Pull pidfd updates from Christian Brauner:
"This patchset makes it possible to retrieve pidfds at process creation
time by introducing the new flag CLONE_PIDFD to the clone() system
call. Linus originally suggested to implement this as a new flag to
clone() instead of making it a separate system call.
After a thorough review from Oleg CLONE_PIDFD returns pidfds in the
parent_tidptr argument. This means we can give back the associated pid
and the pidfd at the same time. Access to process metadata information
thus becomes rather trivial.
As has been agreed, CLONE_PIDFD creates file descriptors based on
anonymous inodes similar to the new mount api. They are made
unconditional by this patchset as they are now needed by core kernel
code (vfs, pidfd) even more than they already were before (timerfd,
signalfd, io_uring, epoll etc.). The core patchset is rather small.
The bulky looking changelist is caused by David's very simple changes
to Kconfig to make anon inodes unconditional.
A pidfd comes with additional information in fdinfo if the kernel
supports procfs. The fdinfo file contains the pid of the process in
the callers pid namespace in the same format as the procfs status
file, i.e. "Pid:\t%d".
To remove worries about missing metadata access this patchset comes
with a sample/test program that illustrates how a combination of
CLONE_PIDFD and pidfd_send_signal() can be used to gain race-free
access to process metadata through /proc/<pid>.
Further work based on this patchset has been done by Joel. His work
makes pidfds pollable. It finished too late for this merge window. I
would prefer to have it sitting in linux-next for a while and send it
for inclusion during the 5.3 merge window"
* tag 'pidfd-v5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
samples: show race-free pidfd metadata access
signal: support CLONE_PIDFD with pidfd_send_signal
clone: add CLONE_PIDFD
Make anon_inodes unconditional
bool "Kernel-based Virtual Machine (KVM) support"
depends on MMU && OF
select PREEMPT_NOTIFIERS
- select ANON_INODES
select ARM_GIC
select ARM_GIC_V3
select ARM_GIC_V3_ITS
depends on OF
select MMU_NOTIFIER
select PREEMPT_NOTIFIERS
- select ANON_INODES
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_ARCH_TLB_FLUSH_ALL
select KVM_MMIO
depends on MIPS_FP_SUPPORT
select EXPORT_UASM
select PREEMPT_NOTIFIERS
- select ANON_INODES
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
select HAVE_KVM_VCPU_ASYNC_IOCTL
select KVM_MMIO
config KVM
bool
select PREEMPT_NOTIFIERS
- select ANON_INODES
select HAVE_KVM_EVENTFD
select HAVE_KVM_VCPU_ASYNC_IOCTL
select SRCU
prompt "Kernel-based Virtual Machine (KVM) support"
depends on HAVE_KVM
select PREEMPT_NOTIFIERS
- select ANON_INODES
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_VCPU_ASYNC_IOCTL
select HAVE_KVM_EVENTFD
#
select ACPI_LEGACY_TABLES_LOOKUP if ACPI
select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
- select ANON_INODES
select ARCH_32BIT_OFF_T if X86_32
select ARCH_CLOCKSOURCE_DATA
select ARCH_CLOCKSOURCE_INIT
depends on X86_LOCAL_APIC
select PREEMPT_NOTIFIERS
select MMU_NOTIFIER
- select ANON_INODES
select HAVE_KVM_IRQCHIP
select HAVE_KVM_IRQFD
select IRQ_BYPASS_MANAGER
config DMA_SHARED_BUFFER
bool
default n
- select ANON_INODES
select IRQ_WORK
help
This option enables the framework for buffer-sharing between
config TCG_VTPM_PROXY
tristate "VTPM Proxy Interface"
depends on TCG_TPM
- select ANON_INODES
---help---
This driver proxies for an emulated TPM (vTPM) running in userspace.
A device /dev/vtpmx is provided that creates a device pair
config SYNC_FILE
bool "Explicit Synchronization Framework"
default n
- select ANON_INODES
select DMA_SHARED_BUFFER
---help---
The Sync File Framework adds explicit syncronization via
menuconfig GPIOLIB
bool "GPIO Support"
- select ANON_INODES
help
This enables GPIO support through the generic GPIO library.
You only need to enable this, if you also want to enable
menuconfig IIO
tristate "Industrial I/O support"
- select ANON_INODES
help
The industrial I/O subsystem provides a unified framework for
drivers for many different types of embedded sensors using a
config INFINIBAND_USER_ACCESS
tristate "InfiniBand userspace access (verbs and CM)"
- select ANON_INODES
depends on MMU
---help---
Userspace InfiniBand access support. This enables the
tristate "VFIO Non-Privileged userspace driver framework"
depends on IOMMU_API
select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM || ARM64)
- select ANON_INODES
help
VFIO provides a framework for secure userspace device drivers.
See Documentation/vfio.txt for more details.
obj-y += notify/
obj-$(CONFIG_EPOLL) += eventpoll.o
-obj-$(CONFIG_ANON_INODES) += anon_inodes.o
+obj-y += anon_inodes.o
obj-$(CONFIG_SIGNALFD) += signalfd.o
obj-$(CONFIG_TIMERFD) += timerfd.o
obj-$(CONFIG_EVENTFD) += eventfd.o
config FANOTIFY
bool "Filesystem wide access notification"
select FSNOTIFY
- select ANON_INODES
select EXPORTFS
default n
---help---
config INOTIFY_USER
bool "Inotify support for userspace"
- select ANON_INODES
select FSNOTIFY
default y
---help---
extern struct pid init_struct_pid;
+extern const struct file_operations pidfd_fops;
+
static inline struct pid *get_pid(struct pid *pid)
{
if (pid)
#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */
+#define CLONE_PIDFD 0x00001000 /* set if a pidfd should be placed in parent */
#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */
#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */
#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */
config SYSCTL
bool
-config ANON_INODES
- bool
-
config HAVE_UID16
bool
config EPOLL
bool "Enable eventpoll support" if EXPERT
default y
- select ANON_INODES
help
Disabling this option will cause the kernel to be built without
support for epoll family of system calls.
config SIGNALFD
bool "Enable signalfd() system call" if EXPERT
- select ANON_INODES
default y
help
Enable the signalfd() system call that allows to receive signals
config TIMERFD
bool "Enable timerfd() system call" if EXPERT
- select ANON_INODES
default y
help
Enable the timerfd() system call that allows to receive timer
config EVENTFD
bool "Enable eventfd() system call" if EXPERT
- select ANON_INODES
default y
help
Enable the eventfd() system call that allows to receive both
# syscall, maps, verifier
config BPF_SYSCALL
bool "Enable bpf() system call"
- select ANON_INODES
select BPF
select IRQ_WORK
default n
config USERFAULTFD
bool "Enable userfaultfd() system call"
- select ANON_INODES
depends on MMU
help
Enable the userfaultfd() system call that allows to intercept and
bool "Kernel performance events and counters"
default y if PROFILING
depends on HAVE_PERF_EVENTS
- select ANON_INODES
select IRQ_WORK
select SRCU
help
* management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
*/
+#include <linux/anon_inodes.h>
#include <linux/slab.h>
#include <linux/sched/autogroup.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/cputime.h>
+#include <linux/seq_file.h>
#include <linux/rtmutex.h>
#include <linux/init.h>
#include <linux/unistd.h>
#endif /* #ifdef CONFIG_TASKS_RCU */
}
+static int pidfd_release(struct inode *inode, struct file *file)
+{
+ struct pid *pid = file->private_data;
+
+ file->private_data = NULL;
+ put_pid(pid);
+ return 0;
+}
+
+#ifdef CONFIG_PROC_FS
+static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct pid_namespace *ns = proc_pid_ns(file_inode(m->file));
+ struct pid *pid = f->private_data;
+
+ seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
+ seq_putc(m, '\n');
+}
+#endif
+
+const struct file_operations pidfd_fops = {
+ .release = pidfd_release,
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = pidfd_show_fdinfo,
+#endif
+};
+
+/**
+ * pidfd_create() - Create a new pid file descriptor.
+ *
+ * @pid: struct pid that the pidfd will reference
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set.
+ *
+ * Note, that this function can only be called after the fd table has
+ * been unshared to avoid leaking the pidfd to the new process.
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ * On error, a negative errno number will be returned.
+ */
+static int pidfd_create(struct pid *pid)
+{
+ int fd;
+
+ fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
+ O_RDWR | O_CLOEXEC);
+ if (fd < 0)
+ put_pid(pid);
+
+ return fd;
+}
+
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
+ int __user *parent_tidptr,
int __user *child_tidptr,
struct pid *pid,
int trace,
unsigned long tls,
int node)
{
- int retval;
+ int pidfd = -1, retval;
struct task_struct *p;
struct multiprocess_signals delayed;
return ERR_PTR(-EINVAL);
}
+ if (clone_flags & CLONE_PIDFD) {
+ int reserved;
+
+ /*
+ * - CLONE_PARENT_SETTID is useless for pidfds and also
+ * parent_tidptr is used to return pidfds.
+ * - CLONE_DETACHED is blocked so that we can potentially
+ * reuse it later for CLONE_PIDFD.
+ * - CLONE_THREAD is blocked until someone really needs it.
+ */
+ if (clone_flags &
+ (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD))
+ return ERR_PTR(-EINVAL);
+
+ /*
+ * Verify that parent_tidptr is sane so we can potentially
+ * reuse it later.
+ */
+ if (get_user(reserved, parent_tidptr))
+ return ERR_PTR(-EFAULT);
+
+ if (reserved != 0)
+ return ERR_PTR(-EINVAL);
+ }
+
/*
* Force any signals received before this point to be delivered
* before the fork happens. Collect up signals sent to multiple
}
}
+ /*
+ * This has to happen after we've potentially unshared the file
+ * descriptor table (so that the pidfd doesn't leak into the child
+ * if the fd table isn't shared).
+ */
+ if (clone_flags & CLONE_PIDFD) {
+ retval = pidfd_create(pid);
+ if (retval < 0)
+ goto bad_fork_free_pid;
+
+ pidfd = retval;
+ retval = put_user(pidfd, parent_tidptr);
+ if (retval)
+ goto bad_fork_put_pidfd;
+ }
+
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
*/
retval = cgroup_can_fork(p);
if (retval)
- goto bad_fork_free_pid;
+ goto bad_fork_put_pidfd;
/*
* From this point on we must avoid any synchronous user-space
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p);
+bad_fork_put_pidfd:
+ if (clone_flags & CLONE_PIDFD)
+ ksys_close(pidfd);
bad_fork_free_pid:
cgroup_threadgroup_change_end(current);
if (pid != &init_struct_pid)
struct task_struct *fork_idle(int cpu)
{
struct task_struct *task;
- task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+ task = copy_process(CLONE_VM, 0, 0, NULL, NULL, &init_struct_pid, 0, 0,
cpu_to_node(cpu));
if (!IS_ERR(task)) {
init_idle_pids(task);
trace = 0;
}
- p = copy_process(clone_flags, stack_start, stack_size,
+ p = copy_process(clone_flags, stack_start, stack_size, parent_tidptr,
child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
add_latent_entropy();
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
return copy_siginfo_from_user(kinfo, info);
}
+static struct pid *pidfd_to_pid(const struct file *file)
+{
+ if (file->f_op == &pidfd_fops)
+ return file->private_data;
+
+ return tgid_pidfd_to_pid(file);
+}
+
/**
* sys_pidfd_send_signal - send a signal to a process through a task file
* descriptor
return -EBADF;
/* Is this a pidfd? */
- pid = tgid_pidfd_to_pid(f.file);
+ pid = pidfd_to_pid(f.file);
if (IS_ERR(pid)) {
ret = PTR_ERR(pid);
goto 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)
/* kernel/sched/core.c */
-/* kernel/signal.c */
-COND_SYSCALL(pidfd_send_signal);
-
/* kernel/sys.c */
COND_SYSCALL(setregid);
COND_SYSCALL(setgid);
obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ trace_events/ livepatch/ \
hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ \
configfs/ connector/ v4l/ trace_printk/ \
- vfio-mdev/ statx/ qmi/ binderfs/
+ vfio-mdev/ statx/ qmi/ binderfs/ pidfd/
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+hostprogs-y := pidfd-metadata
+always := $(hostprogs-y)
+HOSTCFLAGS_pidfd-metadata.o += -I$(objtree)/usr/include
+all: pidfd-metadata
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <err.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#ifndef CLONE_PIDFD
+#define CLONE_PIDFD 0x00001000
+#endif
+
+static int do_child(void *args)
+{
+ printf("%d\n", getpid());
+ _exit(EXIT_SUCCESS);
+}
+
+static pid_t pidfd_clone(int flags, int *pidfd)
+{
+ size_t stack_size = 1024;
+ char *stack[1024] = { 0 };
+
+#ifdef __ia64__
+ return __clone2(do_child, stack, stack_size, flags | SIGCHLD, NULL, pidfd);
+#else
+ return clone(do_child, stack + stack_size, flags | SIGCHLD, NULL, pidfd);
+#endif
+}
+
+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 pidfd_metadata_fd(pid_t pid, int pidfd)
+{
+ int procfd, ret;
+ char path[100];
+
+ snprintf(path, sizeof(path), "/proc/%d", pid);
+ procfd = open(path, O_DIRECTORY | O_RDONLY | O_CLOEXEC);
+ if (procfd < 0) {
+ warn("Failed to open %s\n", path);
+ return -1;
+ }
+
+ /*
+ * Verify that the pid has not been recycled and our /proc/<pid> handle
+ * is still valid.
+ */
+ ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0);
+ if (ret < 0) {
+ switch (errno) {
+ case EPERM:
+ /* Process exists, just not allowed to signal it. */
+ break;
+ default:
+ warn("Failed to signal process\n");
+ close(procfd);
+ procfd = -1;
+ }
+ }
+
+ return procfd;
+}
+
+int main(int argc, char *argv[])
+{
+ int pidfd = 0, ret = EXIT_FAILURE;
+ char buf[4096] = { 0 };
+ pid_t pid;
+ int procfd, statusfd;
+ ssize_t bytes;
+
+ pid = pidfd_clone(CLONE_PIDFD, &pidfd);
+ if (pid < 0)
+ exit(ret);
+
+ procfd = pidfd_metadata_fd(pid, pidfd);
+ close(pidfd);
+ if (procfd < 0)
+ goto out;
+
+ statusfd = openat(procfd, "status", O_RDONLY | O_CLOEXEC);
+ close(procfd);
+ if (statusfd < 0)
+ goto out;
+
+ bytes = read(statusfd, buf, sizeof(buf));
+ if (bytes > 0)
+ bytes = write(STDOUT_FILENO, buf, bytes);
+ close(statusfd);
+ ret = EXIT_SUCCESS;
+
+out:
+ (void)wait(NULL);
+
+ exit(ret);
+}
projects / linux-2.6-block.git / commitdiff