pidfs, coredump: add PIDFD_INFO_COREDUMP

Extend the PIDFD_INFO_COREDUMP ioctl() with the new PIDFD_INFO_COREDUMP
mask flag. This adds the @coredump_mask field to struct pidfd_info.

When a task coredumps the kernel will provide the following information
to userspace in @coredump_mask:

* PIDFD_COREDUMPED is raised if the task did actually coredump.
* PIDFD_COREDUMP_SKIP is raised if the task skipped coredumping (e.g.,
  undumpable).
* PIDFD_COREDUMP_USER is raised if this is a regular coredump and
  doesn't need special care by the coredump server.
* PIDFD_COREDUMP_ROOT is raised if the generated coredump should be
  treated as sensitive and the coredump server should restrict to the
  generated coredump to sufficiently privileged users.

The kernel guarantees that by the time the connection is made the all
PIDFD_INFO_COREDUMP info is available.

Link: https://lore.kernel.org/20250516-work-coredump-socket-v8-5-664f3caf2516@kernel.org
Acked-by: Luca Boccassi <luca.boccassi@gmail.com>
Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Reviewed-by: Jann Horn <jannh@google.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 55 insertions, 0 deletions

diff --git a/fs/pidfs.c b/fs/pidfs.c
index 3b39e471840b..c0069fd52dd4 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -20,6 +20,7 @@
 #include <linux/time_namespace.h>
 #include <linux/utsname.h>
 #include <net/net_namespace.h>
+#include <linux/coredump.h>
 
 #include "internal.h"
 #include "mount.h"
@@ -33,6 +34,7 @@ static struct kmem_cache *pidfs_cachep __ro_after_init;
 struct pidfs_exit_info {
 	__u64 cgroupid;
 	__s32 exit_code;
+	__u32 coredump_mask;
 };
 
 struct pidfs_inode {
@@ -240,6 +242,22 @@ static inline bool pid_in_current_pidns(const struct pid *pid)
 	return false;
 }
 
+static __u32 pidfs_coredump_mask(unsigned long mm_flags)
+{
+	switch (__get_dumpable(mm_flags)) {
+	case SUID_DUMP_USER:
+		return PIDFD_COREDUMP_USER;
+	case SUID_DUMP_ROOT:
+		return PIDFD_COREDUMP_ROOT;
+	case SUID_DUMP_DISABLE:
+		return PIDFD_COREDUMP_SKIP;
+	default:
+		WARN_ON_ONCE(true);
+	}
+
+	return 0;
+}
+
 static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct pidfd_info __user *uinfo = (struct pidfd_info __user *)arg;
@@ -280,6 +298,11 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 		}
 	}
 
+	if (mask & PIDFD_INFO_COREDUMP) {
+		kinfo.mask |= PIDFD_INFO_COREDUMP;
+		kinfo.coredump_mask = READ_ONCE(pidfs_i(inode)->__pei.coredump_mask);
+	}
+
 	task = get_pid_task(pid, PIDTYPE_PID);
 	if (!task) {
 		/*
@@ -296,6 +319,13 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 	if (!c)
 		return -ESRCH;
 
+	if (!(kinfo.mask & PIDFD_INFO_COREDUMP)) {
+		task_lock(task);
+		if (task->mm)
+			kinfo.coredump_mask = pidfs_coredump_mask(task->mm->flags);
+		task_unlock(task);
+	}
+
 	/* Unconditionally return identifiers and credentials, the rest only on request */
 
 	user_ns = current_user_ns();
@@ -559,6 +589,31 @@ void pidfs_exit(struct task_struct *tsk)
 	}
 }
 
+#ifdef CONFIG_COREDUMP
+void pidfs_coredump(const struct coredump_params *cprm)
+{
+	struct pid *pid = cprm->pid;
+	struct pidfs_exit_info *exit_info;
+	struct dentry *dentry;
+	struct inode *inode;
+	__u32 coredump_mask = 0;
+
+	dentry = pid->stashed;
+	if (WARN_ON_ONCE(!dentry))
+		return;
+
+	inode = d_inode(dentry);
+	exit_info = &pidfs_i(inode)->__pei;
+	/* Note how we were coredumped. */
+	coredump_mask = pidfs_coredump_mask(cprm->mm_flags);
+	/* Note that we actually did coredump. */
+	coredump_mask |= PIDFD_COREDUMPED;
+	/* If coredumping is set to skip we should never end up here. */
+	VFS_WARN_ON_ONCE(coredump_mask & PIDFD_COREDUMP_SKIP);
+	smp_store_release(&exit_info->coredump_mask, coredump_mask);
+}
+#endif
+
 static struct vfsmount *pidfs_mnt __ro_after_init;
 
 /*