diff options
Diffstat (limited to 'tools/testing')
93 files changed, 4337 insertions, 1446 deletions
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index 47fdaa146443..f0e488ed90d8 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -52,7 +52,7 @@ static int get_zswap_stored_pages(size_t *value) static int get_cg_wb_count(const char *cg) { - return cg_read_key_long(cg, "memory.stat", "zswp_wb"); + return cg_read_key_long(cg, "memory.stat", "zswpwb"); } static long get_zswpout(const char *cgroup) @@ -60,6 +60,27 @@ static long get_zswpout(const char *cgroup) return cg_read_key_long(cgroup, "memory.stat", "zswpout "); } +static int allocate_and_read_bytes(const char *cgroup, void *arg) +{ + size_t size = (size_t)arg; + char *mem = (char *)malloc(size); + int ret = 0; + + if (!mem) + return -1; + for (int i = 0; i < size; i += 4095) + mem[i] = 'a'; + + /* Go through the allocated memory to (z)swap in and out pages */ + for (int i = 0; i < size; i += 4095) { + if (mem[i] != 'a') + ret = -1; + } + + free(mem); + return ret; +} + static int allocate_bytes(const char *cgroup, void *arg) { size_t size = (size_t)arg; @@ -100,7 +121,6 @@ static int test_zswap_usage(const char *root) int ret = KSFT_FAIL; char *test_group; - /* Set up */ test_group = cg_name(root, "no_shrink_test"); if (!test_group) goto out; @@ -134,6 +154,101 @@ out: } /* + * Check that when memory.zswap.max = 0, no pages can go to the zswap pool for + * the cgroup. + */ +static int test_swapin_nozswap(const char *root) +{ + int ret = KSFT_FAIL; + char *test_group; + long swap_peak, zswpout; + + test_group = cg_name(root, "no_zswap_test"); + if (!test_group) + goto out; + if (cg_create(test_group)) + goto out; + if (cg_write(test_group, "memory.max", "8M")) + goto out; + if (cg_write(test_group, "memory.zswap.max", "0")) + goto out; + + /* Allocate and read more than memory.max to trigger swapin */ + if (cg_run(test_group, allocate_and_read_bytes, (void *)MB(32))) + goto out; + + /* Verify that pages are swapped out, but no zswap happened */ + swap_peak = cg_read_long(test_group, "memory.swap.peak"); + if (swap_peak < 0) { + ksft_print_msg("failed to get cgroup's swap_peak\n"); + goto out; + } + + if (swap_peak < MB(24)) { + ksft_print_msg("at least 24MB of memory should be swapped out\n"); + goto out; + } + + zswpout = get_zswpout(test_group); + if (zswpout < 0) { + ksft_print_msg("failed to get zswpout\n"); + goto out; + } + + if (zswpout > 0) { + ksft_print_msg("zswapout > 0 when memory.zswap.max = 0\n"); + goto out; + } + + ret = KSFT_PASS; + +out: + cg_destroy(test_group); + free(test_group); + return ret; +} + +/* Simple test to verify the (z)swapin code paths */ +static int test_zswapin(const char *root) +{ + int ret = KSFT_FAIL; + char *test_group; + long zswpin; + + test_group = cg_name(root, "zswapin_test"); + if (!test_group) + goto out; + if (cg_create(test_group)) + goto out; + if (cg_write(test_group, "memory.max", "8M")) + goto out; + if (cg_write(test_group, "memory.zswap.max", "max")) + goto out; + + /* Allocate and read more than memory.max to trigger (z)swap in */ + if (cg_run(test_group, allocate_and_read_bytes, (void *)MB(32))) + goto out; + + zswpin = cg_read_key_long(test_group, "memory.stat", "zswpin "); + if (zswpin < 0) { + ksft_print_msg("failed to get zswpin\n"); + goto out; + } + + if (zswpin < MB(24) / PAGE_SIZE) { + ksft_print_msg("at least 24MB should be brought back from zswap\n"); + goto out; + } + + ret = KSFT_PASS; + +out: + cg_destroy(test_group); + free(test_group); + return ret; +} + +/* * When trying to store a memcg page in zswap, if the memcg hits its memory * limit in zswap, writeback should affect only the zswapped pages of that * memcg. @@ -144,7 +259,6 @@ static int test_no_invasive_cgroup_shrink(const char *root) size_t control_allocation_size = MB(10); char *control_allocation, *wb_group = NULL, *control_group = NULL; - /* Set up */ wb_group = setup_test_group_1M(root, "per_memcg_wb_test1"); if (!wb_group) return KSFT_FAIL; @@ -309,6 +423,8 @@ struct zswap_test { const char *name; } tests[] = { T(test_zswap_usage), + T(test_swapin_nozswap), + T(test_zswapin), T(test_no_kmem_bypass), T(test_no_invasive_cgroup_shrink), }; diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore index c6c2965a6607..e65ef9d9cedc 100644 --- a/tools/testing/selftests/damon/.gitignore +++ b/tools/testing/selftests/damon/.gitignore @@ -1,2 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only huge_count_read_write +debugfs_target_ids_read_before_terminate_race +debugfs_target_ids_pid_leak +access_memory diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 8a1cc2bf1864..789d6949c247 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -2,6 +2,8 @@ # Makefile for damon selftests TEST_GEN_FILES += huge_count_read_write +TEST_GEN_FILES += debugfs_target_ids_read_before_terminate_race +TEST_GEN_FILES += debugfs_target_ids_pid_leak TEST_GEN_FILES += access_memory TEST_FILES = _chk_dependency.sh _debugfs_common.sh @@ -9,9 +11,12 @@ TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh TEST_PROGS += debugfs_duplicate_context_creation.sh TEST_PROGS += debugfs_rm_non_contexts.sh +TEST_PROGS += debugfs_target_ids_read_before_terminate_race.sh +TEST_PROGS += debugfs_target_ids_pid_leak.sh TEST_PROGS += sysfs.sh sysfs_update_removed_scheme_dir.sh TEST_PROGS += sysfs_update_schemes_tried_regions_hang.py TEST_PROGS += sysfs_update_schemes_tried_regions_wss_estimation.py +TEST_PROGS += damos_quota.py damos_apply_interval.py TEST_PROGS += reclaim.sh lru_sort.sh include ../lib.mk diff --git a/tools/testing/selftests/damon/_chk_dependency.sh b/tools/testing/selftests/damon/_chk_dependency.sh index 0328ac0b5a5e..dda3a87dc00a 100644 --- a/tools/testing/selftests/damon/_chk_dependency.sh +++ b/tools/testing/selftests/damon/_chk_dependency.sh @@ -4,7 +4,14 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -DBGFS=/sys/kernel/debug/damon +DBGFS=$(grep debugfs /proc/mounts --max-count 1 | awk '{print $2}') +if [ "$DBGFS" = "" ] +then + echo "debugfs not mounted" + exit $ksft_skip +fi + +DBGFS+="/damon" if [ $EUID -ne 0 ]; then @@ -18,7 +25,14 @@ then exit $ksft_skip fi -for f in attrs target_ids monitor_on +if [ -f "$DBGFS/monitor_on_DEPRECATED" ] +then + monitor_on_file="monitor_on_DEPRECATED" +else + monitor_on_file="monitor_on" +fi + +for f in attrs target_ids "$monitor_on_file" do if [ ! -f "$DBGFS/$f" ] then @@ -28,7 +42,7 @@ do done permission_error="Operation not permitted" -for f in attrs target_ids monitor_on +for f in attrs target_ids "$monitor_on_file" do status=$( cat "$DBGFS/$f" 2>&1 ) if [ "${status#*$permission_error}" != "$status" ]; then diff --git a/tools/testing/selftests/damon/_damon_sysfs.py b/tools/testing/selftests/damon/_damon_sysfs.py index e98cf4b6a4b7..d23d7398a27a 100644 --- a/tools/testing/selftests/damon/_damon_sysfs.py +++ b/tools/testing/selftests/damon/_damon_sysfs.py @@ -70,18 +70,65 @@ class DamosAccessPattern: if err != None: return err +class DamosQuota: + sz = None # size quota, in bytes + ms = None # time quota + reset_interval_ms = None # quota reset interval + scheme = None # owner scheme + + def __init__(self, sz=0, ms=0, reset_interval_ms=0): + self.sz = sz + self.ms = ms + self.reset_interval_ms = reset_interval_ms + + def sysfs_dir(self): + return os.path.join(self.scheme.sysfs_dir(), 'quotas') + + def stage(self): + err = write_file(os.path.join(self.sysfs_dir(), 'bytes'), self.sz) + if err != None: + return err + err = write_file(os.path.join(self.sysfs_dir(), 'ms'), self.ms) + if err != None: + return err + err = write_file(os.path.join(self.sysfs_dir(), 'reset_interval_ms'), + self.reset_interval_ms) + if err != None: + return err + +class DamosStats: + nr_tried = None + sz_tried = None + nr_applied = None + sz_applied = None + qt_exceeds = None + + def __init__(self, nr_tried, sz_tried, nr_applied, sz_applied, qt_exceeds): + self.nr_tried = nr_tried + self.sz_tried = sz_tried + self.nr_applied = nr_applied + self.sz_applied = sz_applied + self.qt_exceeds = qt_exceeds + class Damos: action = None access_pattern = None - # todo: Support quotas, watermarks, stats, tried_regions + quota = None + apply_interval_us = None + # todo: Support watermarks, stats, tried_regions idx = None context = None tried_bytes = None + stats = None - def __init__(self, action='stat', access_pattern=DamosAccessPattern()): + def __init__(self, action='stat', access_pattern=DamosAccessPattern(), + quota=DamosQuota(), apply_interval_us=0): self.action = action self.access_pattern = access_pattern self.access_pattern.scheme = self + self.quota = quota + self.quota.scheme = self + self.apply_interval_us = apply_interval_us def sysfs_dir(self): return os.path.join( @@ -94,13 +141,12 @@ class Damos: err = self.access_pattern.stage() if err != None: return err - - # disable quotas - err = write_file(os.path.join(self.sysfs_dir(), 'quotas', 'ms'), '0') + err = write_file(os.path.join(self.sysfs_dir(), 'apply_interval_us'), + '%d' % self.apply_interval_us) if err != None: return err - err = write_file( - os.path.join(self.sysfs_dir(), 'quotas', 'bytes'), '0') + + err = self.quota.stage() if err != None: return err @@ -298,6 +344,23 @@ class Kdamond: return err scheme.tried_bytes = int(content) + def update_schemes_stats(self): + err = write_file(os.path.join(self.sysfs_dir(), 'state'), + 'update_schemes_stats') + if err != None: + return err + for context in self.contexts: + for scheme in context.schemes: + stat_values = [] + for stat in ['nr_tried', 'sz_tried', 'nr_applied', + 'sz_applied', 'qt_exceeds']: + content, err = read_file( + os.path.join(scheme.sysfs_dir(), 'stats', stat)) + if err != None: + return err + stat_values.append(int(content)) + scheme.stats = DamosStats(*stat_values) + class Kdamonds: kdamonds = [] diff --git a/tools/testing/selftests/damon/_debugfs_common.sh b/tools/testing/selftests/damon/_debugfs_common.sh index 48989d4813ae..aa995516870b 100644 --- a/tools/testing/selftests/damon/_debugfs_common.sh +++ b/tools/testing/selftests/damon/_debugfs_common.sh @@ -45,6 +45,13 @@ test_content() { source ./_chk_dependency.sh damon_onoff="$DBGFS/monitor_on" +if [ -f "$DBGFS/monitor_on_DEPRECATED" ] +then + damon_onoff="$DBGFS/monitor_on_DEPRECATED" +else + damon_onoff="$DBGFS/monitor_on" +fi + if [ $(cat "$damon_onoff") = "on" ] then echo "monitoring is on" diff --git a/tools/testing/selftests/damon/damos_apply_interval.py b/tools/testing/selftests/damon/damos_apply_interval.py new file mode 100644 index 000000000000..f04d43702481 --- /dev/null +++ b/tools/testing/selftests/damon/damos_apply_interval.py @@ -0,0 +1,67 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import subprocess +import time + +import _damon_sysfs + +def main(): + # access two 10 MiB memory regions, 2 second per each + sz_region = 10 * 1024 * 1024 + proc = subprocess.Popen(['./access_memory', '2', '%d' % sz_region, '2000']) + + # Set quota up to 1 MiB per 100 ms + kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond( + contexts=[_damon_sysfs.DamonCtx( + ops='vaddr', + targets=[_damon_sysfs.DamonTarget(pid=proc.pid)], + schemes=[ + _damon_sysfs.Damos( + access_pattern=_damon_sysfs.DamosAccessPattern( + # >= 25% access rate, >= 200ms age + nr_accesses=[5, 20], age=[2, 2**64 - 1]), + # aggregation interval (100 ms) is used + apply_interval_us=0), + # use 10ms apply interval + _damon_sysfs.Damos( + access_pattern=_damon_sysfs.DamosAccessPattern( + # >= 25% access rate, >= 200ms age + nr_accesses=[5, 20], age=[2, 2**64 - 1]), + # explicitly set 10 ms apply interval + apply_interval_us=10 * 1000) + ] # schemes + )] # contexts + )]) # kdamonds + + err = kdamonds.start() + if err != None: + print('kdamond start failed: %s' % err) + exit(1) + + wss_collected = [] + nr_quota_exceeds = 0 + while proc.poll() == None: + time.sleep(0.1) + err = kdamonds.kdamonds[0].update_schemes_stats() + if err != None: + print('stats update failed: %s' % err) + exit(1) + schemes = kdamonds.kdamonds[0].contexts[0].schemes + nr_tried_stats = [s.stats.nr_tried for s in schemes] + if nr_tried_stats[0] == 0 or nr_tried_stats[1] == 0: + print('scheme(s) are not tried') + exit(1) + + # Because the second scheme was having the apply interval that is ten times + # lower than that of the first scheme, the second scheme should be tried + # about ten times more frequently than the first scheme. For possible + # timing errors, check if it was at least nine times more freuqnetly tried. + ratio = nr_tried_stats[1] / nr_tried_stats[0] + if ratio < 9: + print('%d / %d = %f (< 9)' % + (nr_tried_stats[1], nr_tried_stats[0], ratio)) + exit(1) + +if __name__ == '__main__': + main() diff --git a/tools/testing/selftests/damon/damos_quota.py b/tools/testing/selftests/damon/damos_quota.py new file mode 100644 index 000000000000..7d4c6bb2e3cd --- /dev/null +++ b/tools/testing/selftests/damon/damos_quota.py @@ -0,0 +1,67 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import subprocess +import time + +import _damon_sysfs + +def main(): + # access two 10 MiB memory regions, 2 second per each + sz_region = 10 * 1024 * 1024 + proc = subprocess.Popen(['./access_memory', '2', '%d' % sz_region, '2000']) + + # Set quota up to 1 MiB per 100 ms + sz_quota = 1024 * 1024 # 1 MiB + quota_reset_interval = 100 # 100 ms + kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond( + contexts=[_damon_sysfs.DamonCtx( + ops='vaddr', + targets=[_damon_sysfs.DamonTarget(pid=proc.pid)], + schemes=[_damon_sysfs.Damos( + access_pattern=_damon_sysfs.DamosAccessPattern( + # >= 25% access rate, >= 200ms age + nr_accesses=[5, 20], age=[2, 2**64 - 1]), + quota=_damon_sysfs.DamosQuota( + sz=sz_quota, reset_interval_ms=quota_reset_interval) + )] # schemes + )] # contexts + )]) # kdamonds + + err = kdamonds.start() + if err != None: + print('kdamond start failed: %s' % err) + exit(1) + + wss_collected = [] + nr_quota_exceeds = 0 + while proc.poll() == None: + time.sleep(0.1) + err = kdamonds.kdamonds[0].update_schemes_tried_bytes() + if err != None: + print('tried bytes update failed: %s' % err) + exit(1) + err = kdamonds.kdamonds[0].update_schemes_stats() + if err != None: + print('stats update failed: %s' % err) + exit(1) + + scheme = kdamonds.kdamonds[0].contexts[0].schemes[0] + wss_collected.append(scheme.tried_bytes) + nr_quota_exceeds = scheme.stats.qt_exceeds + + wss_collected.sort() + for wss in wss_collected: + if wss > sz_quota: + print('quota is not kept: %s > %s' % (wss, sz_quota)) + print('collected samples are as below') + print('\n'.join(['%d' % wss for wss in wss_collected])) + exit(1) + + if nr_quota_exceeds < len(wss_collected): + print('quota is not always exceeded: %d > %d' % + (len(wss_collected), nr_quota_exceeds)) + exit(1) + +if __name__ == '__main__': + main() diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh index 87aff8083822..effbea33dc16 100755 --- a/tools/testing/selftests/damon/debugfs_empty_targets.sh +++ b/tools/testing/selftests/damon/debugfs_empty_targets.sh @@ -8,6 +8,14 @@ source _debugfs_common.sh orig_target_ids=$(cat "$DBGFS/target_ids") echo "" > "$DBGFS/target_ids" -orig_monitor_on=$(cat "$DBGFS/monitor_on") -test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids" + +if [ -f "$DBGFS/monitor_on_DEPRECATED" ] +then + monitor_on_file="$DBGFS/monitor_on_DEPRECATED" +else + monitor_on_file="$DBGFS/monitor_on" +fi + +orig_monitor_on=$(cat "$monitor_on_file") +test_write_fail "$monitor_on_file" "on" "orig_monitor_on" "empty target ids" echo "$orig_target_ids" > "$DBGFS/target_ids" diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c new file mode 100644 index 000000000000..0cc2eef7d142 --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: SeongJae Park <sj@kernel.org> + */ + +#define _GNU_SOURCE + +#include <fcntl.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/time.h> +#include <unistd.h> + +#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids" + +static void write_targetid_exit(void) +{ + int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); + char pid_str[128]; + + snprintf(pid_str, sizeof(pid_str), "%d", getpid()); + write(target_ids_fd, pid_str, sizeof(pid_str)); + close(target_ids_fd); + exit(0); +} + +unsigned long msec_timestamp(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return tv.tv_sec * 1000UL + tv.tv_usec / 1000; +} + +int main(int argc, char *argv[]) +{ + unsigned long start_ms; + int time_to_run, nr_forks = 0; + + if (argc != 2) { + fprintf(stderr, "Usage: %s <msecs to run>\n", argv[0]); + exit(1); + } + time_to_run = atoi(argv[1]); + + start_ms = msec_timestamp(); + while (true) { + int pid = fork(); + + if (pid < 0) { + fprintf(stderr, "fork() failed\n"); + exit(1); + } + if (pid == 0) + write_targetid_exit(); + wait(NULL); + nr_forks++; + + if (msec_timestamp() - start_ms > time_to_run) + break; + } + printf("%d\n", nr_forks); + return 0; +} diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh new file mode 100644 index 000000000000..31fe33c2b032 --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh @@ -0,0 +1,22 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +before=$(grep "^pid " /proc/slabinfo | awk '{print $2}') + +nr_leaks=$(./debugfs_target_ids_pid_leak 1000) +expected_after_max=$((before + nr_leaks / 2)) + +after=$(grep "^pid " /proc/slabinfo | awk '{print $2}') + +echo > /sys/kernel/debug/damon/target_ids + +echo "tried $nr_leaks pid leak" +echo "number of active pid slabs: $before -> $after" +echo "(up to $expected_after_max expected)" +if [ $after -gt $expected_after_max ] +then + echo "maybe pids are leaking" + exit 1 +else + exit 0 +fi diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c new file mode 100644 index 000000000000..b06f52a8ce2d --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: SeongJae Park <sj@kernel.org> + */ +#define _GNU_SOURCE + +#include <fcntl.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <time.h> +#include <unistd.h> + +#define DBGFS_MONITOR_ON "/sys/kernel/debug/damon/monitor_on_DEPRECATED" +#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids" + +static void turn_damon_on_exit(void) +{ + int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); + int monitor_on_fd = open(DBGFS_MONITOR_ON, O_RDWR); + char pid_str[128]; + + snprintf(pid_str, sizeof(pid_str), "%d", getpid()); + write(target_ids_fd, pid_str, sizeof(pid_str)); + write(monitor_on_fd, "on\n", 3); + close(target_ids_fd); + close(monitor_on_fd); + usleep(1000); + exit(0); +} + +static void try_race(void) +{ + int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); + int pid = fork(); + int buf[256]; + + if (pid < 0) { + fprintf(stderr, "fork() failed\n"); + exit(1); + } + if (pid == 0) + turn_damon_on_exit(); + while (true) { + int status; + + read(target_ids_fd, buf, sizeof(buf)); + if (waitpid(-1, &status, WNOHANG) == pid) + break; + } + close(target_ids_fd); +} + +static inline uint64_t ts_to_ms(struct timespec *ts) +{ + return (uint64_t)ts->tv_sec * 1000 + (uint64_t)ts->tv_nsec / 1000000; +} + +int main(int argc, char *argv[]) +{ + struct timespec start_time, now; + int runtime_ms; + + if (argc != 2) { + fprintf(stderr, "Usage: %s <runtime in ms>\n", argv[0]); + exit(1); + } + runtime_ms = atoi(argv[1]); + clock_gettime(CLOCK_MONOTONIC, &start_time); + while (true) { + try_race(); + clock_gettime(CLOCK_MONOTONIC, &now); + if (ts_to_ms(&now) - ts_to_ms(&start_time) > runtime_ms) + break; + } + return 0; +} diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh new file mode 100644 index 000000000000..fc793c4c9aea --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh @@ -0,0 +1,14 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +dmesg -C + +./debugfs_target_ids_read_before_terminate_race 5000 + +if dmesg | grep -q dbgfs_target_ids_read +then + dmesg + exit 1 +else + exit 0 +fi diff --git a/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py index 8c690ba1a573..28c887a0108f 100644 --- a/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py +++ b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py @@ -20,7 +20,7 @@ def main(): err = kdamonds.start() if err != None: - print('kdmaond start failed: %s' % err) + print('kdamond start failed: %s' % err) exit(1) while proc.poll() == None: diff --git a/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py index cdbf19b442c9..90ad7409a7a6 100644 --- a/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py +++ b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py @@ -23,7 +23,7 @@ def main(): err = kdamonds.start() if err != None: - print('kdmaond start failed: %s' % err) + print('kdamond start failed: %s' % err) exit(1) wss_collected = [] diff --git a/tools/testing/selftests/filesystems/eventfd/.gitignore b/tools/testing/selftests/filesystems/eventfd/.gitignore new file mode 100644 index 000000000000..483faf59fe4a --- /dev/null +++ b/tools/testing/selftests/filesystems/eventfd/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +eventfd_test diff --git a/tools/testing/selftests/filesystems/eventfd/Makefile b/tools/testing/selftests/filesystems/eventfd/Makefile new file mode 100644 index 000000000000..0a8e3910df15 --- /dev/null +++ b/tools/testing/selftests/filesystems/eventfd/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS += $(KHDR_INCLUDES) +LDLIBS += -lpthread +TEST_GEN_PROGS := eventfd_test + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/eventfd/eventfd_test.c b/tools/testing/selftests/filesystems/eventfd/eventfd_test.c new file mode 100644 index 000000000000..f142a137526c --- /dev/null +++ b/tools/testing/selftests/filesystems/eventfd/eventfd_test.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <asm/unistd.h> +#include <linux/time_types.h> +#include <unistd.h> +#include <assert.h> +#include <signal.h> +#include <pthread.h> +#include <sys/epoll.h> +#include <sys/eventfd.h> +#include "../../kselftest_harness.h" + +struct error { + int code; + char msg[512]; +}; + +static int error_set(struct error *err, int code, const char *fmt, ...) +{ + va_list args; + int r; + + if (code == 0 || !err || err->code != 0) + return code; + + err->code = code; + va_start(args, fmt); + r = vsnprintf(err->msg, sizeof(err->msg), fmt, args); + assert((size_t)r < sizeof(err->msg)); + va_end(args); + + return code; +} + +static inline int sys_eventfd2(unsigned int count, int flags) +{ + return syscall(__NR_eventfd2, count, flags); +} + +TEST(eventfd01) +{ + int fd, flags; + + fd = sys_eventfd2(0, 0); + ASSERT_GE(fd, 0); + + flags = fcntl(fd, F_GETFL); + // since the kernel automatically added O_RDWR. + EXPECT_EQ(flags, O_RDWR); + + close(fd); +} + +TEST(eventfd02) +{ + int fd, flags; + + fd = sys_eventfd2(0, EFD_CLOEXEC); + ASSERT_GE(fd, 0); + + flags = fcntl(fd, F_GETFD); + ASSERT_GT(flags, -1); + EXPECT_EQ(flags, FD_CLOEXEC); + + close(fd); +} + +TEST(eventfd03) +{ + int fd, flags; + + fd = sys_eventfd2(0, EFD_NONBLOCK); + ASSERT_GE(fd, 0); + + flags = fcntl(fd, F_GETFL); + ASSERT_GT(flags, -1); + EXPECT_EQ(flags & EFD_NONBLOCK, EFD_NONBLOCK); + EXPECT_EQ(flags & O_RDWR, O_RDWR); + + close(fd); +} + +TEST(eventfd04) +{ + int fd, flags; + + fd = sys_eventfd2(0, EFD_CLOEXEC|EFD_NONBLOCK); + ASSERT_GE(fd, 0); + + flags = fcntl(fd, F_GETFL); + ASSERT_GT(flags, -1); + EXPECT_EQ(flags & EFD_NONBLOCK, EFD_NONBLOCK); + EXPECT_EQ(flags & O_RDWR, O_RDWR); + + flags = fcntl(fd, F_GETFD); + ASSERT_GT(flags, -1); + EXPECT_EQ(flags, FD_CLOEXEC); + + close(fd); +} + +static inline void trim_newline(char *str) +{ + char *pos = strrchr(str, '\n'); + + if (pos) + *pos = '\0'; +} + +static int verify_fdinfo(int fd, struct error *err, const char *prefix, + size_t prefix_len, const char *expect, ...) +{ + char buffer[512] = {0, }; + char path[512] = {0, }; + va_list args; + FILE *f; + char *line = NULL; + size_t n = 0; + int found = 0; + int r; + + va_start(args, expect); + r = vsnprintf(buffer, sizeof(buffer), expect, args); + assert((size_t)r < sizeof(buffer)); + va_end(args); + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd); + f = fopen(path, "re"); + if (!f) + return error_set(err, -1, "fdinfo open failed for %d", fd); + + while (getline(&line, &n, f) != -1) { + char *val; + + if (strncmp(line, prefix, prefix_len)) + continue; + + found = 1; + + val = line + prefix_len; + r = strcmp(val, buffer); + if (r != 0) { + trim_newline(line); + trim_newline(buffer); + error_set(err, -1, "%s '%s' != '%s'", + prefix, val, buffer); + } + break; + } + + free(line); + fclose(f); + + if (found == 0) + return error_set(err, -1, "%s not found for fd %d", + prefix, fd); + + return 0; +} + +TEST(eventfd05) +{ + struct error err = {0}; + int fd, ret; + + fd = sys_eventfd2(0, EFD_SEMAPHORE); + ASSERT_GE(fd, 0); + + ret = fcntl(fd, F_GETFL); + ASSERT_GT(ret, -1); + EXPECT_EQ(ret & O_RDWR, O_RDWR); + + // The semaphore could only be obtained from fdinfo. + ret = verify_fdinfo(fd, &err, "eventfd-semaphore: ", 19, "1\n"); + if (ret != 0) + ksft_print_msg("eventfd-semaphore check failed, msg: %s\n", + err.msg); + EXPECT_EQ(ret, 0); + + close(fd); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 492e937fab00..741c7dc16afc 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -36,7 +36,9 @@ LIBKVM_x86_64 += lib/x86_64/apic.c LIBKVM_x86_64 += lib/x86_64/handlers.S LIBKVM_x86_64 += lib/x86_64/hyperv.c LIBKVM_x86_64 += lib/x86_64/memstress.c +LIBKVM_x86_64 += lib/x86_64/pmu.c LIBKVM_x86_64 += lib/x86_64/processor.c +LIBKVM_x86_64 += lib/x86_64/sev.c LIBKVM_x86_64 += lib/x86_64/svm.c LIBKVM_x86_64 += lib/x86_64/ucall.c LIBKVM_x86_64 += lib/x86_64/vmx.c @@ -53,6 +55,7 @@ LIBKVM_s390x += lib/s390x/diag318_test_handler.c LIBKVM_s390x += lib/s390x/processor.c LIBKVM_s390x += lib/s390x/ucall.c +LIBKVM_riscv += lib/riscv/handlers.S LIBKVM_riscv += lib/riscv/processor.c LIBKVM_riscv += lib/riscv/ucall.c @@ -80,6 +83,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test +TEST_GEN_PROGS_x86_64 += x86_64/pmu_counters_test TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test @@ -117,6 +121,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_caps_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests +TEST_GEN_PROGS_x86_64 += x86_64/sev_smoke_test TEST_GEN_PROGS_x86_64 += x86_64/amx_test TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test @@ -143,7 +148,6 @@ TEST_GEN_PROGS_x86_64 += system_counter_offset_test TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test TEST_GEN_PROGS_aarch64 += aarch64/aarch32_id_regs -TEST_GEN_PROGS_aarch64 += aarch64/arch_timer TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions TEST_GEN_PROGS_aarch64 += aarch64/hypercalls TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test @@ -155,6 +159,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/vgic_init TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access TEST_GEN_PROGS_aarch64 += access_tracking_perf_test +TEST_GEN_PROGS_aarch64 += arch_timer TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test @@ -184,6 +189,7 @@ TEST_GEN_PROGS_s390x += rseq_test TEST_GEN_PROGS_s390x += set_memory_region_test TEST_GEN_PROGS_s390x += kvm_binary_stats_test +TEST_GEN_PROGS_riscv += arch_timer TEST_GEN_PROGS_riscv += demand_paging_test TEST_GEN_PROGS_riscv += dirty_log_test TEST_GEN_PROGS_riscv += get-reg-list @@ -194,6 +200,7 @@ TEST_GEN_PROGS_riscv += kvm_page_table_test TEST_GEN_PROGS_riscv += set_memory_region_test TEST_GEN_PROGS_riscv += steal_time +SPLIT_TESTS += arch_timer SPLIT_TESTS += get-reg-list TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR)) @@ -217,7 +224,7 @@ else LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include endif CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ - -Wno-gnu-variable-sized-type-not-at-end -MD -MP \ + -Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \ -fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \ -fno-builtin-strnlen \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ @@ -260,32 +267,36 @@ LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING)) LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) -SPLIT_TESTS_TARGETS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS)) -SPLIT_TESTS_OBJS := $(patsubst %, $(ARCH_DIR)/%.o, $(SPLIT_TESTS)) +SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS)) +SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH_DIR)/%.o, $(SPLIT_TESTS)) TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS)) TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED)) TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ)) TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS)) -TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TESTS_OBJS)) +TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TEST_GEN_OBJ)) -include $(TEST_DEP_FILES) -$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): %: %.o +$(shell mkdir -p $(sort $(OUTPUT)/$(ARCH_DIR) $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) + +$(filter-out $(SPLIT_TEST_GEN_PROGS), $(TEST_GEN_PROGS)) \ +$(TEST_GEN_PROGS_EXTENDED): %: %.o $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@ $(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -$(SPLIT_TESTS_TARGETS): %: %.o $(SPLIT_TESTS_OBJS) +$(SPLIT_TEST_GEN_PROGS): $(OUTPUT)/%: $(OUTPUT)/%.o $(OUTPUT)/$(ARCH_DIR)/%.o $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@ +$(SPLIT_TEST_GEN_OBJ): $(OUTPUT)/$(ARCH_DIR)/%.o: $(ARCH_DIR)/%.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ EXTRA_CLEAN += $(GEN_HDRS) \ $(LIBKVM_OBJS) \ - $(SPLIT_TESTS_OBJS) \ + $(SPLIT_TEST_GEN_OBJ) \ $(TEST_DEP_FILES) \ $(TEST_GEN_OBJ) \ cscope.* -x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS) $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ @@ -298,8 +309,8 @@ $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS) $(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@ -x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) -$(SPLIT_TESTS_OBJS): $(GEN_HDRS) +$(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) +$(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS) $(TEST_GEN_PROGS): $(LIBKVM_OBJS) $(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS) $(TEST_GEN_OBJ): $(GEN_HDRS) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 2cb8dd1f8275..ddba2c2fb5de 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -1,64 +1,19 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * arch_timer.c - Tests the aarch64 timer IRQ functionality - * * The test validates both the virtual and physical timer IRQs using - * CVAL and TVAL registers. This consitutes the four stages in the test. - * The guest's main thread configures the timer interrupt for a stage - * and waits for it to fire, with a timeout equal to the timer period. - * It asserts that the timeout doesn't exceed the timer period. - * - * On the other hand, upon receipt of an interrupt, the guest's interrupt - * handler validates the interrupt by checking if the architectural state - * is in compliance with the specifications. - * - * The test provides command-line options to configure the timer's - * period (-p), number of vCPUs (-n), and iterations per stage (-i). - * To stress-test the timer stack even more, an option to migrate the - * vCPUs across pCPUs (-m), at a particular rate, is also provided. + * CVAL and TVAL registers. * * Copyright (c) 2021, Google LLC. */ #define _GNU_SOURCE -#include <stdlib.h> -#include <pthread.h> -#include <linux/kvm.h> -#include <linux/sizes.h> -#include <linux/bitmap.h> -#include <sys/sysinfo.h> - -#include "kvm_util.h" -#include "processor.h" -#include "delay.h" #include "arch_timer.h" +#include "delay.h" #include "gic.h" +#include "processor.h" +#include "timer_test.h" #include "vgic.h" -#define NR_VCPUS_DEF 4 -#define NR_TEST_ITERS_DEF 5 -#define TIMER_TEST_PERIOD_MS_DEF 10 -#define TIMER_TEST_ERR_MARGIN_US 100 -#define TIMER_TEST_MIGRATION_FREQ_MS 2 - -struct test_args { - int nr_vcpus; - int nr_iter; - int timer_period_ms; - int migration_freq_ms; - struct kvm_arm_counter_offset offset; -}; - -static struct test_args test_args = { - .nr_vcpus = NR_VCPUS_DEF, - .nr_iter = NR_TEST_ITERS_DEF, - .timer_period_ms = TIMER_TEST_PERIOD_MS_DEF, - .migration_freq_ms = TIMER_TEST_MIGRATION_FREQ_MS, - .offset = { .reserved = 1 }, -}; - -#define msecs_to_usecs(msec) ((msec) * 1000LL) - #define GICD_BASE_GPA 0x8000000ULL #define GICR_BASE_GPA 0x80A0000ULL @@ -70,22 +25,8 @@ enum guest_stage { GUEST_STAGE_MAX, }; -/* Shared variables between host and guest */ -struct test_vcpu_shared_data { - int nr_iter; - enum guest_stage guest_stage; - uint64_t xcnt; -}; - -static struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; -static pthread_t pt_vcpu_run[KVM_MAX_VCPUS]; -static struct test_vcpu_shared_data vcpu_shared_data[KVM_MAX_VCPUS]; - static int vtimer_irq, ptimer_irq; -static unsigned long *vcpu_done_map; -static pthread_mutex_t vcpu_done_map_lock; - static void guest_configure_timer_action(struct test_vcpu_shared_data *shared_data) { @@ -158,9 +99,9 @@ static void guest_validate_irq(unsigned int intid, /* Basic 'timer condition met' check */ __GUEST_ASSERT(xcnt >= cval, - "xcnt = 0x%llx, cval = 0x%llx, xcnt_diff_us = 0x%llx", + "xcnt = 0x%lx, cval = 0x%lx, xcnt_diff_us = 0x%lx", xcnt, cval, xcnt_diff_us); - __GUEST_ASSERT(xctl & CTL_ISTATUS, "xcnt = 0x%llx", xcnt); + __GUEST_ASSERT(xctl & CTL_ISTATUS, "xctl = 0x%lx", xctl); WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1); } @@ -190,10 +131,14 @@ static void guest_run_stage(struct test_vcpu_shared_data *shared_data, /* Setup a timeout for the interrupt to arrive */ udelay(msecs_to_usecs(test_args.timer_period_ms) + - TIMER_TEST_ERR_MARGIN_US); + test_args.timer_err_margin_us); irq_iter = READ_ONCE(shared_data->nr_iter); - GUEST_ASSERT_EQ(config_iter + 1, irq_iter); + __GUEST_ASSERT(config_iter + 1 == irq_iter, + "config_iter + 1 = 0x%lx, irq_iter = 0x%lx.\n" + " Guest timer interrupt was not trigged within the specified\n" + " interval, try to increase the error margin by [-e] option.\n", + config_iter + 1, irq_iter); } } @@ -222,137 +167,6 @@ static void guest_code(void) GUEST_DONE(); } -static void *test_vcpu_run(void *arg) -{ - unsigned int vcpu_idx = (unsigned long)arg; - struct ucall uc; - struct kvm_vcpu *vcpu = vcpus[vcpu_idx]; - struct kvm_vm *vm = vcpu->vm; - struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[vcpu_idx]; - - vcpu_run(vcpu); - - /* Currently, any exit from guest is an indication of completion */ - pthread_mutex_lock(&vcpu_done_map_lock); - __set_bit(vcpu_idx, vcpu_done_map); - pthread_mutex_unlock(&vcpu_done_map_lock); - - switch (get_ucall(vcpu, &uc)) { - case UCALL_SYNC: - case UCALL_DONE: - break; - case UCALL_ABORT: - sync_global_from_guest(vm, *shared_data); - fprintf(stderr, "Guest assert failed, vcpu %u; stage; %u; iter: %u\n", - vcpu_idx, shared_data->guest_stage, shared_data->nr_iter); - REPORT_GUEST_ASSERT(uc); - break; - default: - TEST_FAIL("Unexpected guest exit"); - } - - return NULL; -} - -static uint32_t test_get_pcpu(void) -{ - uint32_t pcpu; - unsigned int nproc_conf; - cpu_set_t online_cpuset; - - nproc_conf = get_nprocs_conf(); - sched_getaffinity(0, sizeof(cpu_set_t), &online_cpuset); - - /* Randomly find an available pCPU to place a vCPU on */ - do { - pcpu = rand() % nproc_conf; - } while (!CPU_ISSET(pcpu, &online_cpuset)); - - return pcpu; -} - -static int test_migrate_vcpu(unsigned int vcpu_idx) -{ - int ret; - cpu_set_t cpuset; - uint32_t new_pcpu = test_get_pcpu(); - - CPU_ZERO(&cpuset); - CPU_SET(new_pcpu, &cpuset); - - pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu_idx, new_pcpu); - - ret = pthread_setaffinity_np(pt_vcpu_run[vcpu_idx], - sizeof(cpuset), &cpuset); - - /* Allow the error where the vCPU thread is already finished */ - TEST_ASSERT(ret == 0 || ret == ESRCH, - "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d", - vcpu_idx, new_pcpu, ret); - - return ret; -} - -static void *test_vcpu_migration(void *arg) -{ - unsigned int i, n_done; - bool vcpu_done; - - do { - usleep(msecs_to_usecs(test_args.migration_freq_ms)); - - for (n_done = 0, i = 0; i < test_args.nr_vcpus; i++) { - pthread_mutex_lock(&vcpu_done_map_lock); - vcpu_done = test_bit(i, vcpu_done_map); - pthread_mutex_unlock(&vcpu_done_map_lock); - - if (vcpu_done) { - n_done++; - continue; - } - - test_migrate_vcpu(i); - } - } while (test_args.nr_vcpus != n_done); - - return NULL; -} - -static void test_run(struct kvm_vm *vm) -{ - pthread_t pt_vcpu_migration; - unsigned int i; - int ret; - - pthread_mutex_init(&vcpu_done_map_lock, NULL); - vcpu_done_map = bitmap_zalloc(test_args.nr_vcpus); - TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap"); - - for (i = 0; i < (unsigned long)test_args.nr_vcpus; i++) { - ret = pthread_create(&pt_vcpu_run[i], NULL, test_vcpu_run, - (void *)(unsigned long)i); - TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread", i); - } - - /* Spawn a thread to control the vCPU migrations */ - if (test_args.migration_freq_ms) { - srand(time(NULL)); - - ret = pthread_create(&pt_vcpu_migration, NULL, - test_vcpu_migration, NULL); - TEST_ASSERT(!ret, "Failed to create the migration pthread"); - } - - - for (i = 0; i < test_args.nr_vcpus; i++) - pthread_join(pt_vcpu_run[i], NULL); - - if (test_args.migration_freq_ms) - pthread_join(pt_vcpu_migration, NULL); - - bitmap_free(vcpu_done_map); -} - static void test_init_timer_irq(struct kvm_vm *vm) { /* Timer initid should be same for all the vCPUs, so query only vCPU-0 */ @@ -369,7 +183,7 @@ static void test_init_timer_irq(struct kvm_vm *vm) static int gic_fd; -static struct kvm_vm *test_vm_create(void) +struct kvm_vm *test_vm_create(void) { struct kvm_vm *vm; unsigned int i; @@ -380,10 +194,14 @@ static struct kvm_vm *test_vm_create(void) vm_init_descriptor_tables(vm); vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handler); - if (!test_args.offset.reserved) { - if (kvm_has_cap(KVM_CAP_COUNTER_OFFSET)) - vm_ioctl(vm, KVM_ARM_SET_COUNTER_OFFSET, &test_args.offset); - else + if (!test_args.reserved) { + if (kvm_has_cap(KVM_CAP_COUNTER_OFFSET)) { + struct kvm_arm_counter_offset offset = { + .counter_offset = test_args.counter_offset, + .reserved = 0, + }; + vm_ioctl(vm, KVM_ARM_SET_COUNTER_OFFSET, &offset); + } else TEST_FAIL("no support for global offset"); } @@ -400,81 +218,8 @@ static struct kvm_vm *test_vm_create(void) return vm; } -static void test_vm_cleanup(struct kvm_vm *vm) +void test_vm_cleanup(struct kvm_vm *vm) { close(gic_fd); kvm_vm_free(vm); } - -static void test_print_help(char *name) -{ - pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n", - name); - pr_info("\t-n: Number of vCPUs to configure (default: %u; max: %u)\n", - NR_VCPUS_DEF, KVM_MAX_VCPUS); - pr_info("\t-i: Number of iterations per stage (default: %u)\n", - NR_TEST_ITERS_DEF); - pr_info("\t-p: Periodicity (in ms) of the guest timer (default: %u)\n", - TIMER_TEST_PERIOD_MS_DEF); - pr_info("\t-m: Frequency (in ms) of vCPUs to migrate to different pCPU. 0 to turn off (default: %u)\n", - TIMER_TEST_MIGRATION_FREQ_MS); - pr_info("\t-o: Counter offset (in counter cycles, default: 0)\n"); - pr_info("\t-h: print this help screen\n"); -} - -static bool parse_args(int argc, char *argv[]) -{ - int opt; - - while ((opt = getopt(argc, argv, "hn:i:p:m:o:")) != -1) { - switch (opt) { - case 'n': - test_args.nr_vcpus = atoi_positive("Number of vCPUs", optarg); - if (test_args.nr_vcpus > KVM_MAX_VCPUS) { - pr_info("Max allowed vCPUs: %u\n", - KVM_MAX_VCPUS); - goto err; - } - break; - case 'i': - test_args.nr_iter = atoi_positive("Number of iterations", optarg); - break; - case 'p': - test_args.timer_period_ms = atoi_positive("Periodicity", optarg); - break; - case 'm': - test_args.migration_freq_ms = atoi_non_negative("Frequency", optarg); - break; - case 'o': - test_args.offset.counter_offset = strtol(optarg, NULL, 0); - test_args.offset.reserved = 0; - break; - case 'h': - default: - goto err; - } - } - - return true; - -err: - test_print_help(argv[0]); - return false; -} - -int main(int argc, char *argv[]) -{ - struct kvm_vm *vm; - - if (!parse_args(argc, argv)) - exit(KSFT_SKIP); - - __TEST_REQUIRE(!test_args.migration_freq_ms || get_nprocs() >= 2, - "At least two physical CPUs needed for vCPU migration"); - - vm = test_vm_create(); - test_run(vm); - test_vm_cleanup(vm); - - return 0; -} diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c index 866002917441..2582c49e525a 100644 --- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c @@ -365,7 +365,7 @@ static void guest_wp_handler(struct ex_regs *regs) static void guest_ss_handler(struct ex_regs *regs) { - __GUEST_ASSERT(ss_idx < 4, "Expected index < 4, got '%u'", ss_idx); + __GUEST_ASSERT(ss_idx < 4, "Expected index < 4, got '%lu'", ss_idx); ss_addr[ss_idx++] = regs->pc; regs->pstate |= SPSR_SS; } diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c index 27c10e7a7e01..9d192ce0078d 100644 --- a/tools/testing/selftests/kvm/aarch64/hypercalls.c +++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c @@ -105,12 +105,12 @@ static void guest_test_hvc(const struct test_hvc_info *hc_info) case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: case TEST_STAGE_HVC_IFACE_FALSE_INFO: __GUEST_ASSERT(res.a0 == SMCCC_RET_NOT_SUPPORTED, - "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u", + "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%lx, stage = %u", res.a0, hc_info->func_id, hc_info->arg1, stage); break; case TEST_STAGE_HVC_IFACE_FEAT_ENABLED: __GUEST_ASSERT(res.a0 != SMCCC_RET_NOT_SUPPORTED, - "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u", + "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%lx, stage = %u", res.a0, hc_info->func_id, hc_info->arg1, stage); break; default: diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index 53fddad57cbb..5972905275cf 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -292,7 +292,7 @@ static void guest_code(struct test_desc *test) static void no_dabt_handler(struct ex_regs *regs) { - GUEST_FAIL("Unexpected dabt, far_el1 = 0x%llx", read_sysreg(far_el1)); + GUEST_FAIL("Unexpected dabt, far_el1 = 0x%lx", read_sysreg(far_el1)); } static void no_iabt_handler(struct ex_regs *regs) diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c index bac05210b539..16e2338686c1 100644 --- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c +++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c @@ -32,6 +32,10 @@ struct reg_ftr_bits { enum ftr_type type; uint8_t shift; uint64_t mask; + /* + * For FTR_EXACT, safe_val is used as the exact safe value. + * For FTR_LOWER_SAFE, safe_val is used as the minimal safe value. + */ int64_t safe_val; }; @@ -65,13 +69,13 @@ struct test_feature_reg { static const struct reg_ftr_bits ftr_id_aa64dfr0_el1[] = { S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, PMUVer, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, DebugVer, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, DebugVer, ID_AA64DFR0_EL1_DebugVer_IMP), REG_FTR_END, }; static const struct reg_ftr_bits ftr_id_dfr0_el1[] = { - S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, PerfMon, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, CopDbg, 0), + S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, PerfMon, ID_DFR0_EL1_PerfMon_PMUv3), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, CopDbg, ID_DFR0_EL1_CopDbg_Armv8), REG_FTR_END, }; @@ -224,13 +228,13 @@ uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) { uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0); - if (ftr_bits->type == FTR_UNSIGNED) { + if (ftr_bits->sign == FTR_UNSIGNED) { switch (ftr_bits->type) { case FTR_EXACT: ftr = ftr_bits->safe_val; break; case FTR_LOWER_SAFE: - if (ftr > 0) + if (ftr > ftr_bits->safe_val) ftr--; break; case FTR_HIGHER_SAFE: @@ -252,7 +256,7 @@ uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) ftr = ftr_bits->safe_val; break; case FTR_LOWER_SAFE: - if (ftr > 0) + if (ftr > ftr_bits->safe_val) ftr--; break; case FTR_HIGHER_SAFE: @@ -276,7 +280,7 @@ uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) { uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0); - if (ftr_bits->type == FTR_UNSIGNED) { + if (ftr_bits->sign == FTR_UNSIGNED) { switch (ftr_bits->type) { case FTR_EXACT: ftr = max((uint64_t)ftr_bits->safe_val + 1, ftr + 1); diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c index 5f9713364693..f2fb0e3f14bc 100644 --- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c +++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c @@ -93,22 +93,6 @@ static inline void write_sel_evtyper(int sel, unsigned long val) isb(); } -static inline void enable_counter(int idx) -{ - uint64_t v = read_sysreg(pmcntenset_el0); - - write_sysreg(BIT(idx) | v, pmcntenset_el0); - isb(); -} - -static inline void disable_counter(int idx) -{ - uint64_t v = read_sysreg(pmcntenset_el0); - - write_sysreg(BIT(idx) | v, pmcntenclr_el0); - isb(); -} - static void pmu_disable_reset(void) { uint64_t pmcr = read_sysreg(pmcr_el0); @@ -195,11 +179,11 @@ struct pmc_accessor pmc_accessors[] = { \ if (set_expected) \ __GUEST_ASSERT((_tval & mask), \ - "tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \ + "tval: 0x%lx; mask: 0x%lx; set_expected: %u", \ _tval, mask, set_expected); \ else \ __GUEST_ASSERT(!(_tval & mask), \ - "tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \ + "tval: 0x%lx; mask: 0x%lx; set_expected: %u", \ _tval, mask, set_expected); \ } @@ -286,7 +270,7 @@ static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx) acc->write_typer(pmc_idx, write_data); read_data = acc->read_typer(pmc_idx); __GUEST_ASSERT(read_data == write_data, - "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx", + "pmc_idx: 0x%x; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx", pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data); /* @@ -297,14 +281,14 @@ static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx) /* The count value must be 0, as it is disabled and reset */ __GUEST_ASSERT(read_data == 0, - "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx", + "pmc_idx: 0x%x; acc_idx: 0x%lx; read_data: 0x%lx", pmc_idx, PMC_ACC_TO_IDX(acc), read_data); write_data = read_data + pmc_idx + 0x12345; acc->write_cntr(pmc_idx, write_data); read_data = acc->read_cntr(pmc_idx); __GUEST_ASSERT(read_data == write_data, - "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx", + "pmc_idx: 0x%x; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx", pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data); } @@ -379,7 +363,7 @@ static void guest_code(uint64_t expected_pmcr_n) int i, pmc; __GUEST_ASSERT(expected_pmcr_n <= ARMV8_PMU_MAX_GENERAL_COUNTERS, - "Expected PMCR.N: 0x%lx; ARMv8 general counters: 0x%lx", + "Expected PMCR.N: 0x%lx; ARMv8 general counters: 0x%x", expected_pmcr_n, ARMV8_PMU_MAX_GENERAL_COUNTERS); pmcr = read_sysreg(pmcr_el0); diff --git a/tools/testing/selftests/kvm/arch_timer.c b/tools/testing/selftests/kvm/arch_timer.c new file mode 100644 index 000000000000..ae1f1a6d8312 --- /dev/null +++ b/tools/testing/selftests/kvm/arch_timer.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * arch_timer.c - Tests the arch timer IRQ functionality + * + * The guest's main thread configures the timer interrupt and waits + * for it to fire, with a timeout equal to the timer period. + * It asserts that the timeout doesn't exceed the timer period plus + * a user configurable error margin(default to 100us) + * + * On the other hand, upon receipt of an interrupt, the guest's interrupt + * handler validates the interrupt by checking if the architectural state + * is in compliance with the specifications. + * + * The test provides command-line options to configure the timer's + * period (-p), number of vCPUs (-n), iterations per stage (-i) and timer + * interrupt arrival error margin (-e). To stress-test the timer stack + * even more, an option to migrate the vCPUs across pCPUs (-m), at a + * particular rate, is also provided. + * + * Copyright (c) 2021, Google LLC. + */ + +#define _GNU_SOURCE + +#include <stdlib.h> +#include <pthread.h> +#include <linux/sizes.h> +#include <linux/bitmap.h> +#include <sys/sysinfo.h> + +#include "timer_test.h" + +struct test_args test_args = { + .nr_vcpus = NR_VCPUS_DEF, + .nr_iter = NR_TEST_ITERS_DEF, + .timer_period_ms = TIMER_TEST_PERIOD_MS_DEF, + .migration_freq_ms = TIMER_TEST_MIGRATION_FREQ_MS, + .timer_err_margin_us = TIMER_TEST_ERR_MARGIN_US, + .reserved = 1, +}; + +struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; +struct test_vcpu_shared_data vcpu_shared_data[KVM_MAX_VCPUS]; + +static pthread_t pt_vcpu_run[KVM_MAX_VCPUS]; +static unsigned long *vcpu_done_map; +static pthread_mutex_t vcpu_done_map_lock; + +static void *test_vcpu_run(void *arg) +{ + unsigned int vcpu_idx = (unsigned long)arg; + struct ucall uc; + struct kvm_vcpu *vcpu = vcpus[vcpu_idx]; + struct kvm_vm *vm = vcpu->vm; + struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[vcpu_idx]; + + vcpu_run(vcpu); + + /* Currently, any exit from guest is an indication of completion */ + pthread_mutex_lock(&vcpu_done_map_lock); + __set_bit(vcpu_idx, vcpu_done_map); + pthread_mutex_unlock(&vcpu_done_map_lock); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + case UCALL_DONE: + break; + case UCALL_ABORT: + sync_global_from_guest(vm, *shared_data); + fprintf(stderr, "Guest assert failed, vcpu %u; stage; %u; iter: %u\n", + vcpu_idx, shared_data->guest_stage, shared_data->nr_iter); + REPORT_GUEST_ASSERT(uc); + break; + default: + TEST_FAIL("Unexpected guest exit"); + } + + pr_info("PASS(vCPU-%d).\n", vcpu_idx); + + return NULL; +} + +static uint32_t test_get_pcpu(void) +{ + uint32_t pcpu; + unsigned int nproc_conf; + cpu_set_t online_cpuset; + + nproc_conf = get_nprocs_conf(); + sched_getaffinity(0, sizeof(cpu_set_t), &online_cpuset); + + /* Randomly find an available pCPU to place a vCPU on */ + do { + pcpu = rand() % nproc_conf; + } while (!CPU_ISSET(pcpu, &online_cpuset)); + + return pcpu; +} + +static int test_migrate_vcpu(unsigned int vcpu_idx) +{ + int ret; + cpu_set_t cpuset; + uint32_t new_pcpu = test_get_pcpu(); + + CPU_ZERO(&cpuset); + CPU_SET(new_pcpu, &cpuset); + + pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu_idx, new_pcpu); + + ret = pthread_setaffinity_np(pt_vcpu_run[vcpu_idx], + sizeof(cpuset), &cpuset); + + /* Allow the error where the vCPU thread is already finished */ + TEST_ASSERT(ret == 0 || ret == ESRCH, + "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d", + vcpu_idx, new_pcpu, ret); + + return ret; +} + +static void *test_vcpu_migration(void *arg) +{ + unsigned int i, n_done; + bool vcpu_done; + + do { + usleep(msecs_to_usecs(test_args.migration_freq_ms)); + + for (n_done = 0, i = 0; i < test_args.nr_vcpus; i++) { + pthread_mutex_lock(&vcpu_done_map_lock); + vcpu_done = test_bit(i, vcpu_done_map); + pthread_mutex_unlock(&vcpu_done_map_lock); + + if (vcpu_done) { + n_done++; + continue; + } + + test_migrate_vcpu(i); + } + } while (test_args.nr_vcpus != n_done); + + return NULL; +} + +static void test_run(struct kvm_vm *vm) +{ + pthread_t pt_vcpu_migration; + unsigned int i; + int ret; + + pthread_mutex_init(&vcpu_done_map_lock, NULL); + vcpu_done_map = bitmap_zalloc(test_args.nr_vcpus); + TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap"); + + for (i = 0; i < (unsigned long)test_args.nr_vcpus; i++) { + ret = pthread_create(&pt_vcpu_run[i], NULL, test_vcpu_run, + (void *)(unsigned long)i); + TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread", i); + } + + /* Spawn a thread to control the vCPU migrations */ + if (test_args.migration_freq_ms) { + srand(time(NULL)); + + ret = pthread_create(&pt_vcpu_migration, NULL, + test_vcpu_migration, NULL); + TEST_ASSERT(!ret, "Failed to create the migration pthread"); + } + + + for (i = 0; i < test_args.nr_vcpus; i++) + pthread_join(pt_vcpu_run[i], NULL); + + if (test_args.migration_freq_ms) + pthread_join(pt_vcpu_migration, NULL); + + bitmap_free(vcpu_done_map); +} + +static void test_print_help(char *name) +{ + pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n" + "\t\t [-m migration_freq_ms] [-o counter_offset]\n" + "\t\t [-e timer_err_margin_us]\n", name); + pr_info("\t-n: Number of vCPUs to configure (default: %u; max: %u)\n", + NR_VCPUS_DEF, KVM_MAX_VCPUS); + pr_info("\t-i: Number of iterations per stage (default: %u)\n", + NR_TEST_ITERS_DEF); + pr_info("\t-p: Periodicity (in ms) of the guest timer (default: %u)\n", + TIMER_TEST_PERIOD_MS_DEF); + pr_info("\t-m: Frequency (in ms) of vCPUs to migrate to different pCPU. 0 to turn off (default: %u)\n", + TIMER_TEST_MIGRATION_FREQ_MS); + pr_info("\t-o: Counter offset (in counter cycles, default: 0) [aarch64-only]\n"); + pr_info("\t-e: Interrupt arrival error margin (in us) of the guest timer (default: %u)\n", + TIMER_TEST_ERR_MARGIN_US); + pr_info("\t-h: print this help screen\n"); +} + +static bool parse_args(int argc, char *argv[]) +{ + int opt; + + while ((opt = getopt(argc, argv, "hn:i:p:m:o:e:")) != -1) { + switch (opt) { + case 'n': + test_args.nr_vcpus = atoi_positive("Number of vCPUs", optarg); + if (test_args.nr_vcpus > KVM_MAX_VCPUS) { + pr_info("Max allowed vCPUs: %u\n", + KVM_MAX_VCPUS); + goto err; + } + break; + case 'i': + test_args.nr_iter = atoi_positive("Number of iterations", optarg); + break; + case 'p': + test_args.timer_period_ms = atoi_positive("Periodicity", optarg); + break; + case 'm': + test_args.migration_freq_ms = atoi_non_negative("Frequency", optarg); + break; + case 'e': + test_args.timer_err_margin_us = atoi_non_negative("Error Margin", optarg); + break; + case 'o': + test_args.counter_offset = strtol(optarg, NULL, 0); + test_args.reserved = 0; + break; + case 'h': + default: + goto err; + } + } + + return true; + +err: + test_print_help(argv[0]); + return false; +} + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + + if (!parse_args(argc, argv)) + exit(KSFT_SKIP); + + __TEST_REQUIRE(!test_args.migration_freq_ms || get_nprocs() >= 2, + "At least two physical CPUs needed for vCPU migration"); + + vm = test_vm_create(); + test_run(vm); + test_vm_cleanup(vm); + + return 0; +} diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index c78a98c1a915..92eae206baa6 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -167,6 +167,9 @@ static void test_create_guest_memfd_multiple(struct kvm_vm *vm) TEST_ASSERT(ret != -1, "memfd fstat should succeed"); TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size"); TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers"); + + close(fd2); + close(fd1); } int main(int argc, char *argv[]) diff --git a/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h new file mode 100644 index 000000000000..e43a57d99b56 --- /dev/null +++ b/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_ARCH_H +#define SELFTEST_KVM_UTIL_ARCH_H + +struct kvm_vm_arch {}; + +#endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index cf20e44e86f2..9e518b562827 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -226,8 +226,4 @@ void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, uint64_t arg6, struct arm_smccc_res *res); - - -uint32_t guest_get_vcpuid(void); - #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_test_harness.h b/tools/testing/selftests/kvm/include/kvm_test_harness.h new file mode 100644 index 000000000000..8f7c6858e8e2 --- /dev/null +++ b/tools/testing/selftests/kvm/include/kvm_test_harness.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Macros for defining a KVM test + * + * Copyright (C) 2022, Google LLC. + */ + +#ifndef SELFTEST_KVM_TEST_HARNESS_H +#define SELFTEST_KVM_TEST_HARNESS_H + +#include "kselftest_harness.h" + +#define KVM_ONE_VCPU_TEST_SUITE(name) \ + FIXTURE(name) { \ + struct kvm_vcpu *vcpu; \ + }; \ + \ + FIXTURE_SETUP(name) { \ + (void)vm_create_with_one_vcpu(&self->vcpu, NULL); \ + } \ + \ + FIXTURE_TEARDOWN(name) { \ + kvm_vm_free(self->vcpu->vm); \ + } + +#define KVM_ONE_VCPU_TEST(suite, test, guestcode) \ +static void __suite##_##test(struct kvm_vcpu *vcpu); \ + \ +TEST_F(suite, test) \ +{ \ + vcpu_arch_set_entry_point(self->vcpu, guestcode); \ + __suite##_##test(self->vcpu); \ +} \ +static void __suite##_##test(struct kvm_vcpu *vcpu) + +#endif /* SELFTEST_KVM_TEST_HARNESS_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 9e5afc472c14..3e0db283a46a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -18,9 +18,11 @@ #include <linux/types.h> #include <asm/atomic.h> +#include <asm/kvm.h> #include <sys/ioctl.h> +#include "kvm_util_arch.h" #include "sparsebit.h" /* @@ -46,6 +48,7 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ struct userspace_mem_region { struct kvm_userspace_memory_region2 region; struct sparsebit *unused_phy_pages; + struct sparsebit *protected_phy_pages; int fd; off_t offset; enum vm_mem_backing_src_type backing_src_type; @@ -90,6 +93,7 @@ enum kvm_mem_region_type { struct kvm_vm { int mode; unsigned long type; + uint8_t subtype; int kvm_fd; int fd; unsigned int pgtable_levels; @@ -111,6 +115,9 @@ struct kvm_vm { vm_vaddr_t idt; vm_vaddr_t handlers; uint32_t dirty_ring_size; + uint64_t gpa_tag_mask; + + struct kvm_vm_arch arch; /* Cache of information for binary stats interface */ int stats_fd; @@ -191,10 +198,14 @@ enum vm_guest_mode { }; struct vm_shape { - enum vm_guest_mode mode; - unsigned int type; + uint32_t type; + uint8_t mode; + uint8_t subtype; + uint16_t padding; }; +kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t)); + #define VM_TYPE_DEFAULT 0 #define VM_SHAPE(__mode) \ @@ -259,6 +270,10 @@ bool get_kvm_param_bool(const char *param); bool get_kvm_intel_param_bool(const char *param); bool get_kvm_amd_param_bool(const char *param); +int get_kvm_param_integer(const char *param); +int get_kvm_intel_param_integer(const char *param); +int get_kvm_amd_param_integer(const char *param); + unsigned int kvm_check_cap(long cap); static inline bool kvm_has_cap(long cap) @@ -564,6 +579,13 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, uint64_t guest_paddr, uint32_t slot, uint64_t npages, uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset); +#ifndef vm_arch_has_protected_memory +static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) +{ + return false; +} +#endif + 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); @@ -573,6 +595,9 @@ vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_mi vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, enum kvm_mem_region_type type); +vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type); vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type); @@ -585,6 +610,12 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); + +static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa) +{ + return gpa & ~vm->gpa_tag_mask; +} + void vcpu_run(struct kvm_vcpu *vcpu); int _vcpu_run(struct kvm_vcpu *vcpu); @@ -827,10 +858,23 @@ const char *exit_reason_str(unsigned int exit_reason); vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, uint32_t memslot); -vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot); +vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot, + bool protected); vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); +static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot) +{ + /* + * By default, allocate memory as protected for VMs that support + * protected memory, as the majority of memory for such VMs is + * protected, i.e. using shared memory is effectively opt-in. + */ + return __vm_phy_pages_alloc(vm, num, paddr_min, memslot, + vm_arch_has_protected_memory(vm)); +} + /* * ____vm_create() does KVM_CREATE_VM and little else. __vm_create() also * loads the test binary into guest memory and creates an IRQ chip (x86 only). @@ -969,15 +1013,18 @@ static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu, * Input Args: * vm - Virtual Machine * vcpu_id - The id of the VCPU to add to the VM. - * guest_code - The vCPU's entry point */ -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code); +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code); static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, void *guest_code) { - return vm_arch_vcpu_add(vm, vcpu_id, guest_code); + struct kvm_vcpu *vcpu = vm_arch_vcpu_add(vm, vcpu_id); + + vcpu_arch_set_entry_point(vcpu, guest_code); + + return vcpu; } /* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */ @@ -1081,4 +1128,8 @@ void kvm_selftest_arch_init(void); void kvm_arch_vm_post_create(struct kvm_vm *vm); +bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr); + +uint32_t guest_get_vcpuid(void); + #endif /* SELFTEST_KVM_UTIL_BASE_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/arch_timer.h b/tools/testing/selftests/kvm/include/riscv/arch_timer.h new file mode 100644 index 000000000000..225d81dad064 --- /dev/null +++ b/tools/testing/selftests/kvm/include/riscv/arch_timer.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * RISC-V Arch Timer(sstc) specific interface + * + * Copyright (c) 2024 Intel Corporation + */ + +#ifndef SELFTEST_KVM_ARCH_TIMER_H +#define SELFTEST_KVM_ARCH_TIMER_H + +#include <asm/csr.h> +#include <asm/vdso/processor.h> + +static unsigned long timer_freq; + +#define msec_to_cycles(msec) \ + ((timer_freq) * (uint64_t)(msec) / 1000) + +#define usec_to_cycles(usec) \ + ((timer_freq) * (uint64_t)(usec) / 1000000) + +#define cycles_to_usec(cycles) \ + ((uint64_t)(cycles) * 1000000 / (timer_freq)) + +static inline uint64_t timer_get_cycles(void) +{ + return csr_read(CSR_TIME); +} + +static inline void timer_set_cmp(uint64_t cval) +{ + csr_write(CSR_STIMECMP, cval); +} + +static inline uint64_t timer_get_cmp(void) +{ + return csr_read(CSR_STIMECMP); +} + +static inline void timer_irq_enable(void) +{ + csr_set(CSR_SIE, IE_TIE); +} + +static inline void timer_irq_disable(void) +{ + csr_clear(CSR_SIE, IE_TIE); +} + +static inline void timer_set_next_cmp_ms(uint32_t msec) +{ + uint64_t now_ct = timer_get_cycles(); + uint64_t next_ct = now_ct + msec_to_cycles(msec); + + timer_set_cmp(next_ct); +} + +static inline void __delay(uint64_t cycles) +{ + uint64_t start = timer_get_cycles(); + + while ((timer_get_cycles() - start) < cycles) + cpu_relax(); +} + +static inline void udelay(unsigned long usec) +{ + __delay(usec_to_cycles(usec)); +} + +#endif /* SELFTEST_KVM_ARCH_TIMER_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h b/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h new file mode 100644 index 000000000000..e43a57d99b56 --- /dev/null +++ b/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_ARCH_H +#define SELFTEST_KVM_UTIL_ARCH_H + +struct kvm_vm_arch {}; + +#endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index a0f9efe5a2a8..ce473fe251dd 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -7,8 +7,9 @@ #ifndef SELFTEST_KVM_PROCESSOR_H #define SELFTEST_KVM_PROCESSOR_H -#include "kvm_util.h" #include <linux/stringify.h> +#include <asm/csr.h> +#include "kvm_util.h" static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype, uint64_t idx, uint64_t size) @@ -47,6 +48,58 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype, KVM_REG_RISCV_SBI_SINGLE, \ idx, KVM_REG_SIZE_ULONG) +bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext); + +struct ex_regs { + unsigned long ra; + unsigned long sp; + unsigned long gp; + unsigned long tp; + unsigned long t0; + unsigned long t1; + unsigned long t2; + unsigned long s0; + unsigned long s1; + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; + unsigned long s2; + unsigned long s3; + unsigned long s4; + unsigned long s5; + unsigned long s6; + unsigned long s7; + unsigned long s8; + unsigned long s9; + unsigned long s10; + unsigned long s11; + unsigned long t3; + unsigned long t4; + unsigned long t5; + unsigned long t6; + unsigned long epc; + unsigned long status; + unsigned long cause; +}; + +#define NR_VECTORS 2 +#define NR_EXCEPTIONS 32 +#define EC_MASK (NR_EXCEPTIONS - 1) + +typedef void(*exception_handler_fn)(struct ex_regs *); + +void vm_init_vector_tables(struct kvm_vm *vm); +void vcpu_init_vector_tables(struct kvm_vcpu *vcpu); + +void vm_install_exception_handler(struct kvm_vm *vm, int vector, exception_handler_fn handler); + +void vm_install_interrupt_handler(struct kvm_vm *vm, exception_handler_fn handler); + /* L3 index Bit[47:39] */ #define PGTBL_L3_INDEX_MASK 0x0000FF8000000000ULL #define PGTBL_L3_INDEX_SHIFT 39 @@ -101,13 +154,6 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype, #define PGTBL_PAGE_SIZE PGTBL_L0_BLOCK_SIZE #define PGTBL_PAGE_SIZE_SHIFT PGTBL_L0_BLOCK_SHIFT -#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL) -#define SATP_MODE_39 _AC(0x8000000000000000, UL) -#define SATP_MODE_48 _AC(0x9000000000000000, UL) -#define SATP_ASID_BITS 16 -#define SATP_ASID_SHIFT 44 -#define SATP_ASID_MASK _AC(0xFFFF, UL) - /* SBI return error codes */ #define SBI_SUCCESS 0 #define SBI_ERR_FAILURE -1 @@ -147,4 +193,14 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, bool guest_sbi_probe_extension(int extid, long *out_val); +static inline void local_irq_enable(void) +{ + csr_set(CSR_SSTATUS, SR_SIE); +} + +static inline void local_irq_disable(void) +{ + csr_clear(CSR_SSTATUS, SR_SIE); +} + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h b/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h new file mode 100644 index 000000000000..e43a57d99b56 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_ARCH_H +#define SELFTEST_KVM_UTIL_ARCH_H + +struct kvm_vm_arch {}; + +#endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h index 12a9a4b9cead..bc760761e1a3 100644 --- a/tools/testing/selftests/kvm/include/sparsebit.h +++ b/tools/testing/selftests/kvm/include/sparsebit.h @@ -30,26 +30,26 @@ typedef uint64_t sparsebit_num_t; struct sparsebit *sparsebit_alloc(void); void sparsebit_free(struct sparsebit **sbitp); -void sparsebit_copy(struct sparsebit *dstp, struct sparsebit *src); +void sparsebit_copy(struct sparsebit *dstp, const struct sparsebit *src); -bool sparsebit_is_set(struct sparsebit *sbit, sparsebit_idx_t idx); -bool sparsebit_is_set_num(struct sparsebit *sbit, +bool sparsebit_is_set(const struct sparsebit *sbit, sparsebit_idx_t idx); +bool sparsebit_is_set_num(const struct sparsebit *sbit, sparsebit_idx_t idx, sparsebit_num_t num); -bool sparsebit_is_clear(struct sparsebit *sbit, sparsebit_idx_t idx); -bool sparsebit_is_clear_num(struct sparsebit *sbit, +bool sparsebit_is_clear(const struct sparsebit *sbit, sparsebit_idx_t idx); +bool sparsebit_is_clear_num(const struct sparsebit *sbit, sparsebit_idx_t idx, sparsebit_num_t num); -sparsebit_num_t sparsebit_num_set(struct sparsebit *sbit); -bool sparsebit_any_set(struct sparsebit *sbit); -bool sparsebit_any_clear(struct sparsebit *sbit); -bool sparsebit_all_set(struct sparsebit *sbit); -bool sparsebit_all_clear(struct sparsebit *sbit); -sparsebit_idx_t sparsebit_first_set(struct sparsebit *sbit); -sparsebit_idx_t sparsebit_first_clear(struct sparsebit *sbit); -sparsebit_idx_t sparsebit_next_set(struct sparsebit *sbit, sparsebit_idx_t prev); -sparsebit_idx_t sparsebit_next_clear(struct sparsebit *sbit, sparsebit_idx_t prev); -sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *sbit, +sparsebit_num_t sparsebit_num_set(const struct sparsebit *sbit); +bool sparsebit_any_set(const struct sparsebit *sbit); +bool sparsebit_any_clear(const struct sparsebit *sbit); +bool sparsebit_all_set(const struct sparsebit *sbit); +bool sparsebit_all_clear(const struct sparsebit *sbit); +sparsebit_idx_t sparsebit_first_set(const struct sparsebit *sbit); +sparsebit_idx_t sparsebit_first_clear(const struct sparsebit *sbit); +sparsebit_idx_t sparsebit_next_set(const struct sparsebit *sbit, sparsebit_idx_t prev); +sparsebit_idx_t sparsebit_next_clear(const struct sparsebit *sbit, sparsebit_idx_t prev); +sparsebit_idx_t sparsebit_next_set_num(const struct sparsebit *sbit, sparsebit_idx_t start, sparsebit_num_t num); -sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *sbit, +sparsebit_idx_t sparsebit_next_clear_num(const struct sparsebit *sbit, sparsebit_idx_t start, sparsebit_num_t num); void sparsebit_set(struct sparsebit *sbitp, sparsebit_idx_t idx); @@ -62,9 +62,29 @@ void sparsebit_clear_num(struct sparsebit *sbitp, sparsebit_idx_t start, sparsebit_num_t num); void sparsebit_clear_all(struct sparsebit *sbitp); -void sparsebit_dump(FILE *stream, struct sparsebit *sbit, +void sparsebit_dump(FILE *stream, const struct sparsebit *sbit, unsigned int indent); -void sparsebit_validate_internal(struct sparsebit *sbit); +void sparsebit_validate_internal(const struct sparsebit *sbit); + +/* + * Iterate over an inclusive ranges within sparsebit @s. In each iteration, + * @range_begin and @range_end will take the beginning and end of the set + * range, which are of type sparsebit_idx_t. + * + * For example, if the range [3, 7] (inclusive) is set, within the + * iteration,@range_begin will take the value 3 and @range_end will take + * the value 7. + * + * Ensure that there is at least one bit set before using this macro with + * sparsebit_any_set(), because sparsebit_first_set() will abort if none + * are set. + */ +#define sparsebit_for_each_set_range(s, range_begin, range_end) \ + for (range_begin = sparsebit_first_set(s), \ + range_end = sparsebit_next_clear(s, range_begin) - 1; \ + range_begin && range_end; \ + range_begin = sparsebit_next_set(s, range_end), \ + range_end = sparsebit_next_clear(s, range_begin) - 1) #ifdef __cplusplus } diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 50a5e31ba8da..8a6e30612c86 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -20,6 +20,8 @@ #include <sys/mman.h> #include "kselftest.h" +#define msecs_to_usecs(msec) ((msec) * 1000ULL) + static inline int _no_printf(const char *format, ...) { return 0; } #ifdef DEBUG diff --git a/tools/testing/selftests/kvm/include/timer_test.h b/tools/testing/selftests/kvm/include/timer_test.h new file mode 100644 index 000000000000..9b6edaafe6d4 --- /dev/null +++ b/tools/testing/selftests/kvm/include/timer_test.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * timer test specific header + * + * Copyright (C) 2018, Google LLC + */ + +#ifndef SELFTEST_KVM_TIMER_TEST_H +#define SELFTEST_KVM_TIMER_TEST_H + +#include "kvm_util.h" + +#define NR_VCPUS_DEF 4 +#define NR_TEST_ITERS_DEF 5 +#define TIMER_TEST_PERIOD_MS_DEF 10 +#define TIMER_TEST_ERR_MARGIN_US 100 +#define TIMER_TEST_MIGRATION_FREQ_MS 2 + +/* Timer test cmdline parameters */ +struct test_args { + uint32_t nr_vcpus; + uint32_t nr_iter; + uint32_t timer_period_ms; + uint32_t migration_freq_ms; + uint32_t timer_err_margin_us; + /* Members of struct kvm_arm_counter_offset */ + uint64_t counter_offset; + uint64_t reserved; +}; + +/* Shared variables between host and guest */ +struct test_vcpu_shared_data { + uint32_t nr_iter; + int guest_stage; + uint64_t xcnt; +}; + +extern struct test_args test_args; +extern struct kvm_vcpu *vcpus[]; +extern struct test_vcpu_shared_data vcpu_shared_data[]; + +struct kvm_vm *test_vm_create(void); +void test_vm_cleanup(struct kvm_vm *vm); + +#endif /* SELFTEST_KVM_TIMER_TEST_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h new file mode 100644 index 000000000000..9f1725192aa2 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_ARCH_H +#define SELFTEST_KVM_UTIL_ARCH_H + +#include <stdbool.h> +#include <stdint.h> + +struct kvm_vm_arch { + uint64_t c_bit; + uint64_t s_bit; + int sev_fd; + bool is_pt_protected; +}; + +static inline bool __vm_arch_has_protected_memory(struct kvm_vm_arch *arch) +{ + return arch->c_bit || arch->s_bit; +} + +#define vm_arch_has_protected_memory(vm) \ + __vm_arch_has_protected_memory(&(vm)->arch) + +#endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/x86_64/pmu.h b/tools/testing/selftests/kvm/include/x86_64/pmu.h new file mode 100644 index 000000000000..3c10c4dc0ae8 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/pmu.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023, Tencent, Inc. + */ +#ifndef SELFTEST_KVM_PMU_H +#define SELFTEST_KVM_PMU_H + +#include <stdint.h> + +#define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300 + +/* + * Encode an eventsel+umask pair into event-select MSR format. Note, this is + * technically AMD's format, as Intel's format only supports 8 bits for the + * event selector, i.e. doesn't use bits 24:16 for the selector. But, OR-ing + * in '0' is a nop and won't clobber the CMASK. + */ +#define RAW_EVENT(eventsel, umask) (((eventsel & 0xf00UL) << 24) | \ + ((eventsel) & 0xff) | \ + ((umask) & 0xff) << 8) + +/* + * These are technically Intel's definitions, but except for CMASK (see above), + * AMD's layout is compatible with Intel's. + */ +#define ARCH_PERFMON_EVENTSEL_EVENT GENMASK_ULL(7, 0) +#define ARCH_PERFMON_EVENTSEL_UMASK GENMASK_ULL(15, 8) +#define ARCH_PERFMON_EVENTSEL_USR BIT_ULL(16) +#define ARCH_PERFMON_EVENTSEL_OS BIT_ULL(17) +#define ARCH_PERFMON_EVENTSEL_EDGE BIT_ULL(18) +#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL BIT_ULL(19) +#define ARCH_PERFMON_EVENTSEL_INT BIT_ULL(20) +#define ARCH_PERFMON_EVENTSEL_ANY BIT_ULL(21) +#define ARCH_PERFMON_EVENTSEL_ENABLE BIT_ULL(22) +#define ARCH_PERFMON_EVENTSEL_INV BIT_ULL(23) +#define ARCH_PERFMON_EVENTSEL_CMASK GENMASK_ULL(31, 24) + +/* RDPMC control flags, Intel only. */ +#define INTEL_RDPMC_METRICS BIT_ULL(29) +#define INTEL_RDPMC_FIXED BIT_ULL(30) +#define INTEL_RDPMC_FAST BIT_ULL(31) + +/* Fixed PMC controls, Intel only. */ +#define FIXED_PMC_GLOBAL_CTRL_ENABLE(_idx) BIT_ULL((32 + (_idx))) + +#define FIXED_PMC_KERNEL BIT_ULL(0) +#define FIXED_PMC_USER BIT_ULL(1) +#define FIXED_PMC_ANYTHREAD BIT_ULL(2) +#define FIXED_PMC_ENABLE_PMI BIT_ULL(3) +#define FIXED_PMC_NR_BITS 4 +#define FIXED_PMC_CTRL(_idx, _val) ((_val) << ((_idx) * FIXED_PMC_NR_BITS)) + +#define PMU_CAP_FW_WRITES BIT_ULL(13) +#define PMU_CAP_LBR_FMT 0x3f + +#define INTEL_ARCH_CPU_CYCLES RAW_EVENT(0x3c, 0x00) +#define INTEL_ARCH_INSTRUCTIONS_RETIRED RAW_EVENT(0xc0, 0x00) +#define INTEL_ARCH_REFERENCE_CYCLES RAW_EVENT(0x3c, 0x01) +#define INTEL_ARCH_LLC_REFERENCES RAW_EVENT(0x2e, 0x4f) +#define INTEL_ARCH_LLC_MISSES RAW_EVENT(0x2e, 0x41) +#define INTEL_ARCH_BRANCHES_RETIRED RAW_EVENT(0xc4, 0x00) +#define INTEL_ARCH_BRANCHES_MISPREDICTED RAW_EVENT(0xc5, 0x00) +#define INTEL_ARCH_TOPDOWN_SLOTS RAW_EVENT(0xa4, 0x01) + +#define AMD_ZEN_CORE_CYCLES RAW_EVENT(0x76, 0x00) +#define AMD_ZEN_INSTRUCTIONS_RETIRED RAW_EVENT(0xc0, 0x00) +#define AMD_ZEN_BRANCHES_RETIRED RAW_EVENT(0xc2, 0x00) +#define AMD_ZEN_BRANCHES_MISPREDICTED RAW_EVENT(0xc3, 0x00) + +/* + * Note! The order and thus the index of the architectural events matters as + * support for each event is enumerated via CPUID using the index of the event. + */ +enum intel_pmu_architectural_events { + INTEL_ARCH_CPU_CYCLES_INDEX, + INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX, + INTEL_ARCH_REFERENCE_CYCLES_INDEX, + INTEL_ARCH_LLC_REFERENCES_INDEX, + INTEL_ARCH_LLC_MISSES_INDEX, + INTEL_ARCH_BRANCHES_RETIRED_INDEX, + INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX, + INTEL_ARCH_TOPDOWN_SLOTS_INDEX, + NR_INTEL_ARCH_EVENTS, +}; + +enum amd_pmu_zen_events { + AMD_ZEN_CORE_CYCLES_INDEX, + AMD_ZEN_INSTRUCTIONS_INDEX, + AMD_ZEN_BRANCHES_INDEX, + AMD_ZEN_BRANCH_MISSES_INDEX, + NR_AMD_ZEN_EVENTS, +}; + +extern const uint64_t intel_pmu_arch_events[]; +extern const uint64_t amd_pmu_zen_events[]; + +#endif /* SELFTEST_KVM_PMU_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 5bca8c947c82..3bd03b088dda 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -23,6 +23,15 @@ extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; +enum vm_guest_x86_subtype { + VM_SUBTYPE_NONE = 0, + VM_SUBTYPE_SEV, + VM_SUBTYPE_SEV_ES, +}; + +/* Forced emulation prefix, used to invoke the emulator unconditionally. */ +#define KVM_FEP "ud2; .byte 'k', 'v', 'm';" + #define NMI_VECTOR 0x02 #define X86_EFLAGS_FIXED (1u << 1) @@ -273,6 +282,7 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_MAX_EXT_LEAF KVM_X86_CPU_PROPERTY(0x80000000, 0, EAX, 0, 31) #define X86_PROPERTY_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 0, 7) #define X86_PROPERTY_MAX_VIRT_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 8, 15) +#define X86_PROPERTY_SEV_C_BIT KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 0, 5) #define X86_PROPERTY_PHYS_ADDR_REDUCTION KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11) #define X86_PROPERTY_MAX_CENTAUR_LEAF KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31) @@ -282,24 +292,41 @@ struct kvm_x86_cpu_property { * that indicates the feature is _not_ supported, and a property that states * the length of the bit mask of unsupported features. A feature is supported * if the size of the bit mask is larger than the "unavailable" bit, and said - * bit is not set. + * bit is not set. Fixed counters also bizarre enumeration, but inverted from + * arch events for general purpose counters. Fixed counters are supported if a + * feature flag is set **OR** the total number of fixed counters is greater + * than index of the counter. * - * Wrap the "unavailable" feature to simplify checking whether or not a given - * architectural event is supported. + * Wrap the events for general purpose and fixed counters to simplify checking + * whether or not a given architectural event is supported. */ struct kvm_x86_pmu_feature { - struct kvm_x86_cpu_feature anti_feature; + struct kvm_x86_cpu_feature f; }; -#define KVM_X86_PMU_FEATURE(name, __bit) \ -({ \ - struct kvm_x86_pmu_feature feature = { \ - .anti_feature = KVM_X86_CPU_FEATURE(0xa, 0, EBX, __bit), \ - }; \ - \ - feature; \ +#define KVM_X86_PMU_FEATURE(__reg, __bit) \ +({ \ + struct kvm_x86_pmu_feature feature = { \ + .f = KVM_X86_CPU_FEATURE(0xa, 0, __reg, __bit), \ + }; \ + \ + kvm_static_assert(KVM_CPUID_##__reg == KVM_CPUID_EBX || \ + KVM_CPUID_##__reg == KVM_CPUID_ECX); \ + feature; \ }) -#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(BRANCH_INSNS_RETIRED, 5) +#define X86_PMU_FEATURE_CPU_CYCLES KVM_X86_PMU_FEATURE(EBX, 0) +#define X86_PMU_FEATURE_INSNS_RETIRED KVM_X86_PMU_FEATURE(EBX, 1) +#define X86_PMU_FEATURE_REFERENCE_CYCLES KVM_X86_PMU_FEATURE(EBX, 2) +#define X86_PMU_FEATURE_LLC_REFERENCES KVM_X86_PMU_FEATURE(EBX, 3) +#define X86_PMU_FEATURE_LLC_MISSES KVM_X86_PMU_FEATURE(EBX, 4) +#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(EBX, 5) +#define X86_PMU_FEATURE_BRANCHES_MISPREDICTED KVM_X86_PMU_FEATURE(EBX, 6) +#define X86_PMU_FEATURE_TOPDOWN_SLOTS KVM_X86_PMU_FEATURE(EBX, 7) + +#define X86_PMU_FEATURE_INSNS_RETIRED_FIXED KVM_X86_PMU_FEATURE(ECX, 0) +#define X86_PMU_FEATURE_CPU_CYCLES_FIXED KVM_X86_PMU_FEATURE(ECX, 1) +#define X86_PMU_FEATURE_REFERENCE_TSC_CYCLES_FIXED KVM_X86_PMU_FEATURE(ECX, 2) +#define X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED KVM_X86_PMU_FEATURE(ECX, 3) static inline unsigned int x86_family(unsigned int eax) { @@ -698,10 +725,16 @@ static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + uint32_t nr_bits; - return nr_bits > feature.anti_feature.bit && - !this_cpu_has(feature.anti_feature); + if (feature.f.reg == KVM_CPUID_EBX) { + nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + return nr_bits > feature.f.bit && !this_cpu_has(feature.f); + } + + GUEST_ASSERT(feature.f.reg == KVM_CPUID_ECX); + nr_bits = this_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + return nr_bits > feature.f.bit || this_cpu_has(feature.f); } static __always_inline uint64_t this_cpu_supported_xcr0(void) @@ -917,10 +950,16 @@ static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + uint32_t nr_bits; - return nr_bits > feature.anti_feature.bit && - !kvm_cpu_has(feature.anti_feature); + if (feature.f.reg == KVM_CPUID_EBX) { + nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + return nr_bits > feature.f.bit && !kvm_cpu_has(feature.f); + } + + TEST_ASSERT_EQ(feature.f.reg, KVM_CPUID_ECX); + nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + return nr_bits > feature.f.bit || kvm_cpu_has(feature.f); } static __always_inline uint64_t kvm_cpu_supported_xcr0(void) @@ -995,7 +1034,9 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); } -void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr); +void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_property property, + uint32_t value); void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function); void vcpu_set_or_clear_cpuid_feature(struct kvm_vcpu *vcpu, @@ -1059,6 +1100,7 @@ do { \ } while (0) void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); +void kvm_init_vm_address_properties(struct kvm_vm *vm); bool vm_is_unrestricted_guest(struct kvm_vm *vm); struct ex_regs { @@ -1120,16 +1162,19 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, * r9 = exception vector (non-zero) * r10 = error code */ -#define KVM_ASM_SAFE(insn) \ +#define __KVM_ASM_SAFE(insn, fep) \ "mov $" __stringify(KVM_EXCEPTION_MAGIC) ", %%r9\n\t" \ "lea 1f(%%rip), %%r10\n\t" \ "lea 2f(%%rip), %%r11\n\t" \ - "1: " insn "\n\t" \ + fep "1: " insn "\n\t" \ "xor %%r9, %%r9\n\t" \ "2:\n\t" \ "mov %%r9b, %[vector]\n\t" \ "mov %%r10, %[error_code]\n\t" +#define KVM_ASM_SAFE(insn) __KVM_ASM_SAFE(insn, "") +#define KVM_ASM_SAFE_FEP(insn) __KVM_ASM_SAFE(insn, KVM_FEP) + #define KVM_ASM_SAFE_OUTPUTS(v, ec) [vector] "=qm"(v), [error_code] "=rm"(ec) #define KVM_ASM_SAFE_CLOBBERS "r9", "r10", "r11" @@ -1156,21 +1201,58 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, vector; \ }) -static inline uint8_t rdmsr_safe(uint32_t msr, uint64_t *val) -{ - uint64_t error_code; - uint8_t vector; - uint32_t a, d; +#define kvm_asm_safe_fep(insn, inputs...) \ +({ \ + uint64_t ign_error_code; \ + uint8_t vector; \ + \ + asm volatile(KVM_ASM_SAFE(insn) \ + : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ + : inputs \ + : KVM_ASM_SAFE_CLOBBERS); \ + vector; \ +}) - asm volatile(KVM_ASM_SAFE("rdmsr") - : "=a"(a), "=d"(d), KVM_ASM_SAFE_OUTPUTS(vector, error_code) - : "c"(msr) - : KVM_ASM_SAFE_CLOBBERS); +#define kvm_asm_safe_ec_fep(insn, error_code, inputs...) \ +({ \ + uint8_t vector; \ + \ + asm volatile(KVM_ASM_SAFE_FEP(insn) \ + : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ + : inputs \ + : KVM_ASM_SAFE_CLOBBERS); \ + vector; \ +}) - *val = (uint64_t)a | ((uint64_t)d << 32); - return vector; +#define BUILD_READ_U64_SAFE_HELPER(insn, _fep, _FEP) \ +static inline uint8_t insn##_safe ##_fep(uint32_t idx, uint64_t *val) \ +{ \ + uint64_t error_code; \ + uint8_t vector; \ + uint32_t a, d; \ + \ + asm volatile(KVM_ASM_SAFE##_FEP(#insn) \ + : "=a"(a), "=d"(d), \ + KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ + : "c"(idx) \ + : KVM_ASM_SAFE_CLOBBERS); \ + \ + *val = (uint64_t)a | ((uint64_t)d << 32); \ + return vector; \ } +/* + * Generate {insn}_safe() and {insn}_safe_fep() helpers for instructions that + * use ECX as in input index, and EDX:EAX as a 64-bit output. + */ +#define BUILD_READ_U64_SAFE_HELPERS(insn) \ + BUILD_READ_U64_SAFE_HELPER(insn, , ) \ + BUILD_READ_U64_SAFE_HELPER(insn, _fep, _FEP) \ + +BUILD_READ_U64_SAFE_HELPERS(rdmsr) +BUILD_READ_U64_SAFE_HELPERS(rdpmc) +BUILD_READ_U64_SAFE_HELPERS(xgetbv) + static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val) { return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr)); @@ -1186,6 +1268,16 @@ static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value) bool kvm_is_tdp_enabled(void); +static inline bool kvm_is_pmu_enabled(void) +{ + return get_kvm_param_bool("enable_pmu"); +} + +static inline bool kvm_is_forced_emulation_enabled(void) +{ + return !!get_kvm_param_integer("force_emulation_prefix"); +} + uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, int *level); uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr); diff --git a/tools/testing/selftests/kvm/include/x86_64/sev.h b/tools/testing/selftests/kvm/include/x86_64/sev.h new file mode 100644 index 000000000000..8a1bf88474c9 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/sev.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Helpers used for SEV guests + * + */ +#ifndef SELFTEST_KVM_SEV_H +#define SELFTEST_KVM_SEV_H + +#include <stdint.h> +#include <stdbool.h> + +#include "linux/psp-sev.h" + +#include "kvm_util.h" +#include "svm_util.h" +#include "processor.h" + +enum sev_guest_state { + SEV_GUEST_STATE_UNINITIALIZED = 0, + SEV_GUEST_STATE_LAUNCH_UPDATE, + SEV_GUEST_STATE_LAUNCH_SECRET, + SEV_GUEST_STATE_RUNNING, +}; + +#define SEV_POLICY_NO_DBG (1UL << 0) +#define SEV_POLICY_ES (1UL << 2) + +#define GHCB_MSR_TERM_REQ 0x100 + +void sev_vm_launch(struct kvm_vm *vm, uint32_t policy); +void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement); +void sev_vm_launch_finish(struct kvm_vm *vm); + +struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t policy, void *guest_code, + struct kvm_vcpu **cpu); + +kvm_static_assert(SEV_RET_SUCCESS == 0); + +/* + * The KVM_MEMORY_ENCRYPT_OP uAPI is utter garbage and takes an "unsigned long" + * instead of a proper struct. The size of the parameter is embedded in the + * ioctl number, i.e. is ABI and thus immutable. Hack around the mess by + * creating an overlay to pass in an "unsigned long" without a cast (casting + * will make the compiler unhappy due to dereferencing an aliased pointer). + */ +#define __vm_sev_ioctl(vm, cmd, arg) \ +({ \ + int r; \ + \ + union { \ + struct kvm_sev_cmd c; \ + unsigned long raw; \ + } sev_cmd = { .c = { \ + .id = (cmd), \ + .data = (uint64_t)(arg), \ + .sev_fd = (vm)->arch.sev_fd, \ + } }; \ + \ + r = __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_OP, &sev_cmd.raw); \ + r ?: sev_cmd.c.error; \ +}) + +#define vm_sev_ioctl(vm, cmd, arg) \ +({ \ + int ret = __vm_sev_ioctl(vm, cmd, arg); \ + \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm); \ +}) + +static inline void sev_vm_init(struct kvm_vm *vm) +{ + vm->arch.sev_fd = open_sev_dev_path_or_exit(); + + vm_sev_ioctl(vm, KVM_SEV_INIT, NULL); +} + + +static inline void sev_es_vm_init(struct kvm_vm *vm) +{ + vm->arch.sev_fd = open_sev_dev_path_or_exit(); + + vm_sev_ioctl(vm, KVM_SEV_ES_INIT, NULL); +} + +static inline void sev_register_encrypted_memory(struct kvm_vm *vm, + struct userspace_mem_region *region) +{ + struct kvm_enc_region range = { + .addr = region->region.userspace_addr, + .size = region->region.memory_size, + }; + + vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); +} + +static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa, + uint64_t size) +{ + struct kvm_sev_launch_update_data update_data = { + .uaddr = (unsigned long)addr_gpa2hva(vm, gpa), + .len = size, + }; + + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_DATA, &update_data); +} + +#endif /* SELFTEST_KVM_SEV_H */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 43b9a7283360..a9eb17295be4 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -365,8 +365,13 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) indent, "", pstate, pc); } -struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - struct kvm_vcpu_init *init, void *guest_code) +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) +{ + vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); +} + +static struct kvm_vcpu *__aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_vcpu_init *init) { size_t stack_size; uint64_t stack_vaddr; @@ -381,15 +386,22 @@ struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, aarch64_vcpu_setup(vcpu, init); vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size); - vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); + return vcpu; +} + +struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_vcpu_init *init, void *guest_code) +{ + struct kvm_vcpu *vcpu = __aarch64_vcpu_add(vm, vcpu_id, init); + + vcpu_arch_set_entry_point(vcpu, guest_code); return vcpu; } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { - return aarch64_vcpu_add(vm, vcpu_id, NULL, guest_code); + return __aarch64_vcpu_add(vm, vcpu_id, NULL); } void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 1b197426f29f..b2262b5fad9e 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -52,13 +52,13 @@ int open_kvm_dev_path_or_exit(void) return _open_kvm_dev_path_or_exit(O_RDONLY); } -static bool get_module_param_bool(const char *module_name, const char *param) +static ssize_t get_module_param(const char *module_name, const char *param, + void *buffer, size_t buffer_size) { const int path_size = 128; char path[path_size]; - char value; - ssize_t r; - int fd; + ssize_t bytes_read; + int fd, r; r = snprintf(path, path_size, "/sys/module/%s/parameters/%s", module_name, param); @@ -67,11 +67,46 @@ static bool get_module_param_bool(const char *module_name, const char *param) fd = open_path_or_exit(path, O_RDONLY); - r = read(fd, &value, 1); - TEST_ASSERT(r == 1, "read(%s) failed", path); + bytes_read = read(fd, buffer, buffer_size); + TEST_ASSERT(bytes_read > 0, "read(%s) returned %ld, wanted %ld bytes", + path, bytes_read, buffer_size); r = close(fd); TEST_ASSERT(!r, "close(%s) failed", path); + return bytes_read; +} + +static int get_module_param_integer(const char *module_name, const char *param) +{ + /* + * 16 bytes to hold a 64-bit value (1 byte per char), 1 byte for the + * NUL char, and 1 byte because the kernel sucks and inserts a newline + * at the end. + */ + char value[16 + 1 + 1]; + ssize_t r; + + memset(value, '\0', sizeof(value)); + + r = get_module_param(module_name, param, value, sizeof(value)); + TEST_ASSERT(value[r - 1] == '\n', + "Expected trailing newline, got char '%c'", value[r - 1]); + + /* + * Squash the newline, otherwise atoi_paranoid() will complain about + * trailing non-NUL characters in the string. + */ + value[r - 1] = '\0'; + return atoi_paranoid(value); +} + +static bool get_module_param_bool(const char *module_name, const char *param) +{ + char value; + ssize_t r; + + r = get_module_param(module_name, param, &value, sizeof(value)); + TEST_ASSERT_EQ(r, 1); if (value == 'Y') return true; @@ -96,6 +131,21 @@ bool get_kvm_amd_param_bool(const char *param) return get_module_param_bool("kvm_amd", param); } +int get_kvm_param_integer(const char *param) +{ + return get_module_param_integer("kvm", param); +} + +int get_kvm_intel_param_integer(const char *param) +{ + return get_module_param_integer("kvm_intel", param); +} + +int get_kvm_amd_param_integer(const char *param) +{ + return get_module_param_integer("kvm_amd", param); +} + /* * Capability * @@ -226,6 +276,7 @@ struct kvm_vm *____vm_create(struct vm_shape shape) vm->mode = shape.mode; vm->type = shape.type; + vm->subtype = shape.subtype; vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits; vm->va_bits = vm_guest_mode_params[vm->mode].va_bits; @@ -266,6 +317,7 @@ struct kvm_vm *____vm_create(struct vm_shape shape) case VM_MODE_PXXV48_4K: #ifdef __x86_64__ kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits); + kvm_init_vm_address_properties(vm); /* * Ignore KVM support for 5-level paging (vm->va_bits == 57), * it doesn't take effect unless a CR4.LA57 is set, which it @@ -666,6 +718,7 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); sparsebit_free(®ion->unused_phy_pages); + sparsebit_free(®ion->protected_phy_pages); ret = munmap(region->mmap_start, region->mmap_size); TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); if (region->fd >= 0) { @@ -1047,6 +1100,8 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, } region->unused_phy_pages = sparsebit_alloc(); + if (vm_arch_has_protected_memory(vm)) + region->protected_phy_pages = sparsebit_alloc(); sparsebit_set_num(region->unused_phy_pages, guest_paddr >> vm->page_shift, npages); region->region.slot = slot; @@ -1377,15 +1432,17 @@ va_found: return pgidx_start * vm->page_size; } -vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type) +static vm_vaddr_t ____vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type, + bool protected) { uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); virt_pgd_alloc(vm); - vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages, - KVM_UTIL_MIN_PFN * vm->page_size, - vm->memslots[type]); + vm_paddr_t paddr = __vm_phy_pages_alloc(vm, pages, + KVM_UTIL_MIN_PFN * vm->page_size, + vm->memslots[type], protected); /* * Find an unused range of virtual page addresses of at least @@ -1405,6 +1462,20 @@ vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, return vaddr_start; } +vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type) +{ + return ____vm_vaddr_alloc(vm, sz, vaddr_min, type, + vm_arch_has_protected_memory(vm)); +} + +vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type) +{ + return ____vm_vaddr_alloc(vm, sz, vaddr_min, type, false); +} + /* * VM Virtual Address Allocate * @@ -1527,6 +1598,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; + gpa = vm_untag_gpa(vm, gpa); + region = userspace_mem_region_find(vm, gpa, gpa); if (!region) { TEST_FAIL("No vm physical memory at 0x%lx", gpa); @@ -1873,6 +1946,10 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) region->host_mem); fprintf(stream, "%*sunused_phy_pages: ", indent + 2, ""); sparsebit_dump(stream, region->unused_phy_pages, 0); + if (region->protected_phy_pages) { + fprintf(stream, "%*sprotected_phy_pages: ", indent + 2, ""); + sparsebit_dump(stream, region->protected_phy_pages, 0); + } } fprintf(stream, "%*sMapped Virtual Pages:\n", indent, ""); sparsebit_dump(stream, vm->vpages_mapped, indent + 2); @@ -1974,6 +2051,7 @@ const char *exit_reason_str(unsigned int exit_reason) * num - number of pages * paddr_min - Physical address minimum * memslot - Memory region to allocate page from + * protected - True if the pages will be used as protected/private memory * * Output Args: None * @@ -1985,8 +2063,9 @@ const char *exit_reason_str(unsigned int exit_reason) * and their base address is returned. A TEST_ASSERT failure occurs if * not enough pages are available at or above paddr_min. */ -vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot) +vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot, + bool protected) { struct userspace_mem_region *region; sparsebit_idx_t pg, base; @@ -1999,8 +2078,10 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, paddr_min, vm->page_size); region = memslot2region(vm, memslot); - base = pg = paddr_min >> vm->page_shift; + TEST_ASSERT(!protected || region->protected_phy_pages, + "Region doesn't support protected memory"); + base = pg = paddr_min >> vm->page_shift; do { for (; pg < base + num; ++pg) { if (!sparsebit_is_set(region->unused_phy_pages, pg)) { @@ -2019,8 +2100,11 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, abort(); } - for (pg = base; pg < base + num; ++pg) + for (pg = base; pg < base + num; ++pg) { sparsebit_clear(region->unused_phy_pages, pg); + if (protected) + sparsebit_set(region->protected_phy_pages, pg); + } return base * vm->page_size; } @@ -2224,3 +2308,18 @@ void __attribute((constructor)) kvm_selftest_init(void) kvm_selftest_arch_init(); } + +bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr) +{ + sparsebit_idx_t pg = 0; + struct userspace_mem_region *region; + + if (!vm_arch_has_protected_memory(vm)) + return false; + + region = userspace_mem_region_find(vm, paddr, paddr); + TEST_ASSERT(region, "No vm physical memory at 0x%lx", paddr); + + pg = paddr >> vm->page_shift; + return sparsebit_is_set(region->protected_phy_pages, pg); +} diff --git a/tools/testing/selftests/kvm/lib/riscv/handlers.S b/tools/testing/selftests/kvm/lib/riscv/handlers.S new file mode 100644 index 000000000000..aa0abd3f35bb --- /dev/null +++ b/tools/testing/selftests/kvm/lib/riscv/handlers.S @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Intel Corporation + */ + +#ifndef __ASSEMBLY__ +#define __ASSEMBLY__ +#endif + +#include <asm/csr.h> + +.macro save_context + addi sp, sp, (-8*34) + sd x1, 0(sp) + sd x2, 8(sp) + sd x3, 16(sp) + sd x4, 24(sp) + sd x5, 32(sp) + sd x6, 40(sp) + sd x7, 48(sp) + sd x8, 56(sp) + sd x9, 64(sp) + sd x10, 72(sp) + sd x11, 80(sp) + sd x12, 88(sp) + sd x13, 96(sp) + sd x14, 104(sp) + sd x15, 112(sp) + sd x16, 120(sp) + sd x17, 128(sp) + sd x18, 136(sp) + sd x19, 144(sp) + sd x20, 152(sp) + sd x21, 160(sp) + sd x22, 168(sp) + sd x23, 176(sp) + sd x24, 184(sp) + sd x25, 192(sp) + sd x26, 200(sp) + sd x27, 208(sp) + sd x28, 216(sp) + sd x29, 224(sp) + sd x30, 232(sp) + sd x31, 240(sp) + csrr s0, CSR_SEPC + csrr s1, CSR_SSTATUS + csrr s2, CSR_SCAUSE + sd s0, 248(sp) + sd s1, 256(sp) + sd s2, 264(sp) +.endm + +.macro restore_context + ld s2, 264(sp) + ld s1, 256(sp) + ld s0, 248(sp) + csrw CSR_SCAUSE, s2 + csrw CSR_SSTATUS, s1 + csrw CSR_SEPC, s0 + ld x31, 240(sp) + ld x30, 232(sp) + ld x29, 224(sp) + ld x28, 216(sp) + ld x27, 208(sp) + ld x26, 200(sp) + ld x25, 192(sp) + ld x24, 184(sp) + ld x23, 176(sp) + ld x22, 168(sp) + ld x21, 160(sp) + ld x20, 152(sp) + ld x19, 144(sp) + ld x18, 136(sp) + ld x17, 128(sp) + ld x16, 120(sp) + ld x15, 112(sp) + ld x14, 104(sp) + ld x13, 96(sp) + ld x12, 88(sp) + ld x11, 80(sp) + ld x10, 72(sp) + ld x9, 64(sp) + ld x8, 56(sp) + ld x7, 48(sp) + ld x6, 40(sp) + ld x5, 32(sp) + ld x4, 24(sp) + ld x3, 16(sp) + ld x2, 8(sp) + ld x1, 0(sp) + addi sp, sp, (8*34) +.endm + +.balign 4 +.global exception_vectors +exception_vectors: + save_context + move a0, sp + call route_exception + restore_context + sret diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index 2bb33a8ac03c..e8211f5d6863 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -13,6 +13,18 @@ #define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000 +static vm_vaddr_t exception_handlers; + +bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext) +{ + unsigned long value = 0; + int ret; + + ret = __vcpu_get_reg(vcpu, ext, &value); + + return !ret && !!value; +} + static uint64_t page_align(struct kvm_vm *vm, uint64_t v) { return (v + vm->page_size) & ~(vm->page_size - 1); @@ -277,8 +289,12 @@ static void __aligned(16) guest_unexp_trap(void) 0, 0, 0, 0, 0, 0); } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code) +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) +{ + vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code); +} + +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { int r; size_t stack_size; @@ -312,7 +328,9 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, /* Setup stack pointer and program counter of guest */ vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.sp), stack_vaddr + stack_size); - vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code); + + /* Setup sscratch for guest_get_vcpuid() */ + vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(sscratch), vcpu_id); /* Setup default exception vector of guest */ vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(stvec), (unsigned long)guest_unexp_trap); @@ -364,8 +382,80 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) va_end(ap); } +void kvm_exit_unexpected_exception(int vector, int ec) +{ + ucall(UCALL_UNHANDLED, 2, vector, ec); +} + void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { + struct ucall uc; + + if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) { + TEST_FAIL("Unexpected exception (vector:0x%lx, ec:0x%lx)", + uc.args[0], uc.args[1]); + } +} + +struct handlers { + exception_handler_fn exception_handlers[NR_VECTORS][NR_EXCEPTIONS]; +}; + +void route_exception(struct ex_regs *regs) +{ + struct handlers *handlers = (struct handlers *)exception_handlers; + int vector = 0, ec; + + ec = regs->cause & ~CAUSE_IRQ_FLAG; + if (ec >= NR_EXCEPTIONS) + goto unexpected_exception; + + /* Use the same handler for all the interrupts */ + if (regs->cause & CAUSE_IRQ_FLAG) { + vector = 1; + ec = 0; + } + + if (handlers && handlers->exception_handlers[vector][ec]) + return handlers->exception_handlers[vector][ec](regs); + +unexpected_exception: + return kvm_exit_unexpected_exception(vector, ec); +} + +void vcpu_init_vector_tables(struct kvm_vcpu *vcpu) +{ + extern char exception_vectors; + + vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(stvec), (unsigned long)&exception_vectors); +} + +void vm_init_vector_tables(struct kvm_vm *vm) +{ + vm->handlers = __vm_vaddr_alloc(vm, sizeof(struct handlers), + vm->page_size, MEM_REGION_DATA); + + *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; +} + +void vm_install_exception_handler(struct kvm_vm *vm, int vector, exception_handler_fn handler) +{ + struct handlers *handlers = addr_gva2hva(vm, vm->handlers); + + assert(vector < NR_EXCEPTIONS); + handlers->exception_handlers[0][vector] = handler; +} + +void vm_install_interrupt_handler(struct kvm_vm *vm, exception_handler_fn handler) +{ + struct handlers *handlers = addr_gva2hva(vm, vm->handlers); + + handlers->exception_handlers[1][0] = handler; +} + +uint32_t guest_get_vcpuid(void) +{ + return csr_read(CSR_SSCRATCH); } struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index f6d227892cbc..4ad4492eea1d 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -155,15 +155,18 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) virt_dump_region(stream, vm, indent, vm->pgd); } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code) +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) +{ + vcpu->run->psw_addr = (uintptr_t)guest_code; +} + +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { size_t stack_size = DEFAULT_STACK_PGS * getpagesize(); uint64_t stack_vaddr; struct kvm_regs regs; struct kvm_sregs sregs; struct kvm_vcpu *vcpu; - struct kvm_run *run; TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", vm->page_size); @@ -184,9 +187,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, sregs.crs[1] = vm->pgd | 0xf; /* Primary region table */ vcpu_sregs_set(vcpu, &sregs); - run = vcpu->run; - run->psw_mask = 0x0400000180000000ULL; /* DAT enabled + 64 bit mode */ - run->psw_addr = (uintptr_t)guest_code; + vcpu->run->psw_mask = 0x0400000180000000ULL; /* DAT enabled + 64 bit mode */ return vcpu; } diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c index 88cb6b84e6f3..cfed9d26cc71 100644 --- a/tools/testing/selftests/kvm/lib/sparsebit.c +++ b/tools/testing/selftests/kvm/lib/sparsebit.c @@ -202,7 +202,7 @@ static sparsebit_num_t node_num_set(struct node *nodep) /* Returns a pointer to the node that describes the * lowest bit index. */ -static struct node *node_first(struct sparsebit *s) +static struct node *node_first(const struct sparsebit *s) { struct node *nodep; @@ -216,7 +216,7 @@ static struct node *node_first(struct sparsebit *s) * lowest bit index > the index of the node pointed to by np. * Returns NULL if no node with a higher index exists. */ -static struct node *node_next(struct sparsebit *s, struct node *np) +static struct node *node_next(const struct sparsebit *s, struct node *np) { struct node *nodep = np; @@ -244,7 +244,7 @@ static struct node *node_next(struct sparsebit *s, struct node *np) * highest index < the index of the node pointed to by np. * Returns NULL if no node with a lower index exists. */ -static struct node *node_prev(struct sparsebit *s, struct node *np) +static struct node *node_prev(const struct sparsebit *s, struct node *np) { struct node *nodep = np; @@ -273,7 +273,7 @@ static struct node *node_prev(struct sparsebit *s, struct node *np) * subtree and duplicates the bit settings to the newly allocated nodes. * Returns the newly allocated copy of subtree. */ -static struct node *node_copy_subtree(struct node *subtree) +static struct node *node_copy_subtree(const struct node *subtree) { struct node *root; @@ -307,7 +307,7 @@ static struct node *node_copy_subtree(struct node *subtree) * index is within the bits described by the mask bits or the number of * contiguous bits set after the mask. Returns NULL if there is no such node. */ -static struct node *node_find(struct sparsebit *s, sparsebit_idx_t idx) +static struct node *node_find(const struct sparsebit *s, sparsebit_idx_t idx) { struct node *nodep; @@ -393,7 +393,7 @@ static struct node *node_add(struct sparsebit *s, sparsebit_idx_t idx) } /* Returns whether all the bits in the sparsebit array are set. */ -bool sparsebit_all_set(struct sparsebit *s) +bool sparsebit_all_set(const struct sparsebit *s) { /* * If any nodes there must be at least one bit set. Only case @@ -775,7 +775,7 @@ static void node_reduce(struct sparsebit *s, struct node *nodep) /* Returns whether the bit at the index given by idx, within the * sparsebit array is set or not. */ -bool sparsebit_is_set(struct sparsebit *s, sparsebit_idx_t idx) +bool sparsebit_is_set(const struct sparsebit *s, sparsebit_idx_t idx) { struct node *nodep; @@ -921,7 +921,7 @@ static inline sparsebit_idx_t node_first_clear(struct node *nodep, int start) * used by test cases after they detect an unexpected condition, as a means * to capture diagnostic information. */ -static void sparsebit_dump_internal(FILE *stream, struct sparsebit *s, +static void sparsebit_dump_internal(FILE *stream, const struct sparsebit *s, unsigned int indent) { /* Dump the contents of s */ @@ -969,7 +969,7 @@ void sparsebit_free(struct sparsebit **sbitp) * sparsebit_alloc(). It can though already have bits set, which * if different from src will be cleared. */ -void sparsebit_copy(struct sparsebit *d, struct sparsebit *s) +void sparsebit_copy(struct sparsebit *d, const struct sparsebit *s) { /* First clear any bits already set in the destination */ sparsebit_clear_all(d); @@ -981,7 +981,7 @@ void sparsebit_copy(struct sparsebit *d, struct sparsebit *s) } /* Returns whether num consecutive bits starting at idx are all set. */ -bool sparsebit_is_set_num(struct sparsebit *s, +bool sparsebit_is_set_num(const struct sparsebit *s, sparsebit_idx_t idx, sparsebit_num_t num) { sparsebit_idx_t next_cleared; @@ -1005,14 +1005,14 @@ bool sparsebit_is_set_num(struct sparsebit *s, } /* Returns whether the bit at the index given by idx. */ -bool sparsebit_is_clear(struct sparsebit *s, +bool sparsebit_is_clear(const struct sparsebit *s, sparsebit_idx_t idx) { return !sparsebit_is_set(s, idx); } /* Returns whether num consecutive bits starting at idx are all cleared. */ -bool sparsebit_is_clear_num(struct sparsebit *s, +bool sparsebit_is_clear_num(const struct sparsebit *s, sparsebit_idx_t idx, sparsebit_num_t num) { sparsebit_idx_t next_set; @@ -1041,13 +1041,13 @@ bool sparsebit_is_clear_num(struct sparsebit *s, * value. Use sparsebit_any_set(), instead of sparsebit_num_set() > 0, * to determine if the sparsebit array has any bits set. */ -sparsebit_num_t sparsebit_num_set(struct sparsebit *s) +sparsebit_num_t sparsebit_num_set(const struct sparsebit *s) { return s->num_set; } /* Returns whether any bit is set in the sparsebit array. */ -bool sparsebit_any_set(struct sparsebit *s) +bool sparsebit_any_set(const struct sparsebit *s) { /* * Nodes only describe set bits. If any nodes then there @@ -1070,20 +1070,20 @@ bool sparsebit_any_set(struct sparsebit *s) } /* Returns whether all the bits in the sparsebit array are cleared. */ -bool sparsebit_all_clear(struct sparsebit *s) +bool sparsebit_all_clear(const struct sparsebit *s) { return !sparsebit_any_set(s); } /* Returns whether all the bits in the sparsebit array are set. */ -bool sparsebit_any_clear(struct sparsebit *s) +bool sparsebit_any_clear(const struct sparsebit *s) { return !sparsebit_all_set(s); } /* Returns the index of the first set bit. Abort if no bits are set. */ -sparsebit_idx_t sparsebit_first_set(struct sparsebit *s) +sparsebit_idx_t sparsebit_first_set(const struct sparsebit *s) { struct node *nodep; @@ -1097,7 +1097,7 @@ sparsebit_idx_t sparsebit_first_set(struct sparsebit *s) /* Returns the index of the first cleared bit. Abort if * no bits are cleared. */ -sparsebit_idx_t sparsebit_first_clear(struct sparsebit *s) +sparsebit_idx_t sparsebit_first_clear(const struct sparsebit *s) { struct node *nodep1, *nodep2; @@ -1151,7 +1151,7 @@ sparsebit_idx_t sparsebit_first_clear(struct sparsebit *s) /* Returns index of next bit set within s after the index given by prev. * Returns 0 if there are no bits after prev that are set. */ -sparsebit_idx_t sparsebit_next_set(struct sparsebit *s, +sparsebit_idx_t sparsebit_next_set(const struct sparsebit *s, sparsebit_idx_t prev) { sparsebit_idx_t lowest_possible = prev + 1; @@ -1244,7 +1244,7 @@ sparsebit_idx_t sparsebit_next_set(struct sparsebit *s, /* Returns index of next bit cleared within s after the index given by prev. * Returns 0 if there are no bits after prev that are cleared. */ -sparsebit_idx_t sparsebit_next_clear(struct sparsebit *s, +sparsebit_idx_t sparsebit_next_clear(const struct sparsebit *s, sparsebit_idx_t prev) { sparsebit_idx_t lowest_possible = prev + 1; @@ -1300,7 +1300,7 @@ sparsebit_idx_t sparsebit_next_clear(struct sparsebit *s, * and returns the index of the first sequence of num consecutively set * bits. Returns a value of 0 of no such sequence exists. */ -sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *s, +sparsebit_idx_t sparsebit_next_set_num(const struct sparsebit *s, sparsebit_idx_t start, sparsebit_num_t num) { sparsebit_idx_t idx; @@ -1335,7 +1335,7 @@ sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *s, * and returns the index of the first sequence of num consecutively cleared * bits. Returns a value of 0 of no such sequence exists. */ -sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *s, +sparsebit_idx_t sparsebit_next_clear_num(const struct sparsebit *s, sparsebit_idx_t start, sparsebit_num_t num) { sparsebit_idx_t idx; @@ -1583,7 +1583,7 @@ static size_t display_range(FILE *stream, sparsebit_idx_t low, * contiguous bits. This is done because '-' is used to specify command-line * options, and sometimes ranges are specified as command-line arguments. */ -void sparsebit_dump(FILE *stream, struct sparsebit *s, +void sparsebit_dump(FILE *stream, const struct sparsebit *s, unsigned int indent) { size_t current_line_len = 0; @@ -1681,7 +1681,7 @@ void sparsebit_dump(FILE *stream, struct sparsebit *s, * s. On error, diagnostic information is printed to stderr and * abort is called. */ -void sparsebit_validate_internal(struct sparsebit *s) +void sparsebit_validate_internal(const struct sparsebit *s) { bool error_detected = false; struct node *nodep, *prev = NULL; diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c index 816a3fa109bf..f5af65a41c29 100644 --- a/tools/testing/selftests/kvm/lib/ucall_common.c +++ b/tools/testing/selftests/kvm/lib/ucall_common.c @@ -29,7 +29,8 @@ void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) vm_vaddr_t vaddr; int i; - vaddr = __vm_vaddr_alloc(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR, MEM_REGION_DATA); + vaddr = vm_vaddr_alloc_shared(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR, + MEM_REGION_DATA); hdr = (struct ucall_header *)addr_gva2hva(vm, vaddr); memset(hdr, 0, sizeof(*hdr)); diff --git a/tools/testing/selftests/kvm/lib/x86_64/pmu.c b/tools/testing/selftests/kvm/lib/x86_64/pmu.c new file mode 100644 index 000000000000..f31f0427c17c --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/pmu.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023, Tencent, Inc. + */ + +#include <stdint.h> + +#include <linux/kernel.h> + +#include "kvm_util.h" +#include "pmu.h" + +const uint64_t intel_pmu_arch_events[] = { + INTEL_ARCH_CPU_CYCLES, + INTEL_ARCH_INSTRUCTIONS_RETIRED, + INTEL_ARCH_REFERENCE_CYCLES, + INTEL_ARCH_LLC_REFERENCES, + INTEL_ARCH_LLC_MISSES, + INTEL_ARCH_BRANCHES_RETIRED, + INTEL_ARCH_BRANCHES_MISPREDICTED, + INTEL_ARCH_TOPDOWN_SLOTS, +}; +kvm_static_assert(ARRAY_SIZE(intel_pmu_arch_events) == NR_INTEL_ARCH_EVENTS); + +const uint64_t amd_pmu_zen_events[] = { + AMD_ZEN_CORE_CYCLES, + AMD_ZEN_INSTRUCTIONS_RETIRED, + AMD_ZEN_BRANCHES_RETIRED, + AMD_ZEN_BRANCHES_MISPREDICTED, +}; +kvm_static_assert(ARRAY_SIZE(amd_pmu_zen_events) == NR_AMD_ZEN_EVENTS); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index f639b3e062e3..74a4c736c9ae 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -9,6 +9,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "sev.h" #ifndef NUM_INTERRUPTS #define NUM_INTERRUPTS 256 @@ -157,6 +158,8 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, { uint64_t *pte = virt_get_pte(vm, parent_pte, vaddr, current_level); + paddr = vm_untag_gpa(vm, paddr); + if (!(*pte & PTE_PRESENT_MASK)) { *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK; if (current_level == target_level) @@ -200,6 +203,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) "Physical address beyond maximum supported,\n" " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", paddr, vm->max_gfn, vm->page_size); + TEST_ASSERT(vm_untag_gpa(vm, paddr) == paddr, + "Unexpected bits in paddr: %lx", paddr); /* * Allocate upper level page tables, if not already present. Return @@ -222,6 +227,15 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) TEST_ASSERT(!(*pte & PTE_PRESENT_MASK), "PTE already present for 4k page at vaddr: 0x%lx", vaddr); *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK); + + /* + * Neither SEV nor TDX supports shared page tables, so only the final + * leaf PTE needs manually set the C/S-bit. + */ + if (vm_is_gpa_protected(vm, paddr)) + *pte |= vm->arch.c_bit; + else + *pte |= vm->arch.s_bit; } void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) @@ -265,6 +279,9 @@ uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, { uint64_t *pml4e, *pdpe, *pde; + TEST_ASSERT(!vm->arch.is_pt_protected, + "Walking page tables of protected guests is impossible"); + TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM, "Invalid PG_LEVEL_* '%d'", *level); @@ -496,7 +513,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) * No need for a hugepage mask on the PTE, x86-64 requires the "unused" * address bits to be zero. */ - return PTE_GET_PA(*pte) | (gva & ~HUGEPAGE_MASK(level)); + return vm_untag_gpa(vm, PTE_GET_PA(*pte)) | (gva & ~HUGEPAGE_MASK(level)); } static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt) @@ -560,10 +577,23 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm) vm_create_irqchip(vm); sync_global_to_guest(vm, host_cpu_is_intel); sync_global_to_guest(vm, host_cpu_is_amd); + + if (vm->subtype == VM_SUBTYPE_SEV) + sev_vm_init(vm); + else if (vm->subtype == VM_SUBTYPE_SEV_ES) + sev_es_vm_init(vm); +} + +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) +{ + struct kvm_regs regs; + + vcpu_regs_get(vcpu, ®s); + regs.rip = (unsigned long) guest_code; + vcpu_regs_set(vcpu, ®s); } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { struct kvm_mp_state mp_state; struct kvm_regs regs; @@ -597,7 +627,6 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, vcpu_regs_get(vcpu, ®s); regs.rflags = regs.rflags | 0x2; regs.rsp = stack_vaddr; - regs.rip = (unsigned long) guest_code; vcpu_regs_set(vcpu, ®s); /* Setup the MP state */ @@ -752,12 +781,21 @@ void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid) vcpu_set_cpuid(vcpu); } -void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr) +void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_property property, + uint32_t value) { - struct kvm_cpuid_entry2 *entry = vcpu_get_cpuid_entry(vcpu, 0x80000008); + struct kvm_cpuid_entry2 *entry; + + entry = __vcpu_get_cpuid_entry(vcpu, property.function, property.index); + + (&entry->eax)[property.reg] &= ~GENMASK(property.hi_bit, property.lo_bit); + (&entry->eax)[property.reg] |= value << property.lo_bit; - entry->eax = (entry->eax & ~0xff) | maxphyaddr; vcpu_set_cpuid(vcpu); + + /* Sanity check that @value doesn't exceed the bounds in any way. */ + TEST_ASSERT_EQ(kvm_cpuid_property(vcpu->cpuid, property), value); } void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function) @@ -1041,6 +1079,14 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) } } +void kvm_init_vm_address_properties(struct kvm_vm *vm) +{ + if (vm->subtype == VM_SUBTYPE_SEV || vm->subtype == VM_SUBTYPE_SEV_ES) { + vm->arch.c_bit = BIT_ULL(this_cpu_property(X86_PROPERTY_SEV_C_BIT)); + vm->gpa_tag_mask = vm->arch.c_bit; + } +} + static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, int dpl, unsigned short selector) { diff --git a/tools/testing/selftests/kvm/lib/x86_64/sev.c b/tools/testing/selftests/kvm/lib/x86_64/sev.c new file mode 100644 index 000000000000..e248d3364b9c --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/sev.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <stdint.h> +#include <stdbool.h> + +#include "sev.h" + +/* + * sparsebit_next_clear() can return 0 if [x, 2**64-1] are all set, and the + * -1 would then cause an underflow back to 2**64 - 1. This is expected and + * correct. + * + * If the last range in the sparsebit is [x, y] and we try to iterate, + * sparsebit_next_set() will return 0, and sparsebit_next_clear() will try + * and find the first range, but that's correct because the condition + * expression would cause us to quit the loop. + */ +static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *region) +{ + const struct sparsebit *protected_phy_pages = region->protected_phy_pages; + const vm_paddr_t gpa_base = region->region.guest_phys_addr; + const sparsebit_idx_t lowest_page_in_region = gpa_base >> vm->page_shift; + sparsebit_idx_t i, j; + + if (!sparsebit_any_set(protected_phy_pages)) + return; + + sev_register_encrypted_memory(vm, region); + + sparsebit_for_each_set_range(protected_phy_pages, i, j) { + const uint64_t size = (j - i + 1) * vm->page_size; + const uint64_t offset = (i - lowest_page_in_region) * vm->page_size; + + sev_launch_update_data(vm, gpa_base + offset, size); + } +} + +void sev_vm_launch(struct kvm_vm *vm, uint32_t policy) +{ + struct kvm_sev_launch_start launch_start = { + .policy = policy, + }; + struct userspace_mem_region *region; + struct kvm_sev_guest_status status; + int ctr; + + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_START, &launch_start); + vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status); + + TEST_ASSERT_EQ(status.policy, policy); + TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_LAUNCH_UPDATE); + + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) + encrypt_region(vm, region); + + if (policy & SEV_POLICY_ES) + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + + vm->arch.is_pt_protected = true; +} + +void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement) +{ + struct kvm_sev_launch_measure launch_measure; + struct kvm_sev_guest_status guest_status; + + launch_measure.len = 256; + launch_measure.uaddr = (__u64)measurement; + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_MEASURE, &launch_measure); + + vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &guest_status); + TEST_ASSERT_EQ(guest_status.state, SEV_GUEST_STATE_LAUNCH_SECRET); +} + +void sev_vm_launch_finish(struct kvm_vm *vm) +{ + struct kvm_sev_guest_status status; + + vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status); + TEST_ASSERT(status.state == SEV_GUEST_STATE_LAUNCH_UPDATE || + status.state == SEV_GUEST_STATE_LAUNCH_SECRET, + "Unexpected guest state: %d", status.state); + + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_FINISH, NULL); + + vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status); + TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_RUNNING); +} + +struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t policy, void *guest_code, + struct kvm_vcpu **cpu) +{ + struct vm_shape shape = { + .type = VM_TYPE_DEFAULT, + .mode = VM_MODE_DEFAULT, + .subtype = policy & SEV_POLICY_ES ? VM_SUBTYPE_SEV_ES : + VM_SUBTYPE_SEV, + }; + struct kvm_vm *vm; + struct kvm_vcpu *cpus[1]; + uint8_t measurement[512]; + + vm = __vm_create_with_vcpus(shape, 1, 0, guest_code, cpus); + *cpu = cpus[0]; + + sev_vm_launch(vm, policy); + + /* TODO: Validate the measurement is as expected. */ + sev_vm_launch_measure(vm, measurement); + + sev_vm_launch_finish(vm); + + return vm; +} diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c new file mode 100644 index 000000000000..e22848f747c0 --- /dev/null +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * arch_timer.c - Tests the riscv64 sstc timer IRQ functionality + * + * The test validates the sstc timer IRQs using vstimecmp registers. + * It's ported from the aarch64 arch_timer test. + * + * Copyright (c) 2024, Intel Corporation. + */ + +#define _GNU_SOURCE + +#include "arch_timer.h" +#include "kvm_util.h" +#include "processor.h" +#include "timer_test.h" + +static int timer_irq = IRQ_S_TIMER; + +static void guest_irq_handler(struct ex_regs *regs) +{ + uint64_t xcnt, xcnt_diff_us, cmp; + unsigned int intid = regs->cause & ~CAUSE_IRQ_FLAG; + uint32_t cpu = guest_get_vcpuid(); + struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; + + timer_irq_disable(); + + xcnt = timer_get_cycles(); + cmp = timer_get_cmp(); + xcnt_diff_us = cycles_to_usec(xcnt - shared_data->xcnt); + + /* Make sure we are dealing with the correct timer IRQ */ + GUEST_ASSERT_EQ(intid, timer_irq); + + __GUEST_ASSERT(xcnt >= cmp, + "xcnt = 0x%"PRIx64", cmp = 0x%"PRIx64", xcnt_diff_us = 0x%" PRIx64, + xcnt, cmp, xcnt_diff_us); + + WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1); +} + +static void guest_run(struct test_vcpu_shared_data *shared_data) +{ + uint32_t irq_iter, config_iter; + + shared_data->nr_iter = 0; + shared_data->guest_stage = 0; + + for (config_iter = 0; config_iter < test_args.nr_iter; config_iter++) { + /* Setup the next interrupt */ + timer_set_next_cmp_ms(test_args.timer_period_ms); + shared_data->xcnt = timer_get_cycles(); + timer_irq_enable(); + + /* Setup a timeout for the interrupt to arrive */ + udelay(msecs_to_usecs(test_args.timer_period_ms) + + test_args.timer_err_margin_us); + + irq_iter = READ_ONCE(shared_data->nr_iter); + __GUEST_ASSERT(config_iter + 1 == irq_iter, + "config_iter + 1 = 0x%x, irq_iter = 0x%x.\n" + " Guest timer interrupt was not trigged within the specified\n" + " interval, try to increase the error margin by [-e] option.\n", + config_iter + 1, irq_iter); + } +} + +static void guest_code(void) +{ + uint32_t cpu = guest_get_vcpuid(); + struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu]; + + timer_irq_disable(); + local_irq_enable(); + + guest_run(shared_data); + + GUEST_DONE(); +} + +struct kvm_vm *test_vm_create(void) +{ + struct kvm_vm *vm; + int nr_vcpus = test_args.nr_vcpus; + + vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus); + __TEST_REQUIRE(__vcpu_has_ext(vcpus[0], RISCV_ISA_EXT_REG(KVM_RISCV_ISA_EXT_SSTC)), + "SSTC not available, skipping test\n"); + + vm_init_vector_tables(vm); + vm_install_interrupt_handler(vm, guest_irq_handler); + + for (int i = 0; i < nr_vcpus; i++) + vcpu_init_vector_tables(vcpus[i]); + + /* Initialize guest timer frequency. */ + vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency), &timer_freq); + sync_global_to_guest(vm, timer_freq); + pr_debug("timer_freq: %lu\n", timer_freq); + + /* Make all the test's cmdline args visible to the guest */ + sync_global_to_guest(vm, test_args); + + return vm; +} + +void test_vm_cleanup(struct kvm_vm *vm) +{ + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 6435e7a65642..b882b7b9b785 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -47,6 +47,7 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZACAS: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBC: @@ -73,6 +74,7 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSED: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSH: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZTSO: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFH: @@ -123,15 +125,6 @@ bool check_reject_set(int err) return err == EINVAL; } -static bool vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext_id) -{ - int ret; - unsigned long value; - - ret = __vcpu_get_reg(vcpu, ext_id, &value); - return (ret) ? false : !!value; -} - void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) { unsigned long isa_ext_state[KVM_RISCV_ISA_EXT_MAX] = { 0 }; @@ -176,7 +169,7 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) __vcpu_set_reg(vcpu, feature, 1); /* Double check whether the desired extension was enabled */ - __TEST_REQUIRE(vcpu_has_ext(vcpu, feature), + __TEST_REQUIRE(__vcpu_has_ext(vcpu, feature), "%s not available, skipping tests", s->name); } } @@ -419,6 +412,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), KVM_ISA_EXT_ARR(SVPBMT), + KVM_ISA_EXT_ARR(ZACAS), KVM_ISA_EXT_ARR(ZBA), KVM_ISA_EXT_ARR(ZBB), KVM_ISA_EXT_ARR(ZBC), @@ -445,6 +439,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(ZKSED), KVM_ISA_EXT_ARR(ZKSH), KVM_ISA_EXT_ARR(ZKT), + KVM_ISA_EXT_ARR(ZTSO), KVM_ISA_EXT_ARR(ZVBB), KVM_ISA_EXT_ARR(ZVBC), KVM_ISA_EXT_ARR(ZVFH), @@ -940,6 +935,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC); KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL); KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT); KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT); +KVM_ISA_EXT_SIMPLE_CONFIG(zacas, ZACAS); KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA); KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB); KVM_ISA_EXT_SIMPLE_CONFIG(zbc, ZBC); @@ -966,6 +962,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zkr, ZKR); KVM_ISA_EXT_SIMPLE_CONFIG(zksed, ZKSED); KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH); KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT); +KVM_ISA_EXT_SIMPLE_CONFIG(ztso, ZTSO); KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB); KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC); KVM_ISA_EXT_SIMPLE_CONFIG(zvfh, ZVFH); @@ -993,6 +990,7 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_svinval, &config_svnapot, &config_svpbmt, + &config_zacas, &config_zba, &config_zbb, &config_zbc, @@ -1019,6 +1017,7 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_zksed, &config_zksh, &config_zkt, + &config_ztso, &config_zvbb, &config_zvbc, &config_zvfh, diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index b6da8f71ea19..48cb910e660d 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -515,6 +515,8 @@ static __uint128_t rotate(int size, __uint128_t val, int amount) amount = (amount + bits) % bits; val = cut_to_size(size, val); + if (!amount) + return val; return (val << (bits - amount)) | (val >> amount); } diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c index 0f728f05ea82..f3c2239228b1 100644 --- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c @@ -9,6 +9,7 @@ #include <linux/stringify.h> #include <stdint.h> +#include "kvm_test_harness.h" #include "apic.h" #include "test_util.h" #include "kvm_util.h" @@ -83,6 +84,8 @@ static void guest_main(void) GUEST_DONE(); } +KVM_ONE_VCPU_TEST_SUITE(fix_hypercall); + static void enter_guest(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; @@ -103,14 +106,11 @@ static void enter_guest(struct kvm_vcpu *vcpu) } } -static void test_fix_hypercall(bool disable_quirk) +static void test_fix_hypercall(struct kvm_vcpu *vcpu, bool disable_quirk) { - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - - vm = vm_create_with_one_vcpu(&vcpu, guest_main); + struct kvm_vm *vm = vcpu->vm; - vm_init_descriptor_tables(vcpu->vm); + vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vcpu->vm, UD_VECTOR, guest_ud_handler); @@ -126,10 +126,19 @@ static void test_fix_hypercall(bool disable_quirk) enter_guest(vcpu); } -int main(void) +KVM_ONE_VCPU_TEST(fix_hypercall, enable_quirk, guest_main) +{ + test_fix_hypercall(vcpu, false); +} + +KVM_ONE_VCPU_TEST(fix_hypercall, disable_quirk, guest_main) +{ + test_fix_hypercall(vcpu, true); +} + +int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_FIX_HYPERCALL_INSN); - test_fix_hypercall(false); - test_fix_hypercall(true); + return test_harness_run(argc, argv); } diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c new file mode 100644 index 000000000000..29609b52f8fa --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c @@ -0,0 +1,620 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023, Tencent, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <x86intrin.h> + +#include "pmu.h" +#include "processor.h" + +/* Number of LOOP instructions for the guest measurement payload. */ +#define NUM_BRANCHES 10 +/* + * Number of "extra" instructions that will be counted, i.e. the number of + * instructions that are needed to set up the loop and then disabled the + * counter. 1 CLFLUSH/CLFLUSHOPT/NOP, 1 MFENCE, 2 MOV, 2 XOR, 1 WRMSR. + */ +#define NUM_EXTRA_INSNS 7 +#define NUM_INSNS_RETIRED (NUM_BRANCHES + NUM_EXTRA_INSNS) + +static uint8_t kvm_pmu_version; +static bool kvm_has_perf_caps; +static bool is_forced_emulation_enabled; + +static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + void *guest_code, + uint8_t pmu_version, + uint64_t perf_capabilities) +{ + struct kvm_vm *vm; + + vm = vm_create_with_one_vcpu(vcpu, guest_code); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(*vcpu); + + sync_global_to_guest(vm, kvm_pmu_version); + sync_global_to_guest(vm, is_forced_emulation_enabled); + + /* + * Set PERF_CAPABILITIES before PMU version as KVM disallows enabling + * features via PERF_CAPABILITIES if the guest doesn't have a vPMU. + */ + if (kvm_has_perf_caps) + vcpu_set_msr(*vcpu, MSR_IA32_PERF_CAPABILITIES, perf_capabilities); + + vcpu_set_cpuid_property(*vcpu, X86_PROPERTY_PMU_VERSION, pmu_version); + return vm; +} + +static void run_vcpu(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + do { + vcpu_run(vcpu); + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_PRINTF: + pr_info("%s", uc.buffer); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + } while (uc.cmd != UCALL_DONE); +} + +static uint8_t guest_get_pmu_version(void) +{ + /* + * Return the effective PMU version, i.e. the minimum between what KVM + * supports and what is enumerated to the guest. The host deliberately + * advertises a PMU version to the guest beyond what is actually + * supported by KVM to verify KVM doesn't freak out and do something + * bizarre with an architecturally valid, but unsupported, version. + */ + return min_t(uint8_t, kvm_pmu_version, this_cpu_property(X86_PROPERTY_PMU_VERSION)); +} + +/* + * If an architectural event is supported and guaranteed to generate at least + * one "hit, assert that its count is non-zero. If an event isn't supported or + * the test can't guarantee the associated action will occur, then all bets are + * off regarding the count, i.e. no checks can be done. + * + * Sanity check that in all cases, the event doesn't count when it's disabled, + * and that KVM correctly emulates the write of an arbitrary value. + */ +static void guest_assert_event_count(uint8_t idx, + struct kvm_x86_pmu_feature event, + uint32_t pmc, uint32_t pmc_msr) +{ + uint64_t count; + + count = _rdpmc(pmc); + if (!this_pmu_has(event)) + goto sanity_checks; + + switch (idx) { + case INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX: + GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED); + break; + case INTEL_ARCH_BRANCHES_RETIRED_INDEX: + GUEST_ASSERT_EQ(count, NUM_BRANCHES); + break; + case INTEL_ARCH_LLC_REFERENCES_INDEX: + case INTEL_ARCH_LLC_MISSES_INDEX: + if (!this_cpu_has(X86_FEATURE_CLFLUSHOPT) && + !this_cpu_has(X86_FEATURE_CLFLUSH)) + break; + fallthrough; + case INTEL_ARCH_CPU_CYCLES_INDEX: + case INTEL_ARCH_REFERENCE_CYCLES_INDEX: + GUEST_ASSERT_NE(count, 0); + break; + case INTEL_ARCH_TOPDOWN_SLOTS_INDEX: + GUEST_ASSERT(count >= NUM_INSNS_RETIRED); + break; + default: + break; + } + +sanity_checks: + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + GUEST_ASSERT_EQ(_rdpmc(pmc), count); + + wrmsr(pmc_msr, 0xdead); + GUEST_ASSERT_EQ(_rdpmc(pmc), 0xdead); +} + +/* + * Enable and disable the PMC in a monolithic asm blob to ensure that the + * compiler can't insert _any_ code into the measured sequence. Note, ECX + * doesn't need to be clobbered as the input value, @pmc_msr, is restored + * before the end of the sequence. + * + * If CLFUSH{,OPT} is supported, flush the cacheline containing (at least) the + * start of the loop to force LLC references and misses, i.e. to allow testing + * that those events actually count. + * + * If forced emulation is enabled (and specified), force emulation on a subset + * of the measured code to verify that KVM correctly emulates instructions and + * branches retired events in conjunction with hardware also counting said + * events. + */ +#define GUEST_MEASURE_EVENT(_msr, _value, clflush, FEP) \ +do { \ + __asm__ __volatile__("wrmsr\n\t" \ + clflush "\n\t" \ + "mfence\n\t" \ + "1: mov $" __stringify(NUM_BRANCHES) ", %%ecx\n\t" \ + FEP "loop .\n\t" \ + FEP "mov %%edi, %%ecx\n\t" \ + FEP "xor %%eax, %%eax\n\t" \ + FEP "xor %%edx, %%edx\n\t" \ + "wrmsr\n\t" \ + :: "a"((uint32_t)_value), "d"(_value >> 32), \ + "c"(_msr), "D"(_msr) \ + ); \ +} while (0) + +#define GUEST_TEST_EVENT(_idx, _event, _pmc, _pmc_msr, _ctrl_msr, _value, FEP) \ +do { \ + wrmsr(pmc_msr, 0); \ + \ + if (this_cpu_has(X86_FEATURE_CLFLUSHOPT)) \ + GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflushopt 1f", FEP); \ + else if (this_cpu_has(X86_FEATURE_CLFLUSH)) \ + GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflush 1f", FEP); \ + else \ + GUEST_MEASURE_EVENT(_ctrl_msr, _value, "nop", FEP); \ + \ + guest_assert_event_count(_idx, _event, _pmc, _pmc_msr); \ +} while (0) + +static void __guest_test_arch_event(uint8_t idx, struct kvm_x86_pmu_feature event, + uint32_t pmc, uint32_t pmc_msr, + uint32_t ctrl_msr, uint64_t ctrl_msr_value) +{ + GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, ""); + + if (is_forced_emulation_enabled) + GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, KVM_FEP); +} + +#define X86_PMU_FEATURE_NULL \ +({ \ + struct kvm_x86_pmu_feature feature = {}; \ + \ + feature; \ +}) + +static bool pmu_is_null_feature(struct kvm_x86_pmu_feature event) +{ + return !(*(u64 *)&event); +} + +static void guest_test_arch_event(uint8_t idx) +{ + const struct { + struct kvm_x86_pmu_feature gp_event; + struct kvm_x86_pmu_feature fixed_event; + } intel_event_to_feature[] = { + [INTEL_ARCH_CPU_CYCLES_INDEX] = { X86_PMU_FEATURE_CPU_CYCLES, X86_PMU_FEATURE_CPU_CYCLES_FIXED }, + [INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX] = { X86_PMU_FEATURE_INSNS_RETIRED, X86_PMU_FEATURE_INSNS_RETIRED_FIXED }, + /* + * Note, the fixed counter for reference cycles is NOT the same + * as the general purpose architectural event. The fixed counter + * explicitly counts at the same frequency as the TSC, whereas + * the GP event counts at a fixed, but uarch specific, frequency. + * Bundle them here for simplicity. + */ + [INTEL_ARCH_REFERENCE_CYCLES_INDEX] = { X86_PMU_FEATURE_REFERENCE_CYCLES, X86_PMU_FEATURE_REFERENCE_TSC_CYCLES_FIXED }, + [INTEL_ARCH_LLC_REFERENCES_INDEX] = { X86_PMU_FEATURE_LLC_REFERENCES, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_LLC_MISSES_INDEX] = { X86_PMU_FEATURE_LLC_MISSES, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_BRANCHES_RETIRED_INDEX] = { X86_PMU_FEATURE_BRANCH_INSNS_RETIRED, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX] = { X86_PMU_FEATURE_BRANCHES_MISPREDICTED, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_TOPDOWN_SLOTS_INDEX] = { X86_PMU_FEATURE_TOPDOWN_SLOTS, X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED }, + }; + + uint32_t nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + uint32_t pmu_version = guest_get_pmu_version(); + /* PERF_GLOBAL_CTRL exists only for Architectural PMU Version 2+. */ + bool guest_has_perf_global_ctrl = pmu_version >= 2; + struct kvm_x86_pmu_feature gp_event, fixed_event; + uint32_t base_pmc_msr; + unsigned int i; + + /* The host side shouldn't invoke this without a guest PMU. */ + GUEST_ASSERT(pmu_version); + + if (this_cpu_has(X86_FEATURE_PDCM) && + rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES) + base_pmc_msr = MSR_IA32_PMC0; + else + base_pmc_msr = MSR_IA32_PERFCTR0; + + gp_event = intel_event_to_feature[idx].gp_event; + GUEST_ASSERT_EQ(idx, gp_event.f.bit); + + GUEST_ASSERT(nr_gp_counters); + + for (i = 0; i < nr_gp_counters; i++) { + uint64_t eventsel = ARCH_PERFMON_EVENTSEL_OS | + ARCH_PERFMON_EVENTSEL_ENABLE | + intel_pmu_arch_events[idx]; + + wrmsr(MSR_P6_EVNTSEL0 + i, 0); + if (guest_has_perf_global_ctrl) + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, BIT_ULL(i)); + + __guest_test_arch_event(idx, gp_event, i, base_pmc_msr + i, + MSR_P6_EVNTSEL0 + i, eventsel); + } + + if (!guest_has_perf_global_ctrl) + return; + + fixed_event = intel_event_to_feature[idx].fixed_event; + if (pmu_is_null_feature(fixed_event) || !this_pmu_has(fixed_event)) + return; + + i = fixed_event.f.bit; + + wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL)); + + __guest_test_arch_event(idx, fixed_event, i | INTEL_RDPMC_FIXED, + MSR_CORE_PERF_FIXED_CTR0 + i, + MSR_CORE_PERF_GLOBAL_CTRL, + FIXED_PMC_GLOBAL_CTRL_ENABLE(i)); +} + +static void guest_test_arch_events(void) +{ + uint8_t i; + + for (i = 0; i < NR_INTEL_ARCH_EVENTS; i++) + guest_test_arch_event(i); + + GUEST_DONE(); +} + +static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities, + uint8_t length, uint8_t unavailable_mask) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + /* Testing arch events requires a vPMU (there are no negative tests). */ + if (!pmu_version) + return; + + vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_arch_events, + pmu_version, perf_capabilities); + + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH, + length); + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_EVENTS_MASK, + unavailable_mask); + + run_vcpu(vcpu); + + kvm_vm_free(vm); +} + +/* + * Limit testing to MSRs that are actually defined by Intel (in the SDM). MSRs + * that aren't defined counter MSRs *probably* don't exist, but there's no + * guarantee that currently undefined MSR indices won't be used for something + * other than PMCs in the future. + */ +#define MAX_NR_GP_COUNTERS 8 +#define MAX_NR_FIXED_COUNTERS 3 + +#define GUEST_ASSERT_PMC_MSR_ACCESS(insn, msr, expect_gp, vector) \ +__GUEST_ASSERT(expect_gp ? vector == GP_VECTOR : !vector, \ + "Expected %s on " #insn "(0x%x), got vector %u", \ + expect_gp ? "#GP" : "no fault", msr, vector) \ + +#define GUEST_ASSERT_PMC_VALUE(insn, msr, val, expected) \ + __GUEST_ASSERT(val == expected_val, \ + "Expected " #insn "(0x%x) to yield 0x%lx, got 0x%lx", \ + msr, expected_val, val); + +static void guest_test_rdpmc(uint32_t rdpmc_idx, bool expect_success, + uint64_t expected_val) +{ + uint8_t vector; + uint64_t val; + + vector = rdpmc_safe(rdpmc_idx, &val); + GUEST_ASSERT_PMC_MSR_ACCESS(RDPMC, rdpmc_idx, !expect_success, vector); + if (expect_success) + GUEST_ASSERT_PMC_VALUE(RDPMC, rdpmc_idx, val, expected_val); + + if (!is_forced_emulation_enabled) + return; + + vector = rdpmc_safe_fep(rdpmc_idx, &val); + GUEST_ASSERT_PMC_MSR_ACCESS(RDPMC, rdpmc_idx, !expect_success, vector); + if (expect_success) + GUEST_ASSERT_PMC_VALUE(RDPMC, rdpmc_idx, val, expected_val); +} + +static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters, + uint8_t nr_counters, uint32_t or_mask) +{ + const bool pmu_has_fast_mode = !guest_get_pmu_version(); + uint8_t i; + + for (i = 0; i < nr_possible_counters; i++) { + /* + * TODO: Test a value that validates full-width writes and the + * width of the counters. + */ + const uint64_t test_val = 0xffff; + const uint32_t msr = base_msr + i; + + /* + * Fixed counters are supported if the counter is less than the + * number of enumerated contiguous counters *or* the counter is + * explicitly enumerated in the supported counters mask. + */ + const bool expect_success = i < nr_counters || (or_mask & BIT(i)); + + /* + * KVM drops writes to MSR_P6_PERFCTR[0|1] if the counters are + * unsupported, i.e. doesn't #GP and reads back '0'. + */ + const uint64_t expected_val = expect_success ? test_val : 0; + const bool expect_gp = !expect_success && msr != MSR_P6_PERFCTR0 && + msr != MSR_P6_PERFCTR1; + uint32_t rdpmc_idx; + uint8_t vector; + uint64_t val; + + vector = wrmsr_safe(msr, test_val); + GUEST_ASSERT_PMC_MSR_ACCESS(WRMSR, msr, expect_gp, vector); + + vector = rdmsr_safe(msr, &val); + GUEST_ASSERT_PMC_MSR_ACCESS(RDMSR, msr, expect_gp, vector); + + /* On #GP, the result of RDMSR is undefined. */ + if (!expect_gp) + GUEST_ASSERT_PMC_VALUE(RDMSR, msr, val, expected_val); + + /* + * Redo the read tests with RDPMC, which has different indexing + * semantics and additional capabilities. + */ + rdpmc_idx = i; + if (base_msr == MSR_CORE_PERF_FIXED_CTR0) + rdpmc_idx |= INTEL_RDPMC_FIXED; + + guest_test_rdpmc(rdpmc_idx, expect_success, expected_val); + + /* + * KVM doesn't support non-architectural PMUs, i.e. it should + * impossible to have fast mode RDPMC. Verify that attempting + * to use fast RDPMC always #GPs. + */ + GUEST_ASSERT(!expect_success || !pmu_has_fast_mode); + rdpmc_idx |= INTEL_RDPMC_FAST; + guest_test_rdpmc(rdpmc_idx, false, -1ull); + + vector = wrmsr_safe(msr, 0); + GUEST_ASSERT_PMC_MSR_ACCESS(WRMSR, msr, expect_gp, vector); + } +} + +static void guest_test_gp_counters(void) +{ + uint8_t nr_gp_counters = 0; + uint32_t base_msr; + + if (guest_get_pmu_version()) + nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + + if (this_cpu_has(X86_FEATURE_PDCM) && + rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES) + base_msr = MSR_IA32_PMC0; + else + base_msr = MSR_IA32_PERFCTR0; + + guest_rd_wr_counters(base_msr, MAX_NR_GP_COUNTERS, nr_gp_counters, 0); + GUEST_DONE(); +} + +static void test_gp_counters(uint8_t pmu_version, uint64_t perf_capabilities, + uint8_t nr_gp_counters) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_gp_counters, + pmu_version, perf_capabilities); + + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_NR_GP_COUNTERS, + nr_gp_counters); + + run_vcpu(vcpu); + + kvm_vm_free(vm); +} + +static void guest_test_fixed_counters(void) +{ + uint64_t supported_bitmask = 0; + uint8_t nr_fixed_counters = 0; + uint8_t i; + + /* Fixed counters require Architectural vPMU Version 2+. */ + if (guest_get_pmu_version() >= 2) + nr_fixed_counters = this_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + + /* + * The supported bitmask for fixed counters was introduced in PMU + * version 5. + */ + if (guest_get_pmu_version() >= 5) + supported_bitmask = this_cpu_property(X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK); + + guest_rd_wr_counters(MSR_CORE_PERF_FIXED_CTR0, MAX_NR_FIXED_COUNTERS, + nr_fixed_counters, supported_bitmask); + + for (i = 0; i < MAX_NR_FIXED_COUNTERS; i++) { + uint8_t vector; + uint64_t val; + + if (i >= nr_fixed_counters && !(supported_bitmask & BIT_ULL(i))) { + vector = wrmsr_safe(MSR_CORE_PERF_FIXED_CTR_CTRL, + FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL)); + __GUEST_ASSERT(vector == GP_VECTOR, + "Expected #GP for counter %u in FIXED_CTR_CTRL", i); + + vector = wrmsr_safe(MSR_CORE_PERF_GLOBAL_CTRL, + FIXED_PMC_GLOBAL_CTRL_ENABLE(i)); + __GUEST_ASSERT(vector == GP_VECTOR, + "Expected #GP for counter %u in PERF_GLOBAL_CTRL", i); + continue; + } + + wrmsr(MSR_CORE_PERF_FIXED_CTR0 + i, 0); + wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL)); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, FIXED_PMC_GLOBAL_CTRL_ENABLE(i)); + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + val = rdmsr(MSR_CORE_PERF_FIXED_CTR0 + i); + + GUEST_ASSERT_NE(val, 0); + } + GUEST_DONE(); +} + +static void test_fixed_counters(uint8_t pmu_version, uint64_t perf_capabilities, + uint8_t nr_fixed_counters, + uint32_t supported_bitmask) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_fixed_counters, + pmu_version, perf_capabilities); + + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK, + supported_bitmask); + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_NR_FIXED_COUNTERS, + nr_fixed_counters); + + run_vcpu(vcpu); + + kvm_vm_free(vm); +} + +static void test_intel_counters(void) +{ + uint8_t nr_arch_events = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + uint8_t nr_gp_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + uint8_t pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); + unsigned int i; + uint8_t v, j; + uint32_t k; + + const uint64_t perf_caps[] = { + 0, + PMU_CAP_FW_WRITES, + }; + + /* + * Test up to PMU v5, which is the current maximum version defined by + * Intel, i.e. is the last version that is guaranteed to be backwards + * compatible with KVM's existing behavior. + */ + uint8_t max_pmu_version = max_t(typeof(pmu_version), pmu_version, 5); + + /* + * Detect the existence of events that aren't supported by selftests. + * This will (obviously) fail any time the kernel adds support for a + * new event, but it's worth paying that price to keep the test fresh. + */ + TEST_ASSERT(nr_arch_events <= NR_INTEL_ARCH_EVENTS, + "New architectural event(s) detected; please update this test (length = %u, mask = %x)", + nr_arch_events, kvm_cpu_property(X86_PROPERTY_PMU_EVENTS_MASK)); + + /* + * Force iterating over known arch events regardless of whether or not + * KVM/hardware supports a given event. + */ + nr_arch_events = max_t(typeof(nr_arch_events), nr_arch_events, NR_INTEL_ARCH_EVENTS); + + for (v = 0; v <= max_pmu_version; v++) { + for (i = 0; i < ARRAY_SIZE(perf_caps); i++) { + if (!kvm_has_perf_caps && perf_caps[i]) + continue; + + pr_info("Testing arch events, PMU version %u, perf_caps = %lx\n", + v, perf_caps[i]); + /* + * To keep the total runtime reasonable, test every + * possible non-zero, non-reserved bitmap combination + * only with the native PMU version and the full bit + * vector length. + */ + if (v == pmu_version) { + for (k = 1; k < (BIT(nr_arch_events) - 1); k++) + test_arch_events(v, perf_caps[i], nr_arch_events, k); + } + /* + * Test single bits for all PMU version and lengths up + * the number of events +1 (to verify KVM doesn't do + * weird things if the guest length is greater than the + * host length). Explicitly test a mask of '0' and all + * ones i.e. all events being available and unavailable. + */ + for (j = 0; j <= nr_arch_events + 1; j++) { + test_arch_events(v, perf_caps[i], j, 0); + test_arch_events(v, perf_caps[i], j, 0xff); + + for (k = 0; k < nr_arch_events; k++) + test_arch_events(v, perf_caps[i], j, BIT(k)); + } + + pr_info("Testing GP counters, PMU version %u, perf_caps = %lx\n", + v, perf_caps[i]); + for (j = 0; j <= nr_gp_counters; j++) + test_gp_counters(v, perf_caps[i], j); + + pr_info("Testing fixed counters, PMU version %u, perf_caps = %lx\n", + v, perf_caps[i]); + for (j = 0; j <= nr_fixed_counters; j++) { + for (k = 0; k <= (BIT(nr_fixed_counters) - 1); k++) + test_fixed_counters(v, perf_caps[i], j, k); + } + } + } +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_is_pmu_enabled()); + + TEST_REQUIRE(host_cpu_is_intel); + TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION)); + TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0); + + kvm_pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); + kvm_has_perf_caps = kvm_cpu_has(X86_FEATURE_PDCM); + is_forced_emulation_enabled = kvm_is_forced_emulation_enabled(); + + test_intel_counters(); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index a3bd54b925ab..3c85d1ae9893 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -11,72 +11,18 @@ */ #define _GNU_SOURCE /* for program_invocation_short_name */ -#include "test_util.h" + #include "kvm_util.h" +#include "pmu.h" #include "processor.h" - -/* - * In lieu of copying perf_event.h into tools... - */ -#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) -#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) - -/* End of stuff taken from perf_event.h. */ - -/* Oddly, this isn't in perf_event.h. */ -#define ARCH_PERFMON_BRANCHES_RETIRED 5 +#include "test_util.h" #define NUM_BRANCHES 42 -#define INTEL_PMC_IDX_FIXED 32 - -/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */ -#define MAX_FILTER_EVENTS 300 #define MAX_TEST_EVENTS 10 #define PMU_EVENT_FILTER_INVALID_ACTION (KVM_PMU_EVENT_DENY + 1) #define PMU_EVENT_FILTER_INVALID_FLAGS (KVM_PMU_EVENT_FLAGS_VALID_MASK << 1) -#define PMU_EVENT_FILTER_INVALID_NEVENTS (MAX_FILTER_EVENTS + 1) - -/* - * This is how the event selector and unit mask are stored in an AMD - * core performance event-select register. Intel's format is similar, - * but the event selector is only 8 bits. - */ -#define EVENT(select, umask) ((select & 0xf00UL) << 24 | (select & 0xff) | \ - (umask & 0xff) << 8) - -/* - * "Branch instructions retired", from the Intel SDM, volume 3, - * "Pre-defined Architectural Performance Events." - */ - -#define INTEL_BR_RETIRED EVENT(0xc4, 0) - -/* - * "Retired branch instructions", from Processor Programming Reference - * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, - * Preliminary Processor Programming Reference (PPR) for AMD Family - * 17h Model 31h, Revision B0 Processors, and Preliminary Processor - * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision - * B1 Processors Volume 1 of 2. - */ - -#define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0) - - -/* - * "Retired instructions", from Processor Programming Reference - * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, - * Preliminary Processor Programming Reference (PPR) for AMD Family - * 17h Model 31h, Revision B0 Processors, and Preliminary Processor - * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision - * B1 Processors Volume 1 of 2. - * --- and --- - * "Instructions retired", from the Intel SDM, volume 3, - * "Pre-defined Architectural Performance Events." - */ - -#define INST_RETIRED EVENT(0xc0, 0) +#define PMU_EVENT_FILTER_INVALID_NEVENTS (KVM_PMU_EVENT_FILTER_MAX_EVENTS + 1) struct __kvm_pmu_event_filter { __u32 action; @@ -84,26 +30,28 @@ struct __kvm_pmu_event_filter { __u32 fixed_counter_bitmap; __u32 flags; __u32 pad[4]; - __u64 events[MAX_FILTER_EVENTS]; + __u64 events[KVM_PMU_EVENT_FILTER_MAX_EVENTS]; }; /* - * This event list comprises Intel's eight architectural events plus - * AMD's "retired branch instructions" for Zen[123] (and possibly - * other AMD CPUs). + * This event list comprises Intel's known architectural events, plus AMD's + * "retired branch instructions" for Zen1-Zen3 (and* possibly other AMD CPUs). + * Note, AMD and Intel use the same encoding for instructions retired. */ +kvm_static_assert(INTEL_ARCH_INSTRUCTIONS_RETIRED == AMD_ZEN_INSTRUCTIONS_RETIRED); + static const struct __kvm_pmu_event_filter base_event_filter = { .nevents = ARRAY_SIZE(base_event_filter.events), .events = { - EVENT(0x3c, 0), - INST_RETIRED, - EVENT(0x3c, 1), - EVENT(0x2e, 0x4f), - EVENT(0x2e, 0x41), - EVENT(0xc4, 0), - EVENT(0xc5, 0), - EVENT(0xa4, 1), - AMD_ZEN_BR_RETIRED, + INTEL_ARCH_CPU_CYCLES, + INTEL_ARCH_INSTRUCTIONS_RETIRED, + INTEL_ARCH_REFERENCE_CYCLES, + INTEL_ARCH_LLC_REFERENCES, + INTEL_ARCH_LLC_MISSES, + INTEL_ARCH_BRANCHES_RETIRED, + INTEL_ARCH_BRANCHES_MISPREDICTED, + INTEL_ARCH_TOPDOWN_SLOTS, + AMD_ZEN_BRANCHES_RETIRED, }, }; @@ -165,9 +113,9 @@ static void intel_guest_code(void) for (;;) { wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | - ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED); + ARCH_PERFMON_EVENTSEL_OS | INTEL_ARCH_BRANCHES_RETIRED); wrmsr(MSR_P6_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | - ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED); + ARCH_PERFMON_EVENTSEL_OS | INTEL_ARCH_INSTRUCTIONS_RETIRED); wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x3); run_and_measure_loop(MSR_IA32_PMC0); @@ -189,9 +137,9 @@ static void amd_guest_code(void) for (;;) { wrmsr(MSR_K7_EVNTSEL0, 0); wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | - ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED); + ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BRANCHES_RETIRED); wrmsr(MSR_K7_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | - ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED); + ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_INSTRUCTIONS_RETIRED); run_and_measure_loop(MSR_K7_PERFCTR0); GUEST_SYNC(0); @@ -312,7 +260,7 @@ static void test_amd_deny_list(struct kvm_vcpu *vcpu) .action = KVM_PMU_EVENT_DENY, .nevents = 1, .events = { - EVENT(0x1C2, 0), + RAW_EVENT(0x1C2, 0), }, }; @@ -347,9 +295,9 @@ static void test_not_member_deny_list(struct kvm_vcpu *vcpu) f.action = KVM_PMU_EVENT_DENY; - remove_event(&f, INST_RETIRED); - remove_event(&f, INTEL_BR_RETIRED); - remove_event(&f, AMD_ZEN_BR_RETIRED); + remove_event(&f, INTEL_ARCH_INSTRUCTIONS_RETIRED); + remove_event(&f, INTEL_ARCH_BRANCHES_RETIRED); + remove_event(&f, AMD_ZEN_BRANCHES_RETIRED); test_with_filter(vcpu, &f); ASSERT_PMC_COUNTING_INSTRUCTIONS(); @@ -361,9 +309,9 @@ static void test_not_member_allow_list(struct kvm_vcpu *vcpu) f.action = KVM_PMU_EVENT_ALLOW; - remove_event(&f, INST_RETIRED); - remove_event(&f, INTEL_BR_RETIRED); - remove_event(&f, AMD_ZEN_BR_RETIRED); + remove_event(&f, INTEL_ARCH_INSTRUCTIONS_RETIRED); + remove_event(&f, INTEL_ARCH_BRANCHES_RETIRED); + remove_event(&f, AMD_ZEN_BRANCHES_RETIRED); test_with_filter(vcpu, &f); ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(); @@ -452,9 +400,9 @@ static bool use_amd_pmu(void) * - Sapphire Rapids, Ice Lake, Cascade Lake, Skylake. */ #define MEM_INST_RETIRED 0xD0 -#define MEM_INST_RETIRED_LOAD EVENT(MEM_INST_RETIRED, 0x81) -#define MEM_INST_RETIRED_STORE EVENT(MEM_INST_RETIRED, 0x82) -#define MEM_INST_RETIRED_LOAD_STORE EVENT(MEM_INST_RETIRED, 0x83) +#define MEM_INST_RETIRED_LOAD RAW_EVENT(MEM_INST_RETIRED, 0x81) +#define MEM_INST_RETIRED_STORE RAW_EVENT(MEM_INST_RETIRED, 0x82) +#define MEM_INST_RETIRED_LOAD_STORE RAW_EVENT(MEM_INST_RETIRED, 0x83) static bool supports_event_mem_inst_retired(void) { @@ -486,9 +434,9 @@ static bool supports_event_mem_inst_retired(void) * B1 Processors Volume 1 of 2. */ #define LS_DISPATCH 0x29 -#define LS_DISPATCH_LOAD EVENT(LS_DISPATCH, BIT(0)) -#define LS_DISPATCH_STORE EVENT(LS_DISPATCH, BIT(1)) -#define LS_DISPATCH_LOAD_STORE EVENT(LS_DISPATCH, BIT(2)) +#define LS_DISPATCH_LOAD RAW_EVENT(LS_DISPATCH, BIT(0)) +#define LS_DISPATCH_STORE RAW_EVENT(LS_DISPATCH, BIT(1)) +#define LS_DISPATCH_LOAD_STORE RAW_EVENT(LS_DISPATCH, BIT(2)) #define INCLUDE_MASKED_ENTRY(event_select, mask, match) \ KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, false) @@ -729,14 +677,14 @@ static void add_dummy_events(uint64_t *events, int nevents) static void test_masked_events(struct kvm_vcpu *vcpu) { - int nevents = MAX_FILTER_EVENTS - MAX_TEST_EVENTS; - uint64_t events[MAX_FILTER_EVENTS]; + int nevents = KVM_PMU_EVENT_FILTER_MAX_EVENTS - MAX_TEST_EVENTS; + uint64_t events[KVM_PMU_EVENT_FILTER_MAX_EVENTS]; /* Run the test cases against a sparse PMU event filter. */ run_masked_events_tests(vcpu, events, 0); /* Run the test cases against a dense PMU event filter. */ - add_dummy_events(events, MAX_FILTER_EVENTS); + add_dummy_events(events, KVM_PMU_EVENT_FILTER_MAX_EVENTS); run_masked_events_tests(vcpu, events, nevents); } @@ -809,20 +757,19 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu) TEST_ASSERT(!r, "Masking non-existent fixed counters should be allowed"); } -static void intel_run_fixed_counter_guest_code(uint8_t fixed_ctr_idx) +static void intel_run_fixed_counter_guest_code(uint8_t idx) { for (;;) { wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); - wrmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx, 0); + wrmsr(MSR_CORE_PERF_FIXED_CTR0 + idx, 0); /* Only OS_EN bit is enabled for fixed counter[idx]. */ - wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, BIT_ULL(4 * fixed_ctr_idx)); - wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, - BIT_ULL(INTEL_PMC_IDX_FIXED + fixed_ctr_idx)); + wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(idx, FIXED_PMC_KERNEL)); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, FIXED_PMC_GLOBAL_CTRL_ENABLE(idx)); __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); - GUEST_SYNC(rdmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx)); + GUEST_SYNC(rdmsr(MSR_CORE_PERF_FIXED_CTR0 + idx)); } } @@ -920,7 +867,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu, *vcpu2 = NULL; struct kvm_vm *vm; - TEST_REQUIRE(get_kvm_param_bool("enable_pmu")); + TEST_REQUIRE(kvm_is_pmu_enabled()); TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_MASKED_EVENTS)); diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c index 65ad38b6be1f..e0f642d2a3c4 100644 --- a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c +++ b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c @@ -434,6 +434,8 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size); TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r)); + + close(memfd); } static void usage(const char *cmd) diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c index a49828adf294..0a6dfba3905b 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -10,11 +10,9 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" -#include "svm_util.h" +#include "sev.h" #include "kselftest.h" -#define SEV_POLICY_ES 0b100 - #define NR_MIGRATE_TEST_VCPUS 4 #define NR_MIGRATE_TEST_VMS 3 #define NR_LOCK_TESTING_THREADS 3 @@ -22,46 +20,24 @@ bool have_sev_es; -static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error) -{ - struct kvm_sev_cmd cmd = { - .id = cmd_id, - .data = (uint64_t)data, - .sev_fd = open_sev_dev_path_or_exit(), - }; - int ret; - - ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd); - *fw_error = cmd.error; - return ret; -} - -static void sev_ioctl(int vm_fd, int cmd_id, void *data) -{ - int ret; - __u32 fw_error; - - ret = __sev_ioctl(vm_fd, cmd_id, data, &fw_error); - TEST_ASSERT(ret == 0 && fw_error == SEV_RET_SUCCESS, - "%d failed: return code: %d, errno: %d, fw error: %d", - cmd_id, ret, errno, fw_error); -} - static struct kvm_vm *sev_vm_create(bool es) { struct kvm_vm *vm; - struct kvm_sev_launch_start start = { 0 }; int i; vm = vm_create_barebones(); - sev_ioctl(vm->fd, es ? KVM_SEV_ES_INIT : KVM_SEV_INIT, NULL); + if (!es) + sev_vm_init(vm); + else + sev_es_vm_init(vm); + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) __vm_vcpu_add(vm, i); + + sev_vm_launch(vm, es ? SEV_POLICY_ES : 0); + if (es) - start.policy |= SEV_POLICY_ES; - sev_ioctl(vm->fd, KVM_SEV_LAUNCH_START, &start); - if (es) - sev_ioctl(vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); return vm; } @@ -181,7 +157,7 @@ static void test_sev_migrate_parameters(void) sev_vm = sev_vm_create(/* es= */ false); sev_es_vm = sev_vm_create(/* es= */ true); sev_es_vm_no_vmsa = vm_create_barebones(); - sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL); + sev_es_vm_init(sev_es_vm_no_vmsa); __vm_vcpu_add(sev_es_vm_no_vmsa, 1); ret = __sev_migrate_from(sev_vm, sev_es_vm); @@ -230,13 +206,13 @@ static void sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src) TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d", ret, errno); } -static void verify_mirror_allowed_cmds(int vm_fd) +static void verify_mirror_allowed_cmds(struct kvm_vm *vm) { struct kvm_sev_guest_status status; + int cmd_id; - for (int cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) { + for (cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) { int ret; - __u32 fw_error; /* * These commands are allowed for mirror VMs, all others are @@ -256,14 +232,14 @@ static void verify_mirror_allowed_cmds(int vm_fd) * These commands should be disallowed before the data * parameter is examined so NULL is OK here. */ - ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error); + ret = __vm_sev_ioctl(vm, cmd_id, NULL); TEST_ASSERT( ret == -1 && errno == EINVAL, "Should not be able call command: %d. ret: %d, errno: %d", cmd_id, ret, errno); } - sev_ioctl(vm_fd, KVM_SEV_GUEST_STATUS, &status); + vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status); } static void test_sev_mirror(bool es) @@ -281,9 +257,9 @@ static void test_sev_mirror(bool es) __vm_vcpu_add(dst_vm, i); if (es) - sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + vm_sev_ioctl(dst_vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); - verify_mirror_allowed_cmds(dst_vm->fd); + verify_mirror_allowed_cmds(dst_vm); kvm_vm_free(src_vm); kvm_vm_free(dst_vm); diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c new file mode 100644 index 000000000000..026779f3ed06 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0-only +#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" +#include "svm_util.h" +#include "linux/psp-sev.h" +#include "sev.h" + + +static void guest_sev_es_code(void) +{ + /* TODO: Check CPUID after GHCB-based hypercall support is added. */ + GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); + GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED); + + /* + * TODO: Add GHCB and ucall support for SEV-ES guests. For now, simply + * force "termination" to signal "done" via the GHCB MSR protocol. + */ + wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ); + __asm__ __volatile__("rep; vmmcall"); +} + +static void guest_sev_code(void) +{ + GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV)); + GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); + + GUEST_DONE(); +} + +static void test_sev(void *guest_code, uint64_t policy) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + + vm = vm_sev_create_with_one_vcpu(policy, guest_code, &vcpu); + + for (;;) { + vcpu_run(vcpu); + + if (policy & SEV_POLICY_ES) { + TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SYSTEM_EVENT, + "Wanted SYSTEM_EVENT, got %s", + exit_reason_str(vcpu->run->exit_reason)); + TEST_ASSERT_EQ(vcpu->run->system_event.type, KVM_SYSTEM_EVENT_SEV_TERM); + TEST_ASSERT_EQ(vcpu->run->system_event.ndata, 1); + TEST_ASSERT_EQ(vcpu->run->system_event.data[0], GHCB_MSR_TERM_REQ); + break; + } + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + continue; + case UCALL_DONE: + return; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected exit: %s", + exit_reason_str(vcpu->run->exit_reason)); + } + } + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); + + test_sev(guest_sev_code, SEV_POLICY_NO_DBG); + test_sev(guest_sev_code, 0); + + if (kvm_cpu_has(X86_FEATURE_SEV_ES)) { + test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG); + test_sev(guest_sev_es_code, SEV_POLICY_ES); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c index 1a46dd7bb391..416207c38a17 100644 --- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c +++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c @@ -63,7 +63,7 @@ int main(int argc, char *argv[]) vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); - vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR); + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_MAX_PHY_ADDR, MAXPHYADDR); rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE); TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable"); diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index a91b5b145fa3..adb5593daf48 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -17,6 +17,7 @@ #include <sys/ioctl.h> #include <pthread.h> +#include "kvm_test_harness.h" #include "test_util.h" #include "kvm_util.h" #include "processor.h" @@ -41,6 +42,8 @@ void guest_code(void) : "rax", "rbx"); } +KVM_ONE_VCPU_TEST_SUITE(sync_regs_test); + static void compare_regs(struct kvm_regs *left, struct kvm_regs *right) { #define REG_COMPARE(reg) \ @@ -152,18 +155,15 @@ static noinline void *race_sregs_cr4(void *arg) return NULL; } -static void race_sync_regs(void *racer) +static void race_sync_regs(struct kvm_vcpu *vcpu, void *racer) { const time_t TIMEOUT = 2; /* seconds, roughly */ struct kvm_x86_state *state; struct kvm_translation tr; - struct kvm_vcpu *vcpu; struct kvm_run *run; - struct kvm_vm *vm; pthread_t thread; time_t t; - vm = vm_create_with_one_vcpu(&vcpu, guest_code); run = vcpu->run; run->kvm_valid_regs = KVM_SYNC_X86_SREGS; @@ -205,26 +205,12 @@ static void race_sync_regs(void *racer) TEST_ASSERT_EQ(pthread_join(thread, NULL), 0); kvm_x86_state_cleanup(state); - kvm_vm_free(vm); } -int main(int argc, char *argv[]) +KVM_ONE_VCPU_TEST(sync_regs_test, read_invalid, guest_code) { - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - struct kvm_run *run; - struct kvm_regs regs; - struct kvm_sregs sregs; - struct kvm_vcpu_events events; - int rv, cap; - - cap = kvm_check_cap(KVM_CAP_SYNC_REGS); - TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS); - TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD)); - - vm = vm_create_with_one_vcpu(&vcpu, guest_code); - - run = vcpu->run; + struct kvm_run *run = vcpu->run; + int rv; /* Request reading invalid register set from VCPU. */ run->kvm_valid_regs = INVALID_SYNC_FIELD; @@ -240,6 +226,12 @@ int main(int argc, char *argv[]) "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d", rv); run->kvm_valid_regs = 0; +} + +KVM_ONE_VCPU_TEST(sync_regs_test, set_invalid, guest_code) +{ + struct kvm_run *run = vcpu->run; + int rv; /* Request setting invalid register set into VCPU. */ run->kvm_dirty_regs = INVALID_SYNC_FIELD; @@ -255,11 +247,19 @@ int main(int argc, char *argv[]) "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d", rv); run->kvm_dirty_regs = 0; +} + +KVM_ONE_VCPU_TEST(sync_regs_test, req_and_verify_all_valid, guest_code) +{ + struct kvm_run *run = vcpu->run; + struct kvm_vcpu_events events; + struct kvm_sregs sregs; + struct kvm_regs regs; /* Request and verify all valid register sets. */ /* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */ run->kvm_valid_regs = TEST_SYNC_FIELDS; - rv = _vcpu_run(vcpu); + vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); vcpu_regs_get(vcpu, ®s); @@ -270,6 +270,19 @@ int main(int argc, char *argv[]) vcpu_events_get(vcpu, &events); compare_vcpu_events(&events, &run->s.regs.events); +} + +KVM_ONE_VCPU_TEST(sync_regs_test, set_and_verify_various, guest_code) +{ + struct kvm_run *run = vcpu->run; + struct kvm_vcpu_events events; + struct kvm_sregs sregs; + struct kvm_regs regs; + + /* Run once to get register set */ + run->kvm_valid_regs = TEST_SYNC_FIELDS; + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); /* Set and verify various register values. */ run->s.regs.regs.rbx = 0xBAD1DEA; @@ -278,7 +291,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS; - rv = _vcpu_run(vcpu); + vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->s.regs.regs.rbx == 0xBAD1DEA + 1, "rbx sync regs value incorrect 0x%llx.", @@ -295,6 +308,11 @@ int main(int argc, char *argv[]) vcpu_events_get(vcpu, &events); compare_vcpu_events(&events, &run->s.regs.events); +} + +KVM_ONE_VCPU_TEST(sync_regs_test, clear_kvm_dirty_regs_bits, guest_code) +{ + struct kvm_run *run = vcpu->run; /* Clear kvm_dirty_regs bits, verify new s.regs values are * overwritten with existing guest values. @@ -302,11 +320,22 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = 0; run->s.regs.regs.rbx = 0xDEADBEEF; - rv = _vcpu_run(vcpu); + vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->s.regs.regs.rbx != 0xDEADBEEF, "rbx sync regs value incorrect 0x%llx.", run->s.regs.regs.rbx); +} + +KVM_ONE_VCPU_TEST(sync_regs_test, clear_kvm_valid_and_dirty_regs, guest_code) +{ + struct kvm_run *run = vcpu->run; + struct kvm_regs regs; + + /* Run once to get register set */ + run->kvm_valid_regs = TEST_SYNC_FIELDS; + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); /* Clear kvm_valid_regs bits and kvm_dirty_bits. * Verify s.regs values are not overwritten with existing guest values @@ -315,9 +344,10 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = 0; run->kvm_dirty_regs = 0; run->s.regs.regs.rbx = 0xAAAA; + vcpu_regs_get(vcpu, ®s); regs.rbx = 0xBAC0; vcpu_regs_set(vcpu, ®s); - rv = _vcpu_run(vcpu); + vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->s.regs.regs.rbx == 0xAAAA, "rbx sync regs value incorrect 0x%llx.", @@ -326,6 +356,17 @@ int main(int argc, char *argv[]) TEST_ASSERT(regs.rbx == 0xBAC0 + 1, "rbx guest value incorrect 0x%llx.", regs.rbx); +} + +KVM_ONE_VCPU_TEST(sync_regs_test, clear_kvm_valid_regs_bits, guest_code) +{ + struct kvm_run *run = vcpu->run; + struct kvm_regs regs; + + /* Run once to get register set */ + run->kvm_valid_regs = TEST_SYNC_FIELDS; + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); /* Clear kvm_valid_regs bits. Verify s.regs values are not overwritten * with existing guest values but that guest values are overwritten @@ -334,7 +375,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = 0; run->kvm_dirty_regs = TEST_SYNC_FIELDS; run->s.regs.regs.rbx = 0xBBBB; - rv = _vcpu_run(vcpu); + vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->s.regs.regs.rbx == 0xBBBB, "rbx sync regs value incorrect 0x%llx.", @@ -343,12 +384,30 @@ int main(int argc, char *argv[]) TEST_ASSERT(regs.rbx == 0xBBBB + 1, "rbx guest value incorrect 0x%llx.", regs.rbx); +} - kvm_vm_free(vm); +KVM_ONE_VCPU_TEST(sync_regs_test, race_cr4, guest_code) +{ + race_sync_regs(vcpu, race_sregs_cr4); +} + +KVM_ONE_VCPU_TEST(sync_regs_test, race_exc, guest_code) +{ + race_sync_regs(vcpu, race_events_exc); +} - race_sync_regs(race_sregs_cr4); - race_sync_regs(race_events_exc); - race_sync_regs(race_events_inj_pen); +KVM_ONE_VCPU_TEST(sync_regs_test, race_inj_pen, guest_code) +{ + race_sync_regs(vcpu, race_events_inj_pen); +} + +int main(int argc, char *argv[]) +{ + int cap; + + cap = kvm_check_cap(KVM_CAP_SYNC_REGS); + TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS); + TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD)); - return 0; + return test_harness_run(argc, argv); } 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 index 3533dc2fbfee..f4f61a2d2464 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -8,14 +8,12 @@ #define _GNU_SOURCE /* for program_invocation_short_name */ #include <sys/ioctl.h> +#include "kvm_test_harness.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; +static bool fep_available; #define MSR_NON_EXISTENT 0x474f4f00 @@ -260,13 +258,6 @@ static void guest_code_filter_allow(void) 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); @@ -388,12 +379,6 @@ static void guest_fep_gp_handler(struct ex_regs *regs) &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 check_for_guest_assert(struct kvm_vcpu *vcpu) { struct ucall uc; @@ -527,13 +512,15 @@ static void run_guest_then_process_ucall_done(struct kvm_vcpu *vcpu) process_ucall_done(vcpu); } -static void test_msr_filter_allow(void) +KVM_ONE_VCPU_TEST_SUITE(user_msr); + +KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow) { - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; + struct kvm_vm *vm = vcpu->vm; + uint64_t cmd; int rc; - vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_allow); + sync_global_to_guest(vm, fep_available); rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); @@ -561,11 +548,11 @@ static void test_msr_filter_allow(void) run_guest_then_process_wrmsr(vcpu, MSR_NON_EXISTENT); run_guest_then_process_rdmsr(vcpu, MSR_NON_EXISTENT); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); vcpu_run(vcpu); - vm_install_exception_handler(vm, UD_VECTOR, NULL); + cmd = process_ucall(vcpu); - if (process_ucall(vcpu) != UCALL_DONE) { + if (fep_available) { + TEST_ASSERT_EQ(cmd, UCALL_SYNC); vm_install_exception_handler(vm, GP_VECTOR, guest_fep_gp_handler); /* Process emulated rdmsr and wrmsr instructions. */ @@ -583,10 +570,9 @@ static void test_msr_filter_allow(void) /* Confirm the guest completed without issues. */ run_guest_then_process_ucall_done(vcpu); } else { + TEST_ASSERT_EQ(cmd, UCALL_DONE); 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_vcpu *vcpu) @@ -646,16 +632,12 @@ static void handle_wrmsr(struct kvm_run *run) } } -static void test_msr_filter_deny(void) +KVM_ONE_VCPU_TEST(user_msr, msr_filter_deny, guest_code_filter_deny) { - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - struct kvm_run *run; + struct kvm_vm *vm = vcpu->vm; + struct kvm_run *run = vcpu->run; int rc; - vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_deny); - run = vcpu->run; - 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, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_INVAL | @@ -689,18 +671,13 @@ static void test_msr_filter_deny(void) 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) +KVM_ONE_VCPU_TEST(user_msr, msr_permission_bitmap, guest_code_permission_bitmap) { - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; + struct kvm_vm *vm = vcpu->vm; int rc; - vm = vm_create_with_one_vcpu(&vcpu, guest_code_permission_bitmap); - 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, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER); @@ -715,8 +692,6 @@ static void test_msr_permission_bitmap(void) vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs); run_guest_then_process_rdmsr(vcpu, MSR_GS_BASE); run_guest_then_process_ucall_done(vcpu); - - kvm_vm_free(vm); } #define test_user_exit_msr_ioctl(vm, cmd, arg, flag, valid_mask) \ @@ -786,31 +761,20 @@ static void run_msr_filter_flag_test(struct kvm_vm *vm) } /* Test that attempts to write to the unused bits in a flag fails. */ -static void test_user_exit_msr_flags(void) +KVM_ONE_VCPU_TEST(user_msr, user_exit_msr_flags, NULL) { - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - - vm = vm_create_with_one_vcpu(&vcpu, NULL); + struct kvm_vm *vm = vcpu->vm; /* Test flags for KVM_CAP_X86_USER_SPACE_MSR. */ run_user_space_msr_flag_test(vm); /* Test flags and range flags for KVM_X86_SET_MSR_FILTER. */ run_msr_filter_flag_test(vm); - - kvm_vm_free(vm); } int main(int argc, char *argv[]) { - test_msr_filter_allow(); - - test_msr_filter_deny(); - - test_msr_permission_bitmap(); + fep_available = kvm_is_forced_emulation_enabled(); - test_user_exit_msr_flags(); - - return 0; + return test_harness_run(argc, argv); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 2a8d4ac2f020..ea0cb3cae0f7 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -15,10 +15,11 @@ #include <linux/bitmap.h> +#include "kvm_test_harness.h" #include "kvm_util.h" #include "vmx.h" -union perf_capabilities { +static union perf_capabilities { struct { u64 lbr_format:6; u64 pebs_trap:1; @@ -32,7 +33,7 @@ union perf_capabilities { u64 anythread_deprecated:1; }; u64 capabilities; -}; +} host_cap; /* * The LBR format and most PEBS features are immutable, all other features are @@ -73,19 +74,19 @@ static void guest_code(uint64_t current_val) GUEST_DONE(); } +KVM_ONE_VCPU_TEST_SUITE(vmx_pmu_caps); + /* * Verify that guest WRMSRs to PERF_CAPABILITIES #GP regardless of the value * written, that the guest always sees the userspace controlled value, and that * PERF_CAPABILITIES is immutable after KVM_RUN. */ -static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap) +KVM_ONE_VCPU_TEST(vmx_pmu_caps, guest_wrmsr_perf_capabilities, guest_code) { - struct kvm_vcpu *vcpu; - struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, guest_code); struct ucall uc; int r, i; - vm_init_descriptor_tables(vm); + vm_init_descriptor_tables(vcpu->vm); vcpu_init_descriptor_tables(vcpu); vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); @@ -117,31 +118,21 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap) TEST_ASSERT(!r, "Post-KVM_RUN write '0x%llx'didn't fail", host_cap.capabilities ^ BIT_ULL(i)); } - - kvm_vm_free(vm); } /* * Verify KVM allows writing PERF_CAPABILITIES with all KVM-supported features * enabled, as well as '0' (to disable all features). */ -static void test_basic_perf_capabilities(union perf_capabilities host_cap) +KVM_ONE_VCPU_TEST(vmx_pmu_caps, basic_perf_capabilities, guest_code) { - struct kvm_vcpu *vcpu; - struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - - kvm_vm_free(vm); } -static void test_fungible_perf_capabilities(union perf_capabilities host_cap) +KVM_ONE_VCPU_TEST(vmx_pmu_caps, fungible_perf_capabilities, guest_code) { const uint64_t fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities; - - struct kvm_vcpu *vcpu; - struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); int bit; for_each_set_bit(bit, &fungible_caps, 64) { @@ -150,8 +141,6 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap) host_cap.capabilities & ~BIT_ULL(bit)); } vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - - kvm_vm_free(vm); } /* @@ -160,14 +149,11 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap) * separately as they are multi-bit values, e.g. toggling or setting a single * bit can generate a false positive without dedicated safeguards. */ -static void test_immutable_perf_capabilities(union perf_capabilities host_cap) +KVM_ONE_VCPU_TEST(vmx_pmu_caps, immutable_perf_capabilities, guest_code) { const uint64_t reserved_caps = (~host_cap.capabilities | immutable_caps.capabilities) & ~format_caps.capabilities; - - struct kvm_vcpu *vcpu; - struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); union perf_capabilities val = host_cap; int r, bit; @@ -201,8 +187,6 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap) TEST_ASSERT(!r, "Bad PEBS FMT = 0x%x didn't fail, host = 0x%x", val.pebs_format, host_cap.pebs_format); } - - kvm_vm_free(vm); } /* @@ -211,17 +195,13 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap) * LBR_TOS as those bits are writable across all uarch implementations (arch * LBRs will need to poke a different MSR). */ -static void test_lbr_perf_capabilities(union perf_capabilities host_cap) +KVM_ONE_VCPU_TEST(vmx_pmu_caps, lbr_perf_capabilities, guest_code) { - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; int r; if (!host_cap.lbr_format) return; - vm = vm_create_with_one_vcpu(&vcpu, NULL); - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); vcpu_set_msr(vcpu, MSR_LBR_TOS, 7); @@ -229,15 +209,11 @@ static void test_lbr_perf_capabilities(union perf_capabilities host_cap) r = _vcpu_set_msr(vcpu, MSR_LBR_TOS, 7); TEST_ASSERT(!r, "Writing LBR_TOS should fail after disabling vPMU"); - - kvm_vm_free(vm); } int main(int argc, char *argv[]) { - union perf_capabilities host_cap; - - TEST_REQUIRE(get_kvm_param_bool("enable_pmu")); + TEST_REQUIRE(kvm_is_pmu_enabled()); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION)); @@ -248,9 +224,5 @@ int main(int argc, char *argv[]) TEST_ASSERT(host_cap.full_width_write, "Full-width writes should always be supported"); - test_basic_perf_capabilities(host_cap); - test_fungible_perf_capabilities(host_cap); - test_immutable_perf_capabilities(host_cap); - test_guest_wrmsr_perf_capabilities(host_cap); - test_lbr_perf_capabilities(host_cap); + return test_harness_run(argc, argv); } diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 9ec9ab60b63e..d2ea0435f4f7 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -62,6 +62,7 @@ enum { TEST_POLL_TIMEOUT, TEST_POLL_MASKED, TEST_POLL_WAKE, + SET_VCPU_INFO, TEST_TIMER_PAST, TEST_LOCKING_SEND_RACE, TEST_LOCKING_POLL_RACE, @@ -321,6 +322,10 @@ static void guest_code(void) GUEST_SYNC(TEST_POLL_WAKE); + /* Set the vcpu_info to point at exactly the place it already is to + * make sure the attribute is functional. */ + GUEST_SYNC(SET_VCPU_INFO); + /* A timer wake an *unmasked* port which should wake us with an * actual interrupt, while we're polling on a different port. */ ports[0]++; @@ -389,6 +394,7 @@ static int cmp_timespec(struct timespec *a, struct timespec *b) return 0; } +static struct shared_info *shinfo; static struct vcpu_info *vinfo; static struct kvm_vcpu *vcpu; @@ -404,20 +410,38 @@ static void *juggle_shinfo_state(void *arg) { struct kvm_vm *vm = (struct kvm_vm *)arg; - struct kvm_xen_hvm_attr cache_activate = { + struct kvm_xen_hvm_attr cache_activate_gfn = { .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE }; - struct kvm_xen_hvm_attr cache_deactivate = { + struct kvm_xen_hvm_attr cache_deactivate_gfn = { .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, .u.shared_info.gfn = KVM_XEN_INVALID_GFN }; + struct kvm_xen_hvm_attr cache_activate_hva = { + .type = KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA, + .u.shared_info.hva = (unsigned long)shinfo + }; + + struct kvm_xen_hvm_attr cache_deactivate_hva = { + .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, + .u.shared_info.hva = 0 + }; + + int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM); + for (;;) { - __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate); - __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate_gfn); pthread_testcancel(); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate_gfn); + + if (xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA) { + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate_hva); + pthread_testcancel(); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate_hva); + } } return NULL; @@ -442,6 +466,7 @@ int main(int argc, char *argv[]) bool do_runstate_flag = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG); bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL); bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND); + bool has_shinfo_hva = !!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA); clock_gettime(CLOCK_REALTIME, &min_ts); @@ -452,7 +477,7 @@ int main(int argc, char *argv[]) SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 3, 0); virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 3); - struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR); + shinfo = addr_gpa2hva(vm, SHINFO_VADDR); int zero_fd = open("/dev/zero", O_RDONLY); TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero"); @@ -488,10 +513,16 @@ int main(int argc, char *argv[]) "Failed to read back RUNSTATE_UPDATE_FLAG attr"); } - struct kvm_xen_hvm_attr ha = { - .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, - .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE, - }; + struct kvm_xen_hvm_attr ha = {}; + + if (has_shinfo_hva) { + ha.type = KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA; + ha.u.shared_info.hva = (unsigned long)shinfo; + } else { + ha.type = KVM_XEN_ATTR_TYPE_SHARED_INFO; + ha.u.shared_info.gfn = SHINFO_ADDR / PAGE_SIZE; + } + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha); /* @@ -862,6 +893,16 @@ int main(int argc, char *argv[]) alarm(1); break; + case SET_VCPU_INFO: + if (has_shinfo_hva) { + struct kvm_xen_vcpu_attr vih = { + .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA, + .u.hva = (unsigned long)vinfo + }; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &vih); + } + break; + case TEST_TIMER_PAST: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 3df008677239..18f585684e20 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -44,8 +44,6 @@ */ static size_t mfd_def_size = MFD_DEF_SIZE; static const char *memfd_str = MEMFD_STR; -static int newpid_thread_fn2(void *arg); -static void join_newpid_thread(pid_t pid); static ssize_t fd2name(int fd, char *buf, size_t bufsize) { @@ -194,7 +192,6 @@ static unsigned int mfd_assert_get_seals(int fd) static void mfd_assert_has_seals(int fd, unsigned int seals) { char buf[PATH_MAX]; - int nbytes; unsigned int s; fd2name(fd, buf, PATH_MAX); @@ -696,7 +693,6 @@ static void mfd_assert_mode(int fd, int mode) { struct stat st; char buf[PATH_MAX]; - int nbytes; fd2name(fd, buf, PATH_MAX); @@ -715,7 +711,6 @@ static void mfd_assert_mode(int fd, int mode) static void mfd_assert_chmod(int fd, int mode) { char buf[PATH_MAX]; - int nbytes; fd2name(fd, buf, PATH_MAX); @@ -731,7 +726,6 @@ static void mfd_fail_chmod(int fd, int mode) { struct stat st; char buf[PATH_MAX]; - int nbytes; fd2name(fd, buf, PATH_MAX); @@ -1254,9 +1248,6 @@ static void test_sysctl_set_sysctl2(void) static int sysctl_simple_child(void *arg) { - int fd; - int pid; - printf("%s sysctl 0\n", memfd_str); test_sysctl_set_sysctl0(); @@ -1321,7 +1312,6 @@ static void test_sysctl_sysctl2_failset(void) static int sysctl_nested_child(void *arg) { - int fd; int pid; printf("%s nested sysctl 0\n", memfd_str); diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 4ff10ea61461..d26e962f2ac4 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -46,3 +46,4 @@ gup_longterm mkdirty va_high_addr_switch hugetlb_fault_after_madv +hugetlb_madv_vs_map diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 2453add65d12..eb5f39a2668b 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -70,6 +70,7 @@ TEST_GEN_FILES += ksm_tests TEST_GEN_FILES += ksm_functional_tests TEST_GEN_FILES += mdwe_test TEST_GEN_FILES += hugetlb_fault_after_madv +TEST_GEN_FILES += hugetlb_madv_vs_map ifneq ($(ARCH),arm64) TEST_GEN_FILES += soft-dirty @@ -114,6 +115,11 @@ TEST_PROGS := run_vmtests.sh TEST_FILES := test_vmalloc.sh TEST_FILES += test_hmm.sh TEST_FILES += va_high_addr_switch.sh +TEST_FILES += charge_reserved_hugetlb.sh +TEST_FILES += hugetlb_reparenting_test.sh + +# required by charge_reserved_hugetlb.sh +TEST_FILES += write_hugetlb_memory.sh include ../lib.mk diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index e14bdd4455f2..d680c00d2853 100755 --- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh @@ -11,6 +11,8 @@ if [[ $(id -u) -ne 0 ]]; then exit $ksft_skip fi +nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) + fault_limit_file=limit_in_bytes reservation_limit_file=rsvd.limit_in_bytes fault_usage_file=usage_in_bytes @@ -582,3 +584,5 @@ if [[ $do_umount ]]; then umount $cgroup_path rmdir $cgroup_path fi + +echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 656afba02dbc..533999b6c284 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -95,21 +95,22 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_test_result_fail("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - return -1; + ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + ret = -1; + goto out; } if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) { - ksft_test_result_fail("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } /* Start with the initial condition of 0 huge pages*/ if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_test_result_fail("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } @@ -118,16 +119,16 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_test_result_fail("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } lseek(fd, 0, SEEK_SET); if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_test_result_fail("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } @@ -139,24 +140,26 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) != strlen(initial_nr_hugepages)) { - ksft_test_result_fail("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } + ksft_print_msg("Number of huge pages allocated = %d\n", + atoi(nr_hugepages)); + if (compaction_index > 3) { ksft_print_msg("ERROR: Less that 1/%d of memory is available\n" "as huge pages\n", compaction_index); - ksft_test_result_fail("No of huge pages allocated = %d\n", (atoi(nr_hugepages))); goto close_fd; } - ksft_test_result_pass("Memory compaction succeeded. No of huge pages allocated = %d\n", - (atoi(nr_hugepages))); ret = 0; close_fd: close(fd); + out: + ksft_test_result(ret == 0, "check_compaction\n"); return ret; } @@ -174,7 +177,7 @@ int main(int argc, char **argv) ksft_print_header(); if (prereq() || geteuid()) - return ksft_exit_pass(); + return ksft_exit_skip("Prerequisites unsatisfied\n"); ksft_set_plan(1); diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index f32d99565c5e..e74107185324 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -19,6 +19,7 @@ #include <sys/mman.h> #include <fcntl.h> #include "vm_util.h" +#include "../kselftest.h" #define MIN_FREE_PAGES 20 #define NR_HUGE_PAGES 10 /* common number of pages to map/allocate */ @@ -78,7 +79,7 @@ int main(int argc, char **argv) free_hugepages = get_free_hugepages(); if (free_hugepages < MIN_FREE_PAGES) { printf("Not enough free huge pages to test, exiting!\n"); - exit(1); + exit(KSFT_SKIP); } fd = memfd_create(argv[0], MFD_HUGETLB); diff --git a/tools/testing/selftests/mm/hugetlb_madv_vs_map.c b/tools/testing/selftests/mm/hugetlb_madv_vs_map.c new file mode 100644 index 000000000000..d01e8d4901d0 --- /dev/null +++ b/tools/testing/selftests/mm/hugetlb_madv_vs_map.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test case that must run on a system with one and only one huge page available. + * # echo 1 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages + * + * During setup, the test allocates the only available page, and starts three threads: + * - thread1: + * * madvise(MADV_DONTNEED) on the allocated huge page + * - thread 2: + * * Write to the allocated huge page + * - thread 3: + * * Try to allocated an extra huge page (which must not available) + * + * The test fails if thread3 is able to allocate a page. + * + * Touching the first page after thread3's allocation will raise a SIGBUS + * + * Author: Breno Leitao <leitao@debian.org> + */ +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <unistd.h> + +#include "vm_util.h" +#include "../kselftest.h" + +#define MMAP_SIZE (1 << 21) +#define INLOOP_ITER 100 + +char *huge_ptr; + +/* Touch the memory while it is being madvised() */ +void *touch(void *unused) +{ + for (int i = 0; i < INLOOP_ITER; i++) + huge_ptr[0] = '.'; + + return NULL; +} + +void *madv(void *unused) +{ + for (int i = 0; i < INLOOP_ITER; i++) + madvise(huge_ptr, MMAP_SIZE, MADV_DONTNEED); + + return NULL; +} + +/* + * We got here, and there must be no huge page available for mapping + * The other hugepage should be flipping from used <-> reserved, because + * of madvise(DONTNEED). + */ +void *map_extra(void *unused) +{ + void *ptr; + + for (int i = 0; i < INLOOP_ITER; i++) { + ptr = mmap(NULL, MMAP_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + + if ((long)ptr != -1) { + /* Touching the other page now will cause a SIGBUG + * huge_ptr[0] = '1'; + */ + return ptr; + } + } + + return NULL; +} + +int main(void) +{ + pthread_t thread1, thread2, thread3; + unsigned long free_hugepages; + void *ret; + + /* + * On kernel 6.7, we are able to reproduce the problem with ~10 + * interactions + */ + int max = 10; + + free_hugepages = get_free_hugepages(); + + if (free_hugepages != 1) { + ksft_exit_skip("This test needs one and only one page to execute. Got %lu\n", + free_hugepages); + } + + while (max--) { + huge_ptr = mmap(NULL, MMAP_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + + if ((unsigned long)huge_ptr == -1) { + ksft_exit_skip("Failed to allocated huge page\n"); + return KSFT_SKIP; + } + + pthread_create(&thread1, NULL, madv, NULL); + pthread_create(&thread2, NULL, touch, NULL); + pthread_create(&thread3, NULL, map_extra, NULL); + + pthread_join(thread1, NULL); + pthread_join(thread2, NULL); + pthread_join(thread3, &ret); + + if (ret) { + ksft_test_result_fail("Unexpected huge page allocation\n"); + return KSFT_FAIL; + } + + /* Unmap and restart */ + munmap(huge_ptr, MMAP_SIZE); + } + + return KSFT_PASS; +} diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh index 14d26075c863..11f9bbe7dc22 100755 --- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh @@ -11,6 +11,7 @@ if [[ $(id -u) -ne 0 ]]; then exit $ksft_skip fi +nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) usage_file=usage_in_bytes if [[ "$1" == "-cgroup-v2" ]]; then @@ -248,5 +249,9 @@ cleanup echo ALL PASS -umount $CGROUP_ROOT -rm -rf $CGROUP_ROOT +if [[ $do_umount ]]; then + umount $CGROUP_ROOT + rm -rf $CGROUP_ROOT +fi + +echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index fbff0dd09191..d615767e396b 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -155,12 +155,12 @@ static char *mmap_and_merge_range(char val, unsigned long size, int prot, /* Stabilize accounting by disabling KSM completely. */ if (ksm_unmerge()) { ksft_test_result_fail("Disabling (unmerging) KSM failed\n"); - goto unmap; + return MAP_FAILED; } if (get_my_merging_pages() > 0) { ksft_test_result_fail("Still pages merged\n"); - goto unmap; + return MAP_FAILED; } map = mmap(NULL, size, PROT_READ|PROT_WRITE, diff --git a/tools/testing/selftests/mm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index 598159f3df1f..b74813fdc951 100644 --- a/tools/testing/selftests/mm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c @@ -12,6 +12,7 @@ #include <stdio.h> #include <stdlib.h> #include <unistd.h> +#include "../kselftest.h" static void dump_maps(void) { @@ -28,15 +29,12 @@ static unsigned long find_base_addr(unsigned long size) flags = MAP_PRIVATE | MAP_ANONYMOUS; addr = mmap(NULL, size, PROT_NONE, flags, -1, 0); - if (addr == MAP_FAILED) { - printf("Error: couldn't map the space we need for the test\n"); - return 0; - } + if (addr == MAP_FAILED) + ksft_exit_fail_msg("Error: couldn't map the space we need for the test\n"); + + if (munmap(addr, size) != 0) + ksft_exit_fail_msg("Error: munmap failed\n"); - if (munmap(addr, size) != 0) { - printf("Error: couldn't map the space we need for the test\n"); - return 0; - } return (unsigned long)addr; } @@ -46,51 +44,39 @@ int main(void) unsigned long flags, addr, size, page_size; char *p; + ksft_print_header(); + ksft_set_plan(9); + page_size = sysconf(_SC_PAGE_SIZE); - //let's find a base addr that is free before we start the tests + /* let's find a base addr that is free before we start the tests */ size = 5 * page_size; base_addr = find_base_addr(size); - if (!base_addr) { - printf("Error: couldn't map the space we need for the test\n"); - return 1; - } flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE; - // Check we can map all the areas we need below - errno = 0; + /* Check we can map all the areas we need below */ addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p == MAP_FAILED) { dump_maps(); - printf("Error: couldn't map the space we need for the test\n"); - return 1; + ksft_exit_fail_msg("Error: couldn't map the space we need for the test\n"); } - - errno = 0; if (munmap((void *)addr, 5 * page_size) != 0) { dump_maps(); - printf("Error: munmap failed!?\n"); - return 1; + ksft_exit_fail_msg("Error: munmap failed!?\n"); } - printf("unmap() successful\n"); + ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - errno = 0; addr = base_addr + page_size; size = 3 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p == MAP_FAILED) { dump_maps(); - printf("Error: first mmap() failed unexpectedly\n"); - return 1; + ksft_exit_fail_msg("Error: first mmap() failed unexpectedly\n"); } + ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); /* * Exact same mapping again: @@ -100,17 +86,14 @@ int main(void) * +3 | mapped | new * +4 | free | new */ - errno = 0; addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p != MAP_FAILED) { dump_maps(); - printf("Error:1: mmap() succeeded when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:1: mmap() succeeded when it shouldn't have\n"); } + ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); /* * Second mapping contained within first: @@ -121,17 +104,14 @@ int main(void) * +3 | mapped | * +4 | free | */ - errno = 0; addr = base_addr + (2 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p != MAP_FAILED) { dump_maps(); - printf("Error:2: mmap() succeeded when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:2: mmap() succeeded when it shouldn't have\n"); } + ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); /* * Overlap end of existing mapping: @@ -141,17 +121,14 @@ int main(void) * +3 | mapped | new * +4 | free | new */ - errno = 0; addr = base_addr + (3 * page_size); size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p != MAP_FAILED) { dump_maps(); - printf("Error:3: mmap() succeeded when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:3: mmap() succeeded when it shouldn't have\n"); } + ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); /* * Overlap start of existing mapping: @@ -161,17 +138,14 @@ int main(void) * +3 | mapped | * +4 | free | */ - errno = 0; addr = base_addr; size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p != MAP_FAILED) { dump_maps(); - printf("Error:4: mmap() succeeded when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:4: mmap() succeeded when it shouldn't have\n"); } + ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); /* * Adjacent to start of existing mapping: @@ -181,17 +155,14 @@ int main(void) * +3 | mapped | * +4 | free | */ - errno = 0; addr = base_addr; size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p == MAP_FAILED) { dump_maps(); - printf("Error:5: mmap() failed when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:5: mmap() failed when it shouldn't have\n"); } + ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); /* * Adjacent to end of existing mapping: @@ -201,27 +172,22 @@ int main(void) * +3 | mapped | * +4 | free | new */ - errno = 0; addr = base_addr + (4 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p == MAP_FAILED) { dump_maps(); - printf("Error:6: mmap() failed when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:6: mmap() failed when it shouldn't have\n"); } + ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); addr = base_addr; size = 5 * page_size; if (munmap((void *)addr, size) != 0) { dump_maps(); - printf("Error: munmap failed!?\n"); - return 1; + ksft_exit_fail_msg("Error: munmap failed!?\n"); } - printf("unmap() successful\n"); + ksft_test_result_pass("Base Address unmap() successful\n"); - printf("OK\n"); - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 86e8f2048a40..a1f005a90a4f 100644 --- a/tools/testing/selftests/mm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c @@ -16,6 +16,7 @@ #include <sys/mman.h> #include <fcntl.h> #include "vm_util.h" +#include "../kselftest.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) @@ -31,7 +32,7 @@ static void check_bytes(char *addr) { - printf("First hex is %x\n", *((unsigned int *)addr)); + ksft_print_msg("First hex is %x\n", *((unsigned int *)addr)); } static void write_bytes(char *addr, size_t length) @@ -42,23 +43,21 @@ static void write_bytes(char *addr, size_t length) *(addr + i) = (char)i; } -static int read_bytes(char *addr, size_t length) +static void read_bytes(char *addr, size_t length) { unsigned long i; check_bytes(addr); for (i = 0; i < length; i++) - if (*(addr + i) != (char)i) { - printf("Mismatch at %lu\n", i); - return 1; - } - return 0; + if (*(addr + i) != (char)i) + ksft_exit_fail_msg("Mismatch at %lu\n", i); + + ksft_test_result_pass("Read correct data\n"); } int main(int argc, char **argv) { void *addr; - int ret; size_t hugepage_size; size_t length = LENGTH; int flags = FLAGS; @@ -69,6 +68,9 @@ int main(int argc, char **argv) if (hugepage_size > length) length = hugepage_size; + ksft_print_header(); + ksft_set_plan(1); + if (argc > 1) length = atol(argv[1]) << 20; if (argc > 2) { @@ -78,27 +80,23 @@ int main(int argc, char **argv) } if (shift) - printf("%u kB hugepages\n", 1 << (shift - 10)); + ksft_print_msg("%u kB hugepages\n", 1 << (shift - 10)); else - printf("Default size hugepages\n"); - printf("Mapping %lu Mbytes\n", (unsigned long)length >> 20); + ksft_print_msg("Default size hugepages\n"); + ksft_print_msg("Mapping %lu Mbytes\n", (unsigned long)length >> 20); addr = mmap(ADDR, length, PROTECTION, flags, -1, 0); - if (addr == MAP_FAILED) { - perror("mmap"); - exit(1); - } + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mmap: %s\n", strerror(errno)); - printf("Returned address is %p\n", addr); + ksft_print_msg("Returned address is %p\n", addr); check_bytes(addr); write_bytes(addr, length); - ret = read_bytes(addr, length); + read_bytes(addr, length); /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */ - if (munmap(addr, length)) { - perror("munmap"); - exit(1); - } + if (munmap(addr, length)) + ksft_exit_fail_msg("munmap: %s\n", strerror(errno)); - return ret; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/map_populate.c b/tools/testing/selftests/mm/map_populate.c index 7945d0754875..5c8a53869b1b 100644 --- a/tools/testing/selftests/mm/map_populate.c +++ b/tools/testing/selftests/mm/map_populate.c @@ -16,19 +16,21 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> +#include "../kselftest.h" #define MMAP_SZ 4096 -#define BUG_ON(condition, description) \ - do { \ - if (condition) { \ - fprintf(stderr, "[FAIL]\t%s:%d\t%s:%s\n", __func__, \ - __LINE__, (description), strerror(errno)); \ - exit(1); \ - } \ +#define BUG_ON(condition, description) \ + do { \ + if (condition) \ + ksft_exit_fail_msg("[FAIL]\t%s:%d\t%s:%s\n", \ + __func__, __LINE__, (description), \ + strerror(errno)); \ } while (0) -static int parent_f(int sock, unsigned long *smap, int child) +#define TESTS_IN_CHILD 2 + +static void parent_f(int sock, unsigned long *smap, int child) { int status, ret; @@ -43,9 +45,10 @@ static int parent_f(int sock, unsigned long *smap, int child) BUG_ON(ret <= 0, "write(sock)"); waitpid(child, &status, 0); - BUG_ON(!WIFEXITED(status), "child in unexpected state"); - return WEXITSTATUS(status); + /* The ksft macros don't keep counters between processes */ + ksft_cnt.ksft_pass = WEXITSTATUS(status); + ksft_cnt.ksft_fail = TESTS_IN_CHILD - WEXITSTATUS(status); } static int child_f(int sock, unsigned long *smap, int fd) @@ -64,10 +67,11 @@ static int child_f(int sock, unsigned long *smap, int fd) ret = read(sock, &buf, sizeof(int)); BUG_ON(ret <= 0, "read(sock)"); - BUG_ON(*smap == 0x22222BAD, "MAP_POPULATE didn't COW private page"); - BUG_ON(*smap != 0xdeadbabe, "mapping was corrupted"); + ksft_test_result(*smap != 0x22222BAD, "MAP_POPULATE COW private page\n"); + ksft_test_result(*smap == 0xdeadbabe, "The mapping state\n"); - return 0; + /* The ksft macros don't keep counters between processes */ + return ksft_cnt.ksft_pass; } int main(int argc, char **argv) @@ -76,6 +80,9 @@ int main(int argc, char **argv) FILE *ftmp; unsigned long *smap; + ksft_print_header(); + ksft_set_plan(TESTS_IN_CHILD); + ftmp = tmpfile(); BUG_ON(!ftmp, "tmpfile()"); @@ -101,7 +108,9 @@ int main(int argc, char **argv) ret = close(sock[0]); BUG_ON(ret, "close()"); - return parent_f(sock[1], smap, child); + parent_f(sock[1], smap, child); + + ksft_finished(); } ret = close(sock[1]); diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index 1fba77df7f62..1cd80b0f76c3 100644 --- a/tools/testing/selftests/mm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c @@ -13,6 +13,7 @@ #include <sys/ipc.h> #include <sys/shm.h> #include <time.h> +#include "../kselftest.h" #include "mlock2.h" #define CHUNK_UNIT (128 * 1024) @@ -31,14 +32,14 @@ int set_cap_limits(rlim_t max) new.rlim_cur = max; new.rlim_max = max; if (setrlimit(RLIMIT_MEMLOCK, &new)) { - perror("setrlimit() returns error\n"); + ksft_perror("setrlimit() returns error\n"); return -1; } /* drop capabilities including CAP_IPC_LOCK */ if (cap_set_proc(cap)) { - perror("cap_set_proc() returns error\n"); - return -2; + ksft_perror("cap_set_proc() returns error\n"); + return -1; } return 0; @@ -52,27 +53,24 @@ int get_proc_locked_vm_size(void) unsigned long lock_size = 0; f = fopen("/proc/self/status", "r"); - if (!f) { - perror("fopen"); - return -1; - } + if (!f) + ksft_exit_fail_msg("fopen: %s\n", strerror(errno)); while (fgets(line, 1024, f)) { if (strstr(line, "VmLck")) { ret = sscanf(line, "VmLck:\t%8lu kB", &lock_size); if (ret <= 0) { - printf("sscanf() on VmLck error: %s: %d\n", - line, ret); fclose(f); - return -1; + ksft_exit_fail_msg("sscanf() on VmLck error: %s: %d\n", + line, ret); } fclose(f); return (int)(lock_size << 10); } } - perror("cannot parse VmLck in /proc/self/status\n"); fclose(f); + ksft_exit_fail_msg("cannot parse VmLck in /proc/self/status: %s\n", strerror(errno)); return -1; } @@ -91,10 +89,8 @@ int get_proc_page_size(unsigned long addr) size_t size; smaps = seek_to_smaps_entry(addr); - if (!smaps) { - printf("Unable to parse /proc/self/smaps\n"); - return 0; - } + if (!smaps) + ksft_exit_fail_msg("Unable to parse /proc/self/smaps\n"); while (getline(&line, &size, smaps) > 0) { if (!strstr(line, "MMUPageSize")) { @@ -105,12 +101,9 @@ int get_proc_page_size(unsigned long addr) } /* found the MMUPageSize of this section */ - if (sscanf(line, "MMUPageSize: %8lu kB", - &mmupage_size) < 1) { - printf("Unable to parse smaps entry for Size:%s\n", - line); - break; - } + if (sscanf(line, "MMUPageSize: %8lu kB", &mmupage_size) < 1) + ksft_exit_fail_msg("Unable to parse smaps entry for Size:%s\n", + line); } free(line); @@ -136,7 +129,7 @@ int get_proc_page_size(unsigned long addr) * return value: 0 - success * else: failure */ -int test_mlock_within_limit(char *p, int alloc_size) +static void test_mlock_within_limit(char *p, int alloc_size) { int i; int ret = 0; @@ -145,11 +138,9 @@ int test_mlock_within_limit(char *p, int alloc_size) int page_size = 0; getrlimit(RLIMIT_MEMLOCK, &cur); - if (cur.rlim_cur < alloc_size) { - printf("alloc_size[%d] < %u rlimit,lead to mlock failure\n", - alloc_size, (unsigned int)cur.rlim_cur); - return -1; - } + if (cur.rlim_cur < alloc_size) + ksft_exit_fail_msg("alloc_size[%d] < %u rlimit,lead to mlock failure\n", + alloc_size, (unsigned int)cur.rlim_cur); srand(time(NULL)); for (i = 0; i < TEST_LOOP; i++) { @@ -169,13 +160,11 @@ int test_mlock_within_limit(char *p, int alloc_size) ret = mlock2_(p + start_offset, lock_size, MLOCK_ONFAULT); - if (ret) { - printf("%s() failure at |%p(%d)| mlock:|%p(%d)|\n", - is_mlock ? "mlock" : "mlock2", - p, alloc_size, - p + start_offset, lock_size); - return ret; - } + if (ret) + ksft_exit_fail_msg("%s() failure at |%p(%d)| mlock:|%p(%d)|\n", + is_mlock ? "mlock" : "mlock2", + p, alloc_size, + p + start_offset, lock_size); } /* @@ -183,18 +172,12 @@ int test_mlock_within_limit(char *p, int alloc_size) */ locked_vm_size = get_proc_locked_vm_size(); page_size = get_proc_page_size((unsigned long)p); - if (page_size == 0) { - printf("cannot get proc MMUPageSize\n"); - return -1; - } - if (locked_vm_size > PAGE_ALIGN(alloc_size, page_size) + page_size) { - printf("test_mlock_within_limit() left VmLck:%d on %d chunk\n", - locked_vm_size, alloc_size); - return -1; - } + if (locked_vm_size > PAGE_ALIGN(alloc_size, page_size) + page_size) + ksft_exit_fail_msg("%s left VmLck:%d on %d chunk\n", + __func__, locked_vm_size, alloc_size); - return 0; + ksft_test_result_pass("%s\n", __func__); } @@ -213,7 +196,7 @@ int test_mlock_within_limit(char *p, int alloc_size) * return value: 0 - success * else: failure */ -int test_mlock_outof_limit(char *p, int alloc_size) +static void test_mlock_outof_limit(char *p, int alloc_size) { int i; int ret = 0; @@ -221,11 +204,9 @@ int test_mlock_outof_limit(char *p, int alloc_size) struct rlimit cur; getrlimit(RLIMIT_MEMLOCK, &cur); - if (cur.rlim_cur >= alloc_size) { - printf("alloc_size[%d] >%u rlimit, violates test condition\n", - alloc_size, (unsigned int)cur.rlim_cur); - return -1; - } + if (cur.rlim_cur >= alloc_size) + ksft_exit_fail_msg("alloc_size[%d] >%u rlimit, violates test condition\n", + alloc_size, (unsigned int)cur.rlim_cur); old_locked_vm_size = get_proc_locked_vm_size(); srand(time(NULL)); @@ -240,56 +221,47 @@ int test_mlock_outof_limit(char *p, int alloc_size) else ret = mlock2_(p + start_offset, lock_size, MLOCK_ONFAULT); - if (ret == 0) { - printf("%s() succeeds? on %p(%d) mlock%p(%d)\n", - is_mlock ? "mlock" : "mlock2", - p, alloc_size, - p + start_offset, lock_size); - return -1; - } + if (ret == 0) + ksft_exit_fail_msg("%s() succeeds? on %p(%d) mlock%p(%d)\n", + is_mlock ? "mlock" : "mlock2", + p, alloc_size, p + start_offset, lock_size); } locked_vm_size = get_proc_locked_vm_size(); - if (locked_vm_size != old_locked_vm_size) { - printf("tests leads to new mlocked page: old[%d], new[%d]\n", - old_locked_vm_size, - locked_vm_size); - return -1; - } + if (locked_vm_size != old_locked_vm_size) + ksft_exit_fail_msg("tests leads to new mlocked page: old[%d], new[%d]\n", + old_locked_vm_size, + locked_vm_size); - return 0; + ksft_test_result_pass("%s\n", __func__); } int main(int argc, char **argv) { char *p = NULL; - int ret = 0; + + ksft_print_header(); if (set_cap_limits(MLOCK_RLIMIT_SIZE)) - return -1; + ksft_finished(); + + ksft_set_plan(2); p = malloc(MLOCK_WITHIN_LIMIT_SIZE); - if (p == NULL) { - perror("malloc() failure\n"); - return -1; - } - ret = test_mlock_within_limit(p, MLOCK_WITHIN_LIMIT_SIZE); - if (ret) - return ret; + if (p == NULL) + ksft_exit_fail_msg("malloc() failure: %s\n", strerror(errno)); + + test_mlock_within_limit(p, MLOCK_WITHIN_LIMIT_SIZE); munlock(p, MLOCK_WITHIN_LIMIT_SIZE); free(p); - p = malloc(MLOCK_OUTOF_LIMIT_SIZE); - if (p == NULL) { - perror("malloc() failure\n"); - return -1; - } - ret = test_mlock_outof_limit(p, MLOCK_OUTOF_LIMIT_SIZE); - if (ret) - return ret; + if (p == NULL) + ksft_exit_fail_msg("malloc() failure: %s\n", strerror(errno)); + + test_mlock_outof_limit(p, MLOCK_OUTOF_LIMIT_SIZE); munlock(p, MLOCK_OUTOF_LIMIT_SIZE); free(p); - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c index 80cddc0de206..26f744188ad0 100644 --- a/tools/testing/selftests/mm/mlock2-tests.c +++ b/tools/testing/selftests/mm/mlock2-tests.c @@ -7,9 +7,8 @@ #include <sys/time.h> #include <sys/resource.h> #include <stdbool.h> -#include "mlock2.h" - #include "../kselftest.h" +#include "mlock2.h" struct vm_boundaries { unsigned long start; @@ -40,14 +39,14 @@ static int get_vm_area(unsigned long addr, struct vm_boundaries *area) while(fgets(line, 1024, file)) { end_addr = strchr(line, '-'); if (!end_addr) { - printf("cannot parse /proc/self/maps\n"); + ksft_print_msg("cannot parse /proc/self/maps\n"); goto out; } *end_addr = '\0'; end_addr++; stop = strchr(end_addr, ' '); if (!stop) { - printf("cannot parse /proc/self/maps\n"); + ksft_print_msg("cannot parse /proc/self/maps\n"); goto out; } @@ -78,7 +77,7 @@ static bool is_vmflag_set(unsigned long addr, const char *vmflag) smaps = seek_to_smaps_entry(addr); if (!smaps) { - printf("Unable to parse /proc/self/smaps\n"); + ksft_print_msg("Unable to parse /proc/self/smaps\n"); goto out; } @@ -115,7 +114,7 @@ static unsigned long get_value_for_name(unsigned long addr, const char *name) smaps = seek_to_smaps_entry(addr); if (!smaps) { - printf("Unable to parse /proc/self/smaps\n"); + ksft_print_msg("Unable to parse /proc/self/smaps\n"); goto out; } @@ -129,7 +128,7 @@ static unsigned long get_value_for_name(unsigned long addr, const char *name) value_ptr = line + strlen(name); if (sscanf(value_ptr, "%lu kB", &value) < 1) { - printf("Unable to parse smaps entry for Size\n"); + ksft_print_msg("Unable to parse smaps entry for Size\n"); goto out; } break; @@ -180,57 +179,45 @@ static int lock_check(unsigned long addr) static int unlock_lock_check(char *map) { if (is_vmflag_set((unsigned long)map, LOCKED)) { - printf("VMA flag %s is present on page 1 after unlock\n", LOCKED); + ksft_print_msg("VMA flag %s is present on page 1 after unlock\n", LOCKED); return 1; } return 0; } -static int test_mlock_lock() +static void test_mlock_lock(void) { char *map; - int ret = 1; unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (map == MAP_FAILED) { - perror("test_mlock_locked mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); if (mlock2_(map, 2 * page_size, 0)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("mlock2(0)"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlock2(0): %s\n", strerror(errno)); } - if (!lock_check((unsigned long)map)) - goto unmap; + ksft_test_result(lock_check((unsigned long)map), "%s: Locked\n", __func__); /* Now unlock and recheck attributes */ if (munlock(map, 2 * page_size)) { - perror("munlock()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlock(): %s\n", strerror(errno)); } - ret = unlock_lock_check(map); - -unmap: + ksft_test_result(!unlock_lock_check(map), "%s: Locked\n", __func__); munmap(map, 2 * page_size); -out: - return ret; } static int onfault_check(char *map) { *map = 'a'; if (!is_vma_lock_on_fault((unsigned long)map)) { - printf("VMA is not marked for lock on fault\n"); + ksft_print_msg("VMA is not marked for lock on fault\n"); return 1; } @@ -243,172 +230,131 @@ static int unlock_onfault_check(char *map) if (is_vma_lock_on_fault((unsigned long)map) || is_vma_lock_on_fault((unsigned long)map + page_size)) { - printf("VMA is still lock on fault after unlock\n"); + ksft_print_msg("VMA is still lock on fault after unlock\n"); return 1; } return 0; } -static int test_mlock_onfault() +static void test_mlock_onfault(void) { char *map; - int ret = 1; unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (map == MAP_FAILED) { - perror("test_mlock_locked mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("mlock2(MLOCK_ONFAULT)"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlock2(MLOCK_ONFAULT): %s\n", strerror(errno)); } - if (onfault_check(map)) - goto unmap; + ksft_test_result(!onfault_check(map), "%s: VMA marked for lock on fault\n", __func__); /* Now unlock and recheck attributes */ if (munlock(map, 2 * page_size)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("munlock()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlock(): %s\n", strerror(errno)); } - ret = unlock_onfault_check(map); -unmap: + ksft_test_result(!unlock_onfault_check(map), "VMA open lock after fault\n"); munmap(map, 2 * page_size); -out: - return ret; } -static int test_lock_onfault_of_present() +static void test_lock_onfault_of_present(void) { char *map; - int ret = 1; unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (map == MAP_FAILED) { - perror("test_mlock_locked mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); *map = 'a'; if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("mlock2(MLOCK_ONFAULT)"); - goto unmap; + munmap(map, 2 * page_size); + ksft_test_result_fail("mlock2(MLOCK_ONFAULT) error: %s", strerror(errno)); } - if (!is_vma_lock_on_fault((unsigned long)map) || - !is_vma_lock_on_fault((unsigned long)map + page_size)) { - printf("VMA with present pages is not marked lock on fault\n"); - goto unmap; - } - ret = 0; -unmap: + ksft_test_result(is_vma_lock_on_fault((unsigned long)map) || + is_vma_lock_on_fault((unsigned long)map + page_size), + "VMA with present pages is not marked lock on fault\n"); munmap(map, 2 * page_size); -out: - return ret; } -static int test_munlockall() +static void test_munlockall0(void) { char *map; - int ret = 1; unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - - if (map == MAP_FAILED) { - perror("test_munlockall mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s\n", strerror(errno)); if (mlockall(MCL_CURRENT)) { - perror("mlockall(MCL_CURRENT)"); - goto out; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlockall(MCL_CURRENT): %s\n", strerror(errno)); } - if (!lock_check((unsigned long)map)) - goto unmap; + ksft_test_result(lock_check((unsigned long)map), "%s: Locked memory area\n", __func__); if (munlockall()) { - perror("munlockall()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlockall(): %s\n", strerror(errno)); } - if (unlock_lock_check(map)) - goto unmap; - + ksft_test_result(!unlock_lock_check(map), "%s: No locked memory\n", __func__); munmap(map, 2 * page_size); +} + +static void test_munlockall1(void) +{ + char *map; + unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - - if (map == MAP_FAILED) { - perror("test_munlockall second mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); if (mlockall(MCL_CURRENT | MCL_ONFAULT)) { - perror("mlockall(MCL_CURRENT | MCL_ONFAULT)"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlockall(MCL_CURRENT | MCL_ONFAULT): %s\n", strerror(errno)); } - if (onfault_check(map)) - goto unmap; + ksft_test_result(!onfault_check(map), "%s: VMA marked for lock on fault\n", __func__); if (munlockall()) { - perror("munlockall()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlockall(): %s\n", strerror(errno)); } - if (unlock_onfault_check(map)) - goto unmap; + ksft_test_result(!unlock_onfault_check(map), "%s: Unlocked\n", __func__); if (mlockall(MCL_CURRENT | MCL_FUTURE)) { - perror("mlockall(MCL_CURRENT | MCL_FUTURE)"); - goto out; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlockall(MCL_CURRENT | MCL_FUTURE): %s\n", strerror(errno)); } - if (!lock_check((unsigned long)map)) - goto unmap; + ksft_test_result(lock_check((unsigned long)map), "%s: Locked\n", __func__); if (munlockall()) { - perror("munlockall()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlockall() %s\n", strerror(errno)); } - ret = unlock_lock_check(map); - -unmap: + ksft_test_result(!unlock_lock_check(map), "%s: No locked memory\n", __func__); munmap(map, 2 * page_size); -out: - munlockall(); - return ret; } -static int test_vma_management(bool call_mlock) +static void test_vma_management(bool call_mlock) { - int ret = 1; void *map; unsigned long page_size = getpagesize(); struct vm_boundaries page1; @@ -417,25 +363,19 @@ static int test_vma_management(bool call_mlock) map = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (map == MAP_FAILED) { - perror("mmap()"); - return ret; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("mlock(ONFAULT)\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("mlock error: %s", strerror(errno)); } if (get_vm_area((unsigned long)map, &page1) || get_vm_area((unsigned long)map + page_size, &page2) || get_vm_area((unsigned long)map + page_size * 2, &page3)) { - printf("couldn't find mapping in /proc/self/maps\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("couldn't find mapping in /proc/self/maps"); } /* @@ -444,76 +384,86 @@ static int test_vma_management(bool call_mlock) * not a failure) */ if (page1.start != page2.start || page2.start != page3.start) { - printf("VMAs are not merged to start, aborting test\n"); - ret = 0; - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("VMAs are not merged to start, aborting test"); } if (munlock(map + page_size, page_size)) { - perror("munlock()"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("munlock(): %s", strerror(errno)); } if (get_vm_area((unsigned long)map, &page1) || get_vm_area((unsigned long)map + page_size, &page2) || get_vm_area((unsigned long)map + page_size * 2, &page3)) { - printf("couldn't find mapping in /proc/self/maps\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("couldn't find mapping in /proc/self/maps"); } /* All three VMAs should be different */ if (page1.start == page2.start || page2.start == page3.start) { - printf("failed to split VMA for munlock\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("failed to split VMA for munlock"); } /* Now unlock the first and third page and check the VMAs again */ if (munlock(map, page_size * 3)) { - perror("munlock()"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("munlock(): %s", strerror(errno)); } if (get_vm_area((unsigned long)map, &page1) || get_vm_area((unsigned long)map + page_size, &page2) || get_vm_area((unsigned long)map + page_size * 2, &page3)) { - printf("couldn't find mapping in /proc/self/maps\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("couldn't find mapping in /proc/self/maps"); } /* Now all three VMAs should be the same */ if (page1.start != page2.start || page2.start != page3.start) { - printf("failed to merge VMAs after munlock\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("failed to merge VMAs after munlock"); } - ret = 0; -out: + ksft_test_result_pass("%s call_mlock %d\n", __func__, call_mlock); munmap(map, 3 * page_size); - return ret; } -static int test_mlockall(int (test_function)(bool call_mlock)) +static void test_mlockall(void) { - int ret = 1; + if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) + ksft_exit_fail_msg("mlockall failed: %s\n", strerror(errno)); - if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) { - perror("mlockall"); - return ret; - } - - ret = test_function(false); + test_vma_management(false); munlockall(); - return ret; } int main(int argc, char **argv) { - int ret = 0; - ret += test_mlock_lock(); - ret += test_mlock_onfault(); - ret += test_munlockall(); - ret += test_lock_onfault_of_present(); - ret += test_vma_management(true); - ret += test_mlockall(test_vma_management); - return ret; + int ret, size = 3 * getpagesize(); + void *map; + + ksft_print_header(); + + map = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); + + ret = mlock2_(map, size, MLOCK_ONFAULT); + if (ret && errno == ENOSYS) + ksft_finished(); + + munmap(map, size); + + ksft_set_plan(13); + + test_mlock_lock(); + test_mlock_onfault(); + test_munlockall0(); + test_munlockall1(); + test_lock_onfault_of_present(); + test_vma_management(true); + test_mlockall(); + + ksft_finished(); } diff --git a/tools/testing/selftests/mm/mlock2.h b/tools/testing/selftests/mm/mlock2.h index 8e02991b313c..4417eaa5cfb7 100644 --- a/tools/testing/selftests/mm/mlock2.h +++ b/tools/testing/selftests/mm/mlock2.h @@ -6,12 +6,7 @@ static int mlock2_(void *start, size_t len, int flags) { -#ifdef __NR_mlock2 return syscall(__NR_mlock2, start, len, flags); -#else - errno = ENOSYS; - return -1; -#endif } static FILE *seek_to_smaps_entry(unsigned long addr) @@ -27,10 +22,8 @@ static FILE *seek_to_smaps_entry(unsigned long addr) char path[BUFSIZ]; file = fopen("/proc/self/smaps", "r"); - if (!file) { - perror("fopen smaps"); - _exit(1); - } + if (!file) + ksft_exit_fail_msg("fopen smaps: %s\n", strerror(errno)); while (getline(&line, &size, file) > 0) { if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n", diff --git a/tools/testing/selftests/mm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index d822004a374e..100370a7111d 100644 --- a/tools/testing/selftests/mm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c @@ -26,19 +26,15 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) buf = (char *)mmap(NULL, nr_pages * psize(), PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, 0, 0); - if (buf == MAP_FAILED) { - perror("mmap failed, halting the test"); - return KSFT_FAIL; - } + if (buf == MAP_FAILED) + ksft_exit_fail_msg("mmap failed, halting the test: %s\n", strerror(errno)); for (i = 0; i < nr_pages; i++) *((unsigned long *)(buf + (i * psize()))) = i; /* Signal the parent that the child is ready */ - if (write(pipefd, "", 1) < 0) { - perror("write"); - return KSFT_FAIL; - } + if (write(pipefd, "", 1) < 0) + ksft_exit_fail_msg("write: %s\n", strerror(errno)); /* Wait to be killed (when reparenting happens) */ while (getppid() == ppid && timeout > 0) { @@ -54,23 +50,17 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) /* The process_mrelease calls in this test are expected to fail */ static void run_negative_tests(int pidfd) { - int res; /* Test invalid flags. Expect to fail with EINVAL error code. */ if (!syscall(__NR_process_mrelease, pidfd, (unsigned int)-1) || errno != EINVAL) { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("process_mrelease with wrong flags"); - exit(res); + ksft_exit_fail_msg("process_mrelease with wrong flags: %s\n", strerror(errno)); } /* * Test reaping while process is alive with no pending SIGKILL. * Expect to fail with EINVAL error code. */ - if (!syscall(__NR_process_mrelease, pidfd, 0) || errno != EINVAL) { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("process_mrelease on a live process"); - exit(res); - } + if (!syscall(__NR_process_mrelease, pidfd, 0) || errno != EINVAL) + ksft_exit_fail_msg("process_mrelease on a live process: %s\n", strerror(errno)); } static int child_main(int pipefd[], size_t size) @@ -93,11 +83,18 @@ int main(void) char byte; int res; + ksft_print_header(); + ksft_set_plan(1); + /* Test a wrong pidfd */ if (!syscall(__NR_process_mrelease, -1, 0) || errno != EBADF) { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("process_mrelease with wrong pidfd"); - exit(res); + if (errno == ENOSYS) { + ksft_test_result_skip("process_mrelease not implemented\n"); + ksft_finished(); + } else { + ksft_exit_fail_msg("process_mrelease with wrong pidfd: %s", + strerror(errno)); + } } /* Start the test with 1MB child memory allocation */ @@ -107,16 +104,14 @@ retry: * Pipe for the child to signal when it's done allocating * memory */ - if (pipe(pipefd)) { - perror("pipe"); - exit(KSFT_FAIL); - } + if (pipe(pipefd)) + ksft_exit_fail_msg("pipe: %s\n", strerror(errno)); + pid = fork(); if (pid < 0) { - perror("fork"); close(pipefd[0]); close(pipefd[1]); - exit(KSFT_FAIL); + ksft_exit_fail_msg("fork: %s\n", strerror(errno)); } if (pid == 0) { @@ -134,28 +129,23 @@ retry: res = read(pipefd[0], &byte, 1); close(pipefd[0]); if (res < 0) { - perror("read"); if (!kill(pid, SIGKILL)) waitpid(pid, NULL, 0); - exit(KSFT_FAIL); + ksft_exit_fail_msg("read: %s\n", strerror(errno)); } pidfd = syscall(__NR_pidfd_open, pid, 0); if (pidfd < 0) { - perror("pidfd_open"); if (!kill(pid, SIGKILL)) waitpid(pid, NULL, 0); - exit(KSFT_FAIL); + ksft_exit_fail_msg("pidfd_open: %s\n", strerror(errno)); } /* Run negative tests which require a live child */ run_negative_tests(pidfd); - if (kill(pid, SIGKILL)) { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("kill"); - exit(res); - } + if (kill(pid, SIGKILL)) + ksft_exit_fail_msg("kill: %s\n", strerror(errno)); success = (syscall(__NR_process_mrelease, pidfd, 0) == 0); if (!success) { @@ -169,18 +159,15 @@ retry: if (errno == ESRCH) { retry = (size <= MAX_SIZE_MB); } else { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("process_mrelease"); waitpid(pid, NULL, 0); - exit(res); + ksft_exit_fail_msg("process_mrelease: %s\n", strerror(errno)); } } /* Cleanup to prevent zombies */ - if (waitpid(pid, NULL, 0) < 0) { - perror("waitpid"); - exit(KSFT_FAIL); - } + if (waitpid(pid, NULL, 0) < 0) + ksft_exit_fail_msg("waitpid: %s\n", strerror(errno)); + close(pidfd); if (!success) { @@ -188,11 +175,10 @@ retry: size *= 2; goto retry; } - printf("All process_mrelease attempts failed!\n"); - exit(KSFT_FAIL); + ksft_exit_fail_msg("All process_mrelease attempts failed!\n"); } - printf("Success reaping a child with %zuMB of memory allocations\n", - size); - return KSFT_PASS; + ksft_test_result_pass("Success reaping a child with %zuMB of memory allocations\n", + size); + ksft_finished(); } diff --git a/tools/testing/selftests/mm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c index a06e73ec8568..1d75084b9ca5 100644 --- a/tools/testing/selftests/mm/mremap_dontunmap.c +++ b/tools/testing/selftests/mm/mremap_dontunmap.c @@ -27,14 +27,14 @@ static void dump_maps(void) system(cmd); } -#define BUG_ON(condition, description) \ - do { \ - if (condition) { \ - fprintf(stderr, "[FAIL]\t%s():%d\t%s:%s\n", __func__, \ - __LINE__, (description), strerror(errno)); \ - dump_maps(); \ - exit(1); \ - } \ +#define BUG_ON(condition, description) \ + do { \ + if (condition) { \ + dump_maps(); \ + ksft_exit_fail_msg("[FAIL]\t%s:%d\t%s:%s\n", \ + __func__, __LINE__, (description), \ + strerror(errno)); \ + } \ } while (0) // Try a simple operation for to "test" for kernel support this prevents @@ -122,6 +122,7 @@ static void mremap_dontunmap_simple() "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, num_pages * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } // This test validates that MREMAP_DONTUNMAP on a shared mapping works as expected. @@ -173,6 +174,7 @@ static void mremap_dontunmap_simple_shmem() "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, num_pages * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } // This test validates MREMAP_DONTUNMAP will move page tables to a specific @@ -219,6 +221,7 @@ static void mremap_dontunmap_simple_fixed() "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, num_pages * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } // This test validates that we can MREMAP_DONTUNMAP for a portion of an @@ -269,6 +272,7 @@ static void mremap_dontunmap_partial_mapping() "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, num_pages * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } // This test validates that we can remap over only a portion of a mapping. @@ -328,19 +332,24 @@ static void mremap_dontunmap_partial_mapping_overwrite(void) "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, 5 * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } int main(void) { + ksft_print_header(); + page_size = sysconf(_SC_PAGE_SIZE); // test for kernel support for MREMAP_DONTUNMAP skipping the test if // not. if (kernel_support_for_mremap_dontunmap() != 0) { - printf("No kernel support for MREMAP_DONTUNMAP\n"); - return KSFT_SKIP; + ksft_print_msg("No kernel support for MREMAP_DONTUNMAP\n"); + ksft_finished(); } + ksft_set_plan(5); + // Keep a page sized buffer around for when we need it. page_buffer = mmap(NULL, page_size, PROT_READ | PROT_WRITE, @@ -356,6 +365,5 @@ int main(void) BUG_ON(munmap(page_buffer, page_size) == -1, "unable to unmap page buffer"); - printf("OK\n"); - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/on-fault-limit.c b/tools/testing/selftests/mm/on-fault-limit.c index b5888d613f34..431c1277d83a 100644 --- a/tools/testing/selftests/mm/on-fault-limit.c +++ b/tools/testing/selftests/mm/on-fault-limit.c @@ -5,40 +5,38 @@ #include <string.h> #include <sys/time.h> #include <sys/resource.h> +#include "../kselftest.h" -static int test_limit(void) +static void test_limit(void) { - int ret = 1; struct rlimit lims; void *map; - if (getrlimit(RLIMIT_MEMLOCK, &lims)) { - perror("getrlimit"); - return ret; - } + if (getrlimit(RLIMIT_MEMLOCK, &lims)) + ksft_exit_fail_msg("getrlimit: %s\n", strerror(errno)); - if (mlockall(MCL_ONFAULT | MCL_FUTURE)) { - perror("mlockall"); - return ret; - } + if (mlockall(MCL_ONFAULT | MCL_FUTURE)) + ksft_exit_fail_msg("mlockall: %s\n", strerror(errno)); map = mmap(NULL, 2 * lims.rlim_max, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, -1, 0); + + ksft_test_result(map == MAP_FAILED, "The map failed respecting mlock limits\n"); + if (map != MAP_FAILED) - printf("mmap should have failed, but didn't\n"); - else { - ret = 0; munmap(map, 2 * lims.rlim_max); - } - munlockall(); - return ret; } int main(int argc, char **argv) { - int ret = 0; + ksft_print_header(); + ksft_set_plan(1); + + if (!getuid()) + ksft_test_result_skip("The test must be run from a normal user\n"); + else + test_limit(); - ret += test_limit(); - return ret; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 48dc151f8fca..f822ae31af22 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -54,6 +54,7 @@ int test_nr; u64 shadow_pkey_reg; int dprint_in_signal; char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; +char buf[256]; void cat_into_file(char *str, char *file) { @@ -1744,6 +1745,38 @@ void pkey_setup_shadow(void) shadow_pkey_reg = __read_pkey_reg(); } +void restore_settings_atexit(void) +{ + cat_into_file(buf, "/proc/sys/vm/nr_hugepages"); +} + +void save_settings(void) +{ + int fd; + int err; + + if (geteuid()) + return; + + fd = open("/proc/sys/vm/nr_hugepages", O_RDONLY); + if (fd < 0) { + fprintf(stderr, "error opening\n"); + perror("error: "); + exit(__LINE__); + } + + /* -1 to guarantee leaving the trailing \0 */ + err = read(fd, buf, sizeof(buf)-1); + if (err < 0) { + fprintf(stderr, "error reading\n"); + perror("error: "); + exit(__LINE__); + } + + atexit(restore_settings_atexit); + close(fd); +} + int main(void) { int nr_iterations = 22; @@ -1751,6 +1784,7 @@ int main(void) srand((unsigned int)time(NULL)); + save_settings(); setup_handlers(); printf("has pkeys: %d\n", pkeys_supported); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 246d53a5d7f2..c2c542fe7b17 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -15,10 +15,11 @@ usage() { cat <<EOF usage: ${BASH_SOURCE[0]:-$0} [ options ] - -a: run all tests, including extra ones + -a: run all tests, including extra ones (other than destructive ones) -t: specify specific categories to tests to run -h: display this message -n: disable TAP output + -d: run destructive tests The default behavior is to run required tests only. If -a is specified, will run all tests. @@ -64,6 +65,8 @@ separated by spaces: test copy-on-write semantics - thp test transparent huge pages +- hugetlb + test hugetlbfs huge pages - migration invoke move_pages(2) to exercise the migration entry code paths in the kernel @@ -79,6 +82,7 @@ EOF } RUN_ALL=false +RUN_DESTRUCTIVE=false TAP_PREFIX="# " while getopts "aht:n" OPT; do @@ -87,6 +91,7 @@ while getopts "aht:n" OPT; do "h") usage ;; "t") VM_SELFTEST_ITEMS=${OPTARG} ;; "n") TAP_PREFIX= ;; + "d") RUN_DESTRUCTIVE=true ;; esac done shift $((OPTIND -1)) @@ -173,7 +178,6 @@ if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then if [ "$freepgs" -lt "$needpgs" ]; then printf "Not enough huge pages available (%d < %d)\n" \ "$freepgs" "$needpgs" - exit 1 fi else echo "no hugetlbfs support in kernel?" @@ -206,6 +210,15 @@ pretty_name() { # Usage: run_test [test binary] [arbitrary test arguments...] run_test() { if test_selected ${CATEGORY}; then + # On memory constrainted systems some tests can fail to allocate hugepages. + # perform some cleanup before the test for a higher success rate. + if [ ${CATEGORY} == "thp" ] | [ ${CATEGORY} == "hugetlb" ]; then + echo 3 > /proc/sys/vm/drop_caches + sleep 2 + echo 1 > /proc/sys/vm/compact_memory + sleep 2 + fi + local test=$(pretty_name "$*") local title="running $*" local sep=$(echo -n "$title" | tr "[:graph:][:space:]" -) @@ -253,6 +266,7 @@ nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages) # For this test, we need one and just one huge page echo 1 > /proc/sys/vm/nr_hugepages CATEGORY="hugetlb" run_test ./hugetlb_fault_after_madv +CATEGORY="hugetlb" run_test ./hugetlb_madv_vs_map # Restore the previous number of huge pages, since further tests rely on it echo "$nr_hugepages_tmp" > /proc/sys/vm/nr_hugepages @@ -291,7 +305,12 @@ echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages CATEGORY="compaction" run_test ./compaction_test -CATEGORY="mlock" run_test sudo -u nobody ./on-fault-limit +if command -v sudo &> /dev/null; +then + CATEGORY="mlock" run_test sudo -u nobody ./on-fault-limit +else + echo "# SKIP ./on-fault-limit" +fi CATEGORY="mmap" run_test ./map_populate @@ -304,6 +323,11 @@ CATEGORY="process_mrelease" run_test ./mrelease_test CATEGORY="mremap" run_test ./mremap_test CATEGORY="hugetlb" run_test ./thuge-gen +CATEGORY="hugetlb" run_test ./charge_reserved_hugetlb.sh -cgroup-v2 +CATEGORY="hugetlb" run_test ./hugetlb_reparenting_test.sh -cgroup-v2 +if $RUN_DESTRUCTIVE; then +CATEGORY="hugetlb" run_test ./hugetlb-read-hwpoison +fi if [ $VADDR64 -ne 0 ]; then @@ -387,7 +411,27 @@ CATEGORY="thp" run_test ./khugepaged -s 2 CATEGORY="thp" run_test ./transhuge-stress -d 20 -CATEGORY="thp" run_test ./split_huge_page_test +# Try to create XFS if not provided +if [ -z "${SPLIT_HUGE_PAGE_TEST_XFS_PATH}" ]; then + if test_selected "thp"; then + if grep xfs /proc/filesystems &>/dev/null; then + XFS_IMG=$(mktemp /tmp/xfs_img_XXXXXX) + SPLIT_HUGE_PAGE_TEST_XFS_PATH=$(mktemp -d /tmp/xfs_dir_XXXXXX) + truncate -s 314572800 ${XFS_IMG} + mkfs.xfs -q ${XFS_IMG} + mount -o loop ${XFS_IMG} ${SPLIT_HUGE_PAGE_TEST_XFS_PATH} + MOUNTED_XFS=1 + fi + fi +fi + +CATEGORY="thp" run_test ./split_huge_page_test ${SPLIT_HUGE_PAGE_TEST_XFS_PATH} + +if [ -n "${MOUNTED_XFS}" ]; then + umount ${SPLIT_HUGE_PAGE_TEST_XFS_PATH} + rmdir ${SPLIT_HUGE_PAGE_TEST_XFS_PATH} + rm -f ${XFS_IMG} +fi CATEGORY="migration" run_test ./migration diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 0e74635c8c3d..856662d2f87a 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -16,17 +16,20 @@ #include <sys/mount.h> #include <malloc.h> #include <stdbool.h> +#include <time.h> #include "vm_util.h" +#include "../kselftest.h" uint64_t pagesize; unsigned int pageshift; uint64_t pmd_pagesize; #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages" +#define SMAP_PATH "/proc/self/smaps" #define INPUT_MAX 80 -#define PID_FMT "%d,0x%lx,0x%lx" -#define PATH_FMT "%s,0x%lx,0x%lx" +#define PID_FMT "%d,0x%lx,0x%lx,%d" +#define PATH_FMT "%s,0x%lx,0x%lx,%d" #define PFN_MASK ((1UL<<55)-1) #define KPF_THP (1UL<<22) @@ -50,21 +53,19 @@ int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) return 0; } -static int write_file(const char *path, const char *buf, size_t buflen) +static void write_file(const char *path, const char *buf, size_t buflen) { int fd; ssize_t numwritten; fd = open(path, O_WRONLY); if (fd == -1) - return 0; + ksft_exit_fail_msg("%s open failed: %s\n", path, strerror(errno)); numwritten = write(fd, buf, buflen - 1); close(fd); if (numwritten < 1) - return 0; - - return (unsigned int) numwritten; + ksft_exit_fail_msg("Write failed\n"); } static void write_debugfs(const char *fmt, ...) @@ -77,15 +78,10 @@ static void write_debugfs(const char *fmt, ...) ret = vsnprintf(input, INPUT_MAX, fmt, argp); va_end(argp); - if (ret >= INPUT_MAX) { - printf("%s: Debugfs input is too long\n", __func__); - exit(EXIT_FAILURE); - } + if (ret >= INPUT_MAX) + ksft_exit_fail_msg("%s: Debugfs input is too long\n", __func__); - if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) { - perror(SPLIT_DEBUGFS); - exit(EXIT_FAILURE); - } + write_file(SPLIT_DEBUGFS, input, ret + 1); } void split_pmd_thp(void) @@ -95,39 +91,30 @@ void split_pmd_thp(void) size_t i; one_page = memalign(pmd_pagesize, len); - - if (!one_page) { - printf("Fail to allocate memory\n"); - exit(EXIT_FAILURE); - } + if (!one_page) + ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno)); madvise(one_page, len, MADV_HUGEPAGE); for (i = 0; i < len; i++) one_page[i] = (char)i; - if (!check_huge_anon(one_page, 4, pmd_pagesize)) { - printf("No THP is allocated\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 4, pmd_pagesize)) + ksft_exit_fail_msg("No THP is allocated\n"); /* split all THPs */ write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, - (uint64_t)one_page + len); + (uint64_t)one_page + len, 0); for (i = 0; i < len; i++) - if (one_page[i] != (char)i) { - printf("%ld byte corrupted\n", i); - exit(EXIT_FAILURE); - } + if (one_page[i] != (char)i) + ksft_exit_fail_msg("%ld byte corrupted\n", i); - if (!check_huge_anon(one_page, 0, pmd_pagesize)) { - printf("Still AnonHugePages not split\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 0, pmd_pagesize)) + ksft_exit_fail_msg("Still AnonHugePages not split\n"); - printf("Split huge pages successful\n"); + ksft_test_result_pass("Split huge pages successful\n"); free(one_page); } @@ -143,36 +130,29 @@ void split_pte_mapped_thp(void) int pagemap_fd; int kpageflags_fd; - if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) { - perror("get pagemap proc error"); - exit(EXIT_FAILURE); - } - pagemap_fd = open(pagemap_proc, O_RDONLY); + if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) + ksft_exit_fail_msg("get pagemap proc error: %s\n", strerror(errno)); - if (pagemap_fd == -1) { - perror("read pagemap:"); - exit(EXIT_FAILURE); - } + pagemap_fd = open(pagemap_proc, O_RDONLY); + if (pagemap_fd == -1) + ksft_exit_fail_msg("read pagemap: %s\n", strerror(errno)); kpageflags_fd = open(kpageflags_proc, O_RDONLY); - - if (kpageflags_fd == -1) { - perror("read kpageflags:"); - exit(EXIT_FAILURE); - } + if (kpageflags_fd == -1) + ksft_exit_fail_msg("read kpageflags: %s\n", strerror(errno)); one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (one_page == MAP_FAILED) + ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno)); madvise(one_page, len, MADV_HUGEPAGE); for (i = 0; i < len; i++) one_page[i] = (char)i; - if (!check_huge_anon(one_page, 4, pmd_pagesize)) { - printf("No THP is allocated\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 4, pmd_pagesize)) + ksft_exit_fail_msg("No THP is allocated\n"); /* remap the first pagesize of first THP */ pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE); @@ -183,10 +163,8 @@ void split_pte_mapped_thp(void) pagesize, pagesize, MREMAP_MAYMOVE|MREMAP_FIXED, pte_mapped + pagesize * i); - if (pte_mapped2 == (char *)-1) { - perror("mremap failed"); - exit(EXIT_FAILURE); - } + if (pte_mapped2 == MAP_FAILED) + ksft_exit_fail_msg("mremap failed: %s\n", strerror(errno)); } /* smap does not show THPs after mremap, use kpageflags instead */ @@ -196,33 +174,28 @@ void split_pte_mapped_thp(void) is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) thp_size++; - if (thp_size != 4) { - printf("Some THPs are missing during mremap\n"); - exit(EXIT_FAILURE); - } + if (thp_size != 4) + ksft_exit_fail_msg("Some THPs are missing during mremap\n"); /* split all remapped THPs */ write_debugfs(PID_FMT, getpid(), (uint64_t)pte_mapped, - (uint64_t)pte_mapped + pagesize * 4); + (uint64_t)pte_mapped + pagesize * 4, 0); /* smap does not show THPs after mremap, use kpageflags instead */ thp_size = 0; for (i = 0; i < pagesize * 4; i++) { - if (pte_mapped[i] != (char)i) { - printf("%ld byte corrupted\n", i); - exit(EXIT_FAILURE); - } + if (pte_mapped[i] != (char)i) + ksft_exit_fail_msg("%ld byte corrupted\n", i); + if (i % pagesize == 0 && is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) thp_size++; } - if (thp_size) { - printf("Still %ld THPs not split\n", thp_size); - exit(EXIT_FAILURE); - } + if (thp_size) + ksft_exit_fail_msg("Still %ld THPs not split\n", thp_size); - printf("Split PTE-mapped huge pages successful\n"); + ksft_test_result_pass("Split PTE-mapped huge pages successful\n"); munmap(one_page, len); close(pagemap_fd); close(kpageflags_fd); @@ -238,24 +211,21 @@ void split_file_backed_thp(void) char testfile[INPUT_MAX]; uint64_t pgoff_start = 0, pgoff_end = 1024; - printf("Please enable pr_debug in split_huge_pages_in_file() if you need more info.\n"); + ksft_print_msg("Please enable pr_debug in split_huge_pages_in_file() for more info.\n"); status = mount("tmpfs", tmpfs_loc, "tmpfs", 0, "huge=always,size=4m"); - if (status) { - printf("Unable to create a tmpfs for testing\n"); - exit(EXIT_FAILURE); - } + if (status) + ksft_exit_fail_msg("Unable to create a tmpfs for testing\n"); status = snprintf(testfile, INPUT_MAX, "%s/thp_file", tmpfs_loc); if (status >= INPUT_MAX) { - printf("Fail to create file-backed THP split testing file\n"); - goto cleanup; + ksft_exit_fail_msg("Fail to create file-backed THP split testing file\n"); } fd = open(testfile, O_CREAT|O_WRONLY); if (fd == -1) { - perror("Cannot open testing file\n"); + ksft_perror("Cannot open testing file"); goto cleanup; } @@ -264,50 +234,213 @@ void split_file_backed_thp(void) close(fd); if (num_written < 1) { - printf("Fail to write data to testing file\n"); + ksft_perror("Fail to write data to testing file"); goto cleanup; } /* split the file-backed THP */ - write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end); + write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end, 0); status = unlink(testfile); - if (status) - perror("Cannot remove testing file\n"); + if (status) { + ksft_perror("Cannot remove testing file"); + goto cleanup; + } -cleanup: status = umount(tmpfs_loc); if (status) { - printf("Unable to umount %s\n", tmpfs_loc); - exit(EXIT_FAILURE); + rmdir(tmpfs_loc); + ksft_exit_fail_msg("Unable to umount %s\n", tmpfs_loc); } + status = rmdir(tmpfs_loc); - if (status) { - perror("cannot remove tmp dir"); - exit(EXIT_FAILURE); + if (status) + ksft_exit_fail_msg("cannot remove tmp dir: %s\n", strerror(errno)); + + ksft_print_msg("Please check dmesg for more information\n"); + ksft_test_result_pass("File-backed THP split test done\n"); + return; + +cleanup: + umount(tmpfs_loc); + rmdir(tmpfs_loc); + ksft_exit_fail_msg("Error occurred\n"); +} + +bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template, + const char **thp_fs_loc) +{ + if (xfs_path) { + *thp_fs_loc = xfs_path; + return false; + } + + *thp_fs_loc = mkdtemp(thp_fs_template); + + if (!*thp_fs_loc) + ksft_exit_fail_msg("cannot create temp folder\n"); + + return true; +} + +void cleanup_thp_fs(const char *thp_fs_loc, bool created_tmp) +{ + int status; + + if (!created_tmp) + return; + + status = rmdir(thp_fs_loc); + if (status) + ksft_exit_fail_msg("cannot remove tmp dir: %s\n", + strerror(errno)); +} + +int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd, + char **addr) +{ + size_t i; + int dummy; + + srand(time(NULL)); + + *fd = open(testfile, O_CREAT | O_RDWR, 0664); + if (*fd == -1) + ksft_exit_fail_msg("Failed to create a file at %s\n", testfile); + + for (i = 0; i < fd_size; i++) { + unsigned char byte = (unsigned char)i; + + write(*fd, &byte, sizeof(byte)); + } + close(*fd); + sync(); + *fd = open("/proc/sys/vm/drop_caches", O_WRONLY); + if (*fd == -1) { + ksft_perror("open drop_caches"); + goto err_out_unlink; + } + if (write(*fd, "3", 1) != 1) { + ksft_perror("write to drop_caches"); + goto err_out_unlink; + } + close(*fd); + + *fd = open(testfile, O_RDWR); + if (*fd == -1) { + ksft_perror("Failed to open testfile\n"); + goto err_out_unlink; + } + + *addr = mmap(NULL, fd_size, PROT_READ|PROT_WRITE, MAP_SHARED, *fd, 0); + if (*addr == (char *)-1) { + ksft_perror("cannot mmap"); + goto err_out_close; + } + madvise(*addr, fd_size, MADV_HUGEPAGE); + + for (size_t i = 0; i < fd_size; i++) + dummy += *(*addr + i); + + if (!check_huge_file(*addr, fd_size / pmd_pagesize, pmd_pagesize)) { + ksft_print_msg("No large pagecache folio generated, please provide a filesystem supporting large folio\n"); + munmap(*addr, fd_size); + close(*fd); + unlink(testfile); + ksft_test_result_skip("Pagecache folio split skipped\n"); + return -2; + } + return 0; +err_out_close: + close(*fd); +err_out_unlink: + unlink(testfile); + ksft_exit_fail_msg("Failed to create large pagecache folios\n"); + return -1; +} + +void split_thp_in_pagecache_to_order(size_t fd_size, int order, const char *fs_loc) +{ + int fd; + char *addr; + size_t i; + char testfile[INPUT_MAX]; + int err = 0; + + err = snprintf(testfile, INPUT_MAX, "%s/test", fs_loc); + + if (err < 0) + ksft_exit_fail_msg("cannot generate right test file name\n"); + + err = create_pagecache_thp_and_fd(testfile, fd_size, &fd, &addr); + if (err) + return; + err = 0; + + write_debugfs(PID_FMT, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order); + + for (i = 0; i < fd_size; i++) + if (*(addr + i) != (char)i) { + ksft_print_msg("%lu byte corrupted in the file\n", i); + err = EXIT_FAILURE; + goto out; + } + + if (!check_huge_file(addr, 0, pmd_pagesize)) { + ksft_print_msg("Still FilePmdMapped not split\n"); + err = EXIT_FAILURE; + goto out; } - printf("file-backed THP split test done, please check dmesg for more information\n"); +out: + munmap(addr, fd_size); + close(fd); + unlink(testfile); + if (err) + ksft_exit_fail_msg("Split PMD-mapped pagecache folio to order %d failed\n", order); + ksft_test_result_pass("Split PMD-mapped pagecache folio to order %d passed\n", order); } int main(int argc, char **argv) { + int i; + size_t fd_size; + char *optional_xfs_path = NULL; + char fs_loc_template[] = "/tmp/thp_fs_XXXXXX"; + const char *fs_loc; + bool created_tmp; + + ksft_print_header(); + if (geteuid() != 0) { - printf("Please run the benchmark as root\n"); - exit(EXIT_FAILURE); + ksft_print_msg("Please run the benchmark as root\n"); + ksft_finished(); } + if (argc > 1) + optional_xfs_path = argv[1]; + + ksft_set_plan(3+9); + pagesize = getpagesize(); pageshift = ffs(pagesize) - 1; pmd_pagesize = read_pmd_pagesize(); - if (!pmd_pagesize) { - printf("Reading PMD pagesize failed\n"); - exit(EXIT_FAILURE); - } + if (!pmd_pagesize) + ksft_exit_fail_msg("Reading PMD pagesize failed\n"); + + fd_size = 2 * pmd_pagesize; split_pmd_thp(); split_pte_mapped_thp(); split_file_backed_thp(); + created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template, + &fs_loc); + for (i = 8; i >= 0; i--) + split_thp_in_pagecache_to_order(fd_size, i, fs_loc); + cleanup_thp_fs(fs_loc, created_tmp); + + ksft_finished(); + return 0; } diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c index 622987f12c89..ea7fd8fe2876 100644 --- a/tools/testing/selftests/mm/thuge-gen.c +++ b/tools/testing/selftests/mm/thuge-gen.c @@ -4,7 +4,7 @@ Before running this huge pages for each huge page size must have been reserved. For large pages beyond MAX_PAGE_ORDER (like 1GB on x86) boot options must - be used. + be used. 1GB wouldn't be tested if it isn't available. Also shmmax must be increased. And you need to run as root to work around some weird permissions in shm. And nothing using huge pages should run in parallel. @@ -26,8 +26,7 @@ #include <stdarg.h> #include <string.h> #include "vm_util.h" - -#define err(x) perror(x), exit(1) +#include "../kselftest.h" #define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) #define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) @@ -44,11 +43,8 @@ #define SHM_HUGE_1GB (30 << SHM_HUGE_SHIFT) #define NUM_PAGESIZES 5 - #define NUM_PAGES 4 -#define Dprintf(fmt...) // printf(fmt) - unsigned long page_sizes[NUM_PAGESIZES]; int num_page_sizes; @@ -60,28 +56,15 @@ int ilog2(unsigned long v) return l; } -void find_pagesizes(void) -{ - glob_t g; - int i; - glob("/sys/kernel/mm/hugepages/hugepages-*kB", 0, NULL, &g); - assert(g.gl_pathc <= NUM_PAGESIZES); - for (i = 0; i < g.gl_pathc; i++) { - sscanf(g.gl_pathv[i], "/sys/kernel/mm/hugepages/hugepages-%lukB", - &page_sizes[i]); - page_sizes[i] <<= 10; - printf("Found %luMB\n", page_sizes[i] >> 20); - } - num_page_sizes = g.gl_pathc; - globfree(&g); -} - void show(unsigned long ps) { char buf[100]; + if (ps == getpagesize()) return; - printf("%luMB: ", ps >> 20); + + ksft_print_msg("%luMB: ", ps >> 20); + fflush(stdout); snprintf(buf, sizeof buf, "cat /sys/kernel/mm/hugepages/hugepages-%lukB/free_hugepages", @@ -105,7 +88,7 @@ unsigned long read_sysfs(int warn, char *fmt, ...) f = fopen(buf, "r"); if (!f) { if (warn) - printf("missing %s\n", buf); + ksft_print_msg("missing %s\n", buf); return 0; } if (getline(&line, &linelen, f) > 0) { @@ -119,123 +102,143 @@ unsigned long read_sysfs(int warn, char *fmt, ...) unsigned long read_free(unsigned long ps) { return read_sysfs(ps != getpagesize(), - "/sys/kernel/mm/hugepages/hugepages-%lukB/free_hugepages", - ps >> 10); + "/sys/kernel/mm/hugepages/hugepages-%lukB/free_hugepages", + ps >> 10); } void test_mmap(unsigned long size, unsigned flags) { char *map; unsigned long before, after; - int err; before = read_free(size); map = mmap(NULL, size*NUM_PAGES, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS|MAP_HUGETLB|flags, -1, 0); + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap: %s\n", strerror(errno)); - if (map == (char *)-1) err("mmap"); memset(map, 0xff, size*NUM_PAGES); after = read_free(size); - Dprintf("before %lu after %lu diff %ld size %lu\n", - before, after, before - after, size); - assert(size == getpagesize() || (before - after) == NUM_PAGES); + show(size); - err = munmap(map, size * NUM_PAGES); - assert(!err); + ksft_test_result(size == getpagesize() || (before - after) == NUM_PAGES, + "%s mmap\n", __func__); + + if (munmap(map, size * NUM_PAGES)) + ksft_exit_fail_msg("%s: unmap %s\n", __func__, strerror(errno)); } void test_shmget(unsigned long size, unsigned flags) { int id; unsigned long before, after; - int err; + struct shm_info i; + char *map; before = read_free(size); id = shmget(IPC_PRIVATE, size * NUM_PAGES, IPC_CREAT|0600|flags); - if (id < 0) err("shmget"); - - struct shm_info i; - if (shmctl(id, SHM_INFO, (void *)&i) < 0) err("shmctl"); - Dprintf("alloc %lu res %lu\n", i.shm_tot, i.shm_rss); + if (id < 0) { + if (errno == EPERM) { + ksft_test_result_skip("shmget requires root privileges: %s\n", + strerror(errno)); + return; + } + ksft_exit_fail_msg("shmget: %s\n", strerror(errno)); + } + if (shmctl(id, SHM_INFO, (void *)&i) < 0) + ksft_exit_fail_msg("shmctl: %s\n", strerror(errno)); - Dprintf("id %d\n", id); - char *map = shmat(id, NULL, 0600); - if (map == (char*)-1) err("shmat"); + map = shmat(id, NULL, 0600); + if (map == MAP_FAILED) + ksft_exit_fail_msg("shmat: %s\n", strerror(errno)); shmctl(id, IPC_RMID, NULL); memset(map, 0xff, size*NUM_PAGES); after = read_free(size); - Dprintf("before %lu after %lu diff %ld size %lu\n", - before, after, before - after, size); - assert(size == getpagesize() || (before - after) == NUM_PAGES); show(size); - err = shmdt(map); - assert(!err); + ksft_test_result(size == getpagesize() || (before - after) == NUM_PAGES, + "%s: mmap\n", __func__); + if (shmdt(map)) + ksft_exit_fail_msg("%s: shmdt: %s\n", __func__, strerror(errno)); } -void sanity_checks(void) +void find_pagesizes(void) { - int i; unsigned long largest = getpagesize(); + int i; + glob_t g; - for (i = 0; i < num_page_sizes; i++) { - if (page_sizes[i] > largest) + glob("/sys/kernel/mm/hugepages/hugepages-*kB", 0, NULL, &g); + assert(g.gl_pathc <= NUM_PAGESIZES); + for (i = 0; (i < g.gl_pathc) && (num_page_sizes < NUM_PAGESIZES); i++) { + sscanf(g.gl_pathv[i], "/sys/kernel/mm/hugepages/hugepages-%lukB", + &page_sizes[num_page_sizes]); + page_sizes[num_page_sizes] <<= 10; + ksft_print_msg("Found %luMB\n", page_sizes[i] >> 20); + + if (page_sizes[num_page_sizes] > largest) largest = page_sizes[i]; - if (read_free(page_sizes[i]) < NUM_PAGES) { - printf("Not enough huge pages for page size %lu MB, need %u\n", - page_sizes[i] >> 20, - NUM_PAGES); - exit(0); - } + if (read_free(page_sizes[num_page_sizes]) >= NUM_PAGES) + num_page_sizes++; + else + ksft_print_msg("SKIP for size %lu MB as not enough huge pages, need %u\n", + page_sizes[num_page_sizes] >> 20, NUM_PAGES); } + globfree(&g); - if (read_sysfs(0, "/proc/sys/kernel/shmmax") < NUM_PAGES * largest) { - printf("Please do echo %lu > /proc/sys/kernel/shmmax", largest * NUM_PAGES); - exit(0); - } + if (read_sysfs(0, "/proc/sys/kernel/shmmax") < NUM_PAGES * largest) + ksft_exit_fail_msg("Please do echo %lu > /proc/sys/kernel/shmmax", + largest * NUM_PAGES); #if defined(__x86_64__) if (largest != 1U<<30) { - printf("No GB pages available on x86-64\n" - "Please boot with hugepagesz=1G hugepages=%d\n", NUM_PAGES); - exit(0); + ksft_exit_fail_msg("No GB pages available on x86-64\n" + "Please boot with hugepagesz=1G hugepages=%d\n", NUM_PAGES); } #endif } int main(void) { - int i; unsigned default_hps = default_huge_page_size(); + int i; + + ksft_print_header(); find_pagesizes(); - sanity_checks(); + if (!num_page_sizes) + ksft_finished(); + + ksft_set_plan(2 * num_page_sizes + 3); for (i = 0; i < num_page_sizes; i++) { unsigned long ps = page_sizes[i]; int arg = ilog2(ps) << MAP_HUGE_SHIFT; - printf("Testing %luMB mmap with shift %x\n", ps >> 20, arg); + + ksft_print_msg("Testing %luMB mmap with shift %x\n", ps >> 20, arg); test_mmap(ps, MAP_HUGETLB | arg); } - printf("Testing default huge mmap\n"); + + ksft_print_msg("Testing default huge mmap\n"); test_mmap(default_hps, MAP_HUGETLB); - puts("Testing non-huge shmget"); + ksft_print_msg("Testing non-huge shmget\n"); test_shmget(getpagesize(), 0); for (i = 0; i < num_page_sizes; i++) { unsigned long ps = page_sizes[i]; int arg = ilog2(ps) << SHM_HUGE_SHIFT; - printf("Testing %luMB shmget with shift %x\n", ps >> 20, arg); + ksft_print_msg("Testing %luMB shmget with shift %x\n", ps >> 20, arg); test_shmget(ps, SHM_HUGETLB | arg); } - puts("default huge shmget"); + + ksft_print_msg("default huge shmget\n"); test_shmget(default_hps, SHM_HUGETLB); - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/transhuge-stress.c b/tools/testing/selftests/mm/transhuge-stress.c index c61fb9350b8c..68201192e37c 100644 --- a/tools/testing/selftests/mm/transhuge-stress.c +++ b/tools/testing/selftests/mm/transhuge-stress.c @@ -16,6 +16,7 @@ #include <string.h> #include <sys/mman.h> #include "vm_util.h" +#include "../kselftest.h" int backing_fd = -1; int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE; @@ -34,6 +35,8 @@ int main(int argc, char **argv) int pagemap_fd; int duration = 0; + ksft_print_header(); + ram = sysconf(_SC_PHYS_PAGES); if (ram > SIZE_MAX / psize() / 4) ram = SIZE_MAX / 4; @@ -43,7 +46,8 @@ int main(int argc, char **argv) while (++i < argc) { if (!strcmp(argv[i], "-h")) - errx(1, "usage: %s [-f <filename>] [-d <duration>] [size in MiB]", argv[0]); + ksft_exit_fail_msg("usage: %s [-f <filename>] [-d <duration>] [size in MiB]\n", + argv[0]); else if (!strcmp(argv[i], "-f")) name = argv[++i]; else if (!strcmp(argv[i], "-d")) @@ -52,10 +56,12 @@ int main(int argc, char **argv) len = atoll(argv[i]) << 20; } + ksft_set_plan(1); + if (name) { backing_fd = open(name, O_RDWR); if (backing_fd == -1) - errx(2, "open %s", name); + ksft_exit_fail_msg("open %s\n", name); mmap_flags = MAP_SHARED; } @@ -65,21 +71,21 @@ int main(int argc, char **argv) pagemap_fd = open("/proc/self/pagemap", O_RDONLY); if (pagemap_fd < 0) - err(2, "open pagemap"); + ksft_exit_fail_msg("open pagemap\n"); len -= len % HPAGE_SIZE; ptr = mmap(NULL, len + HPAGE_SIZE, PROT_RW, mmap_flags, backing_fd, 0); if (ptr == MAP_FAILED) - err(2, "initial mmap"); + ksft_exit_fail_msg("initial mmap"); ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE; if (madvise(ptr, len, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); + ksft_exit_fail_msg("MADV_HUGEPAGE"); map_len = ram >> (HPAGE_SHIFT - 1); map = malloc(map_len); if (!map) - errx(2, "map malloc"); + ksft_exit_fail_msg("map malloc\n"); clock_gettime(CLOCK_MONOTONIC, &start); @@ -103,7 +109,7 @@ int main(int argc, char **argv) if (idx >= map_len) { map = realloc(map, idx + 1); if (!map) - errx(2, "map realloc"); + ksft_exit_fail_msg("map realloc\n"); memset(map + map_len, 0, idx + 1 - map_len); map_len = idx + 1; } @@ -114,17 +120,19 @@ int main(int argc, char **argv) /* split transhuge page, keep last page */ if (madvise(p, HPAGE_SIZE - psize(), MADV_DONTNEED)) - err(2, "MADV_DONTNEED"); + ksft_exit_fail_msg("MADV_DONTNEED"); } clock_gettime(CLOCK_MONOTONIC, &b); s = b.tv_sec - a.tv_sec + (b.tv_nsec - a.tv_nsec) / 1000000000.; - warnx("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t" - "%4d succeed, %4d failed, %4d different pages", - s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20), - nr_succeed, nr_failed, nr_pages); + ksft_print_msg("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t" + "%4d succeed, %4d failed, %4d different pages\n", + s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20), + nr_succeed, nr_failed, nr_pages); - if (duration > 0 && b.tv_sec - start.tv_sec >= duration) - return 0; + if (duration > 0 && b.tv_sec - start.tv_sec >= duration) { + ksft_test_result_pass("Completed\n"); + ksft_finished(); + } } } diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 7e83829bbb33..f78bab0f3d45 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -441,6 +441,12 @@ int main(int argc, char **argv) parse_test_type_arg(argv[1]); bytes = atol(argv[2]) * 1024 * 1024; + if (test_type == TEST_HUGETLB && + get_free_hugepages() < bytes / page_size) { + printf("skip: Skipping userfaultfd... not enough hugepages\n"); + return KSFT_SKIP; + } + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); nr_pages_per_cpu = bytes / page_size / nr_cpus; diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index bae0ceaf95b1..7bcf8d48256a 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -12,6 +12,7 @@ #include <errno.h> #include <sys/mman.h> #include <sys/time.h> +#include "../kselftest.h" /* * Maximum address range mapped with a single mmap() @@ -68,23 +69,15 @@ static char *hind_addr(void) return (char *) (1UL << bits); } -static int validate_addr(char *ptr, int high_addr) +static void validate_addr(char *ptr, int high_addr) { unsigned long addr = (unsigned long) ptr; - if (high_addr) { - if (addr < HIGH_ADDR_MARK) { - printf("Bad address %lx\n", addr); - return 1; - } - return 0; - } + if (high_addr && addr < HIGH_ADDR_MARK) + ksft_exit_fail_msg("Bad address %lx\n", addr); - if (addr > HIGH_ADDR_MARK) { - printf("Bad address %lx\n", addr); - return 1; - } - return 0; + if (addr > HIGH_ADDR_MARK) + ksft_exit_fail_msg("Bad address %lx\n", addr); } static int validate_lower_address_hint(void) @@ -107,23 +100,29 @@ int main(int argc, char *argv[]) char *hint; unsigned long i, lchunks, hchunks; + ksft_print_header(); + ksft_set_plan(1); + for (i = 0; i < NR_CHUNKS_LOW; i++) { ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (ptr[i] == MAP_FAILED) { - if (validate_lower_address_hint()) - return 1; + if (validate_lower_address_hint()) { + ksft_test_result_skip("Memory constraint not fulfilled\n"); + ksft_finished(); + } break; } - if (validate_addr(ptr[i], 0)) - return 1; + validate_addr(ptr[i], 0); } lchunks = i; hptr = (char **) calloc(NR_CHUNKS_HIGH, sizeof(char *)); - if (hptr == NULL) - return 1; + if (hptr == NULL) { + ksft_test_result_skip("Memory constraint not fulfilled\n"); + ksft_finished(); + } for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hind_addr(); @@ -133,8 +132,7 @@ int main(int argc, char *argv[]) if (hptr[i] == MAP_FAILED) break; - if (validate_addr(hptr[i], 1)) - return 1; + validate_addr(hptr[i], 1); } hchunks = i; @@ -145,5 +143,7 @@ int main(int argc, char *argv[]) munmap(hptr[i], MAP_CHUNK_SIZE); free(hptr); - return 0; + + ksft_test_result_pass("Test\n"); + ksft_finished(); } diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 05736c615734..5a62530da3b5 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -232,17 +232,17 @@ int64_t allocate_transhuge(void *ptr, int pagemap_fd) if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, MAP_FIXED | MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) - errx(2, "mmap transhuge"); + ksft_exit_fail_msg("mmap transhuge\n"); if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); + ksft_exit_fail_msg("MADV_HUGEPAGE\n"); /* allocate transparent huge page */ *(volatile void **)ptr = ptr; if (pread(pagemap_fd, ent, sizeof(ent), (uintptr_t)ptr >> (pshift() - 3)) != sizeof(ent)) - err(2, "read pagemap"); + ksft_exit_fail_msg("read pagemap\n"); if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && diff --git a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h index a89f1fbf86ec..1d293ab77185 100644 --- a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h +++ b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h @@ -47,4 +47,16 @@ /* Default to taking the first of any alternative feature sections */ test_feature = 1 +#define DCBT_SETUP_STREAMS(from, from_parms, to, to_parms, scratch) \ + lis scratch,0x8000; /* GO=1 */ \ + clrldi scratch,scratch,32; \ + /* setup read stream 0 */ \ + dcbt 0,from,0b01000; /* addr from */ \ + dcbt 0,from_parms,0b01010; /* length and depth from */ \ + /* setup write stream 1 */ \ + dcbtst 0,to,0b01000; /* addr to */ \ + dcbtst 0,to_parms,0b01010; /* length and depth to */ \ + eieio; \ + dcbt 0,scratch,0b01010; /* all streams GO */ + #endif /* __SELFTESTS_POWERPC_PPC_ASM_H */ |