Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

1 files changed, 702 insertions, 0 deletions

diff --git a/fs/ioctl.c b/fs/ioctl.c
new file mode 100644
index 000000000..1c152c2b1
--- /dev/null
+++ b/fs/ioctl.c
@@ -0,0 +1,702 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ioctl.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/syscalls.h>
+#include <linux/mm.h>
+#include <linux/capability.h>
+#include <linux/compat.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/security.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
+#include <linux/falloc.h>
+#include <linux/sched/signal.h>
+#include <linux/fiemap.h>
+#include <linux/mount.h>
+#include <linux/fscrypt.h>
+#include <linux/fileattr.h>
+
+#include "internal.h"
+
+#include <asm/ioctls.h>
+
+/* So that the fiemap access checks can't overflow on 32 bit machines. */
+#define FIEMAP_MAX_EXTENTS	(UINT_MAX / sizeof(struct fiemap_extent))
+
+/**
+ * vfs_ioctl - call filesystem specific ioctl methods
+ * @filp:	open file to invoke ioctl method on
+ * @cmd:	ioctl command to execute
+ * @arg:	command-specific argument for ioctl
+ *
+ * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise
+ * returns -ENOTTY.
+ *
+ * Returns 0 on success, -errno on error.
+ */
+static int vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	int error = -ENOTTY;
+
+	if (!filp->f_op->unlocked_ioctl)
+		goto out;
+
+	error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
+	if (error == -ENOIOCTLCMD)
+		error = -ENOTTY;
+ out:
+	return error;
+}
+
+static int ioctl_fibmap(struct file *filp, int __user *p)
+{
+	struct inode *inode = file_inode(filp);
+	struct super_block *sb = inode->i_sb;
+	int error, ur_block;
+	sector_t block;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	error = get_user(ur_block, p);
+	if (error)
+		return error;
+
+	if (ur_block < 0)
+		return -EINVAL;
+
+	block = ur_block;
+	error = bmap(inode, &block);
+
+	if (block > INT_MAX) {
+		error = -ERANGE;
+		pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n",
+				    current->comm, task_pid_nr(current),
+				    sb->s_id, filp);
+	}
+
+	if (error)
+		ur_block = 0;
+	else
+		ur_block = block;
+
+	if (put_user(ur_block, p))
+		error = -EFAULT;
+
+	return error;
+}
+
+/**
+ * fiemap_fill_next_extent - Fiemap helper function
+ * @fieinfo:	Fiemap context passed into ->fiemap
+ * @logical:	Extent logical start offset, in bytes
+ * @phys:	Extent physical start offset, in bytes
+ * @len:	Extent length, in bytes
+ * @flags:	FIEMAP_EXTENT flags that describe this extent
+ *
+ * Called from file system ->fiemap callback. Will populate extent
+ * info as passed in via arguments and copy to user memory. On
+ * success, extent count on fieinfo is incremented.
+ *
+ * Returns 0 on success, -errno on error, 1 if this was the last
+ * extent that will fit in user array.
+ */
+int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
+			    u64 phys, u64 len, u32 flags)
+{
+	struct fiemap_extent extent;
+	struct fiemap_extent __user *dest = fieinfo->fi_extents_start;
+
+	/* only count the extents */
+	if (fieinfo->fi_extents_max == 0) {
+		fieinfo->fi_extents_mapped++;
+		return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+	}
+
+	if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
+		return 1;
+
+#define SET_UNKNOWN_FLAGS	(FIEMAP_EXTENT_DELALLOC)
+#define SET_NO_UNMOUNTED_IO_FLAGS	(FIEMAP_EXTENT_DATA_ENCRYPTED)
+#define SET_NOT_ALIGNED_FLAGS	(FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
+
+	if (flags & SET_UNKNOWN_FLAGS)
+		flags |= FIEMAP_EXTENT_UNKNOWN;
+	if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
+		flags |= FIEMAP_EXTENT_ENCODED;
+	if (flags & SET_NOT_ALIGNED_FLAGS)
+		flags |= FIEMAP_EXTENT_NOT_ALIGNED;
+
+	memset(&extent, 0, sizeof(extent));
+	extent.fe_logical = logical;
+	extent.fe_physical = phys;
+	extent.fe_length = len;
+	extent.fe_flags = flags;
+
+	dest += fieinfo->fi_extents_mapped;
+	if (copy_to_user(dest, &extent, sizeof(extent)))
+		return -EFAULT;
+
+	fieinfo->fi_extents_mapped++;
+	if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
+		return 1;
+	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+}
+EXPORT_SYMBOL(fiemap_fill_next_extent);
+
+/**
+ * fiemap_prep - check validity of requested flags for fiemap
+ * @inode:	Inode to operate on
+ * @fieinfo:	Fiemap context passed into ->fiemap
+ * @start:	Start of the mapped range
+ * @len:	Length of the mapped range, can be truncated by this function.
+ * @supported_flags:	Set of fiemap flags that the file system understands
+ *
+ * This function must be called from each ->fiemap instance to validate the
+ * fiemap request against the file system parameters.
+ *
+ * Returns 0 on success, or a negative error on failure.
+ */
+int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		u64 start, u64 *len, u32 supported_flags)
+{
+	u64 maxbytes = inode->i_sb->s_maxbytes;
+	u32 incompat_flags;
+	int ret = 0;
+
+	if (*len == 0)
+		return -EINVAL;
+	if (start >= maxbytes)
+		return -EFBIG;
+
+	/*
+	 * Shrink request scope to what the fs can actually handle.
+	 */
+	if (*len > maxbytes || (maxbytes - *len) < start)
+		*len = maxbytes - start;
+
+	supported_flags |= FIEMAP_FLAG_SYNC;
+	supported_flags &= FIEMAP_FLAGS_COMPAT;
+	incompat_flags = fieinfo->fi_flags & ~supported_flags;
+	if (incompat_flags) {
+		fieinfo->fi_flags = incompat_flags;
+		return -EBADR;
+	}
+
+	if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC)
+		ret = filemap_write_and_wait(inode->i_mapping);
+	return ret;
+}
+EXPORT_SYMBOL(fiemap_prep);
+
+static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap)
+{
+	struct fiemap fiemap;
+	struct fiemap_extent_info fieinfo = { 0, };
+	struct inode *inode = file_inode(filp);
+	int error;
+
+	if (!inode->i_op->fiemap)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap)))
+		return -EFAULT;
+
+	if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
+		return -EINVAL;
+
+	fieinfo.fi_flags = fiemap.fm_flags;
+	fieinfo.fi_extents_max = fiemap.fm_extent_count;
+	fieinfo.fi_extents_start = ufiemap->fm_extents;
+
+	error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start,
+			fiemap.fm_length);
+
+	fiemap.fm_flags = fieinfo.fi_flags;
+	fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
+	if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap)))
+		error = -EFAULT;
+
+	return error;
+}
+
+static int ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
+			    u64 off, u64 olen, u64 destoff)
+{
+	CLASS(fd, src_file)(srcfd);
+	loff_t cloned;
+	int ret;
+
+	if (fd_empty(src_file))
+		return -EBADF;
+	cloned = vfs_clone_file_range(fd_file(src_file), off, dst_file, destoff,
+				      olen, 0);
+	if (cloned < 0)
+		ret = cloned;
+	else if (olen && cloned != olen)
+		ret = -EINVAL;
+	else
+		ret = 0;
+	return ret;
+}
+
+static int ioctl_file_clone_range(struct file *file,
+				  struct file_clone_range __user *argp)
+{
+	struct file_clone_range args;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+	return ioctl_file_clone(file, args.src_fd, args.src_offset,
+				args.src_length, args.dest_offset);
+}
+
+/*
+ * This provides compatibility with legacy XFS pre-allocation ioctls
+ * which predate the fallocate syscall.
+ *
+ * Only the l_start, l_len and l_whence fields of the 'struct space_resv'
+ * are used here, rest are ignored.
+ */
+static int ioctl_preallocate(struct file *filp, int mode, void __user *argp)
+{
+	struct inode *inode = file_inode(filp);
+	struct space_resv sr;
+
+	if (copy_from_user(&sr, argp, sizeof(sr)))
+		return -EFAULT;
+
+	switch (sr.l_whence) {
+	case SEEK_SET:
+		break;
+	case SEEK_CUR:
+		sr.l_start += filp->f_pos;
+		break;
+	case SEEK_END:
+		sr.l_start += i_size_read(inode);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start,
+			sr.l_len);
+}
+
+/* on ia32 l_start is on a 32-bit boundary */
+#if defined CONFIG_COMPAT && defined(CONFIG_X86_64)
+/* just account for different alignment */
+static int compat_ioctl_preallocate(struct file *file, int mode,
+				    struct space_resv_32 __user *argp)
+{
+	struct inode *inode = file_inode(file);
+	struct space_resv_32 sr;
+
+	if (copy_from_user(&sr, argp, sizeof(sr)))
+		return -EFAULT;
+
+	switch (sr.l_whence) {
+	case SEEK_SET:
+		break;
+	case SEEK_CUR:
+		sr.l_start += file->f_pos;
+		break;
+	case SEEK_END:
+		sr.l_start += i_size_read(inode);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return vfs_fallocate(file, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
+}
+#endif
+
+static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p)
+{
+	switch (cmd) {
+	case FIBMAP:
+		return ioctl_fibmap(filp, p);
+	case FS_IOC_RESVSP:
+	case FS_IOC_RESVSP64:
+		return ioctl_preallocate(filp, 0, p);
+	case FS_IOC_UNRESVSP:
+	case FS_IOC_UNRESVSP64:
+		return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p);
+	case FS_IOC_ZERO_RANGE:
+		return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p);
+	}
+
+	return -ENOIOCTLCMD;
+}
+
+static int ioctl_fionbio(struct file *filp, int __user *argp)
+{
+	unsigned int flag;
+	int on, error;
+
+	error = get_user(on, argp);
+	if (error)
+		return error;
+	flag = O_NONBLOCK;
+#ifdef __sparc__
+	/* SunOS compatibility item. */
+	if (O_NONBLOCK != O_NDELAY)
+		flag |= O_NDELAY;
+#endif
+	spin_lock(&filp->f_lock);
+	if (on)
+		filp->f_flags |= flag;
+	else
+		filp->f_flags &= ~flag;
+	spin_unlock(&filp->f_lock);
+	return error;
+}
+
+static int ioctl_fioasync(unsigned int fd, struct file *filp,
+			  int __user *argp)
+{
+	unsigned int flag;
+	int on, error;
+
+	error = get_user(on, argp);
+	if (error)
+		return error;
+	flag = on ? FASYNC : 0;
+
+	/* Did FASYNC state change ? */
+	if ((flag ^ filp->f_flags) & FASYNC) {
+		if (filp->f_op->fasync)
+			/* fasync() adjusts filp->f_flags */
+			error = filp->f_op->fasync(fd, filp, on);
+		else
+			error = -ENOTTY;
+	}
+	return error < 0 ? error : 0;
+}
+
+static int ioctl_fsfreeze(struct file *filp)
+{
+	struct super_block *sb = file_inode(filp)->i_sb;
+
+	if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* If filesystem doesn't support freeze feature, return. */
+	if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL)
+		return -EOPNOTSUPP;
+
+	/* Freeze */
+	if (sb->s_op->freeze_super)
+		return sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE, NULL);
+	return freeze_super(sb, FREEZE_HOLDER_USERSPACE, NULL);
+}
+
+static int ioctl_fsthaw(struct file *filp)
+{
+	struct super_block *sb = file_inode(filp)->i_sb;
+
+	if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* Thaw */
+	if (sb->s_op->thaw_super)
+		return sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE, NULL);
+	return thaw_super(sb, FREEZE_HOLDER_USERSPACE, NULL);
+}
+
+static int ioctl_file_dedupe_range(struct file *file,
+				   struct file_dedupe_range __user *argp)
+{
+	struct file_dedupe_range *same = NULL;
+	int ret;
+	unsigned long size;
+	u16 count;
+
+	if (get_user(count, &argp->dest_count)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	size = struct_size(same, info, count);
+	if (size > PAGE_SIZE) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	same = memdup_user(argp, size);
+	if (IS_ERR(same)) {
+		ret = PTR_ERR(same);
+		same = NULL;
+		goto out;
+	}
+
+	same->dest_count = count;
+	ret = vfs_dedupe_file_range(file, same);
+	if (ret)
+		goto out;
+
+	ret = copy_to_user(argp, same, size);
+	if (ret)
+		ret = -EFAULT;
+
+out:
+	kfree(same);
+	return ret;
+}
+
+static int ioctl_getfsuuid(struct file *file, void __user *argp)
+{
+	struct super_block *sb = file_inode(file)->i_sb;
+	struct fsuuid2 u = { .len = sb->s_uuid_len, };
+
+	if (!sb->s_uuid_len)
+		return -ENOTTY;
+
+	memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len);
+
+	return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0;
+}
+
+static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp)
+{
+	struct super_block *sb = file_inode(file)->i_sb;
+
+	if (!strlen(sb->s_sysfs_name))
+		return -ENOTTY;
+
+	struct fs_sysfs_path u = {};
+
+	u.len = scnprintf(u.name, sizeof(u.name), "%s/%s", sb->s_type->name, sb->s_sysfs_name);
+
+	return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0;
+}
+
+/*
+ * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
+ * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
+ *
+ * When you add any new common ioctls to the switches above and below,
+ * please ensure they have compatible arguments in compat mode.
+ *
+ * The LSM mailing list should also be notified of any command additions or
+ * changes, as specific LSMs may be affected.
+ */
+static int do_vfs_ioctl(struct file *filp, unsigned int fd,
+			unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct inode *inode = file_inode(filp);
+
+	switch (cmd) {
+	case FIOCLEX:
+		set_close_on_exec(fd, 1);
+		return 0;
+
+	case FIONCLEX:
+		set_close_on_exec(fd, 0);
+		return 0;
+
+	case FIONBIO:
+		return ioctl_fionbio(filp, argp);
+
+	case FIOASYNC:
+		return ioctl_fioasync(fd, filp, argp);
+
+	case FIOQSIZE:
+		if (S_ISDIR(inode->i_mode) ||
+		    (S_ISREG(inode->i_mode) && !IS_ANON_FILE(inode)) ||
+		    S_ISLNK(inode->i_mode)) {
+			loff_t res = inode_get_bytes(inode);
+			return copy_to_user(argp, &res, sizeof(res)) ?
+					    -EFAULT : 0;
+		}
+
+		return -ENOTTY;
+
+	case FIFREEZE:
+		return ioctl_fsfreeze(filp);
+
+	case FITHAW:
+		return ioctl_fsthaw(filp);
+
+	case FS_IOC_FIEMAP:
+		return ioctl_fiemap(filp, argp);
+
+	case FIGETBSZ:
+		/* anon_bdev filesystems may not have a block size */
+		if (!inode->i_sb->s_blocksize)
+			return -EINVAL;
+
+		return put_user(inode->i_sb->s_blocksize, (int __user *)argp);
+
+	case FICLONE:
+		return ioctl_file_clone(filp, arg, 0, 0, 0);
+
+	case FICLONERANGE:
+		return ioctl_file_clone_range(filp, argp);
+
+	case FIDEDUPERANGE:
+		return ioctl_file_dedupe_range(filp, argp);
+
+	case FIONREAD:
+		if (!S_ISREG(inode->i_mode) || IS_ANON_FILE(inode))
+			return vfs_ioctl(filp, cmd, arg);
+
+		return put_user(i_size_read(inode) - filp->f_pos,
+				(int __user *)argp);
+
+	case FS_IOC_GETFLAGS:
+		return ioctl_getflags(filp, argp);
+
+	case FS_IOC_SETFLAGS:
+		return ioctl_setflags(filp, argp);
+
+	case FS_IOC_FSGETXATTR:
+		return ioctl_fsgetxattr(filp, argp);
+
+	case FS_IOC_FSSETXATTR:
+		return ioctl_fssetxattr(filp, argp);
+
+	case FS_IOC_GETFSUUID:
+		return ioctl_getfsuuid(filp, argp);
+
+	case FS_IOC_GETFSSYSFSPATH:
+		return ioctl_get_fs_sysfs_path(filp, argp);
+
+	default:
+		if (S_ISREG(inode->i_mode) && !IS_ANON_FILE(inode))
+			return file_ioctl(filp, cmd, argp);
+		break;
+	}
+
+	return -ENOIOCTLCMD;
+}
+
+SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
+{
+	CLASS(fd, f)(fd);
+	int error;
+
+	if (fd_empty(f))
+		return -EBADF;
+
+	error = security_file_ioctl(fd_file(f), cmd, arg);
+	if (error)
+		return error;
+
+	error = do_vfs_ioctl(fd_file(f), fd, cmd, arg);
+	if (error == -ENOIOCTLCMD)
+		error = vfs_ioctl(fd_file(f), cmd, arg);
+
+	return error;
+}
+
+#ifdef CONFIG_COMPAT
+/**
+ * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation
+ * @file: The file to operate on.
+ * @cmd: The ioctl command number.
+ * @arg: The argument to the ioctl.
+ *
+ * This is not normally called as a function, but instead set in struct
+ * file_operations as
+ *
+ *     .compat_ioctl = compat_ptr_ioctl,
+ *
+ * On most architectures, the compat_ptr_ioctl() just passes all arguments
+ * to the corresponding ->ioctl handler. The exception is arch/s390, where
+ * compat_ptr() clears the top bit of a 32-bit pointer value, so user space
+ * pointers to the second 2GB alias the first 2GB, as is the case for
+ * native 32-bit s390 user space.
+ *
+ * The compat_ptr_ioctl() function must therefore be used only with ioctl
+ * functions that either ignore the argument or pass a pointer to a
+ * compatible data type.
+ *
+ * If any ioctl command handled by fops->unlocked_ioctl passes a plain
+ * integer instead of a pointer, or any of the passed data types
+ * is incompatible between 32-bit and 64-bit architectures, a proper
+ * handler is required instead of compat_ptr_ioctl.
+ */
+long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	if (!file->f_op->unlocked_ioctl)
+		return -ENOIOCTLCMD;
+
+	return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
+}
+EXPORT_SYMBOL(compat_ptr_ioctl);
+
+COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
+		       compat_ulong_t, arg)
+{
+	CLASS(fd, f)(fd);
+	int error;
+
+	if (fd_empty(f))
+		return -EBADF;
+
+	error = security_file_ioctl_compat(fd_file(f), cmd, arg);
+	if (error)
+		return error;
+
+	switch (cmd) {
+	/* FICLONE takes an int argument, so don't use compat_ptr() */
+	case FICLONE:
+		error = ioctl_file_clone(fd_file(f), arg, 0, 0, 0);
+		break;
+
+#if defined(CONFIG_X86_64)
+	/* these get messy on amd64 due to alignment differences */
+	case FS_IOC_RESVSP_32:
+	case FS_IOC_RESVSP64_32:
+		error = compat_ioctl_preallocate(fd_file(f), 0, compat_ptr(arg));
+		break;
+	case FS_IOC_UNRESVSP_32:
+	case FS_IOC_UNRESVSP64_32:
+		error = compat_ioctl_preallocate(fd_file(f), FALLOC_FL_PUNCH_HOLE,
+				compat_ptr(arg));
+		break;
+	case FS_IOC_ZERO_RANGE_32:
+		error = compat_ioctl_preallocate(fd_file(f), FALLOC_FL_ZERO_RANGE,
+				compat_ptr(arg));
+		break;
+#endif
+
+	/*
+	 * These access 32-bit values anyway so no further handling is
+	 * necessary.
+	 */
+	case FS_IOC32_GETFLAGS:
+	case FS_IOC32_SETFLAGS:
+		cmd = (cmd == FS_IOC32_GETFLAGS) ?
+			FS_IOC_GETFLAGS : FS_IOC_SETFLAGS;
+		fallthrough;
+	/*
+	 * everything else in do_vfs_ioctl() takes either a compatible
+	 * pointer argument or no argument -- call it with a modified
+	 * argument.
+	 */
+	default:
+		error = do_vfs_ioctl(fd_file(f), fd, cmd,
+				     (unsigned long)compat_ptr(arg));
+		if (error != -ENOIOCTLCMD)
+			break;
+
+		if (fd_file(f)->f_op->compat_ioctl)
+			error = fd_file(f)->f_op->compat_ioctl(fd_file(f), cmd, arg);
+		if (error == -ENOIOCTLCMD)
+			error = -ENOTTY;
+		break;
+	}
+	return error;
+}
+#endif