Revision aa76042a016474775ccd187c068669148c30c3bb authored by James Hogan on 27 May 2016, 21:25:23 UTC, committed by Ralf Baechle on 28 May 2016, 10:35:11 UTC
The Hardware page Table Walker (HTW) is being misconfigured on 64-bit
kernels. The PWSize.PS (pointer size) bit determines whether pointers
within directories are loaded as 32-bit or 64-bit addresses, but was
never being set to 1 for 64-bit kernels where the unsigned long in pgd_t
is 64-bits wide.

This actually reduces rather than improves performance when the HTW is
enabled on P6600 since the HTW is initiated lots, but walks are all
aborted due I think to bad intermediate pointers.

Since we were already taking the width of the PTEs into account by
setting PWSize.PTEW, which is the left shift applied to the page table
index *in addition to* the native pointer size, we also need to reduce
PTEW by 1 when PS=1. This is done by calculating PTEW based on the
relative size of pte_t compared to pgd_t.

Finally in order for the HTW to be used when PS=1, the appropriate
XK/XS/XU bits corresponding to the different 64-bit segments need to be
set in PWCtl. We enable only XU for now to enable walking for XUSeg.

Supporting walking for XKSeg would be a bit more involved so is left for
a future patch. It would either require the use of a per-CPU top level
base directory if supported by the HTW (a bit like pgd_current but with
a second entry pointing at swapper_pg_dir), or the HTW would prepend bit
63 of the address to the global directory index which doesn't really
match how we split user and kernel page directories.

Fixes: cab25bc7537b ("MIPS: Extend hardware table walking support to MIPS64")
Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13364/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
1 parent 6446e6c
Raw File
fhandle.c
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/exportfs.h>
#include <linux/fs_struct.h>
#include <linux/fsnotify.h>
#include <linux/personality.h>
#include <asm/uaccess.h>
#include "internal.h"
#include "mount.h"

static long do_sys_name_to_handle(struct path *path,
				  struct file_handle __user *ufh,
				  int __user *mnt_id)
{
	long retval;
	struct file_handle f_handle;
	int handle_dwords, handle_bytes;
	struct file_handle *handle = NULL;

	/*
	 * We need to make sure whether the file system
	 * support decoding of the file handle
	 */
	if (!path->dentry->d_sb->s_export_op ||
	    !path->dentry->d_sb->s_export_op->fh_to_dentry)
		return -EOPNOTSUPP;

	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
		return -EFAULT;

	if (f_handle.handle_bytes > MAX_HANDLE_SZ)
		return -EINVAL;

	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
			 GFP_KERNEL);
	if (!handle)
		return -ENOMEM;

	/* convert handle size to multiple of sizeof(u32) */
	handle_dwords = f_handle.handle_bytes >> 2;

	/* we ask for a non connected handle */
	retval = exportfs_encode_fh(path->dentry,
				    (struct fid *)handle->f_handle,
				    &handle_dwords,  0);
	handle->handle_type = retval;
	/* convert handle size to bytes */
	handle_bytes = handle_dwords * sizeof(u32);
	handle->handle_bytes = handle_bytes;
	if ((handle->handle_bytes > f_handle.handle_bytes) ||
	    (retval == FILEID_INVALID) || (retval == -ENOSPC)) {
		/* As per old exportfs_encode_fh documentation
		 * we could return ENOSPC to indicate overflow
		 * But file system returned 255 always. So handle
		 * both the values
		 */
		/*
		 * set the handle size to zero so we copy only
		 * non variable part of the file_handle
		 */
		handle_bytes = 0;
		retval = -EOVERFLOW;
	} else
		retval = 0;
	/* copy the mount id */
	if (copy_to_user(mnt_id, &real_mount(path->mnt)->mnt_id,
			 sizeof(*mnt_id)) ||
	    copy_to_user(ufh, handle,
			 sizeof(struct file_handle) + handle_bytes))
		retval = -EFAULT;
	kfree(handle);
	return retval;
}

/**
 * sys_name_to_handle_at: convert name to handle
 * @dfd: directory relative to which name is interpreted if not absolute
 * @name: name that should be converted to handle.
 * @handle: resulting file handle
 * @mnt_id: mount id of the file system containing the file
 * @flag: flag value to indicate whether to follow symlink or not
 *
 * @handle->handle_size indicate the space available to store the
 * variable part of the file handle in bytes. If there is not
 * enough space, the field is updated to return the minimum
 * value required.
 */
SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
		struct file_handle __user *, handle, int __user *, mnt_id,
		int, flag)
{
	struct path path;
	int lookup_flags;
	int err;

	if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
		return -EINVAL;

	lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
	if (flag & AT_EMPTY_PATH)
		lookup_flags |= LOOKUP_EMPTY;
	err = user_path_at(dfd, name, lookup_flags, &path);
	if (!err) {
		err = do_sys_name_to_handle(&path, handle, mnt_id);
		path_put(&path);
	}
	return err;
}

static struct vfsmount *get_vfsmount_from_fd(int fd)
{
	struct vfsmount *mnt;

	if (fd == AT_FDCWD) {
		struct fs_struct *fs = current->fs;
		spin_lock(&fs->lock);
		mnt = mntget(fs->pwd.mnt);
		spin_unlock(&fs->lock);
	} else {
		struct fd f = fdget(fd);
		if (!f.file)
			return ERR_PTR(-EBADF);
		mnt = mntget(f.file->f_path.mnt);
		fdput(f);
	}
	return mnt;
}

static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
{
	return 1;
}

static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
			     struct path *path)
{
	int retval = 0;
	int handle_dwords;

	path->mnt = get_vfsmount_from_fd(mountdirfd);
	if (IS_ERR(path->mnt)) {
		retval = PTR_ERR(path->mnt);
		goto out_err;
	}
	/* change the handle size to multiple of sizeof(u32) */
	handle_dwords = handle->handle_bytes >> 2;
	path->dentry = exportfs_decode_fh(path->mnt,
					  (struct fid *)handle->f_handle,
					  handle_dwords, handle->handle_type,
					  vfs_dentry_acceptable, NULL);
	if (IS_ERR(path->dentry)) {
		retval = PTR_ERR(path->dentry);
		goto out_mnt;
	}
	return 0;
out_mnt:
	mntput(path->mnt);
out_err:
	return retval;
}

static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
		   struct path *path)
{
	int retval = 0;
	struct file_handle f_handle;
	struct file_handle *handle = NULL;

	/*
	 * With handle we don't look at the execute bit on the
	 * the directory. Ideally we would like CAP_DAC_SEARCH.
	 * But we don't have that
	 */
	if (!capable(CAP_DAC_READ_SEARCH)) {
		retval = -EPERM;
		goto out_err;
	}
	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
		retval = -EFAULT;
		goto out_err;
	}
	if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
	    (f_handle.handle_bytes == 0)) {
		retval = -EINVAL;
		goto out_err;
	}
	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
			 GFP_KERNEL);
	if (!handle) {
		retval = -ENOMEM;
		goto out_err;
	}
	/* copy the full handle */
	*handle = f_handle;
	if (copy_from_user(&handle->f_handle,
			   &ufh->f_handle,
			   f_handle.handle_bytes)) {
		retval = -EFAULT;
		goto out_handle;
	}

	retval = do_handle_to_path(mountdirfd, handle, path);

out_handle:
	kfree(handle);
out_err:
	return retval;
}

long do_handle_open(int mountdirfd,
		    struct file_handle __user *ufh, int open_flag)
{
	long retval = 0;
	struct path path;
	struct file *file;
	int fd;

	retval = handle_to_path(mountdirfd, ufh, &path);
	if (retval)
		return retval;

	fd = get_unused_fd_flags(open_flag);
	if (fd < 0) {
		path_put(&path);
		return fd;
	}
	file = file_open_root(path.dentry, path.mnt, "", open_flag, 0);
	if (IS_ERR(file)) {
		put_unused_fd(fd);
		retval =  PTR_ERR(file);
	} else {
		retval = fd;
		fsnotify_open(file);
		fd_install(fd, file);
	}
	path_put(&path);
	return retval;
}

/**
 * sys_open_by_handle_at: Open the file handle
 * @mountdirfd: directory file descriptor
 * @handle: file handle to be opened
 * @flag: open flags.
 *
 * @mountdirfd indicate the directory file descriptor
 * of the mount point. file handle is decoded relative
 * to the vfsmount pointed by the @mountdirfd. @flags
 * value is same as the open(2) flags.
 */
SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
		struct file_handle __user *, handle,
		int, flags)
{
	long ret;

	if (force_o_largefile())
		flags |= O_LARGEFILE;

	ret = do_handle_open(mountdirfd, handle, flags);
	return ret;
}
back to top