From 3eb39f47934f9d5a3027fe00d906a45fe3a15fad Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 19 Nov 2018 00:51:56 +0100 Subject: signal: add pidfd_send_signal() syscall The kill() syscall operates on process identifiers (pid). After a process has exited its pid can be reused by another process. If a caller sends a signal to a reused pid it will end up signaling the wrong process. This issue has often surfaced and there has been a push to address this problem [1]. This patch uses file descriptors (fd) from proc/ as stable handles on struct pid. Even if a pid is recycled the handle will not change. The fd can be used to send signals to the process it refers to. Thus, the new syscall pidfd_send_signal() is introduced to solve this problem. Instead of pids it operates on process fds (pidfd). /* prototype and argument /* long pidfd_send_signal(int pidfd, int sig, siginfo_t *info, unsigned int flags); /* syscall number 424 */ The syscall number was chosen to be 424 to align with Arnd's rework in his y2038 to minimize merge conflicts (cf. [25]). In addition to the pidfd and signal argument it takes an additional siginfo_t and flags argument. If the siginfo_t argument is NULL then pidfd_send_signal() is equivalent to kill(, ). If it is not NULL pidfd_send_signal() is equivalent to rt_sigqueueinfo(). The flags argument is added to allow for future extensions of this syscall. It currently needs to be passed as 0. Failing to do so will cause EINVAL. /* pidfd_send_signal() replaces multiple pid-based syscalls */ The pidfd_send_signal() syscall currently takes on the job of rt_sigqueueinfo(2) and parts of the functionality of kill(2), Namely, when a positive pid is passed to kill(2). It will however be possible to also replace tgkill(2) and rt_tgsigqueueinfo(2) if this syscall is extended. /* sending signals to threads (tid) and process groups (pgid) */ Specifically, the pidfd_send_signal() syscall does currently not operate on process groups or threads. This is left for future extensions. In order to extend the syscall to allow sending signal to threads and process groups appropriately named flags (e.g. PIDFD_TYPE_PGID, and PIDFD_TYPE_TID) should be added. This implies that the flags argument will determine what is signaled and not the file descriptor itself. Put in other words, grouping in this api is a property of the flags argument not a property of the file descriptor (cf. [13]). Clarification for this has been requested by Eric (cf. [19]). When appropriate extensions through the flags argument are added then pidfd_send_signal() can additionally replace the part of kill(2) which operates on process groups as well as the tgkill(2) and rt_tgsigqueueinfo(2) syscalls. How such an extension could be implemented has been very roughly sketched in [14], [15], and [16]. However, this should not be taken as a commitment to a particular implementation. There might be better ways to do it. Right now this is intentionally left out to keep this patchset as simple as possible (cf. [4]). /* naming */ The syscall had various names throughout iterations of this patchset: - procfd_signal() - procfd_send_signal() - taskfd_send_signal() In the last round of reviews it was pointed out that given that if the flags argument decides the scope of the signal instead of different types of fds it might make sense to either settle for "procfd_" or "pidfd_" as prefix. The community was willing to accept either (cf. [17] and [18]). Given that one developer expressed strong preference for the "pidfd_" prefix (cf. [13]) and with other developers less opinionated about the name we should settle for "pidfd_" to avoid further bikeshedding. The "_send_signal" suffix was chosen to reflect the fact that the syscall takes on the job of multiple syscalls. It is therefore intentional that the name is not reminiscent of neither kill(2) nor rt_sigqueueinfo(2). Not the fomer because it might imply that pidfd_send_signal() is a replacement for kill(2), and not the latter because it is a hassle to remember the correct spelling - especially for non-native speakers - and because it is not descriptive enough of what the syscall actually does. The name "pidfd_send_signal" makes it very clear that its job is to send signals. /* zombies */ Zombies can be signaled just as any other process. No special error will be reported since a zombie state is an unreliable state (cf. [3]). However, this can be added as an extension through the @flags argument if the need ever arises. /* cross-namespace signals */ The patch currently enforces that the signaler and signalee either are in the same pid namespace or that the signaler's pid namespace is an ancestor of the signalee's pid namespace. This is done for the sake of simplicity and because it is unclear to what values certain members of struct siginfo_t would need to be set to (cf. [5], [6]). /* compat syscalls */ It became clear that we would like to avoid adding compat syscalls (cf. [7]). The compat syscall handling is now done in kernel/signal.c itself by adding __copy_siginfo_from_user_generic() which lets us avoid compat syscalls (cf. [8]). It should be noted that the addition of __copy_siginfo_from_user_any() is caused by a bug in the original implementation of rt_sigqueueinfo(2) (cf. 12). With upcoming rework for syscall handling things might improve significantly (cf. [11]) and __copy_siginfo_from_user_any() will not gain any additional callers. /* testing */ This patch was tested on x64 and x86. /* userspace usage */ An asciinema recording for the basic functionality can be found under [9]. With this patch a process can be killed via: #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include static inline int do_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, unsigned int flags) { #ifdef __NR_pidfd_send_signal return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); #else return -ENOSYS; #endif } int main(int argc, char *argv[]) { int fd, ret, saved_errno, sig; if (argc < 3) exit(EXIT_FAILURE); fd = open(argv[1], O_DIRECTORY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open \"%s\"\n", strerror(errno), argv[1]); exit(EXIT_FAILURE); } sig = atoi(argv[2]); printf("Sending signal %d to process %s\n", sig, argv[1]); ret = do_pidfd_send_signal(fd, sig, NULL, 0); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to send signal %d to process %s\n", strerror(errno), sig, argv[1]); exit(EXIT_FAILURE); } exit(EXIT_SUCCESS); } /* Q&A * Given that it seems the same questions get asked again by people who are * late to the party it makes sense to add a Q&A section to the commit * message so it's hopefully easier to avoid duplicate threads. * * For the sake of progress please consider these arguments settled unless * there is a new point that desperately needs to be addressed. Please make * sure to check the links to the threads in this commit message whether * this has not already been covered. */ Q-01: (Florian Weimer [20], Andrew Morton [21]) What happens when the target process has exited? A-01: Sending the signal will fail with ESRCH (cf. [22]). Q-02: (Andrew Morton [21]) Is the task_struct pinned by the fd? A-02: No. A reference to struct pid is kept. struct pid - as far as I understand - was created exactly for the reason to not require to pin struct task_struct (cf. [22]). Q-03: (Andrew Morton [21]) Does the entire procfs directory remain visible? Just one entry within it? A-03: The same thing that happens right now when you hold a file descriptor to /proc/ open (cf. [22]). Q-04: (Andrew Morton [21]) Does the pid remain reserved? A-04: No. This patchset guarantees a stable handle not that pids are not recycled (cf. [22]). Q-05: (Andrew Morton [21]) Do attempts to signal that fd return errors? A-05: See {Q,A}-01. Q-06: (Andrew Morton [22]) Is there a cleaner way of obtaining the fd? Another syscall perhaps. A-06: Userspace can already trivially retrieve file descriptors from procfs so this is something that we will need to support anyway. Hence, there's no immediate need to add another syscalls just to make pidfd_send_signal() not dependent on the presence of procfs. However, adding a syscalls to get such file descriptors is planned for a future patchset (cf. [22]). Q-07: (Andrew Morton [21] and others) This fd-for-a-process sounds like a handy thing and people may well think up other uses for it in the future, probably unrelated to signals. Are the code and the interface designed to permit such future applications? A-07: Yes (cf. [22]). Q-08: (Andrew Morton [21] and others) Now I think about it, why a new syscall? This thing is looking rather like an ioctl? A-08: This has been extensively discussed. It was agreed that a syscall is preferred for a variety or reasons. Here are just a few taken from prior threads. Syscalls are safer than ioctl()s especially when signaling to fds. Processes are a core kernel concept so a syscall seems more appropriate. The layout of the syscall with its four arguments would require the addition of a custom struct for the ioctl() thereby causing at least the same amount or even more complexity for userspace than a simple syscall. The new syscall will replace multiple other pid-based syscalls (see description above). The file-descriptors-for-processes concept introduced with this syscall will be extended with other syscalls in the future. See also [22], [23] and various other threads already linked in here. Q-09: (Florian Weimer [24]) What happens if you use the new interface with an O_PATH descriptor? A-09: pidfds opened as O_PATH fds cannot be used to send signals to a process (cf. [2]). Signaling processes through pidfds is the equivalent of writing to a file. Thus, this is not an operation that operates "purely at the file descriptor level" as required by the open(2) manpage. See also [4]. /* References */ [1]: https://lore.kernel.org/lkml/20181029221037.87724-1-dancol@google.com/ [2]: https://lore.kernel.org/lkml/874lbtjvtd.fsf@oldenburg2.str.redhat.com/ [3]: https://lore.kernel.org/lkml/20181204132604.aspfupwjgjx6fhva@brauner.io/ [4]: https://lore.kernel.org/lkml/20181203180224.fkvw4kajtbvru2ku@brauner.io/ [5]: https://lore.kernel.org/lkml/20181121213946.GA10795@mail.hallyn.com/ [6]: https://lore.kernel.org/lkml/20181120103111.etlqp7zop34v6nv4@brauner.io/ [7]: https://lore.kernel.org/lkml/36323361-90BD-41AF-AB5B-EE0D7BA02C21@amacapital.net/ [8]: https://lore.kernel.org/lkml/87tvjxp8pc.fsf@xmission.com/ [9]: https://asciinema.org/a/IQjuCHew6bnq1cr78yuMv16cy [11]: https://lore.kernel.org/lkml/F53D6D38-3521-4C20-9034-5AF447DF62FF@amacapital.net/ [12]: https://lore.kernel.org/lkml/87zhtjn8ck.fsf@xmission.com/ [13]: https://lore.kernel.org/lkml/871s6u9z6u.fsf@xmission.com/ [14]: https://lore.kernel.org/lkml/20181206231742.xxi4ghn24z4h2qki@brauner.io/ [15]: https://lore.kernel.org/lkml/20181207003124.GA11160@mail.hallyn.com/ [16]: https://lore.kernel.org/lkml/20181207015423.4miorx43l3qhppfz@brauner.io/ [17]: https://lore.kernel.org/lkml/CAGXu5jL8PciZAXvOvCeCU3wKUEB_dU-O3q0tDw4uB_ojMvDEew@mail.gmail.com/ [18]: https://lore.kernel.org/lkml/20181206222746.GB9224@mail.hallyn.com/ [19]: https://lore.kernel.org/lkml/20181208054059.19813-1-christian@brauner.io/ [20]: https://lore.kernel.org/lkml/8736rebl9s.fsf@oldenburg.str.redhat.com/ [21]: https://lore.kernel.org/lkml/20181228152012.dbf0508c2508138efc5f2bbe@linux-foundation.org/ [22]: https://lore.kernel.org/lkml/20181228233725.722tdfgijxcssg76@brauner.io/ [23]: https://lwn.net/Articles/773459/ [24]: https://lore.kernel.org/lkml/8736rebl9s.fsf@oldenburg.str.redhat.com/ [25]: https://lore.kernel.org/lkml/CAK8P3a0ej9NcJM8wXNPbcGUyOUZYX+VLoDFdbenW3s3114oQZw@mail.gmail.com/ Cc: "Eric W. Biederman" Cc: Jann Horn Cc: Andy Lutomirsky Cc: Andrew Morton Cc: Oleg Nesterov Cc: Al Viro Cc: Florian Weimer Signed-off-by: Christian Brauner Reviewed-by: Tycho Andersen Reviewed-by: Kees Cook Reviewed-by: David Howells Acked-by: Arnd Bergmann Acked-by: Thomas Gleixner Acked-by: Serge Hallyn Acked-by: Aleksa Sarai --- arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + fs/proc/base.c | 9 +++ include/linux/proc_fs.h | 6 ++ include/linux/syscalls.h | 3 + include/uapi/asm-generic/unistd.h | 4 +- kernel/signal.c | 133 +++++++++++++++++++++++++++++++-- kernel/sys_ni.c | 1 + 8 files changed, 151 insertions(+), 7 deletions(-) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 3cf7b533b3d1..234d91df8ca6 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -398,3 +398,4 @@ 384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl 385 i386 io_pgetevents sys_io_pgetevents __ia32_compat_sys_io_pgetevents 386 i386 rseq sys_rseq __ia32_sys_rseq +424 i386 pidfd_send_signal sys_pidfd_send_signal __ia32_sys_pidfd_send_signal diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index f0b1709a5ffb..58f4b3ad4fe0 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -343,6 +343,7 @@ 332 common statx __x64_sys_statx 333 common io_pgetevents __x64_sys_io_pgetevents 334 common rseq __x64_sys_rseq +424 common pidfd_send_signal __x64_sys_pidfd_send_signal # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/fs/proc/base.c b/fs/proc/base.c index 633a63462573..b6627c471078 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3046,6 +3046,15 @@ static const struct file_operations proc_tgid_base_operations = { .llseek = generic_file_llseek, }; +struct pid *tgid_pidfd_to_pid(const struct file *file) +{ + if (!d_is_dir(file->f_path.dentry) || + (file->f_op != &proc_tgid_base_operations)) + return ERR_PTR(-EBADF); + + return proc_pid(file_inode(file)); +} + static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index d0e1f1522a78..52a283ba0465 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -73,6 +73,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo int (*show)(struct seq_file *, void *), proc_write_t write, void *data); +extern struct pid *tgid_pidfd_to_pid(const struct file *file); #else /* CONFIG_PROC_FS */ @@ -114,6 +115,11 @@ static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *p #define proc_create_net(name, mode, parent, state_size, ops) ({NULL;}) #define proc_create_net_single(name, mode, parent, show, data) ({NULL;}) +static inline struct pid *tgid_pidfd_to_pid(const struct file *file) +{ + return ERR_PTR(-EBADF); +} + #endif /* CONFIG_PROC_FS */ struct net; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 257cccba3062..5eb2e351675e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -926,6 +926,9 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, unsigned mask, struct statx __user *buffer); asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len, int flags, uint32_t sig); +asmlinkage long sys_pidfd_send_signal(int pidfd, int sig, + siginfo_t __user *info, + unsigned int flags); /* * Architecture-specific system calls diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index d90127298f12..c861e7d1053b 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -740,9 +740,11 @@ __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) __SYSCALL(__NR_rseq, sys_rseq) #define __NR_kexec_file_load 294 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) +#define __NR_pidfd_send_signal 424 +__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal) #undef __NR_syscalls -#define __NR_syscalls 295 +#define __NR_syscalls 425 /* * 32 bit systems traditionally used different diff --git a/kernel/signal.c b/kernel/signal.c index e1d7ad8e6ab1..268bed80244f 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -19,7 +19,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -3429,6 +3431,16 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, #endif #endif +static inline void prepare_kill_siginfo(int sig, struct kernel_siginfo *info) +{ + clear_siginfo(info); + info->si_signo = sig; + info->si_errno = 0; + info->si_code = SI_USER; + info->si_pid = task_tgid_vnr(current); + info->si_uid = from_kuid_munged(current_user_ns(), current_uid()); +} + /** * sys_kill - send a signal to a process * @pid: the PID of the process @@ -3438,16 +3450,125 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { struct kernel_siginfo info; - clear_siginfo(&info); - info.si_signo = sig; - info.si_errno = 0; - info.si_code = SI_USER; - info.si_pid = task_tgid_vnr(current); - info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + prepare_kill_siginfo(sig, &info); return kill_something_info(sig, &info, pid); } +#ifdef CONFIG_PROC_FS +/* + * Verify that the signaler and signalee either are in the same pid namespace + * or that the signaler's pid namespace is an ancestor of the signalee's pid + * namespace. + */ +static bool access_pidfd_pidns(struct pid *pid) +{ + struct pid_namespace *active = task_active_pid_ns(current); + struct pid_namespace *p = ns_of_pid(pid); + + for (;;) { + if (!p) + return false; + if (p == active) + break; + p = p->parent; + } + + return true; +} + +static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t *info) +{ +#ifdef CONFIG_COMPAT + /* + * Avoid hooking up compat syscalls and instead handle necessary + * conversions here. Note, this is a stop-gap measure and should not be + * considered a generic solution. + */ + if (in_compat_syscall()) + return copy_siginfo_from_user32( + kinfo, (struct compat_siginfo __user *)info); +#endif + return copy_siginfo_from_user(kinfo, info); +} + +/** + * sys_pidfd_send_signal - send a signal to a process through a task file + * descriptor + * @pidfd: the file descriptor of the process + * @sig: signal to be sent + * @info: the signal info + * @flags: future flags to be passed + * + * The syscall currently only signals via PIDTYPE_PID which covers + * kill(, . It does not signal threads or process + * groups. + * In order to extend the syscall to threads and process groups the @flags + * argument should be used. In essence, the @flags argument will determine + * what is signaled and not the file descriptor itself. Put in other words, + * grouping is a property of the flags argument not a property of the file + * descriptor. + * + * Return: 0 on success, negative errno on failure + */ +SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, + siginfo_t __user *, info, unsigned int, flags) +{ + int ret; + struct fd f; + struct pid *pid; + kernel_siginfo_t kinfo; + + /* Enforce flags be set to 0 until we add an extension. */ + if (flags) + return -EINVAL; + + f = fdget_raw(pidfd); + if (!f.file) + return -EBADF; + + /* Is this a pidfd? */ + pid = tgid_pidfd_to_pid(f.file); + if (IS_ERR(pid)) { + ret = PTR_ERR(pid); + goto err; + } + + ret = -EINVAL; + if (!access_pidfd_pidns(pid)) + goto err; + + if (info) { + ret = copy_siginfo_from_user_any(&kinfo, info); + if (unlikely(ret)) + goto err; + + ret = -EINVAL; + if (unlikely(sig != kinfo.si_signo)) + goto err; + + if ((task_pid(current) != pid) && + (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) { + /* Only allow sending arbitrary signals to yourself. */ + ret = -EPERM; + if (kinfo.si_code != SI_USER) + goto err; + + /* Turn this into a regular kill signal. */ + prepare_kill_siginfo(sig, &kinfo); + } + } else { + prepare_kill_siginfo(sig, &kinfo); + } + + ret = kill_pid_info(sig, &kinfo, pid); + +err: + fdput(f); + return ret; +} +#endif /* CONFIG_PROC_FS */ + static int do_send_specific(pid_t tgid, pid_t pid, int sig, struct kernel_siginfo *info) { diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index ab9d0e3c6d50..f905f4f9f677 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -163,6 +163,7 @@ COND_SYSCALL(syslog); /* kernel/sched/core.c */ /* kernel/signal.c */ +COND_SYSCALL(pidfd_send_signal); /* kernel/sys.c */ COND_SYSCALL(setregid); -- cgit v1.2.3 From 575a0ae9744d571f7c6aae4487a05850baae9e1c Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sat, 29 Dec 2018 22:27:33 +0100 Subject: selftests: add tests for pidfd_send_signal() As suggested by Andrew Morton in [1] add selftests for the new sys_pidfd_send_signal() syscall: /* test_pidfd_send_signal_syscall_support */ Test whether the pidfd_send_signal() syscall is supported and the tests can be run or need to be skipped. /* test_pidfd_send_signal_simple_success */ Test whether sending a signal via a pidfd works. /* test_pidfd_send_signal_exited_fail */ Verify that sending a signal to an already exited process fails with ESRCH. /* test_pidfd_send_signal_recycled_pid_fail */ Verify that a recycled pid cannot be signaled via a pidfd referring to an already exited process that had the same pid (cf. [2], [3]). [1]: https://lore.kernel.org/lkml/20181228152012.dbf0508c2508138efc5f2bbe@linux-foundation.org/ [2]: https://lore.kernel.org/lkml/20181230210245.GA30252@mail.hallyn.com/ [3]: https://lore.kernel.org/lkml/20181230232711.7aayb7vnhogbv4co@brauner.io/ Cc: Arnd Bergmann Cc: "Eric W. Biederman" Cc: Kees Cook Cc: Jann Horn Cc: Andy Lutomirsky Cc: Andrew Morton Cc: Oleg Nesterov Cc: Aleksa Sarai Cc: Al Viro Cc: Florian Weimer Signed-off-by: Christian Brauner Reviewed-by: Tycho Andersen Acked-by: Serge Hallyn --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/pidfd/Makefile | 6 + tools/testing/selftests/pidfd/pidfd_test.c | 381 +++++++++++++++++++++++++++++ 3 files changed, 388 insertions(+) create mode 100644 tools/testing/selftests/pidfd/Makefile create mode 100644 tools/testing/selftests/pidfd/pidfd_test.c diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 1a2bd15c5b6e..cfbc3528e9ef 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -30,6 +30,7 @@ TARGETS += net TARGETS += netfilter TARGETS += networking/timestamping TARGETS += nsfs +TARGETS += pidfd TARGETS += powerpc TARGETS += proc TARGETS += pstore diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile new file mode 100644 index 000000000000..deaf8073bc06 --- /dev/null +++ b/tools/testing/selftests/pidfd/Makefile @@ -0,0 +1,6 @@ +CFLAGS += -g -I../../../../usr/include/ + +TEST_GEN_PROGS := pidfd_test + +include ../lib.mk + diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c new file mode 100644 index 000000000000..d59378a93782 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -0,0 +1,381 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest.h" + +static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, + unsigned int flags) +{ + return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); +} + +static int signal_received; + +static void set_signal_received_on_sigusr1(int sig) +{ + if (sig == SIGUSR1) + signal_received = 1; +} + +/* + * Straightforward test to see whether pidfd_send_signal() works is to send + * a signal to ourself. + */ +static int test_pidfd_send_signal_simple_success(void) +{ + int pidfd, ret; + const char *test_name = "pidfd_send_signal send SIGUSR1"; + + pidfd = open("/proc/self", O_DIRECTORY | O_CLOEXEC); + if (pidfd < 0) + ksft_exit_fail_msg( + "%s test: Failed to open process file descriptor\n", + test_name); + + signal(SIGUSR1, set_signal_received_on_sigusr1); + + ret = sys_pidfd_send_signal(pidfd, SIGUSR1, NULL, 0); + close(pidfd); + if (ret < 0) + ksft_exit_fail_msg("%s test: Failed to send signal\n", + test_name); + + if (signal_received != 1) + ksft_exit_fail_msg("%s test: Failed to receive signal\n", + test_name); + + signal_received = 0; + ksft_test_result_pass("%s test: Sent signal\n", test_name); + return 0; +} + +static int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (ret != pid) + goto again; + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + +static int test_pidfd_send_signal_exited_fail(void) +{ + int pidfd, ret, saved_errno; + char buf[256]; + pid_t pid; + const char *test_name = "pidfd_send_signal signal exited process"; + + pid = fork(); + if (pid < 0) + ksft_exit_fail_msg("%s test: Failed to create new process\n", + test_name); + + if (pid == 0) + _exit(EXIT_SUCCESS); + + snprintf(buf, sizeof(buf), "/proc/%d", pid); + + pidfd = open(buf, O_DIRECTORY | O_CLOEXEC); + + (void)wait_for_pid(pid); + + if (pidfd < 0) + ksft_exit_fail_msg( + "%s test: Failed to open process file descriptor\n", + test_name); + + ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0); + saved_errno = errno; + close(pidfd); + if (ret == 0) + ksft_exit_fail_msg( + "%s test: Managed to send signal to process even though it should have failed\n", + test_name); + + if (saved_errno != ESRCH) + ksft_exit_fail_msg( + "%s test: Expected to receive ESRCH as errno value but received %d instead\n", + test_name, saved_errno); + + ksft_test_result_pass("%s test: Failed to send signal as expected\n", + test_name); + return 0; +} + +/* + * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c + * That means, when it wraps around any pid < 300 will be skipped. + * So we need to use a pid > 300 in order to test recycling. + */ +#define PID_RECYCLE 1000 + +/* + * Maximum number of cycles we allow. This is equivalent to PID_MAX_DEFAULT. + * If users set a higher limit or we have cycled PIDFD_MAX_DEFAULT number of + * times then we skip the test to not go into an infinite loop or block for a + * long time. + */ +#define PIDFD_MAX_DEFAULT 0x8000 + +/* + * Define a few custom error codes for the child process to clearly indicate + * what is happening. This way we can tell the difference between a system + * error, a test error, etc. + */ +#define PIDFD_PASS 0 +#define PIDFD_FAIL 1 +#define PIDFD_ERROR 2 +#define PIDFD_SKIP 3 +#define PIDFD_XFAIL 4 + +static int test_pidfd_send_signal_recycled_pid_fail(void) +{ + int i, ret; + pid_t pid1; + const char *test_name = "pidfd_send_signal signal recycled pid"; + + ret = unshare(CLONE_NEWPID); + if (ret < 0) + ksft_exit_fail_msg("%s test: Failed to unshare pid namespace\n", + test_name); + + ret = unshare(CLONE_NEWNS); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: Failed to unshare mount namespace\n", + test_name); + + ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); + if (ret < 0) + ksft_exit_fail_msg("%s test: Failed to remount / private\n", + test_name); + + /* pid 1 in new pid namespace */ + pid1 = fork(); + if (pid1 < 0) + ksft_exit_fail_msg("%s test: Failed to create new process\n", + test_name); + + if (pid1 == 0) { + char buf[256]; + pid_t pid2; + int pidfd = -1; + + (void)umount2("/proc", MNT_DETACH); + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret < 0) + _exit(PIDFD_ERROR); + + /* grab pid PID_RECYCLE */ + for (i = 0; i <= PIDFD_MAX_DEFAULT; i++) { + pid2 = fork(); + if (pid2 < 0) + _exit(PIDFD_ERROR); + + if (pid2 == 0) + _exit(PIDFD_PASS); + + if (pid2 == PID_RECYCLE) { + snprintf(buf, sizeof(buf), "/proc/%d", pid2); + ksft_print_msg("pid to recycle is %d\n", pid2); + pidfd = open(buf, O_DIRECTORY | O_CLOEXEC); + } + + if (wait_for_pid(pid2)) + _exit(PIDFD_ERROR); + + if (pid2 >= PID_RECYCLE) + break; + } + + /* + * We want to be as predictable as we can so if we haven't been + * able to grab pid PID_RECYCLE skip the test. + */ + if (pid2 != PID_RECYCLE) { + /* skip test */ + close(pidfd); + _exit(PIDFD_SKIP); + } + + if (pidfd < 0) + _exit(PIDFD_ERROR); + + for (i = 0; i <= PIDFD_MAX_DEFAULT; i++) { + char c; + int pipe_fds[2]; + pid_t recycled_pid; + int child_ret = PIDFD_PASS; + + ret = pipe2(pipe_fds, O_CLOEXEC); + if (ret < 0) + _exit(PIDFD_ERROR); + + recycled_pid = fork(); + if (recycled_pid < 0) + _exit(PIDFD_ERROR); + + if (recycled_pid == 0) { + close(pipe_fds[1]); + (void)read(pipe_fds[0], &c, 1); + close(pipe_fds[0]); + + _exit(PIDFD_PASS); + } + + /* + * Stop the child so we can inspect whether we have + * recycled pid PID_RECYCLE. + */ + close(pipe_fds[0]); + ret = kill(recycled_pid, SIGSTOP); + close(pipe_fds[1]); + if (ret) { + (void)wait_for_pid(recycled_pid); + _exit(PIDFD_ERROR); + } + + /* + * We have recycled the pid. Try to signal it. This + * needs to fail since this is a different process than + * the one the pidfd refers to. + */ + if (recycled_pid == PID_RECYCLE) { + ret = sys_pidfd_send_signal(pidfd, SIGCONT, + NULL, 0); + if (ret && errno == ESRCH) + child_ret = PIDFD_XFAIL; + else + child_ret = PIDFD_FAIL; + } + + /* let the process move on */ + ret = kill(recycled_pid, SIGCONT); + if (ret) + (void)kill(recycled_pid, SIGKILL); + + if (wait_for_pid(recycled_pid)) + _exit(PIDFD_ERROR); + + switch (child_ret) { + case PIDFD_FAIL: + /* fallthrough */ + case PIDFD_XFAIL: + _exit(child_ret); + case PIDFD_PASS: + break; + default: + /* not reached */ + _exit(PIDFD_ERROR); + } + + /* + * If the user set a custom pid_max limit we could be + * in the millions. + * Skip the test in this case. + */ + if (recycled_pid > PIDFD_MAX_DEFAULT) + _exit(PIDFD_SKIP); + } + + /* failed to recycle pid */ + _exit(PIDFD_SKIP); + } + + ret = wait_for_pid(pid1); + switch (ret) { + case PIDFD_FAIL: + ksft_exit_fail_msg( + "%s test: Managed to signal recycled pid %d\n", + test_name, PID_RECYCLE); + case PIDFD_PASS: + ksft_exit_fail_msg("%s test: Failed to recycle pid %d\n", + test_name, PID_RECYCLE); + case PIDFD_SKIP: + ksft_print_msg("%s test: Skipping test\n", test_name); + ret = 0; + break; + case PIDFD_XFAIL: + ksft_test_result_pass( + "%s test: Failed to signal recycled pid as expected\n", + test_name); + ret = 0; + break; + default /* PIDFD_ERROR */: + ksft_exit_fail_msg("%s test: Error while running tests\n", + test_name); + } + + return ret; +} + +static int test_pidfd_send_signal_syscall_support(void) +{ + int pidfd, ret; + const char *test_name = "pidfd_send_signal check for support"; + + pidfd = open("/proc/self", O_DIRECTORY | O_CLOEXEC); + if (pidfd < 0) + ksft_exit_fail_msg( + "%s test: Failed to open process file descriptor\n", + test_name); + + ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0); + if (ret < 0) { + /* + * pidfd_send_signal() will currently return ENOSYS when + * CONFIG_PROC_FS is not set. + */ + if (errno == ENOSYS) + ksft_exit_skip( + "%s test: pidfd_send_signal() syscall not supported (Ensure that CONFIG_PROC_FS=y is set)\n", + test_name); + + ksft_exit_fail_msg("%s test: Failed to send signal\n", + test_name); + } + + close(pidfd); + ksft_test_result_pass( + "%s test: pidfd_send_signal() syscall is supported. Tests can be executed\n", + test_name); + return 0; +} + +int main(int argc, char **argv) +{ + ksft_print_header(); + + test_pidfd_send_signal_syscall_support(); + test_pidfd_send_signal_simple_success(); + test_pidfd_send_signal_exited_fail(); + test_pidfd_send_signal_recycled_pid_fail(); + + return ksft_exit_pass(); +} -- cgit v1.2.3