Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 503 insertions, 0 deletions

diff --git a/fs/bpf_fs_kfuncs.c b/fs/bpf_fs_kfuncs.c
new file mode 100644
index 000000000..6cb877267
--- /dev/null
+++ b/fs/bpf_fs_kfuncs.c
@@ -0,0 +1,503 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC. */
+
+#include <linux/binfmt_misc.h>
+#include <linux/bpf.h>
+#include <linux/bpf_lsm.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <linux/dcache.h>
+#include <linux/fs.h>
+#include <linux/fsnotify.h>
+#include <linux/file.h>
+#include <linux/kernfs.h>
+#include <linux/mm.h>
+#include <linux/net.h>
+#include <linux/xattr.h>
+
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_get_task_exe_file - get a reference on the exe_file struct file member of
+ *                         the mm_struct that is nested within the supplied
+ *                         task_struct
+ * @task: task_struct of which the nested mm_struct exe_file member to get a
+ * reference on
+ *
+ * Get a reference on the exe_file struct file member field of the mm_struct
+ * nested within the supplied *task*. The referenced file pointer acquired by
+ * this BPF kfunc must be released using bpf_put_file(). Failing to call
+ * bpf_put_file() on the returned referenced struct file pointer that has been
+ * acquired by this BPF kfunc will result in the BPF program being rejected by
+ * the BPF verifier.
+ *
+ * This BPF kfunc may only be called from BPF LSM programs.
+ *
+ * Internally, this BPF kfunc leans on get_task_exe_file(), such that calling
+ * bpf_get_task_exe_file() would be analogous to calling get_task_exe_file()
+ * directly in kernel context.
+ *
+ * Return: A referenced struct file pointer to the exe_file member of the
+ * mm_struct that is nested within the supplied *task*. On error, NULL is
+ * returned.
+ */
+__bpf_kfunc struct file *bpf_get_task_exe_file(struct task_struct *task)
+{
+	return get_task_exe_file(task);
+}
+
+/**
+ * bpf_put_file - put a reference on the supplied file
+ * @file: file to put a reference on
+ *
+ * Put a reference on the supplied *file*. Only referenced file pointers may be
+ * passed to this BPF kfunc. Attempting to pass an unreferenced file pointer, or
+ * any other arbitrary pointer for that matter, will result in the BPF program
+ * being rejected by the BPF verifier.
+ *
+ * This BPF kfunc may only be called from BPF LSM programs.
+ */
+__bpf_kfunc void bpf_put_file(struct file *file)
+{
+	fput(file);
+}
+
+/**
+ * bpf_path_d_path - resolve the pathname for the supplied path
+ * @path: path to resolve the pathname for
+ * @buf: buffer to return the resolved pathname in
+ * @buf__sz: length of the supplied buffer
+ *
+ * Resolve the pathname for the supplied *path* and store it in *buf*. This BPF
+ * kfunc is the safer variant of the legacy bpf_d_path() helper and should be
+ * used in place of bpf_d_path() whenever possible.
+ *
+ * This BPF kfunc may only be called from BPF LSM programs.
+ *
+ * Return: A positive integer corresponding to the length of the resolved
+ * pathname in *buf*, including the NUL termination character. On error, a
+ * negative integer is returned.
+ */
+__bpf_kfunc int bpf_path_d_path(const struct path *path, char *buf, size_t buf__sz)
+{
+	int len;
+	char *ret;
+
+	if (!buf__sz)
+		return -EINVAL;
+
+	ret = d_path(path, buf, buf__sz);
+	if (IS_ERR(ret))
+		return PTR_ERR(ret);
+
+	len = buf + buf__sz - ret;
+	memmove(buf, ret, len);
+	return len;
+}
+
+static bool match_security_bpf_prefix(const char *name__str)
+{
+	return !strncmp(name__str, XATTR_NAME_BPF_LSM, XATTR_NAME_BPF_LSM_LEN);
+}
+
+static int bpf_xattr_read_permission(const char *name, struct inode *inode)
+{
+	if (!inode)
+		return -EINVAL;
+
+	/* Allow reading xattr with user. and security.bpf. prefix */
+	if (strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) &&
+	    !match_security_bpf_prefix(name))
+		return -EPERM;
+
+	return inode_permission(&nop_mnt_idmap, inode, MAY_READ);
+}
+
+/**
+ * bpf_get_dentry_xattr - get xattr of a dentry
+ * @dentry: dentry to get xattr from
+ * @name__str: name of the xattr
+ * @value_p: output buffer of the xattr value
+ *
+ * Get xattr *name__str* of *dentry* and store the output in *value_ptr*.
+ *
+ * For security reasons, only *name__str* with prefixes "user." or
+ * "security.bpf." are allowed.
+ *
+ * Return: length of the xattr value on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_get_dentry_xattr(struct dentry *dentry, const char *name__str,
+				     struct bpf_dynptr *value_p)
+{
+	struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p;
+	struct inode *inode = d_inode(dentry);
+	u32 value_len;
+	void *value;
+	int ret;
+
+	value_len = __bpf_dynptr_size(value_ptr);
+	value = __bpf_dynptr_data_rw(value_ptr, value_len);
+	if (!value)
+		return -EINVAL;
+
+	ret = bpf_xattr_read_permission(name__str, inode);
+	if (ret)
+		return ret;
+	return __vfs_getxattr(dentry, inode, name__str, value, value_len);
+}
+
+/**
+ * bpf_get_file_xattr - get xattr of a file
+ * @file: file to get xattr from
+ * @name__str: name of the xattr
+ * @value_p: output buffer of the xattr value
+ *
+ * Get xattr *name__str* of *file* and store the output in *value_ptr*.
+ *
+ * For security reasons, only *name__str* with prefixes "user." or
+ * "security.bpf." are allowed.
+ *
+ * Return: length of the xattr value on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str,
+				   struct bpf_dynptr *value_p)
+{
+	struct dentry *dentry;
+
+	dentry = file_dentry(file);
+	return bpf_get_dentry_xattr(dentry, name__str, value_p);
+}
+
+__bpf_kfunc_end_defs();
+
+static int bpf_xattr_write_permission(const char *name, struct inode *inode)
+{
+	if (!inode)
+		return -EINVAL;
+
+	/* Only allow setting and removing security.bpf. xattrs */
+	if (!match_security_bpf_prefix(name))
+		return -EPERM;
+
+	return inode_permission(&nop_mnt_idmap, inode, MAY_WRITE);
+}
+
+/**
+ * bpf_set_dentry_xattr_locked - set a xattr of a dentry
+ * @dentry: dentry to get xattr from
+ * @name__str: name of the xattr
+ * @value_p: xattr value
+ * @flags: flags to pass into filesystem operations
+ *
+ * Set xattr *name__str* of *dentry* to the value in *value_ptr*.
+ *
+ * For security reasons, only *name__str* with prefix "security.bpf."
+ * is allowed.
+ *
+ * The caller already locked dentry->d_inode.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+int bpf_set_dentry_xattr_locked(struct dentry *dentry, const char *name__str,
+				const struct bpf_dynptr *value_p, int flags)
+{
+
+	const struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p;
+	struct inode *inode = d_inode(dentry);
+	const void *value;
+	u32 value_len;
+	int ret;
+
+	value_len = __bpf_dynptr_size(value_ptr);
+	value = __bpf_dynptr_data(value_ptr, value_len);
+	if (!value)
+		return -EINVAL;
+
+	ret = bpf_xattr_write_permission(name__str, inode);
+	if (ret)
+		return ret;
+
+	ret = __vfs_setxattr(&nop_mnt_idmap, dentry, inode, name__str,
+			     value, value_len, flags);
+	if (!ret) {
+		fsnotify_xattr(dentry);
+
+		/* This xattr is set by BPF LSM, so we do not call
+		 * security_inode_post_setxattr. Otherwise, we would
+		 * risk deadlocks by calling back to the same kfunc.
+		 *
+		 * This is the same as security_inode_setsecurity().
+		 */
+	}
+	return ret;
+}
+
+/**
+ * bpf_remove_dentry_xattr_locked - remove a xattr of a dentry
+ * @dentry: dentry to get xattr from
+ * @name__str: name of the xattr
+ *
+ * Rmove xattr *name__str* of *dentry*.
+ *
+ * For security reasons, only *name__str* with prefix "security.bpf."
+ * is allowed.
+ *
+ * The caller already locked dentry->d_inode.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+int bpf_remove_dentry_xattr_locked(struct dentry *dentry, const char *name__str)
+{
+	struct inode *inode = d_inode(dentry);
+	int ret;
+
+	ret = bpf_xattr_write_permission(name__str, inode);
+	if (ret)
+		return ret;
+
+	ret = __vfs_removexattr(&nop_mnt_idmap, dentry, name__str);
+	if (!ret) {
+		fsnotify_xattr(dentry);
+
+		/* This xattr is removed by BPF LSM, so we do not call
+		 * security_inode_post_removexattr. Otherwise, we would
+		 * risk deadlocks by calling back to the same kfunc.
+		 */
+	}
+	return ret;
+}
+
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_set_dentry_xattr - set a xattr of a dentry
+ * @dentry: dentry to get xattr from
+ * @name__str: name of the xattr
+ * @value_p: xattr value
+ * @flags: flags to pass into filesystem operations
+ *
+ * Set xattr *name__str* of *dentry* to the value in *value_ptr*.
+ *
+ * For security reasons, only *name__str* with prefix "security.bpf."
+ * is allowed.
+ *
+ * The caller has not locked dentry->d_inode.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_set_dentry_xattr(struct dentry *dentry, const char *name__str,
+				     const struct bpf_dynptr *value_p, int flags)
+{
+	struct inode *inode = d_inode(dentry);
+	int ret;
+
+	if (!inode)
+		return -EINVAL;
+
+	inode_lock(inode);
+	ret = bpf_set_dentry_xattr_locked(dentry, name__str, value_p, flags);
+	inode_unlock(inode);
+	return ret;
+}
+
+/**
+ * bpf_remove_dentry_xattr - remove a xattr of a dentry
+ * @dentry: dentry to get xattr from
+ * @name__str: name of the xattr
+ *
+ * Rmove xattr *name__str* of *dentry*.
+ *
+ * For security reasons, only *name__str* with prefix "security.bpf."
+ * is allowed.
+ *
+ * The caller has not locked dentry->d_inode.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_remove_dentry_xattr(struct dentry *dentry, const char *name__str)
+{
+	struct inode *inode = d_inode(dentry);
+	int ret;
+
+	if (!inode)
+		return -EINVAL;
+
+	inode_lock(inode);
+	ret = bpf_remove_dentry_xattr_locked(dentry, name__str);
+	inode_unlock(inode);
+	return ret;
+}
+
+#ifdef CONFIG_CGROUPS
+/**
+ * bpf_cgroup_read_xattr - read xattr of a cgroup's node in cgroupfs
+ * @cgroup: cgroup to get xattr from
+ * @name__str: name of the xattr
+ * @value_p: output buffer of the xattr value
+ *
+ * Get xattr *name__str* of *cgroup* and store the output in *value_ptr*.
+ *
+ * For security reasons, only *name__str* with prefix "user." is allowed.
+ *
+ * Return: length of the xattr value on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_cgroup_read_xattr(struct cgroup *cgroup, const char *name__str,
+					struct bpf_dynptr *value_p)
+{
+	struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p;
+	u32 value_len;
+	void *value;
+
+	/* Only allow reading "user.*" xattrs */
+	if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+		return -EPERM;
+
+	value_len = __bpf_dynptr_size(value_ptr);
+	value = __bpf_dynptr_data_rw(value_ptr, value_len);
+	if (!value)
+		return -EINVAL;
+
+	return kernfs_xattr_get(cgroup->kn, name__str, value, value_len);
+}
+#endif /* CONFIG_CGROUPS */
+
+#ifdef CONFIG_NET
+/**
+ * bpf_sock_read_xattr - read xattr of a socket's inode in sockfs
+ * @sock: socket to get xattr from
+ * @name__str: name of the xattr
+ * @value_p: output buffer of the xattr value
+ *
+ * Get xattr *name__str* of *sock* and store the output in *value_p*.
+ *
+ * For security reasons, only *name__str* with prefix "user." is allowed.
+ *
+ * Return: length of the xattr value on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_sock_read_xattr(struct socket *sock, const char *name__str,
+				    struct bpf_dynptr *value_p)
+{
+	struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p;
+	u32 value_len;
+	void *value;
+
+	/* Only allow reading "user.*" xattrs */
+	if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+		return -EPERM;
+
+	value_len = __bpf_dynptr_size(value_ptr);
+	value = __bpf_dynptr_data_rw(value_ptr, value_len);
+	if (!value)
+		return -EINVAL;
+
+	return sock_read_xattr(sock, name__str, value, value_len);
+}
+#endif /* CONFIG_NET */
+
+/**
+ * bpf_real_data_inode - get the real inode hosting a file's data
+ * @file: file to resolve
+ *
+ * Resolve @file to the inode that hosts its data. For a regular file on a
+ * union/overlay filesystem this is the underlying (upper or lower) inode that
+ * stores the data, not the overlay inode.
+ *
+ * Data resolution only applies to regular files. For a non-regular file (e.g.
+ * a device node, fifo or socket) on a union/overlay filesystem the overlay
+ * inode itself is returned; for any file on a non-union filesystem the inode
+ * attached to @file is returned.
+ *
+ * Return: The inode hosting @file's data, or NULL.
+ */
+__bpf_kfunc struct inode *bpf_real_data_inode(struct file *file)
+{
+	return d_real_inode(file_dentry(file));
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(bpf_fs_kfunc_set_ids)
+BTF_ID_FLAGS(func, bpf_get_task_exe_file, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_put_file, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_path_d_path)
+BTF_ID_FLAGS(func, bpf_get_dentry_xattr, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_set_dentry_xattr, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_remove_dentry_xattr, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_real_data_inode, KF_SLEEPABLE | KF_RET_NULL)
+#ifdef CONFIG_NET
+BTF_ID_FLAGS(func, bpf_sock_read_xattr, KF_RCU)
+#endif
+BTF_KFUNCS_END(bpf_fs_kfunc_set_ids)
+
+/* Side-effecting kfuncs that stay exclusive to LSM programs. */
+BTF_SET_START(bpf_fs_kfunc_lsm_only_ids)
+BTF_ID(func, bpf_set_dentry_xattr)
+BTF_ID(func, bpf_remove_dentry_xattr)
+BTF_SET_END(bpf_fs_kfunc_lsm_only_ids)
+
+static int bpf_fs_kfuncs_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+	if (!btf_id_set8_contains(&bpf_fs_kfunc_set_ids, kfunc_id))
+		return 0;
+	if (prog->type == BPF_PROG_TYPE_LSM)
+		return 0;
+	if (prog->type != BPF_PROG_TYPE_STRUCT_OPS)
+		return -EACCES;
+	/* ->st_ops is unset during the cfg pass; enforced once it is set. */
+	if (!prog->aux->st_ops)
+		return 0;
+	if (bpf_prog_is_binfmt_misc_ops(prog) &&
+	    !btf_id_set_contains(&bpf_fs_kfunc_lsm_only_ids, kfunc_id))
+		return 0;
+	return -EACCES;
+}
+
+/* bpf_[set|remove]_dentry_xattr.* hooks have KF_SLEEPABLE, so they are only
+ * available to sleepable hooks with dentry arguments.
+ *
+ * Setting and removing xattr requires exclusive lock on dentry->d_inode.
+ * Some hooks already locked d_inode, while some hooks have not locked
+ * d_inode. Therefore, we need different kfuncs for different hooks.
+ * Specifically, hooks in the following list (d_inode_locked_hooks)
+ * should call bpf_[set|remove]_dentry_xattr_locked; while other hooks
+ * should call bpf_[set|remove]_dentry_xattr.
+ */
+BTF_SET_START(d_inode_locked_hooks)
+BTF_ID(func, bpf_lsm_inode_post_removexattr)
+BTF_ID(func, bpf_lsm_inode_post_setattr)
+BTF_ID(func, bpf_lsm_inode_post_setxattr)
+BTF_ID(func, bpf_lsm_inode_removexattr)
+BTF_ID(func, bpf_lsm_inode_rmdir)
+BTF_ID(func, bpf_lsm_inode_setattr)
+BTF_ID(func, bpf_lsm_inode_setxattr)
+BTF_ID(func, bpf_lsm_inode_unlink)
+#ifdef CONFIG_SECURITY_PATH
+BTF_ID(func, bpf_lsm_path_unlink)
+BTF_ID(func, bpf_lsm_path_rmdir)
+#endif /* CONFIG_SECURITY_PATH */
+BTF_SET_END(d_inode_locked_hooks)
+
+bool bpf_lsm_has_d_inode_locked(const struct bpf_prog *prog)
+{
+	return btf_id_set_contains(&d_inode_locked_hooks, prog->aux->attach_btf_id);
+}
+
+static const struct btf_kfunc_id_set bpf_fs_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &bpf_fs_kfunc_set_ids,
+	.filter = bpf_fs_kfuncs_filter,
+};
+
+static int __init bpf_fs_kfuncs_init(void)
+{
+	int ret;
+
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set);
+	if (ret || !IS_ENABLED(CONFIG_BINFMT_MISC_BPF))
+		return ret;
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+					 &bpf_fs_kfunc_set);
+}
+
+late_initcall(bpf_fs_kfuncs_init);