Merge patch series "coredump: allow for flexible coredump handling"

Christian Brauner <brauner@kernel.org> says:

In addition to the extensive selftests I've already written a
(non-production ready) simple Rust coredump server for this in
userspace:

https://github.com/brauner/dumdum.git

Extend the coredump socket to allow the coredump server to tell the
kernel how to process individual coredumps. This allows for fine-grained
coredump management. Userspace can decide to just let the kernel write
out the coredump, or generate the coredump itself, or just reject it.

When the crashing task connects to the coredump socket the kernel will
send a struct coredump_req to the coredump server. The kernel will set
the size member of struct coredump_req allowing the coredump server how
much data can be read.

The coredump server uses MSG_PEEK to peek the size of struct
coredump_req. If the kernel uses a newer struct coredump_req the
coredump server just reads the size it knows and discard any remaining
bytes in the buffer. If the kernel uses an older struct coredump_req
the coredump server just reads the size the kernel knows.

The returned struct coredump_req will inform the coredump server what
features the kernel supports. The coredump_req->mask member is set to
the currently know features.

The coredump server may only use features whose bits were raised by the
kernel in coredump_req->mask.

In response to a coredump_req from the kernel the coredump server sends
a struct coredump_ack to the kernel. The kernel informs the coredump
server what version of struct coredump_ack it supports by setting struct
coredump_req->size_ack to the size it knows about. The coredump server
may only send as many bytes as coredump_req->size_ack indicates (a
smaller size is fine of course). The coredump server must set
coredump_ack->size accordingly.

The coredump server sets the features it wants to use in struct
coredump_ack->mask. Only bits returned in struct coredump_req->mask may
be used.

In case an invalid struct coredump_ack is sent to the kernel a non-zero
u32 integer is sent indicating the reason for the failure. If it was
successful a zero u32 integer is sent.

In the initial version the following features are supported in
coredump_{req,ack}->mask:

* COREDUMP_KERNEL
  The kernel will write the coredump data to the socket.

* COREDUMP_USERSPACE
  The kernel will not write coredump data but will indicate to the
  parent that a coredump has been generated. This is used when userspace
  generates its own coredumps.

* COREDUMP_REJECT
  The kernel will skip generating a coredump for this task.

* COREDUMP_WAIT
  The kernel will prevent the task from exiting until the coredump
  server has shutdown the socket connection.

The flexible coredump socket can be enabled by using the "@@" prefix
instead of the single "@" prefix for the regular coredump socket:

  @@/run/systemd/coredump.socket

will enable flexible coredump handling. Current kernels already enforce
that "@" must be followed by "/" and will reject anything else. So
extending this is backward and forward compatible.

Link: https://lore.kernel.org/20250603-work-coredump-socket-protocol-v2-0-05a5f0c18ecc@kernel.org

* patches from https://lore.kernel.org/20250603-work-coredump-socket-protocol-v2-0-05a5f0c18ecc@kernel.org:
  selftests/coredump: add coredump server selftests
  tools: add coredump.h header
  selftests/coredump: cleanup coredump tests
  selftests/coredump: fix build
  coredump: allow for flexible coredump handling

Signed-off-by: Christian Brauner <brauner@kernel.org>

6 files changed, 1807 insertions, 270 deletions

diff --git a/fs/coredump.c b/fs/coredump.c
index f217ebf2b3b6..b3eaa8c27ced 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -51,6 +51,7 @@
 #include <net/sock.h>
 #include <uapi/linux/pidfd.h>
 #include <uapi/linux/un.h>
+#include <uapi/linux/coredump.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -83,15 +84,17 @@ 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,
-	COREDUMP_SOCK = 3,
+	COREDUMP_FILE		= 1,
+	COREDUMP_PIPE		= 2,
+	COREDUMP_SOCK		= 3,
+	COREDUMP_SOCK_REQ	= 4,
 };
 
 struct core_name {
 	char *corename;
 	int used, size;
 	enum coredump_type_t core_type;
+	u64 mask;
 };
 
 static int expand_corename(struct core_name *cn, int size)
@@ -235,6 +238,9 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm,
 	int pid_in_pattern = 0;
 	int err = 0;
 
+	cn->mask = COREDUMP_KERNEL;
+	if (core_pipe_limit)
+		cn->mask |= COREDUMP_WAIT;
 	cn->used = 0;
 	cn->corename = NULL;
 	if (*pat_ptr == '|')
@@ -264,6 +270,13 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm,
 		pat_ptr++;
 		if (!(*pat_ptr))
 			return -ENOMEM;
+		if (*pat_ptr == '@') {
+			pat_ptr++;
+			if (!(*pat_ptr))
+				return -ENOMEM;
+
+			cn->core_type = COREDUMP_SOCK_REQ;
+		}
 
 		err = cn_printf(cn, "%s", pat_ptr);
 		if (err)
@@ -632,6 +645,135 @@ static int umh_coredump_setup(struct subprocess_info *info, struct cred *new)
 	return 0;
 }
 
+#ifdef CONFIG_UNIX
+static inline bool coredump_sock_recv(struct file *file, struct coredump_ack *ack, size_t size, int flags)
+{
+	struct msghdr msg = {};
+	struct kvec iov = { .iov_base = ack, .iov_len = size };
+	ssize_t ret;
+
+	memset(ack, 0, size);
+	ret = kernel_recvmsg(sock_from_file(file), &msg, &iov, 1, size, flags);
+	return ret == size;
+}
+
+static inline bool coredump_sock_send(struct file *file, struct coredump_req *req)
+{
+	struct msghdr msg = { .msg_flags = MSG_NOSIGNAL };
+	struct kvec iov = { .iov_base = req, .iov_len = sizeof(*req) };
+	ssize_t ret;
+
+	ret = kernel_sendmsg(sock_from_file(file), &msg, &iov, 1, sizeof(*req));
+	return ret == sizeof(*req);
+}
+
+static_assert(sizeof(enum coredump_mark) == sizeof(__u32));
+
+static inline bool coredump_sock_mark(struct file *file, enum coredump_mark mark)
+{
+	struct msghdr msg = { .msg_flags = MSG_NOSIGNAL };
+	struct kvec iov = { .iov_base = &mark, .iov_len = sizeof(mark) };
+	ssize_t ret;
+
+	ret = kernel_sendmsg(sock_from_file(file), &msg, &iov, 1, sizeof(mark));
+	return ret == sizeof(mark);
+}
+
+static inline void coredump_sock_wait(struct file *file)
+{
+	ssize_t n;
+
+	/*
+	 * We use a simple read to wait for the coredump processing to
+	 * finish. Either the socket is closed or we get sent unexpected
+	 * data. In both cases, we're done.
+	 */
+	n = __kernel_read(file, &(char){ 0 }, 1, NULL);
+	if (n > 0)
+		coredump_report_failure("Coredump socket had unexpected data");
+	else if (n < 0)
+		coredump_report_failure("Coredump socket failed");
+}
+
+static inline void coredump_sock_shutdown(struct file *file)
+{
+	struct socket *socket;
+
+	socket = sock_from_file(file);
+	if (!socket)
+		return;
+
+	/* Let userspace know we're done processing the coredump. */
+	kernel_sock_shutdown(socket, SHUT_WR);
+}
+
+static bool coredump_request(struct core_name *cn, struct coredump_params *cprm)
+{
+	struct coredump_req req = {
+		.size		= sizeof(struct coredump_req),
+		.mask		= COREDUMP_KERNEL | COREDUMP_USERSPACE |
+				  COREDUMP_REJECT | COREDUMP_WAIT,
+		.size_ack	= sizeof(struct coredump_ack),
+	};
+	struct coredump_ack ack = {};
+	ssize_t usize;
+
+	if (cn->core_type != COREDUMP_SOCK_REQ)
+		return true;
+
+	/* Let userspace know what we support. */
+	if (!coredump_sock_send(cprm->file, &req))
+		return false;
+
+	/* Peek the size of the coredump_ack. */
+	if (!coredump_sock_recv(cprm->file, &ack, sizeof(ack.size),
+				MSG_PEEK | MSG_WAITALL))
+		return false;
+
+	/* Refuse unknown coredump_ack sizes. */
+	usize = ack.size;
+	if (usize < COREDUMP_ACK_SIZE_VER0) {
+		coredump_sock_mark(cprm->file, COREDUMP_MARK_MINSIZE);
+		return false;
+	}
+
+	if (usize > sizeof(ack)) {
+		coredump_sock_mark(cprm->file, COREDUMP_MARK_MAXSIZE);
+		return false;
+	}
+
+	/* Now retrieve the coredump_ack. */
+	if (!coredump_sock_recv(cprm->file, &ack, usize, MSG_WAITALL))
+		return false;
+	if (ack.size != usize)
+		return false;
+
+	/* Refuse unknown coredump_ack flags. */
+	if (ack.mask & ~req.mask) {
+		coredump_sock_mark(cprm->file, COREDUMP_MARK_UNSUPPORTED);
+		return false;
+	}
+
+	/* Refuse mutually exclusive options. */
+	if (hweight64(ack.mask & (COREDUMP_USERSPACE | COREDUMP_KERNEL |
+				  COREDUMP_REJECT)) != 1) {
+		coredump_sock_mark(cprm->file, COREDUMP_MARK_CONFLICTING);
+		return false;
+	}
+
+	if (ack.spare) {
+		coredump_sock_mark(cprm->file, COREDUMP_MARK_UNSUPPORTED);
+		return false;
+	}
+
+	cn->mask = ack.mask;
+	return coredump_sock_mark(cprm->file, COREDUMP_MARK_REQACK);
+}
+#else
+static inline void coredump_sock_wait(struct file *file) { }
+static inline void coredump_sock_shutdown(struct file *file) { }
+#endif
+
 void do_coredump(const kernel_siginfo_t *siginfo)
 {
 	struct core_state core_state;
@@ -850,6 +992,8 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 		}
 		break;
 	}
+	case COREDUMP_SOCK_REQ:
+		fallthrough;
 	case COREDUMP_SOCK: {
 #ifdef CONFIG_UNIX
 		struct file *file __free(fput) = NULL;
@@ -918,6 +1062,9 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 
 		cprm.limit = RLIM_INFINITY;
 		cprm.file = no_free_ptr(file);
+
+		if (!coredump_request(&cn, &cprm))
+			goto close_fail;
 #else
 		coredump_report_failure("Core dump socket support %s disabled", cn.corename);
 		goto close_fail;
@@ -929,12 +1076,17 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 		goto close_fail;
 	}
 
+	/* Don't even generate the coredump. */
+	if (cn.mask & COREDUMP_REJECT)
+		goto close_fail;
+
 	/* get us an unshared descriptor table; almost always a no-op */
 	/* The cell spufs coredump code reads the file descriptor tables */
 	retval = unshare_files();
 	if (retval)
 		goto close_fail;
-	if (!dump_interrupted()) {
+
+	if ((cn.mask & COREDUMP_KERNEL) && !dump_interrupted()) {
 		/*
 		 * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would
 		 * have this set to NULL.
@@ -962,38 +1114,27 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 		free_vma_snapshot(&cprm);
 	}
 
-#ifdef CONFIG_UNIX
-	/* Let userspace know we're done processing the coredump. */
-	if (sock_from_file(cprm.file))
-		kernel_sock_shutdown(sock_from_file(cprm.file), SHUT_WR);
-#endif
+	coredump_sock_shutdown(cprm.file);
+
+	/* Let the parent know that a coredump was generated. */
+	if (cn.mask & COREDUMP_USERSPACE)
+		core_dumped = true;
 
 	/*
 	 * When core_pipe_limit is set we wait for the coredump server
 	 * or usermodehelper to finish before exiting so it can e.g.,
 	 * inspect /proc/<pid>.
 	 */
-	if (core_pipe_limit) {
+	if (cn.mask & COREDUMP_WAIT) {
 		switch (cn.core_type) {
 		case COREDUMP_PIPE:
 			wait_for_dump_helpers(cprm.file);
 			break;
-#ifdef CONFIG_UNIX
-		case COREDUMP_SOCK: {
-			ssize_t n;
-
-			/*
-			 * We use a simple read to wait for the coredump
-			 * processing to finish. Either the socket is
-			 * closed or we get sent unexpected data. In
-			 * both cases, we're done.
-			 */
-			n = __kernel_read(cprm.file, &(char){ 0 }, 1, NULL);
-			if (n != 0)
-				coredump_report_failure("Unexpected data on coredump socket");
+		case COREDUMP_SOCK_REQ:
+			fallthrough;
+		case COREDUMP_SOCK:
+			coredump_sock_wait(cprm.file);
 			break;
-		}
-#endif
 		default:
 			break;
 		}
@@ -1249,8 +1390,8 @@ static inline bool check_coredump_socket(void)
 	if (current->nsproxy->mnt_ns != init_task.nsproxy->mnt_ns)
 		return false;
 
-	/* Must be an absolute path. */
-	if (*(core_pattern + 1) != '/')
+	/* Must be an absolute path or the socket request. */
+	if (*(core_pattern + 1) != '/' && *(core_pattern + 1) != '@')
 		return false;
 
 	return true;
diff --git a/include/uapi/linux/coredump.h b/include/uapi/linux/coredump.h
new file mode 100644
index 000000000000..dc3789b78af0
--- /dev/null
+++ b/include/uapi/linux/coredump.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_COREDUMP_H
+#define _UAPI_LINUX_COREDUMP_H
+
+#include <linux/types.h>
+
+/**
+ * coredump_{req,ack} flags
+ * @COREDUMP_KERNEL: kernel writes coredump
+ * @COREDUMP_USERSPACE: userspace writes coredump
+ * @COREDUMP_REJECT: don't generate coredump
+ * @COREDUMP_WAIT: wait for coredump server
+ */
+enum {
+	COREDUMP_KERNEL		= (1ULL << 0),
+	COREDUMP_USERSPACE	= (1ULL << 1),
+	COREDUMP_REJECT		= (1ULL << 2),
+	COREDUMP_WAIT		= (1ULL << 3),
+};
+
+/**
+ * struct coredump_req - message kernel sends to userspace
+ * @size: size of struct coredump_req
+ * @size_ack: known size of struct coredump_ack on this kernel
+ * @mask: supported features
+ *
+ * When a coredump happens the kernel will connect to the coredump
+ * socket and send a coredump request to the coredump server. The @size
+ * member is set to the size of struct coredump_req and provides a hint
+ * to userspace how much data can be read. Userspace may use MSG_PEEK to
+ * peek the size of struct coredump_req and then choose to consume it in
+ * one go. Userspace may also simply read a COREDUMP_ACK_SIZE_VER0
+ * request. If the size the kernel sends is larger userspace simply
+ * discards any remaining data.
+ *
+ * The coredump_req->mask member is set to the currently know features.
+ * Userspace may only set coredump_ack->mask to the bits raised by the
+ * kernel in coredump_req->mask.
+ *
+ * The coredump_req->size_ack member is set by the kernel to the size of
+ * struct coredump_ack the kernel knows. Userspace may only send up to
+ * coredump_req->size_ack bytes to the kernel and must set
+ * coredump_ack->size accordingly.
+ */
+struct coredump_req {
+	__u32 size;
+	__u32 size_ack;
+	__u64 mask;
+};
+
+enum {
+	COREDUMP_REQ_SIZE_VER0 = 16U, /* size of first published struct */
+};
+
+/**
+ * struct coredump_ack - message userspace sends to kernel
+ * @size: size of the struct
+ * @spare: unused
+ * @mask: features kernel is supposed to use
+ *
+ * The @size member must be set to the size of struct coredump_ack. It
+ * may never exceed what the kernel returned in coredump_req->size_ack
+ * but it may of course be smaller (>= COREDUMP_ACK_SIZE_VER0 and <=
+ * coredump_req->size_ack).
+ *
+ * The @mask member must be set to the features the coredump server
+ * wants the kernel to use. Only bits the kernel returned in
+ * coredump_req->mask may be set.
+ */
+struct coredump_ack {
+	__u32 size;
+	__u32 spare;
+	__u64 mask;
+};
+
+enum {
+	COREDUMP_ACK_SIZE_VER0 = 16U, /* size of first published struct */
+};
+
+/**
+ * enum coredump_mark - Markers for the coredump socket
+ *
+ * The kernel will place a single byte on the coredump socket. The
+ * markers notify userspace whether the coredump ack succeeded or
+ * failed.
+ *
+ * @COREDUMP_MARK_MINSIZE: the provided coredump_ack size was too small
+ * @COREDUMP_MARK_MAXSIZE: the provided coredump_ack size was too big
+ * @COREDUMP_MARK_UNSUPPORTED: the provided coredump_ack mask was invalid
+ * @COREDUMP_MARK_CONFLICTING: the provided coredump_ack mask has conflicting options
+ * @COREDUMP_MARK_REQACK: the coredump request and ack was successful
+ * @__COREDUMP_MARK_MAX: the maximum coredump mark value
+ */
+enum coredump_mark {
+	COREDUMP_MARK_REQACK		= 0U,
+	COREDUMP_MARK_MINSIZE		= 1U,
+	COREDUMP_MARK_MAXSIZE		= 2U,
+	COREDUMP_MARK_UNSUPPORTED	= 3U,
+	COREDUMP_MARK_CONFLICTING	= 4U,
+	__COREDUMP_MARK_MAX		= (1U << 31),
+};
+
+#endif /* _UAPI_LINUX_COREDUMP_H */
diff --git a/tools/include/uapi/linux/coredump.h b/tools/include/uapi/linux/coredump.h
new file mode 100644
index 000000000000..dc3789b78af0
--- /dev/null
+++ b/tools/include/uapi/linux/coredump.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_COREDUMP_H
+#define _UAPI_LINUX_COREDUMP_H
+
+#include <linux/types.h>
+
+/**
+ * coredump_{req,ack} flags
+ * @COREDUMP_KERNEL: kernel writes coredump
+ * @COREDUMP_USERSPACE: userspace writes coredump
+ * @COREDUMP_REJECT: don't generate coredump
+ * @COREDUMP_WAIT: wait for coredump server
+ */
+enum {
+	COREDUMP_KERNEL		= (1ULL << 0),
+	COREDUMP_USERSPACE	= (1ULL << 1),
+	COREDUMP_REJECT		= (1ULL << 2),
+	COREDUMP_WAIT		= (1ULL << 3),
+};
+
+/**
+ * struct coredump_req - message kernel sends to userspace
+ * @size: size of struct coredump_req
+ * @size_ack: known size of struct coredump_ack on this kernel
+ * @mask: supported features
+ *
+ * When a coredump happens the kernel will connect to the coredump
+ * socket and send a coredump request to the coredump server. The @size
+ * member is set to the size of struct coredump_req and provides a hint
+ * to userspace how much data can be read. Userspace may use MSG_PEEK to
+ * peek the size of struct coredump_req and then choose to consume it in
+ * one go. Userspace may also simply read a COREDUMP_ACK_SIZE_VER0
+ * request. If the size the kernel sends is larger userspace simply
+ * discards any remaining data.
+ *
+ * The coredump_req->mask member is set to the currently know features.
+ * Userspace may only set coredump_ack->mask to the bits raised by the
+ * kernel in coredump_req->mask.
+ *
+ * The coredump_req->size_ack member is set by the kernel to the size of
+ * struct coredump_ack the kernel knows. Userspace may only send up to
+ * coredump_req->size_ack bytes to the kernel and must set
+ * coredump_ack->size accordingly.
+ */
+struct coredump_req {
+	__u32 size;
+	__u32 size_ack;
+	__u64 mask;
+};
+
+enum {
+	COREDUMP_REQ_SIZE_VER0 = 16U, /* size of first published struct */
+};
+
+/**
+ * struct coredump_ack - message userspace sends to kernel
+ * @size: size of the struct
+ * @spare: unused
+ * @mask: features kernel is supposed to use
+ *
+ * The @size member must be set to the size of struct coredump_ack. It
+ * may never exceed what the kernel returned in coredump_req->size_ack
+ * but it may of course be smaller (>= COREDUMP_ACK_SIZE_VER0 and <=
+ * coredump_req->size_ack).
+ *
+ * The @mask member must be set to the features the coredump server
+ * wants the kernel to use. Only bits the kernel returned in
+ * coredump_req->mask may be set.
+ */
+struct coredump_ack {
+	__u32 size;
+	__u32 spare;
+	__u64 mask;
+};
+
+enum {
+	COREDUMP_ACK_SIZE_VER0 = 16U, /* size of first published struct */
+};
+
+/**
+ * enum coredump_mark - Markers for the coredump socket
+ *
+ * The kernel will place a single byte on the coredump socket. The
+ * markers notify userspace whether the coredump ack succeeded or
+ * failed.
+ *
+ * @COREDUMP_MARK_MINSIZE: the provided coredump_ack size was too small
+ * @COREDUMP_MARK_MAXSIZE: the provided coredump_ack size was too big
+ * @COREDUMP_MARK_UNSUPPORTED: the provided coredump_ack mask was invalid
+ * @COREDUMP_MARK_CONFLICTING: the provided coredump_ack mask has conflicting options
+ * @COREDUMP_MARK_REQACK: the coredump request and ack was successful
+ * @__COREDUMP_MARK_MAX: the maximum coredump mark value
+ */
+enum coredump_mark {
+	COREDUMP_MARK_REQACK		= 0U,
+	COREDUMP_MARK_MINSIZE		= 1U,
+	COREDUMP_MARK_MAXSIZE		= 2U,
+	COREDUMP_MARK_UNSUPPORTED	= 3U,
+	COREDUMP_MARK_CONFLICTING	= 4U,
+	__COREDUMP_MARK_MAX		= (1U << 31),
+};
+
+#endif /* _UAPI_LINUX_COREDUMP_H */
diff --git a/tools/testing/selftests/coredump/Makefile b/tools/testing/selftests/coredump/Makefile
index ed210037b29d..77b3665c73c7 100644
--- a/tools/testing/selftests/coredump/Makefile
+++ b/tools/testing/selftests/coredump/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-CFLAGS = $(KHDR_INCLUDES)
+CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
 
 TEST_GEN_PROGS := stackdump_test
 TEST_FILES := stackdump
diff --git a/tools/testing/selftests/coredump/config b/tools/testing/selftests/coredump/config
new file mode 100644
index 000000000000..a05ef112b4f9
--- /dev/null
+++ b/tools/testing/selftests/coredump/config
@@ -0,0 +1,3 @@
+CONFIG_COREDUMP=y
+CONFIG_NET=y
+CONFIG_UNIX=y
diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c
index 9984413be9f0..9a789156f27e 100644
--- a/tools/testing/selftests/coredump/stackdump_test.c
+++ b/tools/testing/selftests/coredump/stackdump_test.c
@@ -1,12 +1,18 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <assert.h>
 #include <fcntl.h>
 #include <inttypes.h>
 #include <libgen.h>
+#include <limits.h>
+#include <linux/coredump.h>
+#include <linux/fs.h>
 #include <linux/limits.h>
 #include <pthread.h>
 #include <string.h>
 #include <sys/mount.h>
+#include <poll.h>
+#include <sys/epoll.h>
 #include <sys/resource.h>
 #include <sys/stat.h>
 #include <sys/socket.h>
@@ -14,16 +20,23 @@
 #include <unistd.h>
 
 #include "../kselftest_harness.h"
+#include "../filesystems/wrappers.h"
 #include "../pidfd/pidfd.h"
 
 #define STACKDUMP_FILE "stack_values"
 #define STACKDUMP_SCRIPT "stackdump"
 #define NUM_THREAD_SPAWN 128
 
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
 static void *do_nothing(void *)
 {
 	while (1)
 		pause();
+
+	return NULL;
 }
 
 static void crashing_child(void)
@@ -42,16 +55,32 @@ FIXTURE(coredump)
 {
 	char original_core_pattern[256];
 	pid_t pid_coredump_server;
+	int fd_tmpfs_detached;
 };
 
+static int create_detached_tmpfs(void)
+{
+	int fd_context, fd_tmpfs;
+
+	fd_context = sys_fsopen("tmpfs", 0);
+	if (fd_context < 0)
+		return -1;
+
+	if (sys_fsconfig(fd_context, FSCONFIG_CMD_CREATE, NULL, NULL, 0) < 0)
+		return -1;
+
+	fd_tmpfs = sys_fsmount(fd_context, 0, 0);
+	close(fd_context);
+	return fd_tmpfs;
+}
+
 FIXTURE_SETUP(coredump)
 {
-	char buf[PATH_MAX];
 	FILE *file;
-	char *dir;
 	int ret;
 
 	self->pid_coredump_server = -ESRCH;
+	self->fd_tmpfs_detached = -1;
 	file = fopen("/proc/sys/kernel/core_pattern", "r");
 	ASSERT_NE(NULL, file);
 
@@ -60,6 +89,8 @@ FIXTURE_SETUP(coredump)
 	ASSERT_LT(ret, sizeof(self->original_core_pattern));
 
 	self->original_core_pattern[ret] = '\0';
+	self->fd_tmpfs_detached = create_detached_tmpfs();
+	ASSERT_GE(self->fd_tmpfs_detached, 0);
 
 	ret = fclose(file);
 	ASSERT_EQ(0, ret);
@@ -98,6 +129,15 @@ FIXTURE_TEARDOWN(coredump)
 		goto fail;
 	}
 
+	if (self->fd_tmpfs_detached >= 0) {
+		ret = close(self->fd_tmpfs_detached);
+		if (ret < 0) {
+			reason = "Unable to close detached tmpfs";
+			goto fail;
+		}
+		self->fd_tmpfs_detached = -1;
+	}
+
 	return;
 fail:
 	/* This should never happen */
@@ -106,11 +146,10 @@ fail:
 
 TEST_F_TIMEOUT(coredump, stackdump, 120)
 {
-	struct sigaction action = {};
 	unsigned long long stack;
 	char *test_dir, *line;
 	size_t line_length;
-	char buf[PATH_MAX];
+	char buf[PAGE_SIZE];
 	int ret, i, status;
 	FILE *file;
 	pid_t pid;
@@ -169,153 +208,163 @@ TEST_F_TIMEOUT(coredump, stackdump, 120)
 	fclose(file);
 }
 
-TEST_F(coredump, socket)
+static int create_and_listen_unix_socket(const char *path)
+{
+	struct sockaddr_un addr = {
+		.sun_family = AF_UNIX,
+	};
+	assert(strlen(path) < sizeof(addr.sun_path) - 1);
+	strncpy(addr.sun_path, path, sizeof(addr.sun_path) - 1);
+	size_t addr_len =
+		offsetof(struct sockaddr_un, sun_path) + strlen(path) + 1;
+	int fd, ret;
+
+	fd = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+	if (fd < 0)
+		goto out;
+
+	ret = bind(fd, (const struct sockaddr *)&addr, addr_len);
+	if (ret < 0)
+		goto out;
+
+	ret = listen(fd, 128);
+	if (ret < 0)
+		goto out;
+
+	return fd;
+
+out:
+	if (fd >= 0)
+		close(fd);
+	return -1;
+}
+
+static bool set_core_pattern(const char *pattern)
 {
-	int fd, pidfd, ret, status;
 	FILE *file;
+	int ret;
+
+	file = fopen("/proc/sys/kernel/core_pattern", "w");
+	if (!file)
+		return false;
+
+	ret = fprintf(file, "%s", pattern);
+	fclose(file);
+
+	return ret == strlen(pattern);
+}
+
+static int get_peer_pidfd(int fd)
+{
+	int fd_peer_pidfd;
+	socklen_t fd_peer_pidfd_len = sizeof(fd_peer_pidfd);
+	int ret = getsockopt(fd, SOL_SOCKET, SO_PEERPIDFD, &fd_peer_pidfd,
+			     &fd_peer_pidfd_len);
+	if (ret < 0) {
+		fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n");
+		return -1;
+	}
+	return fd_peer_pidfd;
+}
+
+static bool get_pidfd_info(int fd_peer_pidfd, struct pidfd_info *info)
+{
+	memset(info, 0, sizeof(*info));
+	info->mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+	return ioctl(fd_peer_pidfd, PIDFD_GET_INFO, info) == 0;
+}
+
+static void
+wait_and_check_coredump_server(pid_t pid_coredump_server,
+			       struct __test_metadata *const _metadata,
+			       FIXTURE_DATA(coredump)* self)
+{
+	int status;
+	waitpid(pid_coredump_server, &status, 0);
+	self->pid_coredump_server = -ESRCH;
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+}
+
+TEST_F(coredump, socket)
+{
+	int pidfd, ret, status;
 	pid_t pid, pid_coredump_server;
 	struct stat st;
-	char core_file[PATH_MAX];
 	struct pidfd_info info = {};
 	int ipc_sockets[2];
 	char c;
-	const struct sockaddr_un coredump_sk = {
-		.sun_family = AF_UNIX,
-		.sun_path = "/tmp/coredump.socket",
-	};
-	size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) +
-				 sizeof("/tmp/coredump.socket");
+
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
 
 	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
 	ASSERT_EQ(ret, 0);
 
-	file = fopen("/proc/sys/kernel/core_pattern", "w");
-	ASSERT_NE(file, NULL);
-
-	ret = fprintf(file, "@/tmp/coredump.socket");
-	ASSERT_EQ(ret, strlen("@/tmp/coredump.socket"));
-	ASSERT_EQ(fclose(file), 0);
-
 	pid_coredump_server = fork();
 	ASSERT_GE(pid_coredump_server, 0);
 	if (pid_coredump_server == 0) {
-		int fd_server, fd_coredump, fd_peer_pidfd, fd_core_file;
-		socklen_t fd_peer_pidfd_len;
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+		int exit_code = EXIT_FAILURE;
 
 		close(ipc_sockets[0]);
 
-		fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
 		if (fd_server < 0)
-			_exit(EXIT_FAILURE);
-
-		ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to bind coredump socket\n");
-			close(fd_server);
-			close(ipc_sockets[1]);
-			_exit(EXIT_FAILURE);
-		}
-
-		ret = listen(fd_server, 1);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to listen on coredump socket\n");
-			close(fd_server);
-			close(ipc_sockets[1]);
-			_exit(EXIT_FAILURE);
-		}
+			goto out;
 
-		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
-			close(fd_server);
-			close(ipc_sockets[1]);
-			_exit(EXIT_FAILURE);
-		}
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
 
 		close(ipc_sockets[1]);
 
 		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
-		if (fd_coredump < 0) {
-			fprintf(stderr, "Failed to accept coredump socket connection\n");
-			close(fd_server);
-			_exit(EXIT_FAILURE);
-		}
+		if (fd_coredump < 0)
+			goto out;
 
-		fd_peer_pidfd_len = sizeof(fd_peer_pidfd);
-		ret = getsockopt(fd_coredump, SOL_SOCKET, SO_PEERPIDFD,
-				 &fd_peer_pidfd, &fd_peer_pidfd_len);
-		if (ret < 0) {
-			fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n");
-			close(fd_coredump);
-			close(fd_server);
-			_exit(EXIT_FAILURE);
-		}
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0)
+			goto out;
 
-		memset(&info, 0, sizeof(info));
-		info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
-		ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, &info);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to retrieve pidfd info from peer pidfd for coredump socket connection\n");
-			close(fd_coredump);
-			close(fd_server);
-			close(fd_peer_pidfd);
-			_exit(EXIT_FAILURE);
-		}
+		if (!get_pidfd_info(fd_peer_pidfd, &info))
+			goto out;
 
-		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
-			fprintf(stderr, "Missing coredump information from coredumping task\n");
-			close(fd_coredump);
-			close(fd_server);
-			close(fd_peer_pidfd);
-			_exit(EXIT_FAILURE);
-		}
+		if (!(info.mask & PIDFD_INFO_COREDUMP))
+			goto out;
 
-		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
-			fprintf(stderr, "Received connection from non-coredumping task\n");
-			close(fd_coredump);
-			close(fd_server);
-			close(fd_peer_pidfd);
-			_exit(EXIT_FAILURE);
-		}
+		if (!(info.coredump_mask & PIDFD_COREDUMPED))
+			goto out;
 
 		fd_core_file = creat("/tmp/coredump.file", 0644);
-		if (fd_core_file < 0) {
-			fprintf(stderr, "Failed to create coredump file\n");
-			close(fd_coredump);
-			close(fd_server);
-			close(fd_peer_pidfd);
-			_exit(EXIT_FAILURE);
-		}
+		if (fd_core_file < 0)
+			goto out;
 
 		for (;;) {
 			char buffer[4096];
 			ssize_t bytes_read, bytes_write;
 
 			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
-			if (bytes_read < 0) {
-				close(fd_coredump);
-				close(fd_server);
-				close(fd_peer_pidfd);
-				close(fd_core_file);
-				_exit(EXIT_FAILURE);
-			}
+			if (bytes_read < 0)
+				goto out;
 
 			if (bytes_read == 0)
 				break;
 
 			bytes_write = write(fd_core_file, buffer, bytes_read);
-			if (bytes_read != bytes_write) {
-				close(fd_coredump);
-				close(fd_server);
-				close(fd_peer_pidfd);
-				close(fd_core_file);
-				_exit(EXIT_FAILURE);
-			}
+			if (bytes_read != bytes_write)
+				goto out;
 		}
 
-		close(fd_coredump);
-		close(fd_server);
-		close(fd_peer_pidfd);
-		close(fd_core_file);
-		_exit(EXIT_SUCCESS);
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_core_file >= 0)
+			close(fd_core_file);
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
 	}
 	self->pid_coredump_server = pid_coredump_server;
 
@@ -335,48 +384,27 @@ TEST_F(coredump, socket)
 	ASSERT_TRUE(WIFSIGNALED(status));
 	ASSERT_TRUE(WCOREDUMP(status));
 
-	info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
-	ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0);
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
 	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
 	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
 
-	waitpid(pid_coredump_server, &status, 0);
-	self->pid_coredump_server = -ESRCH;
-	ASSERT_TRUE(WIFEXITED(status));
-	ASSERT_EQ(WEXITSTATUS(status), 0);
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
 
 	ASSERT_EQ(stat("/tmp/coredump.file", &st), 0);
 	ASSERT_GT(st.st_size, 0);
-	/*
-	 * We should somehow validate the produced core file.
-	 * For now just allow for visual inspection
-	 */
 	system("file /tmp/coredump.file");
 }
 
 TEST_F(coredump, socket_detect_userspace_client)
 {
-	int fd, pidfd, ret, status;
-	FILE *file;
+	int pidfd, ret, status;
 	pid_t pid, pid_coredump_server;
 	struct stat st;
-	char core_file[PATH_MAX];
 	struct pidfd_info info = {};
 	int ipc_sockets[2];
 	char c;
-	const struct sockaddr_un coredump_sk = {
-		.sun_family = AF_UNIX,
-		.sun_path = "/tmp/coredump.socket",
-	};
-	size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) +
-				 sizeof("/tmp/coredump.socket");
 
-	file = fopen("/proc/sys/kernel/core_pattern", "w");
-	ASSERT_NE(file, NULL);
-
-	ret = fprintf(file, "@/tmp/coredump.socket");
-	ASSERT_EQ(ret, strlen("@/tmp/coredump.socket"));
-	ASSERT_EQ(fclose(file), 0);
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
 
 	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
 	ASSERT_EQ(ret, 0);
@@ -384,88 +412,46 @@ TEST_F(coredump, socket_detect_userspace_client)
 	pid_coredump_server = fork();
 	ASSERT_GE(pid_coredump_server, 0);
 	if (pid_coredump_server == 0) {
-		int fd_server, fd_coredump, fd_peer_pidfd, fd_core_file;
-		socklen_t fd_peer_pidfd_len;
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
 
 		close(ipc_sockets[0]);
 
-		fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
 		if (fd_server < 0)
-			_exit(EXIT_FAILURE);
+			goto out;
 
-		ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to bind coredump socket\n");
-			close(fd_server);
-			close(ipc_sockets[1]);
-			_exit(EXIT_FAILURE);
-		}
-
-		ret = listen(fd_server, 1);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to listen on coredump socket\n");
-			close(fd_server);
-			close(ipc_sockets[1]);
-			_exit(EXIT_FAILURE);
-		}
-
-		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
-			close(fd_server);
-			close(ipc_sockets[1]);
-			_exit(EXIT_FAILURE);
-		}
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
 
 		close(ipc_sockets[1]);
 
 		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
-		if (fd_coredump < 0) {
-			fprintf(stderr, "Failed to accept coredump socket connection\n");
-			close(fd_server);
-			_exit(EXIT_FAILURE);
-		}
+		if (fd_coredump < 0)
+			goto out;
 
-		fd_peer_pidfd_len = sizeof(fd_peer_pidfd);
-		ret = getsockopt(fd_coredump, SOL_SOCKET, SO_PEERPIDFD,
-				 &fd_peer_pidfd, &fd_peer_pidfd_len);
-		if (ret < 0) {
-			fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n");
-			close(fd_coredump);
-			close(fd_server);
-			_exit(EXIT_FAILURE);
-		}
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0)
+			goto out;
 
-		memset(&info, 0, sizeof(info));
-		info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
-		ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, &info);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to retrieve pidfd info from peer pidfd for coredump socket connection\n");
-			close(fd_coredump);
-			close(fd_server);
-			close(fd_peer_pidfd);
-			_exit(EXIT_FAILURE);
-		}
+		if (!get_pidfd_info(fd_peer_pidfd, &info))
+			goto out;
 
-		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
-			fprintf(stderr, "Missing coredump information from coredumping task\n");
-			close(fd_coredump);
-			close(fd_server);
-			close(fd_peer_pidfd);
-			_exit(EXIT_FAILURE);
-		}
+		if (!(info.mask & PIDFD_INFO_COREDUMP))
+			goto out;
 
-		if (info.coredump_mask & PIDFD_COREDUMPED) {
-			fprintf(stderr, "Received unexpected connection from coredumping task\n");
+		if (info.coredump_mask & PIDFD_COREDUMPED)
+			goto out;
+
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
 			close(fd_coredump);
+		if (fd_server >= 0)
 			close(fd_server);
-			close(fd_peer_pidfd);
-			_exit(EXIT_FAILURE);
-		}
-
-		close(fd_coredump);
-		close(fd_server);
-		close(fd_peer_pidfd);
-		close(fd_core_file);
-		_exit(EXIT_SUCCESS);
+		_exit(exit_code);
 	}
 	self->pid_coredump_server = pid_coredump_server;
 
@@ -478,17 +464,22 @@ TEST_F(coredump, socket_detect_userspace_client)
 	if (pid == 0) {
 		int fd_socket;
 		ssize_t ret;
+		const struct sockaddr_un coredump_sk = {
+			.sun_family = AF_UNIX,
+			.sun_path = "/tmp/coredump.socket",
+		};
+		size_t coredump_sk_len =
+			offsetof(struct sockaddr_un, sun_path) +
+			sizeof("/tmp/coredump.socket");
 
 		fd_socket = socket(AF_UNIX, SOCK_STREAM, 0);
 		if (fd_socket < 0)
 			_exit(EXIT_FAILURE);
 
-
 		ret = connect(fd_socket, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
 		if (ret < 0)
 			_exit(EXIT_FAILURE);
 
-		(void *)write(fd_socket, &(char){ 0 }, 1);
 		close(fd_socket);
 		_exit(EXIT_SUCCESS);
 	}
@@ -500,15 +491,11 @@ TEST_F(coredump, socket_detect_userspace_client)
 	ASSERT_TRUE(WIFEXITED(status));
 	ASSERT_EQ(WEXITSTATUS(status), 0);
 
-	info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
-	ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0);
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
 	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
 	ASSERT_EQ((info.coredump_mask & PIDFD_COREDUMPED), 0);
 
-	waitpid(pid_coredump_server, &status, 0);
-	self->pid_coredump_server = -ESRCH;
-	ASSERT_TRUE(WIFEXITED(status));
-	ASSERT_EQ(WEXITSTATUS(status), 0);
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
 
 	ASSERT_NE(stat("/tmp/coredump.file", &st), 0);
 	ASSERT_EQ(errno, ENOENT);
@@ -516,17 +503,10 @@ TEST_F(coredump, socket_detect_userspace_client)
 
 TEST_F(coredump, socket_enoent)
 {
-	int pidfd, ret, status;
-	FILE *file;
+	int pidfd, status;
 	pid_t pid;
-	char core_file[PATH_MAX];
 
-	file = fopen("/proc/sys/kernel/core_pattern", "w");
-	ASSERT_NE(file, NULL);
-
-	ret = fprintf(file, "@/tmp/coredump.socket");
-	ASSERT_EQ(ret, strlen("@/tmp/coredump.socket"));
-	ASSERT_EQ(fclose(file), 0);
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
 
 	pid = fork();
 	ASSERT_GE(pid, 0);
@@ -544,7 +524,6 @@ TEST_F(coredump, socket_enoent)
 TEST_F(coredump, socket_no_listener)
 {
 	int pidfd, ret, status;
-	FILE *file;
 	pid_t pid, pid_coredump_server;
 	int ipc_sockets[2];
 	char c;
@@ -555,45 +534,518 @@ TEST_F(coredump, socket_no_listener)
 	size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) +
 				 sizeof("/tmp/coredump.socket");
 
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
 	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
 	ASSERT_EQ(ret, 0);
 
-	file = fopen("/proc/sys/kernel/core_pattern", "w");
-	ASSERT_NE(file, NULL);
-
-	ret = fprintf(file, "@/tmp/coredump.socket");
-	ASSERT_EQ(ret, strlen("@/tmp/coredump.socket"));
-	ASSERT_EQ(fclose(file), 0);
-
 	pid_coredump_server = fork();
 	ASSERT_GE(pid_coredump_server, 0);
 	if (pid_coredump_server == 0) {
-		int fd_server;
-		socklen_t fd_peer_pidfd_len;
+		int fd_server = -1;
+		int exit_code = EXIT_FAILURE;
 
 		close(ipc_sockets[0]);
 
 		fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
 		if (fd_server < 0)
-			_exit(EXIT_FAILURE);
+			goto out;
 
 		ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
-		if (ret < 0) {
-			fprintf(stderr, "Failed to bind coredump socket\n");
+		if (ret < 0)
+			goto out;
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
+
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_server >= 0)
 			close(fd_server);
-			close(ipc_sockets[1]);
-			_exit(EXIT_FAILURE);
+		close(ipc_sockets[1]);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+static ssize_t recv_marker(int fd)
+{
+	enum coredump_mark mark = COREDUMP_MARK_REQACK;
+	ssize_t ret;
+
+	ret = recv(fd, &mark, sizeof(mark), MSG_WAITALL);
+	if (ret != sizeof(mark))
+		return -1;
+
+	switch (mark) {
+	case COREDUMP_MARK_REQACK:
+		fprintf(stderr, "Received marker: ReqAck\n");
+		return COREDUMP_MARK_REQACK;
+	case COREDUMP_MARK_MINSIZE:
+		fprintf(stderr, "Received marker: MinSize\n");
+		return COREDUMP_MARK_MINSIZE;
+	case COREDUMP_MARK_MAXSIZE:
+		fprintf(stderr, "Received marker: MaxSize\n");
+		return COREDUMP_MARK_MAXSIZE;
+	case COREDUMP_MARK_UNSUPPORTED:
+		fprintf(stderr, "Received marker: Unsupported\n");
+		return COREDUMP_MARK_UNSUPPORTED;
+	case COREDUMP_MARK_CONFLICTING:
+		fprintf(stderr, "Received marker: Conflicting\n");
+		return COREDUMP_MARK_CONFLICTING;
+	default:
+		fprintf(stderr, "Received unknown marker: %u\n", mark);
+		break;
+	}
+	return -1;
+}
+
+static bool read_marker(int fd, enum coredump_mark mark)
+{
+	ssize_t ret;
+
+	ret = recv_marker(fd);
+	if (ret < 0)
+		return false;
+	return ret == mark;
+}
+
+static bool read_coredump_req(int fd, struct coredump_req *req)
+{
+	ssize_t ret;
+	size_t field_size, user_size, ack_size, kernel_size, remaining_size;
+
+	memset(req, 0, sizeof(*req));
+	field_size = sizeof(req->size);
+
+	/* Peek the size of the coredump request. */
+	ret = recv(fd, req, field_size, MSG_PEEK | MSG_WAITALL);
+	if (ret != field_size)
+		return false;
+	kernel_size = req->size;
+
+	if (kernel_size < COREDUMP_ACK_SIZE_VER0)
+		return false;
+	if (kernel_size >= PAGE_SIZE)
+		return false;
+
+	/* Use the minimum of user and kernel size to read the full request. */
+	user_size = sizeof(struct coredump_req);
+	ack_size = user_size < kernel_size ? user_size : kernel_size;
+	ret = recv(fd, req, ack_size, MSG_WAITALL);
+	if (ret != ack_size)
+		return false;
+
+	fprintf(stderr, "Read coredump request with size %u and mask 0x%llx\n",
+		req->size, (unsigned long long)req->mask);
+
+	if (user_size > kernel_size)
+		remaining_size = user_size - kernel_size;
+	else
+		remaining_size = kernel_size - user_size;
+
+	if (PAGE_SIZE <= remaining_size)
+		return false;
+
+	/*
+	 * Discard any additional data if the kernel's request was larger than
+	 * what we knew about or cared about.
+	 */
+	if (remaining_size) {
+		char buffer[PAGE_SIZE];
+
+		ret = recv(fd, buffer, sizeof(buffer), MSG_WAITALL);
+		if (ret != remaining_size)
+			return false;
+		fprintf(stderr, "Discarded %zu bytes of data after coredump request\n", remaining_size);
+	}
+
+	return true;
+}
+
+static bool send_coredump_ack(int fd, const struct coredump_req *req,
+			      __u64 mask, size_t size_ack)
+{
+	ssize_t ret;
+	/*
+	 * Wrap struct coredump_ack in a larger struct so we can
+	 * simulate sending to much data to the kernel.
+	 */
+	struct large_ack_for_size_testing {
+		struct coredump_ack ack;
+		char buffer[PAGE_SIZE];
+	} large_ack = {};
+
+	if (!size_ack)
+		size_ack = sizeof(struct coredump_ack) < req->size_ack ?
+				   sizeof(struct coredump_ack) :
+				   req->size_ack;
+	large_ack.ack.mask = mask;
+	large_ack.ack.size = size_ack;
+	ret = send(fd, &large_ack, size_ack, MSG_NOSIGNAL);
+	if (ret != size_ack)
+		return false;
+
+	fprintf(stderr, "Sent coredump ack with size %zu and mask 0x%llx\n",
+		size_ack, (unsigned long long)mask);
+	return true;
+}
+
+static bool check_coredump_req(const struct coredump_req *req, size_t min_size,
+			       __u64 required_mask)
+{
+	if (req->size < min_size)
+		return false;
+	if ((req->mask & required_mask) != required_mask)
+		return false;
+	if (req->mask & ~required_mask)
+		return false;
+	return true;
+}
+
+TEST_F(coredump, socket_request_kernel)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct stat st;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_core_file = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0)
+			goto out;
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0)
+			goto out;
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0)
+			goto out;
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info))
+			goto out;
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP))
+			goto out;
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED))
+			goto out;
+
+		fd_core_file = creat("/tmp/coredump.file", 0644);
+		if (fd_core_file < 0)
+			goto out;
+
+		if (!read_coredump_req(fd_coredump, &req))
+			goto out;
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT))
+			goto out;
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_KERNEL | COREDUMP_WAIT, 0))
+			goto out;
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK))
+			goto out;
+
+		for (;;) {
+			char buffer[4096];
+			ssize_t bytes_read, bytes_write;
+
+			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+			if (bytes_read < 0)
+				goto out;
+
+			if (bytes_read == 0)
+				break;
+
+			bytes_write = write(fd_core_file, buffer, bytes_read);
+			if (bytes_read != bytes_write)
+				goto out;
 		}
 
-		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_core_file >= 0)
+			close(fd_core_file);
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
 			close(fd_server);
-			close(ipc_sockets[1]);
-			_exit(EXIT_FAILURE);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_TRUE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+
+	ASSERT_EQ(stat("/tmp/coredump.file", &st), 0);
+	ASSERT_GT(st.st_size, 0);
+	system("file /tmp/coredump.file");
+}
+
+TEST_F(coredump, socket_request_userspace)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0)
+			goto out;
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0)
+			goto out;
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0)
+			goto out;
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info))
+			goto out;
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP))
+			goto out;
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED))
+			goto out;
+
+		if (!read_coredump_req(fd_coredump, &req))
+			goto out;
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT))
+			goto out;
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_USERSPACE | COREDUMP_WAIT, 0))
+			goto out;
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK))
+			goto out;
+
+		for (;;) {
+			char buffer[4096];
+			ssize_t bytes_read;
+
+			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+			if (bytes_read > 0)
+				goto out;
+
+			if (bytes_read < 0)
+				goto out;
+
+			if (bytes_read == 0)
+				break;
 		}
 
-		close(fd_server);
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_TRUE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_reject)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0)
+			goto out;
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
+
 		close(ipc_sockets[1]);
-		_exit(EXIT_SUCCESS);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0)
+			goto out;
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0)
+			goto out;
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info))
+			goto out;
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP))
+			goto out;
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED))
+			goto out;
+
+		if (!read_coredump_req(fd_coredump, &req))
+			goto out;
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT))
+			goto out;
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_REJECT | COREDUMP_WAIT, 0))
+			goto out;
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK))
+			goto out;
+
+		for (;;) {
+			char buffer[4096];
+			ssize_t bytes_read;
+
+			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+			if (bytes_read > 0)
+				goto out;
+
+			if (bytes_read < 0)
+				goto out;
+
+			if (bytes_read == 0)
+				break;
+		}
+
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
 	}
 	self->pid_coredump_server = pid_coredump_server;
 
@@ -613,10 +1065,743 @@ TEST_F(coredump, socket_no_listener)
 	ASSERT_TRUE(WIFSIGNALED(status));
 	ASSERT_FALSE(WCOREDUMP(status));
 
-	waitpid(pid_coredump_server, &status, 0);
-	self->pid_coredump_server = -ESRCH;
-	ASSERT_TRUE(WIFEXITED(status));
-	ASSERT_EQ(WEXITSTATUS(status), 0);
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_invalid_flag_combination)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0)
+			goto out;
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0)
+			goto out;
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0)
+			goto out;
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info))
+			goto out;
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP))
+			goto out;
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED))
+			goto out;
+
+		if (!read_coredump_req(fd_coredump, &req))
+			goto out;
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT))
+			goto out;
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_KERNEL | COREDUMP_REJECT | COREDUMP_WAIT, 0))
+			goto out;
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_CONFLICTING))
+			goto out;
+
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_unknown_flag)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0)
+			goto out;
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0)
+			goto out;
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0)
+			goto out;
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info))
+			goto out;
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP))
+			goto out;
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED))
+			goto out;
+
+		if (!read_coredump_req(fd_coredump, &req))
+			goto out;
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT))
+			goto out;
+
+		if (!send_coredump_ack(fd_coredump, &req, (1ULL << 63), 0))
+			goto out;
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_UNSUPPORTED))
+			goto out;
+
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_invalid_size_small)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0)
+			goto out;
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0)
+			goto out;
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0)
+			goto out;
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info))
+			goto out;
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP))
+			goto out;
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED))
+			goto out;
+
+		if (!read_coredump_req(fd_coredump, &req))
+			goto out;
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT))
+			goto out;
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_REJECT | COREDUMP_WAIT,
+				       COREDUMP_ACK_SIZE_VER0 / 2))
+			goto out;
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_MINSIZE))
+			goto out;
+
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_invalid_size_large)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0)
+			goto out;
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0)
+			goto out;
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0)
+			goto out;
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info))
+			goto out;
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP))
+			goto out;
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED))
+			goto out;
+
+		if (!read_coredump_req(fd_coredump, &req))
+			goto out;
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT))
+			goto out;
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_REJECT | COREDUMP_WAIT,
+				       COREDUMP_ACK_SIZE_VER0 + PAGE_SIZE))
+			goto out;
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_MAXSIZE))
+			goto out;
+
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+static int open_coredump_tmpfile(int fd_tmpfs_detached)
+{
+	return openat(fd_tmpfs_detached, ".", O_TMPFILE | O_RDWR | O_EXCL, 0600);
+}
+
+#define NUM_CRASHING_COREDUMPS 5
+
+TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps, 500)
+{
+	int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS];
+	pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+		int exit_code = EXIT_FAILURE;
+		struct coredump_req req = {};
+
+		close(ipc_sockets[0]);
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "Failed to create and listen on unix socket\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "Failed to notify parent via ipc socket\n");
+			goto out;
+		}
+		close(ipc_sockets[1]);
+
+		for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+			fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+			if (fd_coredump < 0) {
+				fprintf(stderr, "accept4 failed: %m\n");
+				goto out;
+			}
+
+			fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+			if (fd_peer_pidfd < 0) {
+				fprintf(stderr, "get_peer_pidfd failed for fd %d: %m\n", fd_coredump);
+				goto out;
+			}
+
+			if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+				fprintf(stderr, "get_pidfd_info failed for fd %d\n", fd_peer_pidfd);
+				goto out;
+			}
+
+			if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+				fprintf(stderr, "pidfd info missing PIDFD_INFO_COREDUMP for fd %d\n", fd_peer_pidfd);
+				goto out;
+			}
+			if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+				fprintf(stderr, "pidfd info missing PIDFD_COREDUMPED for fd %d\n", fd_peer_pidfd);
+				goto out;
+			}
+
+			if (!read_coredump_req(fd_coredump, &req)) {
+				fprintf(stderr, "read_coredump_req failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+						COREDUMP_KERNEL | COREDUMP_USERSPACE |
+						COREDUMP_REJECT | COREDUMP_WAIT)) {
+				fprintf(stderr, "check_coredump_req failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			if (!send_coredump_ack(fd_coredump, &req,
+					       COREDUMP_KERNEL | COREDUMP_WAIT, 0)) {
+				fprintf(stderr, "send_coredump_ack failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+				fprintf(stderr, "read_marker failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+			if (fd_core_file < 0) {
+				fprintf(stderr, "%m - open_coredump_tmpfile failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			for (;;) {
+				char buffer[4096];
+				ssize_t bytes_read, bytes_write;
+
+				bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+				if (bytes_read < 0) {
+					fprintf(stderr, "read failed for fd %d: %m\n", fd_coredump);
+					goto out;
+				}
+
+				if (bytes_read == 0)
+					break;
+
+				bytes_write = write(fd_core_file, buffer, bytes_read);
+				if (bytes_read != bytes_write) {
+					fprintf(stderr, "write failed for fd %d: %m\n", fd_core_file);
+					goto out;
+				}
+			}
+
+			close(fd_core_file);
+			close(fd_peer_pidfd);
+			close(fd_coredump);
+			fd_peer_pidfd = -1;
+			fd_coredump = -1;
+		}
+
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_core_file >= 0)
+			close(fd_core_file);
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		pid[i] = fork();
+		ASSERT_GE(pid[i], 0);
+		if (pid[i] == 0)
+			crashing_child();
+		pidfd[i] = sys_pidfd_open(pid[i], 0);
+		ASSERT_GE(pidfd[i], 0);
+	}
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		waitpid(pid[i], &status[i], 0);
+		ASSERT_TRUE(WIFSIGNALED(status[i]));
+		ASSERT_TRUE(WCOREDUMP(status[i]));
+	}
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+		ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0);
+		ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+		ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+	}
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+#define MAX_EVENTS 128
+
+static void process_coredump_worker(int fd_coredump, int fd_peer_pidfd, int fd_core_file)
+{
+	int epfd = -1;
+	int exit_code = EXIT_FAILURE;
+
+	epfd = epoll_create1(0);
+	if (epfd < 0)
+		goto out;
+
+	struct epoll_event ev;
+	ev.events = EPOLLIN | EPOLLRDHUP | EPOLLET;
+	ev.data.fd = fd_coredump;
+	if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd_coredump, &ev) < 0)
+		goto out;
+
+	for (;;) {
+		struct epoll_event events[1];
+		int n = epoll_wait(epfd, events, 1, -1);
+		if (n < 0)
+			break;
+
+		if (events[0].events & (EPOLLIN | EPOLLRDHUP)) {
+			for (;;) {
+				char buffer[4096];
+				ssize_t bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+				if (bytes_read < 0) {
+					if (errno == EAGAIN || errno == EWOULDBLOCK)
+						break;
+					goto out;
+				}
+				if (bytes_read == 0)
+					goto done;
+				ssize_t bytes_write = write(fd_core_file, buffer, bytes_read);
+				if (bytes_write != bytes_read)
+					goto out;
+			}
+		}
+	}
+
+done:
+	exit_code = EXIT_SUCCESS;
+out:
+	if (epfd >= 0)
+		close(epfd);
+	if (fd_core_file >= 0)
+		close(fd_core_file);
+	if (fd_peer_pidfd >= 0)
+		close(fd_peer_pidfd);
+	if (fd_coredump >= 0)
+		close(fd_coredump);
+	_exit(exit_code);
+}
+
+TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps_epoll_workers, 500)
+{
+	int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS];
+	pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server, worker_pids[NUM_CRASHING_COREDUMPS];
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+	ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		int fd_server = -1, exit_code = EXIT_FAILURE, n_conns = 0;
+		fd_server = -1;
+		exit_code = EXIT_FAILURE;
+		n_conns = 0;
+		close(ipc_sockets[0]);
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0)
+			goto out;
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+			goto out;
+		close(ipc_sockets[1]);
+
+		while (n_conns < NUM_CRASHING_COREDUMPS) {
+			int fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+			struct coredump_req req = {};
+			fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+			if (fd_coredump < 0) {
+				if (errno == EAGAIN || errno == EWOULDBLOCK)
+					continue;
+				goto out;
+			}
+			fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+			if (fd_peer_pidfd < 0)
+				goto out;
+			if (!get_pidfd_info(fd_peer_pidfd, &info))
+				goto out;
+			if (!(info.mask & PIDFD_INFO_COREDUMP) || !(info.coredump_mask & PIDFD_COREDUMPED))
+				goto out;
+			if (!read_coredump_req(fd_coredump, &req))
+				goto out;
+			if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+						COREDUMP_KERNEL | COREDUMP_USERSPACE |
+						COREDUMP_REJECT | COREDUMP_WAIT))
+				goto out;
+			if (!send_coredump_ack(fd_coredump, &req, COREDUMP_KERNEL | COREDUMP_WAIT, 0))
+				goto out;
+			if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK))
+				goto out;
+			fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+			if (fd_core_file < 0)
+				goto out;
+			pid_t worker = fork();
+			if (worker == 0) {
+				close(fd_server);
+				process_coredump_worker(fd_coredump, fd_peer_pidfd, fd_core_file);
+			}
+			worker_pids[n_conns] = worker;
+			if (fd_coredump >= 0)
+				close(fd_coredump);
+			if (fd_peer_pidfd >= 0)
+				close(fd_peer_pidfd);
+			if (fd_core_file >= 0)
+				close(fd_core_file);
+			n_conns++;
+		}
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_server >= 0)
+			close(fd_server);
+
+		// Reap all worker processes
+		for (int i = 0; i < n_conns; i++) {
+			int wstatus;
+			if (waitpid(worker_pids[i], &wstatus, 0) < 0) {
+				fprintf(stderr, "Failed to wait for worker %d: %m\n", worker_pids[i]);
+			} else if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) != EXIT_SUCCESS) {
+				fprintf(stderr, "Worker %d exited with error code %d\n", worker_pids[i], WEXITSTATUS(wstatus));
+				exit_code = EXIT_FAILURE;
+			}
+		}
+
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		pid[i] = fork();
+		ASSERT_GE(pid[i], 0);
+		if (pid[i] == 0)
+			crashing_child();
+		pidfd[i] = sys_pidfd_open(pid[i], 0);
+		ASSERT_GE(pidfd[i], 0);
+	}
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		ASSERT_GE(waitpid(pid[i], &status[i], 0), 0);
+		ASSERT_TRUE(WIFSIGNALED(status[i]));
+		ASSERT_TRUE(WCOREDUMP(status[i]));
+	}
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+		ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0);
+		ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+		ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+	}
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
 }
 
 TEST_HARNESS_MAIN