summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--arch/alpha/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/arm/tools/syscall.tbl1
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/unistd32.h2
-rw-r--r--arch/ia64/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/m68k/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/microblaze/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/mips/kernel/syscalls/syscall_n32.tbl1
-rw-r--r--arch/mips/kernel/syscalls/syscall_n64.tbl1
-rw-r--r--arch/mips/kernel/syscalls/syscall_o32.tbl1
-rw-r--r--arch/parisc/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/powerpc/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/s390/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/sh/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/sparc/kernel/syscalls/syscall.tbl1
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl1
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl1
-rw-r--r--arch/xtensa/kernel/syscalls/syscall.tbl1
-rw-r--r--fs/file.c22
-rw-r--r--include/linux/file.h2
-rw-r--r--include/linux/sched.h2
-rw-r--r--include/linux/syscalls.h1
-rw-r--r--include/uapi/asm-generic/unistd.h4
-rw-r--r--include/uapi/linux/capability.h1
-rw-r--r--include/uapi/linux/prctl.h4
-rw-r--r--kernel/pid.c90
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/sys.c25
-rw-r--r--tools/testing/selftests/pidfd/.gitignore1
-rw-r--r--tools/testing/selftests/pidfd/Makefile2
-rw-r--r--tools/testing/selftests/pidfd/pidfd.h9
-rw-r--r--tools/testing/selftests/pidfd/pidfd_getfd_test.c249
32 files changed, 427 insertions, 7 deletions
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 4d7f2ffa957c..36d42da7466a 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -476,3 +476,4 @@
544 common pidfd_open sys_pidfd_open
# 545 reserved for clone3
547 common openat2 sys_openat2
+548 common pidfd_getfd sys_pidfd_getfd
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 4ba54bc7e19a..4d1cf74a2caa 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -450,3 +450,4 @@
434 common pidfd_open sys_pidfd_open
435 common clone3 sys_clone3
437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 0f255a23733d..1dd22da1c3a9 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 438
+#define __NR_compat_syscalls 439
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 57f6f592d460..c1c61635f89c 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -881,6 +881,8 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
__SYSCALL(__NR_clone3, sys_clone3)
#define __NR_openat2 437
__SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 8d36f2e2dc89..042911e670b8 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -357,3 +357,4 @@
434 common pidfd_open sys_pidfd_open
# 435 reserved for clone3
437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index b911e0f50a71..f4f49fcb76d0 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -436,3 +436,4 @@
434 common pidfd_open sys_pidfd_open
435 common clone3 __sys_clone3
437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index c04385e60833..4c67b11f9c9e 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
434 common pidfd_open sys_pidfd_open
435 common clone3 sys_clone3
437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 68c9ec06851f..1f9e8ad636cc 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -375,3 +375,4 @@
434 n32 pidfd_open sys_pidfd_open
435 n32 clone3 __sys_clone3
437 n32 openat2 sys_openat2
+438 n32 pidfd_getfd sys_pidfd_getfd
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 42a72d010050..c0b9d802dbf6 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -351,3 +351,4 @@
434 n64 pidfd_open sys_pidfd_open
435 n64 clone3 __sys_clone3
437 n64 openat2 sys_openat2
+438 n64 pidfd_getfd sys_pidfd_getfd
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index f114c4aed0ed..ac586774c980 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -424,3 +424,4 @@
434 o32 pidfd_open sys_pidfd_open
435 o32 clone3 __sys_clone3
437 o32 openat2 sys_openat2
+438 o32 pidfd_getfd sys_pidfd_getfd
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index b550ae9a7fea..52a15f5cd130 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -434,3 +434,4 @@
434 common pidfd_open sys_pidfd_open
435 common clone3 sys_clone3_wrapper
437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index a8b5ecb5b602..35b61bfc1b1a 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -518,3 +518,4 @@
434 common pidfd_open sys_pidfd_open
435 nospu clone3 ppc_clone3
437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 16b571c06161..bd7bd3581a0f 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -439,3 +439,4 @@
434 common pidfd_open sys_pidfd_open sys_pidfd_open
435 common clone3 sys_clone3 sys_clone3
437 common openat2 sys_openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index a7185cc18626..c7a30fcd135f 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -439,3 +439,4 @@
434 common pidfd_open sys_pidfd_open
# 435 reserved for clone3
437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index b11c19552022..f13615ecdecc 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -482,3 +482,4 @@
434 common pidfd_open sys_pidfd_open
# 435 reserved for clone3
437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index d22a8b5c3fab..c17cb77eb150 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -441,3 +441,4 @@
434 i386 pidfd_open sys_pidfd_open __ia32_sys_pidfd_open
435 i386 clone3 sys_clone3 __ia32_sys_clone3
437 i386 openat2 sys_openat2 __ia32_sys_openat2
+438 i386 pidfd_getfd sys_pidfd_getfd __ia32_sys_pidfd_getfd
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9035647ef236..44d510bc9b78 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -358,6 +358,7 @@
434 common pidfd_open __x64_sys_pidfd_open
435 common clone3 __x64_sys_clone3/ptregs
437 common openat2 __x64_sys_openat2
+438 common pidfd_getfd __x64_sys_pidfd_getfd
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index f0a68013c038..85a9ab1bc04d 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -407,3 +407,4 @@
434 common pidfd_open sys_pidfd_open
435 common clone3 sys_clone3
437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
diff --git a/fs/file.c b/fs/file.c
index fb7081bfac2b..a364e1a9b7e8 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -708,9 +708,9 @@ void do_close_on_exec(struct files_struct *files)
spin_unlock(&files->file_lock);
}
-static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs)
+static struct file *__fget_files(struct files_struct *files, unsigned int fd,
+ fmode_t mask, unsigned int refs)
{
- struct files_struct *files = current->files;
struct file *file;
rcu_read_lock();
@@ -731,6 +731,12 @@ loop:
return file;
}
+static inline struct file *__fget(unsigned int fd, fmode_t mask,
+ unsigned int refs)
+{
+ return __fget_files(current->files, fd, mask, refs);
+}
+
struct file *fget_many(unsigned int fd, unsigned int refs)
{
return __fget(fd, FMODE_PATH, refs);
@@ -748,6 +754,18 @@ struct file *fget_raw(unsigned int fd)
}
EXPORT_SYMBOL(fget_raw);
+struct file *fget_task(struct task_struct *task, unsigned int fd)
+{
+ struct file *file = NULL;
+
+ task_lock(task);
+ if (task->files)
+ file = __fget_files(task->files, fd, 0, 1);
+ task_unlock(task);
+
+ return file;
+}
+
/*
* Lightweight file lookup - no refcnt increment if fd table isn't shared.
*
diff --git a/include/linux/file.h b/include/linux/file.h
index 3fcddff56bc4..c6c7b24ea9f7 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -16,6 +16,7 @@ extern void fput(struct file *);
extern void fput_many(struct file *, unsigned int);
struct file_operations;
+struct task_struct;
struct vfsmount;
struct dentry;
struct inode;
@@ -47,6 +48,7 @@ static inline void fdput(struct fd fd)
extern struct file *fget(unsigned int fd);
extern struct file *fget_many(unsigned int fd, unsigned int refs);
extern struct file *fget_raw(unsigned int fd);
+extern struct file *fget_task(struct task_struct *task, unsigned int fd);
extern unsigned long __fdget(unsigned int fd);
extern unsigned long __fdget_raw(unsigned int fd);
extern unsigned long __fdget_pos(unsigned int fd);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 716ad1d8d95e..04278493bf15 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -917,7 +917,7 @@ struct task_struct {
/* Signal handlers: */
struct signal_struct *signal;
- struct sighand_struct *sighand;
+ struct sighand_struct __rcu *sighand;
sigset_t blocked;
sigset_t real_blocked;
/* Restored if set_restore_sigmask() was used: */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index ac3a663137b6..1815065d52f3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1002,6 +1002,7 @@ asmlinkage long sys_fspick(int dfd, const char __user *path, unsigned int flags)
asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
siginfo_t __user *info,
unsigned int flags);
+asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags);
/*
* Architecture-specific system calls
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index d4122c091472..3a3201e4618e 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -853,9 +853,11 @@ __SYSCALL(__NR_clone3, sys_clone3)
#define __NR_openat2 437
__SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
#undef __NR_syscalls
-#define __NR_syscalls 438
+#define __NR_syscalls 439
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 240fdb9a60f6..272dc69fa080 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -301,6 +301,7 @@ struct vfs_ns_cap_data {
/* Allow more than 64hz interrupts from the real-time clock */
/* Override max number of consoles on console allocation */
/* Override max number of keymaps */
+/* Control memory reclaim behavior */
#define CAP_SYS_RESOURCE 24
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 7da1b37b27aa..07b4f8131e36 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -234,4 +234,8 @@ struct prctl_mm_map {
#define PR_GET_TAGGED_ADDR_CTRL 56
# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
+/* Control reclaim behavior when allocating memory */
+#define PR_SET_IO_FLUSHER 57
+#define PR_GET_IO_FLUSHER 58
+
#endif /* _LINUX_PRCTL_H */
diff --git a/kernel/pid.c b/kernel/pid.c
index 2278e249141d..0f4ecb57214c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -578,3 +578,93 @@ void __init pid_idr_init(void)
init_pid_ns.pid_cachep = KMEM_CACHE(pid,
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
}
+
+static struct file *__pidfd_fget(struct task_struct *task, int fd)
+{
+ struct file *file;
+ int ret;
+
+ ret = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ if (ret)
+ return ERR_PTR(ret);
+
+ if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
+ file = fget_task(task, fd);
+ else
+ file = ERR_PTR(-EPERM);
+
+ mutex_unlock(&task->signal->cred_guard_mutex);
+
+ return file ?: ERR_PTR(-EBADF);
+}
+
+static int pidfd_getfd(struct pid *pid, int fd)
+{
+ struct task_struct *task;
+ struct file *file;
+ int ret;
+
+ task = get_pid_task(pid, PIDTYPE_PID);
+ if (!task)
+ return -ESRCH;
+
+ file = __pidfd_fget(task, fd);
+ put_task_struct(task);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ ret = security_file_receive(file);
+ if (ret) {
+ fput(file);
+ return ret;
+ }
+
+ ret = get_unused_fd_flags(O_CLOEXEC);
+ if (ret < 0)
+ fput(file);
+ else
+ fd_install(ret, file);
+
+ return ret;
+}
+
+/**
+ * sys_pidfd_getfd() - Get a file descriptor from another process
+ *
+ * @pidfd: the pidfd file descriptor of the process
+ * @fd: the file descriptor number to get
+ * @flags: flags on how to get the fd (reserved)
+ *
+ * This syscall gets a copy of a file descriptor from another process
+ * based on the pidfd, and file descriptor number. It requires that
+ * the calling process has the ability to ptrace the process represented
+ * by the pidfd. The process which is having its file descriptor copied
+ * is otherwise unaffected.
+ *
+ * Return: On success, a cloexec file descriptor is returned.
+ * On error, a negative errno number will be returned.
+ */
+SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd,
+ unsigned int, flags)
+{
+ struct pid *pid;
+ struct fd f;
+ int ret;
+
+ /* flags is currently unused - make sure it's unset */
+ if (flags)
+ return -EINVAL;
+
+ f = fdget(pidfd);
+ if (!f.file)
+ return -EBADF;
+
+ pid = pidfd_pid(f.file);
+ if (IS_ERR(pid))
+ ret = PTR_ERR(pid);
+ else
+ ret = pidfd_getfd(pid, fd);
+
+ fdput(f);
+ return ret;
+}
diff --git a/kernel/signal.c b/kernel/signal.c
index bcd46f547db3..9ad8dea93dbb 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1383,7 +1383,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
* must see ->sighand == NULL.
*/
spin_lock_irqsave(&sighand->siglock, *flags);
- if (likely(sighand == tsk->sighand))
+ if (likely(sighand == rcu_access_pointer(tsk->sighand)))
break;
spin_unlock_irqrestore(&sighand->siglock, *flags);
}
diff --git a/kernel/sys.c b/kernel/sys.c
index a9331f101883..f9bc5c303e3f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2261,6 +2261,8 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
return -EINVAL;
}
+#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LESS_THROTTLE)
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -2488,6 +2490,29 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
return -EINVAL;
error = GET_TAGGED_ADDR_CTRL();
break;
+ case PR_SET_IO_FLUSHER:
+ if (!capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ if (arg2 == 1)
+ current->flags |= PR_IO_FLUSHER;
+ else if (!arg2)
+ current->flags &= ~PR_IO_FLUSHER;
+ else
+ return -EINVAL;
+ break;
+ case PR_GET_IO_FLUSHER:
+ if (!capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
+ break;
default:
error = -EINVAL;
break;
diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore
index 8d069490e17b..3a779c084d96 100644
--- a/tools/testing/selftests/pidfd/.gitignore
+++ b/tools/testing/selftests/pidfd/.gitignore
@@ -2,3 +2,4 @@ pidfd_open_test
pidfd_poll_test
pidfd_test
pidfd_wait
+pidfd_getfd_test
diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index 43db1b98e845..75a545861375 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
CFLAGS += -g -I../../../../usr/include/ -pthread
-TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait
+TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait pidfd_getfd_test
include ../lib.mk
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index c6bc68329f4b..d482515604db 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -36,6 +36,10 @@
#define __NR_clone3 -1
#endif
+#ifndef __NR_pidfd_getfd
+#define __NR_pidfd_getfd -1
+#endif
+
/*
* The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c
* That means, when it wraps around any pid < 300 will be skipped.
@@ -84,4 +88,9 @@ static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info,
return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags);
}
+static inline int sys_pidfd_getfd(int pidfd, int fd, int flags)
+{
+ return syscall(__NR_pidfd_getfd, pidfd, fd, flags);
+}
+
#endif /* __PIDFD_H */
diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
new file mode 100644
index 000000000000..401a7c1d0312
--- /dev/null
+++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/types.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <linux/kcmp.h>
+
+#include "pidfd.h"
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+
+/*
+ * UNKNOWN_FD is an fd number that should never exist in the child, as it is
+ * used to check the negative case.
+ */
+#define UNKNOWN_FD 111
+#define UID_NOBODY 65535
+
+static int sys_kcmp(pid_t pid1, pid_t pid2, int type, unsigned long idx1,
+ unsigned long idx2)
+{
+ return syscall(__NR_kcmp, pid1, pid2, type, idx1, idx2);
+}
+
+static int sys_memfd_create(const char *name, unsigned int flags)
+{
+ return syscall(__NR_memfd_create, name, flags);
+}
+
+static int __child(int sk, int memfd)
+{
+ int ret;
+ char buf;
+
+ /*
+ * Ensure we don't leave around a bunch of orphaned children if our
+ * tests fail.
+ */
+ ret = prctl(PR_SET_PDEATHSIG, SIGKILL);
+ if (ret) {
+ fprintf(stderr, "%s: Child could not set DEATHSIG\n",
+ strerror(errno));
+ return -1;
+ }
+
+ ret = send(sk, &memfd, sizeof(memfd), 0);
+ if (ret != sizeof(memfd)) {
+ fprintf(stderr, "%s: Child failed to send fd number\n",
+ strerror(errno));
+ return -1;
+ }
+
+ /*
+ * The fixture setup is completed at this point. The tests will run.
+ *
+ * This blocking recv enables the parent to message the child.
+ * Either we will read 'P' off of the sk, indicating that we need
+ * to disable ptrace, or we will read a 0, indicating that the other
+ * side has closed the sk. This occurs during fixture teardown time,
+ * indicating that the child should exit.
+ */
+ while ((ret = recv(sk, &buf, sizeof(buf), 0)) > 0) {
+ if (buf == 'P') {
+ ret = prctl(PR_SET_DUMPABLE, 0);
+ if (ret < 0) {
+ fprintf(stderr,
+ "%s: Child failed to disable ptrace\n",
+ strerror(errno));
+ return -1;
+ }
+ } else {
+ fprintf(stderr, "Child received unknown command %c\n",
+ buf);
+ return -1;
+ }
+ ret = send(sk, &buf, sizeof(buf), 0);
+ if (ret != 1) {
+ fprintf(stderr, "%s: Child failed to ack\n",
+ strerror(errno));
+ return -1;
+ }
+ }
+ if (ret < 0) {
+ fprintf(stderr, "%s: Child failed to read from socket\n",
+ strerror(errno));
+ return -1;
+ }
+
+ return 0;
+}
+
+static int child(int sk)
+{
+ int memfd, ret;
+
+ memfd = sys_memfd_create("test", 0);
+ if (memfd < 0) {
+ fprintf(stderr, "%s: Child could not create memfd\n",
+ strerror(errno));
+ ret = -1;
+ } else {
+ ret = __child(sk, memfd);
+ close(memfd);
+ }
+
+ close(sk);
+ return ret;
+}
+
+FIXTURE(child)
+{
+ /*
+ * remote_fd is the number of the FD which we are trying to retrieve
+ * from the child.
+ */
+ int remote_fd;
+ /* pid points to the child which we are fetching FDs from */
+ pid_t pid;
+ /* pidfd is the pidfd of the child */
+ int pidfd;
+ /*
+ * sk is our side of the socketpair used to communicate with the child.
+ * When it is closed, the child will exit.
+ */
+ int sk;
+};
+
+FIXTURE_SETUP(child)
+{
+ int ret, sk_pair[2];
+
+ ASSERT_EQ(0, socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair)) {
+ TH_LOG("%s: failed to create socketpair", strerror(errno));
+ }
+ self->sk = sk_pair[0];
+
+ self->pid = fork();
+ ASSERT_GE(self->pid, 0);
+
+ if (self->pid == 0) {
+ close(sk_pair[0]);
+ if (child(sk_pair[1]))
+ _exit(EXIT_FAILURE);
+ _exit(EXIT_SUCCESS);
+ }
+
+ close(sk_pair[1]);
+
+ self->pidfd = sys_pidfd_open(self->pid, 0);
+ ASSERT_GE(self->pidfd, 0);
+
+ /*
+ * Wait for the child to complete setup. It'll send the remote memfd's
+ * number when ready.
+ */
+ ret = recv(sk_pair[0], &self->remote_fd, sizeof(self->remote_fd), 0);
+ ASSERT_EQ(sizeof(self->remote_fd), ret);
+}
+
+FIXTURE_TEARDOWN(child)
+{
+ EXPECT_EQ(0, close(self->pidfd));
+ EXPECT_EQ(0, close(self->sk));
+
+ EXPECT_EQ(0, wait_for_pid(self->pid));
+}
+
+TEST_F(child, disable_ptrace)
+{
+ int uid, fd;
+ char c;
+
+ /*
+ * Turn into nobody if we're root, to avoid CAP_SYS_PTRACE
+ *
+ * The tests should run in their own process, so even this test fails,
+ * it shouldn't result in subsequent tests failing.
+ */
+ uid = getuid();
+ if (uid == 0)
+ ASSERT_EQ(0, seteuid(UID_NOBODY));
+
+ ASSERT_EQ(1, send(self->sk, "P", 1, 0));
+ ASSERT_EQ(1, recv(self->sk, &c, 1, 0));
+
+ fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0);
+ EXPECT_EQ(-1, fd);
+ EXPECT_EQ(EPERM, errno);
+
+ if (uid == 0)
+ ASSERT_EQ(0, seteuid(0));
+}
+
+TEST_F(child, fetch_fd)
+{
+ int fd, ret;
+
+ fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0);
+ ASSERT_GE(fd, 0);
+
+ EXPECT_EQ(0, sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd));
+
+ ret = fcntl(fd, F_GETFD);
+ ASSERT_GE(ret, 0);
+ EXPECT_GE(ret & FD_CLOEXEC, 0);
+
+ close(fd);
+}
+
+TEST_F(child, test_unknown_fd)
+{
+ int fd;
+
+ fd = sys_pidfd_getfd(self->pidfd, UNKNOWN_FD, 0);
+ EXPECT_EQ(-1, fd) {
+ TH_LOG("getfd succeeded while fetching unknown fd");
+ };
+ EXPECT_EQ(EBADF, errno) {
+ TH_LOG("%s: getfd did not get EBADF", strerror(errno));
+ }
+}
+
+TEST(flags_set)
+{
+ ASSERT_EQ(-1, sys_pidfd_getfd(0, 0, 1));
+ EXPECT_EQ(errno, EINVAL);
+}
+
+#if __NR_pidfd_getfd == -1
+int main(void)
+{
+ fprintf(stderr, "__NR_pidfd_getfd undefined. The pidfd_getfd syscall is unavailable. Test aborting\n");
+ return KSFT_SKIP;
+}
+#else
+TEST_HARNESS_MAIN
+#endif