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, 599 insertions, 0 deletions

diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c
new file mode 100644
index 000000000..298bfc932
--- /dev/null
+++ b/fs/vboxsf/utils.c
@@ -0,0 +1,599 @@
+// SPDX-License-Identifier: MIT
+/*
+ * VirtualBox Guest Shared Folders support: Utility functions.
+ * Mainly conversion from/to VirtualBox/Linux data structures.
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#include <linux/namei.h>
+#include <linux/nls.h>
+#include <linux/sizes.h>
+#include <linux/pagemap.h>
+#include <linux/vfs.h>
+#include <linux/fileattr.h>
+#include "vfsmod.h"
+
+struct inode *vboxsf_new_inode(struct super_block *sb)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(sb);
+	struct inode *inode;
+	unsigned long flags;
+	int cursor, ret;
+	u32 gen;
+
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	idr_preload(GFP_KERNEL);
+	spin_lock_irqsave(&sbi->ino_idr_lock, flags);
+	cursor = idr_get_cursor(&sbi->ino_idr);
+	ret = idr_alloc_cyclic(&sbi->ino_idr, inode, 1, 0, GFP_ATOMIC);
+	if (ret >= 0 && ret < cursor)
+		sbi->next_generation++;
+	gen = sbi->next_generation;
+	spin_unlock_irqrestore(&sbi->ino_idr_lock, flags);
+	idr_preload_end();
+
+	if (ret < 0) {
+		iput(inode);
+		return ERR_PTR(ret);
+	}
+
+	inode->i_ino = ret;
+	inode->i_generation = gen;
+	return inode;
+}
+
+/* set [inode] attributes based on [info], uid/gid based on [sbi] */
+int vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
+		       const struct shfl_fsobjinfo *info, bool reinit)
+{
+	const struct shfl_fsobjattr *attr;
+	s64 allocated;
+	umode_t mode;
+
+	attr = &info->attr;
+
+#define mode_set(r) ((attr->mode & (SHFL_UNIX_##r)) ? (S_##r) : 0)
+
+	mode = mode_set(IRUSR);
+	mode |= mode_set(IWUSR);
+	mode |= mode_set(IXUSR);
+
+	mode |= mode_set(IRGRP);
+	mode |= mode_set(IWGRP);
+	mode |= mode_set(IXGRP);
+
+	mode |= mode_set(IROTH);
+	mode |= mode_set(IWOTH);
+	mode |= mode_set(IXOTH);
+
+#undef mode_set
+
+	/* We use the host-side values for these */
+	inode->i_flags |= S_NOATIME | S_NOCMTIME;
+	inode->i_mapping->a_ops = &vboxsf_reg_aops;
+
+	if (SHFL_IS_DIRECTORY(attr->mode)) {
+		if (sbi->o.dmode_set)
+			mode = sbi->o.dmode;
+		mode &= ~sbi->o.dmask;
+		mode |= S_IFDIR;
+		if (!reinit) {
+			inode->i_op = &vboxsf_dir_iops;
+			inode->i_fop = &vboxsf_dir_fops;
+			/*
+			 * XXX: this probably should be set to the number of entries
+			 * in the directory plus two (. ..)
+			 */
+			set_nlink(inode, 1);
+		} else if (!S_ISDIR(inode->i_mode))
+			return -ESTALE;
+		inode->i_mode = mode;
+	} else if (SHFL_IS_SYMLINK(attr->mode)) {
+		if (sbi->o.fmode_set)
+			mode = sbi->o.fmode;
+		mode &= ~sbi->o.fmask;
+		mode |= S_IFLNK;
+		if (!reinit) {
+			inode->i_op = &vboxsf_lnk_iops;
+			set_nlink(inode, 1);
+		} else if (!S_ISLNK(inode->i_mode))
+			return -ESTALE;
+		inode->i_mode = mode;
+	} else {
+		if (sbi->o.fmode_set)
+			mode = sbi->o.fmode;
+		mode &= ~sbi->o.fmask;
+		mode |= S_IFREG;
+		if (!reinit) {
+			inode->i_op = &vboxsf_reg_iops;
+			inode->i_fop = &vboxsf_reg_fops;
+			set_nlink(inode, 1);
+		} else if (!S_ISREG(inode->i_mode))
+			return -ESTALE;
+		inode->i_mode = mode;
+	}
+
+	inode->i_uid = sbi->o.uid;
+	inode->i_gid = sbi->o.gid;
+
+	inode->i_size = info->size;
+	inode->i_blkbits = 12;
+	/* i_blocks always in units of 512 bytes! */
+	allocated = info->allocated + 511;
+	do_div(allocated, 512);
+	inode->i_blocks = allocated;
+
+	inode_set_atime_to_ts(inode,
+			      ns_to_timespec64(info->access_time.ns_relative_to_unix_epoch));
+	inode_set_ctime_to_ts(inode,
+			      ns_to_timespec64(info->change_time.ns_relative_to_unix_epoch));
+	inode_set_mtime_to_ts(inode,
+			      ns_to_timespec64(info->modification_time.ns_relative_to_unix_epoch));
+	return 0;
+}
+
+int vboxsf_create_at_dentry(struct dentry *dentry,
+			    struct shfl_createparms *params)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
+	struct shfl_string *path;
+	int err;
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	err = vboxsf_create(sbi->root, path, params);
+	__putname(path);
+
+	return err;
+}
+
+int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path,
+		struct shfl_fsobjinfo *info)
+{
+	struct shfl_createparms params = {};
+	int err;
+
+	params.handle = SHFL_HANDLE_NIL;
+	params.create_flags = SHFL_CF_LOOKUP | SHFL_CF_ACT_FAIL_IF_NEW;
+
+	err = vboxsf_create(sbi->root, path, &params);
+	if (err)
+		return err;
+
+	if (params.result != SHFL_FILE_EXISTS)
+		return -ENOENT;
+
+	if (info)
+		*info = params.info;
+
+	return 0;
+}
+
+int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
+	struct shfl_string *path;
+	int err;
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	err = vboxsf_stat(sbi, path, info);
+	__putname(path);
+	return err;
+}
+
+int vboxsf_inode_revalidate(struct dentry *dentry)
+{
+	struct vboxsf_sbi *sbi;
+	struct vboxsf_inode *sf_i;
+	struct shfl_fsobjinfo info;
+	struct timespec64 mtime, prev_mtime;
+	struct inode *inode;
+	int err;
+
+	if (!dentry || !d_really_is_positive(dentry))
+		return -EINVAL;
+
+	inode = d_inode(dentry);
+	prev_mtime = inode_get_mtime(inode);
+	sf_i = VBOXSF_I(inode);
+	sbi = VBOXSF_SBI(dentry->d_sb);
+	if (!sf_i->force_restat) {
+		if (time_before(jiffies, dentry->d_time + sbi->o.ttl))
+			return 0;
+	}
+
+	err = vboxsf_stat_dentry(dentry, &info);
+	if (err)
+		return err;
+
+	dentry->d_time = jiffies;
+	sf_i->force_restat = 0;
+	err = vboxsf_init_inode(sbi, inode, &info, true);
+	if (err)
+		return err;
+
+	/*
+	 * If the file was changed on the host side we need to invalidate the
+	 * page-cache for it.  Note this also gets triggered by our own writes,
+	 * this is unavoidable.
+	 */
+	mtime = inode_get_mtime(inode);
+	if (timespec64_compare(&mtime, &prev_mtime) > 0)
+		invalidate_inode_pages2(inode->i_mapping);
+
+	return 0;
+}
+
+int vboxsf_getattr(struct mnt_idmap *idmap, const struct path *path,
+		   struct kstat *kstat, u32 request_mask, unsigned int flags)
+{
+	int err;
+	struct dentry *dentry = path->dentry;
+	struct inode *inode = d_inode(dentry);
+	struct vboxsf_inode *sf_i = VBOXSF_I(inode);
+
+	switch (flags & AT_STATX_SYNC_TYPE) {
+	case AT_STATX_DONT_SYNC:
+		err = 0;
+		break;
+	case AT_STATX_FORCE_SYNC:
+		sf_i->force_restat = 1;
+		fallthrough;
+	default:
+		err = vboxsf_inode_revalidate(dentry);
+	}
+	if (err)
+		return err;
+
+	generic_fillattr(&nop_mnt_idmap, request_mask, d_inode(dentry), kstat);
+	return 0;
+}
+
+int vboxsf_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		   struct iattr *iattr)
+{
+	struct vboxsf_inode *sf_i = VBOXSF_I(d_inode(dentry));
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
+	struct shfl_createparms params = {};
+	struct shfl_fsobjinfo info = {};
+	u32 buf_len;
+	int err;
+
+	params.handle = SHFL_HANDLE_NIL;
+	params.create_flags = SHFL_CF_ACT_OPEN_IF_EXISTS |
+			      SHFL_CF_ACT_FAIL_IF_NEW |
+			      SHFL_CF_ACCESS_ATTR_WRITE;
+
+	/* this is at least required for Posix hosts */
+	if (iattr->ia_valid & ATTR_SIZE)
+		params.create_flags |= SHFL_CF_ACCESS_WRITE;
+
+	err = vboxsf_create_at_dentry(dentry, &params);
+	if (err || params.result != SHFL_FILE_EXISTS)
+		return err ? err : -ENOENT;
+
+#define mode_set(r) ((iattr->ia_mode & (S_##r)) ? SHFL_UNIX_##r : 0)
+
+	/*
+	 * Setting the file size and setting the other attributes has to
+	 * be handled separately.
+	 */
+	if (iattr->ia_valid & (ATTR_MODE | ATTR_ATIME | ATTR_MTIME)) {
+		if (iattr->ia_valid & ATTR_MODE) {
+			info.attr.mode = mode_set(IRUSR);
+			info.attr.mode |= mode_set(IWUSR);
+			info.attr.mode |= mode_set(IXUSR);
+			info.attr.mode |= mode_set(IRGRP);
+			info.attr.mode |= mode_set(IWGRP);
+			info.attr.mode |= mode_set(IXGRP);
+			info.attr.mode |= mode_set(IROTH);
+			info.attr.mode |= mode_set(IWOTH);
+			info.attr.mode |= mode_set(IXOTH);
+
+			if (iattr->ia_mode & S_IFDIR)
+				info.attr.mode |= SHFL_TYPE_DIRECTORY;
+			else
+				info.attr.mode |= SHFL_TYPE_FILE;
+		}
+
+		if (iattr->ia_valid & ATTR_ATIME)
+			info.access_time.ns_relative_to_unix_epoch =
+					    timespec64_to_ns(&iattr->ia_atime);
+
+		if (iattr->ia_valid & ATTR_MTIME)
+			info.modification_time.ns_relative_to_unix_epoch =
+					    timespec64_to_ns(&iattr->ia_mtime);
+
+		/*
+		 * Ignore ctime (inode change time) as it can't be set
+		 * from userland anyway.
+		 */
+
+		buf_len = sizeof(info);
+		err = vboxsf_fsinfo(sbi->root, params.handle,
+				    SHFL_INFO_SET | SHFL_INFO_FILE, &buf_len,
+				    &info);
+		if (err) {
+			vboxsf_close(sbi->root, params.handle);
+			return err;
+		}
+
+		/* the host may have given us different attr then requested */
+		sf_i->force_restat = 1;
+	}
+
+#undef mode_set
+
+	if (iattr->ia_valid & ATTR_SIZE) {
+		memset(&info, 0, sizeof(info));
+		info.size = iattr->ia_size;
+		buf_len = sizeof(info);
+		err = vboxsf_fsinfo(sbi->root, params.handle,
+				    SHFL_INFO_SET | SHFL_INFO_SIZE, &buf_len,
+				    &info);
+		if (err) {
+			vboxsf_close(sbi->root, params.handle);
+			return err;
+		}
+
+		/* the host may have given us different attr then requested */
+		sf_i->force_restat = 1;
+	}
+
+	vboxsf_close(sbi->root, params.handle);
+
+	/* Update the inode with what the host has actually given us. */
+	if (sf_i->force_restat)
+		vboxsf_inode_revalidate(dentry);
+
+	return 0;
+}
+
+/*
+ * [dentry] contains string encoded in coding system that corresponds
+ * to [sbi]->nls, we must convert it to UTF8 here.
+ * Returns a shfl_string allocated through __getname (must be freed using
+ * __putname), or an ERR_PTR on error.
+ */
+struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi,
+					    struct dentry *dentry)
+{
+	struct shfl_string *shfl_path;
+	int path_len, out_len, nb;
+	char *buf, *path;
+	wchar_t uni;
+	u8 *out;
+
+	buf = __getname();
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+
+	path = dentry_path_raw(dentry, buf, PATH_MAX);
+	if (IS_ERR(path)) {
+		__putname(buf);
+		return ERR_CAST(path);
+	}
+	path_len = strlen(path);
+
+	if (sbi->nls) {
+		shfl_path = __getname();
+		if (!shfl_path) {
+			__putname(buf);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		out = shfl_path->string.utf8;
+		out_len = PATH_MAX - SHFLSTRING_HEADER_SIZE - 1;
+
+		while (path_len) {
+			nb = sbi->nls->char2uni(path, path_len, &uni);
+			if (nb < 0) {
+				__putname(shfl_path);
+				__putname(buf);
+				return ERR_PTR(-EINVAL);
+			}
+			path += nb;
+			path_len -= nb;
+
+			nb = utf32_to_utf8(uni, out, out_len);
+			if (nb < 0) {
+				__putname(shfl_path);
+				__putname(buf);
+				return ERR_PTR(-ENAMETOOLONG);
+			}
+			out += nb;
+			out_len -= nb;
+		}
+		*out = 0;
+		shfl_path->length = out - shfl_path->string.utf8;
+		shfl_path->size = shfl_path->length + 1;
+		__putname(buf);
+	} else {
+		if ((SHFLSTRING_HEADER_SIZE + path_len + 1) > PATH_MAX) {
+			__putname(buf);
+			return ERR_PTR(-ENAMETOOLONG);
+		}
+		/*
+		 * dentry_path stores the name at the end of buf, but the
+		 * shfl_string string we return must be properly aligned.
+		 */
+		shfl_path = (struct shfl_string *)buf;
+		memmove(shfl_path->string.utf8, path, path_len);
+		shfl_path->string.utf8[path_len] = 0;
+		shfl_path->length = path_len;
+		shfl_path->size = path_len + 1;
+	}
+
+	return shfl_path;
+}
+
+int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len,
+		  const unsigned char *utf8_name, size_t utf8_len)
+{
+	const char *in;
+	char *out;
+	size_t out_bound_len;
+	size_t in_bound_len;
+
+	in = utf8_name;
+	in_bound_len = utf8_len;
+
+	out = name;
+	/* Reserve space for terminating 0 */
+	out_bound_len = name_bound_len - 1;
+
+	while (in_bound_len) {
+		int nb;
+		unicode_t uni;
+
+		nb = utf8_to_utf32(in, in_bound_len, &uni);
+		if (nb < 0)
+			return -EINVAL;
+
+		in += nb;
+		in_bound_len -= nb;
+
+		nb = sbi->nls->uni2char(uni, out, out_bound_len);
+		if (nb < 0)
+			return nb;
+
+		out += nb;
+		out_bound_len -= nb;
+	}
+
+	*out = 0;
+
+	return 0;
+}
+
+static struct vboxsf_dir_buf *vboxsf_dir_buf_alloc(struct list_head *list)
+{
+	struct vboxsf_dir_buf *b;
+
+	b = kmalloc_obj(*b);
+	if (!b)
+		return NULL;
+
+	b->buf = kmalloc(DIR_BUFFER_SIZE, GFP_KERNEL);
+	if (!b->buf) {
+		kfree(b);
+		return NULL;
+	}
+
+	b->entries = 0;
+	b->used = 0;
+	b->free = DIR_BUFFER_SIZE;
+	list_add(&b->head, list);
+
+	return b;
+}
+
+static void vboxsf_dir_buf_free(struct vboxsf_dir_buf *b)
+{
+	list_del(&b->head);
+	kfree(b->buf);
+	kfree(b);
+}
+
+struct vboxsf_dir_info *vboxsf_dir_info_alloc(void)
+{
+	struct vboxsf_dir_info *p;
+
+	p = kmalloc_obj(*p);
+	if (!p)
+		return NULL;
+
+	INIT_LIST_HEAD(&p->info_list);
+	return p;
+}
+
+void vboxsf_dir_info_free(struct vboxsf_dir_info *p)
+{
+	struct list_head *list, *pos, *tmp;
+
+	list = &p->info_list;
+	list_for_each_safe(pos, tmp, list) {
+		struct vboxsf_dir_buf *b;
+
+		b = list_entry(pos, struct vboxsf_dir_buf, head);
+		vboxsf_dir_buf_free(b);
+	}
+	kfree(p);
+}
+
+int vboxsf_dir_read_all(struct vboxsf_sbi *sbi, struct vboxsf_dir_info *sf_d,
+			u64 handle)
+{
+	struct vboxsf_dir_buf *b;
+	u32 entries, size;
+	int err = 0;
+	void *buf;
+
+	/* vboxsf_dirinfo returns 1 on end of dir */
+	while (err == 0) {
+		b = vboxsf_dir_buf_alloc(&sf_d->info_list);
+		if (!b) {
+			err = -ENOMEM;
+			break;
+		}
+
+		buf = b->buf;
+		size = b->free;
+
+		err = vboxsf_dirinfo(sbi->root, handle, NULL, 0, 0,
+				     &size, buf, &entries);
+		if (err < 0)
+			break;
+
+		b->entries += entries;
+		b->free -= size;
+		b->used += size;
+	}
+
+	if (b && b->used == 0)
+		vboxsf_dir_buf_free(b);
+
+	/* -EILSEQ means the host could not translate a filename, ignore */
+	if (err > 0 || err == -EILSEQ)
+		err = 0;
+
+	return err;
+}
+
+int vboxsf_query_case_sensitive(struct vboxsf_sbi *sbi)
+{
+	struct shfl_volinfo volinfo = {};
+	u32 buf_len;
+	int err;
+
+	buf_len = sizeof(volinfo);
+	err = vboxsf_fsinfo(sbi->root, 0, SHFL_INFO_GET | SHFL_INFO_VOLUME,
+			    &buf_len, &volinfo);
+	if (err)
+		return err;
+	if (buf_len < sizeof(volinfo))
+		return 0;
+
+	sbi->case_insensitive = !volinfo.properties.case_sensitive;
+	return 0;
+}
+
+int vboxsf_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
+
+	if (sbi->case_insensitive) {
+		fa->fsx_xflags |= FS_XFLAG_CASEFOLD;
+		fa->flags |= FS_CASEFOLD_FL;
+	}
+	return 0;
+}