Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

8 files changed, 725 insertions, 28 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 4ccf423603..933f6c3fe6 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -150,6 +150,9 @@ always-y += ibumad_kern.o
 always-y += hbm_out_kern.o
 always-y += hbm_edt_kern.o
 
+TPROGS_CFLAGS = $(TPROGS_USER_CFLAGS)
+TPROGS_LDFLAGS = $(TPROGS_USER_LDFLAGS)
+
 ifeq ($(ARCH), arm)
 # Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux
 # headers when arm instruction set identification is requested.
@@ -169,12 +172,16 @@ endif
 TPROGS_CFLAGS += -Wall -O2
 TPROGS_CFLAGS += -Wmissing-prototypes
 TPROGS_CFLAGS += -Wstrict-prototypes
+TPROGS_CFLAGS += $(call try-run,\
+	printf "int main() { return 0; }" |\
+	$(CC) -Werror -fsanitize=bounds -x c - -o "$$TMP",-fsanitize=bounds,)
 
 TPROGS_CFLAGS += -I$(objtree)/usr/include
 TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
 TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE)
 TPROGS_CFLAGS += -I$(srctree)/tools/include
 TPROGS_CFLAGS += -I$(srctree)/tools/perf
+TPROGS_CFLAGS += -I$(srctree)/tools/lib
 TPROGS_CFLAGS += -DHAVE_ATTR_TEST=0
 
 ifdef SYSROOT
@@ -247,14 +254,15 @@ clean:
 $(LIBBPF): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT)
 # Fix up variables inherited from Kbuild that tools/ build system won't like
 	$(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(TPROGS_CFLAGS)" \
-		LDFLAGS=$(TPROGS_LDFLAGS) srctree=$(BPF_SAMPLES_PATH)/../../ \
+		LDFLAGS="$(TPROGS_LDFLAGS)" srctree=$(BPF_SAMPLES_PATH)/../../ \
 		O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \
 		$@ install_headers
 
 BPFTOOLDIR := $(TOOLS_PATH)/bpf/bpftool
 BPFTOOL_OUTPUT := $(abspath $(BPF_SAMPLES_PATH))/bpftool
-BPFTOOL := $(BPFTOOL_OUTPUT)/bootstrap/bpftool
-$(BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) | $(BPFTOOL_OUTPUT)
+DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)/bootstrap/bpftool
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) | $(BPFTOOL_OUTPUT)
 	$(MAKE) -C $(BPFTOOLDIR) srctree=$(BPF_SAMPLES_PATH)/../../ 		\
 		OUTPUT=$(BPFTOOL_OUTPUT)/ bootstrap
 
@@ -312,8 +320,11 @@ XDP_SAMPLE_CFLAGS += -Wall -O2 \
 		     -I$(LIBBPF_INCLUDE) \
 		     -I$(src)/../../tools/testing/selftests/bpf
 
-$(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS)
+$(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS) $(TPROGS_USER_CFLAGS)
 $(obj)/$(XDP_SAMPLE): $(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h
+# Override includes for trace_helpers.o because __must_check won't be defined
+# in our include path.
+$(obj)/$(TRACE_HELPERS): TPROGS_CFLAGS := $(TPROGS_CFLAGS) -D__must_check=
 
 -include $(BPF_SAMPLES_PATH)/Makefile.target
 
diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
index 7048bb3594..634e81d83e 100644
--- a/samples/bpf/asm_goto_workaround.h
+++ b/samples/bpf/asm_goto_workaround.h
@@ -4,14 +4,14 @@
 #define __ASM_GOTO_WORKAROUND_H
 
 /*
- * This will bring in asm_volatile_goto and asm_inline macro definitions
+ * This will bring in asm_goto_output and asm_inline macro definitions
  * if enabled by compiler and config options.
  */
 #include <linux/types.h>
 
-#ifdef asm_volatile_goto
-#undef asm_volatile_goto
-#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
+#ifdef asm_goto_output
+#undef asm_goto_output
+#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output")
 #endif
 
 /*
diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c
index 090fecfe64..58fef969a6 100644
--- a/samples/bpf/syscall_tp_kern.c
+++ b/samples/bpf/syscall_tp_kern.c
@@ -4,6 +4,7 @@
 #include <uapi/linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
+#if !defined(__aarch64__)
 struct syscalls_enter_open_args {
 	unsigned long long unused;
 	long syscall_nr;
@@ -11,6 +12,7 @@ struct syscalls_enter_open_args {
 	long flags;
 	long mode;
 };
+#endif
 
 struct syscalls_exit_open_args {
 	unsigned long long unused;
@@ -18,6 +20,15 @@ struct syscalls_exit_open_args {
 	long ret;
 };
 
+struct syscalls_enter_open_at_args {
+	unsigned long long unused;
+	long syscall_nr;
+	long long dfd;
+	long filename_ptr;
+	long flags;
+	long mode;
+};
+
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__type(key, u32);
@@ -54,14 +65,14 @@ int trace_enter_open(struct syscalls_enter_open_args *ctx)
 #endif
 
 SEC("tracepoint/syscalls/sys_enter_openat")
-int trace_enter_open_at(struct syscalls_enter_open_args *ctx)
+int trace_enter_open_at(struct syscalls_enter_open_at_args *ctx)
 {
 	count(&enter_open_map);
 	return 0;
 }
 
 SEC("tracepoint/syscalls/sys_enter_openat2")
-int trace_enter_open_at2(struct syscalls_enter_open_args *ctx)
+int trace_enter_open_at2(struct syscalls_enter_open_at_args *ctx)
 {
 	count(&enter_open_map);
 	return 0;
diff --git a/samples/kprobes/kretprobe_example.c b/samples/kprobes/kretprobe_example.c
index cbf16542d8..ed79fd3d48 100644
--- a/samples/kprobes/kretprobe_example.c
+++ b/samples/kprobes/kretprobe_example.c
@@ -35,7 +35,7 @@ struct my_data {
 	ktime_t entry_stamp;
 };
 
-/* Here we use the entry_hanlder to timestamp function entry */
+/* Here we use the entry_handler to timestamp function entry */
 static int entry_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	struct my_data *data;
diff --git a/samples/landlock/sandboxer.c b/samples/landlock/sandboxer.c
index e2056c8b90..08596c0ef0 100644
--- a/samples/landlock/sandboxer.c
+++ b/samples/landlock/sandboxer.c
@@ -8,6 +8,8 @@
  */
 
 #define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__
+#include <arpa/inet.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <linux/landlock.h>
@@ -51,7 +53,9 @@ static inline int landlock_restrict_self(const int ruleset_fd,
 
 #define ENV_FS_RO_NAME "LL_FS_RO"
 #define ENV_FS_RW_NAME "LL_FS_RW"
-#define ENV_PATH_TOKEN ":"
+#define ENV_TCP_BIND_NAME "LL_TCP_BIND"
+#define ENV_TCP_CONNECT_NAME "LL_TCP_CONNECT"
+#define ENV_DELIMITER ":"
 
 static int parse_path(char *env_path, const char ***const path_list)
 {
@@ -60,13 +64,13 @@ static int parse_path(char *env_path, const char ***const path_list)
 	if (env_path) {
 		num_paths++;
 		for (i = 0; env_path[i]; i++) {
-			if (env_path[i] == ENV_PATH_TOKEN[0])
+			if (env_path[i] == ENV_DELIMITER[0])
 				num_paths++;
 		}
 	}
 	*path_list = malloc(num_paths * sizeof(**path_list));
 	for (i = 0; i < num_paths; i++)
-		(*path_list)[i] = strsep(&env_path, ENV_PATH_TOKEN);
+		(*path_list)[i] = strsep(&env_path, ENV_DELIMITER);
 
 	return num_paths;
 }
@@ -81,8 +85,8 @@ static int parse_path(char *env_path, const char ***const path_list)
 
 /* clang-format on */
 
-static int populate_ruleset(const char *const env_var, const int ruleset_fd,
-			    const __u64 allowed_access)
+static int populate_ruleset_fs(const char *const env_var, const int ruleset_fd,
+			       const __u64 allowed_access)
 {
 	int num_paths, i, ret = 1;
 	char *env_path_name;
@@ -143,6 +147,39 @@ out_free_name:
 	return ret;
 }
 
+static int populate_ruleset_net(const char *const env_var, const int ruleset_fd,
+				const __u64 allowed_access)
+{
+	int ret = 1;
+	char *env_port_name, *strport;
+	struct landlock_net_port_attr net_port = {
+		.allowed_access = allowed_access,
+		.port = 0,
+	};
+
+	env_port_name = getenv(env_var);
+	if (!env_port_name)
+		return 0;
+	env_port_name = strdup(env_port_name);
+	unsetenv(env_var);
+
+	while ((strport = strsep(&env_port_name, ENV_DELIMITER))) {
+		net_port.port = atoi(strport);
+		if (landlock_add_rule(ruleset_fd, LANDLOCK_RULE_NET_PORT,
+				      &net_port, 0)) {
+			fprintf(stderr,
+				"Failed to update the ruleset with port \"%llu\": %s\n",
+				net_port.port, strerror(errno));
+			goto out_free_name;
+		}
+	}
+	ret = 0;
+
+out_free_name:
+	free(env_port_name);
+	return ret;
+}
+
 /* clang-format off */
 
 #define ACCESS_FS_ROUGHLY_READ ( \
@@ -166,39 +203,58 @@ out_free_name:
 
 /* clang-format on */
 
-#define LANDLOCK_ABI_LAST 3
+#define LANDLOCK_ABI_LAST 4
 
 int main(const int argc, char *const argv[], char *const *const envp)
 {
 	const char *cmd_path;
 	char *const *cmd_argv;
 	int ruleset_fd, abi;
+	char *env_port_name;
 	__u64 access_fs_ro = ACCESS_FS_ROUGHLY_READ,
 	      access_fs_rw = ACCESS_FS_ROUGHLY_READ | ACCESS_FS_ROUGHLY_WRITE;
+
 	struct landlock_ruleset_attr ruleset_attr = {
 		.handled_access_fs = access_fs_rw,
+		.handled_access_net = LANDLOCK_ACCESS_NET_BIND_TCP |
+				      LANDLOCK_ACCESS_NET_CONNECT_TCP,
 	};
 
 	if (argc < 2) {
 		fprintf(stderr,
-			"usage: %s=\"...\" %s=\"...\" %s <cmd> [args]...\n\n",
-			ENV_FS_RO_NAME, ENV_FS_RW_NAME, argv[0]);
+			"usage: %s=\"...\" %s=\"...\" %s=\"...\" %s=\"...\"%s "
+			"<cmd> [args]...\n\n",
+			ENV_FS_RO_NAME, ENV_FS_RW_NAME, ENV_TCP_BIND_NAME,
+			ENV_TCP_CONNECT_NAME, argv[0]);
 		fprintf(stderr,
 			"Launch a command in a restricted environment.\n\n");
-		fprintf(stderr, "Environment variables containing paths, "
-				"each separated by a colon:\n");
+		fprintf(stderr,
+			"Environment variables containing paths and ports "
+			"each separated by a colon:\n");
 		fprintf(stderr,
 			"* %s: list of paths allowed to be used in a read-only way.\n",
 			ENV_FS_RO_NAME);
 		fprintf(stderr,
-			"* %s: list of paths allowed to be used in a read-write way.\n",
+			"* %s: list of paths allowed to be used in a read-write way.\n\n",
 			ENV_FS_RW_NAME);
 		fprintf(stderr,
+			"Environment variables containing ports are optional "
+			"and could be skipped.\n");
+		fprintf(stderr,
+			"* %s: list of ports allowed to bind (server).\n",
+			ENV_TCP_BIND_NAME);
+		fprintf(stderr,
+			"* %s: list of ports allowed to connect (client).\n",
+			ENV_TCP_CONNECT_NAME);
+		fprintf(stderr,
 			"\nexample:\n"
 			"%s=\"/bin:/lib:/usr:/proc:/etc:/dev/urandom\" "
 			"%s=\"/dev/null:/dev/full:/dev/zero:/dev/pts:/tmp\" "
+			"%s=\"9418\" "
+			"%s=\"80:443\" "
 			"%s bash -i\n\n",
-			ENV_FS_RO_NAME, ENV_FS_RW_NAME, argv[0]);
+			ENV_FS_RO_NAME, ENV_FS_RW_NAME, ENV_TCP_BIND_NAME,
+			ENV_TCP_CONNECT_NAME, argv[0]);
 		fprintf(stderr,
 			"This sandboxer can use Landlock features "
 			"up to ABI version %d.\n",
@@ -255,7 +311,12 @@ int main(const int argc, char *const argv[], char *const *const envp)
 	case 2:
 		/* Removes LANDLOCK_ACCESS_FS_TRUNCATE for ABI < 3 */
 		ruleset_attr.handled_access_fs &= ~LANDLOCK_ACCESS_FS_TRUNCATE;
-
+		__attribute__((fallthrough));
+	case 3:
+		/* Removes network support for ABI < 4 */
+		ruleset_attr.handled_access_net &=
+			~(LANDLOCK_ACCESS_NET_BIND_TCP |
+			  LANDLOCK_ACCESS_NET_CONNECT_TCP);
 		fprintf(stderr,
 			"Hint: You should update the running kernel "
 			"to leverage Landlock features "
@@ -274,18 +335,42 @@ int main(const int argc, char *const argv[], char *const *const envp)
 	access_fs_ro &= ruleset_attr.handled_access_fs;
 	access_fs_rw &= ruleset_attr.handled_access_fs;
 
+	/* Removes bind access attribute if not supported by a user. */
+	env_port_name = getenv(ENV_TCP_BIND_NAME);
+	if (!env_port_name) {
+		ruleset_attr.handled_access_net &=
+			~LANDLOCK_ACCESS_NET_BIND_TCP;
+	}
+	/* Removes connect access attribute if not supported by a user. */
+	env_port_name = getenv(ENV_TCP_CONNECT_NAME);
+	if (!env_port_name) {
+		ruleset_attr.handled_access_net &=
+			~LANDLOCK_ACCESS_NET_CONNECT_TCP;
+	}
+
 	ruleset_fd =
 		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
 	if (ruleset_fd < 0) {
 		perror("Failed to create a ruleset");
 		return 1;
 	}
-	if (populate_ruleset(ENV_FS_RO_NAME, ruleset_fd, access_fs_ro)) {
+
+	if (populate_ruleset_fs(ENV_FS_RO_NAME, ruleset_fd, access_fs_ro)) {
+		goto err_close_ruleset;
+	}
+	if (populate_ruleset_fs(ENV_FS_RW_NAME, ruleset_fd, access_fs_rw)) {
 		goto err_close_ruleset;
 	}
-	if (populate_ruleset(ENV_FS_RW_NAME, ruleset_fd, access_fs_rw)) {
+
+	if (populate_ruleset_net(ENV_TCP_BIND_NAME, ruleset_fd,
+				 LANDLOCK_ACCESS_NET_BIND_TCP)) {
+		goto err_close_ruleset;
+	}
+	if (populate_ruleset_net(ENV_TCP_CONNECT_NAME, ruleset_fd,
+				 LANDLOCK_ACCESS_NET_CONNECT_TCP)) {
 		goto err_close_ruleset;
 	}
+
 	if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
 		perror("Failed to restrict privileges");
 		goto err_close_ruleset;
diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c
index 3764d1911b..93405264ff 100644
--- a/samples/vfio-mdev/mbochs.c
+++ b/samples/vfio-mdev/mbochs.c
@@ -1262,7 +1262,7 @@ static long mbochs_ioctl(struct vfio_device *vdev, unsigned int cmd,
 
 	case VFIO_DEVICE_QUERY_GFX_PLANE:
 	{
-		struct vfio_device_gfx_plane_info plane;
+		struct vfio_device_gfx_plane_info plane = {};
 
 		minsz = offsetofend(struct vfio_device_gfx_plane_info,
 				    region_index);
diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c
index 064e1c0a7a..72ea5832c9 100644
--- a/samples/vfio-mdev/mdpy.c
+++ b/samples/vfio-mdev/mdpy.c
@@ -591,7 +591,7 @@ static long mdpy_ioctl(struct vfio_device *vdev, unsigned int cmd,
 
 	case VFIO_DEVICE_QUERY_GFX_PLANE:
 	{
-		struct vfio_device_gfx_plane_info plane;
+		struct vfio_device_gfx_plane_info plane = {};
 
 		minsz = offsetofend(struct vfio_device_gfx_plane_info,
 				    region_index);
diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c
index 245db52bed..69ba0281f9 100644
--- a/samples/vfio-mdev/mtty.c
+++ b/samples/vfio-mdev/mtty.c
@@ -29,6 +29,8 @@
 #include <linux/serial.h>
 #include <uapi/linux/serial_reg.h>
 #include <linux/eventfd.h>
+#include <linux/anon_inodes.h>
+
 /*
  * #defines
  */
@@ -124,6 +126,29 @@ struct serial_port {
 	u8 intr_trigger_level;  /* interrupt trigger level */
 };
 
+struct mtty_data {
+	u64 magic;
+#define MTTY_MAGIC 0x7e9d09898c3e2c4e /* Nothing clever, just random */
+	u32 major_ver;
+#define MTTY_MAJOR_VER 1
+	u32 minor_ver;
+#define MTTY_MINOR_VER 0
+	u32 nr_ports;
+	u32 flags;
+	struct serial_port ports[2];
+};
+
+struct mdev_state;
+
+struct mtty_migration_file {
+	struct file *filp;
+	struct mutex lock;
+	struct mdev_state *mdev_state;
+	struct mtty_data data;
+	ssize_t filled_size;
+	u8 disabled:1;
+};
+
 /* State of each mdev device */
 struct mdev_state {
 	struct vfio_device vdev;
@@ -140,6 +165,12 @@ struct mdev_state {
 	struct mutex rxtx_lock;
 	struct vfio_device_info dev_info;
 	int nr_ports;
+	enum vfio_device_mig_state state;
+	struct mutex state_mutex;
+	struct mutex reset_mutex;
+	struct mtty_migration_file *saving_migf;
+	struct mtty_migration_file *resuming_migf;
+	u8 deferred_reset:1;
 	u8 intx_mask:1;
 };
 
@@ -743,6 +774,543 @@ accessfailed:
 	return ret;
 }
 
+static size_t mtty_data_size(struct mdev_state *mdev_state)
+{
+	return offsetof(struct mtty_data, ports) +
+		(mdev_state->nr_ports * sizeof(struct serial_port));
+}
+
+static void mtty_disable_file(struct mtty_migration_file *migf)
+{
+	mutex_lock(&migf->lock);
+	migf->disabled = true;
+	migf->filled_size = 0;
+	migf->filp->f_pos = 0;
+	mutex_unlock(&migf->lock);
+}
+
+static void mtty_disable_files(struct mdev_state *mdev_state)
+{
+	if (mdev_state->saving_migf) {
+		mtty_disable_file(mdev_state->saving_migf);
+		fput(mdev_state->saving_migf->filp);
+		mdev_state->saving_migf = NULL;
+	}
+
+	if (mdev_state->resuming_migf) {
+		mtty_disable_file(mdev_state->resuming_migf);
+		fput(mdev_state->resuming_migf->filp);
+		mdev_state->resuming_migf = NULL;
+	}
+}
+
+static void mtty_state_mutex_unlock(struct mdev_state *mdev_state)
+{
+again:
+	mutex_lock(&mdev_state->reset_mutex);
+	if (mdev_state->deferred_reset) {
+		mdev_state->deferred_reset = false;
+		mutex_unlock(&mdev_state->reset_mutex);
+		mdev_state->state = VFIO_DEVICE_STATE_RUNNING;
+		mtty_disable_files(mdev_state);
+		goto again;
+	}
+	mutex_unlock(&mdev_state->state_mutex);
+	mutex_unlock(&mdev_state->reset_mutex);
+}
+
+static int mtty_release_migf(struct inode *inode, struct file *filp)
+{
+	struct mtty_migration_file *migf = filp->private_data;
+
+	mtty_disable_file(migf);
+	mutex_destroy(&migf->lock);
+	kfree(migf);
+
+	return 0;
+}
+
+static long mtty_precopy_ioctl(struct file *filp, unsigned int cmd,
+			       unsigned long arg)
+{
+	struct mtty_migration_file *migf = filp->private_data;
+	struct mdev_state *mdev_state = migf->mdev_state;
+	loff_t *pos = &filp->f_pos;
+	struct vfio_precopy_info info = {};
+	unsigned long minsz;
+	int ret;
+
+	if (cmd != VFIO_MIG_GET_PRECOPY_INFO)
+		return -ENOTTY;
+
+	minsz = offsetofend(struct vfio_precopy_info, dirty_bytes);
+
+	if (copy_from_user(&info, (void __user *)arg, minsz))
+		return -EFAULT;
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	mutex_lock(&mdev_state->state_mutex);
+	if (mdev_state->state != VFIO_DEVICE_STATE_PRE_COPY &&
+	    mdev_state->state != VFIO_DEVICE_STATE_PRE_COPY_P2P) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	mutex_lock(&migf->lock);
+
+	if (migf->disabled) {
+		mutex_unlock(&migf->lock);
+		ret = -ENODEV;
+		goto unlock;
+	}
+
+	if (*pos > migf->filled_size) {
+		mutex_unlock(&migf->lock);
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	info.dirty_bytes = 0;
+	info.initial_bytes = migf->filled_size - *pos;
+	mutex_unlock(&migf->lock);
+
+	ret = copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
+unlock:
+	mtty_state_mutex_unlock(mdev_state);
+	return ret;
+}
+
+static ssize_t mtty_save_read(struct file *filp, char __user *buf,
+			      size_t len, loff_t *pos)
+{
+	struct mtty_migration_file *migf = filp->private_data;
+	ssize_t ret = 0;
+
+	if (pos)
+		return -ESPIPE;
+
+	pos = &filp->f_pos;
+
+	mutex_lock(&migf->lock);
+
+	dev_dbg(migf->mdev_state->vdev.dev, "%s ask %zu\n", __func__, len);
+
+	if (migf->disabled) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	if (*pos > migf->filled_size) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	len = min_t(size_t, migf->filled_size - *pos, len);
+	if (len) {
+		if (copy_to_user(buf, (void *)&migf->data + *pos, len)) {
+			ret = -EFAULT;
+			goto out_unlock;
+		}
+		*pos += len;
+		ret = len;
+	}
+out_unlock:
+	dev_dbg(migf->mdev_state->vdev.dev, "%s read %zu\n", __func__, ret);
+	mutex_unlock(&migf->lock);
+	return ret;
+}
+
+static const struct file_operations mtty_save_fops = {
+	.owner = THIS_MODULE,
+	.read = mtty_save_read,
+	.unlocked_ioctl = mtty_precopy_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
+	.release = mtty_release_migf,
+	.llseek = no_llseek,
+};
+
+static void mtty_save_state(struct mdev_state *mdev_state)
+{
+	struct mtty_migration_file *migf = mdev_state->saving_migf;
+	int i;
+
+	mutex_lock(&migf->lock);
+	for (i = 0; i < mdev_state->nr_ports; i++) {
+		memcpy(&migf->data.ports[i],
+			&mdev_state->s[i], sizeof(struct serial_port));
+		migf->filled_size += sizeof(struct serial_port);
+	}
+	dev_dbg(mdev_state->vdev.dev,
+		"%s filled to %zu\n", __func__, migf->filled_size);
+	mutex_unlock(&migf->lock);
+}
+
+static int mtty_load_state(struct mdev_state *mdev_state)
+{
+	struct mtty_migration_file *migf = mdev_state->resuming_migf;
+	int i;
+
+	mutex_lock(&migf->lock);
+	/* magic and version already tested by resume write fn */
+	if (migf->filled_size < mtty_data_size(mdev_state)) {
+		dev_dbg(mdev_state->vdev.dev, "%s expected %zu, got %zu\n",
+			__func__, mtty_data_size(mdev_state),
+			migf->filled_size);
+		mutex_unlock(&migf->lock);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < mdev_state->nr_ports; i++)
+		memcpy(&mdev_state->s[i],
+		       &migf->data.ports[i], sizeof(struct serial_port));
+
+	mutex_unlock(&migf->lock);
+	return 0;
+}
+
+static struct mtty_migration_file *
+mtty_save_device_data(struct mdev_state *mdev_state,
+		      enum vfio_device_mig_state state)
+{
+	struct mtty_migration_file *migf = mdev_state->saving_migf;
+	struct mtty_migration_file *ret = NULL;
+
+	if (migf) {
+		if (state == VFIO_DEVICE_STATE_STOP_COPY)
+			goto fill_data;
+		return ret;
+	}
+
+	migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT);
+	if (!migf)
+		return ERR_PTR(-ENOMEM);
+
+	migf->filp = anon_inode_getfile("mtty_mig", &mtty_save_fops,
+					migf, O_RDONLY);
+	if (IS_ERR(migf->filp)) {
+		int rc = PTR_ERR(migf->filp);
+
+		kfree(migf);
+		return ERR_PTR(rc);
+	}
+
+	stream_open(migf->filp->f_inode, migf->filp);
+	mutex_init(&migf->lock);
+	migf->mdev_state = mdev_state;
+
+	migf->data.magic = MTTY_MAGIC;
+	migf->data.major_ver = MTTY_MAJOR_VER;
+	migf->data.minor_ver = MTTY_MINOR_VER;
+	migf->data.nr_ports = mdev_state->nr_ports;
+
+	migf->filled_size = offsetof(struct mtty_data, ports);
+
+	dev_dbg(mdev_state->vdev.dev, "%s filled header to %zu\n",
+		__func__, migf->filled_size);
+
+	ret = mdev_state->saving_migf = migf;
+
+fill_data:
+	if (state == VFIO_DEVICE_STATE_STOP_COPY)
+		mtty_save_state(mdev_state);
+
+	return ret;
+}
+
+static ssize_t mtty_resume_write(struct file *filp, const char __user *buf,
+				 size_t len, loff_t *pos)
+{
+	struct mtty_migration_file *migf = filp->private_data;
+	struct mdev_state *mdev_state = migf->mdev_state;
+	loff_t requested_length;
+	ssize_t ret = 0;
+
+	if (pos)
+		return -ESPIPE;
+
+	pos = &filp->f_pos;
+
+	if (*pos < 0 ||
+	    check_add_overflow((loff_t)len, *pos, &requested_length))
+		return -EINVAL;
+
+	if (requested_length > mtty_data_size(mdev_state))
+		return -ENOMEM;
+
+	mutex_lock(&migf->lock);
+
+	if (migf->disabled) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	if (copy_from_user((void *)&migf->data + *pos, buf, len)) {
+		ret = -EFAULT;
+		goto out_unlock;
+	}
+
+	*pos += len;
+	ret = len;
+
+	dev_dbg(migf->mdev_state->vdev.dev, "%s received %zu, total %zu\n",
+		__func__, len, migf->filled_size + len);
+
+	if (migf->filled_size < offsetof(struct mtty_data, ports) &&
+	    migf->filled_size + len >= offsetof(struct mtty_data, ports)) {
+		if (migf->data.magic != MTTY_MAGIC || migf->data.flags ||
+		    migf->data.major_ver != MTTY_MAJOR_VER ||
+		    migf->data.minor_ver != MTTY_MINOR_VER ||
+		    migf->data.nr_ports != mdev_state->nr_ports) {
+			dev_dbg(migf->mdev_state->vdev.dev,
+				"%s failed validation\n", __func__);
+			ret = -EFAULT;
+		} else {
+			dev_dbg(migf->mdev_state->vdev.dev,
+				"%s header validated\n", __func__);
+		}
+	}
+
+	migf->filled_size += len;
+
+out_unlock:
+	mutex_unlock(&migf->lock);
+	return ret;
+}
+
+static const struct file_operations mtty_resume_fops = {
+	.owner = THIS_MODULE,
+	.write = mtty_resume_write,
+	.release = mtty_release_migf,
+	.llseek = no_llseek,
+};
+
+static struct mtty_migration_file *
+mtty_resume_device_data(struct mdev_state *mdev_state)
+{
+	struct mtty_migration_file *migf;
+	int ret;
+
+	migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT);
+	if (!migf)
+		return ERR_PTR(-ENOMEM);
+
+	migf->filp = anon_inode_getfile("mtty_mig", &mtty_resume_fops,
+					migf, O_WRONLY);
+	if (IS_ERR(migf->filp)) {
+		ret = PTR_ERR(migf->filp);
+		kfree(migf);
+		return ERR_PTR(ret);
+	}
+
+	stream_open(migf->filp->f_inode, migf->filp);
+	mutex_init(&migf->lock);
+	migf->mdev_state = mdev_state;
+
+	mdev_state->resuming_migf = migf;
+
+	return migf;
+}
+
+static struct file *mtty_step_state(struct mdev_state *mdev_state,
+				     enum vfio_device_mig_state new)
+{
+	enum vfio_device_mig_state cur = mdev_state->state;
+
+	dev_dbg(mdev_state->vdev.dev, "%s: %d -> %d\n", __func__, cur, new);
+
+	/*
+	 * The following state transitions are no-op considering
+	 * mtty does not do DMA nor require any explicit start/stop.
+	 *
+	 *         RUNNING -> RUNNING_P2P
+	 *         RUNNING_P2P -> RUNNING
+	 *         RUNNING_P2P -> STOP
+	 *         PRE_COPY -> PRE_COPY_P2P
+	 *         PRE_COPY_P2P -> PRE_COPY
+	 *         STOP -> RUNNING_P2P
+	 */
+	if ((cur == VFIO_DEVICE_STATE_RUNNING &&
+	     new == VFIO_DEVICE_STATE_RUNNING_P2P) ||
+	    (cur == VFIO_DEVICE_STATE_RUNNING_P2P &&
+	     (new == VFIO_DEVICE_STATE_RUNNING ||
+	      new == VFIO_DEVICE_STATE_STOP)) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY &&
+	     new == VFIO_DEVICE_STATE_PRE_COPY_P2P) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P &&
+	     new == VFIO_DEVICE_STATE_PRE_COPY) ||
+	    (cur == VFIO_DEVICE_STATE_STOP &&
+	     new == VFIO_DEVICE_STATE_RUNNING_P2P))
+		return NULL;
+
+	/*
+	 * The following state transitions simply close migration files,
+	 * with the exception of RESUMING -> STOP, which needs to load
+	 * the state first.
+	 *
+	 *         RESUMING -> STOP
+	 *         PRE_COPY -> RUNNING
+	 *         PRE_COPY_P2P -> RUNNING_P2P
+	 *         STOP_COPY -> STOP
+	 */
+	if (cur == VFIO_DEVICE_STATE_RESUMING &&
+	    new == VFIO_DEVICE_STATE_STOP) {
+		int ret;
+
+		ret = mtty_load_state(mdev_state);
+		if (ret)
+			return ERR_PTR(ret);
+		mtty_disable_files(mdev_state);
+		return NULL;
+	}
+
+	if ((cur == VFIO_DEVICE_STATE_PRE_COPY &&
+	     new == VFIO_DEVICE_STATE_RUNNING) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P &&
+	     new == VFIO_DEVICE_STATE_RUNNING_P2P) ||
+	    (cur == VFIO_DEVICE_STATE_STOP_COPY &&
+	     new == VFIO_DEVICE_STATE_STOP)) {
+		mtty_disable_files(mdev_state);
+		return NULL;
+	}
+
+	/*
+	 * The following state transitions return migration files.
+	 *
+	 *         RUNNING -> PRE_COPY
+	 *         RUNNING_P2P -> PRE_COPY_P2P
+	 *         STOP -> STOP_COPY
+	 *         STOP -> RESUMING
+	 *         PRE_COPY_P2P -> STOP_COPY
+	 */
+	if ((cur == VFIO_DEVICE_STATE_RUNNING &&
+	     new == VFIO_DEVICE_STATE_PRE_COPY) ||
+	    (cur == VFIO_DEVICE_STATE_RUNNING_P2P &&
+	     new == VFIO_DEVICE_STATE_PRE_COPY_P2P) ||
+	    (cur == VFIO_DEVICE_STATE_STOP &&
+	     new == VFIO_DEVICE_STATE_STOP_COPY) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P &&
+	     new == VFIO_DEVICE_STATE_STOP_COPY)) {
+		struct mtty_migration_file *migf;
+
+		migf = mtty_save_device_data(mdev_state, new);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+
+		if (migf) {
+			get_file(migf->filp);
+
+			return migf->filp;
+		}
+		return NULL;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_STOP &&
+	    new == VFIO_DEVICE_STATE_RESUMING) {
+		struct mtty_migration_file *migf;
+
+		migf = mtty_resume_device_data(mdev_state);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+
+		get_file(migf->filp);
+
+		return migf->filp;
+	}
+
+	/* vfio_mig_get_next_state() does not use arcs other than the above */
+	WARN_ON(true);
+	return ERR_PTR(-EINVAL);
+}
+
+static struct file *mtty_set_state(struct vfio_device *vdev,
+				   enum vfio_device_mig_state new_state)
+{
+	struct mdev_state *mdev_state =
+		container_of(vdev, struct mdev_state, vdev);
+	struct file *ret = NULL;
+
+	dev_dbg(vdev->dev, "%s -> %d\n", __func__, new_state);
+
+	mutex_lock(&mdev_state->state_mutex);
+	while (mdev_state->state != new_state) {
+		enum vfio_device_mig_state next_state;
+		int rc = vfio_mig_get_next_state(vdev, mdev_state->state,
+						 new_state, &next_state);
+		if (rc) {
+			ret = ERR_PTR(rc);
+			break;
+		}
+
+		ret = mtty_step_state(mdev_state, next_state);
+		if (IS_ERR(ret))
+			break;
+
+		mdev_state->state = next_state;
+
+		if (WARN_ON(ret && new_state != next_state)) {
+			fput(ret);
+			ret = ERR_PTR(-EINVAL);
+			break;
+		}
+	}
+	mtty_state_mutex_unlock(mdev_state);
+	return ret;
+}
+
+static int mtty_get_state(struct vfio_device *vdev,
+			  enum vfio_device_mig_state *current_state)
+{
+	struct mdev_state *mdev_state =
+		container_of(vdev, struct mdev_state, vdev);
+
+	mutex_lock(&mdev_state->state_mutex);
+	*current_state = mdev_state->state;
+	mtty_state_mutex_unlock(mdev_state);
+	return 0;
+}
+
+static int mtty_get_data_size(struct vfio_device *vdev,
+			      unsigned long *stop_copy_length)
+{
+	struct mdev_state *mdev_state =
+		container_of(vdev, struct mdev_state, vdev);
+
+	*stop_copy_length = mtty_data_size(mdev_state);
+	return 0;
+}
+
+static const struct vfio_migration_ops mtty_migration_ops = {
+	.migration_set_state = mtty_set_state,
+	.migration_get_state = mtty_get_state,
+	.migration_get_data_size = mtty_get_data_size,
+};
+
+static int mtty_log_start(struct vfio_device *vdev,
+			  struct rb_root_cached *ranges,
+			  u32 nnodes, u64 *page_size)
+{
+	return 0;
+}
+
+static int mtty_log_stop(struct vfio_device *vdev)
+{
+	return 0;
+}
+
+static int mtty_log_read_and_clear(struct vfio_device *vdev,
+				   unsigned long iova, unsigned long length,
+				   struct iova_bitmap *dirty)
+{
+	return 0;
+}
+
+static const struct vfio_log_ops mtty_log_ops = {
+	.log_start = mtty_log_start,
+	.log_stop = mtty_log_stop,
+	.log_read_and_clear = mtty_log_read_and_clear,
+};
+
 static int mtty_init_dev(struct vfio_device *vdev)
 {
 	struct mdev_state *mdev_state =
@@ -775,6 +1343,16 @@ static int mtty_init_dev(struct vfio_device *vdev)
 	mutex_init(&mdev_state->ops_lock);
 	mdev_state->mdev = mdev;
 	mtty_create_config_space(mdev_state);
+
+	mutex_init(&mdev_state->state_mutex);
+	mutex_init(&mdev_state->reset_mutex);
+	vdev->migration_flags = VFIO_MIGRATION_STOP_COPY |
+				VFIO_MIGRATION_P2P |
+				VFIO_MIGRATION_PRE_COPY;
+	vdev->mig_ops = &mtty_migration_ops;
+	vdev->log_ops = &mtty_log_ops;
+	mdev_state->state = VFIO_DEVICE_STATE_RUNNING;
+
 	return 0;
 
 err_nr_ports:
@@ -808,6 +1386,8 @@ static void mtty_release_dev(struct vfio_device *vdev)
 	struct mdev_state *mdev_state =
 		container_of(vdev, struct mdev_state, vdev);
 
+	mutex_destroy(&mdev_state->reset_mutex);
+	mutex_destroy(&mdev_state->state_mutex);
 	atomic_add(mdev_state->nr_ports, &mdev_avail_ports);
 	kfree(mdev_state->vconfig);
 }
@@ -824,6 +1404,15 @@ static int mtty_reset(struct mdev_state *mdev_state)
 {
 	pr_info("%s: called\n", __func__);
 
+	mutex_lock(&mdev_state->reset_mutex);
+	mdev_state->deferred_reset = true;
+	if (!mutex_trylock(&mdev_state->state_mutex)) {
+		mutex_unlock(&mdev_state->reset_mutex);
+		return 0;
+	}
+	mutex_unlock(&mdev_state->reset_mutex);
+	mtty_state_mutex_unlock(mdev_state);
+
 	return 0;
 }
 
@@ -1350,6 +1939,7 @@ static void mtty_close(struct vfio_device *vdev)
 	struct mdev_state *mdev_state =
 				container_of(vdev, struct mdev_state, vdev);
 
+	mtty_disable_files(mdev_state);
 	mtty_disable_intx(mdev_state);
 	mtty_disable_msi(mdev_state);
 }