On Fri, Aug 21, 2026, at 7:17 PM, Darrick J. Wong wrote:
> On Tue, Aug 11, 2026 at 05:17:50PM -0500, John Groves wrote:
>
> <snip>
>
> > > > + switch (fmh.ext_type) {
> > > > + case FAMFS_IOC_EXT_SIMPLE: {
> > > > + struct famfs_ioc_simple_ext *se_in = fmap_buf + next_offset;
> > > > +
> > > > + next_offset += (size_t)fmh.nextents * sizeof(*se_in);
> > > > + if (next_offset > fmh.fmap_size) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + meta->fm_nextents = fmh.nextents;
> > > > + meta->se = kcalloc(meta->fm_nextents, sizeof(*meta->se),
> > > > + GFP_KERNEL);
> > > > + if (!meta->se) {
> > > > + rc = -ENOMEM;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + for (i = 0; i < fmh.nextents; i++) {
> > > > + meta->se[i].dev_index = se_in[i].se_devindex;
> > > > + meta->se[i].ext_offset = se_in[i].se_offset;
> > > > + meta->se[i].ext_len = se_in[i].se_len;
> > > > +
> > > > + if (meta->se[i].dev_index >= FAMFS_MAX_DAXDEVS) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > + meta->dev_bitmap |= BIT_ULL(meta->se[i].dev_index);
> > > > + errs += famfs_check_ext_alignment(&meta->se[i]);
> > > > + extent_total += meta->se[i].ext_len;
> > >
> > > offset + length + entent_total can overflow, and file_size can be larger
> > > than MAX_LFS_FILESIZE. And overflow can wrap the DAX address back to 0
> > > and map the wrong memory.
> > >
> > > Maybe check_add_overflow() can be utilized ?
> >
> > Good idea, thanks!
>
> Yes, all those arithmetics should catch overflows.
>
> > >
> > >
> > > > + }
> > > > + break;
> > > > + }
> > > > +
> > > > + case FAMFS_IOC_EXT_INTERLEAVE: {
> > > > + s64 size_remainder = meta->file_size;
> > > > + u32 niext = fmh.nextents;
> > > > +
> > > > + meta->fm_niext = niext;
> > > > + meta->ie = kcalloc(niext, sizeof(*meta->ie), GFP_KERNEL);
> > > > + if (!meta->ie) {
> > > > + rc = -ENOMEM;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + /* Outer loop is over the separate interleaved extents */
> > > > + for (i = 0; i < niext; i++) {
> > > > + struct famfs_ioc_iext *ie_in = fmap_buf + next_offset;
> > > > + struct famfs_ioc_simple_ext *sie_in;
> > > > + u64 nstrips;
> > > > +
> > > > + next_offset += sizeof(*ie_in);
> > > > + if (next_offset > fmh.fmap_size) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + /* chunk_size must be exactly one supported alloc unit */
> > > > + if (ie_in->ie_chunk_size != PAGE_SIZE &&
> > > > + ie_in->ie_chunk_size != PMD_SIZE) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > + if (ie_in->ie_nbytes == 0) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + nstrips = ie_in->ie_nstrips;
> > > > + if (nstrips < 1) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + meta->ie[i].fie_chunk_size = ie_in->ie_chunk_size;
> > > > + meta->ie[i].fie_nstrips = ie_in->ie_nstrips;
> > > > + meta->ie[i].fie_nbytes = ie_in->ie_nbytes;
> > > > +
> > > > + /* The strip extents follow the interleaved-ext header */
> > > > + sie_in = fmap_buf + next_offset;
> > > > + next_offset += nstrips * sizeof(*sie_in);
> > > > + if (next_offset > fmh.fmap_size) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + meta->ie[i].ie_strips =
> > > > + kcalloc(nstrips,
> > > > + sizeof(meta->ie[i].ie_strips[0]),
> > > > + GFP_KERNEL);
> > > > + if (!meta->ie[i].ie_strips) {
> > > > + rc = -ENOMEM;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + /* Inner loop is over the strips */
> > > > + for (j = 0; j < nstrips; j++) {
> > > > + struct famfs_meta_simple_ext *so =
> > > > + &meta->ie[i].ie_strips[j];
> > > > +
> > > > + so->dev_index = sie_in[j].se_devindex;
> > > > + so->ext_offset = sie_in[j].se_offset;
> > > > + so->ext_len = sie_in[j].se_len;
> > > > +
> > > > + if (so->dev_index >= FAMFS_MAX_DAXDEVS) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > + meta->dev_bitmap |= BIT_ULL(so->dev_index);
> > > > + errs += famfs_check_ext_alignment(so);
> > > > + extent_total += so->ext_len;
> > > > + size_remainder -= so->ext_len;
> > >
> > > We use physical allocation size here to check logical file coverage,
> > > it doesn't make sense to me.
> > > For example, file_size can be 1MB and ie_nbytes only 4KB, but a 1MB
> > > ext_len makes this check pass, and you access the area after the first 4
> > > KB will fail,
> > > because it has no logical mapping.
> > >
> > > Maybe we should make sure the sum of ie_nbytes covers file_size, and
> > > separately check that each strip's ext_len is large enough for its
> > > assigned
> > > chunks ?
> >
> > Chapeau to you for actually studying this code. Not many have gone
> > there. It's arcane, but logically not too complicated.
> >
> > You're right that famfs_file_init_dax() doesn't check for pathological
> > strip sizes or overflows. It does do some basic checking, but would
> > not catch a short strip followed by one or more "correct" strips.
> > That stuff would indicate a buggy or malicious caller, since it
> > violates the fmap logic.
> >
> > However, the vma fault handler for interleaved files,
> > famfs_meta_to_dax_offset_interleaved(), *does* check for strip
> > overflows. It resolves a file offset to an offset in a specific
> > strip (based on strip count and chunk size), and then checks that
> > it falls within the strip and not past the end.
> >
> > Here is that code:
> >
> > /*
> > * MAP_CREATE only checks that the strips' combined
> > * length covers the file, not that each strip is large
> > * enough for the chunks striped onto it. Guard against a
> > * malformed fmap with an undersized strip so we never
> > * resolve to a dax offset past the strip's extent.
> > */
> > if (strip_offset >= strip->ext_len)
> > goto err_out;
> >
> > daxdev = famfs_daxdev_from_index(fsi, strip->dev_index, &rc);
> > if (!daxdev) {
> > meta->error = true;
> > return rc;
> > }
> >
> > iomap->addr = strip->ext_offset + strip_offset;
> > iomap->offset = file_offset;
> > iomap->length = min_t(loff_t, len, chunk_remainder);
> > iomap->length = min_t(loff_t, iomap->length,
> > strip->ext_len - strip_offset);
> > iomap->dax_dev = daxdev;
> > iomap->type = IOMAP_MAPPED;
> >
> > return 0;
> >
> > Since this condition is an error or malice on the part of the
> > MAP_CREATE caller, I'm comfortable with catching it at fault time.
>
> I think you should reject *any* bad mapping data at MAP_CREATE time
> because then you can catch application bugs early with an immediate
> error being sent to the famfs server. Don't let bad data into the
> kernel.
I can do that. I will note that the only application that does this (file
creation
during creat, cp or logplay in the famfs cli) definitively never has a shorter
strip
extent followed by a longer one (which would be true for there to be a strip
overflow that wasn't caught till fault() time.
but it's easy enough to check at MAP_CREATE so will do.
>
> > > > + }
> > > > + }
> > > > +
> > > > + if (size_remainder > 0) {
> > > > + /* Strips do not cover the whole file */
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > + break;
> > > > + }
> > > > +
> > > > + default:
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + if (errs > 0) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > + if (extent_total < meta->file_size) {
> > > > + rc = -EINVAL;
> > > > + goto out;
> > > > + }
> > > > +
> > > > + /* Publish the famfs metadata on inode->i_private */
> > > > + inode_lock(inode);
> > > > + if (inode->i_private) {
> > > > + rc = -EEXIST; /* file already has famfs metadata */
> > > > + } else {
> > > > + inode->i_private = meta;
> > > > + i_size_write(inode, meta->file_size);
> > > > + inode->i_flags |= S_DAX;
> > > > + meta = NULL; /* owned by the inode now */
> > > > + rc = 0;
> > > > + }
> > > > + inode_unlock(inode);
> > > > +
> > > > +out:
> > > > + kvfree(fmap_buf);
> > > > + if (meta)
> > > > + famfs_meta_free(meta);
> > > > + return rc;
> > > > +}
> > > > +
> > > > +/**
> > > > + * famfs_file_ioctl() - Top-level famfs file ioctl handler
> > > > + * @file: the file
> > > > + * @cmd: ioctl opcode
> > > > + * @arg: ioctl opcode argument (if any)
> > > > + */
> > > > +static long
> > > > +famfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long
> > > > arg)
> > > > +{
> > > > + struct inode *inode = file_inode(file);
> > > > + struct famfs_fs_info *fsi = inode->i_sb->s_fs_info;
> > > > + long rc;
> > > > +
> > > > + if (fsi->deverror && (cmd != FAMFSIOC_NOP))
> > > > + return -ENODEV;
> > > > +
> > > > + switch (cmd) {
> > > > + case FAMFSIOC_NOP:
> > > > + rc = 0;
> > > > + break;
> > > > +
> > > > + case FAMFSIOC_MAP_CREATE:
> > > > + rc = famfs_file_init_dax(file, (void __user *)arg);
> > > > + break;
> > > > +
> > > > + default:
> > > > + rc = -ENOTTY;
> > > > + break;
> > > > + }
> > > > +
> > > > + return rc;
> > > > +}
> > > > +
> > > > /*********************************************************************
> > > > * vm_operations
> > > > */
> > > > @@ -94,9 +400,25 @@ const struct vm_operations_struct famfs_file_vm_ops
> > > > = {
> > > > static ssize_t
> > > > famfs_file_invalid(struct inode *inode)
> > > > {
> > > > + struct famfs_file_meta *meta = inode->i_private;
> > > > + size_t i_size = i_size_read(inode);
> > > > +
> > > > + if (!meta) {
> > > > + pr_debug("%s: un-initialized famfs file\n", __func__);
> > > > + return -EIO;
> > > > + }
> > > > + if (meta->error) {
> > > > + pr_debug("%s: previously detected metadata errors\n", __func__);
> > > > + return -EIO;
> > > > + }
> > > > + if (i_size != meta->file_size) {
> > > > + pr_warn("%s: i_size overwritten from %ld to %ld\n",
> > > > + __func__, meta->file_size, i_size);
> > > > + meta->error = true;
> > > > + return -ENXIO;
> > > > + }
> > > > if (!IS_DAX(inode)) {
> > > > - pr_debug("%s: inode %llx IS_DAX is false\n",
> > > > - __func__, (u64)inode);
> > > > + pr_debug("%s: inode %llx IS_DAX is false\n", __func__, (u64)inode);
> > > > return -ENXIO;
> > > > }
> > > > return 0;
> > > > @@ -233,7 +555,7 @@ const struct file_operations famfs_file_operations
> > > > = {
> > > > /* Custom famfs operations */
> > > > .write_iter = famfs_dax_write_iter,
> > > > .read_iter = famfs_dax_read_iter,
> > > > - .unlocked_ioctl = NULL /*famfs_file_ioctl*/,
> > > > + .unlocked_ioctl = famfs_file_ioctl,
> > > > .mmap = famfs_file_mmap,
> > > >
> > >
> > > We don't have compat_ioctl handler, a 32-bit application on a 64-bit
> > > kernel will get ENOTTY, if we will have that scenario I think the handler
> > > should be added.
> > >
> > > Best regards,
> > > Richard Cheng.
> >
> > This one is simple but arcane. Here are the kconfig deps:
> >
> > FAMFS -> FS_DAX -> ZONE_DEVICE -> MEMORY_HOTPLUG
> >
> > And MEMORY_HOTPLUG is depends on 64BIT. So famfs is definitively 64BIT-only.
> >
> > In this series I added a direct dependency on 64BIT, to make it more
> > clear...
>
> compat_ioctl is for 32-bit programs calling into a 64-bit kernel.
>
> Granted a 32-bit program is probably not a good contender for famfs due
> to limited address space, and you could simply declare that you don't
> support 32-bit programs.
>
> --D
>
V13 already depends on 64BIT, so I think this is already done.
32 bit address space is not big enough to cover any of the intended use
cases for famfs.
Thanks Darrick!
John
