Merge: Backport pidfd/pidfs commits to enabling passing pidfd to coredump usermode helper

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1420

JIRA: https://issues.redhat.com/browse/RHEL-113598
CVE: CVE-2025-38306
MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1420

The goal of this MR is to backport enough upstream pidfd/pidfs related
commits to enable systemd to pass pidfd to coredump usermode helper
for fixing CVE-2025-4598.

Signed-off-by: Waiman Long <longman@redhat.com>

Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: Herton R. Krzesinski <herton@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

Documentation/admin-guide/sysctl/kernel.rst

@@ -177,6 +177,7 @@ core_pattern
 	%E		executable path
 	%c		maximum size of core file by resource limit RLIMIT_CORE
 	%C		CPU the task ran on
+	%F		pidfd number
 	%<OTHER>	both are dropped
 	========	==========================================
 

fs/coredump.c

@@ -43,6 +43,8 @@
 #include <linux/timekeeping.h>
 #include <linux/sysctl.h>
 #include <linux/elf.h>
+#include <linux/pidfs.h>
+#include <uapi/linux/pidfd.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -60,6 +62,12 @@ static void free_vma_snapshot(struct coredump_params *cprm);
 #define CORE_FILE_NOTE_SIZE_DEFAULT (4*1024*1024)
 /* Define a reasonable max cap */
 #define CORE_FILE_NOTE_SIZE_MAX (16*1024*1024)
+/*
+ * File descriptor number for the pidfd for the thread-group leader of
+ * the coredumping task installed into the usermode helper's file
+ * descriptor table.
+ */
+#define COREDUMP_PIDFD_NUMBER 3
 
 static int core_uses_pid;
 static unsigned int core_pipe_limit;
@@ -68,9 +76,15 @@ static char core_pattern[CORENAME_MAX_SIZE] = "core";
 static int core_name_size = CORENAME_MAX_SIZE;
 unsigned int core_file_note_size_limit = CORE_FILE_NOTE_SIZE_DEFAULT;
 
+enum coredump_type_t {
+	COREDUMP_FILE = 1,
+	COREDUMP_PIPE = 2,
+};
+
 struct core_name {
 	char *corename;
 	int used, size;
+	enum coredump_type_t core_type;
 };
 
 static int expand_corename(struct core_name *cn, int size)
@@ -210,18 +224,21 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm,
 {
 	const struct cred *cred = current_cred();
 	const char *pat_ptr = core_pattern;
-	int ispipe = (*pat_ptr == '|');
 	bool was_space = false;
 	int pid_in_pattern = 0;
 	int err = 0;
 
 	cn->used = 0;
 	cn->corename = NULL;
+	if (*pat_ptr == '|')
+		cn->core_type = COREDUMP_PIPE;
+	else
+		cn->core_type = COREDUMP_FILE;
 	if (expand_corename(cn, core_name_size))
 		return -ENOMEM;
 	cn->corename[0] = '\0';
 
-	if (ispipe) {
+	if (cn->core_type == COREDUMP_PIPE) {
 		int argvs = sizeof(core_pattern) / 2;
 		(*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL);
 		if (!(*argv))
@@ -239,7 +256,7 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm,
 		 * Split on spaces before doing template expansion so that
 		 * %e and %E don't get split if they have spaces in them
 		 */
-		if (ispipe) {
+		if (cn->core_type == COREDUMP_PIPE) {
 			if (isspace(*pat_ptr)) {
 				if (cn->used != 0)
 					was_space = true;
@@ -339,6 +356,27 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm,
 			case 'C':
 				err = cn_printf(cn, "%d", cprm->cpu);
 				break;
+			/* pidfd number */
+			case 'F': {
+				/*
+				 * Installing a pidfd only makes sense if
+				 * we actually spawn a usermode helper.
+				 */
+				if (cn->core_type != COREDUMP_PIPE)
+					break;
+
+				/*
+				 * Note that we'll install a pidfd for the
+				 * thread-group leader. We know that task
+				 * linkage hasn't been removed yet and even if
+				 * this @current isn't the actual thread-group
+				 * leader we know that the thread-group leader
+				 * cannot be reaped until @current has exited.
+				 */
+				cprm->pid = task_tgid(current);
+				err = cn_printf(cn, "%d", COREDUMP_PIDFD_NUMBER);
+				break;
+			}
 			default:
 				break;
 			}
@@ -355,12 +393,9 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm,
 	 * If core_pattern does not include a %p (as is the default)
 	 * and core_uses_pid is set, then .%pid will be appended to
 	 * the filename. Do not do this for piped commands. */
-	if (!ispipe && !pid_in_pattern && core_uses_pid) {
-		err = cn_printf(cn, ".%d", task_tgid_vnr(current));
-		if (err)
-			return err;
-	}
-	return ispipe;
+	if (cn->core_type == COREDUMP_FILE && !pid_in_pattern && core_uses_pid)
+		return cn_printf(cn, ".%d", task_tgid_vnr(current));
+	return 0;
 }
 
 static int zap_process(struct signal_struct *signal, int exit_code)
@@ -493,7 +528,7 @@ static void wait_for_dump_helpers(struct file *file)
 }
 
 /*
- * umh_pipe_setup
+ * umh_coredump_setup
  * helper function to customize the process used
  * to collect the core in userspace.  Specifically
  * it sets up a pipe and installs it as fd 0 (stdin)
@@ -503,22 +538,46 @@ static void wait_for_dump_helpers(struct file *file)
  * is a special value that we use to trap recursive
  * core dumps
  */
-static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
+static int umh_coredump_setup(struct subprocess_info *info, struct cred *new)
 {
 	struct file *files[2];
 	struct coredump_params *cp = (struct coredump_params *)info->data;
-	int err = create_pipe_files(files, 0);
+	int err;
+
+	if (cp->pid) {
+		struct file *pidfs_file __free(fput) = NULL;
+
+		pidfs_file = pidfs_alloc_file(cp->pid, 0);
+		if (IS_ERR(pidfs_file))
+			return PTR_ERR(pidfs_file);
+
+		/*
+		 * Usermode helpers are childen of either
+		 * system_unbound_wq or of kthreadd. So we know that
+		 * we're starting off with a clean file descriptor
+		 * table. So we should always be able to use
+		 * COREDUMP_PIDFD_NUMBER as our file descriptor value.
+		 */
+		err = replace_fd(COREDUMP_PIDFD_NUMBER, pidfs_file, 0);
+		if (err < 0)
+			return err;
+	}
+
+	err = create_pipe_files(files, 0);
 	if (err)
 		return err;
 
 	cp->file = files[1];
 
 	err = replace_fd(0, files[0], 0);
 	fput(files[0]);
+	if (err < 0)
+		return err;
+
 	/* and disallow core files too */
 	current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};
 
-	return err;
+	return 0;
 }
 
 void do_coredump(const kernel_siginfo_t *siginfo)
@@ -530,7 +589,6 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 	const struct cred *old_cred;
 	struct cred *cred;
 	int retval = 0;
-	int ispipe;
 	size_t *argv = NULL;
 	int argc = 0;
 	/* require nonrelative corefile path and be extra careful */
@@ -579,70 +637,14 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 
 	old_cred = override_creds(cred);
 
-	ispipe = format_corename(&cn, &cprm, &argv, &argc);
-
-	if (ispipe) {
-		int argi;
-		int dump_count;
-		char **helper_argv;
-		struct subprocess_info *sub_info;
-
-		if (ispipe < 0) {
-			coredump_report_failure("format_corename failed, aborting core");
-			goto fail_unlock;
-		}
-
-		if (cprm.limit == 1) {
-			/* See umh_pipe_setup() which sets RLIMIT_CORE = 1.
-			 *
-			 * Normally core limits are irrelevant to pipes, since
-			 * we're not writing to the file system, but we use
-			 * cprm.limit of 1 here as a special value, this is a
-			 * consistent way to catch recursive crashes.
-			 * We can still crash if the core_pattern binary sets
-			 * RLIM_CORE = !1, but it runs as root, and can do
-			 * lots of stupid things.
-			 *
-			 * Note that we use task_tgid_vnr here to grab the pid
-			 * of the process group leader.  That way we get the
-			 * right pid if a thread in a multi-threaded
-			 * core_pattern process dies.
-			 */
-			coredump_report_failure("RLIMIT_CORE is set to 1, aborting core");
-			goto fail_unlock;
-		}
-		cprm.limit = RLIM_INFINITY;
-
-		dump_count = atomic_inc_return(&core_dump_count);
-		if (core_pipe_limit && (core_pipe_limit < dump_count)) {
-			coredump_report_failure("over core_pipe_limit, skipping core dump");
-			goto fail_dropcount;
-		}
-
-		helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv),
-					    GFP_KERNEL);
-		if (!helper_argv) {
-			coredump_report_failure("%s failed to allocate memory", __func__);
-			goto fail_dropcount;
-		}
-		for (argi = 0; argi < argc; argi++)
-			helper_argv[argi] = cn.corename + argv[argi];
-		helper_argv[argi] = NULL;
-
-		retval = -ENOMEM;
-		sub_info = call_usermodehelper_setup(helper_argv[0],
-						helper_argv, NULL, GFP_KERNEL,
-						umh_pipe_setup, NULL, &cprm);
-		if (sub_info)
-			retval = call_usermodehelper_exec(sub_info,
-							  UMH_WAIT_EXEC);
+	retval = format_corename(&cn, &cprm, &argv, &argc);
+	if (retval < 0) {
+		coredump_report_failure("format_corename failed, aborting core");
+		goto fail_unlock;
+	}
 
-		kfree(helper_argv);
-		if (retval) {
-			coredump_report_failure("|%s pipe failed", cn.corename);
-			goto close_fail;
-		}
-	} else {
+	switch (cn.core_type) {
+	case COREDUMP_FILE: {
 		struct mnt_idmap *idmap;
 		struct inode *inode;
 		int open_flags = O_CREAT | O_WRONLY | O_NOFOLLOW |
@@ -736,6 +738,69 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 		if (do_truncate(idmap, cprm.file->f_path.dentry,
 				0, 0, cprm.file))
 			goto close_fail;
+		break;
+	}
+	case COREDUMP_PIPE: {
+		int argi;
+		int dump_count;
+		char **helper_argv;
+		struct subprocess_info *sub_info;
+
+		if (cprm.limit == 1) {
+			/* See umh_coredump_setup() which sets RLIMIT_CORE = 1.
+			 *
+			 * Normally core limits are irrelevant to pipes, since
+			 * we're not writing to the file system, but we use
+			 * cprm.limit of 1 here as a special value, this is a
+			 * consistent way to catch recursive crashes.
+			 * We can still crash if the core_pattern binary sets
+			 * RLIM_CORE = !1, but it runs as root, and can do
+			 * lots of stupid things.
+			 *
+			 * Note that we use task_tgid_vnr here to grab the pid
+			 * of the process group leader.  That way we get the
+			 * right pid if a thread in a multi-threaded
+			 * core_pattern process dies.
+			 */
+			coredump_report_failure("RLIMIT_CORE is set to 1, aborting core");
+			goto fail_unlock;
+		}
+		cprm.limit = RLIM_INFINITY;
+
+		dump_count = atomic_inc_return(&core_dump_count);
+		if (core_pipe_limit && (core_pipe_limit < dump_count)) {
+			coredump_report_failure("over core_pipe_limit, skipping core dump");
+			goto fail_dropcount;
+		}
+
+		helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv),
+					    GFP_KERNEL);
+		if (!helper_argv) {
+			coredump_report_failure("%s failed to allocate memory", __func__);
+			goto fail_dropcount;
+		}
+		for (argi = 0; argi < argc; argi++)
+			helper_argv[argi] = cn.corename + argv[argi];
+		helper_argv[argi] = NULL;
+
+		retval = -ENOMEM;
+		sub_info = call_usermodehelper_setup(helper_argv[0],
+						helper_argv, NULL, GFP_KERNEL,
+						umh_coredump_setup, NULL, &cprm);
+		if (sub_info)
+			retval = call_usermodehelper_exec(sub_info,
+							  UMH_WAIT_EXEC);
+
+		kfree(helper_argv);
+		if (retval) {
+			coredump_report_failure("|%s pipe failed", cn.corename);
+			goto close_fail;
+		}
+		break;
+	}
+	default:
+		WARN_ON_ONCE(true);
+		goto close_fail;
 	}
 
 	/* get us an unshared descriptor table; almost always a no-op */
@@ -770,13 +835,13 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 		file_end_write(cprm.file);
 		free_vma_snapshot(&cprm);
 	}
-	if (ispipe && core_pipe_limit)
+	if ((cn.core_type == COREDUMP_PIPE) && core_pipe_limit)
 		wait_for_dump_helpers(cprm.file);
 close_fail:
 	if (cprm.file)
 		filp_close(cprm.file, NULL);
 fail_dropcount:
-	if (ispipe)
+	if (cn.core_type == COREDUMP_PIPE)
 		atomic_dec(&core_dump_count);
 fail_unlock:
 	kfree(argv);
@@ -799,10 +864,9 @@ static int __dump_emit(struct coredump_params *cprm, const void *addr, int nr)
 	struct file *file = cprm->file;
 	loff_t pos = file->f_pos;
 	ssize_t n;
+
 	if (cprm->written + nr > cprm->limit)
 		return 0;
-
-
 	if (dump_interrupted())
 		return 0;
 	n = __kernel_write(file, addr, nr, &pos);
@@ -819,20 +883,21 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr)
 {
 	static char zeroes[PAGE_SIZE];
 	struct file *file = cprm->file;
+
 	if (file->f_mode & FMODE_LSEEK) {
-		if (dump_interrupted() ||
-		    vfs_llseek(file, nr, SEEK_CUR) < 0)
+		if (dump_interrupted() || vfs_llseek(file, nr, SEEK_CUR) < 0)
 			return 0;
 		cprm->pos += nr;
 		return 1;
-	} else {
-		while (nr > PAGE_SIZE) {
-			if (!__dump_emit(cprm, zeroes, PAGE_SIZE))
-				return 0;
-			nr -= PAGE_SIZE;
-		}
-		return __dump_emit(cprm, zeroes, nr);
 	}
+
+	while (nr > PAGE_SIZE) {
+		if (!__dump_emit(cprm, zeroes, PAGE_SIZE))
+			return 0;
+		nr -= PAGE_SIZE;
+	}
+
+	return __dump_emit(cprm, zeroes, nr);
 }
 
 int dump_emit(struct coredump_params *cprm, const void *addr, int nr)