diff options
Diffstat (limited to 'tools')
42 files changed, 685 insertions, 148 deletions
diff --git a/tools/arch/arm64/vdso b/tools/arch/arm64/vdso new file mode 120000 index 000000000000..233c7a26f6e5 --- /dev/null +++ b/tools/arch/arm64/vdso @@ -0,0 +1 @@ +../../../arch/arm64/kernel/vdso
\ No newline at end of file diff --git a/tools/arch/loongarch/vdso b/tools/arch/loongarch/vdso new file mode 120000 index 000000000000..ebda43a82db7 --- /dev/null +++ b/tools/arch/loongarch/vdso @@ -0,0 +1 @@ +../../../arch/loongarch/vdso
\ No newline at end of file diff --git a/tools/arch/powerpc/vdso b/tools/arch/powerpc/vdso new file mode 120000 index 000000000000..4e676d1d1cb4 --- /dev/null +++ b/tools/arch/powerpc/vdso @@ -0,0 +1 @@ +../../../arch/powerpc/kernel/vdso
\ No newline at end of file diff --git a/tools/arch/s390/vdso b/tools/arch/s390/vdso new file mode 120000 index 000000000000..6cf4c1cebdcd --- /dev/null +++ b/tools/arch/s390/vdso @@ -0,0 +1 @@ +../../../arch/s390/kernel/vdso64
\ No newline at end of file diff --git a/tools/arch/x86/vdso b/tools/arch/x86/vdso new file mode 120000 index 000000000000..7eb962fd3454 --- /dev/null +++ b/tools/arch/x86/vdso @@ -0,0 +1 @@ +../../../arch/x86/entry/vdso/
\ No newline at end of file diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index d29c9c49e251..ed565eb52275 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -78,7 +78,7 @@ $(OUTPUT)gpio-watch: $(GPIO_WATCH_IN) clean: rm -f $(ALL_PROGRAMS) rm -f $(OUTPUT)include/linux/gpio.h - find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c index 54fdf59dd320..ba0866eb3581 100644 --- a/tools/gpio/gpio-hammer.c +++ b/tools/gpio/gpio-hammer.c @@ -54,7 +54,7 @@ int hammer_device(const char *device_name, unsigned int *lines, int num_lines, fprintf(stdout, "Hammer lines ["); for (i = 0; i < num_lines; i++) { - fprintf(stdout, "%d", lines[i]); + fprintf(stdout, "%u", lines[i]); if (i != (num_lines - 1)) fprintf(stdout, ", "); } @@ -89,7 +89,7 @@ int hammer_device(const char *device_name, unsigned int *lines, int num_lines, fprintf(stdout, "["); for (i = 0; i < num_lines; i++) { - fprintf(stdout, "%d: %d", lines[i], + fprintf(stdout, "%u: %d", lines[i], gpiotools_test_bit(values.bits, i)); if (i != (num_lines - 1)) fprintf(stdout, ", "); diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 3ce316cc9f97..7a00f3066a98 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -296,6 +296,13 @@ static int hv_fcopy_start(struct hv_start_fcopy *smsg_in) file_name = (char *)malloc(file_size * sizeof(char)); path_name = (char *)malloc(path_size * sizeof(char)); + if (!file_name || !path_name) { + free(file_name); + free(path_name); + syslog(LOG_ERR, "Can't allocate memory for file name and/or path name"); + return HV_E_FAIL; + } + wcstoutf8(file_name, (__u16 *)in_file_name, file_size); wcstoutf8(path_name, (__u16 *)in_path_name, path_size); diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h index 7ce02a223732..8e548ac8f740 100644 --- a/tools/include/asm/alternative.h +++ b/tools/include/asm/alternative.h @@ -2,8 +2,18 @@ #ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H #define _TOOLS_ASM_ALTERNATIVE_ASM_H +#if defined(__s390x__) +#ifdef __ASSEMBLY__ +.macro ALTERNATIVE oldinstr, newinstr, feature + \oldinstr +.endm +#endif +#else + /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ #define ALTERNATIVE # #endif + +#endif diff --git a/tools/include/generated/asm-offsets.h b/tools/include/generated/asm-offsets.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/generated/asm-offsets.h diff --git a/tools/include/generated/asm/cpucap-defs.h b/tools/include/generated/asm/cpucap-defs.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/generated/asm/cpucap-defs.h diff --git a/tools/include/generated/asm/sysreg-defs.h b/tools/include/generated/asm/sysreg-defs.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/generated/asm/sysreg-defs.h diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 6f7f22ac9da5..4366da278033 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -2,6 +2,8 @@ #ifndef _TOOLS_LINUX_COMPILER_H_ #define _TOOLS_LINUX_COMPILER_H_ +#ifndef __ASSEMBLY__ + #include <linux/compiler_types.h> #ifndef __compiletime_error @@ -224,4 +226,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __asm__ ("" : "=r" (var) : "0" (var)) #endif +#endif /* __ASSEMBLY__ */ + #endif /* _TOOLS_LINUX_COMPILER_H */ diff --git a/tools/include/linux/linkage.h b/tools/include/linux/linkage.h index bc763d500262..a48ff086899c 100644 --- a/tools/include/linux/linkage.h +++ b/tools/include/linux/linkage.h @@ -1,4 +1,8 @@ #ifndef _TOOLS_INCLUDE_LINUX_LINKAGE_H #define _TOOLS_INCLUDE_LINUX_LINKAGE_H +#define SYM_FUNC_START(x) .globl x; x: + +#define SYM_FUNC_END(x) + #endif /* _TOOLS_INCLUDE_LINUX_LINKAGE_H */ diff --git a/tools/memory-model/Documentation/README b/tools/memory-model/Documentation/README index 304162743a5b..9999c1effdb6 100644 --- a/tools/memory-model/Documentation/README +++ b/tools/memory-model/Documentation/README @@ -9,6 +9,8 @@ depending on what you know and what you would like to learn. Please note that the documents later in this list assume that the reader understands the material provided by documents earlier in this list. +If LKMM-specific terms lost you, glossary.txt might help you. + o You are new to Linux-kernel concurrency: simple.txt o You have some background in Linux-kernel concurrency, and would @@ -21,6 +23,9 @@ o You are familiar with the Linux-kernel concurrency primitives that you need, and just want to get started with LKMM litmus tests: litmus-tests.txt +o You would like to access lock-protected shared variables without + having their corresponding locks held: locking.txt + o You are familiar with Linux-kernel concurrency, and would like a detailed intuitive understanding of LKMM, including situations involving more than two threads: recipes.txt @@ -28,12 +33,18 @@ o You are familiar with Linux-kernel concurrency, and would o You would like a detailed understanding of what your compiler can and cannot do to control dependencies: control-dependencies.txt +o You would like to mark concurrent normal accesses to shared + variables so that intentional "racy" accesses can be properly + documented, especially when you are responding to complaints + from KCSAN: access-marking.txt + o You are familiar with Linux-kernel concurrency and the use of LKMM, and would like a quick reference: cheatsheet.txt o You are familiar with Linux-kernel concurrency and the use of LKMM, and would like to learn about LKMM's requirements, - rationale, and implementation: explanation.txt + rationale, and implementation: explanation.txt and + herd-representation.txt o You are interested in the publications related to LKMM, including hardware manuals, academic literature, standards-committee @@ -61,10 +72,21 @@ control-dependencies.txt explanation.txt Detailed description of the memory model. +glossary.txt + Brief definitions of LKMM-related terms. + +herd-representation.txt + The (abstract) representation of the Linux-kernel concurrency + primitives in terms of events. + litmus-tests.txt The format, features, capabilities, and limitations of the litmus tests that LKMM can evaluate. +locking.txt + Rules for accessing lock-protected shared variables outside of + their corresponding critical sections. + ordering.txt Overview of the Linux kernel's low-level memory-ordering primitives by category. diff --git a/tools/memory-model/Documentation/herd-representation.txt b/tools/memory-model/Documentation/herd-representation.txt new file mode 100644 index 000000000000..ed988906f2b7 --- /dev/null +++ b/tools/memory-model/Documentation/herd-representation.txt @@ -0,0 +1,110 @@ +# +# Legend: +# R, a Load event +# W, a Store event +# F, a Fence event +# LKR, a Lock-Read event +# LKW, a Lock-Write event +# UL, an Unlock event +# LF, a Lock-Fail event +# RL, a Read-Locked event +# RU, a Read-Unlocked event +# R*, a Load event included in RMW +# W*, a Store event included in RMW +# SRCU, a Sleepable-Read-Copy-Update event +# +# po, a Program-Order link +# rmw, a Read-Modify-Write link - every rmw link is a po link +# +# By convention, a blank line in a cell means "same as the preceding line". +# +# Disclaimer. The table includes representations of "add" and "and" operations; +# corresponding/identical representations of "sub", "inc", "dec" and "or", "xor", +# "andnot" operations are omitted. +# + ------------------------------------------------------------------------------ + | C macro | Events | + ------------------------------------------------------------------------------ + | Non-RMW ops | | + ------------------------------------------------------------------------------ + | READ_ONCE | R[once] | + | atomic_read | | + | WRITE_ONCE | W[once] | + | atomic_set | | + | smp_load_acquire | R[acquire] | + | atomic_read_acquire | | + | smp_store_release | W[release] | + | atomic_set_release | | + | smp_store_mb | W[once] ->po F[mb] | + | smp_mb | F[mb] | + | smp_rmb | F[rmb] | + | smp_wmb | F[wmb] | + | smp_mb__before_atomic | F[before-atomic] | + | smp_mb__after_atomic | F[after-atomic] | + | spin_unlock | UL | + | spin_is_locked | On success: RL | + | | On failure: RU | + | smp_mb__after_spinlock | F[after-spinlock] | + | smp_mb__after_unlock_lock | F[after-unlock-lock] | + | rcu_read_lock | F[rcu-lock] | + | rcu_read_unlock | F[rcu-unlock] | + | synchronize_rcu | F[sync-rcu] | + | rcu_dereference | R[once] | + | rcu_assign_pointer | W[release] | + | srcu_read_lock | R[srcu-lock] | + | srcu_down_read | | + | srcu_read_unlock | W[srcu-unlock] | + | srcu_up_read | | + | synchronize_srcu | SRCU[sync-srcu] | + | smp_mb__after_srcu_read_unlock | F[after-srcu-read-unlock] | + ------------------------------------------------------------------------------ + | RMW ops w/o return value | | + ------------------------------------------------------------------------------ + | atomic_add | R*[noreturn] ->rmw W*[once] | + | atomic_and | | + | spin_lock | LKR ->po LKW | + ------------------------------------------------------------------------------ + | RMW ops w/ return value | | + ------------------------------------------------------------------------------ + | atomic_add_return | F[mb] ->po R*[once] | + | | ->rmw W*[once] ->po F[mb] | + | atomic_fetch_add | | + | atomic_fetch_and | | + | atomic_xchg | | + | xchg | | + | atomic_add_negative | | + | atomic_add_return_relaxed | R*[once] ->rmw W*[once] | + | atomic_fetch_add_relaxed | | + | atomic_fetch_and_relaxed | | + | atomic_xchg_relaxed | | + | xchg_relaxed | | + | atomic_add_negative_relaxed | | + | atomic_add_return_acquire | R*[acquire] ->rmw W*[once] | + | atomic_fetch_add_acquire | | + | atomic_fetch_and_acquire | | + | atomic_xchg_acquire | | + | xchg_acquire | | + | atomic_add_negative_acquire | | + | atomic_add_return_release | R*[once] ->rmw W*[release] | + | atomic_fetch_add_release | | + | atomic_fetch_and_release | | + | atomic_xchg_release | | + | xchg_release | | + | atomic_add_negative_release | | + ------------------------------------------------------------------------------ + | Conditional RMW ops | | + ------------------------------------------------------------------------------ + | atomic_cmpxchg | On success: F[mb] ->po R*[once] | + | | ->rmw W*[once] ->po F[mb] | + | | On failure: R*[once] | + | cmpxchg | | + | atomic_add_unless | | + | atomic_cmpxchg_relaxed | On success: R*[once] ->rmw W*[once] | + | | On failure: R*[once] | + | atomic_cmpxchg_acquire | On success: R*[acquire] ->rmw W*[once] | + | | On failure: R*[once] | + | atomic_cmpxchg_release | On success: R*[once] ->rmw W*[release] | + | | On failure: R*[once] | + | spin_trylock | On success: LKR ->po LKW | + | | On failure: LF | + ------------------------------------------------------------------------------ diff --git a/tools/memory-model/Documentation/simple.txt b/tools/memory-model/Documentation/simple.txt index 4c789ec8334f..21f06c1d1b70 100644 --- a/tools/memory-model/Documentation/simple.txt +++ b/tools/memory-model/Documentation/simple.txt @@ -266,5 +266,5 @@ More complex use cases ====================== If the alternatives above do not do what you need, please look at the -recipes-pairs.txt file to peel off the next layer of the memory-ordering +recipes.txt file to peel off the next layer of the memory-ordering onion. diff --git a/tools/rcu/rcu-updaters.sh b/tools/rcu/rcu-updaters.sh index 4ef1397927bb..8a5df3f22550 100755 --- a/tools/rcu/rcu-updaters.sh +++ b/tools/rcu/rcu-updaters.sh @@ -21,12 +21,10 @@ fi bpftrace -e 'kprobe:kvfree_call_rcu, kprobe:call_rcu, kprobe:call_rcu_tasks, - kprobe:call_rcu_tasks_rude, kprobe:call_rcu_tasks_trace, kprobe:call_srcu, kprobe:rcu_barrier, kprobe:rcu_barrier_tasks, - kprobe:rcu_barrier_tasks_rude, kprobe:rcu_barrier_tasks_trace, kprobe:srcu_barrier, kprobe:synchronize_rcu, diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index a32771da4293..22807fd78fe6 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -434,7 +434,7 @@ uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func, struct testmod_uprobe { struct path path; - loff_t offset; + struct uprobe *uprobe; struct uprobe_consumer consumer; }; @@ -448,25 +448,25 @@ static int testmod_register_uprobe(loff_t offset) { int err = -EBUSY; - if (uprobe.offset) + if (uprobe.uprobe) return -EBUSY; mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) + if (uprobe.uprobe) goto out; err = kern_path("/proc/self/exe", LOOKUP_FOLLOW, &uprobe.path); if (err) goto out; - err = uprobe_register_refctr(d_real_inode(uprobe.path.dentry), - offset, 0, &uprobe.consumer); - if (err) + uprobe.uprobe = uprobe_register(d_real_inode(uprobe.path.dentry), + offset, 0, &uprobe.consumer); + if (IS_ERR(uprobe.uprobe)) { + err = PTR_ERR(uprobe.uprobe); path_put(&uprobe.path); - else - uprobe.offset = offset; - + uprobe.uprobe = NULL; + } out: mutex_unlock(&testmod_uprobe_mutex); return err; @@ -476,10 +476,11 @@ static void testmod_unregister_uprobe(void) { mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) { - uprobe_unregister(d_real_inode(uprobe.path.dentry), - uprobe.offset, &uprobe.consumer); - uprobe.offset = 0; + if (uprobe.uprobe) { + uprobe_unregister_nosync(uprobe.uprobe, &uprobe.consumer); + uprobe_unregister_sync(); + path_put(&uprobe.path); + uprobe.uprobe = NULL; } mutex_unlock(&testmod_uprobe_mutex); diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 7c08cc153367..03c1bdaed2c3 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -84,6 +84,20 @@ echo member > test/cpuset.cpus.partition echo "" > test/cpuset.cpus [[ $RESULT -eq 0 ]] && skip_test "Child cgroups are using cpuset!" +# +# If isolated CPUs have been reserved at boot time (as shown in +# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-7 +# that will be used by this script for testing purpose. If not, some of +# the tests may fail incorrectly. These isolated CPUs will also be removed +# before being compared with the expected results. +# +BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated) +if [[ -n "$BOOT_ISOLCPUS" ]] +then + [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 7 ]] && + skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested" + echo "Pre-isolated CPUs: $BOOT_ISOLCPUS" +fi cleanup() { online_cpus @@ -321,7 +335,7 @@ TEST_MATRIX=( # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # - # Incorrect change to cpuset.cpus invalidates partition root + # Incorrect change to cpuset.cpus[.exclusive] invalidates partition root # # Adding CPUs to partition root that are not in parent's # cpuset.cpus is allowed, but those extra CPUs are ignored. @@ -365,6 +379,16 @@ TEST_MATRIX=( # cpuset.cpus can overlap with sibling cpuset.cpus.exclusive but not subsumed by it " C0-3 . . C4-5 X5 . . . 0 A1:0-3,B1:4-5" + # Child partition root that try to take all CPUs from parent partition + # with tasks will remain invalid. + " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4,A2:1-4 A1:P1,A2:P-1" + " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1,A2:1-4 A1:P1,A2:P1" + " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4,A2:1-4 A1:P1,A2:P-1" + + # Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't + # affect cpuset.cpus.exclusive.effective. + " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4,XA2:3" + # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: @@ -632,7 +656,8 @@ check_cgroup_states() # Note that isolated CPUs from the sched/domains context include offline # CPUs as well as CPUs in non-isolated 1-CPU partition. Those CPUs may # not be included in the cpuset.cpus.isolated control file which contains -# only CPUs in isolated partitions. +# only CPUs in isolated partitions as well as those that are isolated at +# boot time. # # $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>} # <isolcpus1> - expected sched/domains value @@ -659,18 +684,21 @@ check_isolcpus() fi # - # Check the debug isolated cpumask, if present + # Check cpuset.cpus.isolated cpumask # - [[ -f $ISCPUS ]] && { + if [[ -z "$BOOT_ISOLCPUS" ]] + then + ISOLCPUS=$(cat $ISCPUS) + else + ISOLCPUS=$(cat $ISCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") + fi + [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && { + # Take a 50ms pause and try again + pause 0.05 ISOLCPUS=$(cat $ISCPUS) - [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && { - # Take a 50ms pause and try again - pause 0.05 - ISOLCPUS=$(cat $ISCPUS) - } - [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && return 1 - ISOLCPUS= } + [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && return 1 + ISOLCPUS= # # Use the sched domain in debugfs to check isolated CPUs, if available @@ -703,6 +731,9 @@ check_isolcpus() fi done [[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU + [[ -n "BOOT_ISOLCPUS" ]] && + ISOLCPUS=$(echo $ISOLCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") + [[ "$EXPECT_VAL" = "$ISOLCPUS" ]] } @@ -720,7 +751,8 @@ test_fail() } # -# Check to see if there are unexpected isolated CPUs left +# Check to see if there are unexpected isolated CPUs left beyond the boot +# time isolated ones. # null_isolcpus_check() { diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh new file mode 100755 index 000000000000..42a6628fb8bc --- /dev/null +++ b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh @@ -0,0 +1,77 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Basc test for cpuset v1 interfaces write/read +# + +skip_test() { + echo "$1" + echo "Test SKIPPED" + exit 4 # ksft_skip +} + +write_test() { + dir=$1 + interface=$2 + value=$3 + original=$(cat $dir/$interface) + echo "testing $interface $value" + echo $value > $dir/$interface + new=$(cat $dir/$interface) + [[ $value -ne $(cat $dir/$interface) ]] && { + echo "$interface write $value failed: new:$new" + exit 1 + } +} + +[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!" + +# Find cpuset v1 mount point +CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk '{print $3}') +[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!" + +# +# Create a test cpuset, read write test +# +TDIR=test$$ +[[ -d $CPUSET/$TDIR ]] || mkdir $CPUSET/$TDIR + +ITF_MATRIX=( + #interface value expect root_only + 'cpuset.cpus 0-1 0-1 0' + 'cpuset.mem_exclusive 1 1 0' + 'cpuset.mem_exclusive 0 0 0' + 'cpuset.mem_hardwall 1 1 0' + 'cpuset.mem_hardwall 0 0 0' + 'cpuset.memory_migrate 1 1 0' + 'cpuset.memory_migrate 0 0 0' + 'cpuset.memory_spread_page 1 1 0' + 'cpuset.memory_spread_page 0 0 0' + 'cpuset.memory_spread_slab 1 1 0' + 'cpuset.memory_spread_slab 0 0 0' + 'cpuset.mems 0 0 0' + 'cpuset.sched_load_balance 1 1 0' + 'cpuset.sched_load_balance 0 0 0' + 'cpuset.sched_relax_domain_level 2 2 0' + 'cpuset.memory_pressure_enabled 1 1 1' + 'cpuset.memory_pressure_enabled 0 0 1' +) + +run_test() +{ + cnt="${ITF_MATRIX[@]}" + for i in "${ITF_MATRIX[@]}" ; do + args=($i) + root_only=${args[3]} + [[ $root_only -eq 1 ]] && { + write_test "$CPUSET" "${args[0]}" "${args[1]}" "${args[2]}" + continue + } + write_test "$CPUSET/$TDIR" "${args[0]}" "${args[1]}" "${args[2]}" + done +} + +run_test +rmdir $CPUSET/$TDIR +echo "Test PASSED" +exit 0 diff --git a/tools/testing/selftests/dt/test_unprobed_devices.sh b/tools/testing/selftests/dt/test_unprobed_devices.sh index 2d7e70c5ad2d..5e3f42ef249e 100755 --- a/tools/testing/selftests/dt/test_unprobed_devices.sh +++ b/tools/testing/selftests/dt/test_unprobed_devices.sh @@ -34,8 +34,21 @@ nodes_compatible=$( # Check if node is available if [[ -e "${node}"/status ]]; then status=$(tr -d '\000' < "${node}"/status) - [[ "${status}" != "okay" && "${status}" != "ok" ]] && continue + if [[ "${status}" != "okay" && "${status}" != "ok" ]]; then + if [ -n "${disabled_nodes_regex}" ]; then + disabled_nodes_regex="${disabled_nodes_regex}|${node}" + else + disabled_nodes_regex="${node}" + fi + continue + fi fi + + # Ignore this node if one of its ancestors was disabled + if [ -n "${disabled_nodes_regex}" ]; then + echo "${node}" | grep -q -E "${disabled_nodes_regex}" && continue + fi + echo "${node}" | sed -e 's|\/proc\/device-tree||' done | sort ) diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile index 1321922038d0..ca4483c238b9 100644 --- a/tools/testing/selftests/powerpc/benchmarks/Makefile +++ b/tools/testing/selftests/powerpc/benchmarks/Makefile @@ -18,4 +18,4 @@ $(OUTPUT)/context_switch: LDLIBS += -lpthread $(OUTPUT)/fork: LDLIBS += -lpthread -$(OUTPUT)/exec_target: CFLAGS += -static -nostartfiles +$(OUTPUT)/exec_target: CFLAGS += -nostartfiles diff --git a/tools/testing/selftests/powerpc/benchmarks/exec_target.c b/tools/testing/selftests/powerpc/benchmarks/exec_target.c index c14b0fc1edde..a6408d3f26cd 100644 --- a/tools/testing/selftests/powerpc/benchmarks/exec_target.c +++ b/tools/testing/selftests/powerpc/benchmarks/exec_target.c @@ -7,10 +7,22 @@ */ #define _GNU_SOURCE -#include <unistd.h> #include <sys/syscall.h> void _start(void) { - syscall(SYS_exit, 0); + asm volatile ( + "li %%r0, %[sys_exit];" + "li %%r3, 0;" + "sc;" + : + : [sys_exit] "i" (SYS_exit) + /* + * "sc" will clobber r0, r3-r13, cr0, ctr, xer and memory. + * Even though sys_exit never returns, handle clobber + * registers. + */ + : "r0", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10", + "r11", "r12", "r13", "cr0", "ctr", "xer", "memory" + ); } diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index b33cd8753689..ad79784e552d 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -68,6 +68,8 @@ config_override_param "--gdb options" KcList "$TORTURE_KCONFIG_GDB_ARG" config_override_param "--kasan options" KcList "$TORTURE_KCONFIG_KASAN_ARG" config_override_param "--kcsan options" KcList "$TORTURE_KCONFIG_KCSAN_ARG" config_override_param "--kconfig argument" KcList "$TORTURE_KCONFIG_ARG" +config_override_param "$config_dir/CFcommon.$(uname -m)" KcList \ + "`cat $config_dir/CFcommon.$(uname -m) 2> /dev/null`" cp $T/KcList $resdir/ConfigFragment base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'` diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index 990d24696fd3..0447c4a00cc4 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -19,10 +19,10 @@ PATH=${RCUTORTURE}/bin:$PATH; export PATH TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`" MAKE_ALLOTED_CPUS=$((TORTURE_ALLOTED_CPUS*2)) -HALF_ALLOTED_CPUS=$((TORTURE_ALLOTED_CPUS/2)) -if test "$HALF_ALLOTED_CPUS" -lt 1 +SCALE_ALLOTED_CPUS=$((TORTURE_ALLOTED_CPUS/2)) +if test "$SCALE_ALLOTED_CPUS" -lt 1 then - HALF_ALLOTED_CPUS=1 + SCALE_ALLOTED_CPUS=1 fi VERBOSE_BATCH_CPUS=$((TORTURE_ALLOTED_CPUS/16)) if test "$VERBOSE_BATCH_CPUS" -lt 2 @@ -90,6 +90,7 @@ usage () { echo " --do-scftorture / --do-no-scftorture / --no-scftorture" echo " --do-srcu-lockdep / --do-no-srcu-lockdep / --no-srcu-lockdep" echo " --duration [ <minutes> | <hours>h | <days>d ]" + echo " --guest-cpu-limit N" echo " --kcsan-kmake-arg kernel-make-arguments" exit 1 } @@ -203,6 +204,21 @@ do duration_base=$(($ts*mult)) shift ;; + --guest-cpu-limit|--guest-cpu-lim) + checkarg --guest-cpu-limit "(number)" "$#" "$2" '^[0-9]*$' '^--' + if (("$2" <= "$TORTURE_ALLOTED_CPUS" / 2)) + then + SCALE_ALLOTED_CPUS="$2" + VERBOSE_BATCH_CPUS="$((SCALE_ALLOTED_CPUS/8))" + if (("$VERBOSE_BATCH_CPUS" < 2)) + then + VERBOSE_BATCH_CPUS=0 + fi + else + echo "Ignoring value of $2 for --guest-cpu-limit which is greater than (("$TORTURE_ALLOTED_CPUS" / 2))." + fi + shift + ;; --kcsan-kmake-arg|--kcsan-kmake-args) checkarg --kcsan-kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$' kcsan_kmake_args="`echo "$kcsan_kmake_args $2" | sed -e 's/^ *//' -e 's/ *$//'`" @@ -425,9 +441,9 @@ fi if test "$do_scftorture" = "yes" then # Scale memory based on the number of CPUs. - scfmem=$((3+HALF_ALLOTED_CPUS/16)) - torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot csdlock_debug=1" - torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory ${scfmem}G --trust-make + scfmem=$((3+SCALE_ALLOTED_CPUS/16)) + torture_bootargs="scftorture.nthreads=$SCALE_ALLOTED_CPUS torture.disable_onoff_at_boot csdlock_debug=1" + torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$SCALE_ALLOTED_CPUS" --memory ${scfmem}G --trust-make fi if test "$do_rt" = "yes" @@ -471,8 +487,8 @@ for prim in $primlist do if test -n "$firsttime" then - torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$HALF_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "refscale.verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make + torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$SCALE_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot" + torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$SCALE_ALLOTED_CPUS" --bootargs "refscale.verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make mv $T/last-resdir-nodebug $T/first-resdir-nodebug || : if test -f "$T/last-resdir-kasan" then @@ -520,8 +536,8 @@ for prim in $primlist do if test -n "$firsttime" then - torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$HALF_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make + torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$SCALE_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot" + torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$SCALE_ALLOTED_CPUS" --trust-make mv $T/last-resdir-nodebug $T/first-resdir-nodebug || : if test -f "$T/last-resdir-kasan" then @@ -559,7 +575,7 @@ do_kcsan="$do_kcsan_save" if test "$do_kvfree" = "yes" then torture_bootargs="rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 rcuscale.holdoff=20 rcuscale.kfree_loops=10000 torture.disable_onoff_at_boot" - torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration $duration_rcutorture --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 2G --trust-make + torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration $duration_rcutorture --kconfig "CONFIG_NR_CPUS=$SCALE_ALLOTED_CPUS" --memory 2G --trust-make fi if test "$do_clocksourcewd" = "yes" diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon index 0e92d85313aa..217597e84905 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon @@ -1,7 +1,5 @@ CONFIG_RCU_TORTURE_TEST=y CONFIG_PRINTK_TIME=y -CONFIG_HYPERVISOR_GUEST=y CONFIG_PARAVIRT=y -CONFIG_KVM_GUEST=y CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.i686 b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.i686 new file mode 100644 index 000000000000..d8b2f555686f --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.i686 @@ -0,0 +1,2 @@ +CONFIG_HYPERVISOR_GUEST=y +CONFIG_KVM_GUEST=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.ppc64le b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.ppc64le new file mode 100644 index 000000000000..133da04247ee --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.ppc64le @@ -0,0 +1 @@ +CONFIG_KVM_GUEST=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.x86_64 b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.x86_64 new file mode 100644 index 000000000000..d8b2f555686f --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.x86_64 @@ -0,0 +1,2 @@ +CONFIG_HYPERVISOR_GUEST=y +CONFIG_KVM_GUEST=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot index 979edbf4c820..55ce305b2a3d 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot @@ -2,3 +2,4 @@ nohz_full=2-9 rcutorture.stall_cpu=14 rcutorture.stall_cpu_holdoff=90 rcutorture.fwd_progress=0 +rcutree.nohz_full_patience_delay=1000 diff --git a/tools/testing/selftests/rcutorture/configs/refscale/TINY b/tools/testing/selftests/rcutorture/configs/refscale/TINY new file mode 100644 index 000000000000..759343980b80 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/TINY @@ -0,0 +1,20 @@ +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n +#CHECK#CONFIG_PREEMPT_RCU=n +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index 3de8e7e052ae..af9cedbf5357 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -1,7 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) -SODIUM := $(shell pkg-config --libs libsodium 2>/dev/null) +include ../../../scripts/Makefile.arch TEST_GEN_PROGS := vdso_test_gettimeofday TEST_GEN_PROGS += vdso_test_getcpu @@ -11,14 +9,12 @@ ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64)) TEST_GEN_PROGS += vdso_standalone_test_x86 endif TEST_GEN_PROGS += vdso_test_correctness -ifeq ($(uname_M),x86_64) +ifeq ($(ARCH)$(CONFIG_X86_32),$(filter $(ARCH)$(CONFIG_X86_32),x86 x86_64 loongarch arm64 powerpc s390)) TEST_GEN_PROGS += vdso_test_getrandom -ifneq ($(SODIUM),) TEST_GEN_PROGS += vdso_test_chacha endif -endif -CFLAGS := -std=gnu99 +CFLAGS := -std=gnu99 -O2 ifeq ($(CONFIG_X86_32),y) LDLIBS += -lgcc_s @@ -38,11 +34,12 @@ $(OUTPUT)/vdso_test_correctness: LDFLAGS += -ldl $(OUTPUT)/vdso_test_getrandom: parse_vdso.c $(OUTPUT)/vdso_test_getrandom: CFLAGS += -isystem $(top_srcdir)/tools/include \ + $(KHDR_INCLUDES) \ -isystem $(top_srcdir)/include/uapi -$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/arch/$(ARCH)/entry/vdso/vgetrandom-chacha.S +$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/tools/arch/$(SRCARCH)/vdso/vgetrandom-chacha.S $(OUTPUT)/vdso_test_chacha: CFLAGS += -idirafter $(top_srcdir)/tools/include \ - -isystem $(top_srcdir)/arch/$(ARCH)/include \ - -isystem $(top_srcdir)/include \ - -D__ASSEMBLY__ -DBULID_VDSO -DCONFIG_FUNCTION_ALIGNMENT=0 \ - -Wa,--noexecstack $(SODIUM) + -idirafter $(top_srcdir)/tools/include/generated \ + -idirafter $(top_srcdir)/arch/$(SRCARCH)/include \ + -idirafter $(top_srcdir)/include \ + -D__ASSEMBLY__ -Wa,--noexecstack diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c index 4ae417372e9e..7dd5668ea8a6 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.c +++ b/tools/testing/selftests/vDSO/parse_vdso.c @@ -36,6 +36,12 @@ #define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x) #define ELF(x) ELF_BITS_XFORM(ELF_BITS, x) +#ifdef __s390x__ +#define ELF_HASH_ENTRY ELF(Xword) +#else +#define ELF_HASH_ENTRY ELF(Word) +#endif + static struct vdso_info { bool valid; @@ -47,8 +53,8 @@ static struct vdso_info /* Symbol table */ ELF(Sym) *symtab; const char *symstrings; - ELF(Word) *bucket, *chain; - ELF(Word) nbucket, nchain; + ELF_HASH_ENTRY *bucket, *chain; + ELF_HASH_ENTRY nbucket, nchain; /* Version table */ ELF(Versym) *versym; @@ -115,7 +121,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) /* * Fish out the useful bits of the dynamic table. */ - ELF(Word) *hash = 0; + ELF_HASH_ENTRY *hash = 0; vdso_info.symstrings = 0; vdso_info.symtab = 0; vdso_info.versym = 0; @@ -133,7 +139,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) + vdso_info.load_offset); break; case DT_HASH: - hash = (ELF(Word) *) + hash = (ELF_HASH_ENTRY *) ((uintptr_t)dyn[i].d_un.d_ptr + vdso_info.load_offset); break; @@ -216,7 +222,8 @@ void *vdso_sym(const char *version, const char *name) ELF(Sym) *sym = &vdso_info.symtab[chain]; /* Check for a defined global or weak function w/ right name. */ - if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) + if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC && + ELF64_ST_TYPE(sym->st_info) != STT_NOTYPE) continue; if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && ELF64_ST_BIND(sym->st_info) != STB_WEAK) diff --git a/tools/testing/selftests/vDSO/vdso_call.h b/tools/testing/selftests/vDSO/vdso_call.h new file mode 100644 index 000000000000..bb237d771051 --- /dev/null +++ b/tools/testing/selftests/vDSO/vdso_call.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Macro to call vDSO functions + * + * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France + */ +#ifndef __VDSO_CALL_H__ +#define __VDSO_CALL_H__ + +#ifdef __powerpc__ + +#define LOADARGS_1(fn, __arg1) do { \ + _r0 = fn; \ + _r3 = (long)__arg1; \ +} while (0) + +#define LOADARGS_2(fn, __arg1, __arg2) do { \ + _r0 = fn; \ + _r3 = (long)__arg1; \ + _r4 = (long)__arg2; \ +} while (0) + +#define LOADARGS_3(fn, __arg1, __arg2, __arg3) do { \ + _r0 = fn; \ + _r3 = (long)__arg1; \ + _r4 = (long)__arg2; \ + _r5 = (long)__arg3; \ +} while (0) + +#define LOADARGS_5(fn, __arg1, __arg2, __arg3, __arg4, __arg5) do { \ + _r0 = fn; \ + _r3 = (long)__arg1; \ + _r4 = (long)__arg2; \ + _r5 = (long)__arg3; \ + _r6 = (long)__arg4; \ + _r7 = (long)__arg5; \ +} while (0) + +#define VDSO_CALL(fn, nr, args...) ({ \ + register void *_r0 asm ("r0"); \ + register long _r3 asm ("r3"); \ + register long _r4 asm ("r4"); \ + register long _r5 asm ("r5"); \ + register long _r6 asm ("r6"); \ + register long _r7 asm ("r7"); \ + register long _r8 asm ("r8"); \ + register long _rval asm ("r3"); \ + \ + LOADARGS_##nr(fn, args); \ + \ + asm volatile( \ + " mtctr %0\n" \ + " bctrl\n" \ + " bns+ 1f\n" \ + " neg 3, 3\n" \ + "1:" \ + : "+r" (_r0), "=r" (_r3), "+r" (_r4), "+r" (_r5), \ + "+r" (_r6), "+r" (_r7), "+r" (_r8) \ + : "r" (_rval) \ + : "r9", "r10", "r11", "r12", "cr0", "cr1", "cr5", \ + "cr6", "cr7", "xer", "lr", "ctr", "memory" \ + ); \ + _rval; \ +}) + +#else +#define VDSO_CALL(fn, nr, args...) fn(args) +#endif + +#endif diff --git a/tools/testing/selftests/vDSO/vdso_config.h b/tools/testing/selftests/vDSO/vdso_config.h index 7b543e7f04d7..722260f97561 100644 --- a/tools/testing/selftests/vDSO/vdso_config.h +++ b/tools/testing/selftests/vDSO/vdso_config.h @@ -18,18 +18,18 @@ #elif defined(__aarch64__) #define VDSO_VERSION 3 #define VDSO_NAMES 0 -#elif defined(__powerpc__) +#elif defined(__powerpc64__) #define VDSO_VERSION 1 #define VDSO_NAMES 0 -#define VDSO_32BIT 1 -#elif defined(__powerpc64__) +#elif defined(__powerpc__) #define VDSO_VERSION 1 #define VDSO_NAMES 0 -#elif defined (__s390__) +#define VDSO_32BIT 1 +#elif defined (__s390__) && !defined(__s390x__) #define VDSO_VERSION 2 #define VDSO_NAMES 0 #define VDSO_32BIT 1 -#elif defined (__s390X__) +#elif defined (__s390x__) #define VDSO_VERSION 2 #define VDSO_NAMES 0 #elif defined(__mips__) @@ -68,16 +68,15 @@ static const char *versions[7] = { "LINUX_5.10" }; -static const char *names[2][6] = { +static const char *names[2][7] = { { "__kernel_gettimeofday", "__kernel_clock_gettime", "__kernel_time", "__kernel_clock_getres", "__kernel_getcpu", -#if defined(VDSO_32BIT) "__kernel_clock_gettime64", -#endif + "__kernel_getrandom", }, { "__vdso_gettimeofday", @@ -85,9 +84,8 @@ static const char *names[2][6] = { "__vdso_time", "__vdso_clock_getres", "__vdso_getcpu", -#if defined(VDSO_32BIT) "__vdso_clock_gettime64", -#endif + "__vdso_getrandom", }, }; diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c index 96d32fd65b42..a54424e2336f 100644 --- a/tools/testing/selftests/vDSO/vdso_test_abi.c +++ b/tools/testing/selftests/vDSO/vdso_test_abi.c @@ -20,10 +20,8 @@ #include "../kselftest.h" #include "vdso_config.h" - -extern void *vdso_sym(const char *version, const char *name); -extern void vdso_init_from_sysinfo_ehdr(uintptr_t base); -extern void vdso_init_from_auxv(void *auxv); +#include "vdso_call.h" +#include "parse_vdso.h" static const char *version; static const char **name; @@ -61,7 +59,7 @@ static void vdso_test_gettimeofday(void) } struct timeval tv; - long ret = vdso_gettimeofday(&tv, 0); + long ret = VDSO_CALL(vdso_gettimeofday, 2, &tv, 0); if (ret == 0) { ksft_print_msg("The time is %lld.%06lld\n", @@ -86,7 +84,7 @@ static void vdso_test_clock_gettime(clockid_t clk_id) } struct timespec ts; - long ret = vdso_clock_gettime(clk_id, &ts); + long ret = VDSO_CALL(vdso_clock_gettime, 2, clk_id, &ts); if (ret == 0) { ksft_print_msg("The time is %lld.%06lld\n", @@ -111,7 +109,7 @@ static void vdso_test_time(void) return; } - long ret = vdso_time(NULL); + long ret = VDSO_CALL(vdso_time, 1, NULL); if (ret > 0) { ksft_print_msg("The time in hours since January 1, 1970 is %lld\n", @@ -138,7 +136,7 @@ static void vdso_test_clock_getres(clockid_t clk_id) } struct timespec ts, sys_ts; - long ret = vdso_clock_getres(clk_id, &ts); + long ret = VDSO_CALL(vdso_clock_getres, 2, clk_id, &ts); if (ret == 0) { ksft_print_msg("The vdso resolution is %lld %lld\n", diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c index e38f44e5f803..b1ea532c5996 100644 --- a/tools/testing/selftests/vDSO/vdso_test_chacha.c +++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c @@ -3,23 +3,90 @@ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ -#include <sodium/crypto_stream_chacha20.h> +#include <tools/le_byteshift.h> #include <sys/random.h> +#include <sys/auxv.h> #include <string.h> #include <stdint.h> +#include <stdbool.h> #include "../kselftest.h" -extern void __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, const uint8_t *key, uint32_t *counter, size_t nblocks); +#if defined(__aarch64__) +static bool cpu_has_capabilities(void) +{ + return getauxval(AT_HWCAP) & HWCAP_ASIMD; +} +#elif defined(__s390x__) +static bool cpu_has_capabilities(void) +{ + return getauxval(AT_HWCAP) & HWCAP_S390_VXRS; +} +#else +static bool cpu_has_capabilities(void) +{ + return true; +} +#endif + +static uint32_t rol32(uint32_t word, unsigned int shift) +{ + return (word << (shift & 31)) | (word >> ((-shift) & 31)); +} + +static void reference_chacha20_blocks(uint8_t *dst_bytes, const uint32_t *key, uint32_t *counter, size_t nblocks) +{ + uint32_t s[16] = { + 0x61707865U, 0x3320646eU, 0x79622d32U, 0x6b206574U, + key[0], key[1], key[2], key[3], key[4], key[5], key[6], key[7], + counter[0], counter[1], 0, 0 + }; + + while (nblocks--) { + uint32_t x[16]; + memcpy(x, s, sizeof(x)); + for (unsigned int r = 0; r < 20; r += 2) { + #define QR(a, b, c, d) ( \ + x[a] += x[b], \ + x[d] = rol32(x[d] ^ x[a], 16), \ + x[c] += x[d], \ + x[b] = rol32(x[b] ^ x[c], 12), \ + x[a] += x[b], \ + x[d] = rol32(x[d] ^ x[a], 8), \ + x[c] += x[d], \ + x[b] = rol32(x[b] ^ x[c], 7)) + + QR(0, 4, 8, 12); + QR(1, 5, 9, 13); + QR(2, 6, 10, 14); + QR(3, 7, 11, 15); + QR(0, 5, 10, 15); + QR(1, 6, 11, 12); + QR(2, 7, 8, 13); + QR(3, 4, 9, 14); + } + for (unsigned int i = 0; i < 16; ++i, dst_bytes += sizeof(uint32_t)) + put_unaligned_le32(x[i] + s[i], dst_bytes); + if (!++s[12]) + ++s[13]; + } + counter[0] = s[12]; + counter[1] = s[13]; +} + +typedef uint8_t u8; +typedef uint32_t u32; +typedef uint64_t u64; +#include <vdso/getrandom.h> int main(int argc, char *argv[]) { enum { TRIALS = 1000, BLOCKS = 128, BLOCK_SIZE = 64 }; - static const uint8_t nonce[8] = { 0 }; - uint32_t counter[2]; - uint8_t key[32]; + uint32_t key[8], counter1[2], counter2[2]; uint8_t output1[BLOCK_SIZE * BLOCKS], output2[BLOCK_SIZE * BLOCKS]; ksft_print_header(); + if (!cpu_has_capabilities()) + ksft_exit_skip("Required CPU capabilities missing\n"); ksft_set_plan(1); for (unsigned int trial = 0; trial < TRIALS; ++trial) { @@ -27,17 +94,33 @@ int main(int argc, char *argv[]) printf("getrandom() failed!\n"); return KSFT_SKIP; } - crypto_stream_chacha20(output1, sizeof(output1), nonce, key); + memset(counter1, 0, sizeof(counter1)); + reference_chacha20_blocks(output1, key, counter1, BLOCKS); for (unsigned int split = 0; split < BLOCKS; ++split) { memset(output2, 'X', sizeof(output2)); - memset(counter, 0, sizeof(counter)); + memset(counter2, 0, sizeof(counter2)); if (split) - __arch_chacha20_blocks_nostack(output2, key, counter, split); - __arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter, BLOCKS - split); - if (memcmp(output1, output2, sizeof(output1))) + __arch_chacha20_blocks_nostack(output2, key, counter2, split); + __arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter2, BLOCKS - split); + if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1))) return KSFT_FAIL; } } + memset(counter1, 0, sizeof(counter1)); + counter1[0] = (uint32_t)-BLOCKS + 2; + memset(counter2, 0, sizeof(counter2)); + counter2[0] = (uint32_t)-BLOCKS + 2; + + reference_chacha20_blocks(output1, key, counter1, BLOCKS); + __arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS); + if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1))) + return KSFT_FAIL; + + reference_chacha20_blocks(output1, key, counter1, BLOCKS); + __arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS); + if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1))) + return KSFT_FAIL; + ksft_test_result_pass("chacha: PASS\n"); return KSFT_PASS; } diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c index e691a3cf1491..5fb97ad67eea 100644 --- a/tools/testing/selftests/vDSO/vdso_test_correctness.c +++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c @@ -20,6 +20,7 @@ #include <limits.h> #include "vdso_config.h" +#include "vdso_call.h" #include "../kselftest.h" static const char **name; @@ -114,6 +115,12 @@ static void fill_function_pointers() if (!vdso) vdso = dlopen("linux-gate.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-vdso32.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-vdso64.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); if (!vdso) { printf("[WARN]\tfailed to find vDSO\n"); return; @@ -180,7 +187,7 @@ static void test_getcpu(void) ret_sys = sys_getcpu(&cpu_sys, &node_sys, 0); if (vdso_getcpu) - ret_vdso = vdso_getcpu(&cpu_vdso, &node_vdso, 0); + ret_vdso = VDSO_CALL(vdso_getcpu, 3, &cpu_vdso, &node_vdso, 0); if (vgetcpu) ret_vsys = vgetcpu(&cpu_vsys, &node_vsys, 0); @@ -263,7 +270,7 @@ static void test_one_clock_gettime(int clock, const char *name) if (sys_clock_gettime(clock, &start) < 0) { if (errno == EINVAL) { - vdso_ret = vdso_clock_gettime(clock, &vdso); + vdso_ret = VDSO_CALL(vdso_clock_gettime, 2, clock, &vdso); if (vdso_ret == -EINVAL) { printf("[OK]\tNo such clock.\n"); } else { @@ -276,7 +283,7 @@ static void test_one_clock_gettime(int clock, const char *name) return; } - vdso_ret = vdso_clock_gettime(clock, &vdso); + vdso_ret = VDSO_CALL(vdso_clock_gettime, 2, clock, &vdso); end_ret = sys_clock_gettime(clock, &end); if (vdso_ret != 0 || end_ret != 0) { @@ -325,7 +332,7 @@ static void test_one_clock_gettime64(int clock, const char *name) if (sys_clock_gettime64(clock, &start) < 0) { if (errno == EINVAL) { - vdso_ret = vdso_clock_gettime64(clock, &vdso); + vdso_ret = VDSO_CALL(vdso_clock_gettime64, 2, clock, &vdso); if (vdso_ret == -EINVAL) { printf("[OK]\tNo such clock.\n"); } else { @@ -338,7 +345,7 @@ static void test_one_clock_gettime64(int clock, const char *name) return; } - vdso_ret = vdso_clock_gettime64(clock, &vdso); + vdso_ret = VDSO_CALL(vdso_clock_gettime64, 2, clock, &vdso); end_ret = sys_clock_gettime64(clock, &end); if (vdso_ret != 0 || end_ret != 0) { @@ -395,7 +402,7 @@ static void test_gettimeofday(void) return; } - vdso_ret = vdso_gettimeofday(&vdso, &vdso_tz); + vdso_ret = VDSO_CALL(vdso_gettimeofday, 2, &vdso, &vdso_tz); end_ret = sys_gettimeofday(&end, NULL); if (vdso_ret != 0 || end_ret != 0) { @@ -425,7 +432,7 @@ static void test_gettimeofday(void) } /* And make sure that passing NULL for tz doesn't crash. */ - vdso_gettimeofday(&vdso, NULL); + VDSO_CALL(vdso_gettimeofday, 2, &vdso, NULL); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/vDSO/vdso_test_getcpu.c b/tools/testing/selftests/vDSO/vdso_test_getcpu.c index b758f68c6c9c..cdeaed45fb26 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getcpu.c +++ b/tools/testing/selftests/vDSO/vdso_test_getcpu.c @@ -14,6 +14,7 @@ #include "../kselftest.h" #include "parse_vdso.h" #include "vdso_config.h" +#include "vdso_call.h" struct getcpu_cache; typedef long (*getcpu_t)(unsigned int *, unsigned int *, @@ -42,7 +43,7 @@ int main(int argc, char **argv) return KSFT_SKIP; } - ret = get_cpu(&cpu, &node, 0); + ret = VDSO_CALL(get_cpu, 3, &cpu, &node, 0); if (ret == 0) { printf("Running on CPU %u node %u\n", cpu, node); } else { diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index 05122425a873..72a1d9b43a84 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -16,11 +16,17 @@ #include <sys/mman.h> #include <sys/random.h> #include <sys/syscall.h> +#include <sys/ptrace.h> +#include <sys/wait.h> #include <sys/types.h> #include <linux/random.h> +#include <linux/compiler.h> +#include <linux/ptrace.h> #include "../kselftest.h" #include "parse_vdso.h" +#include "vdso_config.h" +#include "vdso_call.h" #ifndef timespecsub #define timespecsub(tsp, usp, vsp) \ @@ -38,50 +44,43 @@ static struct { pthread_mutex_t lock; void **states; size_t len, cap; -} grnd_allocator = { - .lock = PTHREAD_MUTEX_INITIALIZER -}; - -static struct { ssize_t(*fn)(void *, size_t, unsigned long, void *, size_t); - pthread_key_t key; - pthread_once_t initialized; struct vgetrandom_opaque_params params; -} grnd_ctx = { - .initialized = PTHREAD_ONCE_INIT +} vgrnd = { + .lock = PTHREAD_MUTEX_INITIALIZER }; static void *vgetrandom_get_state(void) { void *state = NULL; - pthread_mutex_lock(&grnd_allocator.lock); - if (!grnd_allocator.len) { + pthread_mutex_lock(&vgrnd.lock); + if (!vgrnd.len) { size_t page_size = getpagesize(); size_t new_cap; size_t alloc_size, num = sysconf(_SC_NPROCESSORS_ONLN); /* Just a decent heuristic. */ void *new_block, *new_states; - alloc_size = (num * grnd_ctx.params.size_of_opaque_state + page_size - 1) & (~(page_size - 1)); - num = (page_size / grnd_ctx.params.size_of_opaque_state) * (alloc_size / page_size); - new_block = mmap(0, alloc_size, grnd_ctx.params.mmap_prot, grnd_ctx.params.mmap_flags, -1, 0); + alloc_size = (num * vgrnd.params.size_of_opaque_state + page_size - 1) & (~(page_size - 1)); + num = (page_size / vgrnd.params.size_of_opaque_state) * (alloc_size / page_size); + new_block = mmap(0, alloc_size, vgrnd.params.mmap_prot, vgrnd.params.mmap_flags, -1, 0); if (new_block == MAP_FAILED) goto out; - new_cap = grnd_allocator.cap + num; - new_states = reallocarray(grnd_allocator.states, new_cap, sizeof(*grnd_allocator.states)); + new_cap = vgrnd.cap + num; + new_states = reallocarray(vgrnd.states, new_cap, sizeof(*vgrnd.states)); if (!new_states) goto unmap; - grnd_allocator.cap = new_cap; - grnd_allocator.states = new_states; + vgrnd.cap = new_cap; + vgrnd.states = new_states; for (size_t i = 0; i < num; ++i) { - if (((uintptr_t)new_block & (page_size - 1)) + grnd_ctx.params.size_of_opaque_state > page_size) + if (((uintptr_t)new_block & (page_size - 1)) + vgrnd.params.size_of_opaque_state > page_size) new_block = (void *)(((uintptr_t)new_block + page_size - 1) & (~(page_size - 1))); - grnd_allocator.states[i] = new_block; - new_block += grnd_ctx.params.size_of_opaque_state; + vgrnd.states[i] = new_block; + new_block += vgrnd.params.size_of_opaque_state; } - grnd_allocator.len = num; + vgrnd.len = num; goto success; unmap: @@ -89,10 +88,10 @@ static void *vgetrandom_get_state(void) goto out; } success: - state = grnd_allocator.states[--grnd_allocator.len]; + state = vgrnd.states[--vgrnd.len]; out: - pthread_mutex_unlock(&grnd_allocator.lock); + pthread_mutex_unlock(&vgrnd.lock); return state; } @@ -100,27 +99,33 @@ static void vgetrandom_put_state(void *state) { if (!state) return; - pthread_mutex_lock(&grnd_allocator.lock); - grnd_allocator.states[grnd_allocator.len++] = state; - pthread_mutex_unlock(&grnd_allocator.lock); + pthread_mutex_lock(&vgrnd.lock); + vgrnd.states[vgrnd.len++] = state; + pthread_mutex_unlock(&vgrnd.lock); } static void vgetrandom_init(void) { - if (pthread_key_create(&grnd_ctx.key, vgetrandom_put_state) != 0) - return; + const char *version = versions[VDSO_VERSION]; + const char *name = names[VDSO_NAMES][6]; unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); + size_t ret; + if (!sysinfo_ehdr) { printf("AT_SYSINFO_EHDR is not present!\n"); exit(KSFT_SKIP); } vdso_init_from_sysinfo_ehdr(sysinfo_ehdr); - grnd_ctx.fn = (__typeof__(grnd_ctx.fn))vdso_sym("LINUX_2.6", "__vdso_getrandom"); - if (!grnd_ctx.fn) { - printf("__vdso_getrandom is missing!\n"); + vgrnd.fn = (__typeof__(vgrnd.fn))vdso_sym(version, name); + if (!vgrnd.fn) { + printf("%s is missing!\n", name); exit(KSFT_FAIL); } - if (grnd_ctx.fn(NULL, 0, 0, &grnd_ctx.params, ~0UL) != 0) { + ret = VDSO_CALL(vgrnd.fn, 5, NULL, 0, 0, &vgrnd.params, ~0UL); + if (ret == -ENOSYS) { + printf("unsupported architecture\n"); + exit(KSFT_SKIP); + } else if (ret) { printf("failed to fetch vgetrandom params!\n"); exit(KSFT_FAIL); } @@ -128,27 +133,21 @@ static void vgetrandom_init(void) static ssize_t vgetrandom(void *buf, size_t len, unsigned long flags) { - void *state; + static __thread void *state; - pthread_once(&grnd_ctx.initialized, vgetrandom_init); - state = pthread_getspecific(grnd_ctx.key); if (!state) { state = vgetrandom_get_state(); - if (pthread_setspecific(grnd_ctx.key, state) != 0) { - vgetrandom_put_state(state); - state = NULL; - } if (!state) { printf("vgetrandom_get_state failed!\n"); exit(KSFT_FAIL); } } - return grnd_ctx.fn(buf, len, flags, state, grnd_ctx.params.size_of_opaque_state); + return VDSO_CALL(vgrnd.fn, 5, buf, len, flags, state, vgrnd.params.size_of_opaque_state); } enum { TRIALS = 25000000, THREADS = 256 }; -static void *test_vdso_getrandom(void *) +static void *test_vdso_getrandom(void *ctx) { for (size_t i = 0; i < TRIALS; ++i) { unsigned int val; @@ -158,7 +157,7 @@ static void *test_vdso_getrandom(void *) return NULL; } -static void *test_libc_getrandom(void *) +static void *test_libc_getrandom(void *ctx) { for (size_t i = 0; i < TRIALS; ++i) { unsigned int val; @@ -168,7 +167,7 @@ static void *test_libc_getrandom(void *) return NULL; } -static void *test_syscall_getrandom(void *) +static void *test_syscall_getrandom(void *ctx) { for (size_t i = 0; i < TRIALS; ++i) { unsigned int val; @@ -244,9 +243,10 @@ static void fill(void) static void kselftest(void) { uint8_t weird_size[1263]; + pid_t child; ksft_print_header(); - ksft_set_plan(1); + ksft_set_plan(2); for (size_t i = 0; i < 1000; ++i) { ssize_t ret = vgetrandom(weird_size, sizeof(weird_size), 0); @@ -255,6 +255,42 @@ static void kselftest(void) } ksft_test_result_pass("getrandom: PASS\n"); + + unshare(CLONE_NEWUSER); + assert(unshare(CLONE_NEWTIME) == 0); + child = fork(); + assert(child >= 0); + if (!child) { + vgetrandom_init(); + child = getpid(); + assert(ptrace(PTRACE_TRACEME, 0, NULL, NULL) == 0); + assert(kill(child, SIGSTOP) == 0); + assert(vgetrandom(weird_size, sizeof(weird_size), 0) == sizeof(weird_size)); + _exit(0); + } + for (;;) { + struct ptrace_syscall_info info = { 0 }; + int status, ret; + assert(waitpid(child, &status, 0) >= 0); + if (WIFEXITED(status)) { + if (WEXITSTATUS(status) != 0) + exit(KSFT_FAIL); + break; + } + assert(WIFSTOPPED(status)); + if (WSTOPSIG(status) == SIGSTOP) + assert(ptrace(PTRACE_SETOPTIONS, child, 0, PTRACE_O_TRACESYSGOOD) == 0); + else if (WSTOPSIG(status) == (SIGTRAP | 0x80)) { + assert(ptrace(PTRACE_GET_SYSCALL_INFO, child, sizeof(info), &info) > 0); + if (info.op == PTRACE_SYSCALL_INFO_ENTRY && info.entry.nr == __NR_getrandom && + info.entry.args[0] == (uintptr_t)weird_size && info.entry.args[1] == sizeof(weird_size)) + exit(KSFT_FAIL); + } + assert(ptrace(PTRACE_SYSCALL, child, 0, 0) == 0); + } + + ksft_test_result_pass("getrandom timens: PASS\n"); + exit(KSFT_PASS); } @@ -265,6 +301,8 @@ static void usage(const char *argv0) int main(int argc, char *argv[]) { + vgetrandom_init(); + if (argc == 1) { kselftest(); return 0; diff --git a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c index ee4f1ca56a71..e31b18ffae33 100644 --- a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c +++ b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c @@ -19,6 +19,7 @@ #include "../kselftest.h" #include "parse_vdso.h" #include "vdso_config.h" +#include "vdso_call.h" int main(int argc, char **argv) { @@ -43,7 +44,7 @@ int main(int argc, char **argv) } struct timeval tv; - long ret = gtod(&tv, 0); + long ret = VDSO_CALL(gtod, 2, &tv, 0); if (ret == 0) { printf("The time is %lld.%06lld\n", |