, 5), + ARM64_SYS_REG(2, 0, 0, 8, 6), + ARM64_SYS_REG(2, 0, 0, 8, 7), + ARM64_SYS_REG(2, 0, 0, 9, 4), + ARM64_SYS_REG(2, 0, 0, 9, 5), + ARM64_SYS_REG(2, 0, 0, 9, 6), + ARM64_SYS_REG(2, 0, 0, 9, 7), + ARM64_SYS_REG(2, 0, 0, 10, 4), + ARM64_SYS_REG(2, 0, 0, 10, 5), + ARM64_SYS_REG(2, 0, 0, 10, 6), + ARM64_SYS_REG(2, 0, 0, 10, 7), + ARM64_SYS_REG(2, 0, 0, 11, 4), + ARM64_SYS_REG(2, 0, 0, 11, 5), + ARM64_SYS_REG(2, 0, 0, 11, 6), + ARM64_SYS_REG(2, 0, 0, 11, 7), + ARM64_SYS_REG(2, 0, 0, 12, 4), + ARM64_SYS_REG(2, 0, 0, 12, 5), + ARM64_SYS_REG(2, 0, 0, 12, 6), + ARM64_SYS_REG(2, 0, 0, 12, 7), + ARM64_SYS_REG(2, 0, 0, 13, 4), + ARM64_SYS_REG(2, 0, 0, 13, 5), + ARM64_SYS_REG(2, 0, 0, 13, 6), + ARM64_SYS_REG(2, 0, 0, 13, 7), + ARM64_SYS_REG(2, 0, 0, 14, 4), + ARM64_SYS_REG(2, 0, 0, 14, 5), + ARM64_SYS_REG(2, 0, 0, 14, 6), + ARM64_SYS_REG(2, 0, 0, 14, 7), + ARM64_SYS_REG(2, 0, 0, 15, 4), + ARM64_SYS_REG(2, 0, 0, 15, 5), + ARM64_SYS_REG(2, 0, 0, 15, 6), + ARM64_SYS_REG(2, 0, 0, 15, 7), + ARM64_SYS_REG(2, 4, 0, 7, 0), /* DBGVCR32_EL2 */ + ARM64_SYS_REG(3, 0, 0, 0, 5), /* MPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 0), /* ID_PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 1), /* ID_PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 2), /* ID_DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 3), /* ID_AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 4), /* ID_MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 5), /* ID_MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 6), /* ID_MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 7), /* ID_MMFR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 0), /* ID_ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 1), /* ID_ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 2), /* ID_ISAR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 3), /* ID_ISAR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 4), /* ID_ISAR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 5), /* ID_ISAR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 6), /* ID_MMFR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 7), /* ID_ISAR6_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 0), /* MVFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 1), /* MVFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 2), /* MVFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 3), + ARM64_SYS_REG(3, 0, 0, 3, 4), /* ID_PFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 5), /* ID_DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 6), /* ID_MMFR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 7), + ARM64_SYS_REG(3, 0, 0, 4, 0), /* ID_AA64PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 2), + ARM64_SYS_REG(3, 0, 0, 4, 3), + ARM64_SYS_REG(3, 0, 0, 4, 4), /* ID_AA64ZFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 5), + ARM64_SYS_REG(3, 0, 0, 4, 6), + ARM64_SYS_REG(3, 0, 0, 4, 7), + ARM64_SYS_REG(3, 0, 0, 5, 0), /* ID_AA64DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 1), /* ID_AA64DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 2), + ARM64_SYS_REG(3, 0, 0, 5, 3), + ARM64_SYS_REG(3, 0, 0, 5, 4), /* ID_AA64AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 5), /* ID_AA64AFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 6), + ARM64_SYS_REG(3, 0, 0, 5, 7), + ARM64_SYS_REG(3, 0, 0, 6, 0), /* ID_AA64ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 1), /* ID_AA64ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 2), + ARM64_SYS_REG(3, 0, 0, 6, 3), + ARM64_SYS_REG(3, 0, 0, 6, 4), + ARM64_SYS_REG(3, 0, 0, 6, 5), + ARM64_SYS_REG(3, 0, 0, 6, 6), + ARM64_SYS_REG(3, 0, 0, 6, 7), + ARM64_SYS_REG(3, 0, 0, 7, 0), /* ID_AA64MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 1), /* ID_AA64MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 2), /* ID_AA64MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), + ARM64_SYS_REG(3, 0, 0, 7, 4), + ARM64_SYS_REG(3, 0, 0, 7, 5), + ARM64_SYS_REG(3, 0, 0, 7, 6), + ARM64_SYS_REG(3, 0, 0, 7, 7), + ARM64_SYS_REG(3, 0, 1, 0, 0), /* SCTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 1), /* ACTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 2), /* CPACR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */ + ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */ + ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */ + ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 1), /* PMINTENSET_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 2), /* PMINTENCLR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 1), /* CONTEXTIDR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 4), /* TPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 14, 1, 0), /* CNTKCTL_EL1 */ + ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */ + ARM64_SYS_REG(3, 3, 9, 12, 0), /* PMCR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 1), /* PMCNTENSET_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 2), /* PMCNTENCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 3), /* PMOVSCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 4), /* PMSWINC_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 5), /* PMSELR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 13, 0), /* PMCCNTR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 0), /* PMUSERENR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 3), /* PMOVSSET_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */ + ARM64_SYS_REG(3, 3, 14, 8, 0), + ARM64_SYS_REG(3, 3, 14, 8, 1), + ARM64_SYS_REG(3, 3, 14, 8, 2), + ARM64_SYS_REG(3, 3, 14, 8, 3), + ARM64_SYS_REG(3, 3, 14, 8, 4), + ARM64_SYS_REG(3, 3, 14, 8, 5), + ARM64_SYS_REG(3, 3, 14, 8, 6), + ARM64_SYS_REG(3, 3, 14, 8, 7), + ARM64_SYS_REG(3, 3, 14, 9, 0), + ARM64_SYS_REG(3, 3, 14, 9, 1), + ARM64_SYS_REG(3, 3, 14, 9, 2), + ARM64_SYS_REG(3, 3, 14, 9, 3), + ARM64_SYS_REG(3, 3, 14, 9, 4), + ARM64_SYS_REG(3, 3, 14, 9, 5), + ARM64_SYS_REG(3, 3, 14, 9, 6), + ARM64_SYS_REG(3, 3, 14, 9, 7), + ARM64_SYS_REG(3, 3, 14, 10, 0), + ARM64_SYS_REG(3, 3, 14, 10, 1), + ARM64_SYS_REG(3, 3, 14, 10, 2), + ARM64_SYS_REG(3, 3, 14, 10, 3), + ARM64_SYS_REG(3, 3, 14, 10, 4), + ARM64_SYS_REG(3, 3, 14, 10, 5), + ARM64_SYS_REG(3, 3, 14, 10, 6), + ARM64_SYS_REG(3, 3, 14, 10, 7), + ARM64_SYS_REG(3, 3, 14, 11, 0), + ARM64_SYS_REG(3, 3, 14, 11, 1), + ARM64_SYS_REG(3, 3, 14, 11, 2), + ARM64_SYS_REG(3, 3, 14, 11, 3), + ARM64_SYS_REG(3, 3, 14, 11, 4), + ARM64_SYS_REG(3, 3, 14, 11, 5), + ARM64_SYS_REG(3, 3, 14, 11, 6), + ARM64_SYS_REG(3, 3, 14, 12, 0), + ARM64_SYS_REG(3, 3, 14, 12, 1), + ARM64_SYS_REG(3, 3, 14, 12, 2), + ARM64_SYS_REG(3, 3, 14, 12, 3), + ARM64_SYS_REG(3, 3, 14, 12, 4), + ARM64_SYS_REG(3, 3, 14, 12, 5), + ARM64_SYS_REG(3, 3, 14, 12, 6), + ARM64_SYS_REG(3, 3, 14, 12, 7), + ARM64_SYS_REG(3, 3, 14, 13, 0), + ARM64_SYS_REG(3, 3, 14, 13, 1), + ARM64_SYS_REG(3, 3, 14, 13, 2), + ARM64_SYS_REG(3, 3, 14, 13, 3), + ARM64_SYS_REG(3, 3, 14, 13, 4), + ARM64_SYS_REG(3, 3, 14, 13, 5), + ARM64_SYS_REG(3, 3, 14, 13, 6), + ARM64_SYS_REG(3, 3, 14, 13, 7), + ARM64_SYS_REG(3, 3, 14, 14, 0), + ARM64_SYS_REG(3, 3, 14, 14, 1), + ARM64_SYS_REG(3, 3, 14, 14, 2), + ARM64_SYS_REG(3, 3, 14, 14, 3), + ARM64_SYS_REG(3, 3, 14, 14, 4), + ARM64_SYS_REG(3, 3, 14, 14, 5), + ARM64_SYS_REG(3, 3, 14, 14, 6), + ARM64_SYS_REG(3, 3, 14, 14, 7), + ARM64_SYS_REG(3, 3, 14, 15, 0), + ARM64_SYS_REG(3, 3, 14, 15, 1), + ARM64_SYS_REG(3, 3, 14, 15, 2), + ARM64_SYS_REG(3, 3, 14, 15, 3), + ARM64_SYS_REG(3, 3, 14, 15, 4), + ARM64_SYS_REG(3, 3, 14, 15, 5), + ARM64_SYS_REG(3, 3, 14, 15, 6), + ARM64_SYS_REG(3, 3, 14, 15, 7), /* PMCCFILTR_EL0 */ + ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */ + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2, +}; +static __u64 base_regs_n = ARRAY_SIZE(base_regs); + +static __u64 vregs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]), +}; +static __u64 vregs_n = ARRAY_SIZE(vregs); + +static __u64 sve_regs[] = { + KVM_REG_ARM64_SVE_VLS, + KVM_REG_ARM64_SVE_ZREG(0, 0), + KVM_REG_ARM64_SVE_ZREG(1, 0), + KVM_REG_ARM64_SVE_ZREG(2, 0), + KVM_REG_ARM64_SVE_ZREG(3, 0), + KVM_REG_ARM64_SVE_ZREG(4, 0), + KVM_REG_ARM64_SVE_ZREG(5, 0), + KVM_REG_ARM64_SVE_ZREG(6, 0), + KVM_REG_ARM64_SVE_ZREG(7, 0), + KVM_REG_ARM64_SVE_ZREG(8, 0), + KVM_REG_ARM64_SVE_ZREG(9, 0), + KVM_REG_ARM64_SVE_ZREG(10, 0), + KVM_REG_ARM64_SVE_ZREG(11, 0), + KVM_REG_ARM64_SVE_ZREG(12, 0), + KVM_REG_ARM64_SVE_ZREG(13, 0), + KVM_REG_ARM64_SVE_ZREG(14, 0), + KVM_REG_ARM64_SVE_ZREG(15, 0), + KVM_REG_ARM64_SVE_ZREG(16, 0), + KVM_REG_ARM64_SVE_ZREG(17, 0), + KVM_REG_ARM64_SVE_ZREG(18, 0), + KVM_REG_ARM64_SVE_ZREG(19, 0), + KVM_REG_ARM64_SVE_ZREG(20, 0), + KVM_REG_ARM64_SVE_ZREG(21, 0), + KVM_REG_ARM64_SVE_ZREG(22, 0), + KVM_REG_ARM64_SVE_ZREG(23, 0), + KVM_REG_ARM64_SVE_ZREG(24, 0), + KVM_REG_ARM64_SVE_ZREG(25, 0), + KVM_REG_ARM64_SVE_ZREG(26, 0), + KVM_REG_ARM64_SVE_ZREG(27, 0), + KVM_REG_ARM64_SVE_ZREG(28, 0), + KVM_REG_ARM64_SVE_ZREG(29, 0), + KVM_REG_ARM64_SVE_ZREG(30, 0), + KVM_REG_ARM64_SVE_ZREG(31, 0), + KVM_REG_ARM64_SVE_PREG(0, 0), + KVM_REG_ARM64_SVE_PREG(1, 0), + KVM_REG_ARM64_SVE_PREG(2, 0), + KVM_REG_ARM64_SVE_PREG(3, 0), + KVM_REG_ARM64_SVE_PREG(4, 0), + KVM_REG_ARM64_SVE_PREG(5, 0), + KVM_REG_ARM64_SVE_PREG(6, 0), + KVM_REG_ARM64_SVE_PREG(7, 0), + KVM_REG_ARM64_SVE_PREG(8, 0), + KVM_REG_ARM64_SVE_PREG(9, 0), + KVM_REG_ARM64_SVE_PREG(10, 0), + KVM_REG_ARM64_SVE_PREG(11, 0), + KVM_REG_ARM64_SVE_PREG(12, 0), + KVM_REG_ARM64_SVE_PREG(13, 0), + KVM_REG_ARM64_SVE_PREG(14, 0), + KVM_REG_ARM64_SVE_PREG(15, 0), + KVM_REG_ARM64_SVE_FFR(0), + ARM64_SYS_REG(3, 0, 1, 2, 0), /* ZCR_EL1 */ +}; +static __u64 sve_regs_n = ARRAY_SIZE(sve_regs); + +static __u64 rejects_set[] = { +#ifdef REG_LIST_SVE + KVM_REG_ARM64_SVE_VLS, +#endif +}; +static __u64 rejects_set_n = ARRAY_SIZE(rejects_set); diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c deleted file mode 100644 index 11672ec6f74e..000000000000 --- a/tools/testing/selftests/kvm/clear_dirty_log_test.c +++ /dev/null @@ -1,6 +0,0 @@ -#define USE_CLEAR_DIRTY_LOG -#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) -#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) -#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ - KVM_DIRTY_LOG_INITIALLY_SET) -#include "dirty_log_test.c" diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 360cd3ea4cd6..3d96a7bfaff3 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -21,20 +21,12 @@ #include <linux/bitops.h> #include <linux/userfaultfd.h> -#include "test_util.h" -#include "kvm_util.h" +#include "perf_test_util.h" #include "processor.h" +#include "test_util.h" #ifdef __NR_userfaultfd -/* The memory slot index demand page */ -#define TEST_MEM_SLOT_INDEX 1 - -/* Default guest test virtual memory offset */ -#define DEFAULT_GUEST_TEST_MEM 0xc0000000 - -#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */ - #ifdef PRINT_PER_PAGE_UPDATES #define PER_PAGE_DEBUG(...) printf(__VA_ARGS__) #else @@ -47,77 +39,17 @@ #define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__) #endif -#define MAX_VCPUS 512 - -/* - * Guest/Host shared variables. Ensure addr_gva2hva() and/or - * sync_global_to/from_guest() are used when accessing from - * the host. READ/WRITE_ONCE() should also be used with anything - * that may change. - */ -static uint64_t host_page_size; -static uint64_t guest_page_size; - static char *guest_data_prototype; -/* - * Guest physical memory offset of the testing memory slot. - * This will be set to the topmost valid physical address minus - * the test memory size. - */ -static uint64_t guest_test_phys_mem; - -/* - * Guest virtual memory offset of the testing memory slot. - * Must not conflict with identity mapped test code. - */ -static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; - -struct vcpu_args { - uint64_t gva; - uint64_t pages; - - /* Only used by the host userspace part of the vCPU thread */ - int vcpu_id; - struct kvm_vm *vm; -}; - -static struct vcpu_args vcpu_args[MAX_VCPUS]; - -/* - * Continuously write to the first 8 bytes of each page in the demand paging - * memory region. - */ -static void guest_code(uint32_t vcpu_id) -{ - uint64_t gva; - uint64_t pages; - int i; - - /* Make sure vCPU args data structure is not corrupt. */ - GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id); - - gva = vcpu_args[vcpu_id].gva; - pages = vcpu_args[vcpu_id].pages; - - for (i = 0; i < pages; i++) { - uint64_t addr = gva + (i * guest_page_size); - - addr &= ~(host_page_size - 1); - *(uint64_t *)addr = 0x0123456789ABCDEF; - } - - GUEST_SYNC(1); -} - static void *vcpu_worker(void *data) { int ret; - struct vcpu_args *args = (struct vcpu_args *)data; - struct kvm_vm *vm = args->vm; - int vcpu_id = args->vcpu_id; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; vcpu_args_set(vm, vcpu_id, 1, vcpu_id); run = vcpu_state(vm, vcpu_id); @@ -133,52 +65,18 @@ static void *vcpu_worker(void *data) exit_reason_str(run->exit_reason)); } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, ts_diff.tv_sec, ts_diff.tv_nsec); return NULL; } -#define PAGE_SHIFT_4K 12 -#define PTES_PER_4K_PT 512 - -static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, - uint64_t vcpu_memory_bytes) -{ - struct kvm_vm *vm; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES; - - /* Account for a few pages per-vCPU for stacks */ - pages += DEFAULT_STACK_PGS * vcpus; - - /* - * Reserve twice the ammount of memory needed to map the test region and - * the page table / stacks region, at 4k, for page tables. Do the - * calculation with 4K page size: the smallest of all archs. (e.g., 64K - * page size guest will need even less memory for page tables). - */ - pages += (2 * pages) / PTES_PER_4K_PT; - pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / - PTES_PER_4K_PT; - pages = vm_adjust_num_guest_pages(mode, pages); - - pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - - vm = _vm_create(mode, pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif - return vm; -} - static int handle_uffd_page_request(int uffd, uint64_t addr) { pid_t tid; struct timespec start; - struct timespec end; + struct timespec ts_diff; struct uffdio_copy copy; int r; @@ -186,7 +84,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) copy.src = (uint64_t)guest_data_prototype; copy.dst = addr; - copy.len = host_page_size; + copy.len = perf_test_args.host_page_size; copy.mode = 0; clock_gettime(CLOCK_MONOTONIC, &start); @@ -198,12 +96,12 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) return r; } - clock_gettime(CLOCK_MONOTONIC, &end); + ts_diff = timespec_diff_now(start); PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, - timespec_to_ns(timespec_sub(end, start))); + timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - host_page_size, addr, tid); + perf_test_args.host_page_size, addr, tid); return 0; } @@ -223,7 +121,8 @@ static void *uffd_handler_thread_fn(void *arg) int pipefd = uffd_args->pipefd; useconds_t delay = uffd_args->delay; int64_t pages = 0; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; clock_gettime(CLOCK_MONOTONIC, &start); while (!quit_uffd_thread) { @@ -292,8 +191,7 @@ static void *uffd_handler_thread_fn(void *arg) pages++; } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n", pages, ts_diff.tv_sec, ts_diff.tv_nsec, pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); @@ -351,99 +249,54 @@ static int setup_demand_paging(struct kvm_vm *vm, } static void run_test(enum vm_guest_mode mode, bool use_uffd, - useconds_t uffd_delay, int vcpus, - uint64_t vcpu_memory_bytes) + useconds_t uffd_delay) { pthread_t *vcpu_threads; pthread_t *uffd_handler_threads = NULL; struct uffd_handler_args *uffd_args = NULL; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; int *pipefds = NULL; struct kvm_vm *vm; - uint64_t guest_num_pages; int vcpu_id; int r; - vm = create_vm(mode, vcpus, vcpu_memory_bytes); - - guest_page_size = vm_get_page_size(vm); - - TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0, - "Guest memory size is not guest page size aligned."); - - guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size; - guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); - - /* - * If there should be more memory in the guest test region than there - * can be pages in the guest, it will definitely cause problems. - */ - TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), - "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", - guest_num_pages, vm_get_max_gfn(vm), vcpus, - vcpu_memory_bytes); - - host_page_size = getpagesize(); - TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0, - "Guest memory size is not host page size aligned."); + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); - guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * - guest_page_size; - guest_test_phys_mem &= ~(host_page_size - 1); + perf_test_args.wr_fract = 1; -#ifdef __s390x__ - /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); -#endif - - pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); - - /* Add an extra memory slot for testing demand paging */ - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - guest_test_phys_mem, - TEST_MEM_SLOT_INDEX, - guest_num_pages, 0); - - /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); - - ucall_init(vm, NULL); - - guest_data_prototype = malloc(host_page_size); + guest_data_prototype = malloc(perf_test_args.host_page_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, host_page_size); + memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); - vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads)); + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + if (use_uffd) { uffd_handler_threads = - malloc(vcpus * sizeof(*uffd_handler_threads)); + malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); - uffd_args = malloc(vcpus * sizeof(*uffd_args)); + uffd_args = malloc(nr_vcpus * sizeof(*uffd_args)); TEST_ASSERT(uffd_args, "Memory allocation failed"); - pipefds = malloc(sizeof(int) * vcpus * 2); + pipefds = malloc(sizeof(int) * nr_vcpus * 2); TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); - } - - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - vm_paddr_t vcpu_gpa; - void *vcpu_hva; - vm_vcpu_add_default(vm, vcpu_id, guest_code); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + vm_paddr_t vcpu_gpa; + void *vcpu_hva; - vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); - PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size); + PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size); - /* Cache the HVA pointer of the region */ - vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + /* Cache the HVA pointer of the region */ + vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); - if (use_uffd) { /* * Set up user fault fd to handle demand paging * requests. @@ -456,53 +309,41 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, &uffd_handler_threads[vcpu_id], pipefds[vcpu_id * 2], uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_memory_bytes); + vcpu_hva, guest_percpu_mem_size); if (r < 0) exit(-r); } - -#ifdef __x86_64__ - vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); -#endif - - vcpu_args[vcpu_id].vm = vm; - vcpu_args[vcpu_id].vcpu_id = vcpu_id; - vcpu_args[vcpu_id].gva = guest_test_virt_mem + - (vcpu_id * vcpu_memory_bytes); - vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size; } /* Export the shared variables to the guest */ - sync_global_to_guest(vm, host_page_size); - sync_global_to_guest(vm, guest_page_size); - sync_global_to_guest(vm, vcpu_args); + sync_global_to_guest(vm, perf_test_args); pr_info("Finished creating vCPUs and starting uffd threads\n"); clock_gettime(CLOCK_MONOTONIC, &start); - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &vcpu_args[vcpu_id]); + &perf_test_args.vcpu_args[vcpu_id]); } pr_info("Started all vCPUs\n"); /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { pthread_join(vcpu_threads[vcpu_id], NULL); PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id); } - pr_info("All vCPU threads joined\n"); + ts_diff = timespec_diff_now(start); - clock_gettime(CLOCK_MONOTONIC, &end); + pr_info("All vCPU threads joined\n"); if (use_uffd) { char c; /* Tell the user fault fd handler threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { r = write(pipefds[vcpu_id * 2 + 1], &c, 1); TEST_ASSERT(r == 1, "Unable to write to pipefd"); @@ -510,11 +351,11 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, } } - ts_diff = timespec_sub(end, start); pr_info("Total guest execution time: %ld.%.9lds\n", ts_diff.tv_sec, ts_diff.tv_nsec); pr_info("Overall demand paging rate: %f pgs/sec\n", - guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); + perf_test_args.vcpu_args[0].pages * nr_vcpus / + ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); ucall_uninit(vm); kvm_vm_free(vm); @@ -568,9 +409,8 @@ static void help(char *name) int main(int argc, char *argv[]) { + int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); bool mode_selected = false; - uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE; - int vcpus = 1; unsigned int mode; int opt, i; bool use_uffd = false; @@ -619,15 +459,12 @@ int main(int argc, char *argv[]) "A negative UFFD delay is not supported."); break; case 'b': - vcpu_memory_bytes = parse_size(optarg); + guest_percpu_mem_size = parse_size(optarg); break; case 'v': - vcpus = atoi(optarg); - TEST_ASSERT(vcpus > 0, - "Must have a positive number of vCPUs"); - TEST_ASSERT(vcpus <= MAX_VCPUS, - "This test does not currently support\n" - "more than %d vCPUs.", MAX_VCPUS); + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, + "Invalid number of vcpus, must be between 1 and %d", max_vcpus); break; case 'h': default: @@ -642,7 +479,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes); + run_test(i, use_uffd, uffd_delay); } return 0; diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c new file mode 100644 index 000000000000..9c6a7be31e03 --- /dev/null +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -0,0 +1,365 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM dirty page logging performance test + * + * Based on dirty_log_test.c + * + * Copyright (C) 2018, Red Hat, Inc. + * Copyright (C) 2020, Google, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <time.h> +#include <pthread.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> + +#include "kvm_util.h" +#include "perf_test_util.h" +#include "processor.h" +#include "test_util.h" + +/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ +#define TEST_HOST_LOOP_N 2UL + +/* Host variables */ +static u64 dirty_log_manual_caps; +static bool host_quit; +static uint64_t iteration; +static uint64_t vcpu_last_completed_iteration[MAX_VCPUS]; + +static void *vcpu_worker(void *data) +{ + int ret; + struct kvm_vm *vm = perf_test_args.vm; + uint64_t pages_count = 0; + struct kvm_run *run; + struct timespec start; + struct timespec ts_diff; + struct timespec total = (struct timespec){0}; + struct timespec avg; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + run = vcpu_state(vm, vcpu_id); + + while (!READ_ONCE(host_quit)) { + uint64_t current_iteration = READ_ONCE(iteration); + + clock_gettime(CLOCK_MONOTONIC, &start); + ret = _vcpu_run(vm, vcpu_id); + ts_diff = timespec_diff_now(start); + + TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); + TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC, + "Invalid guest sync status: exit_reason=%s\n", + exit_reason_str(run->exit_reason)); + + pr_debug("Got sync event from vCPU %d\n", vcpu_id); + vcpu_last_completed_iteration[vcpu_id] = current_iteration; + pr_debug("vCPU %d updated last completed iteration to %lu\n", + vcpu_id, vcpu_last_completed_iteration[vcpu_id]); + + if (current_iteration) { + pages_count += vcpu_args->pages; + total = timespec_add(total, ts_diff); + pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } else { + pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } + + while (current_iteration == READ_ONCE(iteration) && + !READ_ONCE(host_quit)) {} + } + + avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]); + pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id], + total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec); + + return NULL; +} + +static void run_test(enum vm_guest_mode mode, unsigned long iterations, + uint64_t phys_offset, int wr_fract) +{ + pthread_t *vcpu_threads; + struct kvm_vm *vm; + unsigned long *bmap; + uint64_t guest_num_pages; + uint64_t host_num_pages; + int vcpu_id; + struct timespec start; + struct timespec ts_diff; + struct timespec get_dirty_log_total = (struct timespec){0}; + struct timespec vcpu_dirty_total = (struct timespec){0}; + struct timespec avg; + struct kvm_enable_cap cap = {}; + struct timespec clear_dirty_log_total = (struct timespec){0}; + + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); + + perf_test_args.wr_fract = wr_fract; + + guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + host_num_pages = vm_num_host_pages(mode, guest_num_pages); + bmap = bitmap_alloc(host_num_pages); + + if (dirty_log_manual_caps) { + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = dirty_log_manual_caps; + vm_enable_cap(vm, &cap); + } + + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); + TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + + sync_global_to_guest(vm, perf_test_args); + + /* Start the iterations */ + iteration = 0; + host_quit = false; + + clock_gettime(CLOCK_MONOTONIC, &start); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, + &perf_test_args.vcpu_args[vcpu_id]); + } + + /* Allow the vCPU to populate memory */ + pr_debug("Starting iteration %lu - Populating\n", iteration); + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n", + iteration); + + ts_diff = timespec_diff_now(start); + pr_info("Populate memory time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + /* Enable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, + KVM_MEM_LOG_DIRTY_PAGES); + ts_diff = timespec_diff_now(start); + pr_info("Enabling dirty logging time: %ld.%.9lds\n\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + while (iteration < iterations) { + /* + * Incrementing the iteration number will start the vCPUs + * dirtying memory again. + */ + clock_gettime(CLOCK_MONOTONIC, &start); + iteration++; + + pr_debug("Starting iteration %lu\n", iteration); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n", + vcpu_id, iteration); + } + + ts_diff = timespec_diff_now(start); + vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff); + pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); + + ts_diff = timespec_diff_now(start); + get_dirty_log_total = timespec_add(get_dirty_log_total, + ts_diff); + pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + + if (dirty_log_manual_caps) { + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, + host_num_pages); + + ts_diff = timespec_diff_now(start); + clear_dirty_log_total = timespec_add(clear_dirty_log_total, + ts_diff); + pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + } + } + + /* Tell the vcpu thread to quit */ + host_quit = true; + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) + pthread_join(vcpu_threads[vcpu_id], NULL); + + /* Disable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0); + ts_diff = timespec_diff_now(start); + pr_info("Disabling dirty logging time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + avg = timespec_div(get_dirty_log_total, iterations); + pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, get_dirty_log_total.tv_sec, + get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); + + if (dirty_log_manual_caps) { + avg = timespec_div(clear_dirty_log_total, iterations); + pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, clear_dirty_log_total.tv_sec, + clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); + } + + free(bmap); + free(vcpu_threads); + ucall_uninit(vm); + kvm_vm_free(vm); +} + +struct guest_mode { + bool supported; + bool enabled; +}; +static struct guest_mode guest_modes[NUM_VM_MODES]; + +#define guest_mode_init(mode, supported, enabled) ({ \ + guest_modes[mode] = (struct guest_mode){ supported, enabled }; \ +}) + +static void help(char *name) +{ + int i; + + puts(""); + printf("usage: %s [-h] [-i iterations] [-p offset] " + "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name); + puts(""); + printf(" -i: specify iteration counts (default: %"PRIu64")\n", + TEST_HOST_LOOP_N); + printf(" -p: specify guest physical test memory offset\n" + " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -m: specify the guest mode ID to test " + "(default: test all supported modes)\n" + " This option may be used multiple times.\n" + " Guest mode IDs:\n"); + for (i = 0; i < NUM_VM_MODES; ++i) { + printf(" %d: %s%s\n", i, vm_guest_mode_string(i), + guest_modes[i].supported ? " (supported)" : ""); + } + printf(" -b: specify the size of the memory region which should be\n" + " dirtied by each vCPU. e.g. 10M or 3G.\n" + " (default: 1G)\n"); + printf(" -f: specify the fraction of pages which should be written to\n" + " as opposed to simply read, in the form\n" + " 1/<fraction of pages to write>.\n" + " (default: 1 i.e. all pages are written to.)\n"); + printf(" -v: specify the number of vCPUs to run.\n"); + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + unsigned long iterations = TEST_HOST_LOOP_N; + bool mode_selected = false; + uint64_t phys_offset = 0; + unsigned int mode; + int opt, i; + int wr_fract = 1; + + dirty_log_manual_caps = + kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + +#ifdef __x86_64__ + guest_mode_init(VM_MODE_PXXV48_4K, true, true); +#endif +#ifdef __aarch64__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); + guest_mode_init(VM_MODE_P40V48_64K, true, true); + + { + unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + + if (limit >= 52) + guest_mode_init(VM_MODE_P52V48_64K, true, true); + if (limit >= 48) { + guest_mode_init(VM_MODE_P48V48_4K, true, true); + guest_mode_init(VM_MODE_P48V48_64K, true, true); + } + } +#endif +#ifdef __s390x__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); +#endif + + while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) { + switch (opt) { + case 'i': + iterations = strtol(optarg, NULL, 10); + break; + case 'p': + phys_offset = strtoull(optarg, NULL, 0); + break; + case 'm': + if (!mode_selected) { + for (i = 0; i < NUM_VM_MODES; ++i) + guest_modes[i].enabled = false; + mode_selected = true; + } + mode = strtoul(optarg, NULL, 10); + TEST_ASSERT(mode < NUM_VM_MODES, + "Guest mode ID %d too big", mode); + guest_modes[mode].enabled = true; + break; + case 'b': + guest_percpu_mem_size = parse_size(optarg); + break; + case 'f': + wr_fract = atoi(optarg); + TEST_ASSERT(wr_fract >= 1, + "Write fraction cannot be less than one"); + break; + case 'v': + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0, + "Must have a positive number of vCPUs"); + TEST_ASSERT(nr_vcpus <= MAX_VCPUS, + "This test does not currently support\n" + "more than %d vCPUs.", MAX_VCPUS); + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + TEST_ASSERT(iterations >= 2, "The test should have at least two iterations"); + + pr_info("Test iterations: %"PRIu64"\n", iterations); + + for (i = 0; i < NUM_VM_MODES; ++i) { + if (!guest_modes[i].enabled) + continue; + TEST_ASSERT(guest_modes[i].supported, + "Guest mode ID %d (%s) not supported.", + i, vm_guest_mode_string(i)); + run_test(i, iterations, phys_offset, wr_fract); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 752ec158ac59..471baecb7772 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -12,8 +12,13 @@ #include <unistd.h> #include <time.h> #include <pthread.h> +#include <semaphore.h> +#include <sys/types.h> +#include <signal.h> +#include <errno.h> #include <linux/bitmap.h> #include <linux/bitops.h> +#include <asm/barrier.h> #include "test_util.h" #include "kvm_util.h" @@ -57,6 +62,10 @@ # define test_and_clear_bit_le test_and_clear_bit #endif +#define TEST_DIRTY_RING_COUNT 65536 + +#define SIG_IPI SIGUSR1 + /* * Guest/Host shared variables. Ensure addr_gva2hva() and/or * sync_global_to/from_guest() are used when accessing from @@ -128,6 +137,285 @@ static uint64_t host_dirty_count; static uint64_t host_clear_count; static uint64_t host_track_next_count; +/* Whether dirty ring reset is requested, or finished */ +static sem_t dirty_ring_vcpu_stop; +static sem_t dirty_ring_vcpu_cont; +/* + * This is updated by the vcpu thread to tell the host whether it's a + * ring-full event. It should only be read until a sem_wait() of + * dirty_ring_vcpu_stop and before vcpu continues to run. + */ +static bool dirty_ring_vcpu_ring_full; +/* + * This is only used for verifying the dirty pages. Dirty ring has a very + * tricky case when the ring just got full, kvm will do userspace exit due to + * ring full. When that happens, the very last PFN is set but actually the + * data is not changed (the guest WRITE is not really applied yet), because + * we found that the dirty ring is full, refused to continue the vcpu, and + * recorded the dirty gfn with the old contents. + * + * For this specific case, it's safe to skip checking this pfn for this + * bit, because it's a redundant bit, and when the write happens later the bit + * will be set again. We use this variable to always keep track of the latest + * dirty gfn we've collected, so that if a mismatch of data found later in the + * verifying process, we let it pass. + */ +static uint64_t dirty_ring_last_page; + +enum log_mode_t { + /* Only use KVM_GET_DIRTY_LOG for logging */ + LOG_MODE_DIRTY_LOG = 0, + + /* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */ + LOG_MODE_CLEAR_LOG = 1, + + /* Use dirty ring for logging */ + LOG_MODE_DIRTY_RING = 2, + + LOG_MODE_NUM, + + /* Run all supported modes */ + LOG_MODE_ALL = LOG_MODE_NUM, +}; + +/* Mode of logging to test. Default is to run all supported modes */ +static enum log_mode_t host_log_mode_option = LOG_MODE_ALL; +/* Logging mode for current run */ +static enum log_mode_t host_log_mode; +static pthread_t vcpu_thread; +static uint32_t test_dirty_ring_count = TEST_DIRTY_RING_COUNT; + +static void vcpu_kick(void) +{ + pthread_kill(vcpu_thread, SIG_IPI); +} + +/* + * In our test we do signal tricks, let's use a better version of + * sem_wait to avoid signal interrupts + */ +static void sem_wait_until(sem_t *sem) +{ + int ret; + + do + ret = sem_wait(sem); + while (ret == -1 && errno == EINTR); +} + +static bool clear_log_supported(void) +{ + return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); +} + +static void clear_log_create_vm_done(struct kvm_vm *vm) +{ + struct kvm_enable_cap cap = {}; + u64 manual_caps; + + manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!"); + manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = manual_caps; + vm_enable_cap(vm, &cap); +} + +static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); +} + +static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); + kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages); +} + +static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + TEST_ASSERT(ret == 0 || (ret == -1 && err == EINTR), + "vcpu run failed: errno=%d", err); + + TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC, + "Invalid guest sync status: exit_reason=%s\n", + exit_reason_str(run->exit_reason)); +} + +static bool dirty_ring_supported(void) +{ + return kvm_check_cap(KVM_CAP_DIRTY_LOG_RING); +} + +static void dirty_ring_create_vm_done(struct kvm_vm *vm) +{ + /* + * Switch to dirty ring mode after VM creation but before any + * of the vcpu creation. + */ + vm_enable_dirty_ring(vm, test_dirty_ring_count * + sizeof(struct kvm_dirty_gfn)); +} + +static inline bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn) +{ + return gfn->flags == KVM_DIRTY_GFN_F_DIRTY; +} + +static inline void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn) +{ + gfn->flags = KVM_DIRTY_GFN_F_RESET; +} + +static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns, + int slot, void *bitmap, + uint32_t num_pages, uint32_t *fetch_index) +{ + struct kvm_dirty_gfn *cur; + uint32_t count = 0; + + while (true) { + cur = &dirty_gfns[*fetch_index % test_dirty_ring_count]; + if (!dirty_gfn_is_dirtied(cur)) + break; + TEST_ASSERT(cur->slot == slot, "Slot number didn't match: " + "%u != %u", cur->slot, slot); + TEST_ASSERT(cur->offset < num_pages, "Offset overflow: " + "0x%llx >= 0x%x", cur->offset, num_pages); + //pr_info("fetch 0x%x page %llu\n", *fetch_index, cur->offset); + set_bit_le(cur->offset, bitmap); + dirty_ring_last_page = cur->offset; + dirty_gfn_set_collected(cur); + (*fetch_index)++; + count++; + } + + return count; +} + +static void dirty_ring_wait_vcpu(void) +{ + /* This makes sure that hardware PML cache flushed */ + vcpu_kick(); + sem_wait_until(&dirty_ring_vcpu_stop); +} + +static void dirty_ring_continue_vcpu(void) +{ + pr_info("Notifying vcpu to continue\n"); + sem_post(&dirty_ring_vcpu_cont); +} + +static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + /* We only have one vcpu */ + static uint32_t fetch_index = 0; + uint32_t count = 0, cleared; + bool continued_vcpu = false; + + dirty_ring_wait_vcpu(); + + if (!dirty_ring_vcpu_ring_full) { + /* + * This is not a ring-full event, it's safe to allow + * vcpu to continue + */ + dirty_ring_continue_vcpu(); + continued_vcpu = true; + } + + /* Only have one vcpu */ + count = dirty_ring_collect_one(vcpu_map_dirty_ring(vm, VCPU_ID), + slot, bitmap, num_pages, &fetch_index); + + cleared = kvm_vm_reset_dirty_ring(vm); + + /* Cleared pages should be the same as collected */ + TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch " + "with collected (%u)", cleared, count); + + if (!continued_vcpu) { + TEST_ASSERT(dirty_ring_vcpu_ring_full, + "Didn't continue vcpu even without ring full"); + dirty_ring_continue_vcpu(); + } + + pr_info("Iteration %ld collected %u pages\n", iteration, count); +} + +static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + /* A ucall-sync or ring-full event is allowed */ + if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) { + /* We should allow this to continue */ + ; + } else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL || + (ret == -1 && err == EINTR)) { + /* Update the flag first before pause */ + WRITE_ONCE(dirty_ring_vcpu_ring_full, + run->exit_reason == KVM_EXIT_DIRTY_RING_FULL); + sem_post(&dirty_ring_vcpu_stop); + pr_info("vcpu stops because %s...\n", + dirty_ring_vcpu_ring_full ? + "dirty ring is full" : "vcpu is kicked out"); + sem_wait_until(&dirty_ring_vcpu_cont); + pr_info("vcpu continues now.\n"); + } else { + TEST_ASSERT(false, "Invalid guest sync status: " + "exit_reason=%s\n", + exit_reason_str(run->exit_reason)); + } +} + +static void dirty_ring_before_vcpu_join(void) +{ + /* Kick another round of vcpu just to make sure it will quit */ + sem_post(&dirty_ring_vcpu_cont); +} + +struct log_mode { + const char *name; + /* Return true if this mode is supported, otherwise false */ + bool (*supported)(void); + /* Hook when the vm creation is done (before vcpu creation) */ + void (*create_vm_done)(struct kvm_vm *vm); + /* Hook to collect the dirty pages into the bitmap provided */ + void (*collect_dirty_pages) (struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages); + /* Hook to call when after each vcpu run */ + void (*after_vcpu_run)(struct kvm_vm *vm, int ret, int err); + void (*before_vcpu_join) (void); +} log_modes[LOG_MODE_NUM] = { + { + .name = "dirty-log", + .collect_dirty_pages = dirty_log_collect_dirty_pages, + .after_vcpu_run = default_after_vcpu_run, + }, + { + .name = "clear-log", + .supported = clear_log_supported, + .create_vm_done = clear_log_create_vm_done, + .collect_dirty_pages = clear_log_collect_dirty_pages, + .after_vcpu_run = default_after_vcpu_run, + }, + { + .name = "dirty-ring", + .supported = dirty_ring_supported, + .create_vm_done = dirty_ring_create_vm_done, + .collect_dirty_pages = dirty_ring_collect_dirty_pages, + .before_vcpu_join = dirty_ring_before_vcpu_join, + .after_vcpu_run = dirty_ring_after_vcpu_run, + }, +}; + /* * We use this bitmap to track some pages that should have its dirty * bit set in the _next_ iteration. For example, if we detected the @@ -137,6 +425,60 @@ static uint64_t host_track_next_count; */ static unsigned long *host_bmap_track; +static void log_modes_dump(void) +{ + int i; + + printf("all"); + for (i = 0; i < LOG_MODE_NUM; i++) + printf(", %s", log_modes[i].name); + printf("\n"); +} + +static bool log_mode_supported(void) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->supported) + return mode->supported(); + + return true; +} + +static void log_mode_create_vm_done(struct kvm_vm *vm) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->create_vm_done) + mode->create_vm_done(vm); +} + +static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + TEST_ASSERT(mode->collect_dirty_pages != NULL, + "collect_dirty_pages() is required for any log mode!"); + mode->collect_dirty_pages(vm, slot, bitmap, num_pages); +} + +static void log_mode_after_vcpu_run(struct kvm_vm *vm, int ret, int err) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->after_vcpu_run) + mode->after_vcpu_run(vm, ret, err); +} + +static void log_mode_before_vcpu_join(void) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->before_vcpu_join) + mode->before_vcpu_join(); +} + static void generate_random_array(uint64_t *guest_array, uint64_t size) { uint64_t i; @@ -147,29 +489,44 @@ static void generate_random_array(uint64_t *guest_array, uint64_t size) static void *vcpu_worker(void *data) { - int ret; + int ret, vcpu_fd; struct kvm_vm *vm = data; uint64_t *guest_array; uint64_t pages_count = 0; - struct kvm_run *run; + struct kvm_signal_mask *sigmask = alloca(offsetof(struct kvm_signal_mask, sigset) + + sizeof(sigset_t)); + sigset_t *sigset = (sigset_t *) &sigmask->sigset; + + vcpu_fd = vcpu_get_fd(vm, VCPU_ID); + + /* + * SIG_IPI is unblocked atomically while in KVM_RUN. It causes the + * ioctl to return with -EINTR, but it is still pending and we need + * to accept it with the sigwait. + */ + sigmask->len = 8; + pthread_sigmask(0, NULL, sigset); + vcpu_ioctl(vm, VCPU_ID, KVM_SET_SIGNAL_MASK, sigmask); + sigaddset(sigset, SIG_IPI); + pthread_sigmask(SIG_BLOCK, sigset, NULL); - run = vcpu_state(vm, VCPU_ID); + sigemptyset(sigset); + sigaddset(sigset, SIG_IPI); guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array); - generate_random_array(guest_array, TEST_PAGES_PER_LOOP); while (!READ_ONCE(host_quit)) { + /* Clear any existing kick signals */ + generate_random_array(guest_array, TEST_PAGES_PER_LOOP); + pages_count += TEST_PAGES_PER_LOOP; /* Let the guest dirty the random pages */ - ret = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); - if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) { - pages_count += TEST_PAGES_PER_LOOP; - generate_random_array(guest_array, TEST_PAGES_PER_LOOP); - } else { - TEST_FAIL("Invalid guest sync status: " - "exit_reason=%s\n", - exit_reason_str(run->exit_reason)); + ret = ioctl(vcpu_fd, KVM_RUN, NULL); + if (ret == -1 && errno == EINTR) { + int sig = -1; + sigwait(sigset, &sig); + assert(sig == SIG_IPI); } + log_mode_after_vcpu_run(vm, ret, errno); } pr_info("Dirtied %"PRIu64" pages\n", pages_count); @@ -182,6 +539,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) uint64_t step = vm_num_host_pages(mode, 1); uint64_t page; uint64_t *value_ptr; + uint64_t min_iter = 0; for (page = 0; page < host_num_pages; page += step) { value_ptr = host_test_mem + page * host_page_size; @@ -195,15 +553,65 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) page); } - if (test_bit_le(page, bmap)) { + if (test_and_clear_bit_le(page, bmap)) { + bool matched; + host_dirty_count++; + /* * If the bit is set, the value written onto * the corresponding page should be either the * previous iteration number or the current one. */ - TEST_ASSERT(*value_ptr == iteration || - *value_ptr == iteration - 1, + matched = (*value_ptr == iteration || + *value_ptr == iteration - 1); + + if (host_log_mode == LOG_MODE_DIRTY_RING && !matched) { + if (*value_ptr == iteration - 2 && min_iter <= iteration - 2) { + /* + * Short answer: this case is special + * only for dirty ring test where the + * page is the last page before a kvm + * dirty ring full in iteration N-2. + * + * Long answer: Assuming ring size R, + * one possible condition is: + * + * main thr vcpu thr + * -------- -------- + * iter=1 + * write 1 to page 0~(R-1) + * full, vmexit + * collect 0~(R-1) + * kick vcpu + * write 1 to (R-1)~(2R-2) + * full, vmexit + * iter=2 + * collect (R-1)~(2R-2) + * kick vcpu + * write 1 to (2R-2) + * (NOTE!!! "1" cached in cpu reg) + * write 2 to (2R-1)~(3R-3) + * full, vmexit + * iter=3 + * collect (2R-2)~(3R-3) + * (here if we read value on page + * "2R-2" is 1, while iter=3!!!) + * + * This however can only happen once per iteration. + */ + min_iter = iteration - 1; + continue; + } else if (page == dirty_ring_last_page) { + /* + * Please refer to comments in + * dirty_ring_last_page. + */ + continue; + } + } + + TEST_ASSERT(matched, "Set page %"PRIu64" value %"PRIu64 " incorrect (iteration=%"PRIu64")", page, *value_ptr, iteration); @@ -252,11 +660,12 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); + vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); kvm_vm_elf_load(vm, program_invocation_name, 0, 0); #ifdef __x86_64__ vm_create_irqchip(vm); #endif + log_mode_create_vm_done(vm); vm_vcpu_add_default(vm, vcpuid, guest_code); return vm; } @@ -264,17 +673,18 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, #define DIRTY_MEM_BITS 30 /* 1G */ #define PAGE_SHIFT_4K 12 -#ifdef USE_CLEAR_DIRTY_LOG -static u64 dirty_log_manual_caps; -#endif - static void run_test(enum vm_guest_mode mode, unsigned long iterations, unsigned long interval, uint64_t phys_offset) { - pthread_t vcpu_thread; struct kvm_vm *vm; unsigned long *bmap; + if (!log_mode_supported()) { + print_skip("Log mode '%s' not supported", + log_modes[host_log_mode].name); + return; + } + /* * We reserve page table for 2 times of extra dirty mem which * will definitely cover the original (1G+) test range. Here @@ -317,14 +727,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, bmap = bitmap_alloc(host_num_pages); host_bmap_track = bitmap_alloc(host_num_pages); -#ifdef USE_CLEAR_DIRTY_LOG - struct kvm_enable_cap cap = {}; - - cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; - cap.args[0] = dirty_log_manual_caps; - vm_enable_cap(vm, &cap); -#endif - /* Add an extra memory slot for testing dirty logging */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, guest_test_phys_mem, @@ -338,9 +740,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, /* Cache the HVA pointer of the region */ host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem); -#ifdef __x86_64__ - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); -#endif ucall_init(vm, NULL); /* Export the shared variables to the guest */ @@ -362,11 +761,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, while (iteration < iterations) { /* Give the vcpu thread some time to dirty some pages */ usleep(interval * 1000); - kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); -#ifdef USE_CLEAR_DIRTY_LOG - kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, - host_num_pages); -#endif + log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX, + bmap, host_num_pages); vm_dirty_log_verify(mode, bmap); iteration++; sync_global_to_guest(vm, iteration); @@ -374,6 +770,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, /* Tell the vcpu thread to quit */ host_quit = true; + log_mode_before_vcpu_join(); pthread_join(vcpu_thread, NULL); pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), " @@ -404,12 +801,18 @@ static void help(char *name) printf("usage: %s [-h] [-i iterations] [-I interval] " "[-p offset] [-m mode]\n", name); puts(""); + printf(" -c: specify dirty ring size, in number of entries\n"); + printf(" (only useful for dirty-ring test; default: %"PRIu32")\n", + TEST_DIRTY_RING_COUNT); printf(" -i: specify iteration counts (default: %"PRIu64")\n", TEST_HOST_LOOP_N); printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n", TEST_HOST_LOOP_INTERVAL); printf(" -p: specify guest physical test memory offset\n" " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -M: specify the host logging mode " + "(default: run all log modes). Supported modes: \n\t"); + log_modes_dump(); printf(" -m: specify the guest mode ID to test " "(default: test all supported modes)\n" " This option may be used multiple times.\n" @@ -429,18 +832,10 @@ int main(int argc, char *argv[]) bool mode_selected = false; uint64_t phys_offset = 0; unsigned int mode; - int opt, i; - -#ifdef USE_CLEAR_DIRTY_LOG - dirty_log_manual_caps = - kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - if (!dirty_log_manual_caps) { - print_skip("KVM_CLEAR_DIRTY_LOG not available"); - exit(KSFT_SKIP); - } - dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | - KVM_DIRTY_LOG_INITIALLY_SET); -#endif + int opt, i, j; + + sem_init(&dirty_ring_vcpu_stop, 0, 0); + sem_init(&dirty_ring_vcpu_cont, 0, 0); #ifdef __x86_64__ guest_mode_init(VM_MODE_PXXV48_4K, true, true); @@ -464,8 +859,11 @@ int main(int argc, char *argv[]) guest_mode_init(VM_MODE_P40V48_4K, true, true); #endif - while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) { + while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) { switch (opt) { + case 'c': + test_dirty_ring_count = strtol(optarg, NULL, 10); + break; case 'i': iterations = strtol(optarg, NULL, 10); break; @@ -486,6 +884,26 @@ int main(int argc, char *argv[]) "Guest mode ID %d too big", mode); guest_modes[mode].enabled = true; break; + case 'M': + if (!strcmp(optarg, "all")) { + host_log_mode_option = LOG_MODE_ALL; + break; + } + for (i = 0; i < LOG_MODE_NUM; i++) { + if (!strcmp(optarg, log_modes[i].name)) { + pr_info("Setting log mode to: '%s'\n", + optarg); + host_log_mode_option = i; + break; + } + } + if (i == LOG_MODE_NUM) { + printf("Log mode '%s' invalid. Please choose " + "from: ", optarg); + log_modes_dump(); + exit(1); + } + break; case 'h': default: help(argv[0]); @@ -507,7 +925,18 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, iterations, interval, phys_offset); + if (host_log_mode_option == LOG_MODE_ALL) { + /* Run each log mode */ + for (j = 0; j < LOG_MODE_NUM; j++) { + pr_info("Testing Log Mode '%s'\n", + log_modes[j].name); + host_log_mode = j; + run_test(i, iterations, interval, phys_offset); + } + } else { + host_log_mode = host_log_mode_option; + run_test(i, iterations, interval, phys_offset); + } } return 0; diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 919e161dd289..dfa9d369e8fc 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -45,13 +45,28 @@ enum vm_guest_mode { }; #if defined(__aarch64__) -#define VM_MODE_DEFAULT VM_MODE_P40V48_4K + +#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + #elif defined(__x86_64__) -#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K -#else -#define VM_MODE_DEFAULT VM_MODE_P52V48_4K + +#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__s390x__) + +#define VM_MODE_DEFAULT VM_MODE_P52V48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 16) + #endif +#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) +#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) + #define vm_guest_mode_string(m) vm_guest_mode_string[m] extern const char * const vm_guest_mode_string[]; @@ -63,15 +78,18 @@ enum vm_mem_backing_src_type { int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap); +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp, int perm); void kvm_vm_release(struct kvm_vm *vmp); void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log); void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, uint64_t first_page, uint32_t num_pages); +uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm); int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, size_t len); @@ -112,6 +130,8 @@ void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, void *arg); void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); +void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); +int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); @@ -144,11 +164,13 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); +int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_guest_debug *debug); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); @@ -196,6 +218,7 @@ void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid, int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_nested_state *state, bool ignore_error); #endif +void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid); const char *exit_reason_str(unsigned int exit_reason); @@ -243,6 +266,16 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, void *guest_code); +/* Same as vm_create_default, but can be used for more than one vcpu */ +struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]); + +/* Like vm_create_default_with_vcpus, but accepts mode as a parameter */ +struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, + uint64_t extra_mem_pages, uint32_t num_percpu_pages, + void *guest_code, uint32_t vcpuids[]); + /* * Adds a vCPU with reasonable defaults (e.g. a stack) * @@ -294,6 +327,8 @@ int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); memcpy(&(g), _p, sizeof(g)); \ }) +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid); + /* Common ucalls */ enum { UCALL_NONE, diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h new file mode 100644 index 000000000000..239421e4f6b8 --- /dev/null +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * tools/testing/selftests/kvm/include/perf_test_util.h + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H +#define SELFTEST_KVM_PERF_TEST_UTIL_H + +#include "kvm_util.h" +#include "processor.h" + +#define MAX_VCPUS 512 + +#define PAGE_SHIFT_4K 12 +#define PTES_PER_4K_PT 512 + +#define TEST_MEM_SLOT_INDEX 1 + +/* Default guest test virtual memory offset */ +#define DEFAULT_GUEST_TEST_MEM 0xc0000000 + +#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */ + +/* + * Guest physical memory offset of the testing memory slot. + * This will be set to the topmost valid physical address minus + * the test memory size. + */ +static uint64_t guest_test_phys_mem; + +/* + * Guest virtual memory offset of the testing memory slot. + * Must not conflict with identity mapped test code. + */ +static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; + +/* Number of VCPUs for the test */ +static int nr_vcpus = 1; + +struct vcpu_args { + uint64_t gva; + uint64_t pages; + + /* Only used by the host userspace part of the vCPU thread */ + int vcpu_id; +}; + +struct perf_test_args { + struct kvm_vm *vm; + uint64_t host_page_size; + uint64_t guest_page_size; + int wr_fract; + + struct vcpu_args vcpu_args[MAX_VCPUS]; +}; + +static struct perf_test_args perf_test_args; + +/* + * Continuously write to the first 8 bytes of each page in the + * specified region. + */ +static void guest_code(uint32_t vcpu_id) +{ + struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + uint64_t gva; + uint64_t pages; + int i; + + /* Make sure vCPU args data structure is not corrupt. */ + GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id); + + gva = vcpu_args->gva; + pages = vcpu_args->pages; + + while (true) { + for (i = 0; i < pages; i++) { + uint64_t addr = gva + (i * perf_test_args.guest_page_size); + + if (i % perf_test_args.wr_fract == 0) + *(uint64_t *)addr = 0x0123456789ABCDEF; + else + READ_ONCE(*(uint64_t *)addr); + } + + GUEST_SYNC(1); + } +} + +static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, + uint64_t vcpu_memory_bytes) +{ + struct kvm_vm *vm; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES; + uint64_t guest_num_pages; + + /* Account for a few pages per-vCPU for stacks */ + pages += DEFAULT_STACK_PGS * vcpus; + + /* + * Reserve twice the ammount of memory needed to map the test region and + * the page table / stacks region, at 4k, for page tables. Do the + * calculation with 4K page size: the smallest of all archs. (e.g., 64K + * page size guest will need even less memory for page tables). + */ + pages += (2 * pages) / PTES_PER_4K_PT; + pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / + PTES_PER_4K_PT; + pages = vm_adjust_num_guest_pages(mode, pages); + + pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); + + vm = vm_create(mode, pages, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + + perf_test_args.vm = vm; + perf_test_args.guest_page_size = vm_get_page_size(vm); + perf_test_args.host_page_size = getpagesize(); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, + "Guest memory size is not guest page size aligned."); + + guest_num_pages = (vcpus * vcpu_memory_bytes) / + perf_test_args.guest_page_size; + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + + /* + * If there should be more memory in the guest test region than there + * can be pages in the guest, it will definitely cause problems. + */ + TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), + "Requested more guest memory than address space allows.\n" + " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + guest_num_pages, vm_get_max_gfn(vm), vcpus, + vcpu_memory_bytes); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0, + "Guest memory size is not host page size aligned."); + + guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * + perf_test_args.guest_page_size; + guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1); + +#ifdef __s390x__ + /* Align to 1M (segment size) */ + guest_test_phys_mem &= ~((1 << 20) - 1); +#endif + + pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + + /* Add an extra memory slot for testing */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + guest_test_phys_mem, + TEST_MEM_SLOT_INDEX, + guest_num_pages, 0); + + /* Do mapping for the demand paging memory slot */ + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); + + ucall_init(vm, NULL); + + return vm; +} + +static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes) +{ + vm_paddr_t vcpu_gpa; + struct vcpu_args *vcpu_args; + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + + vm_vcpu_add_default(vm, vcpu_id, guest_code); + + vcpu_args->vcpu_id = vcpu_id; + vcpu_args->gva = guest_test_virt_mem + + (vcpu_id * vcpu_memory_bytes); + vcpu_args->pages = vcpu_memory_bytes / + perf_test_args.guest_page_size; + + vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); + pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + } +} + +#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 5eb01bf51b86..ffffa560436b 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -64,5 +64,7 @@ int64_t timespec_to_ns(struct timespec ts); struct timespec timespec_add_ns(struct timespec ts, int64_t ns); struct timespec timespec_add(struct timespec ts1, struct timespec ts2); struct timespec timespec_sub(struct timespec ts1, struct timespec ts2); +struct timespec timespec_diff_now(struct timespec start); +struct timespec timespec_div(struct timespec ts, int divisor); #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 82b7fe16a824..90cd5984751b 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -27,6 +27,7 @@ #define X86_CR4_OSFXSR (1ul << 9) #define X86_CR4_OSXMMEXCPT (1ul << 10) #define X86_CR4_UMIP (1ul << 11) +#define X86_CR4_LA57 (1ul << 12) #define X86_CR4_VMXE (1ul << 13) #define X86_CR4_SMXE (1ul << 14) #define X86_CR4_FSGSBASE (1ul << 16) @@ -36,6 +37,24 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) +/* CPUID.1.ECX */ +#define CPUID_VMX (1ul << 5) +#define CPUID_SMX (1ul << 6) +#define CPUID_PCID (1ul << 17) +#define CPUID_XSAVE (1ul << 26) + +/* CPUID.7.EBX */ +#define CPUID_FSGSBASE (1ul << 0) +#define CPUID_SMEP (1ul << 7) +#define CPUID_SMAP (1ul << 20) + +/* CPUID.7.ECX */ +#define CPUID_UMIP (1ul << 2) +#define CPUID_PKU (1ul << 3) +#define CPUID_LA57 (1ul << 16) + +#define UNEXPECTED_VECTOR_PORT 0xfff0u + /* General Registers in 64-Bit Mode */ struct gpr64_regs { u64 rax; @@ -59,7 +78,7 @@ struct gpr64_regs { struct desc64 { uint16_t limit0; uint16_t base0; - unsigned base1:8, s:1, type:4, dpl:2, p:1; + unsigned base1:8, type:4, s:1, dpl:2, p:1; unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8; uint32_t base3; uint32_t zero1; @@ -239,6 +258,11 @@ static inline struct desc_ptr get_idt(void) return idt; } +static inline void outl(uint16_t port, uint32_t value) +{ + __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value)); +} + #define SET_XMM(__var, __xmm) \ asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm) @@ -338,6 +362,35 @@ uint32_t kvm_get_cpuid_max_basic(void); uint32_t kvm_get_cpuid_max_extended(void); void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); +struct ex_regs { + uint64_t rax, rcx, rdx, rbx; + uint64_t rbp, rsi, rdi; + uint64_t r8, r9, r10, r11; + uint64_t r12, r13, r14, r15; + uint64_t vector; + uint64_t error_code; + uint64_t rip; + uint64_t cs; + uint64_t rflags; +}; + +void vm_init_descriptor_tables(struct kvm_vm *vm); +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)); + +/* + * set_cpuid() - overwrites a matching cpuid entry with the provided value. + * matches based on ent->function && ent->index. returns true + * if a match was found and successfully overwritten. + * @cpuid: the kvm cpuid list to modify. + * @ent: cpuid entry to insert + */ +bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent); + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3); + /* * Basic CPU control in CR0 */ diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index e78d7e26ba61..65eb1079a161 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -11,10 +11,6 @@ #include <stdint.h> #include "processor.h" -#define CPUID_VMX_BIT 5 - -#define CPUID_VMX (1 << 5) - /* * Definitions of Primary Processor-Based VM-Execution Controls. */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 2afa6618b396..cee92d477dc0 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -5,8 +5,6 @@ * Copyright (C) 2018, Red Hat, Inc. */ -#define _GNU_SOURCE /* for program_invocation_name */ - #include <linux/compiler.h> #include "kvm_util.h" @@ -219,21 +217,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) } } -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code) -{ - uint64_t ptrs_per_4k_pte = 512; - uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2; - struct kvm_vm *vm; - - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); - - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); - vm_vcpu_add_default(vm, vcpuid, guest_code); - - return vm; -} - void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init) { struct kvm_vcpu_init default_init = { .target = -1, }; @@ -350,3 +333,7 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) va_end(ap); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index c8e0ec20d3bf..2f37b90ee1a9 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -94,6 +94,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_MMIO && run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) { vm_vaddr_t gva; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 3327cebc1095..88ef7067f1e6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -5,6 +5,7 @@ * Copyright (C) 2018, Google LLC. */ +#define _GNU_SOURCE /* for program_invocation_name */ #include "test_util.h" #include "kvm_util.h" #include "kvm_util_internal.h" @@ -86,6 +87,44 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) return ret; } +/* VCPU Enable Capability + * + * Input Args: + * vm - Virtual Machine + * vcpu_id - VCPU + * cap - Capability + * + * Output Args: None + * + * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * + * Enables a capability (KVM_CAP_*) on the VCPU. + */ +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpu_id); + int r; + + TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id); + + r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap); + TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n" + " rc: %i, errno: %i", r, errno); + + return r; +} + +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) +{ + struct kvm_enable_cap cap = { 0 }; + + cap.cap = KVM_CAP_DIRTY_LOG_RING; + cap.args[0] = ring_size; + vm_enable_cap(vm, &cap); + vm->dirty_ring_size = ring_size; +} + static void vm_open(struct kvm_vm *vm, int perm) { vm->kvm_fd = open(KVM_DEV_PATH, perm); @@ -152,7 +191,7 @@ _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) * descriptor to control the created VM is created with the permissions * given by perm (e.g. O_RDWR). */ -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) +struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) { struct kvm_vm *vm; @@ -243,9 +282,61 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } -struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) +struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, + uint64_t extra_mem_pages, uint32_t num_percpu_pages, + void *guest_code, uint32_t vcpuids[]) +{ + /* The maximum page table size for a memory region will be when the + * smallest pages are used. Considering each page contains x page + * table descriptors, the total extra size for page tables (for extra + * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller + * than N/x*2. + */ + uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; + uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; + struct kvm_vm *vm; + int i; + + TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), + "nr_vcpus = %d too large for host, max-vcpus = %d", + nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS)); + + pages = vm_adjust_num_guest_pages(mode, pages); + vm = vm_create(mode, pages, O_RDWR); + + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); + +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + + for (i = 0; i < nr_vcpus; ++i) { + uint32_t vcpuid = vcpuids ? vcpuids[i] : i; + + vm_vcpu_add_default(vm, vcpuid, guest_code); + +#ifdef __x86_64__ + vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid()); +#endif + } + + return vm; +} + +struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]) { - return _vm_create(mode, phy_pages, perm); + return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages, + num_percpu_pages, guest_code, vcpuids); +} + +struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, + void *guest_code) +{ + return vm_create_default_with_vcpus(1, extra_mem_pages, 0, guest_code, + (uint32_t []){ vcpuid }); } /* @@ -305,6 +396,11 @@ void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, __func__, strerror(-ret)); } +uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) +{ + return ioctl(vm->fd, KVM_RESET_DIRTY_RINGS); +} + /* * Userspace Memory Region Find * @@ -409,10 +505,17 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid) * * Removes a vCPU from a VM and frees its resources. */ -static void vm_vcpu_rm(struct vcpu *vcpu) +static void vm_vcpu_rm(struct kvm_vm *vm, struct vcpu *vcpu) { int ret; + if (vcpu->dirty_gfns) { + ret = munmap(vcpu->dirty_gfns, vm->dirty_ring_size); + TEST_ASSERT(ret == 0, "munmap of VCPU dirty ring failed, " + "rc: %i errno: %i", ret, errno); + vcpu->dirty_gfns = NULL; + } + ret = munmap(vcpu->state, sizeof(*vcpu->state)); TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i " "errno: %i", ret, errno); @@ -430,7 +533,7 @@ void kvm_vm_release(struct kvm_vm *vmp) int ret; list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list) - vm_vcpu_rm(vcpu); + vm_vcpu_rm(vmp, vcpu); ret = close(vmp->fd); TEST_ASSERT(ret == 0, "Close of vm fd failed,\n" @@ -1204,9 +1307,21 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) do { rc = ioctl(vcpu->fd, KVM_RUN, NULL); } while (rc == -1 && errno == EINTR); + + assert_on_unhandled_exception(vm, vcpuid); + return rc; } +int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + + return vcpu->fd; +} + void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); @@ -1261,6 +1376,35 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, } /* + * VM VCPU Get Reg List + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * + * Output Args: + * None + * + * Return: + * A pointer to an allocated struct kvm_reg_list + * + * Get the list of guest registers which are supported for + * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls + */ +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list; + int ret; + + ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, ®_list_n); + TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0"); + reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64)); + reg_list->n = reg_list_n.n; + vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list); + return reg_list; +} + +/* * VM VCPU Regs Get * * Input Args: @@ -1506,6 +1650,42 @@ int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, return ret; } +void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu; + uint32_t size = vm->dirty_ring_size; + + TEST_ASSERT(size > 0, "Should enable dirty ring first"); + + vcpu = vcpu_find(vm, vcpuid); + + TEST_ASSERT(vcpu, "Cannot find vcpu %u", vcpuid); + + if (!vcpu->dirty_gfns) { + void *addr; + + addr = mmap(NULL, size, PROT_READ, + MAP_PRIVATE, vcpu->fd, + vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped private"); + + addr = mmap(NULL, size, PROT_READ | PROT_EXEC, + MAP_PRIVATE, vcpu->fd, + vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped exec"); + + addr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_SHARED, vcpu->fd, + vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + TEST_ASSERT(addr != MAP_FAILED, "Dirty ring map failed"); + + vcpu->dirty_gfns = addr; + vcpu->dirty_gfns_count = size / sizeof(struct kvm_dirty_gfn); + } + + return vcpu->dirty_gfns; +} + /* * VM Ioctl * @@ -1528,6 +1708,32 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) } /* + * KVM system ioctl + * + * Input Args: + * vm - Virtual Machine + * cmd - Ioctl number + * arg - Argument to pass to the ioctl + * + * Return: None + * + * Issues an arbitrary ioctl on a KVM fd. + */ +void kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) +{ + int ret; + + ret = ioctl(vm->kvm_fd, cmd, arg); + TEST_ASSERT(ret == 0, "KVM ioctl %lu failed, rc: %i errno: %i (%s)", + cmd, ret, errno, strerror(errno)); +} + +int _kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) +{ + return ioctl(vm->kvm_fd, cmd, arg); +} + +/* * VM Dump * * Input Args: @@ -1599,6 +1805,9 @@ static struct exit_reason { {KVM_EXIT_INTERNAL_ERROR, "INTERNAL_ERROR"}, {KVM_EXIT_OSI, "OSI"}, {KVM_EXIT_PAPR_HCALL, "PAPR_HCALL"}, + {KVM_EXIT_DIRTY_RING_FULL, "DIRTY_RING_FULL"}, + {KVM_EXIT_X86_RDMSR, "RDMSR"}, + {KVM_EXIT_X86_WRMSR, "WRMSR"}, #ifdef KVM_EXIT_MEMORY_NOT_PRESENT {KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"}, #endif diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 2ef446520748..34465dc562d8 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -28,6 +28,9 @@ struct vcpu { uint32_t id; int fd; struct kvm_run *state; + struct kvm_dirty_gfn *dirty_gfns; + uint32_t fetch_index; + uint32_t dirty_gfns_count; }; struct kvm_vm { @@ -50,6 +53,9 @@ struct kvm_vm { vm_paddr_t pgd; vm_vaddr_t gdt; vm_vaddr_t tss; + vm_vaddr_t idt; + vm_vaddr_t handlers; + uint32_t dirty_ring_size; }; struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index a88c5d665725..0152f356c099 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -5,8 +5,6 @@ * Copyright (C) 2019, Red Hat, Inc. */ -#define _GNU_SOURCE /* for program_invocation_name */ - #include "processor.h" #include "kvm_util.h" #include "../kvm_util_internal.h" @@ -160,26 +158,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) virt_dump_region(stream, vm, indent, vm->pgd); } -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code) -{ - /* - * The additional amount of pages required for the page tables is: - * 1 * n / 256 + 4 * (n / 256) / 2048 + 4 * (n / 256) / 2048^2 + ... - * which is definitely smaller than (n / 256) * 2. - */ - uint64_t extra_pg_pages = extra_mem_pages / 256 * 2; - struct kvm_vm *vm; - - vm = vm_create(VM_MODE_DEFAULT, - DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); - - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); - vm_vcpu_add_default(vm, vcpuid, guest_code); - - return vm; -} - void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) { size_t stack_size = DEFAULT_STACK_PGS * getpagesize(); @@ -241,3 +219,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n", indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c index fd589dc9bfab..9d3b0f15249a 100644 --- a/tools/testing/selftests/kvm/lib/s390x/ucall.c +++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c @@ -38,6 +38,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_S390_SIEIC && run->s390_sieic.icptcode == 4 && (run->s390_sieic.ipa >> 8) == 0x83 && /* 0x83 means DIAGNOSE */ diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 689e97c27ee2..8e04c0b1608e 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -4,10 +4,13 @@ * * Copyright (C) 2020, Google LLC. */ -#include <stdlib.h> + +#include <assert.h> #include <ctype.h> #include <limits.h> -#include <assert.h> +#include <stdlib.h> +#include <time.h> + #include "test_util.h" /* @@ -81,6 +84,21 @@ struct timespec timespec_sub(struct timespec ts1, struct timespec ts2) return timespec_add_ns((struct timespec){0}, ns1 - ns2); } +struct timespec timespec_diff_now(struct timespec start) +{ + struct timespec end; + + clock_gettime(CLOCK_MONOTONIC, &end); + return timespec_sub(end, start); +} + +struct timespec timespec_div(struct timespec ts, int divisor) +{ + int64_t ns = timespec_to_ns(ts) / divisor; + + return timespec_add_ns((struct timespec){0}, ns); +} + void print_skip(const char *fmt, ...) { va_list ap; diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S new file mode 100644 index 000000000000..aaf7bc7d2ce1 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S @@ -0,0 +1,81 @@ +handle_exception: + push %r15 + push %r14 + push %r13 + push %r12 + push %r11 + push %r10 + push %r9 + push %r8 + + push %rdi + push %rsi + push %rbp + push %rbx + push %rdx + push %rcx + push %rax + mov %rsp, %rdi + + call route_exception + + pop %rax + pop %rcx + pop %rdx + pop %rbx + pop %rbp + pop %rsi + pop %rdi + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + /* Discard vector and error code. */ + add $16, %rsp + iretq + +/* + * Build the handle_exception wrappers which push the vector/error code on the + * stack and an array of pointers to those wrappers. + */ +.pushsection .rodata +.globl idt_handlers +idt_handlers: +.popsection + +.macro HANDLERS has_error from to + vector = \from + .rept \to - \from + 1 + .align 8 + + /* Fetch current address and append it to idt_handlers. */ + current_handler = . +.pushsection .rodata +.quad current_handler +.popsection + + .if ! \has_error + pushq $0 + .endif + pushq $vector + jmp handle_exception + vector = vector + 1 + .endr +.endm + +.global idt_handler_code +idt_handler_code: + HANDLERS has_error=0 from=0 to=7 + HANDLERS has_error=1 from=8 to=8 + HANDLERS has_error=0 from=9 to=9 + HANDLERS has_error=1 from=10 to=14 + HANDLERS has_error=0 from=15 to=16 + HANDLERS has_error=1 from=17 to=17 + HANDLERS has_error=0 from=18 to=255 + +.section .note.GNU-stack, "", %progbits diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index f6eb34eaa0d2..95e1a757c629 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -5,16 +5,23 @@ * Copyright (C) 2018, Google LLC. */ -#define _GNU_SOURCE /* for program_invocation_name */ - #include "test_util.h" #include "kvm_util.h" #include "../kvm_util_internal.h" #include "processor.h" +#ifndef NUM_INTERRUPTS +#define NUM_INTERRUPTS 256 +#endif + +#define DEFAULT_CODE_SELECTOR 0x8 +#define DEFAULT_DATA_SELECTOR 0x10 + /* Minimum physical address used for virtual translation tables. */ #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 +vm_vaddr_t exception_handlers; + /* Virtual translation table structure declarations */ struct pageMapL4Entry { uint64_t present:1; @@ -392,11 +399,12 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) desc->limit0 = segp->limit & 0xFFFF; desc->base0 = segp->base & 0xFFFF; desc->base1 = segp->base >> 16; - desc->s = segp->s; desc->type = segp->type; + desc->s = segp->s; desc->dpl = segp->dpl; desc->p = segp->present; desc->limit1 = segp->limit >> 16; + desc->avl = segp->avl; desc->l = segp->l; desc->db = segp->db; desc->g = segp->g; @@ -556,9 +564,9 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); kvm_seg_set_unusable(&sregs.ldt); - kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es); + kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es); kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot); break; @@ -721,36 +729,6 @@ void vcpu_set_cpuid(struct kvm_vm *vm, } -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code) -{ - struct kvm_vm *vm; - /* - * For x86 the maximum page table size for a memory region - * will be when only 4K pages are used. In that case the - * total extra size for page tables (for extra N pages) will - * be: N/512+N/512^2+N/512^3+... which is definitely smaller - * than N/512*2. - */ - uint64_t extra_pg_pages = extra_mem_pages / 512 * 2; - - /* Create VM */ - vm = vm_create(VM_MODE_DEFAULT, - DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, - O_RDWR); - - /* Setup guest code */ - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); - - /* Setup IRQ Chip */ - vm_create_irqchip(vm); - - /* Add the first vCPU. */ - vm_vcpu_add_default(vm, vcpuid, guest_code); - - return vm; -} - /* * VCPU Get MSR * @@ -1118,3 +1096,131 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) *va_bits = (entry->eax >> 8) & 0xff; } } + +struct idt_entry { + uint16_t offset0; + uint16_t selector; + uint16_t ist : 3; + uint16_t : 5; + uint16_t type : 4; + uint16_t : 1; + uint16_t dpl : 2; + uint16_t p : 1; + uint16_t offset1; + uint32_t offset2; uint32_t reserved; +}; + +static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, + int dpl, unsigned short selector) +{ + struct idt_entry *base = + (struct idt_entry *)addr_gva2hva(vm, vm->idt); + struct idt_entry *e = &base[vector]; + + memset(e, 0, sizeof(*e)); + e->offset0 = addr; + e->selector = selector; + e->ist = 0; + e->type = 14; + e->dpl = dpl; + e->p = 1; + e->offset1 = addr >> 16; + e->offset2 = addr >> 32; +} + +void kvm_exit_unexpected_vector(uint32_t value) +{ + outl(UNEXPECTED_VECTOR_PORT, value); +} + +void route_exception(struct ex_regs *regs) +{ + typedef void(*handler)(struct ex_regs *); + handler *handlers = (handler *)exception_handlers; + + if (handlers && handlers[regs->vector]) { + handlers[regs->vector](regs); + return; + } + + kvm_exit_unexpected_vector(regs->vector); +} + +void vm_init_descriptor_tables(struct kvm_vm *vm) +{ + extern void *idt_handlers; + int i; + + vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0); + vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0); + /* Handlers have the same address in both address spaces.*/ + for (i = 0; i < NUM_INTERRUPTS; i++) + set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, + DEFAULT_CODE_SELECTOR); +} + +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_sregs sregs; + + vcpu_sregs_get(vm, vcpuid, &sregs); + sregs.idt.base = vm->idt; + sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1; + sregs.gdt.base = vm->gdt; + sregs.gdt.limit = getpagesize() - 1; + kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs); + vcpu_sregs_set(vm, vcpuid, &sregs); + *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; +} + +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)) +{ + vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); + + handlers[vector] = (vm_vaddr_t)handler; +} + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ + if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO + && vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT + && vcpu_state(vm, vcpuid)->io.size == 4) { + /* Grab pointer to io data */ + uint32_t *data = (void *)vcpu_state(vm, vcpuid) + + vcpu_state(vm, vcpuid)->io.data_offset; + + TEST_ASSERT(false, + "Unexpected vectored event in guest (vector:0x%x)", + *data); + } +} + +bool set_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 *ent) +{ + int i; + + for (i = 0; i < cpuid->nent; i++) { + struct kvm_cpuid_entry2 *cur = &cpuid->entries[i]; + + if (cur->function != ent->function || cur->index != ent->index) + continue; + + memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2)); + return true; + } + + return false; +} + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3) +{ + uint64_t r; + + asm volatile("vmcall" + : "=a"(r) + : "b"(a0), "c"(a1), "d"(a2), "S"(a3)); + return r; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c index da4d89ad5419..a3489973e290 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -40,6 +40,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { struct kvm_regs regs; diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index b3ece55a2da6..5fa5823661da 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -121,8 +121,6 @@ static struct kvm_vm *spawn_vm(pthread_t *vcpu_thread, void *guest_code) vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP, MEM_REGION_GPA, MEM_REGION_SLOT, MEM_REGION_SIZE / getpagesize(), 0); diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index 140e91901582..f40fd097cb35 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -81,7 +81,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); run = vcpu_state(vm, VCPU_ID); while (1) { diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index 2fc6b3af81a1..6097a8283377 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -85,7 +85,6 @@ int main(void) } vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); run = vcpu_state(vm, VCPU_ID); /* Test software BPs - int3 */ diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 757928199f19..37b8a78f6b74 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -92,8 +92,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - if (!nested_vmx_supported() || !kvm_check_cap(KVM_CAP_NESTED_STATE) || !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 745b708c2d3b..88a595b7fbdd 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -46,19 +46,19 @@ static bool smt_possible(void) } static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, - bool evmcs_enabled) + bool evmcs_expected) { int i; int nent = 9; u32 test_val; - if (evmcs_enabled) + if (evmcs_expected) nent += 1; /* 0x4000000A */ TEST_ASSERT(hv_cpuid_entries->nent == nent, "KVM_GET_SUPPORTED_HV_CPUID should return %d entries" " with evmcs=%d (returned %d)", - nent, evmcs_enabled, hv_cpuid_entries->nent); + nent, evmcs_expected, hv_cpuid_entries->nent); for (i = 0; i < hv_cpuid_entries->nent; i++) { struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i]; @@ -68,7 +68,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, "function %x is our of supported range", entry->function); - TEST_ASSERT(evmcs_enabled || (entry->function != 0x4000000A), + TEST_ASSERT(evmcs_expected || (entry->function != 0x4000000A), "0x4000000A leaf should not be reported"); TEST_ASSERT(entry->index == 0, @@ -87,7 +87,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, TEST_ASSERT(entry->eax == test_val, "Wrong max leaf report in 0x40000000.EAX: %x" " (evmcs=%d)", - entry->eax, evmcs_enabled + entry->eax, evmcs_expected ); break; case 0x40000004: @@ -110,20 +110,23 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, } -void test_hv_cpuid_e2big(struct kvm_vm *vm) +void test_hv_cpuid_e2big(struct kvm_vm *vm, bool system) { static struct kvm_cpuid2 cpuid = {.nent = 0}; int ret; - ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); + if (!system) + ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); + else + ret = _kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); TEST_ASSERT(ret == -1 && errno == E2BIG, - "KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when" - " it should have: %d %d", ret, errno); + "%s KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when" + " it should have: %d %d", system ? "KVM" : "vCPU", ret, errno); } -struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm) +struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm, bool system) { int nent = 20; /* should be enough */ static struct kvm_cpuid2 *cpuid; @@ -137,7 +140,10 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm) cpuid->nent = nent; - vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + if (!system) + vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + else + kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, cpuid); return cpuid; } @@ -146,45 +152,50 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm) int main(int argc, char *argv[]) { struct kvm_vm *vm; - int rv, stage; struct kvm_cpuid2 *hv_cpuid_entries; - bool evmcs_enabled; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - rv = kvm_check_cap(KVM_CAP_HYPERV_CPUID); - if (!rv) { + if (!kvm_check_cap(KVM_CAP_HYPERV_CPUID)) { print_skip("KVM_CAP_HYPERV_CPUID not supported"); exit(KSFT_SKIP); } - for (stage = 0; stage < 3; stage++) { - evmcs_enabled = false; + vm = vm_create_default(VCPU_ID, 0, guest_code); - vm = vm_create_default(VCPU_ID, 0, guest_code); - switch (stage) { - case 0: - test_hv_cpuid_e2big(vm); - continue; - case 1: - break; - case 2: - if (!nested_vmx_supported() || - !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { - print_skip("Enlightened VMCS is unsupported"); - continue; - } - vcpu_enable_evmcs(vm, VCPU_ID); - evmcs_enabled = true; - break; - } + /* Test vCPU ioctl version */ + test_hv_cpuid_e2big(vm, false); + + hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, false); + test_hv_cpuid(hv_cpuid_entries, false); + free(hv_cpuid_entries); - hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm); - test_hv_cpuid(hv_cpuid_entries, evmcs_enabled); - free(hv_cpuid_entries); - kvm_vm_free(vm); + if (!nested_vmx_supported() || + !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { + print_skip("Enlightened VMCS is unsupported"); + goto do_sys; } + vcpu_enable_evmcs(vm, VCPU_ID); + hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, false); + test_hv_cpuid(hv_cpuid_entries, true); + free(hv_cpuid_entries); + +do_sys: + /* Test system ioctl version */ + if (!kvm_check_cap(KVM_CAP_SYS_HYPERV_CPUID)) { + print_skip("KVM_CAP_SYS_HYPERV_CPUID not supported"); + goto out; + } + + test_hv_cpuid_e2big(vm, true); + + hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, true); + test_hv_cpuid(hv_cpuid_entries, nested_vmx_supported()); + free(hv_cpuid_entries); + +out: + kvm_vm_free(vm); return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c new file mode 100644 index 000000000000..732b244d6956 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020, Google LLC. + * + * Tests for KVM paravirtual feature disablement + */ +#include <asm/kvm_para.h> +#include <linux/kvm_para.h> +#include <stdint.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +extern unsigned char rdmsr_start; +extern unsigned char rdmsr_end; + +static u64 do_rdmsr(u32 idx) +{ + u32 lo, hi; + + asm volatile("rdmsr_start: rdmsr;" + "rdmsr_end:" + : "=a"(lo), "=c"(hi) + : "c"(idx)); + + return (((u64) hi) << 32) | lo; +} + +extern unsigned char wrmsr_start; +extern unsigned char wrmsr_end; + +static void do_wrmsr(u32 idx, u64 val) +{ + u32 lo, hi; + + lo = val; + hi = val >> 32; + + asm volatile("wrmsr_start: wrmsr;" + "wrmsr_end:" + : : "a"(lo), "c"(idx), "d"(hi)); +} + +static int nr_gp; + +static void guest_gp_handler(struct ex_regs *regs) +{ + unsigned char *rip = (unsigned char *)regs->rip; + bool r, w; + + r = rip == &rdmsr_start; + w = rip == &wrmsr_start; + GUEST_ASSERT(r || w); + + nr_gp++; + + if (r) + regs->rip = (uint64_t)&rdmsr_end; + else + regs->rip = (uint64_t)&wrmsr_end; +} + +struct msr_data { + uint32_t idx; + const char *name; +}; + +#define TEST_MSR(msr) { .idx = msr, .name = #msr } +#define UCALL_PR_MSR 0xdeadbeef +#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr) + +/* + * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or + * written, as the KVM_CPUID_FEATURES leaf is cleared. + */ +static struct msr_data msrs_to_test[] = { + TEST_MSR(MSR_KVM_SYSTEM_TIME), + TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW), + TEST_MSR(MSR_KVM_WALL_CLOCK), + TEST_MSR(MSR_KVM_WALL_CLOCK_NEW), + TEST_MSR(MSR_KVM_ASYNC_PF_EN), + TEST_MSR(MSR_KVM_STEAL_TIME), + TEST_MSR(MSR_KVM_PV_EOI_EN), + TEST_MSR(MSR_KVM_POLL_CONTROL), + TEST_MSR(MSR_KVM_ASYNC_PF_INT), + TEST_MSR(MSR_KVM_ASYNC_PF_ACK), +}; + +static void test_msr(struct msr_data *msr) +{ + PR_MSR(msr); + do_rdmsr(msr->idx); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + + nr_gp = 0; + do_wrmsr(msr->idx, 0); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + nr_gp = 0; +} + +struct hcall_data { + uint64_t nr; + const char *name; +}; + +#define TEST_HCALL(hc) { .nr = hc, .name = #hc } +#define UCALL_PR_HCALL 0xdeadc0de +#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc) + +/* + * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding + * features have been cleared in KVM_CPUID_FEATURES. + */ +static struct hcall_data hcalls_to_test[] = { + TEST_HCALL(KVM_HC_KICK_CPU), + TEST_HCALL(KVM_HC_SEND_IPI), + TEST_HCALL(KVM_HC_SCHED_YIELD), +}; + +static void test_hcall(struct hcall_data *hc) +{ + uint64_t r; + + PR_HCALL(hc); + r = kvm_hypercall(hc->nr, 0, 0, 0, 0); + GUEST_ASSERT(r == -KVM_ENOSYS); +} + +static void guest_main(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) { + test_msr(&msrs_to_test[i]); + } + + for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) { + test_hcall(&hcalls_to_test[i]); + } + + GUEST_DONE(); +} + +static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid) +{ + struct kvm_cpuid_entry2 ent = {0}; + + ent.function = KVM_CPUID_FEATURES; + TEST_ASSERT(set_cpuid(cpuid, &ent), + "failed to clear KVM_CPUID_FEATURES leaf"); +} + +static void pr_msr(struct ucall *uc) +{ + struct msr_data *msr = (struct msr_data *)uc->args[0]; + + pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx); +} + +static void pr_hcall(struct ucall *uc) +{ + struct hcall_data *hc = (struct hcall_data *)uc->args[0]; + + pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr); +} + +static void handle_abort(struct ucall *uc) +{ + TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], + __FILE__, uc->args[1]); +} + +#define VCPU_ID 0 + +static void enter_guest(struct kvm_vm *vm) +{ + struct kvm_run *run; + struct ucall uc; + int r; + + run = vcpu_state(vm, VCPU_ID); + + while (true) { + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_PR_MSR: + pr_msr(&uc); + break; + case UCALL_PR_HCALL: + pr_hcall(&uc); + break; + case UCALL_ABORT: + handle_abort(&uc); + return; + case UCALL_DONE: + return; + } + } +} + +int main(void) +{ + struct kvm_enable_cap cap = {0}; + struct kvm_cpuid2 *best; + struct kvm_vm *vm; + + if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) { + print_skip("KVM_CAP_ENFORCE_PV_FEATURE_CPUID not supported"); + exit(KSFT_SKIP); + } + + vm = vm_create_default(VCPU_ID, 0, guest_main); + + cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID; + cap.args[0] = 1; + vcpu_enable_cap(vm, VCPU_ID, &cap); + + best = kvm_get_supported_cpuid(); + clear_kvm_cpuid_features(best); + vcpu_set_cpuid(vm, VCPU_ID, best); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + + enter_guest(vm); + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c index 9f7656184f31..318be0bf77ab 100644 --- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c @@ -24,16 +24,106 @@ #define VCPU_ID 5 +static void test_cr4_feature_bit(struct kvm_vm *vm, struct kvm_sregs *orig, + uint64_t feature_bit) +{ + struct kvm_sregs sregs; + int rc; + + /* Skip the sub-test, the feature is supported. */ + if (orig->cr4 & feature_bit) + return; + + memcpy(&sregs, orig, sizeof(sregs)); + sregs.cr4 |= feature_bit; + + rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + TEST_ASSERT(rc, "KVM allowed unsupported CR4 bit (0x%lx)", feature_bit); + + /* Sanity check that KVM didn't change anything. */ + vcpu_sregs_get(vm, VCPU_ID, &sregs); + TEST_ASSERT(!memcmp(&sregs, orig, sizeof(sregs)), "KVM modified sregs"); +} + +static uint64_t calc_cr4_feature_bits(struct kvm_vm *vm) +{ + struct kvm_cpuid_entry2 *cpuid_1, *cpuid_7; + uint64_t cr4; + + cpuid_1 = kvm_get_supported_cpuid_entry(1); + cpuid_7 = kvm_get_supported_cpuid_entry(7); + + cr4 = X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE | + X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE | X86_CR4_PGE | + X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT; + if (cpuid_7->ecx & CPUID_UMIP) + cr4 |= X86_CR4_UMIP; + if (cpuid_7->ecx & CPUID_LA57) + cr4 |= X86_CR4_LA57; + if (cpuid_1->ecx & CPUID_VMX) + cr4 |= X86_CR4_VMXE; + if (cpuid_1->ecx & CPUID_SMX) + cr4 |= X86_CR4_SMXE; + if (cpuid_7->ebx & CPUID_FSGSBASE) + cr4 |= X86_CR4_FSGSBASE; + if (cpuid_1->ecx & CPUID_PCID) + cr4 |= X86_CR4_PCIDE; + if (cpuid_1->ecx & CPUID_XSAVE) + cr4 |= X86_CR4_OSXSAVE; + if (cpuid_7->ebx & CPUID_SMEP) + cr4 |= X86_CR4_SMEP; + if (cpuid_7->ebx & CPUID_SMAP) + cr4 |= X86_CR4_SMAP; + if (cpuid_7->ecx & CPUID_PKU) + cr4 |= X86_CR4_PKE; + + return cr4; +} + int main(int argc, char *argv[]) { struct kvm_sregs sregs; struct kvm_vm *vm; + uint64_t cr4; int rc; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - /* Create VM */ + /* + * Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and + * use it to verify all supported CR4 bits can be set prior to defining + * the vCPU model, i.e. without doing KVM_SET_CPUID2. + */ + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm_vcpu_add(vm, VCPU_ID); + + vcpu_sregs_get(vm, VCPU_ID, &sregs); + + sregs.cr4 |= calc_cr4_feature_bits(vm); + cr4 = sregs.cr4; + + rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + TEST_ASSERT(!rc, "Failed to set supported CR4 bits (0x%lx)", cr4); + + vcpu_sregs_get(vm, VCPU_ID, &sregs); + TEST_ASSERT(sregs.cr4 == cr4, "sregs.CR4 (0x%llx) != CR4 (0x%lx)", + sregs.cr4, cr4); + + /* Verify all unsupported features are rejected by KVM. */ + test_cr4_feature_bit(vm, &sregs, X86_CR4_UMIP); + test_cr4_feature_bit(vm, &sregs, X86_CR4_LA57); + test_cr4_feature_bit(vm, &sregs, X86_CR4_VMXE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_SMXE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_FSGSBASE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_PCIDE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_OSXSAVE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_SMEP); + test_cr4_feature_bit(vm, &sregs, X86_CR4_SMAP); + test_cr4_feature_bit(vm, &sregs, X86_CR4_PKE); + kvm_vm_free(vm); + + /* Create a "real" VM and verify APIC_BASE can be set. */ vm = vm_create_default(VCPU_ID, 0, NULL); vcpu_sregs_get(vm, VCPU_ID, &sregs); diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index ae39a220609f..613c42c5a9b8 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -102,8 +102,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - run = vcpu_state(vm, VCPU_ID); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index f6c8b9042f8a..32854c1462ad 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -165,7 +165,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); run = vcpu_state(vm, VCPU_ID); vcpu_regs_get(vm, VCPU_ID, ®s1); diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c index 0e1adb4e3199..be2ca157485b 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c @@ -44,7 +44,6 @@ int main(int argc, char *argv[]) nested_svm_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_alloc_svm(vm, &svm_gva); vcpu_args_set(vm, VCPU_ID, 1, svm_gva); diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c index f8e761149daa..e357d8e222d4 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c @@ -107,7 +107,6 @@ int main(void) uint64_t val; vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); val = 0; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); diff --git a/tools/testing/selftests/kvm/x86_64/user_msr_test.c b/tools/testing/selftests/kvm/x86_64/user_msr_test.c deleted file mode 100644 index cbe1b08890ff..000000000000 --- a/tools/testing/selftests/kvm/x86_64/user_msr_test.c +++ /dev/null @@ -1,248 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * tests for KVM_CAP_X86_USER_SPACE_MSR and KVM_X86_SET_MSR_FILTER - * - * Copyright (C) 2020, Amazon Inc. - * - * This is a functional test to verify that we can deflect MSR events - * into user space. - */ -#define _GNU_SOURCE /* for program_invocation_short_name */ -#include <fcntl.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <sys/ioctl.h> - -#include "test_util.h" - -#include "kvm_util.h" -#include "processor.h" - -#define VCPU_ID 5 - -static u32 msr_reads, msr_writes; - -static u8 bitmap_00000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_00000000_write[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_40000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_c0000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_c0000000_read[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_deadbeef[1] = { 0x1 }; - -static void deny_msr(uint8_t *bitmap, u32 msr) -{ - u32 idx = msr & (KVM_MSR_FILTER_MAX_BITMAP_SIZE - 1); - - bitmap[idx / 8] &= ~(1 << (idx % 8)); -} - -static void prepare_bitmaps(void) -{ - memset(bitmap_00000000, 0xff, sizeof(bitmap_00000000)); - memset(bitmap_00000000_write, 0xff, sizeof(bitmap_00000000_write)); - memset(bitmap_40000000, 0xff, sizeof(bitmap_40000000)); - memset(bitmap_c0000000, 0xff, sizeof(bitmap_c0000000)); - memset(bitmap_c0000000_read, 0xff, sizeof(bitmap_c0000000_read)); - - deny_msr(bitmap_00000000_write, MSR_IA32_POWER_CTL); - deny_msr(bitmap_c0000000_read, MSR_SYSCALL_MASK); - deny_msr(bitmap_c0000000_read, MSR_GS_BASE); -} - -struct kvm_msr_filter filter = { - .flags = KVM_MSR_FILTER_DEFAULT_DENY, - .ranges = { - { - .flags = KVM_MSR_FILTER_READ, - .base = 0x00000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_00000000, - }, { - .flags = KVM_MSR_FILTER_WRITE, - .base = 0x00000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_00000000_write, - }, { - .flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE, - .base = 0x40000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_40000000, - }, { - .flags = KVM_MSR_FILTER_READ, - .base = 0xc0000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_c0000000_read, - }, { - .flags = KVM_MSR_FILTER_WRITE, - .base = 0xc0000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_c0000000, - }, { - .flags = KVM_MSR_FILTER_WRITE | KVM_MSR_FILTER_READ, - .base = 0xdeadbeef, - .nmsrs = 1, - .bitmap = bitmap_deadbeef, - }, - }, -}; - -struct kvm_msr_filter no_filter = { - .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, -}; - -static void guest_msr_calls(bool trapped) -{ - /* This goes into the in-kernel emulation */ - wrmsr(MSR_SYSCALL_MASK, 0); - - if (trapped) { - /* This goes into user space emulation */ - GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) == MSR_SYSCALL_MASK); - GUEST_ASSERT(rdmsr(MSR_GS_BASE) == MSR_GS_BASE); - } else { - GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) != MSR_SYSCALL_MASK); - GUEST_ASSERT(rdmsr(MSR_GS_BASE) != MSR_GS_BASE); - } - - /* If trapped == true, this goes into user space emulation */ - wrmsr(MSR_IA32_POWER_CTL, 0x1234); - - /* This goes into the in-kernel emulation */ - rdmsr(MSR_IA32_POWER_CTL); - - /* Invalid MSR, should always be handled by user space exit */ - GUEST_ASSERT(rdmsr(0xdeadbeef) == 0xdeadbeef); - wrmsr(0xdeadbeef, 0x1234); -} - -static void guest_code(void) -{ - guest_msr_calls(true); - - /* - * Disable msr filtering, so that the kernel - * handles everything in the next round - */ - GUEST_SYNC(0); - - guest_msr_calls(false); - - GUEST_DONE(); -} - -static int handle_ucall(struct kvm_vm *vm) -{ - struct ucall uc; - - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_ABORT: - TEST_FAIL("Guest assertion not met"); - break; - case UCALL_SYNC: - vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &no_filter); - break; - case UCALL_DONE: - return 1; - default: - TEST_FAIL("Unknown ucall %lu", uc.cmd); - } - - return 0; -} - -static void handle_rdmsr(struct kvm_run *run) -{ - run->msr.data = run->msr.index; - msr_reads++; - - if (run->msr.index == MSR_SYSCALL_MASK || - run->msr.index == MSR_GS_BASE) { - TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER, - "MSR read trap w/o access fault"); - } - - if (run->msr.index == 0xdeadbeef) { - TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN, - "MSR deadbeef read trap w/o inval fault"); - } -} - -static void handle_wrmsr(struct kvm_run *run) -{ - /* ignore */ - msr_writes++; - - if (run->msr.index == MSR_IA32_POWER_CTL) { - TEST_ASSERT(run->msr.data == 0x1234, - "MSR data for MSR_IA32_POWER_CTL incorrect"); - TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER, - "MSR_IA32_POWER_CTL trap w/o access fault"); - } - - if (run->msr.index == 0xdeadbeef) { - TEST_ASSERT(run->msr.data == 0x1234, - "MSR data for deadbeef incorrect"); - TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN, - "deadbeef trap w/o inval fault"); - } -} - -int main(int argc, char *argv[]) -{ - struct kvm_enable_cap cap = { - .cap = KVM_CAP_X86_USER_SPACE_MSR, - .args[0] = KVM_MSR_EXIT_REASON_INVAL | - KVM_MSR_EXIT_REASON_UNKNOWN | - KVM_MSR_EXIT_REASON_FILTER, - }; - struct kvm_vm *vm; - struct kvm_run *run; - int rc; - - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - run = vcpu_state(vm, VCPU_ID); - - rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); - TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); - vm_enable_cap(vm, &cap); - - rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); - TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); - - prepare_bitmaps(); - vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter); - - while (1) { - rc = _vcpu_run(vm, VCPU_ID); - - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); - - switch (run->exit_reason) { - case KVM_EXIT_X86_RDMSR: - handle_rdmsr(run); - break; - case KVM_EXIT_X86_WRMSR: - handle_wrmsr(run); - break; - case KVM_EXIT_IO: - if (handle_ucall(vm)) - goto done; - break; - } - - } - -done: - TEST_ASSERT(msr_reads == 4, "Handled 4 rdmsr in user space"); - TEST_ASSERT(msr_writes == 3, "Handled 3 wrmsr in user space"); - - kvm_vm_free(vm); - - return 0; -} diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c new file mode 100644 index 000000000000..72c0d0797522 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -0,0 +1,770 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020, Google LLC. + * + * Tests for exiting into userspace on registered MSRs + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "vmx.h" + +/* Forced emulation prefix, used to invoke the emulator unconditionally. */ +#define KVM_FEP "ud2; .byte 'k', 'v', 'm';" +#define KVM_FEP_LENGTH 5 +static int fep_available = 1; + +#define VCPU_ID 1 +#define MSR_NON_EXISTENT 0x474f4f00 + +static u64 deny_bits = 0; +struct kvm_msr_filter filter_allow = { + .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, + .ranges = { + { + .flags = KVM_MSR_FILTER_READ | + KVM_MSR_FILTER_WRITE, + .nmsrs = 1, + /* Test an MSR the kernel knows about. */ + .base = MSR_IA32_XSS, + .bitmap = (uint8_t*)&deny_bits, + }, { + .flags = KVM_MSR_FILTER_READ | + KVM_MSR_FILTER_WRITE, + .nmsrs = 1, + /* Test an MSR the kernel doesn't know about. */ + .base = MSR_IA32_FLUSH_CMD, + .bitmap = (uint8_t*)&deny_bits, + }, { + .flags = KVM_MSR_FILTER_READ | + KVM_MSR_FILTER_WRITE, + .nmsrs = 1, + /* Test a fabricated MSR that no one knows about. */ + .base = MSR_NON_EXISTENT, + .bitmap = (uint8_t*)&deny_bits, + }, + }, +}; + +struct kvm_msr_filter filter_fs = { + .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, + .ranges = { + { + .flags = KVM_MSR_FILTER_READ, + .nmsrs = 1, + .base = MSR_FS_BASE, + .bitmap = (uint8_t*)&deny_bits, + }, + }, +}; + +struct kvm_msr_filter filter_gs = { + .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, + .ranges = { + { + .flags = KVM_MSR_FILTER_READ, + .nmsrs = 1, + .base = MSR_GS_BASE, + .bitmap = (uint8_t*)&deny_bits, + }, + }, +}; + +static uint64_t msr_non_existent_data; +static int guest_exception_count; +static u32 msr_reads, msr_writes; + +static u8 bitmap_00000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_00000000_write[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_40000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_c0000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_c0000000_read[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_deadbeef[1] = { 0x1 }; + +static void deny_msr(uint8_t *bitmap, u32 msr) +{ + u32 idx = msr & (KVM_MSR_FILTER_MAX_BITMAP_SIZE - 1); + + bitmap[idx / 8] &= ~(1 << (idx % 8)); +} + +static void prepare_bitmaps(void) +{ + memset(bitmap_00000000, 0xff, sizeof(bitmap_00000000)); + memset(bitmap_00000000_write, 0xff, sizeof(bitmap_00000000_write)); + memset(bitmap_40000000, 0xff, sizeof(bitmap_40000000)); + memset(bitmap_c0000000, 0xff, sizeof(bitmap_c0000000)); + memset(bitmap_c0000000_read, 0xff, sizeof(bitmap_c0000000_read)); + + deny_msr(bitmap_00000000_write, MSR_IA32_POWER_CTL); + deny_msr(bitmap_c0000000_read, MSR_SYSCALL_MASK); + deny_msr(bitmap_c0000000_read, MSR_GS_BASE); +} + +struct kvm_msr_filter filter_deny = { + .flags = KVM_MSR_FILTER_DEFAULT_DENY, + .ranges = { + { + .flags = KVM_MSR_FILTER_READ, + .base = 0x00000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_00000000, + }, { + .flags = KVM_MSR_FILTER_WRITE, + .base = 0x00000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_00000000_write, + }, { + .flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE, + .base = 0x40000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_40000000, + }, { + .flags = KVM_MSR_FILTER_READ, + .base = 0xc0000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_c0000000_read, + }, { + .flags = KVM_MSR_FILTER_WRITE, + .base = 0xc0000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_c0000000, + }, { + .flags = KVM_MSR_FILTER_WRITE | KVM_MSR_FILTER_READ, + .base = 0xdeadbeef, + .nmsrs = 1, + .bitmap = bitmap_deadbeef, + }, + }, +}; + +struct kvm_msr_filter no_filter_deny = { + .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, +}; + +/* + * Note: Force test_rdmsr() to not be inlined to prevent the labels, + * rdmsr_start and rdmsr_end, from being defined multiple times. + */ +static noinline uint64_t test_rdmsr(uint32_t msr) +{ + uint32_t a, d; + + guest_exception_count = 0; + + __asm__ __volatile__("rdmsr_start: rdmsr; rdmsr_end:" : + "=a"(a), "=d"(d) : "c"(msr) : "memory"); + + return a | ((uint64_t) d << 32); +} + +/* + * Note: Force test_wrmsr() to not be inlined to prevent the labels, + * wrmsr_start and wrmsr_end, from being defined multiple times. + */ +static noinline void test_wrmsr(uint32_t msr, uint64_t value) +{ + uint32_t a = value; + uint32_t d = value >> 32; + + guest_exception_count = 0; + + __asm__ __volatile__("wrmsr_start: wrmsr; wrmsr_end:" :: + "a"(a), "d"(d), "c"(msr) : "memory"); +} + +extern char rdmsr_start, rdmsr_end; +extern char wrmsr_start, wrmsr_end; + +/* + * Note: Force test_em_rdmsr() to not be inlined to prevent the labels, + * rdmsr_start and rdmsr_end, from being defined multiple times. + */ +static noinline uint64_t test_em_rdmsr(uint32_t msr) +{ + uint32_t a, d; + + guest_exception_count = 0; + + __asm__ __volatile__(KVM_FEP "em_rdmsr_start: rdmsr; em_rdmsr_end:" : + "=a"(a), "=d"(d) : "c"(msr) : "memory"); + + return a | ((uint64_t) d << 32); +} + +/* + * Note: Force test_em_wrmsr() to not be inlined to prevent the labels, + * wrmsr_start and wrmsr_end, from being defined multiple times. + */ +static noinline void test_em_wrmsr(uint32_t msr, uint64_t value) +{ + uint32_t a = value; + uint32_t d = value >> 32; + + guest_exception_count = 0; + + __asm__ __volatile__(KVM_FEP "em_wrmsr_start: wrmsr; em_wrmsr_end:" :: + "a"(a), "d"(d), "c"(msr) : "memory"); +} + +extern char em_rdmsr_start, em_rdmsr_end; +extern char em_wrmsr_start, em_wrmsr_end; + +static void guest_code_filter_allow(void) +{ + uint64_t data; + + /* + * Test userspace intercepting rdmsr / wrmsr for MSR_IA32_XSS. + * + * A GP is thrown if anything other than 0 is written to + * MSR_IA32_XSS. + */ + data = test_rdmsr(MSR_IA32_XSS); + GUEST_ASSERT(data == 0); + GUEST_ASSERT(guest_exception_count == 0); + + test_wrmsr(MSR_IA32_XSS, 0); + GUEST_ASSERT(guest_exception_count == 0); + + test_wrmsr(MSR_IA32_XSS, 1); + GUEST_ASSERT(guest_exception_count == 1); + + /* + * Test userspace intercepting rdmsr / wrmsr for MSR_IA32_FLUSH_CMD. + * + * A GP is thrown if MSR_IA32_FLUSH_CMD is read + * from or if a value other than 1 is written to it. + */ + test_rdmsr(MSR_IA32_FLUSH_CMD); + GUEST_ASSERT(guest_exception_count == 1); + + test_wrmsr(MSR_IA32_FLUSH_CMD, 0); + GUEST_ASSERT(guest_exception_count == 1); + + test_wrmsr(MSR_IA32_FLUSH_CMD, 1); + GUEST_ASSERT(guest_exception_count == 0); + + /* + * Test userspace intercepting rdmsr / wrmsr for MSR_NON_EXISTENT. + * + * Test that a fabricated MSR can pass through the kernel + * and be handled in userspace. + */ + test_wrmsr(MSR_NON_EXISTENT, 2); + GUEST_ASSERT(guest_exception_count == 0); + + data = test_rdmsr(MSR_NON_EXISTENT); + GUEST_ASSERT(data == 2); + GUEST_ASSERT(guest_exception_count == 0); + + /* + * Test to see if the instruction emulator is available (ie: the module + * parameter 'kvm.force_emulation_prefix=1' is set). This instruction + * will #UD if it isn't available. + */ + __asm__ __volatile__(KVM_FEP "nop"); + + if (fep_available) { + /* Let userspace know we aren't done. */ + GUEST_SYNC(0); + + /* + * Now run the same tests with the instruction emulator. + */ + data = test_em_rdmsr(MSR_IA32_XSS); + GUEST_ASSERT(data == 0); + GUEST_ASSERT(guest_exception_count == 0); + test_em_wrmsr(MSR_IA32_XSS, 0); + GUEST_ASSERT(guest_exception_count == 0); + test_em_wrmsr(MSR_IA32_XSS, 1); + GUEST_ASSERT(guest_exception_count == 1); + + test_em_rdmsr(MSR_IA32_FLUSH_CMD); + GUEST_ASSERT(guest_exception_count == 1); + test_em_wrmsr(MSR_IA32_FLUSH_CMD, 0); + GUEST_ASSERT(guest_exception_count == 1); + test_em_wrmsr(MSR_IA32_FLUSH_CMD, 1); + GUEST_ASSERT(guest_exception_count == 0); + + test_em_wrmsr(MSR_NON_EXISTENT, 2); + GUEST_ASSERT(guest_exception_count == 0); + data = test_em_rdmsr(MSR_NON_EXISTENT); + GUEST_ASSERT(data == 2); + GUEST_ASSERT(guest_exception_count == 0); + } + + GUEST_DONE(); +} + +static void guest_msr_calls(bool trapped) +{ + /* This goes into the in-kernel emulation */ + wrmsr(MSR_SYSCALL_MASK, 0); + + if (trapped) { + /* This goes into user space emulation */ + GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) == MSR_SYSCALL_MASK); + GUEST_ASSERT(rdmsr(MSR_GS_BASE) == MSR_GS_BASE); + } else { + GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) != MSR_SYSCALL_MASK); + GUEST_ASSERT(rdmsr(MSR_GS_BASE) != MSR_GS_BASE); + } + + /* If trapped == true, this goes into user space emulation */ + wrmsr(MSR_IA32_POWER_CTL, 0x1234); + + /* This goes into the in-kernel emulation */ + rdmsr(MSR_IA32_POWER_CTL); + + /* Invalid MSR, should always be handled by user space exit */ + GUEST_ASSERT(rdmsr(0xdeadbeef) == 0xdeadbeef); + wrmsr(0xdeadbeef, 0x1234); +} + +static void guest_code_filter_deny(void) +{ + guest_msr_calls(true); + + /* + * Disable msr filtering, so that the kernel + * handles everything in the next round + */ + GUEST_SYNC(0); + + guest_msr_calls(false); + + GUEST_DONE(); +} + +static void guest_code_permission_bitmap(void) +{ + uint64_t data; + + data = test_rdmsr(MSR_FS_BASE); + GUEST_ASSERT(data == MSR_FS_BASE); + data = test_rdmsr(MSR_GS_BASE); + GUEST_ASSERT(data != MSR_GS_BASE); + + /* Let userspace know to switch the filter */ + GUEST_SYNC(0); + + data = test_rdmsr(MSR_FS_BASE); + GUEST_ASSERT(data != MSR_FS_BASE); + data = test_rdmsr(MSR_GS_BASE); + GUEST_ASSERT(data == MSR_GS_BASE); + + GUEST_DONE(); +} + +static void __guest_gp_handler(struct ex_regs *regs, + char *r_start, char *r_end, + char *w_start, char *w_end) +{ + if (regs->rip == (uintptr_t)r_start) { + regs->rip = (uintptr_t)r_end; + regs->rax = 0; + regs->rdx = 0; + } else if (regs->rip == (uintptr_t)w_start) { + regs->rip = (uintptr_t)w_end; + } else { + GUEST_ASSERT(!"RIP is at an unknown location!"); + } + + ++guest_exception_count; +} + +static void guest_gp_handler(struct ex_regs *regs) +{ + __guest_gp_handler(regs, &rdmsr_start, &rdmsr_end, + &wrmsr_start, &wrmsr_end); +} + +static void guest_fep_gp_handler(struct ex_regs *regs) +{ + __guest_gp_handler(regs, &em_rdmsr_start, &em_rdmsr_end, + &em_wrmsr_start, &em_wrmsr_end); +} + +static void guest_ud_handler(struct ex_regs *regs) +{ + fep_available = 0; + regs->rip += KVM_FEP_LENGTH; +} + +static void run_guest(struct kvm_vm *vm) +{ + int rc; + + rc = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); +} + +static void check_for_guest_assert(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + if (run->exit_reason == KVM_EXIT_IO && + get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) { + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + } +} + +static void process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + check_for_guest_assert(vm); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_RDMSR, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->msr.index == msr_index, + "Unexpected msr (0x%04x), expected 0x%04x", + run->msr.index, msr_index); + + switch (run->msr.index) { + case MSR_IA32_XSS: + run->msr.data = 0; + break; + case MSR_IA32_FLUSH_CMD: + run->msr.error = 1; + break; + case MSR_NON_EXISTENT: + run->msr.data = msr_non_existent_data; + break; + case MSR_FS_BASE: + run->msr.data = MSR_FS_BASE; + break; + case MSR_GS_BASE: + run->msr.data = MSR_GS_BASE; + break; + default: + TEST_ASSERT(false, "Unexpected MSR: 0x%04x", run->msr.index); + } +} + +static void process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + check_for_guest_assert(vm); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_WRMSR, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->msr.index == msr_index, + "Unexpected msr (0x%04x), expected 0x%04x", + run->msr.index, msr_index); + + switch (run->msr.index) { + case MSR_IA32_XSS: + if (run->msr.data != 0) + run->msr.error = 1; + break; + case MSR_IA32_FLUSH_CMD: + if (run->msr.data != 1) + run->msr.error = 1; + break; + case MSR_NON_EXISTENT: + msr_non_existent_data = run->msr.data; + break; + default: + TEST_ASSERT(false, "Unexpected MSR: 0x%04x", run->msr.index); + } +} + +static void process_ucall_done(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + check_for_guest_assert(vm); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s)", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE, + "Unexpected ucall command: %lu, expected UCALL_DONE (%d)", + uc.cmd, UCALL_DONE); +} + +static uint64_t process_ucall(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc = {}; + + check_for_guest_assert(vm); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s)", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + break; + case UCALL_ABORT: + check_for_guest_assert(vm); + break; + case UCALL_DONE: + process_ucall_done(vm); + break; + default: + TEST_ASSERT(false, "Unexpected ucall"); + } + + return uc.cmd; +} + +static void run_guest_then_process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) +{ + run_guest(vm); + process_rdmsr(vm, msr_index); +} + +static void run_guest_then_process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) +{ + run_guest(vm); + process_wrmsr(vm, msr_index); +} + +static uint64_t run_guest_then_process_ucall(struct kvm_vm *vm) +{ + run_guest(vm); + return process_ucall(vm); +} + +static void run_guest_then_process_ucall_done(struct kvm_vm *vm) +{ + run_guest(vm); + process_ucall_done(vm); +} + +static void test_msr_filter_allow(void) { + struct kvm_enable_cap cap = { + .cap = KVM_CAP_X86_USER_SPACE_MSR, + .args[0] = KVM_MSR_EXIT_REASON_FILTER, + }; + struct kvm_vm *vm; + int rc; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code_filter_allow); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); + TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); + vm_enable_cap(vm, &cap); + + rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); + TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); + + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + + /* Process guest code userspace exits. */ + run_guest_then_process_rdmsr(vm, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + + run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + + run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT); + run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT); + + vm_handle_exception(vm, UD_VECTOR, guest_ud_handler); + run_guest(vm); + vm_handle_exception(vm, UD_VECTOR, NULL); + + if (process_ucall(vm) != UCALL_DONE) { + vm_handle_exception(vm, GP_VECTOR, guest_fep_gp_handler); + + /* Process emulated rdmsr and wrmsr instructions. */ + run_guest_then_process_rdmsr(vm, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + + run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + + run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT); + run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT); + + /* Confirm the guest completed without issues. */ + run_guest_then_process_ucall_done(vm); + } else { + printf("To run the instruction emulated tests set the module parameter 'kvm.force_emulation_prefix=1'\n"); + } + + kvm_vm_free(vm); +} + +static int handle_ucall(struct kvm_vm *vm) +{ + struct ucall uc; + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("Guest assertion not met"); + break; + case UCALL_SYNC: + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &no_filter_deny); + break; + case UCALL_DONE: + return 1; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + return 0; +} + +static void handle_rdmsr(struct kvm_run *run) +{ + run->msr.data = run->msr.index; + msr_reads++; + + if (run->msr.index == MSR_SYSCALL_MASK || + run->msr.index == MSR_GS_BASE) { + TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER, + "MSR read trap w/o access fault"); + } + + if (run->msr.index == 0xdeadbeef) { + TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN, + "MSR deadbeef read trap w/o inval fault"); + } +} + +static void handle_wrmsr(struct kvm_run *run) +{ + /* ignore */ + msr_writes++; + + if (run->msr.index == MSR_IA32_POWER_CTL) { + TEST_ASSERT(run->msr.data == 0x1234, + "MSR data for MSR_IA32_POWER_CTL incorrect"); + TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER, + "MSR_IA32_POWER_CTL trap w/o access fault"); + } + + if (run->msr.index == 0xdeadbeef) { + TEST_ASSERT(run->msr.data == 0x1234, + "MSR data for deadbeef incorrect"); + TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN, + "deadbeef trap w/o inval fault"); + } +} + +static void test_msr_filter_deny(void) { + struct kvm_enable_cap cap = { + .cap = KVM_CAP_X86_USER_SPACE_MSR, + .args[0] = KVM_MSR_EXIT_REASON_INVAL | + KVM_MSR_EXIT_REASON_UNKNOWN | + KVM_MSR_EXIT_REASON_FILTER, + }; + struct kvm_vm *vm; + struct kvm_run *run; + int rc; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code_filter_deny); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + run = vcpu_state(vm, VCPU_ID); + + rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); + TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); + vm_enable_cap(vm, &cap); + + rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); + TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); + + prepare_bitmaps(); + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_deny); + + while (1) { + rc = _vcpu_run(vm, VCPU_ID); + + TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); + + switch (run->exit_reason) { + case KVM_EXIT_X86_RDMSR: + handle_rdmsr(run); + break; + case KVM_EXIT_X86_WRMSR: + handle_wrmsr(run); + break; + case KVM_EXIT_IO: + if (handle_ucall(vm)) + goto done; + break; + } + + } + +done: + TEST_ASSERT(msr_reads == 4, "Handled 4 rdmsr in user space"); + TEST_ASSERT(msr_writes == 3, "Handled 3 wrmsr in user space"); + + kvm_vm_free(vm); +} + +static void test_msr_permission_bitmap(void) { + struct kvm_enable_cap cap = { + .cap = KVM_CAP_X86_USER_SPACE_MSR, + .args[0] = KVM_MSR_EXIT_REASON_FILTER, + }; + struct kvm_vm *vm; + int rc; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code_permission_bitmap); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); + TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); + vm_enable_cap(vm, &cap); + + rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); + TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); + + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_fs); + run_guest_then_process_rdmsr(vm, MSR_FS_BASE); + TEST_ASSERT(run_guest_then_process_ucall(vm) == UCALL_SYNC, "Expected ucall state to be UCALL_SYNC."); + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs); + run_guest_then_process_rdmsr(vm, MSR_GS_BASE); + run_guest_then_process_ucall_done(vm); + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + test_msr_filter_allow(); + + test_msr_filter_deny(); + + test_msr_permission_bitmap(); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c index 1f65342d6cb7..d14888b34adb 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c @@ -87,7 +87,6 @@ int main(int argc, char *argv[]) nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); kvm_get_cpu_address_width(&paddr_width, &vaddr_width); high_gpa = (1ul << paddr_width) - getpagesize(); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index fe40ade06a49..2835a17f1b7a 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -57,7 +57,6 @@ int main(int argc, char *argv[]) nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); /* Allocate VMX pages and shared descriptors (vmx_pages). */ vcpu_alloc_vmx(vm, &vmx_pages_gva); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index e894a638a155..537de1068554 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -82,7 +82,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); run = vcpu_state(vm, VCPU_ID); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c index a7737af1224f..a07480aed397 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c @@ -169,20 +169,19 @@ int main(int argc, char *argv[]) */ nested_vmx_check_supported(); + if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) { + print_skip("KVM_CAP_NESTED_STATE not supported"); + exit(KSFT_SKIP); + } + /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); run = vcpu_state(vm, VCPU_ID); vcpu_regs_get(vm, VCPU_ID, ®s1); - if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { - vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); - } else { - pr_info("will skip vmx preemption timer checks\n"); - goto done; - } + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); for (stage = 1;; stage++) { _vcpu_run(vm, VCPU_ID); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index d59f3eb67c8f..5827b9bae468 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -244,6 +244,22 @@ void test_vmx_nested_state(struct kvm_vm *vm) free(state); } +void disable_vmx(struct kvm_vm *vm) +{ + struct kvm_cpuid2 *cpuid = kvm_get_supported_cpuid(); + int i; + + for (i = 0; i < cpuid->nent; ++i) + if (cpuid->entries[i].function == 1 && + cpuid->entries[i].index == 0) + break; + TEST_ASSERT(i != cpuid->nent, "CPUID function 1 not found"); + + cpuid->entries[i].ecx &= ~CPUID_VMX; + vcpu_set_cpuid(vm, VCPU_ID, cpuid); + cpuid->entries[i].ecx |= CPUID_VMX; +} + int main(int argc, char *argv[]) { struct kvm_vm *vm; @@ -264,6 +280,11 @@ int main(int argc, char *argv[]) vm = vm_create_default(VCPU_ID, 0, 0); + /* + * First run tests with VMX disabled to check error handling. + */ + disable_vmx(vm); + /* Passing a NULL kvm_nested_state causes a EFAULT. */ test_nested_state_expect_efault(vm, NULL); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index fbe8417cbc2c..7e33a350b053 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -132,7 +132,6 @@ int main(int argc, char *argv[]) nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); /* Allocate VMX pages and shared descriptors (vmx_pages). */ vcpu_alloc_vmx(vm, &vmx_pages_gva); diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index bb543bf69d69..361235ad574b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -100,7 +100,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower.*handle", "matchCount": "1", "teardown": [ @@ -119,7 +119,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": " dst_mac e4:11:22:11:4a:51", "matchCount": "0", "teardown": [ |