diff options
Diffstat (limited to 'tools')
57 files changed, 2198 insertions, 267 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h index ce2ee8f1e361..9306726337fe 100644 --- a/tools/arch/arm64/include/uapi/asm/unistd.h +++ b/tools/arch/arm64/include/uapi/asm/unistd.h @@ -19,7 +19,6 @@ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS -#define __ARCH_WANT_SYS_CLONE3 #define __ARCH_WANT_MEMFD_SECRET #include <asm-generic/unistd.h> diff --git a/tools/arch/loongarch/include/uapi/asm/unistd.h b/tools/arch/loongarch/include/uapi/asm/unistd.h index 0c743344e92d..8eeaac0087c3 100644 --- a/tools/arch/loongarch/include/uapi/asm/unistd.h +++ b/tools/arch/loongarch/include/uapi/asm/unistd.h @@ -4,6 +4,5 @@ */ #define __ARCH_WANT_SYS_CLONE -#define __ARCH_WANT_SYS_CLONE3 #include <asm-generic/unistd.h> diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile index 87b554fab14b..d0b4b0ed10ff 100644 --- a/tools/arch/x86/kcpuid/Makefile +++ b/tools/arch/x86/kcpuid/Makefile @@ -19,6 +19,6 @@ clean : @rm -f kcpuid install : kcpuid - install -d $(DESTDIR)$(BINDIR) + install -d $(DESTDIR)$(BINDIR) $(DESTDIR)$(HWDATADIR) install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid - install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv + install -m 444 -p cpuid.csv $(DESTDIR)$(HWDATADIR)/cpuid.csv diff --git a/tools/gpio/gpio-sloppy-logic-analyzer.sh b/tools/gpio/gpio-sloppy-logic-analyzer.sh new file mode 100755 index 000000000000..ed21a110df5e --- /dev/null +++ b/tools/gpio/gpio-sloppy-logic-analyzer.sh @@ -0,0 +1,246 @@ +#!/bin/sh -eu +# SPDX-License-Identifier: GPL-2.0 +# +# Helper script for the Linux Kernel GPIO sloppy logic analyzer +# +# Copyright (C) Wolfram Sang <wsa@sang-engineering.com> +# Copyright (C) Renesas Electronics Corporation + +samplefreq=1000000 +numsamples=250000 +cpusetdefaultdir='/sys/fs/cgroup' +cpusetprefix='cpuset.' +debugdir='/sys/kernel/debug' +ladirname='gpio-sloppy-logic-analyzer' +outputdir="$PWD" +neededcmds='taskset zip' +max_chans=8 +duration= +initcpu= +listinstances=0 +lainstance= +lasysfsdir= +triggerdat= +trigger_bindat= +progname="${0##*/}" +print_help() +{ + cat << EOF +$progname - helper script for the Linux Kernel Sloppy GPIO Logic Analyzer +Available options: + -c|--cpu <n>: which CPU to isolate for sampling. Only needed once. Default <1>. + Remember that a more powerful CPU gives you higher sampling speeds. + Also CPU0 is not recommended as it usually does extra bookkeeping. + -d|--duration-us <SI-n>: number of microseconds to sample. Overrides -n, no default value. + -h|--help: print this help + -i|--instance <str>: name of the logic analyzer in case you have multiple instances. Default + to first instance found + -k|--kernel-debug-dir <str>: path to the kernel debugfs mountpoint. Default: <$debugdir> + -l|--list-instances: list all available instances + -n|--num_samples <SI-n>: number of samples to acquire. Default <$numsamples> + -o|--output-dir <str>: directory to put the result files. Default: current dir + -s|--sample_freq <SI-n>: desired sampling frequency. Might be capped if too large. + Default: <1000000> + -t|--trigger <str>: pattern to use as trigger. <str> consists of two-char pairs. First + char is channel number starting at "1". Second char is trigger level: + "L" - low; "H" - high; "R" - rising; "F" - falling + These pairs can be combined with "+", so "1H+2F" triggers when probe 1 + is high while probe 2 has a falling edge. You can have multiple triggers + combined with ",". So, "1H+2F,1H+2R" is like the example before but it + waits for a rising edge on probe 2 while probe 1 is still high after the + first trigger has been met. + Trigger data will only be used for the next capture and then be erased. + +<SI-n> is an integer value where SI units "T", "G", "M", "K" are recognized, e.g. '1M500K' is 1500000. + +Examples: +Samples $numsamples values at 1MHz with an already prepared CPU or automatically prepares CPU1 if needed, +use the first logic analyzer instance found: + '$progname' +Samples 50us at 2MHz waiting for a falling edge on channel 2. CPU and instance as above: + '$progname -d 50 -s 2M -t "2F"' + +Note that the process exits after checking all parameters but a sub-process still works in +the background. The result is only available once the sub-process finishes. + +Result is a .sr file to be consumed with PulseView from the free Sigrok project. It is +a zip file which also contains the binary sample data which may be consumed by others. +The filename is the logic analyzer instance name plus a since-epoch timestamp. +EOF +} + +fail() +{ + echo "$1" + exit 1 +} + +parse_si() +{ + conv_si="$(printf $1 | sed 's/[tT]+\?/*1000G+/g; s/[gG]+\?/*1000M+/g; s/[mM]+\?/*1000K+/g; s/[kK]+\?/*1000+/g; s/+$//')" + si_val="$((conv_si))" +} +set_newmask() +{ + for f in $(find "$1" -iname "$2"); do echo "$newmask" > "$f" 2>/dev/null || true; done +} + +init_cpu() +{ + isol_cpu="$1" + + [ -d "$lacpusetdir" ] || mkdir "$lacpusetdir" + + cur_cpu=$(cat "${lacpusetfile}cpus") + [ "$cur_cpu" = "$isol_cpu" ] && return + [ -z "$cur_cpu" ] || fail "CPU$isol_cpu requested but CPU$cur_cpu already isolated" + + echo "$isol_cpu" > "${lacpusetfile}cpus" || fail "Could not isolate CPU$isol_cpu. Does it exist?" + echo 1 > "${lacpusetfile}cpu_exclusive" + echo 0 > "${lacpusetfile}mems" + + oldmask=$(cat /proc/irq/default_smp_affinity) + newmask=$(printf "%x" $((0x$oldmask & ~(1 << isol_cpu)))) + + set_newmask '/proc/irq' '*smp_affinity' + set_newmask '/sys/devices/virtual/workqueue/' 'cpumask' + + # Move tasks away from isolated CPU + for p in $(ps -o pid | tail -n +2); do + mask=$(taskset -p "$p") || continue + # Ignore tasks with a custom mask, i.e. not equal $oldmask + [ "${mask##*: }" = "$oldmask" ] || continue + taskset -p "$newmask" "$p" || continue + done 2>/dev/null >/dev/null + + # Big hammer! Working with 'rcu_momentary_dyntick_idle()' for a more fine-grained solution + # still printed warnings. Same for re-enabling the stall detector after sampling. + echo 1 > /sys/module/rcupdate/parameters/rcu_cpu_stall_suppress + + cpufreqgov="/sys/devices/system/cpu/cpu$isol_cpu/cpufreq/scaling_governor" + [ -w "$cpufreqgov" ] && echo 'performance' > "$cpufreqgov" || true +} + +parse_triggerdat() +{ + oldifs="$IFS" + IFS=','; for trig in $1; do + mask=0; val1=0; val2=0 + IFS='+'; for elem in $trig; do + chan=${elem%[lhfrLHFR]} + mode=${elem#$chan} + # Check if we could parse something and the channel number fits + [ "$chan" != "$elem" ] && [ "$chan" -le $max_chans ] || fail "Trigger syntax error: $elem" + bit=$((1 << (chan - 1))) + mask=$((mask | bit)) + case $mode in + [hH]) val1=$((val1 | bit)); val2=$((val2 | bit));; + [fF]) val1=$((val1 | bit));; + [rR]) val2=$((val2 | bit));; + esac + done + trigger_bindat="$trigger_bindat$(printf '\\%o\\%o' $mask $val1)" + [ $val1 -ne $val2 ] && trigger_bindat="$trigger_bindat$(printf '\\%o\\%o' $mask $val2)" + done + IFS="$oldifs" +} + +do_capture() +{ + taskset "$1" echo 1 > "$lasysfsdir"/capture || fail "Capture error! Check kernel log" + + srtmp=$(mktemp -d) + echo 1 > "$srtmp"/version + cp "$lasysfsdir"/sample_data "$srtmp"/logic-1-1 + cat > "$srtmp"/metadata << EOF +[global] +sigrok version=0.2.0 + +[device 1] +capturefile=logic-1 +total probes=$(wc -l < "$lasysfsdir"/meta_data) +samplerate=${samplefreq}Hz +unitsize=1 +EOF + cat "$lasysfsdir"/meta_data >> "$srtmp"/metadata + + zipname="$outputdir/${lasysfsdir##*/}-$(date +%s).sr" + zip -jq "$zipname" "$srtmp"/* + rm -rf "$srtmp" + delay_ack=$(cat "$lasysfsdir"/delay_ns_acquisition) + [ "$delay_ack" -eq 0 ] && delay_ack=1 + echo "Logic analyzer done. Saved '$zipname'" + echo "Max sample frequency this time: $((1000000000 / delay_ack))Hz." +} + +rep=$(getopt -a -l cpu:,duration-us:,help,instance:,list-instances,kernel-debug-dir:,num_samples:,output-dir:,sample_freq:,trigger: -o c:d:hi:k:ln:o:s:t: -- "$@") || exit 1 +eval set -- "$rep" +while true; do + case "$1" in + -c|--cpu) initcpu="$2"; shift;; + -d|--duration-us) parse_si $2; duration=$si_val; shift;; + -h|--help) print_help; exit 0;; + -i|--instance) lainstance="$2"; shift;; + -k|--kernel-debug-dir) debugdir="$2"; shift;; + -l|--list-instances) listinstances=1;; + -n|--num_samples) parse_si $2; numsamples=$si_val; shift;; + -o|--output-dir) outputdir="$2"; shift;; + -s|--sample_freq) parse_si $2; samplefreq=$si_val; shift;; + -t|--trigger) triggerdat="$2"; shift;; + --) break;; + *) fail "error parsing command line: $*";; + esac + shift +done + +for f in $neededcmds; do + command -v "$f" >/dev/null || fail "Command '$f' not found" +done + +# print cpuset mountpoint if any, errorcode > 0 if noprefix option was found +cpusetdir=$(awk '$3 == "cgroup" && $4 ~ /cpuset/ { print $2; exit (match($4, /noprefix/) > 0) }' /proc/self/mounts) || cpusetprefix='' +if [ -z "$cpusetdir" ]; then + cpusetdir="$cpusetdefaultdir" + [ -d $cpusetdir ] || mkdir $cpusetdir + mount -t cgroup -o cpuset none $cpusetdir || fail "Couldn't mount cpusets. Not in kernel or already in use?" +fi + +lacpusetdir="$cpusetdir/$ladirname" +lacpusetfile="$lacpusetdir/$cpusetprefix" +sysfsdir="$debugdir/$ladirname" + +[ "$samplefreq" -ne 0 ] || fail "Invalid sample frequency" + +[ -d "$sysfsdir" ] || fail "Could not find logic analyzer root dir '$sysfsdir'. Module loaded?" +[ -x "$sysfsdir" ] || fail "Could not access logic analyzer root dir '$sysfsdir'. Need root?" + +[ $listinstances -gt 0 ] && find "$sysfsdir" -mindepth 1 -type d | sed 's|.*/||' && exit 0 + +if [ -n "$lainstance" ]; then + lasysfsdir="$sysfsdir/$lainstance" +else + lasysfsdir=$(find "$sysfsdir" -mindepth 1 -type d -print -quit) +fi +[ -d "$lasysfsdir" ] || fail "Logic analyzer directory '$lasysfsdir' not found!" +[ -d "$outputdir" ] || fail "Output directory '$outputdir' not found!" + +[ -n "$initcpu" ] && init_cpu "$initcpu" +[ -d "$lacpusetdir" ] || { echo "Auto-Isolating CPU1"; init_cpu 1; } + +ndelay=$((1000000000 / samplefreq)) +echo "$ndelay" > "$lasysfsdir"/delay_ns + +[ -n "$duration" ] && numsamples=$((samplefreq * duration / 1000000)) +echo $numsamples > "$lasysfsdir"/buf_size + +if [ -n "$triggerdat" ]; then + parse_triggerdat "$triggerdat" + printf "$trigger_bindat" > "$lasysfsdir"/trigger 2>/dev/null || fail "Trigger data '$triggerdat' rejected" +fi + +workcpu=$(cat "${lacpusetfile}effective_cpus") +[ -n "$workcpu" ] || fail "No isolated CPU found" +cpumask=$(printf '%x' $((1 << workcpu))) +instance=${lasysfsdir##*/} +echo "Setting up '$instance': $numsamples samples at ${samplefreq}Hz with ${triggerdat:-no} trigger using CPU$workcpu" +do_capture "$cpumask" & diff --git a/tools/include/nolibc/stdint.h b/tools/include/nolibc/stdint.h index 6665e272e213..cd79ddd6170e 100644 --- a/tools/include/nolibc/stdint.h +++ b/tools/include/nolibc/stdint.h @@ -96,6 +96,10 @@ typedef uint64_t uintmax_t; #define UINT_FAST32_MAX SIZE_MAX #define UINT_FAST64_MAX UINT64_MAX +#define INTMAX_MIN INT64_MIN +#define INTMAX_MAX INT64_MAX +#define UINTMAX_MAX UINT64_MAX + #ifndef INT_MIN #define INT_MIN (-__INT_MAX__ - 1) #endif @@ -110,4 +114,19 @@ typedef uint64_t uintmax_t; #define LONG_MAX __LONG_MAX__ #endif +#ifndef ULONG_MAX +#define ULONG_MAX ((unsigned long)(__LONG_MAX__) * 2 + 1) +#endif + +#ifndef LLONG_MIN +#define LLONG_MIN (-__LONG_LONG_MAX__ - 1) +#endif +#ifndef LLONG_MAX +#define LLONG_MAX __LONG_LONG_MAX__ +#endif + +#ifndef ULLONG_MAX +#define ULLONG_MAX ((unsigned long long)(__LONG_LONG_MAX__) * 2 + 1) +#endif + #endif /* _NOLIBC_STDINT_H */ diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index 16cd4d807251..c968dbbc4ef8 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -376,6 +376,16 @@ int setvbuf(FILE *stream __attribute__((unused)), return 0; } +static __attribute__((unused)) +const char *strerror(int errno) +{ + static char buf[18] = "errno="; + + i64toa_r(errno, &buf[6]); + + return buf; +} + /* make sure to include all global symbols */ #include "nolibc.h" diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index 5be9d3c7435a..75aa273c23a6 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -438,6 +438,115 @@ char *u64toa(uint64_t in) return itoa_buffer; } +static __attribute__((unused)) +uintmax_t __strtox(const char *nptr, char **endptr, int base, intmax_t lower_limit, uintmax_t upper_limit) +{ + const char signed_ = lower_limit != 0; + unsigned char neg = 0, overflow = 0; + uintmax_t val = 0, limit, old_val; + char c; + + if (base < 0 || base > 36) { + SET_ERRNO(EINVAL); + goto out; + } + + while (isspace(*nptr)) + nptr++; + + if (*nptr == '+') { + nptr++; + } else if (*nptr == '-') { + neg = 1; + nptr++; + } + + if (signed_ && neg) + limit = -(uintmax_t)lower_limit; + else + limit = upper_limit; + + if ((base == 0 || base == 16) && + (strncmp(nptr, "0x", 2) == 0 || strncmp(nptr, "0X", 2) == 0)) { + base = 16; + nptr += 2; + } else if (base == 0 && strncmp(nptr, "0", 1) == 0) { + base = 8; + nptr += 1; + } else if (base == 0) { + base = 10; + } + + while (*nptr) { + c = *nptr; + + if (c >= '0' && c <= '9') + c -= '0'; + else if (c >= 'a' && c <= 'z') + c = c - 'a' + 10; + else if (c >= 'A' && c <= 'Z') + c = c - 'A' + 10; + else + goto out; + + if (c >= base) + goto out; + + nptr++; + old_val = val; + val *= base; + val += c; + + if (val > limit || val < old_val) + overflow = 1; + } + +out: + if (overflow) { + SET_ERRNO(ERANGE); + val = limit; + } + if (endptr) + *endptr = (char *)nptr; + return neg ? -val : val; +} + +static __attribute__((unused)) +long strtol(const char *nptr, char **endptr, int base) +{ + return __strtox(nptr, endptr, base, LONG_MIN, LONG_MAX); +} + +static __attribute__((unused)) +unsigned long strtoul(const char *nptr, char **endptr, int base) +{ + return __strtox(nptr, endptr, base, 0, ULONG_MAX); +} + +static __attribute__((unused)) +long long strtoll(const char *nptr, char **endptr, int base) +{ + return __strtox(nptr, endptr, base, LLONG_MIN, LLONG_MAX); +} + +static __attribute__((unused)) +unsigned long long strtoull(const char *nptr, char **endptr, int base) +{ + return __strtox(nptr, endptr, base, 0, ULLONG_MAX); +} + +static __attribute__((unused)) +intmax_t strtoimax(const char *nptr, char **endptr, int base) +{ + return __strtox(nptr, endptr, base, INTMAX_MIN, INTMAX_MAX); +} + +static __attribute__((unused)) +uintmax_t strtoumax(const char *nptr, char **endptr, int base) +{ + return __strtox(nptr, endptr, base, 0, UINTMAX_MAX); +} + /* make sure to include all global symbols */ #include "nolibc.h" diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index d983c48a3b6a..a00d53d02723 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -776,12 +776,8 @@ __SYSCALL(__NR_fsmount, sys_fsmount) __SYSCALL(__NR_fspick, sys_fspick) #define __NR_pidfd_open 434 __SYSCALL(__NR_pidfd_open, sys_pidfd_open) - -#ifdef __ARCH_WANT_SYS_CLONE3 #define __NR_clone3 435 __SYSCALL(__NR_clone3, sys_clone3) -#endif - #define __NR_close_range 436 __SYSCALL(__NR_close_range, sys_close_range) #define __NR_openat2 437 diff --git a/tools/memory-model/Documentation/README b/tools/memory-model/Documentation/README index db90a26dbdf4..304162743a5b 100644 --- a/tools/memory-model/Documentation/README +++ b/tools/memory-model/Documentation/README @@ -47,6 +47,10 @@ DESCRIPTION OF FILES README This file. +access-marking.txt + Guidelines for marking intentionally concurrent accesses to + shared memory. + cheatsheet.txt Quick-reference guide to the Linux-kernel memory model. diff --git a/tools/memory-model/Documentation/access-marking.txt b/tools/memory-model/Documentation/access-marking.txt index 65778222183e..3fbe77fd564a 100644 --- a/tools/memory-model/Documentation/access-marking.txt +++ b/tools/memory-model/Documentation/access-marking.txt @@ -6,7 +6,8 @@ normal accesses to shared memory, that is "normal" as in accesses that do not use read-modify-write atomic operations. It also describes how to document these accesses, both with comments and with special assertions processed by the Kernel Concurrency Sanitizer (KCSAN). This discussion -builds on an earlier LWN article [1]. +builds on an earlier LWN article [1] and Linux Foundation mentorship +session [2]. ACCESS-MARKING OPTIONS @@ -24,6 +25,11 @@ The Linux kernel provides the following access-marking options: 4. WRITE_ONCE(), for example, "WRITE_ONCE(a, b);" The various forms of atomic_set() also fit in here. +5. __data_racy, for example "int __data_racy a;" + +6. KCSAN's negative-marking assertions, ASSERT_EXCLUSIVE_ACCESS() + and ASSERT_EXCLUSIVE_WRITER(), are described in the + "ACCESS-DOCUMENTATION OPTIONS" section below. These may be used in combination, as shown in this admittedly improbable example: @@ -31,7 +37,7 @@ example: WRITE_ONCE(a, b + data_race(c + d) + READ_ONCE(e)); Neither plain C-language accesses nor data_race() (#1 and #2 above) place -any sort of constraint on the compiler's choice of optimizations [2]. +any sort of constraint on the compiler's choice of optimizations [3]. In contrast, READ_ONCE() and WRITE_ONCE() (#3 and #4 above) restrict the compiler's use of code-motion and common-subexpression optimizations. Therefore, if a given access is involved in an intentional data race, @@ -205,6 +211,23 @@ because doing otherwise prevents KCSAN from detecting violations of your code's synchronization rules. +Use of __data_racy +------------------ + +Adding the __data_racy type qualifier to the declaration of a variable +causes KCSAN to treat all accesses to that variable as if they were +enclosed by data_race(). However, __data_racy does not affect the +compiler, though one could imagine hardened kernel builds treating the +__data_racy type qualifier as if it was the volatile keyword. + +Note well that __data_racy is subject to the same pointer-declaration +rules as are other type qualifiers such as const and volatile. +For example: + + int __data_racy *p; // Pointer to data-racy data. + int *__data_racy p; // Data-racy pointer to non-data-racy data. + + ACCESS-DOCUMENTATION OPTIONS ============================ @@ -342,7 +365,7 @@ as follows: Because foo is read locklessly, all accesses are marked. The purpose of the ASSERT_EXCLUSIVE_WRITER() is to allow KCSAN to check for a buggy -concurrent lockless write. +concurrent write, whether marked or not. Lock-Protected Writes With Heuristic Lockless Reads @@ -594,5 +617,8 @@ REFERENCES [1] "Concurrency bugs should fear the big bad data-race detector (part 2)" https://lwn.net/Articles/816854/ -[2] "Who's afraid of a big bad optimizing compiler?" +[2] "The Kernel Concurrency Sanitizer" + https://www.linuxfoundation.org/webinars/the-kernel-concurrency-sanitizer + +[3] "Who's afraid of a big bad optimizing compiler?" https://lwn.net/Articles/793253/ diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat index 53b5a492739d..03c12efed66a 100644 --- a/tools/memory-model/lock.cat +++ b/tools/memory-model/lock.cat @@ -54,6 +54,12 @@ flag ~empty LKR \ domain(lk-rmw) as unpaired-LKR *) empty ([LKW] ; po-loc ; [LKR]) \ (po-loc ; [UL] ; po-loc) as lock-nest +(* + * In the same way, spin_is_locked() inside a critical section must always + * return True (no RU events can be in a critical section for the same lock). + *) +empty ([LKW] ; po-loc ; [RU]) \ (po-loc ; [UL] ; po-loc) as nested-is-locked + (* The final value of a spinlock should not be tested *) flag ~empty [FW] ; loc ; [ALL-LOCKS] as lock-final @@ -79,42 +85,50 @@ empty ([UNMATCHED-LKW] ; loc ; [UNMATCHED-LKW]) \ id as unmatched-locks (* rfi for LF events: link each LKW to the LF events in its critical section *) let rfi-lf = ([LKW] ; po-loc ; [LF]) \ ([LKW] ; po-loc ; [UL] ; po-loc) -(* rfe for LF events *) +(* Utility macro to convert a single pair to a single-edge relation *) +let pair-to-relation p = p ++ 0 + +(* + * If a given LF event e is outside a critical section, it cannot read + * internally but it may read from an LKW event in another thread. + * Compute the relation containing these possible edges. + *) +let possible-rfe-noncrit-lf e = (LKW * {e}) & loc & ext + +(* Compute set of sets of possible rfe edges for LF events *) let all-possible-rfe-lf = (* - * Given an LF event r, compute the possible rfe edges for that event - * (all those starting from LKW events in other threads), - * and then convert that relation to a set of single-edge relations. + * Convert the possible-rfe-noncrit-lf relation for e + * to a set of single edges *) - let possible-rfe-lf r = - let pair-to-relation p = p ++ 0 - in map pair-to-relation ((LKW * {r}) & loc & ext) - (* Do this for each LF event r that isn't in rfi-lf *) - in map possible-rfe-lf (LF \ range(rfi-lf)) + let set-of-singleton-rfe-lf e = + map pair-to-relation (possible-rfe-noncrit-lf e) + (* Do this for each LF event e that isn't in rfi-lf *) + in map set-of-singleton-rfe-lf (LF \ range(rfi-lf)) (* Generate all rf relations for LF events *) with rfe-lf from cross(all-possible-rfe-lf) let rf-lf = rfe-lf | rfi-lf (* - * RU, i.e., spin_is_locked() returning False, is slightly different. - * We rely on the memory model to rule out cases where spin_is_locked() - * within one of the lock's critical sections returns False. + * A given RU event e may read internally from the last po-previous UL, + * or it may read from a UL event in another thread or the initial write. + * Compute the relation containing these possible edges. *) - -(* rfi for RU events: an RU may read from the last po-previous UL *) -let rfi-ru = ([UL] ; po-loc ; [RU]) \ ([UL] ; po-loc ; [LKW] ; po-loc) - -(* rfe for RU events: an RU may read from an external UL or the initial write *) -let all-possible-rfe-ru = - let possible-rfe-ru r = - let pair-to-relation p = p ++ 0 - in map pair-to-relation (((UL | IW) * {r}) & loc & ext) - in map possible-rfe-ru RU +let possible-rf-ru e = (((UL * {e}) & po-loc) \ + ([UL] ; po-loc ; [UL] ; po-loc)) | + (((UL | IW) * {e}) & loc & ext) + +(* Compute set of sets of possible rf edges for RU events *) +let all-possible-rf-ru = + (* Convert the possible-rf-ru relation for e to a set of single edges *) + let set-of-singleton-rf-ru e = + map pair-to-relation (possible-rf-ru e) + (* Do this for each RU event e *) + in map set-of-singleton-rf-ru RU (* Generate all rf relations for RU events *) -with rfe-ru from cross(all-possible-rfe-ru) -let rf-ru = rfe-ru | rfi-ru +with rf-ru from cross(all-possible-rf-ru) (* Final rf relation *) let rf = rf | rf-lf | rf-ru diff --git a/tools/objtool/Documentation/objtool.txt b/tools/objtool/Documentation/objtool.txt index fe39c2a8ef0d..7c3ee959b63c 100644 --- a/tools/objtool/Documentation/objtool.txt +++ b/tools/objtool/Documentation/objtool.txt @@ -284,6 +284,25 @@ the objtool maintainers. Otherwise the stack frame may not get created before the call. + objtool can help with pinpointing the exact function where it happens: + + $ OBJTOOL_ARGS="--verbose" make arch/x86/kvm/ + + arch/x86/kvm/kvm.o: warning: objtool: .altinstr_replacement+0xc5: call without frame pointer save/setup + arch/x86/kvm/kvm.o: warning: objtool: em_loop.part.0+0x29: (alt) + arch/x86/kvm/kvm.o: warning: objtool: em_loop.part.0+0x0: <=== (sym) + LD [M] arch/x86/kvm/kvm-intel.o + 0000 0000000000028220 <em_loop.part.0>: + 0000 28220: 0f b6 47 61 movzbl 0x61(%rdi),%eax + 0004 28224: 3c e2 cmp $0xe2,%al + 0006 28226: 74 2c je 28254 <em_loop.part.0+0x34> + 0008 28228: 48 8b 57 10 mov 0x10(%rdi),%rdx + 000c 2822c: 83 f0 05 xor $0x5,%eax + 000f 2822f: 48 c1 e0 04 shl $0x4,%rax + 0013 28233: 25 f0 00 00 00 and $0xf0,%eax + 0018 28238: 81 e2 d5 08 00 00 and $0x8d5,%edx + 001e 2823e: 80 ce 02 or $0x2,%dh + ... 2. file.o: warning: objtool: .text+0x53: unreachable instruction diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c index 4134d27c696b..4ea0f9815fda 100644 --- a/tools/objtool/arch/x86/special.c +++ b/tools/objtool/arch/x86/special.c @@ -9,6 +9,29 @@ void arch_handle_alternative(unsigned short feature, struct special_alt *alt) { + static struct special_alt *group, *prev; + + /* + * Recompute orig_len for nested ALTERNATIVE()s. + */ + if (group && group->orig_sec == alt->orig_sec && + group->orig_off == alt->orig_off) { + + struct special_alt *iter = group; + for (;;) { + unsigned int len = max(iter->orig_len, alt->orig_len); + iter->orig_len = alt->orig_len = len; + + if (iter == prev) + break; + + iter = list_next_entry(iter, list); + } + + } else group = alt; + + prev = alt; + switch (feature) { case X86_FEATURE_SMAP: /* diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index 7ebf29c91184..1e8141ef1b15 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -7,12 +7,16 @@ * Yes, this is unfortunate. A better solution is in the works. */ NORETURN(__fortify_panic) +NORETURN(__ia32_sys_exit) +NORETURN(__ia32_sys_exit_group) NORETURN(__kunit_abort) NORETURN(__module_put_and_kthread_exit) NORETURN(__reiserfs_panic) NORETURN(__stack_chk_fail) NORETURN(__tdx_hypercall_failed) NORETURN(__ubsan_handle_builtin_unreachable) +NORETURN(__x64_sys_exit) +NORETURN(__x64_sys_exit_group) NORETURN(arch_cpu_idle_dead) NORETURN(bch2_trans_in_restart_error) NORETURN(bch2_trans_restart_error) diff --git a/tools/objtool/special.c b/tools/objtool/special.c index 91b1950f5bd8..097a69db82a0 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -84,6 +84,14 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry, entry->new_len); } + orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig); + if (!orig_reloc) { + WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); + return -1; + } + + reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off); + if (entry->feature) { unsigned short feature; @@ -94,14 +102,6 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry, arch_handle_alternative(feature, alt); } - orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig); - if (!orig_reloc) { - WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); - return -1; - } - - reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off); - if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); if (!new_reloc) { diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 233f2b6edf52..49b79cf0c5cc 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -86,14 +86,6 @@ static struct comm_str *comm_str__new(const char *str) return result; } -static int comm_str__cmp(const void *_lhs, const void *_rhs) -{ - const struct comm_str *lhs = *(const struct comm_str * const *)_lhs; - const struct comm_str *rhs = *(const struct comm_str * const *)_rhs; - - return strcmp(comm_str__str(lhs), comm_str__str(rhs)); -} - static int comm_str__search(const void *_key, const void *_member) { const char *key = _key; @@ -169,9 +161,24 @@ static struct comm_str *comm_strs__findnew(const char *str) } result = comm_str__new(str); if (result) { - comm_strs->strs[comm_strs->num_strs++] = result; - qsort(comm_strs->strs, comm_strs->num_strs, sizeof(struct comm_str *), - comm_str__cmp); + int low = 0, high = comm_strs->num_strs - 1; + int insert = comm_strs->num_strs; /* Default to inserting at the end. */ + + while (low <= high) { + int mid = low + (high - low) / 2; + int cmp = strcmp(comm_str__str(comm_strs->strs[mid]), str); + + if (cmp < 0) { + low = mid + 1; + } else { + high = mid - 1; + insert = mid; + } + } + memmove(&comm_strs->strs[insert + 1], &comm_strs->strs[insert], + (comm_strs->num_strs - insert) * sizeof(struct comm_str *)); + comm_strs->num_strs++; + comm_strs->strs[insert] = result; } } up_write(&comm_strs->lock); diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c index ab3d0c01dd63..a69a9c661200 100644 --- a/tools/perf/util/dsos.c +++ b/tools/perf/util/dsos.c @@ -203,11 +203,27 @@ int __dsos__add(struct dsos *dsos, struct dso *dso) dsos->dsos = temp; dsos->allocated = to_allocate; } - dsos->dsos[dsos->cnt++] = dso__get(dso); - if (dsos->cnt >= 2 && dsos->sorted) { - dsos->sorted = dsos__cmp_long_name_id_short_name(&dsos->dsos[dsos->cnt - 2], - &dsos->dsos[dsos->cnt - 1]) - <= 0; + if (!dsos->sorted) { + dsos->dsos[dsos->cnt++] = dso__get(dso); + } else { + int low = 0, high = dsos->cnt - 1; + int insert = dsos->cnt; /* Default to inserting at the end. */ + + while (low <= high) { + int mid = low + (high - low) / 2; + int cmp = dsos__cmp_long_name_id_short_name(&dsos->dsos[mid], &dso); + + if (cmp < 0) { + low = mid + 1; + } else { + high = mid - 1; + insert = mid; + } + } + memmove(&dsos->dsos[insert + 1], &dsos->dsos[insert], + (dsos->cnt - insert) * sizeof(struct dso *)); + dsos->cnt++; + dsos->dsos[insert] = dso__get(dso); } dso__set_dsos(dso, dsos); return 0; diff --git a/tools/rcu/rcu-updaters.sh b/tools/rcu/rcu-updaters.sh new file mode 100755 index 000000000000..4ef1397927bb --- /dev/null +++ b/tools/rcu/rcu-updaters.sh @@ -0,0 +1,52 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Run bpftrace to obtain a histogram of the types of primitives used to +# initiate RCU grace periods. The count associated with rcu_gp_init() +# is the number of normal (non-expedited) grace periods. +# +# Usage: rcu-updaters.sh [ duration-in-seconds ] +# +# Note that not all kernel builds have all of these functions. In those +# that do not, this script will issue a diagnostic for each that is not +# found, but continue normally for the rest of the functions. + +duration=${1} +if test -n "${duration}" +then + exitclause='interval:s:'"${duration}"' { exit(); }' +else + echo 'Hit control-C to end sample and print results.' +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, + kprobe:synchronize_rcu_expedited, + kprobe:synchronize_rcu_tasks, + kprobe:synchronize_rcu_tasks_rude, + kprobe:synchronize_rcu_tasks_trace, + kprobe:synchronize_srcu, + kprobe:synchronize_srcu_expedited, + kprobe:get_state_synchronize_rcu, + kprobe:get_state_synchronize_rcu_full, + kprobe:start_poll_synchronize_rcu, + kprobe:start_poll_synchronize_rcu_expedited, + kprobe:start_poll_synchronize_rcu_full, + kprobe:start_poll_synchronize_rcu_expedited_full, + kprobe:poll_state_synchronize_rcu, + kprobe:poll_state_synchronize_rcu_full, + kprobe:cond_synchronize_rcu, + kprobe:cond_synchronize_rcu_full, + kprobe:start_poll_synchronize_srcu, + kprobe:poll_state_synchronize_srcu, + kprobe:rcu_gp_init + { @counts[func] = count(); } '"${exitclause}" diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 3482248aa344..90d5afd52dd0 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -630,11 +630,15 @@ static struct cxl_hdm *mock_cxl_setup_hdm(struct cxl_port *port, struct cxl_endpoint_dvsec_info *info) { struct cxl_hdm *cxlhdm = devm_kzalloc(&port->dev, sizeof(*cxlhdm), GFP_KERNEL); + struct device *dev = &port->dev; if (!cxlhdm) return ERR_PTR(-ENOMEM); cxlhdm->port = port; + cxlhdm->interleave_mask = ~0U; + cxlhdm->iw_cap_mask = ~0UL; + dev_set_drvdata(dev, cxlhdm); return cxlhdm; } diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c index abe4d58d731d..4c941270d8de 100644 --- a/tools/testing/selftests/arm64/abi/ptrace.c +++ b/tools/testing/selftests/arm64/abi/ptrace.c @@ -47,7 +47,7 @@ static void test_tpidr(pid_t child) /* ...write a new value.. */ write_iov.iov_len = sizeof(uint64_t); - write_val[0] = read_val[0]++; + write_val[0] = read_val[0] + 1; ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_TLS, &write_iov); ksft_test_result(ret == 0, "write_tpidr_one\n"); diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index 00e52c966281..8362e7ec35ad 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -2,6 +2,7 @@ fp-pidbench fp-ptrace fp-stress fpsimd-test +kernel-test rdvl-sme rdvl-sve sve-probe-vls diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index 55d4f00d9e8e..d171021e4cdd 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -12,6 +12,7 @@ TEST_GEN_PROGS := \ vec-syscfg \ za-fork za-ptrace TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \ + kernel-test \ rdvl-sme rdvl-sve \ sve-test \ ssve-test \ diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c index dd31647b00a2..faac24bdefeb 100644 --- a/tools/testing/selftests/arm64/fp/fp-stress.c +++ b/tools/testing/selftests/arm64/fp/fp-stress.c @@ -319,6 +319,19 @@ static void start_fpsimd(struct child_data *child, int cpu, int copy) ksft_print_msg("Started %s\n", child->name); } +static void start_kernel(struct child_data *child, int cpu, int copy) +{ + int ret; + + ret = asprintf(&child->name, "KERNEL-%d-%d", cpu, copy); + if (ret == -1) + ksft_exit_fail_msg("asprintf() failed\n"); + + child_start(child, "./kernel-test"); + + ksft_print_msg("Started %s\n", child->name); +} + static void start_sve(struct child_data *child, int vl, int cpu) { int ret; @@ -438,7 +451,7 @@ int main(int argc, char **argv) int ret; int timeout = 10; int cpus, i, j, c; - int sve_vl_count, sme_vl_count, fpsimd_per_cpu; + int sve_vl_count, sme_vl_count; bool all_children_started = false; int seen_children; int sve_vls[MAX_VLS], sme_vls[MAX_VLS]; @@ -482,12 +495,7 @@ int main(int argc, char **argv) have_sme2 = false; } - /* Force context switching if we only have FPSIMD */ - if (!sve_vl_count && !sme_vl_count) - fpsimd_per_cpu = 2; - else - fpsimd_per_cpu = 1; - tests += cpus * fpsimd_per_cpu; + tests += cpus * 2; ksft_print_header(); ksft_set_plan(tests); @@ -542,8 +550,8 @@ int main(int argc, char **argv) tests); for (i = 0; i < cpus; i++) { - for (j = 0; j < fpsimd_per_cpu; j++) - start_fpsimd(&children[num_children++], i, j); + start_fpsimd(&children[num_children++], i, 0); + start_kernel(&children[num_children++], i, 0); for (j = 0; j < sve_vl_count; j++) start_sve(&children[num_children++], sve_vls[j], i); diff --git a/tools/testing/selftests/arm64/fp/kernel-test.c b/tools/testing/selftests/arm64/fp/kernel-test.c new file mode 100644 index 000000000000..e8da3b4cbd23 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/kernel-test.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 ARM Limited. + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <errno.h> +#include <fcntl.h> +#include <signal.h> +#include <string.h> +#include <unistd.h> + +#include <sys/socket.h> + +#include <linux/kernel.h> +#include <linux/if_alg.h> + +#define DATA_SIZE (16 * 4096) + +static int base, sock; + +static int digest_len; +static char *ref; +static char *digest; +static char *alg_name; + +static struct iovec data_iov; +static int zerocopy[2]; +static int sigs; +static int iter; + +static void handle_exit_signal(int sig, siginfo_t *info, void *context) +{ + printf("Terminated by signal %d, iterations=%d, signals=%d\n", + sig, iter, sigs); + exit(0); +} + +static void handle_kick_signal(int sig, siginfo_t *info, void *context) +{ + sigs++; +} + +static char *drivers[] = { + "crct10dif-arm64-ce", + /* "crct10dif-arm64-neon", - Same priority as generic */ + "sha1-ce", + "sha224-arm64", + "sha224-arm64-neon", + "sha224-ce", + "sha256-arm64", + "sha256-arm64-neon", + "sha256-ce", + "sha384-ce", + "sha512-ce", + "sha3-224-ce", + "sha3-256-ce", + "sha3-384-ce", + "sha3-512-ce", + "sm3-ce", + "sm3-neon", +}; + +static bool create_socket(void) +{ + FILE *proc; + struct sockaddr_alg addr; + char buf[1024]; + char *c, *driver_name; + bool is_shash, match; + int ret, i; + + ret = socket(AF_ALG, SOCK_SEQPACKET, 0); + if (ret < 0) { + if (errno == EAFNOSUPPORT) { + printf("AF_ALG not supported\n"); + return false; + } + + printf("Failed to create AF_ALG socket: %s (%d)\n", + strerror(errno), errno); + return false; + } + base = ret; + + memset(&addr, 0, sizeof(addr)); + addr.salg_family = AF_ALG; + strncpy((char *)addr.salg_type, "hash", sizeof(addr.salg_type)); + + proc = fopen("/proc/crypto", "r"); + if (!proc) { + printf("Unable to open /proc/crypto\n"); + return false; + } + + driver_name = NULL; + is_shash = false; + match = false; + + /* Look through /proc/crypto for a driver with kernel mode FP usage */ + while (!match) { + c = fgets(buf, sizeof(buf), proc); + if (!c) { + if (feof(proc)) { + printf("Nothing found in /proc/crypto\n"); + return false; + } + continue; + } + + /* Algorithm descriptions are separated by a blank line */ + if (*c == '\n') { + if (is_shash && driver_name) { + for (i = 0; i < ARRAY_SIZE(drivers); i++) { + if (strcmp(drivers[i], + driver_name) == 0) { + match = true; + } + } + } + + if (!match) { + digest_len = 0; + + free(driver_name); + driver_name = NULL; + + free(alg_name); + alg_name = NULL; + + is_shash = false; + } + continue; + } + + /* Remove trailing newline */ + c = strchr(buf, '\n'); + if (c) + *c = '\0'; + + /* Find the field/value separator and start of the value */ + c = strchr(buf, ':'); + if (!c) + continue; + c += 2; + + if (strncmp(buf, "digestsize", strlen("digestsize")) == 0) + sscanf(c, "%d", &digest_len); + + if (strncmp(buf, "name", strlen("name")) == 0) + alg_name = strdup(c); + + if (strncmp(buf, "driver", strlen("driver")) == 0) + driver_name = strdup(c); + + if (strncmp(buf, "type", strlen("type")) == 0) + if (strncmp(c, "shash", strlen("shash")) == 0) + is_shash = true; + } + + strncpy((char *)addr.salg_name, alg_name, + sizeof(addr.salg_name) - 1); + + ret = bind(base, (struct sockaddr *)&addr, sizeof(addr)); + if (ret < 0) { + printf("Failed to bind %s: %s (%d)\n", + addr.salg_name, strerror(errno), errno); + return false; + } + + ret = accept(base, NULL, 0); + if (ret < 0) { + printf("Failed to accept %s: %s (%d)\n", + addr.salg_name, strerror(errno), errno); + return false; + } + + sock = ret; + + ret = pipe(zerocopy); + if (ret != 0) { + printf("Failed to create zerocopy pipe: %s (%d)\n", + strerror(errno), errno); + return false; + } + + ref = malloc(digest_len); + if (!ref) { + printf("Failed to allocated %d byte reference\n", digest_len); + return false; + } + + digest = malloc(digest_len); + if (!digest) { + printf("Failed to allocated %d byte digest\n", digest_len); + return false; + } + + return true; +} + +static bool compute_digest(void *buf) +{ + struct iovec iov; + int ret, wrote; + + iov = data_iov; + while (iov.iov_len) { + ret = vmsplice(zerocopy[1], &iov, 1, SPLICE_F_GIFT); + if (ret < 0) { + printf("Failed to send buffer: %s (%d)\n", + strerror(errno), errno); + return false; + } + + wrote = ret; + ret = splice(zerocopy[0], NULL, sock, NULL, wrote, 0); + if (ret < 0) { + printf("Failed to splice buffer: %s (%d)\n", + strerror(errno), errno); + } else if (ret != wrote) { + printf("Short splice: %d < %d\n", ret, wrote); + } + + iov.iov_len -= wrote; + iov.iov_base += wrote; + } + +reread: + ret = recv(sock, buf, digest_len, 0); + if (ret == 0) { + printf("No digest returned\n"); + return false; + } + if (ret != digest_len) { + if (errno == -EAGAIN) + goto reread; + printf("Failed to get digest: %s (%d)\n", + strerror(errno), errno); + return false; + } + + return true; +} + +int main(void) +{ + char *data; + struct sigaction sa; + int ret; + + /* Ensure we have unbuffered output */ + setvbuf(stdout, NULL, _IOLBF, 0); + + /* The parent will communicate with us via signals */ + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handle_exit_signal; + sa.sa_flags = SA_RESTART | SA_SIGINFO; + sigemptyset(&sa.sa_mask); + ret = sigaction(SIGTERM, &sa, NULL); + if (ret < 0) + printf("Failed to install SIGTERM handler: %s (%d)\n", + strerror(errno), errno); + + sa.sa_sigaction = handle_kick_signal; + ret = sigaction(SIGUSR2, &sa, NULL); + if (ret < 0) + printf("Failed to install SIGUSR2 handler: %s (%d)\n", + strerror(errno), errno); + + data = malloc(DATA_SIZE); + if (!data) { + printf("Failed to allocate data buffer\n"); + return EXIT_FAILURE; + } + memset(data, 0, DATA_SIZE); + + data_iov.iov_base = data; + data_iov.iov_len = DATA_SIZE; + + /* + * If we can't create a socket assume it's a lack of system + * support and fall back to a basic FPSIMD test for the + * benefit of fp-stress. + */ + if (!create_socket()) { + execl("./fpsimd-test", "./fpsimd-test", NULL); + printf("Failed to fall back to fspimd-test: %d (%s)\n", + errno, strerror(errno)); + return EXIT_FAILURE; + } + + /* + * Compute a reference digest we hope is repeatable, we do + * this at runtime partly to make it easier to play with + * parameters. + */ + if (!compute_digest(ref)) { + printf("Failed to compute reference digest\n"); + return EXIT_FAILURE; + } + + printf("AF_ALG using %s\n", alg_name); + + while (true) { + if (!compute_digest(digest)) { + printf("Failed to compute digest, iter=%d\n", iter); + return EXIT_FAILURE; + } + + if (memcmp(ref, digest, digest_len) != 0) { + printf("Digest mismatch, iter=%d\n", iter); + return EXIT_FAILURE; + } + + iter++; + } + + return EXIT_FAILURE; +} diff --git a/tools/testing/selftests/arm64/tags/Makefile b/tools/testing/selftests/arm64/tags/Makefile index 6d29cfde43a2..0a77f35295fb 100644 --- a/tools/testing/selftests/arm64/tags/Makefile +++ b/tools/testing/selftests/arm64/tags/Makefile @@ -2,6 +2,5 @@ CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := tags_test -TEST_PROGS := run_tags_test.sh include ../../lib.mk diff --git a/tools/testing/selftests/arm64/tags/run_tags_test.sh b/tools/testing/selftests/arm64/tags/run_tags_test.sh deleted file mode 100755 index 745f11379930..000000000000 --- a/tools/testing/selftests/arm64/tags/run_tags_test.sh +++ /dev/null @@ -1,12 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -echo "--------------------" -echo "running tags test" -echo "--------------------" -./tags_test -if [ $? -ne 0 ]; then - echo "[FAIL]" -else - echo "[PASS]" -fi diff --git a/tools/testing/selftests/arm64/tags/tags_test.c b/tools/testing/selftests/arm64/tags/tags_test.c index 955f87c1170d..8ae26e496c89 100644 --- a/tools/testing/selftests/arm64/tags/tags_test.c +++ b/tools/testing/selftests/arm64/tags/tags_test.c @@ -17,19 +17,21 @@ int main(void) static int tbi_enabled = 0; unsigned long tag = 0; struct utsname *ptr; - int err; + + ksft_print_header(); + ksft_set_plan(1); if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE, 0, 0, 0) == 0) tbi_enabled = 1; ptr = (struct utsname *)malloc(sizeof(*ptr)); if (!ptr) - ksft_exit_fail_msg("Failed to allocate utsname buffer\n"); + ksft_exit_fail_perror("Failed to allocate utsname buffer"); if (tbi_enabled) tag = 0x42; ptr = (struct utsname *)SET_TAG(ptr, tag); - err = uname(ptr); + ksft_test_result(!uname(ptr), "Syscall successful with tagged address\n"); free(ptr); - return err; + ksft_finished(); } diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index eeabd798bc3a..98b6b6a886ce 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -58,9 +58,12 @@ CONFIG_MPLS=y CONFIG_MPLS_IPTUNNEL=y CONFIG_MPLS_ROUTING=y CONFIG_MPTCP=y +CONFIG_NET_ACT_SKBMOD=y +CONFIG_NET_CLS=y CONFIG_NET_CLS_ACT=y CONFIG_NET_CLS_BPF=y CONFIG_NET_CLS_FLOWER=y +CONFIG_NET_CLS_MATCHALL=y CONFIG_NET_FOU=y CONFIG_NET_FOU_IP_TUNNELS=y CONFIG_NET_IPGRE=y diff --git a/tools/testing/selftests/bpf/prog_tests/tc_links.c b/tools/testing/selftests/bpf/prog_tests/tc_links.c index bc9841144685..1af9ec1149aa 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_links.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_links.c @@ -9,6 +9,8 @@ #define ping_cmd "ping -q -c1 -w1 127.0.0.1 > /dev/null" #include "test_tc_link.skel.h" + +#include "netlink_helpers.h" #include "tc_helpers.h" void serial_test_tc_links_basic(void) @@ -1787,6 +1789,65 @@ void serial_test_tc_links_ingress(void) test_tc_links_ingress(BPF_TCX_INGRESS, false, false); } +struct qdisc_req { + struct nlmsghdr n; + struct tcmsg t; + char buf[1024]; +}; + +static int qdisc_replace(int ifindex, const char *kind, bool block) +{ + struct rtnl_handle rth = { .fd = -1 }; + struct qdisc_req req; + int err; + + err = rtnl_open(&rth, 0); + if (!ASSERT_OK(err, "open_rtnetlink")) + return err; + + memset(&req, 0, sizeof(req)); + req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.n.nlmsg_flags = NLM_F_CREATE | NLM_F_REPLACE | NLM_F_REQUEST; + req.n.nlmsg_type = RTM_NEWQDISC; + req.t.tcm_family = AF_UNSPEC; + req.t.tcm_ifindex = ifindex; + req.t.tcm_parent = 0xfffffff1; + + addattr_l(&req.n, sizeof(req), TCA_KIND, kind, strlen(kind) + 1); + if (block) + addattr32(&req.n, sizeof(req), TCA_INGRESS_BLOCK, 1); + + err = rtnl_talk(&rth, &req.n, NULL); + ASSERT_OK(err, "talk_rtnetlink"); + rtnl_close(&rth); + return err; +} + +void serial_test_tc_links_dev_chain0(void) +{ + int err, ifindex; + + ASSERT_OK(system("ip link add dev foo type veth peer name bar"), "add veth"); + ifindex = if_nametoindex("foo"); + ASSERT_NEQ(ifindex, 0, "non_zero_ifindex"); + err = qdisc_replace(ifindex, "ingress", true); + if (!ASSERT_OK(err, "attaching ingress")) + goto cleanup; + ASSERT_OK(system("tc filter add block 1 matchall action skbmod swap mac"), "add block"); + err = qdisc_replace(ifindex, "clsact", false); + if (!ASSERT_OK(err, "attaching clsact")) + goto cleanup; + /* Heuristic: kern_sync_rcu() alone does not work; a wait-time of ~5s + * triggered the issue without the fix reliably 100% of the time. + */ + sleep(5); + ASSERT_OK(system("tc filter add dev foo ingress matchall action skbmod swap mac"), "add filter"); +cleanup: + ASSERT_OK(system("ip link del dev foo"), "del veth"); + ASSERT_EQ(if_nametoindex("foo"), 0, "foo removed"); + ASSERT_EQ(if_nametoindex("bar"), 0, "bar removed"); +} + static void test_tc_links_dev_mixed(int target) { LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c new file mode 100644 index 000000000000..871d16cb95cf --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <sched.h> +#include <test_progs.h> +#include <pthread.h> +#include <network_helpers.h> + +#include "timer_lockup.skel.h" + +static long cpu; +static int *timer1_err; +static int *timer2_err; +static bool skip; + +volatile int k = 0; + +static void *timer_lockup_thread(void *arg) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1000, + ); + int i, prog_fd = *(int *)arg; + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(__sync_fetch_and_add(&cpu, 1), &cpuset); + ASSERT_OK(pthread_setaffinity_np(pthread_self(), sizeof(cpuset), + &cpuset), + "cpu affinity"); + + for (i = 0; !READ_ONCE(*timer1_err) && !READ_ONCE(*timer2_err); i++) { + bpf_prog_test_run_opts(prog_fd, &opts); + /* Skip the test if we can't reproduce the race in a reasonable + * amount of time. + */ + if (i > 50) { + WRITE_ONCE(skip, true); + break; + } + } + + return NULL; +} + +void test_timer_lockup(void) +{ + int timer1_prog, timer2_prog; + struct timer_lockup *skel; + pthread_t thrds[2]; + void *ret; + + skel = timer_lockup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load")) + return; + + timer1_prog = bpf_program__fd(skel->progs.timer1_prog); + timer2_prog = bpf_program__fd(skel->progs.timer2_prog); + + timer1_err = &skel->bss->timer1_err; + timer2_err = &skel->bss->timer2_err; + + if (!ASSERT_OK(pthread_create(&thrds[0], NULL, timer_lockup_thread, + &timer1_prog), + "pthread_create thread1")) + goto out; + if (!ASSERT_OK(pthread_create(&thrds[1], NULL, timer_lockup_thread, + &timer2_prog), + "pthread_create thread2")) { + pthread_exit(&thrds[0]); + goto out; + } + + pthread_join(thrds[1], &ret); + pthread_join(thrds[0], &ret); + + if (skip) { + test__skip(); + goto out; + } + + if (*timer1_err != -EDEADLK && *timer1_err != 0) + ASSERT_FAIL("timer1_err bad value"); + if (*timer2_err != -EDEADLK && *timer2_err != 0) + ASSERT_FAIL("timer2_err bad value"); +out: + timer_lockup__destroy(skel); + return; +} diff --git a/tools/testing/selftests/bpf/progs/timer_lockup.c b/tools/testing/selftests/bpf/progs/timer_lockup.c new file mode 100644 index 000000000000..3e520133281e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_lockup.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <time.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct elem { + struct bpf_timer t; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} timer1_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} timer2_map SEC(".maps"); + +int timer1_err; +int timer2_err; + +static int timer_cb1(void *map, int *k, struct elem *v) +{ + struct bpf_timer *timer; + int key = 0; + + timer = bpf_map_lookup_elem(&timer2_map, &key); + if (timer) + timer2_err = bpf_timer_cancel(timer); + + return 0; +} + +static int timer_cb2(void *map, int *k, struct elem *v) +{ + struct bpf_timer *timer; + int key = 0; + + timer = bpf_map_lookup_elem(&timer1_map, &key); + if (timer) + timer1_err = bpf_timer_cancel(timer); + + return 0; +} + +SEC("tc") +int timer1_prog(void *ctx) +{ + struct bpf_timer *timer; + int key = 0; + + timer = bpf_map_lookup_elem(&timer1_map, &key); + if (timer) { + bpf_timer_init(timer, &timer1_map, CLOCK_BOOTTIME); + bpf_timer_set_callback(timer, timer_cb1); + bpf_timer_start(timer, 1, BPF_F_TIMER_CPU_PIN); + } + + return 0; +} + +SEC("tc") +int timer2_prog(void *ctx) +{ + struct bpf_timer *timer; + int key = 0; + + timer = bpf_map_lookup_elem(&timer2_map, &key); + if (timer) { + bpf_timer_init(timer, &timer2_map, CLOCK_BOOTTIME); + bpf_timer_set_callback(timer, timer_cb2); + bpf_timer_start(timer, 1, BPF_F_TIMER_CPU_PIN); + } + + return 0; +} diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore index 2732e0b29271..952e4448bf07 100644 --- a/tools/testing/selftests/cgroup/.gitignore +++ b/tools/testing/selftests/cgroup/.gitignore @@ -1,11 +1,12 @@ # SPDX-License-Identifier: GPL-2.0-only -test_memcontrol test_core -test_freezer -test_kmem -test_kill test_cpu test_cpuset -test_zswap +test_freezer test_hugetlb_memcg +test_kill +test_kmem +test_memcontrol +test_pids +test_zswap wait_inotify diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 16461dc0ffdf..1b897152bab6 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -6,26 +6,29 @@ all: ${HELPER_PROGS} TEST_FILES := with_stress.sh TEST_PROGS := test_stress.sh test_cpuset_prs.sh test_cpuset_v1_hp.sh TEST_GEN_FILES := wait_inotify -TEST_GEN_PROGS = test_memcontrol -TEST_GEN_PROGS += test_kmem -TEST_GEN_PROGS += test_core -TEST_GEN_PROGS += test_freezer -TEST_GEN_PROGS += test_kill +# Keep the lists lexicographically sorted +TEST_GEN_PROGS = test_core TEST_GEN_PROGS += test_cpu TEST_GEN_PROGS += test_cpuset -TEST_GEN_PROGS += test_zswap +TEST_GEN_PROGS += test_freezer TEST_GEN_PROGS += test_hugetlb_memcg +TEST_GEN_PROGS += test_kill +TEST_GEN_PROGS += test_kmem +TEST_GEN_PROGS += test_memcontrol +TEST_GEN_PROGS += test_pids +TEST_GEN_PROGS += test_zswap LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h include ../lib.mk -$(OUTPUT)/test_memcontrol: cgroup_util.c -$(OUTPUT)/test_kmem: cgroup_util.c $(OUTPUT)/test_core: cgroup_util.c -$(OUTPUT)/test_freezer: cgroup_util.c -$(OUTPUT)/test_kill: cgroup_util.c $(OUTPUT)/test_cpu: cgroup_util.c $(OUTPUT)/test_cpuset: cgroup_util.c -$(OUTPUT)/test_zswap: cgroup_util.c +$(OUTPUT)/test_freezer: cgroup_util.c $(OUTPUT)/test_hugetlb_memcg: cgroup_util.c +$(OUTPUT)/test_kill: cgroup_util.c +$(OUTPUT)/test_kmem: cgroup_util.c +$(OUTPUT)/test_memcontrol: cgroup_util.c +$(OUTPUT)/test_pids: cgroup_util.c +$(OUTPUT)/test_zswap: cgroup_util.c diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index b5eb1be2248c..7c08cc153367 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -28,6 +28,14 @@ CPULIST=$(cat $CGROUP2/cpuset.cpus.effective) NR_CPUS=$(lscpu | grep "^CPU(s):" | sed -e "s/.*:[[:space:]]*//") [[ $NR_CPUS -lt 8 ]] && skip_test "Test needs at least 8 cpus available!" +# Check to see if /dev/console exists and is writable +if [[ -c /dev/console && -w /dev/console ]] +then + CONSOLE=/dev/console +else + CONSOLE=/dev/null +fi + # Set verbose flag and delay factor PROG=$1 VERBOSE=0 @@ -103,8 +111,8 @@ console_msg() { MSG=$1 echo "$MSG" - echo "" > /dev/console - echo "$MSG" > /dev/console + echo "" > $CONSOLE + echo "$MSG" > $CONSOLE pause 0.01 } @@ -161,6 +169,14 @@ test_add_proc() # T = put a task into cgroup # O<c>=<v> = Write <v> to CPU online file of <c> # +# ECPUs - effective CPUs of cpusets +# Pstate - partition root state +# ISOLCPUS - isolated CPUs (<icpus>[,<icpus2>]) +# +# Note that if there are 2 fields in ISOLCPUS, the first one is for +# sched-debug matching which includes offline CPUs and single-CPU partitions +# while the second one is for matching cpuset.cpus.isolated. +# SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1" TEST_MATRIX=( # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS @@ -220,23 +236,29 @@ TEST_MATRIX=( " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1,A2:2-3,A3:2-3 A1:P0,A2:P2 2-3" " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2,A2:3,A3:3 A1:P0,A2:P2 3" " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-2,A2:1-2,A3:3 A1:P0,A3:P2 3" + " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3" " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-3,A2:1-3,A3:2-3,B1:2-3 A1:P0,A3:P0,B1:P-2" " C0-3:S+ C1-3:S+ C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3,B1:4 A3:P2,B1:P2 2-4" " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3,B1:4 A3:P2,B1:P2 2-4" " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1,A3:2-3 A2:P2,A3:P2 1-3" " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3,B1:4-5 A3:P2,B1:P2 2-5" + " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4,A2:1-3,A3:1-3 A2:P2 1-3" + " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4,A2:4,A3:2-3 A3:P2 2-3" # Nested remote/local partition tests " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1,A2:,A3:2-3,B1:4-5 \ A1:P0,A2:P1,A3:P2,B1:P1 2-3" " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1,A2:,A3:2-3,B1:4 \ A1:P0,A2:P1,A3:P2,B1:P1 2-4,2-3" + " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1,A2:2-3,A3:2-3,B1:4 \ + A1:P0,A2:P1,A3:P0,B1:P1" " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1,A2:2,A3:3,B1:4 \ A1:P0,A2:P1,A3:P2,B1:P1 2-4,3" " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1,A2:2-3,A3:4 \ A1:P0,A2:P2,A3:P1 2-4,2-3" + " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1,A2:2,A3:3-4 \ + A1:P0,A2:P2,A3:P1 2" " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ . . X5 . . 0 A1:0-4,A2:1-4,A3:2-4 \ A1:P0,A2:P-2,A3:P-1" @@ -262,8 +284,8 @@ TEST_MATRIX=( . . X2-3 P2 . . 0 A1:0-2,A2:3,XA2:3 A2:P2 3" # Invalid to valid local partition direct transition tests - " C1-3:S+:P2 C2-3:X1:P2 . . . . . . 0 A1:1-3,XA1:1-3,A2:2-3:XA2: A1:P2,A2:P-2 1-3" - " C1-3:S+:P2 C2-3:X1:P2 . . . X3:P2 . . 0 A1:1-2,XA1:1-3,A2:3:XA2:3 A1:P2,A2:P2 1-3" + " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3,XA1:1-3,A2:1-3:XA2: A1:P2,A2:P-2 1-3" + " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2,XA1:1-3,A2:3:XA2:3 A1:P2,A2:P2 1-3" " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4,B1:4-6 A1:P-2,B1:P0" " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3,B1:4-6 A1:P2,B1:P0 0-3" " C0-3:P2 . . C3-5:C4-5 . . . . 0 A1:0-3,B1:4-5 A1:P2,B1:P0 0-3" @@ -274,32 +296,26 @@ TEST_MATRIX=( " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ . . X4 . . 0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3" " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ - . . C4 . . 0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3" + . . C4:X . . 0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3" # Local partition CPU change tests " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2,A2:3-5 A1:P2,A2:P1 0-2" " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3,A2:4-5 A1:P2,A2:P1 1-3" # cpus_allowed/exclusive_cpus update tests " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ - . C4 . P2 . 0 A1:4,A2:4,XA2:,XA3:,A3:4 \ + . X:C4 . P2 . 0 A1:4,A2:4,XA2:,XA3:,A3:4 \ A1:P0,A3:P-2" " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ . X1 . P2 . 0 A1:0-3,A2:1-3,XA1:1,XA2:,XA3:,A3:2-3 \ A1:P0,A3:P-2" " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ - . . C3 P2 . 0 A1:0-2,A2:0-2,XA2:3,XA3:3,A3:3 \ - A1:P0,A3:P2 3" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ . . X3 P2 . 0 A1:0-2,A2:1-2,XA2:3,XA3:3,A3:3 \ A1:P0,A3:P2 3" " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ . . X3 . . 0 A1:0-3,A2:1-3,XA2:3,XA3:3,A3:2-3 \ A1:P0,A3:P-2" " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ - . . C3 . . 0 A1:0-3,A2:3,XA2:3,XA3:3,A3:3 \ - A1:P0,A3:P-2" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ - . C4 . . . 0 A1:4,A2:4,A3:4,XA1:,XA2:,XA3 \ + . X4 . . . 0 A1:0-3,A2:1-3,A3:2-3,XA1:4,XA2:,XA3 \ A1:P0,A3:P-2" # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS @@ -346,6 +362,9 @@ TEST_MATRIX=( " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P-1,B1:P-1" " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P0,B1:P-1" + # 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" + # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: @@ -355,6 +374,9 @@ TEST_MATRIX=( # Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3,B1:4-5" + + # cpuset.cpus cannot be a subset of sibling cpuset.cpus.exclusive + " C0-3 . . C4-5 X3-5 . . . 1 A1:0-3,B1:4-5" ) # @@ -556,14 +578,15 @@ check_cgroup_states() do set -- $(echo $CHK | sed -e "s/:/ /g") CGRP=$1 + CGRP_DIR=$CGRP STATE=$2 FILE= EVAL=$(expr substr $STATE 2 2) - [[ $CGRP = A2 ]] && CGRP=A1/A2 - [[ $CGRP = A3 ]] && CGRP=A1/A2/A3 + [[ $CGRP = A2 ]] && CGRP_DIR=A1/A2 + [[ $CGRP = A3 ]] && CGRP_DIR=A1/A2/A3 case $STATE in - P*) FILE=$CGRP/cpuset.cpus.partition + P*) FILE=$CGRP_DIR/cpuset.cpus.partition ;; *) echo "Unknown state: $STATE!" exit 1 @@ -587,6 +610,16 @@ check_cgroup_states() ;; esac [[ $EVAL != $VAL ]] && return 1 + + # + # For root partition, dump sched-domains info to console if + # verbose mode set for manual comparison with sched debug info. + # + [[ $VAL -eq 1 && $VERBOSE -gt 0 ]] && { + DOMS=$(cat $CGRP_DIR/cpuset.cpus.effective) + [[ -n "$DOMS" ]] && + echo " [$CGRP] sched-domain: $DOMS" > $CONSOLE + } done return 0 } @@ -694,9 +727,9 @@ null_isolcpus_check() [[ $VERBOSE -gt 0 ]] || return 0 # Retry a few times before printing error RETRY=0 - while [[ $RETRY -lt 5 ]] + while [[ $RETRY -lt 8 ]] do - pause 0.01 + pause 0.02 check_isolcpus "." [[ $? -eq 0 ]] && return 0 ((RETRY++)) @@ -726,7 +759,7 @@ run_state_test() while [[ $I -lt $CNT ]] do - echo "Running test $I ..." > /dev/console + echo "Running test $I ..." > $CONSOLE [[ $VERBOSE -gt 1 ]] && { echo "" eval echo \${$TEST[$I]} @@ -783,7 +816,7 @@ run_state_test() while [[ $NEWLIST != $CPULIST && $RETRY -lt 8 ]] do # Wait a bit longer & recheck a few times - pause 0.01 + pause 0.02 ((RETRY++)) NEWLIST=$(cat cpuset.cpus.effective) done diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c new file mode 100644 index 000000000000..9ecb83c6cc5c --- /dev/null +++ b/tools/testing/selftests/cgroup/test_pids.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <errno.h> +#include <linux/limits.h> +#include <signal.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include "../kselftest.h" +#include "cgroup_util.h" + +static int run_success(const char *cgroup, void *arg) +{ + return 0; +} + +static int run_pause(const char *cgroup, void *arg) +{ + return pause(); +} + +/* + * This test checks that pids.max prevents forking new children above the + * specified limit in the cgroup. + */ +static int test_pids_max(const char *root) +{ + int ret = KSFT_FAIL; + char *cg_pids; + int pid; + + cg_pids = cg_name(root, "pids_test"); + if (!cg_pids) + goto cleanup; + + if (cg_create(cg_pids)) + goto cleanup; + + if (cg_read_strcmp(cg_pids, "pids.max", "max\n")) + goto cleanup; + + if (cg_write(cg_pids, "pids.max", "2")) + goto cleanup; + + if (cg_enter_current(cg_pids)) + goto cleanup; + + pid = cg_run_nowait(cg_pids, run_pause, NULL); + if (pid < 0) + goto cleanup; + + if (cg_run_nowait(cg_pids, run_success, NULL) != -1 || errno != EAGAIN) + goto cleanup; + + if (kill(pid, SIGINT)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + cg_enter_current(root); + cg_destroy(cg_pids); + free(cg_pids); + + return ret; +} + +/* + * This test checks that pids.events are counted in cgroup associated with pids.max + */ +static int test_pids_events(const char *root) +{ + int ret = KSFT_FAIL; + char *cg_parent = NULL, *cg_child = NULL; + int pid; + + cg_parent = cg_name(root, "pids_parent"); + cg_child = cg_name(cg_parent, "pids_child"); + if (!cg_parent || !cg_child) + goto cleanup; + + if (cg_create(cg_parent)) + goto cleanup; + if (cg_write(cg_parent, "cgroup.subtree_control", "+pids")) + goto cleanup; + if (cg_create(cg_child)) + goto cleanup; + + if (cg_write(cg_parent, "pids.max", "2")) + goto cleanup; + + if (cg_read_strcmp(cg_child, "pids.max", "max\n")) + goto cleanup; + + if (cg_enter_current(cg_child)) + goto cleanup; + + pid = cg_run_nowait(cg_child, run_pause, NULL); + if (pid < 0) + goto cleanup; + + if (cg_run_nowait(cg_child, run_success, NULL) != -1 || errno != EAGAIN) + goto cleanup; + + if (kill(pid, SIGINT)) + goto cleanup; + + if (cg_read_key_long(cg_child, "pids.events", "max ") != 0) + goto cleanup; + if (cg_read_key_long(cg_parent, "pids.events", "max ") != 1) + goto cleanup; + + + ret = KSFT_PASS; + +cleanup: + cg_enter_current(root); + if (cg_child) + cg_destroy(cg_child); + if (cg_parent) + cg_destroy(cg_parent); + free(cg_child); + free(cg_parent); + + return ret; +} + + + +#define T(x) { x, #x } +struct pids_test { + int (*fn)(const char *root); + const char *name; +} tests[] = { + T(test_pids_max), + T(test_pids_events), +}; +#undef T + +int main(int argc, char **argv) +{ + char root[PATH_MAX]; + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(tests)); + if (cg_find_unified_root(root, sizeof(root), NULL)) + ksft_exit_skip("cgroup v2 isn't mounted\n"); + + /* + * Check that pids controller is available: + * pids is listed in cgroup.controllers + */ + if (cg_read_strstr(root, "cgroup.controllers", "pids")) + ksft_exit_skip("pids controller isn't available\n"); + + if (cg_read_strstr(root, "cgroup.subtree_control", "pids")) + if (cg_write(root, "cgroup.subtree_control", "+pids")) + ksft_exit_skip("Failed to set pids controller\n"); + + for (int i = 0; i < ARRAY_SIZE(tests); i++) { + switch (tests[i].fn(root)) { + case KSFT_PASS: + ksft_test_result_pass("%s\n", tests[i].name); + break; + case KSFT_SKIP: + ksft_test_result_skip("%s\n", tests[i].name); + break; + default: + ksft_test_result_fail("%s\n", tests[i].name); + break; + } + } + + ksft_finished(); +} diff --git a/tools/testing/selftests/filesystems/statmount/Makefile b/tools/testing/selftests/filesystems/statmount/Makefile index 07a0d5b545ca..3af3136e35a4 100644 --- a/tools/testing/selftests/filesystems/statmount/Makefile +++ b/tools/testing/selftests/filesystems/statmount/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-or-later CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) -TEST_GEN_PROGS := statmount_test +TEST_GEN_PROGS := statmount_test statmount_test_ns include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/statmount/statmount.h b/tools/testing/selftests/filesystems/statmount/statmount.h new file mode 100644 index 000000000000..f4294bab9d73 --- /dev/null +++ b/tools/testing/selftests/filesystems/statmount/statmount.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __STATMOUNT_H +#define __STATMOUNT_H + +#include <stdint.h> +#include <linux/mount.h> +#include <asm/unistd.h> + +static inline int statmount(uint64_t mnt_id, uint64_t mnt_ns_id, uint64_t mask, + struct statmount *buf, size_t bufsize, + unsigned int flags) +{ + struct mnt_id_req req = { + .size = MNT_ID_REQ_SIZE_VER0, + .mnt_id = mnt_id, + .param = mask, + }; + + if (mnt_ns_id) { + req.size = MNT_ID_REQ_SIZE_VER1; + req.mnt_ns_id = mnt_ns_id; + } + + return syscall(__NR_statmount, &req, buf, bufsize, flags); +} + +static ssize_t listmount(uint64_t mnt_id, uint64_t mnt_ns_id, + uint64_t last_mnt_id, uint64_t list[], size_t num, + unsigned int flags) +{ + struct mnt_id_req req = { + .size = MNT_ID_REQ_SIZE_VER0, + .mnt_id = mnt_id, + .param = last_mnt_id, + }; + + if (mnt_ns_id) { + req.size = MNT_ID_REQ_SIZE_VER1; + req.mnt_ns_id = mnt_ns_id; + } + + return syscall(__NR_listmount, &req, list, num, flags); +} + +#endif /* __STATMOUNT_H */ diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c index e8c019d72cbf..c773334bbcc9 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -4,17 +4,15 @@ #include <assert.h> #include <stddef.h> -#include <stdint.h> #include <sched.h> #include <fcntl.h> #include <sys/param.h> #include <sys/mount.h> #include <sys/stat.h> #include <sys/statfs.h> -#include <linux/mount.h> #include <linux/stat.h> -#include <asm/unistd.h> +#include "statmount.h" #include "../../kselftest.h" static const char *const known_fs[] = { @@ -36,18 +34,6 @@ static const char *const known_fs[] = { "ufs", "v7", "vboxsf", "vfat", "virtiofs", "vxfs", "xenfs", "xfs", "zonefs", NULL }; -static int statmount(uint64_t mnt_id, uint64_t mask, struct statmount *buf, - size_t bufsize, unsigned int flags) -{ - struct mnt_id_req req = { - .size = MNT_ID_REQ_SIZE_VER0, - .mnt_id = mnt_id, - .param = mask, - }; - - return syscall(__NR_statmount, &req, buf, bufsize, flags); -} - static struct statmount *statmount_alloc(uint64_t mnt_id, uint64_t mask, unsigned int flags) { size_t bufsize = 1 << 15; @@ -56,7 +42,7 @@ static struct statmount *statmount_alloc(uint64_t mnt_id, uint64_t mask, unsigne int ret; for (;;) { - ret = statmount(mnt_id, mask, tmp, bufsize, flags); + ret = statmount(mnt_id, 0, mask, tmp, bufsize, flags); if (ret != -1) break; if (tofree) @@ -121,7 +107,7 @@ static char root_mntpoint[] = "/tmp/statmount_test_root.XXXXXX"; static int orig_root; static uint64_t root_id, parent_id; static uint32_t old_root_id, old_parent_id; - +static FILE *f_mountinfo; static void cleanup_namespace(void) { @@ -146,7 +132,7 @@ static void setup_namespace(void) uid_t uid = getuid(); gid_t gid = getgid(); - ret = unshare(CLONE_NEWNS|CLONE_NEWUSER); + ret = unshare(CLONE_NEWNS|CLONE_NEWUSER|CLONE_NEWPID); if (ret == -1) ksft_exit_fail_msg("unsharing mountns and userns: %s\n", strerror(errno)); @@ -157,6 +143,11 @@ static void setup_namespace(void) sprintf(buf, "0 %d 1", gid); write_file("/proc/self/gid_map", buf); + f_mountinfo = fopen("/proc/self/mountinfo", "re"); + if (!f_mountinfo) + ksft_exit_fail_msg("failed to open mountinfo: %s\n", + strerror(errno)); + ret = mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL); if (ret == -1) ksft_exit_fail_msg("making mount tree private: %s\n", @@ -216,25 +207,13 @@ static int setup_mount_tree(int log2_num) return 0; } -static ssize_t listmount(uint64_t mnt_id, uint64_t last_mnt_id, - uint64_t list[], size_t num, unsigned int flags) -{ - struct mnt_id_req req = { - .size = MNT_ID_REQ_SIZE_VER0, - .mnt_id = mnt_id, - .param = last_mnt_id, - }; - - return syscall(__NR_listmount, &req, list, num, flags); -} - static void test_listmount_empty_root(void) { ssize_t res; const unsigned int size = 32; uint64_t list[size]; - res = listmount(LSMT_ROOT, 0, list, size, 0); + res = listmount(LSMT_ROOT, 0, 0, list, size, 0); if (res == -1) { ksft_test_result_fail("listmount: %s\n", strerror(errno)); return; @@ -259,7 +238,7 @@ static void test_statmount_zero_mask(void) struct statmount sm; int ret; - ret = statmount(root_id, 0, &sm, sizeof(sm), 0); + ret = statmount(root_id, 0, 0, &sm, sizeof(sm), 0); if (ret == -1) { ksft_test_result_fail("statmount zero mask: %s\n", strerror(errno)); @@ -285,7 +264,7 @@ static void test_statmount_mnt_basic(void) int ret; uint64_t mask = STATMOUNT_MNT_BASIC; - ret = statmount(root_id, mask, &sm, sizeof(sm), 0); + ret = statmount(root_id, 0, mask, &sm, sizeof(sm), 0); if (ret == -1) { ksft_test_result_fail("statmount mnt basic: %s\n", strerror(errno)); @@ -345,7 +324,7 @@ static void test_statmount_sb_basic(void) struct statx sx; struct statfs sf; - ret = statmount(root_id, mask, &sm, sizeof(sm), 0); + ret = statmount(root_id, 0, mask, &sm, sizeof(sm), 0); if (ret == -1) { ksft_test_result_fail("statmount sb basic: %s\n", strerror(errno)); @@ -470,6 +449,88 @@ static void test_statmount_fs_type(void) free(sm); } +static void test_statmount_mnt_opts(void) +{ + struct statmount *sm; + const char *statmount_opts; + char *line = NULL; + size_t len = 0; + + sm = statmount_alloc(root_id, STATMOUNT_MNT_BASIC | STATMOUNT_MNT_OPTS, + 0); + if (!sm) { + ksft_test_result_fail("statmount mnt opts: %s\n", + strerror(errno)); + return; + } + + while (getline(&line, &len, f_mountinfo) != -1) { + int i; + char *p, *p2; + unsigned int old_mnt_id; + + old_mnt_id = atoi(line); + if (old_mnt_id != sm->mnt_id_old) + continue; + + for (p = line, i = 0; p && i < 5; i++) + p = strchr(p + 1, ' '); + if (!p) + continue; + + p2 = strchr(p + 1, ' '); + if (!p2) + continue; + *p2 = '\0'; + p = strchr(p2 + 1, '-'); + if (!p) + continue; + for (p++, i = 0; p && i < 2; i++) + p = strchr(p + 1, ' '); + if (!p) + continue; + p++; + + /* skip generic superblock options */ + if (strncmp(p, "ro", 2) == 0) + p += 2; + else if (strncmp(p, "rw", 2) == 0) + p += 2; + if (*p == ',') + p++; + if (strncmp(p, "sync", 4) == 0) + p += 4; + if (*p == ',') + p++; + if (strncmp(p, "dirsync", 7) == 0) + p += 7; + if (*p == ',') + p++; + if (strncmp(p, "lazytime", 8) == 0) + p += 8; + if (*p == ',') + p++; + p2 = strrchr(p, '\n'); + if (p2) + *p2 = '\0'; + + statmount_opts = sm->str + sm->mnt_opts; + if (strcmp(statmount_opts, p) != 0) + ksft_test_result_fail( + "unexpected mount options: '%s' != '%s'\n", + statmount_opts, p); + else + ksft_test_result_pass("statmount mount options\n"); + free(sm); + free(line); + return; + } + + ksft_test_result_fail("didnt't find mount entry\n"); + free(sm); + free(line); +} + static void test_statmount_string(uint64_t mask, size_t off, const char *name) { struct statmount *sm; @@ -506,14 +567,14 @@ static void test_statmount_string(uint64_t mask, size_t off, const char *name) exactsize = sm->size; shortsize = sizeof(*sm) + i; - ret = statmount(root_id, mask, sm, exactsize, 0); + ret = statmount(root_id, 0, mask, sm, exactsize, 0); if (ret == -1) { ksft_test_result_fail("statmount exact size: %s\n", strerror(errno)); goto out; } errno = 0; - ret = statmount(root_id, mask, sm, shortsize, 0); + ret = statmount(root_id, 0, mask, sm, shortsize, 0); if (ret != -1 || errno != EOVERFLOW) { ksft_test_result_fail("should have failed with EOVERFLOW: %s\n", strerror(errno)); @@ -541,7 +602,7 @@ static void test_listmount_tree(void) if (res == -1) return; - num = res = listmount(LSMT_ROOT, 0, list, size, 0); + num = res = listmount(LSMT_ROOT, 0, 0, list, size, 0); if (res == -1) { ksft_test_result_fail("listmount: %s\n", strerror(errno)); return; @@ -553,7 +614,7 @@ static void test_listmount_tree(void) } for (i = 0; i < size - step;) { - res = listmount(LSMT_ROOT, i ? list2[i - 1] : 0, list2 + i, step, 0); + res = listmount(LSMT_ROOT, 0, i ? list2[i - 1] : 0, list2 + i, step, 0); if (res == -1) ksft_test_result_fail("short listmount: %s\n", strerror(errno)); @@ -585,18 +646,18 @@ int main(void) int ret; uint64_t all_mask = STATMOUNT_SB_BASIC | STATMOUNT_MNT_BASIC | STATMOUNT_PROPAGATE_FROM | STATMOUNT_MNT_ROOT | - STATMOUNT_MNT_POINT | STATMOUNT_FS_TYPE; + STATMOUNT_MNT_POINT | STATMOUNT_FS_TYPE | STATMOUNT_MNT_NS_ID; ksft_print_header(); - ret = statmount(0, 0, NULL, 0, 0); + ret = statmount(0, 0, 0, NULL, 0, 0); assert(ret == -1); if (errno == ENOSYS) ksft_exit_skip("statmount() syscall not supported\n"); setup_namespace(); - ksft_set_plan(14); + ksft_set_plan(15); test_listmount_empty_root(); test_statmount_zero_mask(); test_statmount_mnt_basic(); @@ -604,6 +665,7 @@ int main(void) test_statmount_mnt_root(); test_statmount_mnt_point(); test_statmount_fs_type(); + test_statmount_mnt_opts(); test_statmount_string(STATMOUNT_MNT_ROOT, str_off(mnt_root), "mount root"); test_statmount_string(STATMOUNT_MNT_POINT, str_off(mnt_point), "mount point"); test_statmount_string(STATMOUNT_FS_TYPE, str_off(fs_type), "fs type"); diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c new file mode 100644 index 000000000000..e044f5fc57fd --- /dev/null +++ b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c @@ -0,0 +1,364 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE + +#include <assert.h> +#include <fcntl.h> +#include <limits.h> +#include <sched.h> +#include <stdlib.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/wait.h> +#include <linux/nsfs.h> +#include <linux/stat.h> + +#include "statmount.h" +#include "../../kselftest.h" + +#define NSID_PASS 0 +#define NSID_FAIL 1 +#define NSID_SKIP 2 +#define NSID_ERROR 3 + +static void handle_result(int ret, const char *testname) +{ + if (ret == NSID_PASS) + ksft_test_result_pass("%s\n", testname); + else if (ret == NSID_FAIL) + ksft_test_result_fail("%s\n", testname); + else if (ret == NSID_ERROR) + ksft_exit_fail_msg("%s\n", testname); + else + ksft_test_result_skip("%s\n", testname); +} + +static inline int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + ksft_print_msg("waitpid returned -1, errno=%d\n", errno); + return -1; + } + + if (!WIFEXITED(status)) { + ksft_print_msg( + "waitpid !WIFEXITED, WIFSIGNALED=%d, WTERMSIG=%d\n", + WIFSIGNALED(status), WTERMSIG(status)); + return -1; + } + + ret = WEXITSTATUS(status); + return ret; +} + +static int get_mnt_ns_id(const char *mnt_ns, uint64_t *mnt_ns_id) +{ + int fd = open(mnt_ns, O_RDONLY); + + if (fd < 0) { + ksft_print_msg("failed to open for ns %s: %s\n", + mnt_ns, strerror(errno)); + sleep(60); + return NSID_ERROR; + } + + if (ioctl(fd, NS_GET_MNTNS_ID, mnt_ns_id) < 0) { + ksft_print_msg("failed to get the nsid for ns %s: %s\n", + mnt_ns, strerror(errno)); + return NSID_ERROR; + } + close(fd); + return NSID_PASS; +} + +static int get_mnt_id(const char *path, uint64_t *mnt_id) +{ + struct statx sx; + int ret; + + ret = statx(AT_FDCWD, path, 0, STATX_MNT_ID_UNIQUE, &sx); + if (ret == -1) { + ksft_print_msg("retrieving unique mount ID for %s: %s\n", path, + strerror(errno)); + return NSID_ERROR; + } + + if (!(sx.stx_mask & STATX_MNT_ID_UNIQUE)) { + ksft_print_msg("no unique mount ID available for %s\n", path); + return NSID_ERROR; + } + + *mnt_id = sx.stx_mnt_id; + return NSID_PASS; +} + +static int write_file(const char *path, const char *val) +{ + int fd = open(path, O_WRONLY); + size_t len = strlen(val); + int ret; + + if (fd == -1) { + ksft_print_msg("opening %s for write: %s\n", path, strerror(errno)); + return NSID_ERROR; + } + + ret = write(fd, val, len); + if (ret == -1) { + ksft_print_msg("writing to %s: %s\n", path, strerror(errno)); + return NSID_ERROR; + } + if (ret != len) { + ksft_print_msg("short write to %s\n", path); + return NSID_ERROR; + } + + ret = close(fd); + if (ret == -1) { + ksft_print_msg("closing %s\n", path); + return NSID_ERROR; + } + + return NSID_PASS; +} + +static int setup_namespace(void) +{ + int ret; + char buf[32]; + uid_t uid = getuid(); + gid_t gid = getgid(); + + ret = unshare(CLONE_NEWNS|CLONE_NEWUSER|CLONE_NEWPID); + if (ret == -1) + ksft_exit_fail_msg("unsharing mountns and userns: %s\n", + strerror(errno)); + + sprintf(buf, "0 %d 1", uid); + ret = write_file("/proc/self/uid_map", buf); + if (ret != NSID_PASS) + return ret; + ret = write_file("/proc/self/setgroups", "deny"); + if (ret != NSID_PASS) + return ret; + sprintf(buf, "0 %d 1", gid); + ret = write_file("/proc/self/gid_map", buf); + if (ret != NSID_PASS) + return ret; + + ret = mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL); + if (ret == -1) { + ksft_print_msg("making mount tree private: %s\n", + strerror(errno)); + return NSID_ERROR; + } + + return NSID_PASS; +} + +static int _test_statmount_mnt_ns_id(void) +{ + struct statmount sm; + uint64_t mnt_ns_id; + uint64_t root_id; + int ret; + + ret = get_mnt_ns_id("/proc/self/ns/mnt", &mnt_ns_id); + if (ret != NSID_PASS) + return ret; + + ret = get_mnt_id("/", &root_id); + if (ret != NSID_PASS) + return ret; + + ret = statmount(root_id, 0, STATMOUNT_MNT_NS_ID, &sm, sizeof(sm), 0); + if (ret == -1) { + ksft_print_msg("statmount mnt ns id: %s\n", strerror(errno)); + return NSID_ERROR; + } + + if (sm.size != sizeof(sm)) { + ksft_print_msg("unexpected size: %u != %u\n", sm.size, + (uint32_t)sizeof(sm)); + return NSID_FAIL; + } + if (sm.mask != STATMOUNT_MNT_NS_ID) { + ksft_print_msg("statmount mnt ns id unavailable\n"); + return NSID_SKIP; + } + + if (sm.mnt_ns_id != mnt_ns_id) { + ksft_print_msg("unexpected mnt ns ID: 0x%llx != 0x%llx\n", + (unsigned long long)sm.mnt_ns_id, + (unsigned long long)mnt_ns_id); + return NSID_FAIL; + } + + return NSID_PASS; +} + +static void test_statmount_mnt_ns_id(void) +{ + pid_t pid; + int ret; + + pid = fork(); + if (pid < 0) + ksft_exit_fail_msg("failed to fork: %s\n", strerror(errno)); + + /* We're the original pid, wait for the result. */ + if (pid != 0) { + ret = wait_for_pid(pid); + handle_result(ret, "test statmount ns id"); + return; + } + + ret = setup_namespace(); + if (ret != NSID_PASS) + exit(ret); + ret = _test_statmount_mnt_ns_id(); + exit(ret); +} + +static int validate_external_listmount(pid_t pid, uint64_t child_nr_mounts) +{ + uint64_t list[256]; + uint64_t mnt_ns_id; + uint64_t nr_mounts; + char buf[256]; + int ret; + + /* Get the mount ns id for our child. */ + snprintf(buf, sizeof(buf), "/proc/%lu/ns/mnt", (unsigned long)pid); + ret = get_mnt_ns_id(buf, &mnt_ns_id); + + nr_mounts = listmount(LSMT_ROOT, mnt_ns_id, 0, list, 256, 0); + if (nr_mounts == (uint64_t)-1) { + ksft_print_msg("listmount: %s\n", strerror(errno)); + return NSID_ERROR; + } + + if (nr_mounts != child_nr_mounts) { + ksft_print_msg("listmount results is %zi != %zi\n", nr_mounts, + child_nr_mounts); + return NSID_FAIL; + } + + /* Validate that all of our entries match our mnt_ns_id. */ + for (int i = 0; i < nr_mounts; i++) { + struct statmount sm; + + ret = statmount(list[i], mnt_ns_id, STATMOUNT_MNT_NS_ID, &sm, + sizeof(sm), 0); + if (ret < 0) { + ksft_print_msg("statmount mnt ns id: %s\n", strerror(errno)); + return NSID_ERROR; + } + + if (sm.mask != STATMOUNT_MNT_NS_ID) { + ksft_print_msg("statmount mnt ns id unavailable\n"); + return NSID_SKIP; + } + + if (sm.mnt_ns_id != mnt_ns_id) { + ksft_print_msg("listmount gave us the wrong ns id: 0x%llx != 0x%llx\n", + (unsigned long long)sm.mnt_ns_id, + (unsigned long long)mnt_ns_id); + return NSID_FAIL; + } + } + + return NSID_PASS; +} + +static void test_listmount_ns(void) +{ + uint64_t nr_mounts; + char pval; + int child_ready_pipe[2]; + int parent_ready_pipe[2]; + pid_t pid; + int ret, child_ret; + + if (pipe(child_ready_pipe) < 0) + ksft_exit_fail_msg("failed to create the child pipe: %s\n", + strerror(errno)); + if (pipe(parent_ready_pipe) < 0) + ksft_exit_fail_msg("failed to create the parent pipe: %s\n", + strerror(errno)); + + pid = fork(); + if (pid < 0) + ksft_exit_fail_msg("failed to fork: %s\n", strerror(errno)); + + if (pid == 0) { + char cval; + uint64_t list[256]; + + close(child_ready_pipe[0]); + close(parent_ready_pipe[1]); + + ret = setup_namespace(); + if (ret != NSID_PASS) + exit(ret); + + nr_mounts = listmount(LSMT_ROOT, 0, 0, list, 256, 0); + if (nr_mounts == (uint64_t)-1) { + ksft_print_msg("listmount: %s\n", strerror(errno)); + exit(NSID_FAIL); + } + + /* + * Tell our parent how many mounts we have, and then wait for it + * to tell us we're done. + */ + write(child_ready_pipe[1], &nr_mounts, sizeof(nr_mounts)); + read(parent_ready_pipe[0], &cval, sizeof(cval)); + exit(NSID_PASS); + } + + close(child_ready_pipe[1]); + close(parent_ready_pipe[0]); + + /* Wait until the child has created everything. */ + if (read(child_ready_pipe[0], &nr_mounts, sizeof(nr_mounts)) != + sizeof(nr_mounts)) + ret = NSID_ERROR; + + ret = validate_external_listmount(pid, nr_mounts); + + if (write(parent_ready_pipe[1], &pval, sizeof(pval)) != sizeof(pval)) + ret = NSID_ERROR; + + child_ret = wait_for_pid(pid); + if (child_ret != NSID_PASS) + ret = child_ret; + handle_result(ret, "test listmount ns id"); +} + +int main(void) +{ + int ret; + + ksft_print_header(); + ret = statmount(0, 0, 0, NULL, 0, 0); + assert(ret == -1); + if (errno == ENOSYS) + ksft_exit_skip("statmount() syscall not supported\n"); + + ksft_set_plan(2); + test_statmount_mnt_ns_id(); + test_listmount_ns(); + + if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0) + ksft_exit_fail(); + else + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 76c2a6945d3e..b8967b6e29d5 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -168,15 +168,7 @@ static inline __printf(1, 2) void ksft_print_msg(const char *msg, ...) static inline void ksft_perror(const char *msg) { -#ifndef NOLIBC ksft_print_msg("%s: %s (%d)\n", msg, strerror(errno), errno); -#else - /* - * nolibc doesn't provide strerror() and it seems - * inappropriate to add one, just print the errno. - */ - ksft_print_msg("%s: %d)\n", msg, errno); -#endif } static inline __printf(1, 2) void ksft_test_result_pass(const char *msg, ...) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index b634969cbb6f..40723a6a083f 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -66,8 +66,6 @@ #include <sys/wait.h> #include <unistd.h> #include <setjmp.h> -#include <syscall.h> -#include <linux/sched.h> #include "kselftest.h" @@ -82,17 +80,6 @@ # define TH_LOG_ENABLED 1 #endif -/* Wait for the child process to end but without sharing memory mapping. */ -static inline pid_t clone3_vfork(void) -{ - struct clone_args args = { - .flags = CLONE_VFORK, - .exit_signal = SIGCHLD, - }; - - return syscall(__NR_clone3, &args, sizeof(args)); -} - /** * TH_LOG() * @@ -437,7 +424,7 @@ static inline pid_t clone3_vfork(void) } \ if (setjmp(_metadata->env) == 0) { \ /* _metadata and potentially self are shared with all forks. */ \ - child = clone3_vfork(); \ + child = fork(); \ if (child == 0) { \ fixture_name##_setup(_metadata, self, variant->data); \ /* Let setup failure terminate early. */ \ @@ -1016,7 +1003,14 @@ void __wait_for_test(struct __test_metadata *t) .sa_flags = SA_SIGINFO, }; struct sigaction saved_action; - int status; + /* + * Sets status so that WIFEXITED(status) returns true and + * WEXITSTATUS(status) returns KSFT_FAIL. This safe default value + * should never be evaluated because of the waitpid(2) check and + * SIGALRM handling. + */ + int status = KSFT_FAIL << 8; + int child; if (sigaction(SIGALRM, &action, &saved_action)) { t->exit_code = KSFT_FAIL; @@ -1028,7 +1022,15 @@ void __wait_for_test(struct __test_metadata *t) __active_test = t; t->timed_out = false; alarm(t->timeout); - waitpid(t->pid, &status, 0); + child = waitpid(t->pid, &status, 0); + if (child == -1 && errno != EINTR) { + t->exit_code = KSFT_FAIL; + fprintf(TH_LOG_STREAM, + "# %s: Failed to wait for PID %d (errno: %d)\n", + t->name, t->pid, errno); + return; + } + alarm(0); if (sigaction(SIGALRM, &saved_action, NULL)) { t->exit_code = KSFT_FAIL; @@ -1083,6 +1085,7 @@ void __wait_for_test(struct __test_metadata *t) WTERMSIG(status)); } } else { + t->exit_code = KSFT_FAIL; fprintf(TH_LOG_STREAM, "# %s: Test ended in some other way [%u]\n", t->name, @@ -1218,6 +1221,7 @@ void __run_test(struct __fixture_metadata *f, struct __test_xfail *xfail; char test_name[1024]; const char *diagnostic; + int child; /* reset test struct */ t->exit_code = KSFT_PASS; @@ -1236,15 +1240,16 @@ void __run_test(struct __fixture_metadata *f, fflush(stdout); fflush(stderr); - t->pid = clone3_vfork(); - if (t->pid < 0) { + child = fork(); + if (child < 0) { ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->exit_code = KSFT_FAIL; - } else if (t->pid == 0) { + } else if (child == 0) { setpgrp(); t->fn(t, variant); _exit(t->exit_code); } else { + t->pid = child; __wait_for_test(t); } ksft_print_msg(" %4s %s\n", diff --git a/tools/testing/selftests/net/af_unix/scm_rights.c b/tools/testing/selftests/net/af_unix/scm_rights.c index 2bfed46e0b19..d66336256580 100644 --- a/tools/testing/selftests/net/af_unix/scm_rights.c +++ b/tools/testing/selftests/net/af_unix/scm_rights.c @@ -14,12 +14,12 @@ FIXTURE(scm_rights) { - int fd[16]; + int fd[32]; }; FIXTURE_VARIANT(scm_rights) { - char name[16]; + char name[32]; int type; int flags; bool test_listener; @@ -172,6 +172,8 @@ static void __create_sockets(struct __test_metadata *_metadata, const FIXTURE_VARIANT(scm_rights) *variant, int n) { + ASSERT_LE(n * 2, sizeof(self->fd) / sizeof(self->fd[0])); + if (variant->test_listener) create_listeners(_metadata, self, n); else @@ -283,4 +285,23 @@ TEST_F(scm_rights, cross_edge) close_sockets(8); } +TEST_F(scm_rights, backtrack_from_scc) +{ + create_sockets(10); + + send_fd(0, 1); + send_fd(0, 4); + send_fd(1, 2); + send_fd(2, 3); + send_fd(3, 1); + + send_fd(5, 6); + send_fd(5, 9); + send_fd(6, 7); + send_fd(7, 8); + send_fd(8, 6); + + close_sockets(10); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index bdc03a2097e8..7ea5fb28c93d 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -85,6 +85,7 @@ static bool cfg_rx; static int cfg_runtime_ms = 4200; static int cfg_verbose; static int cfg_waittime_ms = 500; +static int cfg_notification_limit = 32; static bool cfg_zerocopy; static socklen_t cfg_alen; @@ -95,6 +96,7 @@ static char payload[IP_MAXPACKET]; static long packets, bytes, completions, expected_completions; static int zerocopied = -1; static uint32_t next_completion; +static uint32_t sends_since_notify; static unsigned long gettimeofday_ms(void) { @@ -208,6 +210,7 @@ static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy, int domain) error(1, errno, "send"); if (cfg_verbose && ret != len) fprintf(stderr, "send: ret=%u != %u\n", ret, len); + sends_since_notify++; if (len) { packets++; @@ -435,7 +438,7 @@ static bool do_recv_completion(int fd, int domain) /* Detect notification gaps. These should not happen often, if at all. * Gaps can occur due to drops, reordering and retransmissions. */ - if (lo != next_completion) + if (cfg_verbose && lo != next_completion) fprintf(stderr, "gap: %u..%u does not append to %u\n", lo, hi, next_completion); next_completion = hi + 1; @@ -460,6 +463,7 @@ static bool do_recv_completion(int fd, int domain) static void do_recv_completions(int fd, int domain) { while (do_recv_completion(fd, domain)) {} + sends_since_notify = 0; } /* Wait for all remaining completions on the errqueue */ @@ -549,6 +553,9 @@ static void do_tx(int domain, int type, int protocol) else do_sendmsg(fd, &msg, cfg_zerocopy, domain); + if (cfg_zerocopy && sends_since_notify >= cfg_notification_limit) + do_recv_completions(fd, domain); + while (!do_poll(fd, POLLOUT)) { if (cfg_zerocopy) do_recv_completions(fd, domain); @@ -708,7 +715,7 @@ static void parse_opts(int argc, char **argv) cfg_payload_len = max_payload_len; - while ((c = getopt(argc, argv, "46c:C:D:i:mp:rs:S:t:vz")) != -1) { + while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vz")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -736,6 +743,9 @@ static void parse_opts(int argc, char **argv) if (cfg_ifindex == 0) error(1, errno, "invalid iface: %s", optarg); break; + case 'l': + cfg_notification_limit = strtoul(optarg, NULL, 0); + break; case 'm': cfg_cork_mixed = true; break; diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 40dd95228051..3fbabab46958 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -152,7 +152,7 @@ CFLAGS_mips32be = -EB -mabi=32 CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wextra \ $(call cc-option,-fno-stack-protector) \ - $(CFLAGS_$(XARCH)) $(CFLAGS_STACKPROTECTOR) + $(CFLAGS_$(XARCH)) $(CFLAGS_STACKPROTECTOR) $(CFLAGS_EXTRA) LDFLAGS := REPORT ?= awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{if (!f) printf("\n"); f++; print;} /\[SKIPPED\][\r]*$$/{s++} \ diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 94bb6e11c16f..093d0512f4c5 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -64,6 +64,14 @@ static const char *argv0; /* will be used by constructor tests */ static int constructor_test_value; +static const int is_nolibc = +#ifdef NOLIBC + 1 +#else + 0 +#endif +; + /* definition of a series of tests */ struct test { const char *name; /* test name */ @@ -607,7 +615,7 @@ int expect_strne(const char *expr, int llen, const char *cmp) static __attribute__((unused)) int expect_str_buf_eq(size_t expr, const char *buf, size_t val, int llen, const char *cmp) { - llen += printf(" = %lu <%s> ", expr, buf); + llen += printf(" = %lu <%s> ", (unsigned long)expr, buf); if (strcmp(buf, cmp) != 0) { result(llen, FAIL); return 1; @@ -621,6 +629,51 @@ int expect_str_buf_eq(size_t expr, const char *buf, size_t val, int llen, const return 0; } +#define EXPECT_STRTOX(cond, func, input, base, expected, chars, expected_errno) \ + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_strtox(llen, func, input, base, expected, chars, expected_errno); } while (0) + +static __attribute__((unused)) +int expect_strtox(int llen, void *func, const char *input, int base, intmax_t expected, int expected_chars, int expected_errno) +{ + char *endptr; + int actual_errno, actual_chars; + intmax_t r; + + errno = 0; + if (func == strtol) { + r = strtol(input, &endptr, base); + } else if (func == strtoul) { + r = strtoul(input, &endptr, base); + } else { + result(llen, FAIL); + return 1; + } + actual_errno = errno; + actual_chars = endptr - input; + + llen += printf(" %lld = %lld", (long long)expected, (long long)r); + if (r != expected) { + result(llen, FAIL); + return 1; + } + if (expected_chars == -1) { + if (*endptr != '\0') { + result(llen, FAIL); + return 1; + } + } else if (expected_chars != actual_chars) { + result(llen, FAIL); + return 1; + } + if (actual_errno != expected_errno) { + result(llen, FAIL); + return 1; + } + + result(llen, OK); + return 0; +} + /* declare tests based on line numbers. There must be exactly one test per line. */ #define CASE_TEST(name) \ case __LINE__: llen += printf("%d %s", test, #name); @@ -942,6 +995,7 @@ int run_syscall(int min, int max) int ret = 0; void *p1, *p2; int has_gettid = 1; + int has_brk; /* <proc> indicates whether or not /proc is mounted */ proc = stat("/proc", &stat_buf) == 0; @@ -954,6 +1008,9 @@ int run_syscall(int min, int max) has_gettid = __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ >= 30); #endif + /* on musl setting brk()/sbrk() always fails */ + has_brk = brk(0) == 0; + for (test = min; test >= 0 && test <= max; test++) { int llen = 0; /* line length */ @@ -969,9 +1026,9 @@ int run_syscall(int min, int max) CASE_TEST(kill_0); EXPECT_SYSZR(1, kill(getpid(), 0)); break; CASE_TEST(kill_CONT); EXPECT_SYSZR(1, kill(getpid(), 0)); break; CASE_TEST(kill_BADPID); EXPECT_SYSER(1, kill(INT_MAX, 0), -1, ESRCH); break; - CASE_TEST(sbrk_0); EXPECT_PTRNE(1, sbrk(0), (void *)-1); break; - CASE_TEST(sbrk); if ((p1 = p2 = sbrk(4096)) != (void *)-1) p2 = sbrk(-4096); EXPECT_SYSZR(1, (p2 == (void *)-1) || p2 == p1); break; - CASE_TEST(brk); EXPECT_SYSZR(1, brk(sbrk(0))); break; + CASE_TEST(sbrk_0); EXPECT_PTRNE(has_brk, sbrk(0), (void *)-1); break; + CASE_TEST(sbrk); if ((p1 = p2 = sbrk(4096)) != (void *)-1) p2 = sbrk(-4096); EXPECT_SYSZR(has_brk, (p2 == (void *)-1) || p2 == p1); break; + CASE_TEST(brk); EXPECT_SYSZR(has_brk, brk(sbrk(0))); break; CASE_TEST(chdir_root); EXPECT_SYSZR(1, chdir("/")); chdir(getenv("PWD")); break; CASE_TEST(chdir_dot); EXPECT_SYSZR(1, chdir(".")); break; CASE_TEST(chdir_blah); EXPECT_SYSER(1, chdir("/blah"), -1, ENOENT); break; @@ -1076,19 +1133,17 @@ int run_stdlib(int min, int max) CASE_TEST(strchr_foobar_z); EXPECT_STRZR(1, strchr("foobar", 'z')); break; CASE_TEST(strrchr_foobar_o); EXPECT_STREQ(1, strrchr("foobar", 'o'), "obar"); break; CASE_TEST(strrchr_foobar_z); EXPECT_STRZR(1, strrchr("foobar", 'z')); break; -#ifdef NOLIBC - CASE_TEST(strlcat_0); EXPECT_STRBUFEQ(1, strlcat(buf, "bar", 0), buf, 3, "test"); break; - CASE_TEST(strlcat_1); EXPECT_STRBUFEQ(1, strlcat(buf, "bar", 1), buf, 4, "test"); break; - CASE_TEST(strlcat_5); EXPECT_STRBUFEQ(1, strlcat(buf, "bar", 5), buf, 7, "test"); break; - CASE_TEST(strlcat_6); EXPECT_STRBUFEQ(1, strlcat(buf, "bar", 6), buf, 7, "testb"); break; - CASE_TEST(strlcat_7); EXPECT_STRBUFEQ(1, strlcat(buf, "bar", 7), buf, 7, "testba"); break; - CASE_TEST(strlcat_8); EXPECT_STRBUFEQ(1, strlcat(buf, "bar", 8), buf, 7, "testbar"); break; - CASE_TEST(strlcpy_0); EXPECT_STRBUFEQ(1, strlcpy(buf, "bar", 0), buf, 3, "test"); break; - CASE_TEST(strlcpy_1); EXPECT_STRBUFEQ(1, strlcpy(buf, "bar", 1), buf, 3, ""); break; - CASE_TEST(strlcpy_2); EXPECT_STRBUFEQ(1, strlcpy(buf, "bar", 2), buf, 3, "b"); break; - CASE_TEST(strlcpy_3); EXPECT_STRBUFEQ(1, strlcpy(buf, "bar", 3), buf, 3, "ba"); break; - CASE_TEST(strlcpy_4); EXPECT_STRBUFEQ(1, strlcpy(buf, "bar", 4), buf, 3, "bar"); break; -#endif + CASE_TEST(strlcat_0); EXPECT_STRBUFEQ(is_nolibc, strlcat(buf, "bar", 0), buf, 3, "test"); break; + CASE_TEST(strlcat_1); EXPECT_STRBUFEQ(is_nolibc, strlcat(buf, "bar", 1), buf, 4, "test"); break; + CASE_TEST(strlcat_5); EXPECT_STRBUFEQ(is_nolibc, strlcat(buf, "bar", 5), buf, 7, "test"); break; + CASE_TEST(strlcat_6); EXPECT_STRBUFEQ(is_nolibc, strlcat(buf, "bar", 6), buf, 7, "testb"); break; + CASE_TEST(strlcat_7); EXPECT_STRBUFEQ(is_nolibc, strlcat(buf, "bar", 7), buf, 7, "testba"); break; + CASE_TEST(strlcat_8); EXPECT_STRBUFEQ(is_nolibc, strlcat(buf, "bar", 8), buf, 7, "testbar"); break; + CASE_TEST(strlcpy_0); EXPECT_STRBUFEQ(is_nolibc, strlcpy(buf, "bar", 0), buf, 3, "test"); break; + CASE_TEST(strlcpy_1); EXPECT_STRBUFEQ(is_nolibc, strlcpy(buf, "bar", 1), buf, 3, ""); break; + CASE_TEST(strlcpy_2); EXPECT_STRBUFEQ(is_nolibc, strlcpy(buf, "bar", 2), buf, 3, "b"); break; + CASE_TEST(strlcpy_3); EXPECT_STRBUFEQ(is_nolibc, strlcpy(buf, "bar", 3), buf, 3, "ba"); break; + CASE_TEST(strlcpy_4); EXPECT_STRBUFEQ(is_nolibc, strlcpy(buf, "bar", 4), buf, 3, "bar"); break; CASE_TEST(memcmp_20_20); EXPECT_EQ(1, memcmp("aaa\x20", "aaa\x20", 4), 0); break; CASE_TEST(memcmp_20_60); EXPECT_LT(1, memcmp("aaa\x20", "aaa\x60", 4), 0); break; CASE_TEST(memcmp_60_20); EXPECT_GT(1, memcmp("aaa\x60", "aaa\x20", 4), 0); break; @@ -1139,6 +1194,26 @@ int run_stdlib(int min, int max) CASE_TEST(limit_ptrdiff_min); EXPECT_EQ(1, PTRDIFF_MIN, sizeof(long) == 8 ? (ptrdiff_t) 0x8000000000000000LL : (ptrdiff_t) 0x80000000); break; CASE_TEST(limit_ptrdiff_max); EXPECT_EQ(1, PTRDIFF_MAX, sizeof(long) == 8 ? (ptrdiff_t) 0x7fffffffffffffffLL : (ptrdiff_t) 0x7fffffff); break; CASE_TEST(limit_size_max); EXPECT_EQ(1, SIZE_MAX, sizeof(long) == 8 ? (size_t) 0xffffffffffffffffULL : (size_t) 0xffffffffU); break; + CASE_TEST(strtol_simple); EXPECT_STRTOX(1, strtol, "35", 10, 35, -1, 0); break; + CASE_TEST(strtol_positive); EXPECT_STRTOX(1, strtol, "+35", 10, 35, -1, 0); break; + CASE_TEST(strtol_negative); EXPECT_STRTOX(1, strtol, "-35", 10, -35, -1, 0); break; + CASE_TEST(strtol_hex_auto); EXPECT_STRTOX(1, strtol, "0xFF", 0, 255, -1, 0); break; + CASE_TEST(strtol_base36); EXPECT_STRTOX(1, strtol, "12yZ", 36, 50507, -1, 0); break; + CASE_TEST(strtol_cutoff); EXPECT_STRTOX(1, strtol, "1234567890", 8, 342391, 7, 0); break; + CASE_TEST(strtol_octal_auto); EXPECT_STRTOX(1, strtol, "011", 0, 9, -1, 0); break; + CASE_TEST(strtol_hex_00); EXPECT_STRTOX(1, strtol, "0x00", 16, 0, -1, 0); break; + CASE_TEST(strtol_hex_FF); EXPECT_STRTOX(1, strtol, "FF", 16, 255, -1, 0); break; + CASE_TEST(strtol_hex_ff); EXPECT_STRTOX(1, strtol, "ff", 16, 255, -1, 0); break; + CASE_TEST(strtol_hex_prefix); EXPECT_STRTOX(1, strtol, "0xFF", 16, 255, -1, 0); break; + CASE_TEST(strtol_trailer); EXPECT_STRTOX(1, strtol, "35foo", 10, 35, 2, 0); break; + CASE_TEST(strtol_overflow); EXPECT_STRTOX(1, strtol, "0x8000000000000000", 16, LONG_MAX, -1, ERANGE); break; + CASE_TEST(strtol_underflow); EXPECT_STRTOX(1, strtol, "-0x8000000000000001", 16, LONG_MIN, -1, ERANGE); break; + CASE_TEST(strtoul_negative); EXPECT_STRTOX(1, strtoul, "-0x1", 16, ULONG_MAX, 4, 0); break; + CASE_TEST(strtoul_overflow); EXPECT_STRTOX(1, strtoul, "0x10000000000000000", 16, ULONG_MAX, -1, ERANGE); break; + CASE_TEST(strerror_success); EXPECT_STREQ(is_nolibc, strerror(0), "errno=0"); break; + CASE_TEST(strerror_EINVAL); EXPECT_STREQ(is_nolibc, strerror(EINVAL), "errno=22"); break; + CASE_TEST(strerror_int_max); EXPECT_STREQ(is_nolibc, strerror(INT_MAX), "errno=2147483647"); break; + CASE_TEST(strerror_int_min); EXPECT_STREQ(is_nolibc, strerror(INT_MIN), "errno=-2147483648"); break; case __LINE__: return ret; /* must be last */ diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh index c0a5a7cea9fa..0446e6326a40 100755 --- a/tools/testing/selftests/nolibc/run-tests.sh +++ b/tools/testing/selftests/nolibc/run-tests.sh @@ -15,9 +15,10 @@ download_location="${cache_dir}/crosstools/" build_location="$(realpath "${cache_dir}"/nolibc-tests/)" perform_download=0 test_mode=system +CFLAGS_EXTRA="-Werror" archs="i386 x86_64 arm64 arm mips32le mips32be ppc ppc64 ppc64le riscv s390 loongarch" -TEMP=$(getopt -o 'j:d:c:b:a:m:ph' -n "$0" -- "$@") +TEMP=$(getopt -o 'j:d:c:b:a:m:peh' -n "$0" -- "$@") eval set -- "$TEMP" unset TEMP @@ -40,6 +41,7 @@ Options: -a [ARCH] Host architecture of toolchains to use (default: ${hostarch}) -b [DIR] Build location (default: ${build_location}) -m [MODE] Test mode user/system (default: ${test_mode}) + -e Disable -Werror EOF } @@ -66,6 +68,9 @@ while true; do '-m') test_mode="$2" shift 2; continue ;; + '-e') + CFLAGS_EXTRA="" + shift; continue ;; '-h') print_usage exit 0 @@ -153,7 +158,7 @@ test_arch() { exit 1 esac printf '%-15s' "$arch:" - swallow_output "${MAKE[@]}" "$test_target" V=1 + swallow_output "${MAKE[@]}" CFLAGS_EXTRA="$CFLAGS_EXTRA" "$test_target" V=1 cp run.out run.out."${arch}" "${MAKE[@]}" report | grep passed } diff --git a/tools/testing/selftests/powerpc/flags.mk b/tools/testing/selftests/powerpc/flags.mk index b909bee3cb2a..abb9e58d95c4 100644 --- a/tools/testing/selftests/powerpc/flags.mk +++ b/tools/testing/selftests/powerpc/flags.mk @@ -5,8 +5,5 @@ GIT_VERSION := $(shell git describe --always --long --dirty || echo "unknown") export GIT_VERSION endif -ifeq ($(CFLAGS),) -CFLAGS := -std=gnu99 -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(selfdir)/powerpc/include $(CFLAGS) +CFLAGS := -std=gnu99 -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(selfdir)/powerpc/include $(USERCFLAGS) export CFLAGS -endif - diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index c7686fb6641a..55315ed695f4 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -291,11 +291,30 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param return ret; } +static bool arch_supports_noncont_cat(const struct resctrl_test *test) +{ + unsigned int eax, ebx, ecx, edx; + + /* AMD always supports non-contiguous CBM. */ + if (get_vendor() == ARCH_AMD) + return true; + + /* Intel support for non-contiguous CBM needs to be discovered. */ + if (!strcmp(test->resource, "L3")) + __cpuid_count(0x10, 1, eax, ebx, ecx, edx); + else if (!strcmp(test->resource, "L2")) + __cpuid_count(0x10, 2, eax, ebx, ecx, edx); + else + return false; + + return ((ecx >> 3) & 1); +} + static int noncont_cat_run_test(const struct resctrl_test *test, const struct user_params *uparams) { unsigned long full_cache_mask, cont_mask, noncont_mask; - unsigned int eax, ebx, ecx, edx, sparse_masks; + unsigned int sparse_masks; int bit_center, ret; char schemata[64]; @@ -304,15 +323,8 @@ static int noncont_cat_run_test(const struct resctrl_test *test, if (ret) return ret; - if (!strcmp(test->resource, "L3")) - __cpuid_count(0x10, 1, eax, ebx, ecx, edx); - else if (!strcmp(test->resource, "L2")) - __cpuid_count(0x10, 2, eax, ebx, ecx, edx); - else - return -EINVAL; - - if (sparse_masks != ((ecx >> 3) & 1)) { - ksft_print_msg("CPUID output doesn't match 'sparse_masks' file content!\n"); + if (arch_supports_noncont_cat(test) != sparse_masks) { + ksft_print_msg("Hardware and kernel differ on non-contiguous CBM support!\n"); return 1; } diff --git a/tools/testing/selftests/riscv/sigreturn/sigreturn.c b/tools/testing/selftests/riscv/sigreturn/sigreturn.c index 62397d5934f1..ed351a1cb917 100644 --- a/tools/testing/selftests/riscv/sigreturn/sigreturn.c +++ b/tools/testing/selftests/riscv/sigreturn/sigreturn.c @@ -51,7 +51,7 @@ static int vector_sigreturn(int data, void (*handler)(int, siginfo_t *, void *)) asm(".option push \n\ .option arch, +v \n\ - vsetivli x0, 1, e32, ta, ma \n\ + vsetivli x0, 1, e32, m1, ta, ma \n\ vmv.s.x v0, %1 \n\ # Generate SIGSEGV \n\ lw a0, 0(x0) \n\ diff --git a/tools/testing/selftests/timens/exec.c b/tools/testing/selftests/timens/exec.c index e40dc5be2f66..d12ff955de0d 100644 --- a/tools/testing/selftests/timens/exec.c +++ b/tools/testing/selftests/timens/exec.c @@ -30,7 +30,7 @@ int main(int argc, char *argv[]) for (i = 0; i < 2; i++) { _gettime(CLOCK_MONOTONIC, &tst, i); - if (abs(tst.tv_sec - now.tv_sec) > 5) + if (labs(tst.tv_sec - now.tv_sec) > 5) return pr_fail("%ld %ld\n", now.tv_sec, tst.tv_sec); } return 0; @@ -50,7 +50,7 @@ int main(int argc, char *argv[]) for (i = 0; i < 2; i++) { _gettime(CLOCK_MONOTONIC, &tst, i); - if (abs(tst.tv_sec - now.tv_sec) > 5) + if (labs(tst.tv_sec - now.tv_sec) > 5) return pr_fail("%ld %ld\n", now.tv_sec, tst.tv_sec); } @@ -70,7 +70,7 @@ int main(int argc, char *argv[]) /* Check that a child process is in the new timens. */ for (i = 0; i < 2; i++) { _gettime(CLOCK_MONOTONIC, &tst, i); - if (abs(tst.tv_sec - now.tv_sec - OFFSET) > 5) + if (labs(tst.tv_sec - now.tv_sec - OFFSET) > 5) return pr_fail("%ld %ld\n", now.tv_sec + OFFSET, tst.tv_sec); } diff --git a/tools/testing/selftests/timens/timer.c b/tools/testing/selftests/timens/timer.c index 5e7f0051bd7b..5b939f59dfa4 100644 --- a/tools/testing/selftests/timens/timer.c +++ b/tools/testing/selftests/timens/timer.c @@ -56,7 +56,7 @@ int run_test(int clockid, struct timespec now) return pr_perror("timerfd_gettime"); elapsed = new_value.it_value.tv_sec; - if (abs(elapsed - 3600) > 60) { + if (llabs(elapsed - 3600) > 60) { ksft_test_result_fail("clockid: %d elapsed: %lld\n", clockid, elapsed); return 1; diff --git a/tools/testing/selftests/timens/timerfd.c b/tools/testing/selftests/timens/timerfd.c index 9edd43d6b2c1..a4196bbd6e33 100644 --- a/tools/testing/selftests/timens/timerfd.c +++ b/tools/testing/selftests/timens/timerfd.c @@ -61,7 +61,7 @@ int run_test(int clockid, struct timespec now) return pr_perror("timerfd_gettime(%d)", clockid); elapsed = new_value.it_value.tv_sec; - if (abs(elapsed - 3600) > 60) { + if (llabs(elapsed - 3600) > 60) { ksft_test_result_fail("clockid: %d elapsed: %lld\n", clockid, elapsed); return 1; diff --git a/tools/testing/selftests/timens/vfork_exec.c b/tools/testing/selftests/timens/vfork_exec.c index beb7614941fb..5b8907bf451d 100644 --- a/tools/testing/selftests/timens/vfork_exec.c +++ b/tools/testing/selftests/timens/vfork_exec.c @@ -32,7 +32,7 @@ static void *tcheck(void *_args) for (i = 0; i < 2; i++) { _gettime(CLOCK_MONOTONIC, &tst, i); - if (abs(tst.tv_sec - now->tv_sec) > 5) { + if (labs(tst.tv_sec - now->tv_sec) > 5) { pr_fail("%s: in-thread: unexpected value: %ld (%ld)\n", args->tst_name, tst.tv_sec, now->tv_sec); return (void *)1UL; @@ -64,7 +64,7 @@ static int check(char *tst_name, struct timespec *now) for (i = 0; i < 2; i++) { _gettime(CLOCK_MONOTONIC, &tst, i); - if (abs(tst.tv_sec - now->tv_sec) > 5) + if (labs(tst.tv_sec - now->tv_sec) > 5) return pr_fail("%s: unexpected value: %ld (%ld)\n", tst_name, tst.tv_sec, now->tv_sec); } diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index d53a4d8008f9..98d8ba2afa00 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -1,35 +1,30 @@ # SPDX-License-Identifier: GPL-2.0 -include ../lib.mk - 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/) -TEST_GEN_PROGS := $(OUTPUT)/vdso_test_gettimeofday $(OUTPUT)/vdso_test_getcpu -TEST_GEN_PROGS += $(OUTPUT)/vdso_test_abi -TEST_GEN_PROGS += $(OUTPUT)/vdso_test_clock_getres +TEST_GEN_PROGS := vdso_test_gettimeofday +TEST_GEN_PROGS += vdso_test_getcpu +TEST_GEN_PROGS += vdso_test_abi +TEST_GEN_PROGS += vdso_test_clock_getres ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64)) -TEST_GEN_PROGS += $(OUTPUT)/vdso_standalone_test_x86 +TEST_GEN_PROGS += vdso_standalone_test_x86 endif -TEST_GEN_PROGS += $(OUTPUT)/vdso_test_correctness +TEST_GEN_PROGS += vdso_test_correctness CFLAGS := -std=gnu99 -CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector -LDFLAGS_vdso_test_correctness := -ldl + ifeq ($(CONFIG_X86_32),y) LDLIBS += -lgcc_s endif -all: $(TEST_GEN_PROGS) +include ../lib.mk $(OUTPUT)/vdso_test_gettimeofday: parse_vdso.c vdso_test_gettimeofday.c $(OUTPUT)/vdso_test_getcpu: parse_vdso.c vdso_test_getcpu.c $(OUTPUT)/vdso_test_abi: parse_vdso.c vdso_test_abi.c $(OUTPUT)/vdso_test_clock_getres: vdso_test_clock_getres.c + $(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c - $(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \ - vdso_standalone_test_x86.c parse_vdso.c \ - -o $@ +$(OUTPUT)/vdso_standalone_test_x86: CFLAGS +=-nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector + $(OUTPUT)/vdso_test_correctness: vdso_test_correctness.c - $(CC) $(CFLAGS) \ - vdso_test_correctness.c \ - -o $@ \ - $(LDFLAGS_vdso_test_correctness) +$(OUTPUT)/vdso_test_correctness: LDFLAGS += -ldl diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c index 413f75620a35..4ae417372e9e 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.c +++ b/tools/testing/selftests/vDSO/parse_vdso.c @@ -55,14 +55,20 @@ static struct vdso_info ELF(Verdef) *verdef; } vdso_info; -/* Straight from the ELF specification. */ -static unsigned long elf_hash(const unsigned char *name) +/* + * Straight from the ELF specification...and then tweaked slightly, in order to + * avoid a few clang warnings. + */ +static unsigned long elf_hash(const char *name) { unsigned long h = 0, g; - while (*name) + const unsigned char *uch_name = (const unsigned char *)name; + + while (*uch_name) { - h = (h << 4) + *name++; - if (g = h & 0xf0000000) + h = (h << 4) + *uch_name++; + g = h & 0xf0000000; + if (g) h ^= g >> 24; h &= ~g; } diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c index 8a44ff973ee1..27f6fdf11969 100644 --- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c +++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c @@ -18,7 +18,7 @@ #include "parse_vdso.h" -/* We need a libc functions... */ +/* We need some libc functions... */ int strcmp(const char *a, const char *b) { /* This implementation is buggy: it never returns -1. */ @@ -34,6 +34,20 @@ int strcmp(const char *a, const char *b) return 0; } +/* + * The clang build needs this, although gcc does not. + * Stolen from lib/string.c. + */ +void *memcpy(void *dest, const void *src, size_t count) +{ + char *tmp = dest; + const char *s = src; + + while (count--) + *tmp++ = *s++; + return dest; +} + /* ...and two syscalls. This is x86-specific. */ static inline long x86_syscall3(long nr, long a0, long a1, long a2) { @@ -70,7 +84,7 @@ void to_base10(char *lastdig, time_t n) } } -__attribute__((externally_visible)) void c_main(void **stack) +void c_main(void **stack) { /* Parse the stack */ long argc = (long)*stack; diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index e95bd56b332f..35856b11c143 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -109,9 +109,9 @@ KERNEL_ARCH := x86_64 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) -QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off -no-acpi +QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off,acpi=off else -QEMU_MACHINE := -cpu max -machine microvm -no-acpi +QEMU_MACHINE := -cpu max -machine microvm,acpi=off endif else ifeq ($(ARCH),i686) CHOST := i686-linux-musl @@ -120,9 +120,9 @@ KERNEL_ARCH := x86 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH)) -QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off -no-acpi +QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off,acpi=off else -QEMU_MACHINE := -cpu coreduo -machine microvm -no-acpi +QEMU_MACHINE := -cpu coreduo -machine microvm,acpi=off endif else ifeq ($(ARCH),mips64) CHOST := mips64-linux-musl |