* Re: [PATCH v2 11/16] staging: vme_user: replace deprecated mmap hook with mmap_prepare
From: Suren Baghdasaryan @ 2026-03-19 15:19 UTC (permalink / raw)
To: Lorenzo Stoakes (Oracle)
Cc: Andrew Morton, Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Michal Hocko, Jann Horn, Pedro Falcato,
linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <8cdad898-b306-40fe-a367-efe7147f83b9@lucifer.local>
On Thu, Mar 19, 2026 at 7:55 AM Lorenzo Stoakes (Oracle) <ljs@kernel.org> wrote:
>
> On Tue, Mar 17, 2026 at 02:32:16PM -0700, Suren Baghdasaryan wrote:
> > On Tue, Mar 17, 2026 at 2:26 PM Suren Baghdasaryan <surenb@google.com> wrote:
> > >
> > > On Mon, Mar 16, 2026 at 2:14 PM Lorenzo Stoakes (Oracle) <ljs@kernel.org> wrote:
> > > >
> > > > The f_op->mmap interface is deprecated, so update driver to use its
> > > > successor, mmap_prepare.
> > > >
> > > > The driver previously used vm_iomap_memory(), so this change replaces it
> > > > with its mmap_prepare equivalent, mmap_action_simple_ioremap().
> > > >
> > > > Functions that wrap mmap() are also converted to wrap mmap_prepare()
> > > > instead.
> > > >
> > > > Also update the documentation accordingly.
> > > >
> > > > Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
> > > > ---
> > > > Documentation/driver-api/vme.rst | 2 +-
> > > > drivers/staging/vme_user/vme.c | 20 +++++------
> > > > drivers/staging/vme_user/vme.h | 2 +-
> > > > drivers/staging/vme_user/vme_user.c | 51 +++++++++++++++++------------
> > > > 4 files changed, 42 insertions(+), 33 deletions(-)
> > > >
> > > > diff --git a/Documentation/driver-api/vme.rst b/Documentation/driver-api/vme.rst
> > > > index c0b475369de0..7111999abc14 100644
> > > > --- a/Documentation/driver-api/vme.rst
> > > > +++ b/Documentation/driver-api/vme.rst
> > > > @@ -107,7 +107,7 @@ The function :c:func:`vme_master_read` can be used to read from and
> > > >
> > > > In addition to simple reads and writes, :c:func:`vme_master_rmw` is provided to
> > > > do a read-modify-write transaction. Parts of a VME window can also be mapped
> > > > -into user space memory using :c:func:`vme_master_mmap`.
> > > > +into user space memory using :c:func:`vme_master_mmap_prepare`.
> > > >
> > > >
> > > > Slave windows
> > > > diff --git a/drivers/staging/vme_user/vme.c b/drivers/staging/vme_user/vme.c
> > > > index f10a00c05f12..7220aba7b919 100644
> > > > --- a/drivers/staging/vme_user/vme.c
> > > > +++ b/drivers/staging/vme_user/vme.c
> > > > @@ -735,9 +735,9 @@ unsigned int vme_master_rmw(struct vme_resource *resource, unsigned int mask,
> > > > EXPORT_SYMBOL(vme_master_rmw);
> > > >
> > > > /**
> > > > - * vme_master_mmap - Mmap region of VME master window.
> > > > + * vme_master_mmap_prepare - Mmap region of VME master window.
> > > > * @resource: Pointer to VME master resource.
> > > > - * @vma: Pointer to definition of user mapping.
> > > > + * @desc: Pointer to descriptor of user mapping.
> > > > *
> > > > * Memory map a region of the VME master window into user space.
> > > > *
> > > > @@ -745,12 +745,13 @@ EXPORT_SYMBOL(vme_master_rmw);
> > > > * resource or -EFAULT if map exceeds window size. Other generic mmap
> > > > * errors may also be returned.
> > > > */
> > > > -int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma)
> > > > +int vme_master_mmap_prepare(struct vme_resource *resource,
> > > > + struct vm_area_desc *desc)
> > > > {
> > > > + const unsigned long vma_size = vma_desc_size(desc);
> > > > struct vme_bridge *bridge = find_bridge(resource);
> > > > struct vme_master_resource *image;
> > > > phys_addr_t phys_addr;
> > > > - unsigned long vma_size;
> > > >
> > > > if (resource->type != VME_MASTER) {
> > > > dev_err(bridge->parent, "Not a master resource\n");
> > > > @@ -758,19 +759,18 @@ int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma)
> > > > }
> > > >
> > > > image = list_entry(resource->entry, struct vme_master_resource, list);
> > > > - phys_addr = image->bus_resource.start + (vma->vm_pgoff << PAGE_SHIFT);
> > > > - vma_size = vma->vm_end - vma->vm_start;
> > > > + phys_addr = image->bus_resource.start + (desc->pgoff << PAGE_SHIFT);
> > > >
> > > > if (phys_addr + vma_size > image->bus_resource.end + 1) {
> > > > dev_err(bridge->parent, "Map size cannot exceed the window size\n");
> > > > return -EFAULT;
> > > > }
> > > >
> > > > - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
> > > > -
> > > > - return vm_iomap_memory(vma, phys_addr, vma->vm_end - vma->vm_start);
> > > > + desc->page_prot = pgprot_noncached(desc->page_prot);
> > > > + mmap_action_simple_ioremap(desc, phys_addr, vma_size);
> > > > + return 0;
> > > > }
> > > > -EXPORT_SYMBOL(vme_master_mmap);
> > > > +EXPORT_SYMBOL(vme_master_mmap_prepare);
> > > >
> > > > /**
> > > > * vme_master_free - Free VME master window
> > > > diff --git a/drivers/staging/vme_user/vme.h b/drivers/staging/vme_user/vme.h
> > > > index 797e9940fdd1..b6413605ea49 100644
> > > > --- a/drivers/staging/vme_user/vme.h
> > > > +++ b/drivers/staging/vme_user/vme.h
> > > > @@ -151,7 +151,7 @@ ssize_t vme_master_read(struct vme_resource *resource, void *buf, size_t count,
> > > > ssize_t vme_master_write(struct vme_resource *resource, void *buf, size_t count, loff_t offset);
> > > > unsigned int vme_master_rmw(struct vme_resource *resource, unsigned int mask, unsigned int compare,
> > > > unsigned int swap, loff_t offset);
> > > > -int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma);
> > > > +int vme_master_mmap_prepare(struct vme_resource *resource, struct vm_area_desc *desc);
> > > > void vme_master_free(struct vme_resource *resource);
> > > >
> > > > struct vme_resource *vme_dma_request(struct vme_dev *vdev, u32 route);
> > > > diff --git a/drivers/staging/vme_user/vme_user.c b/drivers/staging/vme_user/vme_user.c
> > > > index d95dd7d9190a..11e25c2f6b0a 100644
> > > > --- a/drivers/staging/vme_user/vme_user.c
> > > > +++ b/drivers/staging/vme_user/vme_user.c
> > > > @@ -446,24 +446,14 @@ static void vme_user_vm_close(struct vm_area_struct *vma)
> > > > kfree(vma_priv);
> > > > }
> > > >
> > > > -static const struct vm_operations_struct vme_user_vm_ops = {
> > > > - .open = vme_user_vm_open,
> > > > - .close = vme_user_vm_close,
> > > > -};
> > > > -
> > > > -static int vme_user_master_mmap(unsigned int minor, struct vm_area_struct *vma)
> > > > +static int vme_user_vm_mapped(unsigned long start, unsigned long end, pgoff_t pgoff,
> > > > + const struct file *file, void **vm_private_data)
> > > > {
> > > > - int err;
> > > > + const unsigned int minor = iminor(file_inode(file));
> > > > struct vme_user_vma_priv *vma_priv;
> > > >
> > > > mutex_lock(&image[minor].mutex);
> > > >
> > > > - err = vme_master_mmap(image[minor].resource, vma);
> > > > - if (err) {
> > > > - mutex_unlock(&image[minor].mutex);
> > > > - return err;
> > > > - }
> > > > -
> > >
> > > Ok, this changes the set of the operations performed under image[minor].mutex.
> > > Before we had:
> > >
> > > mutex_lock(&image[minor].mutex);
> > > vme_master_mmap();
> > > <some final adjustments>
> > > mutex_unlock(&image[minor].mutex);
> > >
> > > Now we have:
> > >
> > > mutex_lock(&image[minor].mutex);
> > > vme_master_mmap_prepare()
> > > mutex_unlock(&image[minor].mutex);
> > > vm_iomap_memory();
> > > mutex_lock(&image[minor].mutex);
> > > vme_user_vm_mapped(); // <some final adjustments>
> > > mutex_unlock(&image[minor].mutex);
> > >
> > > I think as long as image[minor] does not change while we are not
> > > holding the mutex we should be safe, and looking at the code it seems
> > > to be the case. But I'm not familiar with this driver and might be
> > > wrong. Worth double-checking.
>
> The file is pinned for the duration, the mutex is associated with the file,
> so there's no sane world in which that could be problematic.
>
> Keeping in mind that we manipulate stuff on vme_user_vm_close() that
> directly acceses image[minor] at an arbitary time.
That was my understanding as well. Thanks for confirming.
>
> >
> > A side note: if we had to hold the mutex across all those operations I
> > think we would need to take the mutex in the vm_ops->mmap_prepare and
> > add a vm_ops->map_failed hook or something along that line to drop the
> > mutex in case mmap_action_complete() fails. Not sure if we will have
> > such cases though...
>
> No, I don't want to do this if it can be at all avoided. You should in
> nearly any sane circumstance be able to defer things until the mapped hook
> anyway.
>
> Also a merge can happen too after an .mmap_prepare, so we'd have to have
> some 'success' hook and I'm just not going there it'll end up open to abuse
> again.
>
> (We do have success and error filtering hooks right now, sadly, but they're
> really for hugetlb and I plan to find a way to get rid of them).
>
> The mmap_prepare is meant to essentially be as stateless as possible.
Yes, I also hope we won't encounter cases requiring us to keep any
state information between the mmap_prepare and mapped stages.
>
> Anyway I don't think it's relevant here.
>
> >
> > >
> > > > vma_priv = kmalloc_obj(*vma_priv);
> > > > if (!vma_priv) {
> > > > mutex_unlock(&image[minor].mutex);
> > > > @@ -472,22 +462,41 @@ static int vme_user_master_mmap(unsigned int minor, struct vm_area_struct *vma)
> > > >
> > > > vma_priv->minor = minor;
> > > > refcount_set(&vma_priv->refcnt, 1);
> > > > - vma->vm_ops = &vme_user_vm_ops;
> > > > - vma->vm_private_data = vma_priv;
> > > > -
> > > > + *vm_private_data = vma_priv;
> > > > image[minor].mmap_count++;
> > > >
> > > > mutex_unlock(&image[minor].mutex);
> > > > -
> > > > return 0;
> > > > }
> > > >
> > > > -static int vme_user_mmap(struct file *file, struct vm_area_struct *vma)
> > > > +static const struct vm_operations_struct vme_user_vm_ops = {
> > > > + .mapped = vme_user_vm_mapped,
> > > > + .open = vme_user_vm_open,
> > > > + .close = vme_user_vm_close,
> > > > +};
> > > > +
> > > > +static int vme_user_master_mmap_prepare(unsigned int minor,
> > > > + struct vm_area_desc *desc)
> > > > +{
> > > > + int err;
> > > > +
> > > > + mutex_lock(&image[minor].mutex);
> > > > +
> > > > + err = vme_master_mmap_prepare(image[minor].resource, desc);
> > > > + if (!err)
> > > > + desc->vm_ops = &vme_user_vm_ops;
> > > > +
> > > > + mutex_unlock(&image[minor].mutex);
> > > > + return err;
> > > > +}
> > > > +
> > > > +static int vme_user_mmap_prepare(struct vm_area_desc *desc)
> > > > {
> > > > - unsigned int minor = iminor(file_inode(file));
> > > > + const struct file *file = desc->file;
> > > > + const unsigned int minor = iminor(file_inode(file));
> > > >
> > > > if (type[minor] == MASTER_MINOR)
> > > > - return vme_user_master_mmap(minor, vma);
> > > > + return vme_user_master_mmap_prepare(minor, desc);
> > > >
> > > > return -ENODEV;
> > > > }
> > > > @@ -498,7 +507,7 @@ static const struct file_operations vme_user_fops = {
> > > > .llseek = vme_user_llseek,
> > > > .unlocked_ioctl = vme_user_unlocked_ioctl,
> > > > .compat_ioctl = compat_ptr_ioctl,
> > > > - .mmap = vme_user_mmap,
> > > > + .mmap_prepare = vme_user_mmap_prepare,
> > > > };
> > > >
> > > > static int vme_user_match(struct vme_dev *vdev)
> > > > --
> > > > 2.53.0
> > > >
>
> Cheers, Lorenzo
^ permalink raw reply
* Re: [PATCH v2 11/16] staging: vme_user: replace deprecated mmap hook with mmap_prepare
From: Suren Baghdasaryan @ 2026-03-19 15:19 UTC (permalink / raw)
To: Lorenzo Stoakes (Oracle)
Cc: Andrew Morton, Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Michal Hocko, Jann Horn, Pedro Falcato,
linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <CAJuCfpHXqtxZr5s84jCcz513a2pgMeDoobsLBJH9pSON49cM+w@mail.gmail.com>
On Thu, Mar 19, 2026 at 8:19 AM Suren Baghdasaryan <surenb@google.com> wrote:
>
> On Thu, Mar 19, 2026 at 7:55 AM Lorenzo Stoakes (Oracle) <ljs@kernel.org> wrote:
> >
> > On Tue, Mar 17, 2026 at 02:32:16PM -0700, Suren Baghdasaryan wrote:
> > > On Tue, Mar 17, 2026 at 2:26 PM Suren Baghdasaryan <surenb@google.com> wrote:
> > > >
> > > > On Mon, Mar 16, 2026 at 2:14 PM Lorenzo Stoakes (Oracle) <ljs@kernel.org> wrote:
> > > > >
> > > > > The f_op->mmap interface is deprecated, so update driver to use its
> > > > > successor, mmap_prepare.
> > > > >
> > > > > The driver previously used vm_iomap_memory(), so this change replaces it
> > > > > with its mmap_prepare equivalent, mmap_action_simple_ioremap().
> > > > >
> > > > > Functions that wrap mmap() are also converted to wrap mmap_prepare()
> > > > > instead.
> > > > >
> > > > > Also update the documentation accordingly.
> > > > >
> > > > > Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
> > > > > ---
> > > > > Documentation/driver-api/vme.rst | 2 +-
> > > > > drivers/staging/vme_user/vme.c | 20 +++++------
> > > > > drivers/staging/vme_user/vme.h | 2 +-
> > > > > drivers/staging/vme_user/vme_user.c | 51 +++++++++++++++++------------
> > > > > 4 files changed, 42 insertions(+), 33 deletions(-)
> > > > >
> > > > > diff --git a/Documentation/driver-api/vme.rst b/Documentation/driver-api/vme.rst
> > > > > index c0b475369de0..7111999abc14 100644
> > > > > --- a/Documentation/driver-api/vme.rst
> > > > > +++ b/Documentation/driver-api/vme.rst
> > > > > @@ -107,7 +107,7 @@ The function :c:func:`vme_master_read` can be used to read from and
> > > > >
> > > > > In addition to simple reads and writes, :c:func:`vme_master_rmw` is provided to
> > > > > do a read-modify-write transaction. Parts of a VME window can also be mapped
> > > > > -into user space memory using :c:func:`vme_master_mmap`.
> > > > > +into user space memory using :c:func:`vme_master_mmap_prepare`.
> > > > >
> > > > >
> > > > > Slave windows
> > > > > diff --git a/drivers/staging/vme_user/vme.c b/drivers/staging/vme_user/vme.c
> > > > > index f10a00c05f12..7220aba7b919 100644
> > > > > --- a/drivers/staging/vme_user/vme.c
> > > > > +++ b/drivers/staging/vme_user/vme.c
> > > > > @@ -735,9 +735,9 @@ unsigned int vme_master_rmw(struct vme_resource *resource, unsigned int mask,
> > > > > EXPORT_SYMBOL(vme_master_rmw);
> > > > >
> > > > > /**
> > > > > - * vme_master_mmap - Mmap region of VME master window.
> > > > > + * vme_master_mmap_prepare - Mmap region of VME master window.
> > > > > * @resource: Pointer to VME master resource.
> > > > > - * @vma: Pointer to definition of user mapping.
> > > > > + * @desc: Pointer to descriptor of user mapping.
> > > > > *
> > > > > * Memory map a region of the VME master window into user space.
> > > > > *
> > > > > @@ -745,12 +745,13 @@ EXPORT_SYMBOL(vme_master_rmw);
> > > > > * resource or -EFAULT if map exceeds window size. Other generic mmap
> > > > > * errors may also be returned.
> > > > > */
> > > > > -int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma)
> > > > > +int vme_master_mmap_prepare(struct vme_resource *resource,
> > > > > + struct vm_area_desc *desc)
> > > > > {
> > > > > + const unsigned long vma_size = vma_desc_size(desc);
> > > > > struct vme_bridge *bridge = find_bridge(resource);
> > > > > struct vme_master_resource *image;
> > > > > phys_addr_t phys_addr;
> > > > > - unsigned long vma_size;
> > > > >
> > > > > if (resource->type != VME_MASTER) {
> > > > > dev_err(bridge->parent, "Not a master resource\n");
> > > > > @@ -758,19 +759,18 @@ int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma)
> > > > > }
> > > > >
> > > > > image = list_entry(resource->entry, struct vme_master_resource, list);
> > > > > - phys_addr = image->bus_resource.start + (vma->vm_pgoff << PAGE_SHIFT);
> > > > > - vma_size = vma->vm_end - vma->vm_start;
> > > > > + phys_addr = image->bus_resource.start + (desc->pgoff << PAGE_SHIFT);
> > > > >
> > > > > if (phys_addr + vma_size > image->bus_resource.end + 1) {
> > > > > dev_err(bridge->parent, "Map size cannot exceed the window size\n");
> > > > > return -EFAULT;
> > > > > }
> > > > >
> > > > > - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
> > > > > -
> > > > > - return vm_iomap_memory(vma, phys_addr, vma->vm_end - vma->vm_start);
> > > > > + desc->page_prot = pgprot_noncached(desc->page_prot);
> > > > > + mmap_action_simple_ioremap(desc, phys_addr, vma_size);
> > > > > + return 0;
> > > > > }
> > > > > -EXPORT_SYMBOL(vme_master_mmap);
> > > > > +EXPORT_SYMBOL(vme_master_mmap_prepare);
> > > > >
> > > > > /**
> > > > > * vme_master_free - Free VME master window
> > > > > diff --git a/drivers/staging/vme_user/vme.h b/drivers/staging/vme_user/vme.h
> > > > > index 797e9940fdd1..b6413605ea49 100644
> > > > > --- a/drivers/staging/vme_user/vme.h
> > > > > +++ b/drivers/staging/vme_user/vme.h
> > > > > @@ -151,7 +151,7 @@ ssize_t vme_master_read(struct vme_resource *resource, void *buf, size_t count,
> > > > > ssize_t vme_master_write(struct vme_resource *resource, void *buf, size_t count, loff_t offset);
> > > > > unsigned int vme_master_rmw(struct vme_resource *resource, unsigned int mask, unsigned int compare,
> > > > > unsigned int swap, loff_t offset);
> > > > > -int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma);
> > > > > +int vme_master_mmap_prepare(struct vme_resource *resource, struct vm_area_desc *desc);
> > > > > void vme_master_free(struct vme_resource *resource);
> > > > >
> > > > > struct vme_resource *vme_dma_request(struct vme_dev *vdev, u32 route);
> > > > > diff --git a/drivers/staging/vme_user/vme_user.c b/drivers/staging/vme_user/vme_user.c
> > > > > index d95dd7d9190a..11e25c2f6b0a 100644
> > > > > --- a/drivers/staging/vme_user/vme_user.c
> > > > > +++ b/drivers/staging/vme_user/vme_user.c
> > > > > @@ -446,24 +446,14 @@ static void vme_user_vm_close(struct vm_area_struct *vma)
> > > > > kfree(vma_priv);
> > > > > }
> > > > >
> > > > > -static const struct vm_operations_struct vme_user_vm_ops = {
> > > > > - .open = vme_user_vm_open,
> > > > > - .close = vme_user_vm_close,
> > > > > -};
> > > > > -
> > > > > -static int vme_user_master_mmap(unsigned int minor, struct vm_area_struct *vma)
> > > > > +static int vme_user_vm_mapped(unsigned long start, unsigned long end, pgoff_t pgoff,
> > > > > + const struct file *file, void **vm_private_data)
> > > > > {
> > > > > - int err;
> > > > > + const unsigned int minor = iminor(file_inode(file));
> > > > > struct vme_user_vma_priv *vma_priv;
> > > > >
> > > > > mutex_lock(&image[minor].mutex);
> > > > >
> > > > > - err = vme_master_mmap(image[minor].resource, vma);
> > > > > - if (err) {
> > > > > - mutex_unlock(&image[minor].mutex);
> > > > > - return err;
> > > > > - }
> > > > > -
> > > >
> > > > Ok, this changes the set of the operations performed under image[minor].mutex.
> > > > Before we had:
> > > >
> > > > mutex_lock(&image[minor].mutex);
> > > > vme_master_mmap();
> > > > <some final adjustments>
> > > > mutex_unlock(&image[minor].mutex);
> > > >
> > > > Now we have:
> > > >
> > > > mutex_lock(&image[minor].mutex);
> > > > vme_master_mmap_prepare()
> > > > mutex_unlock(&image[minor].mutex);
> > > > vm_iomap_memory();
> > > > mutex_lock(&image[minor].mutex);
> > > > vme_user_vm_mapped(); // <some final adjustments>
> > > > mutex_unlock(&image[minor].mutex);
> > > >
> > > > I think as long as image[minor] does not change while we are not
> > > > holding the mutex we should be safe, and looking at the code it seems
> > > > to be the case. But I'm not familiar with this driver and might be
> > > > wrong. Worth double-checking.
> >
> > The file is pinned for the duration, the mutex is associated with the file,
> > so there's no sane world in which that could be problematic.
> >
> > Keeping in mind that we manipulate stuff on vme_user_vm_close() that
> > directly acceses image[minor] at an arbitary time.
>
> That was my understanding as well. Thanks for confirming.
>
> >
> > >
> > > A side note: if we had to hold the mutex across all those operations I
> > > think we would need to take the mutex in the vm_ops->mmap_prepare and
> > > add a vm_ops->map_failed hook or something along that line to drop the
> > > mutex in case mmap_action_complete() fails. Not sure if we will have
> > > such cases though...
> >
> > No, I don't want to do this if it can be at all avoided. You should in
> > nearly any sane circumstance be able to defer things until the mapped hook
> > anyway.
> >
> > Also a merge can happen too after an .mmap_prepare, so we'd have to have
> > some 'success' hook and I'm just not going there it'll end up open to abuse
> > again.
> >
> > (We do have success and error filtering hooks right now, sadly, but they're
> > really for hugetlb and I plan to find a way to get rid of them).
> >
> > The mmap_prepare is meant to essentially be as stateless as possible.
>
> Yes, I also hope we won't encounter cases requiring us to keep any
> state information between the mmap_prepare and mapped stages.
>
> >
> > Anyway I don't think it's relevant here.
> >
> > >
> > > >
> > > > > vma_priv = kmalloc_obj(*vma_priv);
> > > > > if (!vma_priv) {
> > > > > mutex_unlock(&image[minor].mutex);
> > > > > @@ -472,22 +462,41 @@ static int vme_user_master_mmap(unsigned int minor, struct vm_area_struct *vma)
> > > > >
> > > > > vma_priv->minor = minor;
> > > > > refcount_set(&vma_priv->refcnt, 1);
> > > > > - vma->vm_ops = &vme_user_vm_ops;
> > > > > - vma->vm_private_data = vma_priv;
> > > > > -
> > > > > + *vm_private_data = vma_priv;
> > > > > image[minor].mmap_count++;
> > > > >
> > > > > mutex_unlock(&image[minor].mutex);
> > > > > -
> > > > > return 0;
> > > > > }
> > > > >
> > > > > -static int vme_user_mmap(struct file *file, struct vm_area_struct *vma)
> > > > > +static const struct vm_operations_struct vme_user_vm_ops = {
> > > > > + .mapped = vme_user_vm_mapped,
> > > > > + .open = vme_user_vm_open,
> > > > > + .close = vme_user_vm_close,
> > > > > +};
> > > > > +
> > > > > +static int vme_user_master_mmap_prepare(unsigned int minor,
> > > > > + struct vm_area_desc *desc)
> > > > > +{
> > > > > + int err;
> > > > > +
> > > > > + mutex_lock(&image[minor].mutex);
> > > > > +
> > > > > + err = vme_master_mmap_prepare(image[minor].resource, desc);
> > > > > + if (!err)
> > > > > + desc->vm_ops = &vme_user_vm_ops;
> > > > > +
> > > > > + mutex_unlock(&image[minor].mutex);
> > > > > + return err;
> > > > > +}
> > > > > +
> > > > > +static int vme_user_mmap_prepare(struct vm_area_desc *desc)
> > > > > {
> > > > > - unsigned int minor = iminor(file_inode(file));
> > > > > + const struct file *file = desc->file;
> > > > > + const unsigned int minor = iminor(file_inode(file));
> > > > >
> > > > > if (type[minor] == MASTER_MINOR)
> > > > > - return vme_user_master_mmap(minor, vma);
> > > > > + return vme_user_master_mmap_prepare(minor, desc);
> > > > >
> > > > > return -ENODEV;
> > > > > }
> > > > > @@ -498,7 +507,7 @@ static const struct file_operations vme_user_fops = {
> > > > > .llseek = vme_user_llseek,
> > > > > .unlocked_ioctl = vme_user_unlocked_ioctl,
> > > > > .compat_ioctl = compat_ptr_ioctl,
> > > > > - .mmap = vme_user_mmap,
> > > > > + .mmap_prepare = vme_user_mmap_prepare,
> > > > > };
> > > > >
> > > > > static int vme_user_match(struct vme_dev *vdev)
> > > > > --
> > > > > 2.53.0
> > > > >
> >
> > Cheers, Lorenzo
^ permalink raw reply
* Re: [PATCH v2 06/16] mm: add mmap_action_simple_ioremap()
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 16:29 UTC (permalink / raw)
To: Suren Baghdasaryan
Cc: Andrew Morton, Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Michal Hocko, Jann Horn, Pedro Falcato,
linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <330f3614-7dc1-4e80-96c4-8472b25108bb@lucifer.local>
On Wed, Mar 18, 2026 at 08:39:25PM +0000, Lorenzo Stoakes (Oracle) wrote:
> On Mon, Mar 16, 2026 at 09:14:28PM -0700, Suren Baghdasaryan wrote:
> > > +int simple_ioremap_prepare(struct vm_area_desc *desc)
> > > +{
> > > + struct mmap_action *action = &desc->action;
> > > + const phys_addr_t start = action->simple_ioremap.start_phys_addr;
> > > + const unsigned long size = action->simple_ioremap.size;
> > > + unsigned long pfn;
> > > + int err;
> > > +
> > > + err = __simple_ioremap_prep(desc->start, desc->end, desc->pgoff,
> > > + start, size, &pfn);
> > > + if (err)
> > > + return err;
> > > +
> > > + /* The I/O remap logic does the heavy lifting. */
> > > + mmap_action_ioremap(desc, desc->start, pfn, vma_desc_size(desc));
> >
> > nit: Looks like a perfect opportunity to use mmap_action_ioremap_full() here.
>
> Yeah can do!
>
> >
> > > + return mmap_action_prepare(desc);
> >
> > Ok, so IIUC this uses recursion:
> > mmap_action_prepare(MMAP_SIMPLE_IO_REMAP) -> simple_ioremap_prepare()
> > -> mmap_action_prepare(MMAP_IO_REMAP_PFN).
>
> Yep, it's one level, I think that should be ok? :)
On second thoughts, it's silly not just to call io_remap_pfn_range_prepare()
direct so will change it to do that!
Cheers, Lorenzo
^ permalink raw reply
* RE: [PATCH v12 0/5] shut down devices asynchronously
From: Michael Kelley @ 2026-03-19 17:13 UTC (permalink / raw)
To: David Jeffery, linux-kernel@vger.kernel.org,
driver-core@lists.linux.dev, linux-pci@vger.kernel.org,
linux-scsi@vger.kernel.org, Greg Kroah-Hartman, Rafael J. Wysocki,
Danilo Krummrich
Cc: Tarun Sahu, Pasha Tatashin, Michał Cłapiński,
Jordan Richards, Ewan Milne, John Meneghini, Lombardi, Maurizio,
Stuart Hayes, Laurence Oberman, Bart Van Assche, Bjorn Helgaas,
linux-hyperv@vger.kernel.org
In-Reply-To: <20260319141142.5781-1-djeffery@redhat.com>
From: David Jeffery <djeffery@redhat.com>
>
> This patchset allows the kernel to shutdown devices asynchronously and
> unrelated async devices to be shut down in parallel to each other.
>
> Only devices which explicitly enable it are shut down asynchronously. The
> default is for a device to be shut down from the synchronous shutdown loop.
>
> This can dramatically reduce system shutdown/reboot time on systems that
> have multiple devices that take many seconds to shut down (like certain
> NVMe drives). On one system tested, the shutdown time went from 11 minutes
> without this patch to 55 seconds with the patch. And on another system from
> 80 seconds to 11.
>
(Copying the linux-hyperv mailing list as FYI.)
Tested this patch set on two different x86/x64 VMs in the Azure public cloud.
Baseline kernel is linux-next20260312. The VMs are running on Hyper-V with
synthetic SCSI devices, PCI pass-thru NVME disks, and emulated PCI NVMe
disks, depending on the VM configuration.
First VM is an Azure L64s_v3, with 2 synthetic SCSI disks and 8 PCI NVMe
pass-thru disks. Time spent in device_shutdown() was reduced from
683 milliseconds to 150 milliseconds (averaged across 4 runs each).
Second VM is an Azure D32lds_v6, with 2 emulated NVMe disks and
4 NVMe pass-thru disks. Time sent in device_shutdown() was reduced from
1010 milliseconds to 610 milliseconds (averaged across 2 runs each).
In both cases, the results seem reasonable. None of these disks should
be particularly slow in shutting down, so the results are not as dramatic
are reported by David. But there is non-trivial improvement nonetheless.
Tested-by: Michael Kelley <mhklinux@outlook.com>
>
> Stuart Hayes (2):
> driver core: separate function to shutdown one device
> driver core: don't always lock parent in shutdown
>
> David Jeffery (5):
> driver core: async device shutdown infrastructure
> PCI: enable async shutdown support
> scsi: enable async shutdown support
>
> drivers/base/base.h | 2 +
> drivers/base/core.c | 176 +++++++++++++++++++++++++++++++-------
> drivers/pci/probe.c | 2 +
> drivers/scsi/hosts.c | 3 +
> drivers/scsi/scsi_scan.c | 1 +
> drivers/scsi/scsi_sysfs.c | 4 +
> include/linux/device.h | 13 +++
> 7 files changed, 170 insertions(+), 31 deletions(-)
>
> --
> 2.53.0
>
^ permalink raw reply
* Re: [PATCH] net: mana: fix use-after-free in add_adev() error path
From: Simon Horman @ 2026-03-19 18:18 UTC (permalink / raw)
To: Guangshuo Li
Cc: K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Long Li,
Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Saurabh Sengar, Erni Sri Satya Vennela,
Shradha Gupta, Dipayaan Roy, Aditya Garg, Shiraz Saleem,
Leon Romanovsky, linux-hyperv, netdev, linux-kernel, stable
In-Reply-To: <20260318154041.638747-1-lgs201920130244@gmail.com>
On Wed, Mar 18, 2026 at 11:40:41PM +0800, Guangshuo Li wrote:
> If auxiliary_device_add() fails, add_adev() calls
> auxiliary_device_uninit(adev), whose release callback adev_release()
> frees the containing struct mana_adev.
>
> The current error path then falls through to init_fail and accesses
> adev->id. Since adev is embedded in struct mana_adev, this may lead
> to a use-after-free.
It isn't clear to me how the use-after-free manifests.
Could you elaborate?
>
> Fix it by storing the allocated auxiliary device id in a local
> variable and using that saved id in the cleanup path after
> auxiliary_device_uninit().
>
> Fixes: a69839d4327d ("net: mana: Add support for auxiliary device")
> Cc: stable@vger.kernel.org
> Signed-off-by: Guangshuo Li <lgs201920130244@gmail.com>
As a bug fix for code present in the net tree, this patch
should be targeted at that tree like this.
Subject: [PATCH net] ...
And it should apply to that tree.
As it is the CI tries to apply this patch to the default tree, net-next.
Which fails. So there is no further CI performed.
> ---
> drivers/net/ethernet/microsoft/mana/mana_en.c | 6 ++++--
> 1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
> index 1ad154f9db1a..70d71594c599 100644
> --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
> +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
> @@ -3362,6 +3362,7 @@ static int add_adev(struct gdma_dev *gd, const char *name)
> {
> struct auxiliary_device *adev;
> struct mana_adev *madev;
> + int id;
> int ret;
Please preserve reverse xmas tree order for local variables - longest line
to shortest.
>
> madev = kzalloc(sizeof(*madev), GFP_KERNEL);
...
--
pw-bot: changes-requested
^ permalink raw reply
* [PATCH v3 00/16] mm: expand mmap_prepare functionality and usage
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
This series expands the mmap_prepare functionality, which is intended to
replace the deprecated f_op->mmap hook which has been the source of bugs
and security issues for some time.
This series starts with some cleanup of existing mmap_prepare logic, then
adds documentation for the mmap_prepare call to make it easier for
filesystem and driver writers to understand how it works.
It then importantly adds a vm_ops->mapped hook, a key feature that was
missing from mmap_prepare previously - this is invoked when a driver which
specifies mmap_prepare has successfully been mapped but not merged with
another VMA.
mmap_prepare is invoked prior to a merge being attempted, so you cannot
manipulate state such as reference counts as if it were a new mapping.
The vm_ops->mapped hook allows a driver to perform tasks required at this
stage, and provides symmetry against subsequent vm_ops->open,close calls.
The series uses this to correct the afs implementation which wrongly
manipulated reference count at mmap_prepare time.
It then adds an mmap_prepare equivalent of vm_iomap_memory() -
mmap_action_simple_ioremap(), then uses this to update a number of drivers.
It then splits out the mmap_prepare compatibility layer (which allows for
invocation of mmap_prepare hooks in an mmap() hook) in such a way as to
allow for more incremental implementation of mmap_prepare hooks.
It then uses this to extend mmap_prepare usage in drivers.
Finally it adds an mmap_prepare equivalent of vm_map_pages(), which lays
the foundation for future work which will extend mmap_prepare to DMA
coherent mappings.
v3:
* Propagated tags (thanks Suren, Richard!)
* Updated 12/16 to correctly clear the vm_area_desc data structure in
set_desc_from_vma() as per Joshua Hahn (thanks! :)
* Fixed type in 12/16 as per Suren (cheers!)
* Fixed up 6/16 to use mmap_action_ioremap_full() in simple_ioremap_prepare() as
suggested by Suren.
* Also fixed up 6/16 to call io_remap_pfn_range_prepare() direct rather than
mmap_action_prepare() as per Suren.
* Also fixed up 6/16 to pass vm_len rather than vm_[start, end] to
__simple_ioremap_prep() as per Suren (thanks for all the above! :)
* Fixed issue in rmap lock being held - we were referencing a vma->vm_file after
the VMA was unmapped, so UAF. Avoid that. Also do_munmap() relies on rmap lock
NOT being held or may deadlock, so extend functionality to ensure we drop it
when it is held on error paths.
* Updated 'area' -> 'vma' variable in 3/16 in VMA test dup.h.
* Fixed up reference to __compat_vma_mmap() in 12/16 commit message.
* Updated 1/16 to no longer duplicatively apply io_remap_pfn_range_pfn().
* Updated 1/16 to delegate I/O remap complete to remap complete logic.
* Fixed various typos in 12/16.
* Fixed stale comment typos in 13/16.
* Fixed commit msg and comment typos in 14/16.
* Removed accidental sneak peak to future functionality in 15/16 commit message
:).
* Fixed up field names to be identical in VMA tests + mm_types.h in 6/16,
15/16.
v2:
* Rebased on
https://lore.kernel.org/all/cover.1773665966.git.ljs@kernel.org/ to make
Andrew's life easier :)
* Folded all interim fixes into series (thanks Randy for many doc fixes!))
* As per Suren, removed a comment about allocations too small to fail.
* As per Randy, fixed up typo in documentation for vm_area_desc.
* Fixed mmap_action_prepare() not returning if invalid action->type
specified, as updated from Andrew's interim fix (thanks!) and also
reported by kernel test bot.
* Updated mmap_action_prepare() and specific prepare functions to only
pass vm_area_desc parameter as per Suren.
* Fixed up whitespace as per Suren.
* Updated vm_op->open comment in vm_operations_struct to reference forking
as per Suren.
* Added a commit to check that input range is within VMA on remap as per
Suren (this also covers I/O remap and all other cases already asserted).
* Updated AFS to not incorrectly reference count on mmap prepare as per
Usama.
* Also updated various static AFS functions to be consistent with each
other.
* Updated AFS commit message to reflect mmap_prepare being before any VMA
merging as per Suren.
* Updated __compat_vma_mapped() to check for NULL vm_ops as per Usama.
* Updated __compat_vma_mapped() to not reference an unmapped VMA's fields
as per Usama.
* Updated __vma_check_mmap_hook() to check for NULL vm_ops as per Usama.
* Dropped comment about preferring mmap_prepare as seems overly confusing,
as per Suren.
* Updated the mmap lock assert in unmap_vma_locked() to a write lock assert
as per Suren.
* Copied vm_ops->open comment over to VMA tests in appropriate patch as per
Suren.
* Updated mmap_prepare documentation to reflect the fact that no resources
should be allocated upon mmap_prepare.
* Updated mmap_prepare documentation to reference the vm_ops->mapped
callback.
* Fixed stray markdown '## How to use' in documentation.
* Fixed bug reported by kernel test bot re: overlooked
vma_desc_test_flags() -> vma_desc_test() in MTD driver for nommu.
https://lore.kernel.org/linux-mm/cover.1773695307.git.ljs@kernel.org/
v1:
https://lore.kernel.org/linux-mm/cover.1773346620.git.ljs@kernel.org/
Lorenzo Stoakes (Oracle) (16):
mm: various small mmap_prepare cleanups
mm: add documentation for the mmap_prepare file operation callback
mm: document vm_operations_struct->open the same as close()
mm: add vm_ops->mapped hook
fs: afs: correctly drop reference count on mapping failure
mm: add mmap_action_simple_ioremap()
misc: open-dice: replace deprecated mmap hook with mmap_prepare
hpet: replace deprecated mmap hook with mmap_prepare
mtdchar: replace deprecated mmap hook with mmap_prepare, clean up
stm: replace deprecated mmap hook with mmap_prepare
staging: vme_user: replace deprecated mmap hook with mmap_prepare
mm: allow handling of stacked mmap_prepare hooks in more drivers
drivers: hv: vmbus: replace deprecated mmap hook with mmap_prepare
uio: replace deprecated mmap hook with mmap_prepare in uio_info
mm: add mmap_action_map_kernel_pages[_full]()
mm: on remap assert that input range within the proposed VMA
Documentation/driver-api/vme.rst | 2 +-
Documentation/filesystems/index.rst | 1 +
Documentation/filesystems/mmap_prepare.rst | 168 ++++++++++++++
drivers/char/hpet.c | 12 +-
drivers/hv/hyperv_vmbus.h | 4 +-
drivers/hv/vmbus_drv.c | 31 ++-
drivers/hwtracing/stm/core.c | 31 ++-
drivers/misc/open-dice.c | 19 +-
drivers/mtd/mtdchar.c | 21 +-
drivers/staging/vme_user/vme.c | 20 +-
drivers/staging/vme_user/vme.h | 2 +-
drivers/staging/vme_user/vme_user.c | 51 +++--
drivers/target/target_core_user.c | 26 ++-
drivers/uio/uio.c | 10 +-
drivers/uio/uio_hv_generic.c | 11 +-
fs/afs/file.c | 36 ++-
include/linux/fs.h | 14 +-
include/linux/hyperv.h | 4 +-
include/linux/mm.h | 159 ++++++++++++-
include/linux/mm_types.h | 17 +-
include/linux/uio_driver.h | 4 +-
mm/internal.h | 41 ++--
mm/memory.c | 175 ++++++++++----
mm/util.c | 251 ++++++++++++++-------
mm/vma.c | 53 +++--
mm/vma.h | 2 +-
tools/testing/vma/include/dup.h | 152 ++++++++++---
tools/testing/vma/include/stubs.h | 9 +-
28 files changed, 990 insertions(+), 336 deletions(-)
create mode 100644 Documentation/filesystems/mmap_prepare.rst
--
2.53.0
^ permalink raw reply
* [PATCH v3 01/16] mm: various small mmap_prepare cleanups
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
Rather than passing arbitrary fields, pass a vm_area_desc pointer to mmap
prepare functions to mmap prepare, and an action and vma pointer to mmap
complete in order to put all the action-specific logic in the function
actually doing the work.
Additionally, allow mmap prepare functions to return an error so we can
error out as soon as possible if there is something logically incorrect in
the input.
Update remap_pfn_range_prepare() to properly check the input range for the
CoW case.
Also remove io_remap_pfn_range_complete(), as we can simply set up the
fields correctly in io_remap_pfn_range_prepare() and use
remap_pfn_range_complete() for this.
While we're here, make remap_pfn_range_prepare_vma() a little neater, and
pass mmap_action directly to call_action_complete().
Then, update compat_vma_mmap() to perform its logic directly, as
__compat_vma_map() is not used by anything so we don't need to export it.
Also update compat_vma_mmap() to use vfs_mmap_prepare() rather than
calling the mmap_prepare op directly.
Finally, update the VMA userland tests to reflect the changes.
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
include/linux/fs.h | 2 -
include/linux/mm.h | 7 +-
mm/internal.h | 32 ++++----
mm/memory.c | 45 +++++++----
mm/util.c | 121 +++++++++++++-----------------
mm/vma.c | 24 +++---
tools/testing/vma/include/dup.h | 7 +-
tools/testing/vma/include/stubs.h | 8 +-
8 files changed, 126 insertions(+), 120 deletions(-)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8b3dd145b25e..a2628a12bd2b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2058,8 +2058,6 @@ static inline bool can_mmap_file(struct file *file)
return true;
}
-int __compat_vma_mmap(const struct file_operations *f_op,
- struct file *file, struct vm_area_struct *vma);
int compat_vma_mmap(struct file *file, struct vm_area_struct *vma);
static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 42cc40aa63d9..1e63b3a44a47 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4320,10 +4320,9 @@ static inline void mmap_action_ioremap_full(struct vm_area_desc *desc,
mmap_action_ioremap(desc, desc->start, start_pfn, vma_desc_size(desc));
}
-void mmap_action_prepare(struct mmap_action *action,
- struct vm_area_desc *desc);
-int mmap_action_complete(struct mmap_action *action,
- struct vm_area_struct *vma);
+int mmap_action_prepare(struct vm_area_desc *desc);
+int mmap_action_complete(struct vm_area_struct *vma,
+ struct mmap_action *action);
/* Look up the first VMA which exactly match the interval vm_start ... vm_end */
static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
diff --git a/mm/internal.h b/mm/internal.h
index 708d240b4198..0256ca44115a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1793,26 +1793,28 @@ int walk_page_range_debug(struct mm_struct *mm, unsigned long start,
void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm);
int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm);
-void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn);
-int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr,
- unsigned long pfn, unsigned long size, pgprot_t pgprot);
+int remap_pfn_range_prepare(struct vm_area_desc *desc);
+int remap_pfn_range_complete(struct vm_area_struct *vma,
+ struct mmap_action *action);
-static inline void io_remap_pfn_range_prepare(struct vm_area_desc *desc,
- unsigned long orig_pfn, unsigned long size)
+static inline int io_remap_pfn_range_prepare(struct vm_area_desc *desc)
{
+ struct mmap_action *action = &desc->action;
+ const unsigned long orig_pfn = action->remap.start_pfn;
+ const pgprot_t orig_pgprot = action->remap.pgprot;
+ const unsigned long size = action->remap.size;
const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size);
+ int err;
- return remap_pfn_range_prepare(desc, pfn);
-}
+ action->remap.start_pfn = pfn;
+ action->remap.pgprot = pgprot_decrypted(orig_pgprot);
+ err = remap_pfn_range_prepare(desc);
+ if (err)
+ return err;
-static inline int io_remap_pfn_range_complete(struct vm_area_struct *vma,
- unsigned long addr, unsigned long orig_pfn, unsigned long size,
- pgprot_t orig_prot)
-{
- const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size);
- const pgprot_t prot = pgprot_decrypted(orig_prot);
-
- return remap_pfn_range_complete(vma, addr, pfn, size, prot);
+ /* Remap does the actual work. */
+ action->type = MMAP_REMAP_PFN;
+ return 0;
}
#ifdef CONFIG_MMU_NOTIFIER
diff --git a/mm/memory.c b/mm/memory.c
index 219b9bf6cae0..9dec67a18116 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3099,26 +3099,34 @@ static int do_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
}
#endif
-void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn)
+int remap_pfn_range_prepare(struct vm_area_desc *desc)
{
- /*
- * We set addr=VMA start, end=VMA end here, so this won't fail, but we
- * check it again on complete and will fail there if specified addr is
- * invalid.
- */
- get_remap_pgoff(vma_desc_is_cow_mapping(desc), desc->start, desc->end,
- desc->start, desc->end, pfn, &desc->pgoff);
+ const struct mmap_action *action = &desc->action;
+ const unsigned long start = action->remap.start;
+ const unsigned long end = start + action->remap.size;
+ const unsigned long pfn = action->remap.start_pfn;
+ const bool is_cow = vma_desc_is_cow_mapping(desc);
+ int err;
+
+ err = get_remap_pgoff(is_cow, start, end, desc->start, desc->end, pfn,
+ &desc->pgoff);
+ if (err)
+ return err;
+
vma_desc_set_flags_mask(desc, VMA_REMAP_FLAGS);
+ return 0;
}
-static int remap_pfn_range_prepare_vma(struct vm_area_struct *vma, unsigned long addr,
- unsigned long pfn, unsigned long size)
+static int remap_pfn_range_prepare_vma(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long pfn,
+ unsigned long size)
{
- unsigned long end = addr + PAGE_ALIGN(size);
+ const unsigned long end = addr + PAGE_ALIGN(size);
+ const bool is_cow = is_cow_mapping(vma->vm_flags);
int err;
- err = get_remap_pgoff(is_cow_mapping(vma->vm_flags), addr, end,
- vma->vm_start, vma->vm_end, pfn, &vma->vm_pgoff);
+ err = get_remap_pgoff(is_cow, addr, end, vma->vm_start, vma->vm_end,
+ pfn, &vma->vm_pgoff);
if (err)
return err;
@@ -3151,10 +3159,15 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
}
EXPORT_SYMBOL(remap_pfn_range);
-int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr,
- unsigned long pfn, unsigned long size, pgprot_t prot)
+int remap_pfn_range_complete(struct vm_area_struct *vma,
+ struct mmap_action *action)
{
- return do_remap_pfn_range(vma, addr, pfn, size, prot);
+ const unsigned long start = action->remap.start;
+ const unsigned long pfn = action->remap.start_pfn;
+ const unsigned long size = action->remap.size;
+ const pgprot_t prot = action->remap.pgprot;
+
+ return do_remap_pfn_range(vma, start, pfn, size, prot);
}
/**
diff --git a/mm/util.c b/mm/util.c
index ce7ae80047cf..73c97a748d8e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1163,43 +1163,6 @@ void flush_dcache_folio(struct folio *folio)
EXPORT_SYMBOL(flush_dcache_folio);
#endif
-/**
- * __compat_vma_mmap() - See description for compat_vma_mmap()
- * for details. This is the same operation, only with a specific file operations
- * struct which may or may not be the same as vma->vm_file->f_op.
- * @f_op: The file operations whose .mmap_prepare() hook is specified.
- * @file: The file which backs or will back the mapping.
- * @vma: The VMA to apply the .mmap_prepare() hook to.
- * Returns: 0 on success or error.
- */
-int __compat_vma_mmap(const struct file_operations *f_op,
- struct file *file, struct vm_area_struct *vma)
-{
- struct vm_area_desc desc = {
- .mm = vma->vm_mm,
- .file = file,
- .start = vma->vm_start,
- .end = vma->vm_end,
-
- .pgoff = vma->vm_pgoff,
- .vm_file = vma->vm_file,
- .vma_flags = vma->flags,
- .page_prot = vma->vm_page_prot,
-
- .action.type = MMAP_NOTHING, /* Default */
- };
- int err;
-
- err = f_op->mmap_prepare(&desc);
- if (err)
- return err;
-
- mmap_action_prepare(&desc.action, &desc);
- set_vma_from_desc(vma, &desc);
- return mmap_action_complete(&desc.action, vma);
-}
-EXPORT_SYMBOL(__compat_vma_mmap);
-
/**
* compat_vma_mmap() - Apply the file's .mmap_prepare() hook to an
* existing VMA and execute any requested actions.
@@ -1228,7 +1191,31 @@ EXPORT_SYMBOL(__compat_vma_mmap);
*/
int compat_vma_mmap(struct file *file, struct vm_area_struct *vma)
{
- return __compat_vma_mmap(file->f_op, file, vma);
+ struct vm_area_desc desc = {
+ .mm = vma->vm_mm,
+ .file = file,
+ .start = vma->vm_start,
+ .end = vma->vm_end,
+
+ .pgoff = vma->vm_pgoff,
+ .vm_file = vma->vm_file,
+ .vma_flags = vma->flags,
+ .page_prot = vma->vm_page_prot,
+
+ .action.type = MMAP_NOTHING, /* Default */
+ };
+ int err;
+
+ err = vfs_mmap_prepare(file, &desc);
+ if (err)
+ return err;
+
+ err = mmap_action_prepare(&desc);
+ if (err)
+ return err;
+
+ set_vma_from_desc(vma, &desc);
+ return mmap_action_complete(vma, &desc.action);
}
EXPORT_SYMBOL(compat_vma_mmap);
@@ -1320,8 +1307,8 @@ void snapshot_page(struct page_snapshot *ps, const struct page *page)
}
}
-static int mmap_action_finish(struct mmap_action *action,
- const struct vm_area_struct *vma, int err)
+static int mmap_action_finish(struct vm_area_struct *vma,
+ struct mmap_action *action, int err)
{
/*
* If an error occurs, unmap the VMA altogether and return an error. We
@@ -1353,37 +1340,38 @@ static int mmap_action_finish(struct mmap_action *action,
/**
* mmap_action_prepare - Perform preparatory setup for an VMA descriptor
* action which need to be performed.
- * @desc: The VMA descriptor to prepare for @action.
- * @action: The action to perform.
+ * @desc: The VMA descriptor to prepare for its @desc->action.
+ *
+ * Returns: %0 on success, otherwise error.
*/
-void mmap_action_prepare(struct mmap_action *action,
- struct vm_area_desc *desc)
+int mmap_action_prepare(struct vm_area_desc *desc)
{
- switch (action->type) {
+ switch (desc->action.type) {
case MMAP_NOTHING:
- break;
+ return 0;
case MMAP_REMAP_PFN:
- remap_pfn_range_prepare(desc, action->remap.start_pfn);
- break;
+ return remap_pfn_range_prepare(desc);
case MMAP_IO_REMAP_PFN:
- io_remap_pfn_range_prepare(desc, action->remap.start_pfn,
- action->remap.size);
- break;
+ return io_remap_pfn_range_prepare(desc);
}
+
+ WARN_ON_ONCE(1);
+ return -EINVAL;
}
EXPORT_SYMBOL(mmap_action_prepare);
/**
* mmap_action_complete - Execute VMA descriptor action.
- * @action: The action to perform.
* @vma: The VMA to perform the action upon.
+ * @action: The action to perform.
*
* Similar to mmap_action_prepare().
*
* Return: 0 on success, or error, at which point the VMA will be unmapped.
*/
-int mmap_action_complete(struct mmap_action *action,
- struct vm_area_struct *vma)
+int mmap_action_complete(struct vm_area_struct *vma,
+ struct mmap_action *action)
+
{
int err = 0;
@@ -1391,25 +1379,22 @@ int mmap_action_complete(struct mmap_action *action,
case MMAP_NOTHING:
break;
case MMAP_REMAP_PFN:
- err = remap_pfn_range_complete(vma, action->remap.start,
- action->remap.start_pfn, action->remap.size,
- action->remap.pgprot);
+ err = remap_pfn_range_complete(vma, action);
break;
case MMAP_IO_REMAP_PFN:
- err = io_remap_pfn_range_complete(vma, action->remap.start,
- action->remap.start_pfn, action->remap.size,
- action->remap.pgprot);
+ /* Should have been delegated. */
+ WARN_ON_ONCE(1);
+ err = -EINVAL;
break;
}
- return mmap_action_finish(action, vma, err);
+ return mmap_action_finish(vma, action, err);
}
EXPORT_SYMBOL(mmap_action_complete);
#else
-void mmap_action_prepare(struct mmap_action *action,
- struct vm_area_desc *desc)
+int mmap_action_prepare(struct vm_area_desc *desc)
{
- switch (action->type) {
+ switch (desc->action.type) {
case MMAP_NOTHING:
break;
case MMAP_REMAP_PFN:
@@ -1417,11 +1402,13 @@ void mmap_action_prepare(struct mmap_action *action,
WARN_ON_ONCE(1); /* nommu cannot handle these. */
break;
}
+
+ return 0;
}
EXPORT_SYMBOL(mmap_action_prepare);
-int mmap_action_complete(struct mmap_action *action,
- struct vm_area_struct *vma)
+int mmap_action_complete(struct vm_area_struct *vma,
+ struct mmap_action *action)
{
int err = 0;
@@ -1436,7 +1423,7 @@ int mmap_action_complete(struct mmap_action *action,
break;
}
- return mmap_action_finish(action, vma, err);
+ return mmap_action_finish(vma, action, err);
}
EXPORT_SYMBOL(mmap_action_complete);
#endif
diff --git a/mm/vma.c b/mm/vma.c
index c1f183235756..2a86c7575000 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -2640,15 +2640,18 @@ static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma)
vma_set_page_prot(vma);
}
-static void call_action_prepare(struct mmap_state *map,
- struct vm_area_desc *desc)
+static int call_action_prepare(struct mmap_state *map,
+ struct vm_area_desc *desc)
{
- struct mmap_action *action = &desc->action;
+ int err;
- mmap_action_prepare(action, desc);
+ err = mmap_action_prepare(desc);
+ if (err)
+ return err;
- if (action->hide_from_rmap_until_complete)
+ if (desc->action.hide_from_rmap_until_complete)
map->hold_file_rmap_lock = true;
+ return 0;
}
/*
@@ -2672,7 +2675,9 @@ static int call_mmap_prepare(struct mmap_state *map,
if (err)
return err;
- call_action_prepare(map, desc);
+ err = call_action_prepare(map, desc);
+ if (err)
+ return err;
/* Update fields permitted to be changed. */
map->pgoff = desc->pgoff;
@@ -2727,13 +2732,12 @@ static bool can_set_ksm_flags_early(struct mmap_state *map)
}
static int call_action_complete(struct mmap_state *map,
- struct vm_area_desc *desc,
+ struct mmap_action *action,
struct vm_area_struct *vma)
{
- struct mmap_action *action = &desc->action;
int ret;
- ret = mmap_action_complete(action, vma);
+ ret = mmap_action_complete(vma, action);
/* If we held the file rmap we need to release it. */
if (map->hold_file_rmap_lock) {
@@ -2795,7 +2799,7 @@ static unsigned long __mmap_region(struct file *file, unsigned long addr,
__mmap_complete(&map, vma);
if (have_mmap_prepare && allocated_new) {
- error = call_action_complete(&map, &desc, vma);
+ error = call_action_complete(&map, &desc.action, vma);
if (error)
return error;
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 999357e18eb0..9eada1e0949c 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -1271,9 +1271,12 @@ static inline int __compat_vma_mmap(const struct file_operations *f_op,
if (err)
return err;
- mmap_action_prepare(&desc.action, &desc);
+ err = mmap_action_prepare(&desc);
+ if (err)
+ return err;
+
set_vma_from_desc(vma, &desc);
- return mmap_action_complete(&desc.action, vma);
+ return mmap_action_complete(vma, &desc.action);
}
static inline int compat_vma_mmap(struct file *file,
diff --git a/tools/testing/vma/include/stubs.h b/tools/testing/vma/include/stubs.h
index 5afb0afe2d48..a30b8bc84955 100644
--- a/tools/testing/vma/include/stubs.h
+++ b/tools/testing/vma/include/stubs.h
@@ -81,13 +81,13 @@ static inline void free_anon_vma_name(struct vm_area_struct *vma)
{
}
-static inline void mmap_action_prepare(struct mmap_action *action,
- struct vm_area_desc *desc)
+static inline int mmap_action_prepare(struct vm_area_desc *desc)
{
+ return 0;
}
-static inline int mmap_action_complete(struct mmap_action *action,
- struct vm_area_struct *vma)
+static inline int mmap_action_complete(struct vm_area_struct *vma,
+ struct mmap_action *action)
{
return 0;
}
--
2.53.0
^ permalink raw reply related
* [PATCH v3 02/16] mm: add documentation for the mmap_prepare file operation callback
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
This documentation makes it easier for a driver/file system implementer to
correctly use this callback.
It covers the fundamentals, whilst intentionally leaving the less lovely
possible actions one might take undocumented (for instance - the
success_hook, error_hook fields in mmap_action).
The document also covers the new VMA flags implementation which is the
only one which will work correctly with mmap_prepare.
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
Documentation/filesystems/index.rst | 1 +
Documentation/filesystems/mmap_prepare.rst | 142 +++++++++++++++++++++
2 files changed, 143 insertions(+)
create mode 100644 Documentation/filesystems/mmap_prepare.rst
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index f4873197587d..6cbc3e0292ae 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -29,6 +29,7 @@ algorithms work.
fiemap
files
locks
+ mmap_prepare
multigrain-ts
mount_api
quota
diff --git a/Documentation/filesystems/mmap_prepare.rst b/Documentation/filesystems/mmap_prepare.rst
new file mode 100644
index 000000000000..65a1f094e469
--- /dev/null
+++ b/Documentation/filesystems/mmap_prepare.rst
@@ -0,0 +1,142 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
+mmap_prepare callback HOWTO
+===========================
+
+Introduction
+============
+
+The ``struct file->f_op->mmap()`` callback has been deprecated as it is both a
+stability and security risk, and doesn't always permit the merging of adjacent
+mappings resulting in unnecessary memory fragmentation.
+
+It has been replaced with the ``file->f_op->mmap_prepare()`` callback which
+solves these problems.
+
+This hook is called right at the beginning of setting up the mapping, and
+importantly it is invoked *before* any merging of adjacent mappings has taken
+place.
+
+If an error arises upon mapping, it might arise after this callback has been
+invoked, therefore it should be treated as effectively stateless.
+
+That is - no resources should be allocated nor state updated to reflect that a
+mapping has been established, as the mapping may either be merged, or fail to be
+mapped after the callback is complete.
+
+How To Use
+==========
+
+In your driver's struct file_operations struct, specify an ``mmap_prepare``
+callback rather than an ``mmap`` one, e.g. for ext4:
+
+.. code-block:: C
+
+ const struct file_operations ext4_file_operations = {
+ ...
+ .mmap_prepare = ext4_file_mmap_prepare,
+ };
+
+This has a signature of ``int (*mmap_prepare)(struct vm_area_desc *)``.
+
+Examining the struct vm_area_desc type:
+
+.. code-block:: C
+
+ struct vm_area_desc {
+ /* Immutable state. */
+ const struct mm_struct *const mm;
+ struct file *const file; /* May vary from vm_file in stacked callers. */
+ unsigned long start;
+ unsigned long end;
+
+ /* Mutable fields. Populated with initial state. */
+ pgoff_t pgoff;
+ struct file *vm_file;
+ vma_flags_t vma_flags;
+ pgprot_t page_prot;
+
+ /* Write-only fields. */
+ const struct vm_operations_struct *vm_ops;
+ void *private_data;
+
+ /* Take further action? */
+ struct mmap_action action;
+ };
+
+This is straightforward - you have all the fields you need to set up the
+mapping, and you can update the mutable and writable fields, for instance:
+
+.. code-block:: C
+
+ static int ext4_file_mmap_prepare(struct vm_area_desc *desc)
+ {
+ int ret;
+ struct file *file = desc->file;
+ struct inode *inode = file->f_mapping->host;
+
+ ...
+
+ file_accessed(file);
+ if (IS_DAX(file_inode(file))) {
+ desc->vm_ops = &ext4_dax_vm_ops;
+ vma_desc_set_flags(desc, VMA_HUGEPAGE_BIT);
+ } else {
+ desc->vm_ops = &ext4_file_vm_ops;
+ }
+ return 0;
+ }
+
+Importantly, you no longer have to dance around with reference counts or locks
+when updating these fields - **you can simply go ahead and change them**.
+
+Everything is taken care of by the mapping code.
+
+VMA Flags
+---------
+
+Along with ``mmap_prepare``, VMA flags have undergone an overhaul. Where before
+you would invoke one of vm_flags_init(), vm_flags_reset(), vm_flags_set(),
+vm_flags_clear(), and vm_flags_mod() to modify flags (and to have the
+locking done correctly for you, this is no longer necessary.
+
+Also, the legacy approach of specifying VMA flags via ``VM_READ``, ``VM_WRITE``,
+etc. - i.e. using a ``-VM_xxx``- macro has changed too.
+
+When implementing mmap_prepare(), reference flags by their bit number, defined
+as a ``VMA_xxx_BIT`` macro, e.g. ``VMA_READ_BIT``, ``VMA_WRITE_BIT`` etc.,
+and use one of (where ``desc`` is a pointer to struct vm_area_desc):
+
+* ``vma_desc_test_flags(desc, ...)`` - Specify a comma-separated list of flags
+ you wish to test for (whether _any_ are set), e.g. - ``vma_desc_test_flags(
+ desc, VMA_WRITE_BIT, VMA_MAYWRITE_BIT)`` - returns ``true`` if either are set,
+ otherwise ``false``.
+* ``vma_desc_set_flags(desc, ...)`` - Update the VMA descriptor flags to set
+ additional flags specified by a comma-separated list,
+ e.g. - ``vma_desc_set_flags(desc, VMA_PFNMAP_BIT, VMA_IO_BIT)``.
+* ``vma_desc_clear_flags(desc, ...)`` - Update the VMA descriptor flags to clear
+ flags specified by a comma-separated list, e.g. - ``vma_desc_clear_flags(
+ desc, VMA_WRITE_BIT, VMA_MAYWRITE_BIT)``.
+
+Actions
+=======
+
+You can now very easily have actions be performed upon a mapping once set up by
+utilising simple helper functions invoked upon the struct vm_area_desc
+pointer. These are:
+
+* mmap_action_remap() - Remaps a range consisting only of PFNs for a specific
+ range starting a virtual address and PFN number of a set size.
+
+* mmap_action_remap_full() - Same as mmap_action_remap(), only remaps the
+ entire mapping from ``start_pfn`` onward.
+
+* mmap_action_ioremap() - Same as mmap_action_remap(), only performs an I/O
+ remap.
+
+* mmap_action_ioremap_full() - Same as mmap_action_ioremap(), only remaps
+ the entire mapping from ``start_pfn`` onward.
+
+**NOTE:** The ``action`` field should never normally be manipulated directly,
+rather you ought to use one of these helpers.
--
2.53.0
^ permalink raw reply related
* [PATCH v3 03/16] mm: document vm_operations_struct->open the same as close()
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
Describe when the operation is invoked and the context in which it is
invoked, matching the description already added for vm_op->close().
While we're here, update all outdated references to an 'area' field for
VMAs to the more consistent 'vma'.
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
include/linux/mm.h | 15 ++++++++++-----
tools/testing/vma/include/dup.h | 15 ++++++++++-----
2 files changed, 20 insertions(+), 10 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1e63b3a44a47..da94edb287cd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -766,15 +766,20 @@ struct vm_uffd_ops;
* to the functions called when a no-page or a wp-page exception occurs.
*/
struct vm_operations_struct {
- void (*open)(struct vm_area_struct * area);
+ /**
+ * @open: Called when a VMA is remapped, split or forked. Not called
+ * upon first mapping a VMA.
+ * Context: User context. May sleep. Caller holds mmap_lock.
+ */
+ void (*open)(struct vm_area_struct *vma);
/**
* @close: Called when the VMA is being removed from the MM.
* Context: User context. May sleep. Caller holds mmap_lock.
*/
- void (*close)(struct vm_area_struct * area);
+ void (*close)(struct vm_area_struct *vma);
/* Called any time before splitting to check if it's allowed */
- int (*may_split)(struct vm_area_struct *area, unsigned long addr);
- int (*mremap)(struct vm_area_struct *area);
+ int (*may_split)(struct vm_area_struct *vma, unsigned long addr);
+ int (*mremap)(struct vm_area_struct *vma);
/*
* Called by mprotect() to make driver-specific permission
* checks before mprotect() is finalised. The VMA must not
@@ -786,7 +791,7 @@ struct vm_operations_struct {
vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order);
vm_fault_t (*map_pages)(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff);
- unsigned long (*pagesize)(struct vm_area_struct * area);
+ unsigned long (*pagesize)(struct vm_area_struct *vma);
/* notification that a previously read-only page is about to become
* writable, if an error is returned it will cause a SIGBUS */
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 9eada1e0949c..8ae525ed1738 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -632,15 +632,20 @@ struct vm_area_struct {
} __randomize_layout;
struct vm_operations_struct {
- void (*open)(struct vm_area_struct * area);
+ /**
+ * @open: Called when a VMA is remapped, split or forked. Not called
+ * upon first mapping a VMA.
+ * Context: User context. May sleep. Caller holds mmap_lock.
+ */
+ void (*open)(struct vm_area_struct *vma);
/**
* @close: Called when the VMA is being removed from the MM.
* Context: User context. May sleep. Caller holds mmap_lock.
*/
- void (*close)(struct vm_area_struct * area);
+ void (*close)(struct vm_area_struct *vma);
/* Called any time before splitting to check if it's allowed */
- int (*may_split)(struct vm_area_struct *area, unsigned long addr);
- int (*mremap)(struct vm_area_struct *area);
+ int (*may_split)(struct vm_area_struct *vma, unsigned long addr);
+ int (*mremap)(struct vm_area_struct *vma);
/*
* Called by mprotect() to make driver-specific permission
* checks before mprotect() is finalised. The VMA must not
@@ -652,7 +657,7 @@ struct vm_operations_struct {
vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order);
vm_fault_t (*map_pages)(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff);
- unsigned long (*pagesize)(struct vm_area_struct * area);
+ unsigned long (*pagesize)(struct vm_area_struct *vma);
/* notification that a previously read-only page is about to become
* writable, if an error is returned it will cause a SIGBUS */
--
2.53.0
^ permalink raw reply related
* [PATCH v3 04/16] mm: add vm_ops->mapped hook
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
Previously, when a driver needed to do something like establish a
reference count, it could do so in the mmap hook in the knowledge that the
mapping would succeed.
With the introduction of f_op->mmap_prepare this is no longer the case, as
it is invoked prior to actually establishing the mapping.
mmap_prepare is not appropriate for this kind of thing as it is called
before any merge might take place, and after which an error might occur
meaning resources could be leaked.
To take this into account, introduce a new vm_ops->mapped callback which
is invoked when the VMA is first mapped (though notably - not when it is
merged - which is correct and mirrors existing mmap/open/close behaviour).
We do better that vm_ops->open() here, as this callback can return an
error, at which point the VMA will be unmapped.
Note that vm_ops->mapped() is invoked after any mmap action is complete
(such as I/O remapping).
We intentionally do not expose the VMA at this point, exposing only the
fields that could be used, and an output parameter in case the operation
needs to update the vma->vm_private_data field.
In order to deal with stacked filesystems which invoke inner filesystem's
mmap() invocations, add __compat_vma_mapped() and invoke it on vfs_mmap()
(via compat_vma_mmap()) to ensure that the mapped callback is handled when
an mmap() caller invokes a nested filesystem's mmap_prepare() callback.
We can now also remove call_action_complete() and invoke
mmap_action_complete() directly, as we separate out the rmap lock logic.
The rmap lock logic, which was added in order to keep hugetlb working (!)
to allow for the rmap lock to be held longer, needs to be propagated to the
error paths on mmap complete and mapped hook error paths.
This is because do_munmap() might otherwise deadlock with the rmap being
held, so instead we unlock at the point of unmap.
This is fine as any reliance on the rmap being held is irrelevant on error.
While we're here, refactor mmap_action_finish() to avoid a big if (err)
branch.
We also abstract unmapping of a VMA on mmap action completion into its own
helper function, unmap_vma_locked().
Update the mmap_prepare documentation to describe the mapped hook and make
it clear what its intended use is.
Additionally, update VMA userland test headers to reflect the change.
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
Documentation/filesystems/mmap_prepare.rst | 15 +++
include/linux/fs.h | 9 +-
include/linux/mm.h | 20 +++-
mm/internal.h | 8 ++
mm/util.c | 129 ++++++++++++++-------
mm/vma.c | 35 +++---
tools/testing/vma/include/dup.h | 27 ++++-
tools/testing/vma/include/stubs.h | 3 +-
8 files changed, 186 insertions(+), 60 deletions(-)
diff --git a/Documentation/filesystems/mmap_prepare.rst b/Documentation/filesystems/mmap_prepare.rst
index 65a1f094e469..20db474915da 100644
--- a/Documentation/filesystems/mmap_prepare.rst
+++ b/Documentation/filesystems/mmap_prepare.rst
@@ -25,6 +25,21 @@ That is - no resources should be allocated nor state updated to reflect that a
mapping has been established, as the mapping may either be merged, or fail to be
mapped after the callback is complete.
+Mapped callback
+---------------
+
+If resources need to be allocated per-mapping, or state such as a reference
+count needs to be manipulated, this should be done using the ``vm_ops->mapped``
+hook, which itself should be set by the >mmap_prepare hook.
+
+This callback is only invoked if a new mapping has been established and was not
+merged with any other, and is invoked at a point where no error may occur before
+the mapping is established.
+
+You may return an error to the callback itself, which will cause the mapping to
+become unmapped and an error returned to the mmap() caller. This is useful if
+resources need to be allocated, and that allocation might fail.
+
How To Use
==========
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a2628a12bd2b..c390f5c667e3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2059,13 +2059,20 @@ static inline bool can_mmap_file(struct file *file)
}
int compat_vma_mmap(struct file *file, struct vm_area_struct *vma);
+int __vma_check_mmap_hook(struct vm_area_struct *vma);
static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma)
{
+ int err;
+
if (file->f_op->mmap_prepare)
return compat_vma_mmap(file, vma);
- return file->f_op->mmap(file, vma);
+ err = file->f_op->mmap(file, vma);
+ if (err)
+ return err;
+
+ return __vma_check_mmap_hook(vma);
}
static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index da94edb287cd..68dee1101313 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -777,6 +777,23 @@ struct vm_operations_struct {
* Context: User context. May sleep. Caller holds mmap_lock.
*/
void (*close)(struct vm_area_struct *vma);
+ /**
+ * @mapped: Called when the VMA is first mapped in the MM. Not called if
+ * the new VMA is merged with an adjacent VMA.
+ *
+ * The @vm_private_data field is an output field allowing the user to
+ * modify vma->vm_private_data as necessary.
+ *
+ * ONLY valid if set from f_op->mmap_prepare. Will result in an error if
+ * set from f_op->mmap.
+ *
+ * Returns %0 on success, or an error otherwise. On error, the VMA will
+ * be unmapped.
+ *
+ * Context: User context. May sleep. Caller holds mmap_lock.
+ */
+ int (*mapped)(unsigned long start, unsigned long end, pgoff_t pgoff,
+ const struct file *file, void **vm_private_data);
/* Called any time before splitting to check if it's allowed */
int (*may_split)(struct vm_area_struct *vma, unsigned long addr);
int (*mremap)(struct vm_area_struct *vma);
@@ -4327,7 +4344,8 @@ static inline void mmap_action_ioremap_full(struct vm_area_desc *desc,
int mmap_action_prepare(struct vm_area_desc *desc);
int mmap_action_complete(struct vm_area_struct *vma,
- struct mmap_action *action);
+ struct mmap_action *action,
+ bool rmap_lock_held);
/* Look up the first VMA which exactly match the interval vm_start ... vm_end */
static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
diff --git a/mm/internal.h b/mm/internal.h
index 0256ca44115a..e0f554178143 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -202,6 +202,14 @@ static inline void vma_close(struct vm_area_struct *vma)
/* unmap_vmas is in mm/memory.c */
void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap);
+static inline void unmap_vma_locked(struct vm_area_struct *vma)
+{
+ const size_t len = vma_pages(vma) << PAGE_SHIFT;
+
+ mmap_assert_write_locked(vma->vm_mm);
+ do_munmap(vma->vm_mm, vma->vm_start, len, NULL);
+}
+
#ifdef CONFIG_MMU
static inline void get_anon_vma(struct anon_vma *anon_vma)
diff --git a/mm/util.c b/mm/util.c
index 73c97a748d8e..fc1bd8a8f3ea 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1163,6 +1163,54 @@ void flush_dcache_folio(struct folio *folio)
EXPORT_SYMBOL(flush_dcache_folio);
#endif
+static int __compat_vma_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct vm_area_desc desc = {
+ .mm = vma->vm_mm,
+ .file = file,
+ .start = vma->vm_start,
+ .end = vma->vm_end,
+
+ .pgoff = vma->vm_pgoff,
+ .vm_file = vma->vm_file,
+ .vma_flags = vma->flags,
+ .page_prot = vma->vm_page_prot,
+
+ .action.type = MMAP_NOTHING, /* Default */
+ };
+ int err;
+
+ err = vfs_mmap_prepare(file, &desc);
+ if (err)
+ return err;
+
+ err = mmap_action_prepare(&desc);
+ if (err)
+ return err;
+
+ set_vma_from_desc(vma, &desc);
+ return mmap_action_complete(vma, &desc.action, /*rmap_lock_held=*/false);
+}
+
+static int __compat_vma_mapped(struct file *file, struct vm_area_struct *vma)
+{
+ const struct vm_operations_struct *vm_ops = vma->vm_ops;
+ void *vm_private_data = vma->vm_private_data;
+ int err;
+
+ if (!vm_ops || !vm_ops->mapped)
+ return 0;
+
+ err = vm_ops->mapped(vma->vm_start, vma->vm_end, vma->vm_pgoff, file,
+ &vm_private_data);
+ if (err)
+ unmap_vma_locked(vma);
+ else if (vm_private_data != vma->vm_private_data)
+ vma->vm_private_data = vm_private_data;
+
+ return err;
+}
+
/**
* compat_vma_mmap() - Apply the file's .mmap_prepare() hook to an
* existing VMA and execute any requested actions.
@@ -1191,34 +1239,26 @@ EXPORT_SYMBOL(flush_dcache_folio);
*/
int compat_vma_mmap(struct file *file, struct vm_area_struct *vma)
{
- struct vm_area_desc desc = {
- .mm = vma->vm_mm,
- .file = file,
- .start = vma->vm_start,
- .end = vma->vm_end,
-
- .pgoff = vma->vm_pgoff,
- .vm_file = vma->vm_file,
- .vma_flags = vma->flags,
- .page_prot = vma->vm_page_prot,
-
- .action.type = MMAP_NOTHING, /* Default */
- };
int err;
- err = vfs_mmap_prepare(file, &desc);
+ err = __compat_vma_mmap(file, vma);
if (err)
return err;
- err = mmap_action_prepare(&desc);
- if (err)
- return err;
-
- set_vma_from_desc(vma, &desc);
- return mmap_action_complete(vma, &desc.action);
+ return __compat_vma_mapped(file, vma);
}
EXPORT_SYMBOL(compat_vma_mmap);
+int __vma_check_mmap_hook(struct vm_area_struct *vma)
+{
+ /* vm_ops->mapped is not valid if mmap() is specified. */
+ if (vma->vm_ops && WARN_ON_ONCE(vma->vm_ops->mapped))
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL(__vma_check_mmap_hook);
+
static void set_ps_flags(struct page_snapshot *ps, const struct folio *folio,
const struct page *page)
{
@@ -1308,32 +1348,31 @@ void snapshot_page(struct page_snapshot *ps, const struct page *page)
}
static int mmap_action_finish(struct vm_area_struct *vma,
- struct mmap_action *action, int err)
+ struct mmap_action *action, int err,
+ bool rmap_lock_held)
{
+ if (rmap_lock_held)
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
+
+ if (!err) {
+ if (action->success_hook)
+ return action->success_hook(vma);
+ return 0;
+ }
+
/*
* If an error occurs, unmap the VMA altogether and return an error. We
* only clear the newly allocated VMA, since this function is only
* invoked if we do NOT merge, so we only clean up the VMA we created.
*/
- if (err) {
- const size_t len = vma_pages(vma) << PAGE_SHIFT;
-
- do_munmap(current->mm, vma->vm_start, len, NULL);
-
- if (action->error_hook) {
- /* We may want to filter the error. */
- err = action->error_hook(err);
-
- /* The caller should not clear the error. */
- VM_WARN_ON_ONCE(!err);
- }
- return err;
+ unmap_vma_locked(vma);
+ if (action->error_hook) {
+ /* We may want to filter the error. */
+ err = action->error_hook(err);
+ /* The caller should not clear the error. */
+ VM_WARN_ON_ONCE(!err);
}
-
- if (action->success_hook)
- return action->success_hook(vma);
-
- return 0;
+ return err;
}
#ifdef CONFIG_MMU
@@ -1364,13 +1403,15 @@ EXPORT_SYMBOL(mmap_action_prepare);
* mmap_action_complete - Execute VMA descriptor action.
* @vma: The VMA to perform the action upon.
* @action: The action to perform.
+ * @rmap_lock_held: Is the file rmap lock held?
*
* Similar to mmap_action_prepare().
*
* Return: 0 on success, or error, at which point the VMA will be unmapped.
*/
int mmap_action_complete(struct vm_area_struct *vma,
- struct mmap_action *action)
+ struct mmap_action *action,
+ bool rmap_lock_held)
{
int err = 0;
@@ -1388,7 +1429,8 @@ int mmap_action_complete(struct vm_area_struct *vma,
break;
}
- return mmap_action_finish(vma, action, err);
+ return mmap_action_finish(vma, action, err,
+ rmap_lock_held);
}
EXPORT_SYMBOL(mmap_action_complete);
#else
@@ -1408,7 +1450,8 @@ int mmap_action_prepare(struct vm_area_desc *desc)
EXPORT_SYMBOL(mmap_action_prepare);
int mmap_action_complete(struct vm_area_struct *vma,
- struct mmap_action *action)
+ struct mmap_action *action,
+ bool rmap_lock_held)
{
int err = 0;
@@ -1423,7 +1466,7 @@ int mmap_action_complete(struct vm_area_struct *vma,
break;
}
- return mmap_action_finish(vma, action, err);
+ return mmap_action_finish(vma, action, err, rmap_lock_held);
}
EXPORT_SYMBOL(mmap_action_complete);
#endif
diff --git a/mm/vma.c b/mm/vma.c
index 2a86c7575000..a27d1278ea6d 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -2731,21 +2731,28 @@ static bool can_set_ksm_flags_early(struct mmap_state *map)
return false;
}
-static int call_action_complete(struct mmap_state *map,
- struct mmap_action *action,
- struct vm_area_struct *vma)
+static int call_mapped_hook(struct mmap_state *map,
+ struct vm_area_struct *vma)
{
- int ret;
-
- ret = mmap_action_complete(vma, action);
+ const struct vm_operations_struct *vm_ops = vma->vm_ops;
+ void *vm_private_data = vma->vm_private_data;
+ int err;
- /* If we held the file rmap we need to release it. */
- if (map->hold_file_rmap_lock) {
- struct file *file = vma->vm_file;
+ if (!vm_ops || !vm_ops->mapped)
+ return 0;
+ err = vm_ops->mapped(vma->vm_start, vma->vm_end, vma->vm_pgoff,
+ vma->vm_file, &vm_private_data);
+ if (err) {
+ if (map->hold_file_rmap_lock)
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
- i_mmap_unlock_write(file->f_mapping);
+ unmap_vma_locked(vma);
+ return err;
}
- return ret;
+ /* Update private data if changed. */
+ if (vm_private_data != vma->vm_private_data)
+ vma->vm_private_data = vm_private_data;
+ return 0;
}
static unsigned long __mmap_region(struct file *file, unsigned long addr,
@@ -2799,8 +2806,10 @@ static unsigned long __mmap_region(struct file *file, unsigned long addr,
__mmap_complete(&map, vma);
if (have_mmap_prepare && allocated_new) {
- error = call_action_complete(&map, &desc.action, vma);
-
+ error = mmap_action_complete(vma, &desc.action,
+ map.hold_file_rmap_lock);
+ if (!error)
+ error = call_mapped_hook(&map, vma);
if (error)
return error;
}
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 8ae525ed1738..aa34966cbc62 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -643,6 +643,23 @@ struct vm_operations_struct {
* Context: User context. May sleep. Caller holds mmap_lock.
*/
void (*close)(struct vm_area_struct *vma);
+ /**
+ * @mapped: Called when the VMA is first mapped in the MM. Not called if
+ * the new VMA is merged with an adjacent VMA.
+ *
+ * The @vm_private_data field is an output field allowing the user to
+ * modify vma->vm_private_data as necessary.
+ *
+ * ONLY valid if set from f_op->mmap_prepare. Will result in an error if
+ * set from f_op->mmap.
+ *
+ * Returns %0 on success, or an error otherwise. On error, the VMA will
+ * be unmapped.
+ *
+ * Context: User context. May sleep. Caller holds mmap_lock.
+ */
+ int (*mapped)(unsigned long start, unsigned long end, pgoff_t pgoff,
+ const struct file *file, void **vm_private_data);
/* Called any time before splitting to check if it's allowed */
int (*may_split)(struct vm_area_struct *vma, unsigned long addr);
int (*mremap)(struct vm_area_struct *vma);
@@ -1281,7 +1298,7 @@ static inline int __compat_vma_mmap(const struct file_operations *f_op,
return err;
set_vma_from_desc(vma, &desc);
- return mmap_action_complete(vma, &desc.action);
+ return mmap_action_complete(vma, &desc.action, /*rmap_lock_held=*/false);
}
static inline int compat_vma_mmap(struct file *file,
@@ -1500,3 +1517,11 @@ static inline pgprot_t vma_get_page_prot(vma_flags_t vma_flags)
return vm_get_page_prot(vm_flags);
}
+
+static inline void unmap_vma_locked(struct vm_area_struct *vma)
+{
+ const size_t len = vma_pages(vma) << PAGE_SHIFT;
+
+ mmap_assert_write_locked(vma->vm_mm);
+ do_munmap(vma->vm_mm, vma->vm_start, len, NULL);
+}
diff --git a/tools/testing/vma/include/stubs.h b/tools/testing/vma/include/stubs.h
index a30b8bc84955..d1c3d4ddb5e9 100644
--- a/tools/testing/vma/include/stubs.h
+++ b/tools/testing/vma/include/stubs.h
@@ -87,7 +87,8 @@ static inline int mmap_action_prepare(struct vm_area_desc *desc)
}
static inline int mmap_action_complete(struct vm_area_struct *vma,
- struct mmap_action *action)
+ struct mmap_action *action,
+ bool rmap_lock_held)
{
return 0;
}
--
2.53.0
^ permalink raw reply related
* [PATCH v3 05/16] fs: afs: correctly drop reference count on mapping failure
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
Commit 9d5403b1036c ("fs: convert most other generic_file_*mmap() users to
.mmap_prepare()") updated AFS to use the mmap_prepare callback in favour
of the deprecated mmap callback.
However, it did not account for the fact that mmap_prepare is called
pre-merge, and may then be merged, nor that mmap_prepare can fail to map
due to an out of memory error.
Both of those are cases in which we should not be incrementing a reference
count.
With the newly added vm_ops->mapped callback available, we can simply
defer this operation to that callback which is only invoked once the
mapping is successfully in place (but not yet visible to userspace as the
mmap and VMA write locks are held).
Therefore add afs_mapped() to implement this callback for AFS, and remove
the code doing so in afs_mmap_prepare().
Also update afs_vm_open(), afs_vm_close() and afs_vm_map_pages() to be
consistent in how the vnode is accessed.
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
fs/afs/file.c | 36 ++++++++++++++++++++++++++----------
1 file changed, 26 insertions(+), 10 deletions(-)
diff --git a/fs/afs/file.c b/fs/afs/file.c
index f609366fd2ac..85696ac984cc 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -28,6 +28,8 @@ static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos,
static void afs_vm_open(struct vm_area_struct *area);
static void afs_vm_close(struct vm_area_struct *area);
static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff);
+static int afs_mapped(unsigned long start, unsigned long end, pgoff_t pgoff,
+ const struct file *file, void **vm_private_data);
const struct file_operations afs_file_operations = {
.open = afs_open,
@@ -61,6 +63,7 @@ const struct address_space_operations afs_file_aops = {
};
static const struct vm_operations_struct afs_vm_ops = {
+ .mapped = afs_mapped,
.open = afs_vm_open,
.close = afs_vm_close,
.fault = filemap_fault,
@@ -494,32 +497,45 @@ static void afs_drop_open_mmap(struct afs_vnode *vnode)
*/
static int afs_file_mmap_prepare(struct vm_area_desc *desc)
{
- struct afs_vnode *vnode = AFS_FS_I(file_inode(desc->file));
int ret;
- afs_add_open_mmap(vnode);
-
ret = generic_file_mmap_prepare(desc);
- if (ret == 0)
- desc->vm_ops = &afs_vm_ops;
- else
- afs_drop_open_mmap(vnode);
+ if (ret)
+ return ret;
+
+ desc->vm_ops = &afs_vm_ops;
return ret;
}
+static int afs_mapped(unsigned long start, unsigned long end, pgoff_t pgoff,
+ const struct file *file, void **vm_private_data)
+{
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
+
+ afs_add_open_mmap(vnode);
+ return 0;
+}
+
static void afs_vm_open(struct vm_area_struct *vma)
{
- afs_add_open_mmap(AFS_FS_I(file_inode(vma->vm_file)));
+ struct file *file = vma->vm_file;
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
+
+ afs_add_open_mmap(vnode);
}
static void afs_vm_close(struct vm_area_struct *vma)
{
- afs_drop_open_mmap(AFS_FS_I(file_inode(vma->vm_file)));
+ struct file *file = vma->vm_file;
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
+
+ afs_drop_open_mmap(vnode);
}
static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff)
{
- struct afs_vnode *vnode = AFS_FS_I(file_inode(vmf->vma->vm_file));
+ struct file *file = vmf->vma->vm_file;
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
if (afs_check_validity(vnode))
return filemap_map_pages(vmf, start_pgoff, end_pgoff);
--
2.53.0
^ permalink raw reply related
* [PATCH v3 06/16] mm: add mmap_action_simple_ioremap()
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
Currently drivers use vm_iomap_memory() as a simple helper function for
I/O remapping memory over a range starting at a specified physical address
over a specified length.
In order to utilise this from mmap_prepare, separate out the core logic
into __simple_ioremap_prep(), update vm_iomap_memory() to use it, and add
simple_ioremap_prepare() to do the same with a VMA descriptor object.
We also add MMAP_SIMPLE_IO_REMAP and relevant fields to the struct
mmap_action type to permit this operation also.
We use mmap_action_ioremap() to set up the actual I/O remap operation once
we have checked and figured out the parameters, which makes
simple_ioremap_prepare() easy to implement.
We then add mmap_action_simple_ioremap() to allow drivers to make use of
this mode.
We update the mmap_prepare documentation to describe this mode. Finally,
we update the VMA tests to reflect this change.
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
Documentation/filesystems/mmap_prepare.rst | 3 +
include/linux/mm.h | 24 +++++-
include/linux/mm_types.h | 6 +-
mm/internal.h | 1 +
mm/memory.c | 85 +++++++++++++++-------
mm/util.c | 5 ++
tools/testing/vma/include/dup.h | 6 +-
7 files changed, 102 insertions(+), 28 deletions(-)
diff --git a/Documentation/filesystems/mmap_prepare.rst b/Documentation/filesystems/mmap_prepare.rst
index 20db474915da..be76ae475b9c 100644
--- a/Documentation/filesystems/mmap_prepare.rst
+++ b/Documentation/filesystems/mmap_prepare.rst
@@ -153,5 +153,8 @@ pointer. These are:
* mmap_action_ioremap_full() - Same as mmap_action_ioremap(), only remaps
the entire mapping from ``start_pfn`` onward.
+* mmap_action_simple_ioremap() - Sets up an I/O remap from a specified
+ physical address and over a specified length.
+
**NOTE:** The ``action`` field should never normally be manipulated directly,
rather you ought to use one of these helpers.
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 68dee1101313..ef2e4dccfe8e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4337,11 +4337,33 @@ static inline void mmap_action_ioremap(struct vm_area_desc *desc,
* @start_pfn: The first PFN in the range to remap.
*/
static inline void mmap_action_ioremap_full(struct vm_area_desc *desc,
- unsigned long start_pfn)
+ unsigned long start_pfn)
{
mmap_action_ioremap(desc, desc->start, start_pfn, vma_desc_size(desc));
}
+/**
+ * mmap_action_simple_ioremap - helper for mmap_prepare hook to specify that the
+ * physical range in [start_phys_addr, start_phys_addr + size) should be I/O
+ * remapped.
+ * @desc: The VMA descriptor for the VMA requiring remap.
+ * @start_phys_addr: Start of the physical memory to be mapped.
+ * @size: Size of the area to map.
+ *
+ * NOTE: Some drivers might want to tweak desc->page_prot for purposes of
+ * write-combine or similar.
+ */
+static inline void mmap_action_simple_ioremap(struct vm_area_desc *desc,
+ phys_addr_t start_phys_addr,
+ unsigned long size)
+{
+ struct mmap_action *action = &desc->action;
+
+ action->simple_ioremap.start_phys_addr = start_phys_addr;
+ action->simple_ioremap.size = size;
+ action->type = MMAP_SIMPLE_IO_REMAP;
+}
+
int mmap_action_prepare(struct vm_area_desc *desc);
int mmap_action_complete(struct vm_area_struct *vma,
struct mmap_action *action,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 4a229cc0a06b..50685cf29792 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -814,6 +814,7 @@ enum mmap_action_type {
MMAP_NOTHING, /* Mapping is complete, no further action. */
MMAP_REMAP_PFN, /* Remap PFN range. */
MMAP_IO_REMAP_PFN, /* I/O remap PFN range. */
+ MMAP_SIMPLE_IO_REMAP, /* I/O remap with guardrails. */
};
/*
@@ -822,13 +823,16 @@ enum mmap_action_type {
*/
struct mmap_action {
union {
- /* Remap range. */
struct {
unsigned long start;
unsigned long start_pfn;
unsigned long size;
pgprot_t pgprot;
} remap;
+ struct {
+ phys_addr_t start_phys_addr;
+ unsigned long size;
+ } simple_ioremap;
};
enum mmap_action_type type;
diff --git a/mm/internal.h b/mm/internal.h
index e0f554178143..2aa04d87ac10 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1804,6 +1804,7 @@ int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm);
int remap_pfn_range_prepare(struct vm_area_desc *desc);
int remap_pfn_range_complete(struct vm_area_struct *vma,
struct mmap_action *action);
+int simple_ioremap_prepare(struct vm_area_desc *desc);
static inline int io_remap_pfn_range_prepare(struct vm_area_desc *desc)
{
diff --git a/mm/memory.c b/mm/memory.c
index 9dec67a18116..b3bcc21af20a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3170,6 +3170,58 @@ int remap_pfn_range_complete(struct vm_area_struct *vma,
return do_remap_pfn_range(vma, start, pfn, size, prot);
}
+static int __simple_ioremap_prep(unsigned long vm_len, pgoff_t vm_pgoff,
+ phys_addr_t start_phys, unsigned long size,
+ unsigned long *pfnp)
+{
+ unsigned long pfn, pages;
+
+ /* Check that the physical memory area passed in looks valid */
+ if (start_phys + size < start_phys)
+ return -EINVAL;
+ /*
+ * You *really* shouldn't map things that aren't page-aligned,
+ * but we've historically allowed it because IO memory might
+ * just have smaller alignment.
+ */
+ size += start_phys & ~PAGE_MASK;
+ pfn = start_phys >> PAGE_SHIFT;
+ pages = (size + ~PAGE_MASK) >> PAGE_SHIFT;
+ if (pfn + pages < pfn)
+ return -EINVAL;
+
+ /* We start the mapping 'vm_pgoff' pages into the area */
+ if (vm_pgoff > pages)
+ return -EINVAL;
+ pfn += vm_pgoff;
+ pages -= vm_pgoff;
+
+ /* Can we fit all of the mapping? */
+ if ((vm_len >> PAGE_SHIFT) > pages)
+ return -EINVAL;
+
+ *pfnp = pfn;
+ return 0;
+}
+
+int simple_ioremap_prepare(struct vm_area_desc *desc)
+{
+ struct mmap_action *action = &desc->action;
+ const phys_addr_t start = action->simple_ioremap.start_phys_addr;
+ const unsigned long size = action->simple_ioremap.size;
+ unsigned long pfn;
+ int err;
+
+ err = __simple_ioremap_prep(vma_desc_size(desc), desc->pgoff,
+ start, size, &pfn);
+ if (err)
+ return err;
+
+ /* The I/O remap logic does the heavy lifting. */
+ mmap_action_ioremap_full(desc, pfn);
+ return io_remap_pfn_range_prepare(desc);
+}
+
/**
* vm_iomap_memory - remap memory to userspace
* @vma: user vma to map to
@@ -3187,32 +3239,15 @@ int remap_pfn_range_complete(struct vm_area_struct *vma,
*/
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
{
- unsigned long vm_len, pfn, pages;
-
- /* Check that the physical memory area passed in looks valid */
- if (start + len < start)
- return -EINVAL;
- /*
- * You *really* shouldn't map things that aren't page-aligned,
- * but we've historically allowed it because IO memory might
- * just have smaller alignment.
- */
- len += start & ~PAGE_MASK;
- pfn = start >> PAGE_SHIFT;
- pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
- if (pfn + pages < pfn)
- return -EINVAL;
-
- /* We start the mapping 'vm_pgoff' pages into the area */
- if (vma->vm_pgoff > pages)
- return -EINVAL;
- pfn += vma->vm_pgoff;
- pages -= vma->vm_pgoff;
+ const unsigned long vm_start = vma->vm_start;
+ const unsigned long vm_end = vma->vm_end;
+ const unsigned long vm_len = vm_end - vm_start;
+ unsigned long pfn;
+ int err;
- /* Can we fit all of the mapping? */
- vm_len = vma->vm_end - vma->vm_start;
- if (vm_len >> PAGE_SHIFT > pages)
- return -EINVAL;
+ err = __simple_ioremap_prep(vm_len, vma->vm_pgoff, start, len, &pfn);
+ if (err)
+ return err;
/* Ok, let it rip */
return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
diff --git a/mm/util.c b/mm/util.c
index fc1bd8a8f3ea..879ba62b5f0c 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1392,6 +1392,8 @@ int mmap_action_prepare(struct vm_area_desc *desc)
return remap_pfn_range_prepare(desc);
case MMAP_IO_REMAP_PFN:
return io_remap_pfn_range_prepare(desc);
+ case MMAP_SIMPLE_IO_REMAP:
+ return simple_ioremap_prepare(desc);
}
WARN_ON_ONCE(1);
@@ -1423,6 +1425,7 @@ int mmap_action_complete(struct vm_area_struct *vma,
err = remap_pfn_range_complete(vma, action);
break;
case MMAP_IO_REMAP_PFN:
+ case MMAP_SIMPLE_IO_REMAP:
/* Should have been delegated. */
WARN_ON_ONCE(1);
err = -EINVAL;
@@ -1441,6 +1444,7 @@ int mmap_action_prepare(struct vm_area_desc *desc)
break;
case MMAP_REMAP_PFN:
case MMAP_IO_REMAP_PFN:
+ case MMAP_SIMPLE_IO_REMAP:
WARN_ON_ONCE(1); /* nommu cannot handle these. */
break;
}
@@ -1460,6 +1464,7 @@ int mmap_action_complete(struct vm_area_struct *vma,
break;
case MMAP_REMAP_PFN:
case MMAP_IO_REMAP_PFN:
+ case MMAP_SIMPLE_IO_REMAP:
WARN_ON_ONCE(1); /* nommu cannot handle this. */
err = -EINVAL;
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index aa34966cbc62..1b86c34e1158 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -453,6 +453,7 @@ enum mmap_action_type {
MMAP_NOTHING, /* Mapping is complete, no further action. */
MMAP_REMAP_PFN, /* Remap PFN range. */
MMAP_IO_REMAP_PFN, /* I/O remap PFN range. */
+ MMAP_SIMPLE_IO_REMAP, /* I/O remap with guardrails. */
};
/*
@@ -461,13 +462,16 @@ enum mmap_action_type {
*/
struct mmap_action {
union {
- /* Remap range. */
struct {
unsigned long start;
unsigned long start_pfn;
unsigned long size;
pgprot_t pgprot;
} remap;
+ struct {
+ phys_addr_t start_phys_addr;
+ unsigned long size;
+ } simple_ioremap;
};
enum mmap_action_type type;
--
2.53.0
^ permalink raw reply related
* [PATCH v3 07/16] misc: open-dice: replace deprecated mmap hook with mmap_prepare
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
The f_op->mmap interface is deprecated, so update driver to use its
successor, mmap_prepare.
The driver previously used vm_iomap_memory(), so this change replaces it
with its mmap_prepare equivalent, mmap_action_simple_ioremap().
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
drivers/misc/open-dice.c | 19 +++++++++++--------
1 file changed, 11 insertions(+), 8 deletions(-)
diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c
index 24c29e0f00ef..45060fb4ea27 100644
--- a/drivers/misc/open-dice.c
+++ b/drivers/misc/open-dice.c
@@ -86,29 +86,32 @@ static ssize_t open_dice_write(struct file *filp, const char __user *ptr,
/*
* Creates a mapping of the reserved memory region in user address space.
*/
-static int open_dice_mmap(struct file *filp, struct vm_area_struct *vma)
+static int open_dice_mmap_prepare(struct vm_area_desc *desc)
{
+ struct file *filp = desc->file;
struct open_dice_drvdata *drvdata = to_open_dice_drvdata(filp);
- if (vma->vm_flags & VM_MAYSHARE) {
+ if (vma_desc_test(desc, VMA_MAYSHARE_BIT)) {
/* Do not allow userspace to modify the underlying data. */
- if (vma->vm_flags & VM_WRITE)
+ if (vma_desc_test(desc, VMA_WRITE_BIT))
return -EPERM;
/* Ensure userspace cannot acquire VM_WRITE later. */
- vm_flags_clear(vma, VM_MAYWRITE);
+ vma_desc_clear_flags(desc, VMA_MAYWRITE_BIT);
}
/* Create write-combine mapping so all clients observe a wipe. */
- vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
- vm_flags_set(vma, VM_DONTCOPY | VM_DONTDUMP);
- return vm_iomap_memory(vma, drvdata->rmem->base, drvdata->rmem->size);
+ desc->page_prot = pgprot_writecombine(desc->page_prot);
+ vma_desc_set_flags(desc, VMA_DONTCOPY_BIT, VMA_DONTDUMP_BIT);
+ mmap_action_simple_ioremap(desc, drvdata->rmem->base,
+ drvdata->rmem->size);
+ return 0;
}
static const struct file_operations open_dice_fops = {
.owner = THIS_MODULE,
.read = open_dice_read,
.write = open_dice_write,
- .mmap = open_dice_mmap,
+ .mmap_prepare = open_dice_mmap_prepare,
};
static int __init open_dice_probe(struct platform_device *pdev)
--
2.53.0
^ permalink raw reply related
* [PATCH v3 08/16] hpet: replace deprecated mmap hook with mmap_prepare
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
The f_op->mmap interface is deprecated, so update driver to use its
successor, mmap_prepare.
The driver previously used vm_iomap_memory(), so this change replaces it
with its mmap_prepare equivalent, mmap_action_simple_ioremap().
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
drivers/char/hpet.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 60dd09a56f50..8f128cc40147 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -354,8 +354,9 @@ static __init int hpet_mmap_enable(char *str)
}
__setup("hpet_mmap=", hpet_mmap_enable);
-static int hpet_mmap(struct file *file, struct vm_area_struct *vma)
+static int hpet_mmap_prepare(struct vm_area_desc *desc)
{
+ struct file *file = desc->file;
struct hpet_dev *devp;
unsigned long addr;
@@ -368,11 +369,12 @@ static int hpet_mmap(struct file *file, struct vm_area_struct *vma)
if (addr & (PAGE_SIZE - 1))
return -ENOSYS;
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- return vm_iomap_memory(vma, addr, PAGE_SIZE);
+ desc->page_prot = pgprot_noncached(desc->page_prot);
+ mmap_action_simple_ioremap(desc, addr, PAGE_SIZE);
+ return 0;
}
#else
-static int hpet_mmap(struct file *file, struct vm_area_struct *vma)
+static int hpet_mmap_prepare(struct vm_area_desc *desc)
{
return -ENOSYS;
}
@@ -710,7 +712,7 @@ static const struct file_operations hpet_fops = {
.open = hpet_open,
.release = hpet_release,
.fasync = hpet_fasync,
- .mmap = hpet_mmap,
+ .mmap_prepare = hpet_mmap_prepare,
};
static int hpet_is_known(struct hpet_data *hdp)
--
2.53.0
^ permalink raw reply related
* [PATCH v3 09/16] mtdchar: replace deprecated mmap hook with mmap_prepare, clean up
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
Replace the deprecated mmap callback with mmap_prepare.
Commit f5cf8f07423b ("mtd: Disable mtdchar mmap on MMU systems") commented
out the CONFIG_MMU part of this function back in 2012, so after ~14 years
it's probably reasonable to remove this altogether rather than updating
dead code.
Acked-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
drivers/mtd/mtdchar.c | 21 +++------------------
1 file changed, 3 insertions(+), 18 deletions(-)
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 55a43682c567..bf01e6ac7293 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -1376,27 +1376,12 @@ static unsigned mtdchar_mmap_capabilities(struct file *file)
/*
* set up a mapping for shared memory segments
*/
-static int mtdchar_mmap(struct file *file, struct vm_area_struct *vma)
+static int mtdchar_mmap_prepare(struct vm_area_desc *desc)
{
#ifdef CONFIG_MMU
- struct mtd_file_info *mfi = file->private_data;
- struct mtd_info *mtd = mfi->mtd;
- struct map_info *map = mtd->priv;
-
- /* This is broken because it assumes the MTD device is map-based
- and that mtd->priv is a valid struct map_info. It should be
- replaced with something that uses the mtd_get_unmapped_area()
- operation properly. */
- if (0 /*mtd->type == MTD_RAM || mtd->type == MTD_ROM*/) {
-#ifdef pgprot_noncached
- if (file->f_flags & O_DSYNC || map->phys >= __pa(high_memory))
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-#endif
- return vm_iomap_memory(vma, map->phys, map->size);
- }
return -ENODEV;
#else
- return vma->vm_flags & VM_SHARED ? 0 : -EACCES;
+ return vma_desc_test(desc, VMA_SHARED_BIT) ? 0 : -EACCES;
#endif
}
@@ -1411,7 +1396,7 @@ static const struct file_operations mtd_fops = {
#endif
.open = mtdchar_open,
.release = mtdchar_close,
- .mmap = mtdchar_mmap,
+ .mmap_prepare = mtdchar_mmap_prepare,
#ifndef CONFIG_MMU
.get_unmapped_area = mtdchar_get_unmapped_area,
.mmap_capabilities = mtdchar_mmap_capabilities,
--
2.53.0
^ permalink raw reply related
* [PATCH v3 10/16] stm: replace deprecated mmap hook with mmap_prepare
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
The f_op->mmap interface is deprecated, so update driver to use its
successor, mmap_prepare.
The driver previously used vm_iomap_memory(), so this change replaces it
with its mmap_prepare equivalent, mmap_action_simple_ioremap().
Also, in order to correctly maintain reference counting, add a
vm_ops->mapped callback to increment the reference count when successfully
mapped.
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
drivers/hwtracing/stm/core.c | 31 +++++++++++++++++++++----------
1 file changed, 21 insertions(+), 10 deletions(-)
diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c
index 37584e786bb5..f48c6a8a0654 100644
--- a/drivers/hwtracing/stm/core.c
+++ b/drivers/hwtracing/stm/core.c
@@ -666,6 +666,16 @@ static ssize_t stm_char_write(struct file *file, const char __user *buf,
return count;
}
+static int stm_mmap_mapped(unsigned long start, unsigned long end, pgoff_t pgoff,
+ const struct file *file, void **vm_private_data)
+{
+ struct stm_file *stmf = file->private_data;
+ struct stm_device *stm = stmf->stm;
+
+ pm_runtime_get_sync(&stm->dev);
+ return 0;
+}
+
static void stm_mmap_open(struct vm_area_struct *vma)
{
struct stm_file *stmf = vma->vm_file->private_data;
@@ -684,12 +694,14 @@ static void stm_mmap_close(struct vm_area_struct *vma)
}
static const struct vm_operations_struct stm_mmap_vmops = {
+ .mapped = stm_mmap_mapped,
.open = stm_mmap_open,
.close = stm_mmap_close,
};
-static int stm_char_mmap(struct file *file, struct vm_area_struct *vma)
+static int stm_char_mmap_prepare(struct vm_area_desc *desc)
{
+ struct file *file = desc->file;
struct stm_file *stmf = file->private_data;
struct stm_device *stm = stmf->stm;
unsigned long size, phys;
@@ -697,10 +709,10 @@ static int stm_char_mmap(struct file *file, struct vm_area_struct *vma)
if (!stm->data->mmio_addr)
return -EOPNOTSUPP;
- if (vma->vm_pgoff)
+ if (desc->pgoff)
return -EINVAL;
- size = vma->vm_end - vma->vm_start;
+ size = vma_desc_size(desc);
if (stmf->output.nr_chans * stm->data->sw_mmiosz != size)
return -EINVAL;
@@ -712,13 +724,12 @@ static int stm_char_mmap(struct file *file, struct vm_area_struct *vma)
if (!phys)
return -EINVAL;
- pm_runtime_get_sync(&stm->dev);
-
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP);
- vma->vm_ops = &stm_mmap_vmops;
- vm_iomap_memory(vma, phys, size);
+ desc->page_prot = pgprot_noncached(desc->page_prot);
+ vma_desc_set_flags(desc, VMA_IO_BIT, VMA_DONTEXPAND_BIT,
+ VMA_DONTDUMP_BIT);
+ desc->vm_ops = &stm_mmap_vmops;
+ mmap_action_simple_ioremap(desc, phys, size);
return 0;
}
@@ -836,7 +847,7 @@ static const struct file_operations stm_fops = {
.open = stm_char_open,
.release = stm_char_release,
.write = stm_char_write,
- .mmap = stm_char_mmap,
+ .mmap_prepare = stm_char_mmap_prepare,
.unlocked_ioctl = stm_char_ioctl,
.compat_ioctl = compat_ptr_ioctl,
};
--
2.53.0
^ permalink raw reply related
* [PATCH v3 11/16] staging: vme_user: replace deprecated mmap hook with mmap_prepare
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
The f_op->mmap interface is deprecated, so update driver to use its
successor, mmap_prepare.
The driver previously used vm_iomap_memory(), so this change replaces it
with its mmap_prepare equivalent, mmap_action_simple_ioremap().
Functions that wrap mmap() are also converted to wrap mmap_prepare()
instead.
Also update the documentation accordingly.
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
Documentation/driver-api/vme.rst | 2 +-
drivers/staging/vme_user/vme.c | 20 +++++------
drivers/staging/vme_user/vme.h | 2 +-
drivers/staging/vme_user/vme_user.c | 51 +++++++++++++++++------------
4 files changed, 42 insertions(+), 33 deletions(-)
diff --git a/Documentation/driver-api/vme.rst b/Documentation/driver-api/vme.rst
index c0b475369de0..7111999abc14 100644
--- a/Documentation/driver-api/vme.rst
+++ b/Documentation/driver-api/vme.rst
@@ -107,7 +107,7 @@ The function :c:func:`vme_master_read` can be used to read from and
In addition to simple reads and writes, :c:func:`vme_master_rmw` is provided to
do a read-modify-write transaction. Parts of a VME window can also be mapped
-into user space memory using :c:func:`vme_master_mmap`.
+into user space memory using :c:func:`vme_master_mmap_prepare`.
Slave windows
diff --git a/drivers/staging/vme_user/vme.c b/drivers/staging/vme_user/vme.c
index f10a00c05f12..7220aba7b919 100644
--- a/drivers/staging/vme_user/vme.c
+++ b/drivers/staging/vme_user/vme.c
@@ -735,9 +735,9 @@ unsigned int vme_master_rmw(struct vme_resource *resource, unsigned int mask,
EXPORT_SYMBOL(vme_master_rmw);
/**
- * vme_master_mmap - Mmap region of VME master window.
+ * vme_master_mmap_prepare - Mmap region of VME master window.
* @resource: Pointer to VME master resource.
- * @vma: Pointer to definition of user mapping.
+ * @desc: Pointer to descriptor of user mapping.
*
* Memory map a region of the VME master window into user space.
*
@@ -745,12 +745,13 @@ EXPORT_SYMBOL(vme_master_rmw);
* resource or -EFAULT if map exceeds window size. Other generic mmap
* errors may also be returned.
*/
-int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma)
+int vme_master_mmap_prepare(struct vme_resource *resource,
+ struct vm_area_desc *desc)
{
+ const unsigned long vma_size = vma_desc_size(desc);
struct vme_bridge *bridge = find_bridge(resource);
struct vme_master_resource *image;
phys_addr_t phys_addr;
- unsigned long vma_size;
if (resource->type != VME_MASTER) {
dev_err(bridge->parent, "Not a master resource\n");
@@ -758,19 +759,18 @@ int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma)
}
image = list_entry(resource->entry, struct vme_master_resource, list);
- phys_addr = image->bus_resource.start + (vma->vm_pgoff << PAGE_SHIFT);
- vma_size = vma->vm_end - vma->vm_start;
+ phys_addr = image->bus_resource.start + (desc->pgoff << PAGE_SHIFT);
if (phys_addr + vma_size > image->bus_resource.end + 1) {
dev_err(bridge->parent, "Map size cannot exceed the window size\n");
return -EFAULT;
}
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
- return vm_iomap_memory(vma, phys_addr, vma->vm_end - vma->vm_start);
+ desc->page_prot = pgprot_noncached(desc->page_prot);
+ mmap_action_simple_ioremap(desc, phys_addr, vma_size);
+ return 0;
}
-EXPORT_SYMBOL(vme_master_mmap);
+EXPORT_SYMBOL(vme_master_mmap_prepare);
/**
* vme_master_free - Free VME master window
diff --git a/drivers/staging/vme_user/vme.h b/drivers/staging/vme_user/vme.h
index 797e9940fdd1..b6413605ea49 100644
--- a/drivers/staging/vme_user/vme.h
+++ b/drivers/staging/vme_user/vme.h
@@ -151,7 +151,7 @@ ssize_t vme_master_read(struct vme_resource *resource, void *buf, size_t count,
ssize_t vme_master_write(struct vme_resource *resource, void *buf, size_t count, loff_t offset);
unsigned int vme_master_rmw(struct vme_resource *resource, unsigned int mask, unsigned int compare,
unsigned int swap, loff_t offset);
-int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma);
+int vme_master_mmap_prepare(struct vme_resource *resource, struct vm_area_desc *desc);
void vme_master_free(struct vme_resource *resource);
struct vme_resource *vme_dma_request(struct vme_dev *vdev, u32 route);
diff --git a/drivers/staging/vme_user/vme_user.c b/drivers/staging/vme_user/vme_user.c
index d95dd7d9190a..11e25c2f6b0a 100644
--- a/drivers/staging/vme_user/vme_user.c
+++ b/drivers/staging/vme_user/vme_user.c
@@ -446,24 +446,14 @@ static void vme_user_vm_close(struct vm_area_struct *vma)
kfree(vma_priv);
}
-static const struct vm_operations_struct vme_user_vm_ops = {
- .open = vme_user_vm_open,
- .close = vme_user_vm_close,
-};
-
-static int vme_user_master_mmap(unsigned int minor, struct vm_area_struct *vma)
+static int vme_user_vm_mapped(unsigned long start, unsigned long end, pgoff_t pgoff,
+ const struct file *file, void **vm_private_data)
{
- int err;
+ const unsigned int minor = iminor(file_inode(file));
struct vme_user_vma_priv *vma_priv;
mutex_lock(&image[minor].mutex);
- err = vme_master_mmap(image[minor].resource, vma);
- if (err) {
- mutex_unlock(&image[minor].mutex);
- return err;
- }
-
vma_priv = kmalloc_obj(*vma_priv);
if (!vma_priv) {
mutex_unlock(&image[minor].mutex);
@@ -472,22 +462,41 @@ static int vme_user_master_mmap(unsigned int minor, struct vm_area_struct *vma)
vma_priv->minor = minor;
refcount_set(&vma_priv->refcnt, 1);
- vma->vm_ops = &vme_user_vm_ops;
- vma->vm_private_data = vma_priv;
-
+ *vm_private_data = vma_priv;
image[minor].mmap_count++;
mutex_unlock(&image[minor].mutex);
-
return 0;
}
-static int vme_user_mmap(struct file *file, struct vm_area_struct *vma)
+static const struct vm_operations_struct vme_user_vm_ops = {
+ .mapped = vme_user_vm_mapped,
+ .open = vme_user_vm_open,
+ .close = vme_user_vm_close,
+};
+
+static int vme_user_master_mmap_prepare(unsigned int minor,
+ struct vm_area_desc *desc)
+{
+ int err;
+
+ mutex_lock(&image[minor].mutex);
+
+ err = vme_master_mmap_prepare(image[minor].resource, desc);
+ if (!err)
+ desc->vm_ops = &vme_user_vm_ops;
+
+ mutex_unlock(&image[minor].mutex);
+ return err;
+}
+
+static int vme_user_mmap_prepare(struct vm_area_desc *desc)
{
- unsigned int minor = iminor(file_inode(file));
+ const struct file *file = desc->file;
+ const unsigned int minor = iminor(file_inode(file));
if (type[minor] == MASTER_MINOR)
- return vme_user_master_mmap(minor, vma);
+ return vme_user_master_mmap_prepare(minor, desc);
return -ENODEV;
}
@@ -498,7 +507,7 @@ static const struct file_operations vme_user_fops = {
.llseek = vme_user_llseek,
.unlocked_ioctl = vme_user_unlocked_ioctl,
.compat_ioctl = compat_ptr_ioctl,
- .mmap = vme_user_mmap,
+ .mmap_prepare = vme_user_mmap_prepare,
};
static int vme_user_match(struct vme_dev *vdev)
--
2.53.0
^ permalink raw reply related
* [PATCH v3 12/16] mm: allow handling of stacked mmap_prepare hooks in more drivers
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
While the conversion of mmap hooks to mmap_prepare is underway, we will
encounter situations where mmap hooks need to invoke nested mmap_prepare
hooks.
The nesting of mmap hooks is termed 'stacking'. In order to flexibly
facilitate the conversion of custom mmap hooks in drivers which stack, we
must split up the existing __compat_vma_mmap() function into two separate
functions:
* compat_set_desc_from_vma() - This allows the setting of a vm_area_desc
object's fields to the relevant fields of a VMA.
* __compat_vma_mmap() - Once an mmap_prepare hook has been executed upon a
vm_area_desc object, this function performs any mmap actions specified by
the mmap_prepare hook and then invokes its vm_ops->mapped() hook if any
were specified.
In ordinary cases, where a file's f_op->mmap_prepare() hook simply needs
to be invoked in a stacked mmap() hook, compat_vma_mmap() can be used.
However some drivers define their own nested hooks, which are invoked in
turn by another hook.
A concrete example is vmbus_channel->mmap_ring_buffer(), which is invoked
in turn by bin_attribute->mmap():
vmbus_channel->mmap_ring_buffer() has a signature of:
int (*mmap_ring_buffer)(struct vmbus_channel *channel,
struct vm_area_struct *vma);
And bin_attribute->mmap() has a signature of:
int (*mmap)(struct file *, struct kobject *,
const struct bin_attribute *attr,
struct vm_area_struct *vma);
And so compat_vma_mmap() cannot be used here for incremental conversion of
hooks from mmap() to mmap_prepare().
There are many such instances like this, where conversion to mmap_prepare
would otherwise cascade to a huge change set due to nesting of this kind.
The changes in this patch mean we could now instead convert
vmbus_channel->mmap_ring_buffer() to
vmbus_channel->mmap_prepare_ring_buffer(), and implement something like:
struct vm_area_desc desc;
int err;
compat_set_desc_from_vma(&desc, file, vma);
err = channel->mmap_prepare_ring_buffer(channel, &desc);
if (err)
return err;
return __compat_vma_mmap(&desc, vma);
Allowing us to incrementally update this logic, and other logic like it.
Unfortunately, as part of this change, we need to be able to flexibly
assign to the VMA descriptor, so have to remove some of the const
declarations within the structure.
Also update the VMA tests to reflect the changes.
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
include/linux/fs.h | 3 +
include/linux/mm_types.h | 4 +-
mm/util.c | 112 ++++++++++++++++++++++---------
mm/vma.h | 2 +-
tools/testing/vma/include/dup.h | 114 +++++++++++++++++++++-----------
5 files changed, 162 insertions(+), 73 deletions(-)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c390f5c667e3..0bdccfa70b44 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2058,6 +2058,9 @@ static inline bool can_mmap_file(struct file *file)
return true;
}
+void compat_set_desc_from_vma(struct vm_area_desc *desc, const struct file *file,
+ const struct vm_area_struct *vma);
+int __compat_vma_mmap(struct vm_area_desc *desc, struct vm_area_struct *vma);
int compat_vma_mmap(struct file *file, struct vm_area_struct *vma);
int __vma_check_mmap_hook(struct vm_area_struct *vma);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 50685cf29792..7538d64f8848 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -891,8 +891,8 @@ static __always_inline bool vma_flags_empty(vma_flags_t *flags)
*/
struct vm_area_desc {
/* Immutable state. */
- const struct mm_struct *const mm;
- struct file *const file; /* May vary from vm_file in stacked callers. */
+ struct mm_struct *mm;
+ struct file *file; /* May vary from vm_file in stacked callers. */
unsigned long start;
unsigned long end;
diff --git a/mm/util.c b/mm/util.c
index 879ba62b5f0c..8cf59267a9ac 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1163,34 +1163,40 @@ void flush_dcache_folio(struct folio *folio)
EXPORT_SYMBOL(flush_dcache_folio);
#endif
-static int __compat_vma_mmap(struct file *file, struct vm_area_struct *vma)
+/**
+ * compat_set_desc_from_vma() - assigns VMA descriptor @desc fields from a VMA.
+ * @desc: A VMA descriptor whose fields need to be set.
+ * @file: The file object describing the file being mmap()'d.
+ * @vma: The VMA whose fields we wish to assign to @desc.
+ *
+ * This is a compatibility function to allow an mmap() hook to call
+ * mmap_prepare() hooks when drivers nest these. This function specifically
+ * allows the construction of a vm_area_desc value, @desc, from a VMA @vma for
+ * the purposes of doing this.
+ *
+ * Once the conversion of drivers is complete this function will no longer be
+ * required and will be removed.
+ */
+void compat_set_desc_from_vma(struct vm_area_desc *desc,
+ const struct file *file,
+ const struct vm_area_struct *vma)
{
- struct vm_area_desc desc = {
- .mm = vma->vm_mm,
- .file = file,
- .start = vma->vm_start,
- .end = vma->vm_end,
+ memset(desc, 0, sizeof(*desc));
- .pgoff = vma->vm_pgoff,
- .vm_file = vma->vm_file,
- .vma_flags = vma->flags,
- .page_prot = vma->vm_page_prot,
-
- .action.type = MMAP_NOTHING, /* Default */
- };
- int err;
+ desc->mm = vma->vm_mm;
+ desc->file = (struct file *)file;
+ desc->start = vma->vm_start;
+ desc->end = vma->vm_end;
- err = vfs_mmap_prepare(file, &desc);
- if (err)
- return err;
+ desc->pgoff = vma->vm_pgoff;
+ desc->vm_file = vma->vm_file;
+ desc->vma_flags = vma->flags;
+ desc->page_prot = vma->vm_page_prot;
- err = mmap_action_prepare(&desc);
- if (err)
- return err;
-
- set_vma_from_desc(vma, &desc);
- return mmap_action_complete(vma, &desc.action, /*rmap_lock_held=*/false);
+ /* Default. */
+ desc->action.type = MMAP_NOTHING;
}
+EXPORT_SYMBOL(compat_set_desc_from_vma);
static int __compat_vma_mapped(struct file *file, struct vm_area_struct *vma)
{
@@ -1211,6 +1217,50 @@ static int __compat_vma_mapped(struct file *file, struct vm_area_struct *vma)
return err;
}
+/**
+ * __compat_vma_mmap() - Similar to compat_vma_mmap(), only it allows
+ * flexibility as to how the mmap_prepare callback is invoked, which is useful
+ * for drivers which invoke nested mmap_prepare callbacks in an mmap() hook.
+ * @desc: A VMA descriptor upon which an mmap_prepare() hook has already been
+ * executed.
+ * @vma: The VMA to which @desc should be applied.
+ *
+ * The function assumes that you have obtained a VMA descriptor @desc from
+ * compat_set_desc_from_vma(), and already executed the mmap_prepare() hook upon
+ * it.
+ *
+ * It then performs any specified mmap actions, and invokes the vm_ops->mapped()
+ * hook if one is present.
+ *
+ * See the description of compat_vma_mmap() for more details.
+ *
+ * Once the conversion of drivers is complete this function will no longer be
+ * required and will be removed.
+ *
+ * Returns: 0 on success or error.
+ */
+int __compat_vma_mmap(struct vm_area_desc *desc,
+ struct vm_area_struct *vma)
+{
+ int err;
+
+ /* Perform any preparatory tasks for mmap action. */
+ err = mmap_action_prepare(desc);
+ if (err)
+ return err;
+ /* Update the VMA from the descriptor. */
+ compat_set_vma_from_desc(vma, desc);
+ /* Complete any specified mmap actions. */
+ err = mmap_action_complete(vma, &desc->action,
+ /*rmap_lock_held=*/false);
+ if (err)
+ return err;
+
+ /* Invoke vm_ops->mapped callback. */
+ return __compat_vma_mapped(desc->file, vma);
+}
+EXPORT_SYMBOL(__compat_vma_mmap);
+
/**
* compat_vma_mmap() - Apply the file's .mmap_prepare() hook to an
* existing VMA and execute any requested actions.
@@ -1218,10 +1268,10 @@ static int __compat_vma_mapped(struct file *file, struct vm_area_struct *vma)
* @vma: The VMA to apply the .mmap_prepare() hook to.
*
* Ordinarily, .mmap_prepare() is invoked directly upon mmap(). However, certain
- * stacked filesystems invoke a nested mmap hook of an underlying file.
+ * stacked drivers invoke a nested mmap hook of an underlying file.
*
- * Until all filesystems are converted to use .mmap_prepare(), we must be
- * conservative and continue to invoke these stacked filesystems using the
+ * Until all drivers are converted to use .mmap_prepare(), we must be
+ * conservative and continue to invoke these stacked drivers using the
* deprecated .mmap() hook.
*
* However we have a problem if the underlying file system possesses an
@@ -1232,20 +1282,22 @@ static int __compat_vma_mapped(struct file *file, struct vm_area_struct *vma)
* establishes a struct vm_area_desc descriptor, passes to the underlying
* .mmap_prepare() hook and applies any changes performed by it.
*
- * Once the conversion of filesystems is complete this function will no longer
- * be required and will be removed.
+ * Once the conversion of drivers is complete this function will no longer be
+ * required and will be removed.
*
* Returns: 0 on success or error.
*/
int compat_vma_mmap(struct file *file, struct vm_area_struct *vma)
{
+ struct vm_area_desc desc;
int err;
- err = __compat_vma_mmap(file, vma);
+ compat_set_desc_from_vma(&desc, file, vma);
+ err = vfs_mmap_prepare(file, &desc);
if (err)
return err;
- return __compat_vma_mapped(file, vma);
+ return __compat_vma_mmap(&desc, vma);
}
EXPORT_SYMBOL(compat_vma_mmap);
diff --git a/mm/vma.h b/mm/vma.h
index adc18f7dd9f1..a76046c39b14 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -300,7 +300,7 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
* f_op->mmap() but which might have an underlying file system which implements
* f_op->mmap_prepare().
*/
-static inline void set_vma_from_desc(struct vm_area_struct *vma,
+static inline void compat_set_vma_from_desc(struct vm_area_struct *vma,
struct vm_area_desc *desc)
{
/*
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 1b86c34e1158..1f123704078e 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -519,8 +519,8 @@ enum vma_operation {
*/
struct vm_area_desc {
/* Immutable state. */
- const struct mm_struct *const mm;
- struct file *const file; /* May vary from vm_file in stacked callers. */
+ struct mm_struct *mm;
+ struct file *file; /* May vary from vm_file in stacked callers. */
unsigned long start;
unsigned long end;
@@ -1272,43 +1272,95 @@ static inline void vma_set_anonymous(struct vm_area_struct *vma)
}
/* Declared in vma.h. */
-static inline void set_vma_from_desc(struct vm_area_struct *vma,
+static inline void compat_set_vma_from_desc(struct vm_area_struct *vma,
struct vm_area_desc *desc);
-static inline int __compat_vma_mmap(const struct file_operations *f_op,
- struct file *file, struct vm_area_struct *vma)
+static inline void compat_set_desc_from_vma(struct vm_area_desc *desc,
+ const struct file *file,
+ const struct vm_area_struct *vma)
{
- struct vm_area_desc desc = {
- .mm = vma->vm_mm,
- .file = file,
- .start = vma->vm_start,
- .end = vma->vm_end,
+ memset(desc, 0, sizeof(*desc));
- .pgoff = vma->vm_pgoff,
- .vm_file = vma->vm_file,
- .vma_flags = vma->flags,
- .page_prot = vma->vm_page_prot,
+ desc->mm = vma->vm_mm;
+ desc->file = (struct file *)file;
+ desc->start = vma->vm_start;
+ desc->end = vma->vm_end;
- .action.type = MMAP_NOTHING, /* Default */
- };
+ desc->pgoff = vma->vm_pgoff;
+ desc->vm_file = vma->vm_file;
+ desc->vma_flags = vma->flags;
+ desc->page_prot = vma->vm_page_prot;
+
+ /* Default. */
+ desc->action.type = MMAP_NOTHING;
+}
+
+static inline unsigned long vma_pages(const struct vm_area_struct *vma)
+{
+ return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+}
+
+static inline void unmap_vma_locked(struct vm_area_struct *vma)
+{
+ const size_t len = vma_pages(vma) << PAGE_SHIFT;
+
+ mmap_assert_write_locked(vma->vm_mm);
+ do_munmap(vma->vm_mm, vma->vm_start, len, NULL);
+}
+
+static inline int __compat_vma_mapped(struct file *file, struct vm_area_struct *vma)
+{
+ const struct vm_operations_struct *vm_ops = vma->vm_ops;
int err;
- err = f_op->mmap_prepare(&desc);
+ if (!vm_ops->mapped)
+ return 0;
+
+ err = vm_ops->mapped(vma->vm_start, vma->vm_end, vma->vm_pgoff, file,
+ &vma->vm_private_data);
if (err)
- return err;
+ unmap_vma_locked(vma);
+ return err;
+}
- err = mmap_action_prepare(&desc);
+static inline int __compat_vma_mmap(struct vm_area_desc *desc,
+ struct vm_area_struct *vma)
+{
+ int err;
+
+ /* Perform any preparatory tasks for mmap action. */
+ err = mmap_action_prepare(desc);
+ if (err)
+ return err;
+ /* Update the VMA from the descriptor. */
+ compat_set_vma_from_desc(vma, desc);
+ /* Complete any specified mmap actions. */
+ err = mmap_action_complete(vma, &desc->action,
+ /*rmap_lock_held=*/false);
if (err)
return err;
- set_vma_from_desc(vma, &desc);
- return mmap_action_complete(vma, &desc.action, /*rmap_lock_held=*/false);
+ /* Invoke vm_ops->mapped callback. */
+ return __compat_vma_mapped(desc->file, vma);
+}
+
+static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc)
+{
+ return file->f_op->mmap_prepare(desc);
}
static inline int compat_vma_mmap(struct file *file,
struct vm_area_struct *vma)
{
- return __compat_vma_mmap(file->f_op, file, vma);
+ struct vm_area_desc desc;
+ int err;
+
+ compat_set_desc_from_vma(&desc, file, vma);
+ err = vfs_mmap_prepare(file, &desc);
+ if (err)
+ return err;
+
+ return __compat_vma_mmap(&desc, vma);
}
@@ -1318,11 +1370,6 @@ static inline void vma_iter_init(struct vma_iterator *vmi,
mas_init(&vmi->mas, &mm->mm_mt, addr);
}
-static inline unsigned long vma_pages(struct vm_area_struct *vma)
-{
- return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
-}
-
static inline void mmap_assert_locked(struct mm_struct *);
static inline struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
unsigned long start_addr,
@@ -1492,11 +1539,6 @@ static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma)
return file->f_op->mmap(file, vma);
}
-static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc)
-{
- return file->f_op->mmap_prepare(desc);
-}
-
static inline void vma_set_file(struct vm_area_struct *vma, struct file *file)
{
/* Changing an anonymous vma with this is illegal */
@@ -1521,11 +1563,3 @@ static inline pgprot_t vma_get_page_prot(vma_flags_t vma_flags)
return vm_get_page_prot(vm_flags);
}
-
-static inline void unmap_vma_locked(struct vm_area_struct *vma)
-{
- const size_t len = vma_pages(vma) << PAGE_SHIFT;
-
- mmap_assert_write_locked(vma->vm_mm);
- do_munmap(vma->vm_mm, vma->vm_start, len, NULL);
-}
--
2.53.0
^ permalink raw reply related
* [PATCH v3 13/16] drivers: hv: vmbus: replace deprecated mmap hook with mmap_prepare
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
The f_op->mmap interface is deprecated, so update the vmbus driver to use
its successor, mmap_prepare.
This updates all callbacks which referenced the function pointer
hv_mmap_ring_buffer to instead reference hv_mmap_prepare_ring_buffer,
utilising the newly introduced compat_set_desc_from_vma() and
__compat_vma_mmap() to be able to implement this change.
The UIO HV generic driver is the only user of hv_create_ring_sysfs(),
which is the only function which references
vmbus_channel->mmap_prepare_ring_buffer which, in turn, is the only
external interface to hv_mmap_prepare_ring_buffer.
This patch therefore updates this caller to use mmap_prepare instead,
which also previously used vm_iomap_memory(), so this change replaces it
with its mmap_prepare equivalent, mmap_action_simple_ioremap().
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
drivers/hv/hyperv_vmbus.h | 4 ++--
drivers/hv/vmbus_drv.c | 31 +++++++++++++++++++------------
drivers/uio/uio_hv_generic.c | 11 ++++++-----
include/linux/hyperv.h | 4 ++--
4 files changed, 29 insertions(+), 21 deletions(-)
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 7bd8f8486e85..31f576464f18 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -545,8 +545,8 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev)
/* Create and remove sysfs entry for memory mapped ring buffers for a channel */
int hv_create_ring_sysfs(struct vmbus_channel *channel,
- int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
- struct vm_area_struct *vma));
+ int (*hv_mmap_prepare_ring_buffer)(struct vmbus_channel *channel,
+ struct vm_area_desc *desc));
int hv_remove_ring_sysfs(struct vmbus_channel *channel);
#endif /* _HYPERV_VMBUS_H */
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index bc4fc1951ae1..45625487ba36 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1951,12 +1951,19 @@ static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj,
struct vm_area_struct *vma)
{
struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj);
+ struct vm_area_desc desc;
+ int err;
/*
- * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer
- * is not NULL.
+ * hv_(create|remove)_ring_sysfs implementation ensures that
+ * mmap_prepare_ring_buffer is not NULL.
*/
- return channel->mmap_ring_buffer(channel, vma);
+ compat_set_desc_from_vma(&desc, filp, vma);
+ err = channel->mmap_prepare_ring_buffer(channel, &desc);
+ if (err)
+ return err;
+
+ return __compat_vma_mmap(&desc, vma);
}
static struct bin_attribute chan_attr_ring_buffer = {
@@ -2048,13 +2055,13 @@ static const struct kobj_type vmbus_chan_ktype = {
/**
* hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel.
* @channel: Pointer to vmbus_channel structure
- * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of
+ * @hv_mmap_prepare_ring_buffer: function pointer for initializing the function to be called on mmap
* channel's "ring" sysfs node, which is for the ring buffer of that channel.
* Function pointer is of below type:
- * int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
- * struct vm_area_struct *vma))
- * This has a pointer to the channel and a pointer to vm_area_struct,
- * used for mmap, as arguments.
+ * int (*hv_mmap_prepare_ring_buffer)(struct vmbus_channel *channel,
+ * struct vm_area_desc *desc))
+ * This has a pointer to the channel and a pointer to vm_area_desc,
+ * used for mmap_prepare, as arguments.
*
* Sysfs node for ring buffer of a channel is created along with other fields, however its
* visibility is disabled by default. Sysfs creation needs to be controlled when the use-case
@@ -2071,12 +2078,12 @@ static const struct kobj_type vmbus_chan_ktype = {
* Returns 0 on success or error code on failure.
*/
int hv_create_ring_sysfs(struct vmbus_channel *channel,
- int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
- struct vm_area_struct *vma))
+ int (*hv_mmap_prepare_ring_buffer)(struct vmbus_channel *channel,
+ struct vm_area_desc *desc))
{
struct kobject *kobj = &channel->kobj;
- channel->mmap_ring_buffer = hv_mmap_ring_buffer;
+ channel->mmap_prepare_ring_buffer = hv_mmap_prepare_ring_buffer;
channel->ring_sysfs_visible = true;
return sysfs_update_group(kobj, &vmbus_chan_group);
@@ -2098,7 +2105,7 @@ int hv_remove_ring_sysfs(struct vmbus_channel *channel)
channel->ring_sysfs_visible = false;
ret = sysfs_update_group(kobj, &vmbus_chan_group);
- channel->mmap_ring_buffer = NULL;
+ channel->mmap_prepare_ring_buffer = NULL;
return ret;
}
EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs);
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 3f8e2e27697f..29ec2d15ada8 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -154,15 +154,16 @@ static void hv_uio_rescind(struct vmbus_channel *channel)
* The ring buffer is allocated as contiguous memory by vmbus_open
*/
static int
-hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma)
+hv_uio_ring_mmap_prepare(struct vmbus_channel *channel, struct vm_area_desc *desc)
{
void *ring_buffer = page_address(channel->ringbuffer_page);
if (channel->state != CHANNEL_OPENED_STATE)
return -ENODEV;
- return vm_iomap_memory(vma, virt_to_phys(ring_buffer),
- channel->ringbuffer_pagecount << PAGE_SHIFT);
+ mmap_action_simple_ioremap(desc, virt_to_phys(ring_buffer),
+ channel->ringbuffer_pagecount << PAGE_SHIFT);
+ return 0;
}
/* Callback from VMBUS subsystem when new channel created. */
@@ -183,7 +184,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc)
}
set_channel_read_mode(new_sc, HV_CALL_ISR);
- ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap);
+ ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap_prepare);
if (ret) {
dev_err(device, "sysfs create ring bin file failed; %d\n", ret);
vmbus_close(new_sc);
@@ -366,7 +367,7 @@ hv_uio_probe(struct hv_device *dev,
* or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify
* APIs to make sure that ring is created.
*/
- hv_create_ring_sysfs(channel, hv_uio_ring_mmap);
+ hv_create_ring_sysfs(channel, hv_uio_ring_mmap_prepare);
hv_set_drvdata(dev, pdata);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index dfc516c1c719..3a721b1853a4 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1015,8 +1015,8 @@ struct vmbus_channel {
/* The max size of a packet on this channel */
u32 max_pkt_size;
- /* function to mmap ring buffer memory to the channel's sysfs ring attribute */
- int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma);
+ /* function to mmap_prepare ring buffer memory to the channel's sysfs ring attribute */
+ int (*mmap_prepare_ring_buffer)(struct vmbus_channel *channel, struct vm_area_desc *desc);
/* boolean to control visibility of sysfs for ring buffer */
bool ring_sysfs_visible;
--
2.53.0
^ permalink raw reply related
* [PATCH v3 14/16] uio: replace deprecated mmap hook with mmap_prepare in uio_info
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
The f_op->mmap interface is deprecated, so update uio_info to use its
successor, mmap_prepare.
Therefore, replace the uio_info->mmap hook with a new
uio_info->mmap_prepare hook, and update its one user, target_core_user,
to both specify this new mmap_prepare hook and also to use the new
vm_ops->mapped() hook to continue to maintain a correct udev->kref
refcount.
Then update uio_mmap() to utilise the mmap_prepare compatibility layer to
invoke this callback from the uio mmap invocation.
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
drivers/target/target_core_user.c | 26 ++++++++++++++++++--------
drivers/uio/uio.c | 10 ++++++++--
include/linux/uio_driver.h | 4 ++--
3 files changed, 28 insertions(+), 12 deletions(-)
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index af95531ddd35..edc2afd5f4ee 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1860,6 +1860,17 @@ static struct page *tcmu_try_get_data_page(struct tcmu_dev *udev, uint32_t dpi)
return NULL;
}
+static int tcmu_vma_mapped(unsigned long start, unsigned long end, pgoff_t pgoff,
+ const struct file *file, void **vm_private_data)
+{
+ struct tcmu_dev *udev = *vm_private_data;
+
+ pr_debug("vma_mapped\n");
+
+ kref_get(&udev->kref);
+ return 0;
+}
+
static void tcmu_vma_open(struct vm_area_struct *vma)
{
struct tcmu_dev *udev = vma->vm_private_data;
@@ -1919,26 +1930,25 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf)
}
static const struct vm_operations_struct tcmu_vm_ops = {
+ .mapped = tcmu_vma_mapped,
.open = tcmu_vma_open,
.close = tcmu_vma_close,
.fault = tcmu_vma_fault,
};
-static int tcmu_mmap(struct uio_info *info, struct vm_area_struct *vma)
+static int tcmu_mmap_prepare(struct uio_info *info, struct vm_area_desc *desc)
{
struct tcmu_dev *udev = container_of(info, struct tcmu_dev, uio_info);
- vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP);
- vma->vm_ops = &tcmu_vm_ops;
+ vma_desc_set_flags(desc, VMA_DONTEXPAND_BIT, VMA_DONTDUMP_BIT);
+ desc->vm_ops = &tcmu_vm_ops;
- vma->vm_private_data = udev;
+ desc->private_data = udev;
/* Ensure the mmap is exactly the right size */
- if (vma_pages(vma) != udev->mmap_pages)
+ if (vma_desc_pages(desc) != udev->mmap_pages)
return -EINVAL;
- tcmu_vma_open(vma);
-
return 0;
}
@@ -2253,7 +2263,7 @@ static int tcmu_configure_device(struct se_device *dev)
info->irqcontrol = tcmu_irqcontrol;
info->irq = UIO_IRQ_CUSTOM;
- info->mmap = tcmu_mmap;
+ info->mmap_prepare = tcmu_mmap_prepare;
info->open = tcmu_open;
info->release = tcmu_release;
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 5a4998e2caf8..1e4ade78ed84 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -850,8 +850,14 @@ static int uio_mmap(struct file *filep, struct vm_area_struct *vma)
goto out;
}
- if (idev->info->mmap) {
- ret = idev->info->mmap(idev->info, vma);
+ if (idev->info->mmap_prepare) {
+ struct vm_area_desc desc;
+
+ compat_set_desc_from_vma(&desc, filep, vma);
+ ret = idev->info->mmap_prepare(idev->info, &desc);
+ if (ret)
+ goto out;
+ ret = __compat_vma_mmap(&desc, vma);
goto out;
}
diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h
index 334641e20fb1..02eaac47ac44 100644
--- a/include/linux/uio_driver.h
+++ b/include/linux/uio_driver.h
@@ -97,7 +97,7 @@ struct uio_device {
* @irq_flags: flags for request_irq()
* @priv: optional private data
* @handler: the device's irq handler
- * @mmap: mmap operation for this uio device
+ * @mmap_prepare: mmap_prepare operation for this uio device
* @open: open operation for this uio device
* @release: release operation for this uio device
* @irqcontrol: disable/enable irqs when 0/1 is written to /dev/uioX
@@ -112,7 +112,7 @@ struct uio_info {
unsigned long irq_flags;
void *priv;
irqreturn_t (*handler)(int irq, struct uio_info *dev_info);
- int (*mmap)(struct uio_info *info, struct vm_area_struct *vma);
+ int (*mmap_prepare)(struct uio_info *info, struct vm_area_desc *desc);
int (*open)(struct uio_info *info, struct inode *inode);
int (*release)(struct uio_info *info, struct inode *inode);
int (*irqcontrol)(struct uio_info *info, s32 irq_on);
--
2.53.0
^ permalink raw reply related
* [PATCH v3 15/16] mm: add mmap_action_map_kernel_pages[_full]()
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
A user can invoke mmap_action_map_kernel_pages() to specify that the
mapping should map kernel pages starting from desc->start of a specified
number of pages specified in an array.
In order to implement this, adjust mmap_action_prepare() to be able to
return an error code, as it makes sense to assert that the specified
parameters are valid as quickly as possible as well as updating the VMA
flags to include VMA_MIXEDMAP_BIT as necessary.
This provides an mmap_prepare equivalent of vm_insert_pages(). We
additionally update the existing vm_insert_pages() code to use
range_in_vma() and add a new range_in_vma_desc() helper function for the
mmap_prepare case, sharing the code between the two in range_is_subset().
We add both mmap_action_map_kernel_pages() and
mmap_action_map_kernel_pages_full() to allow for both partial and full VMA
mappings.
We update the documentation to reflect the new features.
Finally, we update the VMA tests accordingly to reflect the changes.
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
Documentation/filesystems/mmap_prepare.rst | 8 ++
include/linux/mm.h | 95 +++++++++++++++++++++-
include/linux/mm_types.h | 7 ++
mm/memory.c | 42 +++++++++-
mm/util.c | 6 ++
tools/testing/vma/include/dup.h | 7 ++
6 files changed, 159 insertions(+), 6 deletions(-)
diff --git a/Documentation/filesystems/mmap_prepare.rst b/Documentation/filesystems/mmap_prepare.rst
index be76ae475b9c..e810aa4134eb 100644
--- a/Documentation/filesystems/mmap_prepare.rst
+++ b/Documentation/filesystems/mmap_prepare.rst
@@ -156,5 +156,13 @@ pointer. These are:
* mmap_action_simple_ioremap() - Sets up an I/O remap from a specified
physical address and over a specified length.
+* mmap_action_map_kernel_pages() - Maps a specified array of `struct page`
+ pointers in the VMA from a specific offset.
+
+* mmap_action_map_kernel_pages_full() - Maps a specified array of `struct
+ page` pointers over the entire VMA. The caller must ensure there are
+ sufficient entries in the page array to cover the entire range of the
+ described VMA.
+
**NOTE:** The ``action`` field should never normally be manipulated directly,
rather you ought to use one of these helpers.
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ef2e4dccfe8e..8aadf115278e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2912,7 +2912,7 @@ static inline bool folio_maybe_mapped_shared(struct folio *folio)
* The caller must add any reference (e.g., from folio_try_get()) it might be
* holding itself to the result.
*
- * Returns the expected folio refcount.
+ * Returns: the expected folio refcount.
*/
static inline int folio_expected_ref_count(const struct folio *folio)
{
@@ -4364,6 +4364,45 @@ static inline void mmap_action_simple_ioremap(struct vm_area_desc *desc,
action->type = MMAP_SIMPLE_IO_REMAP;
}
+/**
+ * mmap_action_map_kernel_pages - helper for mmap_prepare hook to specify that
+ * @num kernel pages contained in the @pages array should be mapped to userland
+ * starting at virtual address @start.
+ * @desc: The VMA descriptor for the VMA requiring kernel pags to be mapped.
+ * @start: The virtual address from which to map them.
+ * @pages: An array of struct page pointers describing the memory to map.
+ * @nr_pages: The number of entries in the @pages aray.
+ */
+static inline void mmap_action_map_kernel_pages(struct vm_area_desc *desc,
+ unsigned long start, struct page **pages,
+ unsigned long nr_pages)
+{
+ struct mmap_action *action = &desc->action;
+
+ action->type = MMAP_MAP_KERNEL_PAGES;
+ action->map_kernel.start = start;
+ action->map_kernel.pages = pages;
+ action->map_kernel.nr_pages = nr_pages;
+ action->map_kernel.pgoff = desc->pgoff;
+}
+
+/**
+ * mmap_action_map_kernel_pages_full - helper for mmap_prepare hook to specify that
+ * kernel pages contained in the @pages array should be mapped to userland
+ * from @desc->start to @desc->end.
+ * @desc: The VMA descriptor for the VMA requiring kernel pags to be mapped.
+ * @pages: An array of struct page pointers describing the memory to map.
+ *
+ * The caller must ensure that @pages contains sufficient entries to cover the
+ * entire range described by @desc.
+ */
+static inline void mmap_action_map_kernel_pages_full(struct vm_area_desc *desc,
+ struct page **pages)
+{
+ mmap_action_map_kernel_pages(desc, desc->start, pages,
+ vma_desc_pages(desc));
+}
+
int mmap_action_prepare(struct vm_area_desc *desc);
int mmap_action_complete(struct vm_area_struct *vma,
struct mmap_action *action,
@@ -4381,10 +4420,59 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
return vma;
}
+/**
+ * range_is_subset - Is the specified inner range a subset of the outer range?
+ * @outer_start: The start of the outer range.
+ * @outer_end: The exclusive end of the outer range.
+ * @inner_start: The start of the inner range.
+ * @inner_end: The exclusive end of the inner range.
+ *
+ * Returns: %true if [inner_start, inner_end) is a subset of [outer_start,
+ * outer_end), otherwise %false.
+ */
+static inline bool range_is_subset(unsigned long outer_start,
+ unsigned long outer_end,
+ unsigned long inner_start,
+ unsigned long inner_end)
+{
+ return outer_start <= inner_start && inner_end <= outer_end;
+}
+
+/**
+ * range_in_vma - is the specified [@start, @end) range a subset of the VMA?
+ * @vma: The VMA against which we want to check [@start, @end).
+ * @start: The start of the range we wish to check.
+ * @end: The exclusive end of the range we wish to check.
+ *
+ * Returns: %true if [@start, @end) is a subset of [@vma->vm_start,
+ * @vma->vm_end), %false otherwise.
+ */
static inline bool range_in_vma(const struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- return (vma && vma->vm_start <= start && end <= vma->vm_end);
+ if (!vma)
+ return false;
+
+ return range_is_subset(vma->vm_start, vma->vm_end, start, end);
+}
+
+/**
+ * range_in_vma_desc - is the specified [@start, @end) range a subset of the VMA
+ * described by @desc, a VMA descriptor?
+ * @desc: The VMA descriptor against which we want to check [@start, @end).
+ * @start: The start of the range we wish to check.
+ * @end: The exclusive end of the range we wish to check.
+ *
+ * Returns: %true if [@start, @end) is a subset of [@desc->start, @desc->end),
+ * %false otherwise.
+ */
+static inline bool range_in_vma_desc(const struct vm_area_desc *desc,
+ unsigned long start, unsigned long end)
+{
+ if (!desc)
+ return false;
+
+ return range_is_subset(desc->start, desc->end, start, end);
}
#ifdef CONFIG_MMU
@@ -4428,6 +4516,9 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
struct page **pages, unsigned long *num);
+int map_kernel_pages_prepare(struct vm_area_desc *desc);
+int map_kernel_pages_complete(struct vm_area_struct *vma,
+ struct mmap_action *action);
int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
unsigned long num);
int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7538d64f8848..c46224020a46 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -815,6 +815,7 @@ enum mmap_action_type {
MMAP_REMAP_PFN, /* Remap PFN range. */
MMAP_IO_REMAP_PFN, /* I/O remap PFN range. */
MMAP_SIMPLE_IO_REMAP, /* I/O remap with guardrails. */
+ MMAP_MAP_KERNEL_PAGES, /* Map kernel page range from array. */
};
/*
@@ -833,6 +834,12 @@ struct mmap_action {
phys_addr_t start_phys_addr;
unsigned long size;
} simple_ioremap;
+ struct {
+ unsigned long start;
+ struct page **pages;
+ unsigned long nr_pages;
+ pgoff_t pgoff;
+ } map_kernel;
};
enum mmap_action_type type;
diff --git a/mm/memory.c b/mm/memory.c
index b3bcc21af20a..53ef8ef3d04a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2484,13 +2484,14 @@ static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
struct page **pages, unsigned long *num)
{
- const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1;
+ const unsigned long nr_pages = *num;
+ const unsigned long end = addr + PAGE_SIZE * nr_pages;
- if (addr < vma->vm_start || end_addr >= vma->vm_end)
+ if (!range_in_vma(vma, addr, end))
return -EFAULT;
if (!(vma->vm_flags & VM_MIXEDMAP)) {
- BUG_ON(mmap_read_trylock(vma->vm_mm));
- BUG_ON(vma->vm_flags & VM_PFNMAP);
+ VM_WARN_ON_ONCE(mmap_read_trylock(vma->vm_mm));
+ VM_WARN_ON_ONCE(vma->vm_flags & VM_PFNMAP);
vm_flags_set(vma, VM_MIXEDMAP);
}
/* Defer page refcount checking till we're about to map that page. */
@@ -2498,6 +2499,39 @@ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
}
EXPORT_SYMBOL(vm_insert_pages);
+int map_kernel_pages_prepare(struct vm_area_desc *desc)
+{
+ const struct mmap_action *action = &desc->action;
+ const unsigned long addr = action->map_kernel.start;
+ unsigned long nr_pages, end;
+
+ if (!vma_desc_test(desc, VMA_MIXEDMAP_BIT)) {
+ VM_WARN_ON_ONCE(mmap_read_trylock(desc->mm));
+ VM_WARN_ON_ONCE(vma_desc_test(desc, VMA_PFNMAP_BIT));
+ vma_desc_set_flags(desc, VMA_MIXEDMAP_BIT);
+ }
+
+ nr_pages = action->map_kernel.nr_pages;
+ end = addr + PAGE_SIZE * nr_pages;
+ if (!range_in_vma_desc(desc, addr, end))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL(map_kernel_pages_prepare);
+
+int map_kernel_pages_complete(struct vm_area_struct *vma,
+ struct mmap_action *action)
+{
+ unsigned long nr_pages;
+
+ nr_pages = action->map_kernel.nr_pages;
+ return insert_pages(vma, action->map_kernel.start,
+ action->map_kernel.pages,
+ &nr_pages, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(map_kernel_pages_complete);
+
/**
* vm_insert_page - insert single page into user vma
* @vma: user vma to map to
diff --git a/mm/util.c b/mm/util.c
index 8cf59267a9ac..682d0d24e1c6 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1446,6 +1446,8 @@ int mmap_action_prepare(struct vm_area_desc *desc)
return io_remap_pfn_range_prepare(desc);
case MMAP_SIMPLE_IO_REMAP:
return simple_ioremap_prepare(desc);
+ case MMAP_MAP_KERNEL_PAGES:
+ return map_kernel_pages_prepare(desc);
}
WARN_ON_ONCE(1);
@@ -1476,6 +1478,9 @@ int mmap_action_complete(struct vm_area_struct *vma,
case MMAP_REMAP_PFN:
err = remap_pfn_range_complete(vma, action);
break;
+ case MMAP_MAP_KERNEL_PAGES:
+ err = map_kernel_pages_complete(vma, action);
+ break;
case MMAP_IO_REMAP_PFN:
case MMAP_SIMPLE_IO_REMAP:
/* Should have been delegated. */
@@ -1497,6 +1502,7 @@ int mmap_action_prepare(struct vm_area_desc *desc)
case MMAP_REMAP_PFN:
case MMAP_IO_REMAP_PFN:
case MMAP_SIMPLE_IO_REMAP:
+ case MMAP_MAP_KERNEL_PAGES:
WARN_ON_ONCE(1); /* nommu cannot handle these. */
break;
}
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 1f123704078e..6392e7835f89 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -454,6 +454,7 @@ enum mmap_action_type {
MMAP_REMAP_PFN, /* Remap PFN range. */
MMAP_IO_REMAP_PFN, /* I/O remap PFN range. */
MMAP_SIMPLE_IO_REMAP, /* I/O remap with guardrails. */
+ MMAP_MAP_KERNEL_PAGES, /* Map kernel page range from an array. */
};
/*
@@ -472,6 +473,12 @@ struct mmap_action {
phys_addr_t start_phys_addr;
unsigned long size;
} simple_ioremap;
+ struct {
+ unsigned long start;
+ struct page **pages;
+ unsigned long nr_pages;
+ pgoff_t pgoff;
+ } map_kernel;
};
enum mmap_action_type type;
--
2.53.0
^ permalink raw reply related
* [PATCH v3 16/16] mm: on remap assert that input range within the proposed VMA
From: Lorenzo Stoakes (Oracle) @ 2026-03-19 18:23 UTC (permalink / raw)
To: Andrew Morton
Cc: Jonathan Corbet, Clemens Ladisch, Arnd Bergmann,
Greg Kroah-Hartman, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Alexander Shishkin, Maxime Coquelin,
Alexandre Torgue, Miquel Raynal, Richard Weinberger,
Vignesh Raghavendra, Bodo Stroesser, Martin K . Petersen,
David Howells, Marc Dionne, Alexander Viro, Christian Brauner,
Jan Kara, David Hildenbrand, Liam R . Howlett, Vlastimil Babka,
Mike Rapoport, Suren Baghdasaryan, Michal Hocko, Jann Horn,
Pedro Falcato, linux-kernel, linux-doc, linux-hyperv, linux-stm32,
linux-arm-kernel, linux-mtd, linux-staging, linux-scsi,
target-devel, linux-afs, linux-fsdevel, linux-mm, Ryan Roberts
In-Reply-To: <cover.1773944114.git.ljs@kernel.org>
Now we have range_in_vma_desc(), update remap_pfn_range_prepare() to check
whether the input range in contained within the specified VMA, so we can
fail at prepare time if an invalid range is specified.
This covers the I/O remap mmap actions also which ultimately call into
this function, and other mmap action types either already span the full
VMA or check this already.
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
---
mm/memory.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/mm/memory.c b/mm/memory.c
index 53ef8ef3d04a..68cc592ff0ba 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3142,6 +3142,9 @@ int remap_pfn_range_prepare(struct vm_area_desc *desc)
const bool is_cow = vma_desc_is_cow_mapping(desc);
int err;
+ if (!range_in_vma_desc(desc, start, end))
+ return -EFAULT;
+
err = get_remap_pgoff(is_cow, start, end, desc->start, desc->end, pfn,
&desc->pgoff);
if (err)
--
2.53.0
^ permalink raw reply related
* [PATCH v4 00/55] drivers: hv: dxgkrnl: Driver for Hyper-V virtual compute device
From: Eric Curtin @ 2026-03-19 20:24 UTC (permalink / raw)
To: linux-hyperv; +Cc: linux-kernel, iourit, wei.liu, decui, haiyangz
This patch series introduces the dxgkrnl driver, which provides Linux
support for virtual compute devices (vGPUs) paravirtualized by a Windows
Hyper-V host. The primary use case is Windows Subsystem for Linux (WSL2),
where the driver enables GPU-accelerated workloads inside Linux containers
running on Windows.
The driver creates /dev/dxg, a miscdevice that user-space API libraries
(such as the open-source libdxg) use to communicate with virtual GPU
adapters via IOCTLs implementing a subset of the WDDM/MCDM D3DKMT
interface. Physical GPU access is performed entirely on the Windows host;
the guest driver communicates over Hyper-V VMBus channels.
Key characteristics:
- Self-contained under drivers/hv/dxgkrnl/
- Depends only on CONFIG_HYPERV, DMA_SHARED_BUFFER, SYNC_FILE
- Supports multiple vGPU adapters per VM
- DMA fence integration via dxgsyncfile (SYNC_FILE)
- Supports compute-only accelerators (AI/ML workloads) as well as
full graphics adapters
Changes since v3 (posted March 2022):
- Replace deprecated one-element arrays [1] with C99 flexible arrays []
- Replace %px with %p in trace macros
- Remove unnecessary braces from single-statement if blocks
- Remove LINUX_VERSION_CODE guard for max_pkt_size (added in 5.15,
well before any target kernel for this submission)
- Remove linux/version.h include (no longer needed)
- Fix whitespace issues flagged by checkpatch
- Replace non-debug DXG_ERR do{}while(0) macro with direct dev_err call
- Change -EBADE to -ENODEV for global channel duplicate detection
(as requested by Greg KH in v3 review)
- Remove MODULE_VERSION (not recommended for in-tree drivers)
- Add explanatory comment to guid_to_luid() cast
- Additional features and fixes developed in the WSL2 fork:
* dxgsyncfile: DMA fence / sync file integration
* D3DKMTEnumProcesses, D3DDKMTIsFeatureEnabled, D3DKMTInvalidateCache
* Compute-only adapter support
* pin_user_pages for DMA-accessible memory
* Retry logic for VMBus ring buffer full condition
* Various synchronization and memory safety fixes
Regarding the dxgglobal singleton raised in v3 review:
The design reflects a host architecture constraint: each Hyper-V VM has
exactly one global VMBus channel offered by the host, regardless of how
many vGPU adapters are present. The dxgglobal structure encapsulates this
VM-level state (global channel, adapter list, process list, host event
tracking). Per-adapter state is separately managed in dxgadapter objects.
This design was previously explained in the v3 thread; the architecture
matches the Hyper-V GPU-PV protocol which is fixed by the host side.
The patches apply on top of v6.6-lts. The user-space library (libdxg)
that communicates with this driver is available at:
https://github.com/microsoft/libdxg
The full WDDM compute stack (OpenCL, oneAPI, OpenVINO) is available
open-source via Intel's compute-runtime project.
Iouri Tarassov (iourit@linux.microsoft.com) is the primary author and
maintainer of this driver.
Eric Curtin (1):
drivers: hv: dxgkrnl: Fix checkpatch issues and address reviewer
feedback
Hideyuki Nagase (1):
drivers: hv: dxgkrnl: Fix crash at hmgrtable_free_handle
Iouri Tarassov (53):
drivers: hv: dxgkrnl: Driver initialization and loading
drivers: hv: dxgkrnl: Add VMBus message support, initialize VMBus
channels.
drivers: hv: dxgkrnl: Creation of dxgadapter object
drivers: hv: dxgkrnl: Opening of /dev/dxg device and dxgprocess
creation
drivers: hv: dxgkrnl: Enumerate and open dxgadapter objects
drivers: hv: dxgkrnl: Creation of dxgdevice objects
drivers: hv: dxgkrnl: Creation of dxgcontext objects
drivers: hv: dxgkrnl: Creation of compute device allocations and
resources
drivers: hv: dxgkrnl: Creation of compute device sync objects
drivers: hv: dxgkrnl: Operations using sync objects
drivers: hv: dxgkrnl: Sharing of dxgresource objects
drivers: hv: dxgkrnl: Sharing of sync objects
drivers: hv: dxgkrnl: Creation of paging queue objects.
drivers: hv: dxgkrnl: Submit execution commands to the compute device
drivers: hv: dxgkrnl: Share objects with the host
drivers: hv: dxgkrnl: Query the dxgdevice state
drivers: hv: dxgkrnl: Map(unmap) CPU address to device allocation
drivers: hv: dxgkrnl: Manage device allocation properties
drivers: hv: dxgkrnl: Flush heap transitions
drivers: hv: dxgkrnl: Query video memory information
drivers: hv: dxgkrnl: The escape ioctl
drivers: hv: dxgkrnl: Ioctl to put device to error state
drivers: hv: dxgkrnl: Ioctls to query statistics and clock calibration
drivers: hv: dxgkrnl: Offer and reclaim allocations
drivers: hv: dxgkrnl: Ioctls to manage scheduling priority
drivers: hv: dxgkrnl: Manage residency of allocations
drivers: hv: dxgkrnl: Manage compute device virtual addresses
drivers: hv: dxgkrnl: Add support to map guest pages by host
drivers: hv: dxgkrnl: Removed struct vmbus_gpadl, which was defined in
the main linux branch
drivers: hv: dxgkrnl: Remove dxgk_init_ioctls
drivers: hv: dxgkrnl: Creation of dxgsyncfile objects
drivers: hv: dxgkrnl: Use tracing instead of dev_dbg
drivers: hv: dxgkrnl: Implement D3DKMTWaitSyncFile
drivers: hv: dxgkrnl: Improve tracing and return values from copy from
user
drivers: hv: dxgkrnl: Fix synchronization locks
drivers: hv: dxgkrnl: Close shared file objects in case of a failure
drivers: hv: dxgkrnl: Added missed NULL check for resource object
drivers: hv: dxgkrnl: Fixed dxgkrnl to build for the 6.1 kernel
drivers: hv: dxgkrnl: Added support for compute only adapters
drivers: hv: dxgkrnl: Added implementation for D3DKMTInvalidateCache
drivers: hv: dxgkrnl: Handle process ID in D3DKMTQueryStatistics
drivers: hv: dxgkrnl: Implement the D3DKMTEnumProcesses API
drivers: hv: dxgkrnl: Implement D3DDKMTIsFeatureEnabled API
drivers: hv: dxgkrnl: Implement known escapes
drivers: hv: dxgkrnl: Fixed coding style issues
drivers: hv: dxgkrnl: Fixed the implementation of
D3DKMTQueryClockCalibration
drivers: hv: dxgkrnl: Retry sending a VM bus packet when there is no
place in the ring buffer
drivers: hv: dxgkrnl: Add support for locking a shared allocation by
not the owner
drivers: hv: dxgkrnl: Fix build breaks when switching to 6.6 kernel
due to hv_driver remove callback change.
drivers: hv: dxgkrnl: Fix build breaks when switching to 6.6 kernel
due to removed uuid_le_cmp
drivers: hv: dxgkrnl: Implement D3DKMTEnumProcesses to match the
Windows implementation
drivers: hv: dxgkrnl: Use pin_user_pages instead of get_user_pages for
DMA accessible memory
drivers: hv: dxgkrnl: Do not print error messages when virtual GPU is
not present
MAINTAINERS | 7 +
drivers/hv/Kconfig | 2 +
drivers/hv/Makefile | 1 +
drivers/hv/dxgkrnl/Kconfig | 28 +
drivers/hv/dxgkrnl/Makefile | 5 +
drivers/hv/dxgkrnl/dxgadapter.c | 1367 ++++++++
drivers/hv/dxgkrnl/dxgkrnl.h | 1042 ++++++
drivers/hv/dxgkrnl/dxgmodule.c | 971 +++++
drivers/hv/dxgkrnl/dxgprocess.c | 348 ++
drivers/hv/dxgkrnl/dxgsyncfile.c | 481 +++
drivers/hv/dxgkrnl/dxgsyncfile.h | 33 +
drivers/hv/dxgkrnl/dxgvmbus.c | 3992 +++++++++++++++++++++
drivers/hv/dxgkrnl/dxgvmbus.h | 910 +++++
drivers/hv/dxgkrnl/hmgr.c | 567 +++
drivers/hv/dxgkrnl/hmgr.h | 112 +
drivers/hv/dxgkrnl/ioctl.c | 5648 ++++++++++++++++++++++++++++++
drivers/hv/dxgkrnl/misc.c | 38 +
drivers/hv/dxgkrnl/misc.h | 96 +
include/uapi/misc/d3dkmthk.h | 1794 ++++++++++
19 files changed, 17442 insertions(+)
create mode 100644 drivers/hv/dxgkrnl/Kconfig
create mode 100644 drivers/hv/dxgkrnl/Makefile
create mode 100644 drivers/hv/dxgkrnl/dxgadapter.c
create mode 100644 drivers/hv/dxgkrnl/dxgkrnl.h
create mode 100644 drivers/hv/dxgkrnl/dxgmodule.c
create mode 100644 drivers/hv/dxgkrnl/dxgprocess.c
create mode 100644 drivers/hv/dxgkrnl/dxgsyncfile.c
create mode 100644 drivers/hv/dxgkrnl/dxgsyncfile.h
create mode 100644 drivers/hv/dxgkrnl/dxgvmbus.c
create mode 100644 drivers/hv/dxgkrnl/dxgvmbus.h
create mode 100644 drivers/hv/dxgkrnl/hmgr.c
create mode 100644 drivers/hv/dxgkrnl/hmgr.h
create mode 100644 drivers/hv/dxgkrnl/ioctl.c
create mode 100644 drivers/hv/dxgkrnl/misc.c
create mode 100644 drivers/hv/dxgkrnl/misc.h
create mode 100644 include/uapi/misc/d3dkmthk.h
^ permalink raw reply
* [PATCH 01/55] drivers: hv: dxgkrnl: Driver initialization and loading
From: Eric Curtin @ 2026-03-19 20:24 UTC (permalink / raw)
To: linux-hyperv; +Cc: linux-kernel, iourit, wei.liu, decui, haiyangz
In-Reply-To: <20260319202509.63802-1-eric.curtin@docker.com>
From: Iouri Tarassov <iourit@linux.microsoft.com>
- Create skeleton and add basic functionality for the Hyper-V
compute device driver (dxgkrnl).
- Register for PCI and VMBus driver notifications and handle
initialization of VMBus channels.
- Connect the dxgkrnl module to the drivers/hv/ Makefile and Kconfig
- Create a MAINTAINERS entry
A VMBus channel is a communication interface between the Hyper-V guest
and the host. The are two type of VMBus channels, used in the driver:
- the global channel
- per virtual compute device channel
A PCI device is created for each virtual compute device, projected
by the host. The device vendor is PCI_VENDOR_ID_MICROSOFT and device
id is PCI_DEVICE_ID_VIRTUAL_RENDER. dxg_pci_probe_device handles
arrival of such devices. The PCI config space of the virtual compute
device has luid of the corresponding virtual compute device VM
bus channel. This is how the compute device adapter objects are
linked to VMBus channels.
VMBus interface version is exchanged by reading/writing the PCI config
space of the virtual compute device.
The IO space is used to handle CPU accessible compute device
allocations. Hyper-V allocates IO space for the global VMBus channel.
Signed-off-by: Iouri Tarassov <iourit@linux.microsoft.com>
[kms: forward port to 6.6 from 6.1. No code changes made.]
Signed-off-by: Kelsey Steele <kelseysteele@microsoft.com>
---
MAINTAINERS | 7 +
drivers/hv/Kconfig | 2 +
drivers/hv/Makefile | 1 +
drivers/hv/dxgkrnl/Kconfig | 26 ++
drivers/hv/dxgkrnl/Makefile | 5 +
drivers/hv/dxgkrnl/dxgkrnl.h | 155 ++++++++++
drivers/hv/dxgkrnl/dxgmodule.c | 506 +++++++++++++++++++++++++++++++++
drivers/hv/dxgkrnl/dxgvmbus.c | 92 ++++++
drivers/hv/dxgkrnl/dxgvmbus.h | 19 ++
include/uapi/misc/d3dkmthk.h | 27 ++
10 files changed, 840 insertions(+)
create mode 100644 drivers/hv/dxgkrnl/Kconfig
create mode 100644 drivers/hv/dxgkrnl/Makefile
create mode 100644 drivers/hv/dxgkrnl/dxgkrnl.h
create mode 100644 drivers/hv/dxgkrnl/dxgmodule.c
create mode 100644 drivers/hv/dxgkrnl/dxgvmbus.c
create mode 100644 drivers/hv/dxgkrnl/dxgvmbus.h
create mode 100644 include/uapi/misc/d3dkmthk.h
diff --git a/MAINTAINERS b/MAINTAINERS
index ae4c0cec5073..4fe0b3501931 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9771,6 +9771,13 @@ F: Documentation/devicetree/bindings/mtd/ti,am654-hbmc.yaml
F: drivers/mtd/hyperbus/
F: include/linux/mtd/hyperbus.h
+Hyper-V vGPU DRIVER
+M: Iouri Tarassov <iourit@microsoft.com>
+L: linux-hyperv@vger.kernel.org
+S: Supported
+F: drivers/hv/dxgkrnl/
+F: include/uapi/misc/d3dkmthk.h
+
HYPERVISOR VIRTUAL CONSOLE DRIVER
L: linuxppc-dev@lists.ozlabs.org
S: Odd Fixes
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 862c47b191af..b16c7701da19 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -55,4 +55,6 @@ config HYPERV_BALLOON
help
Select this option to enable Hyper-V Balloon driver.
+source "drivers/hv/dxgkrnl/Kconfig"
+
endmenu
diff --git a/drivers/hv/Makefile b/drivers/hv/Makefile
index d76df5c8c2a9..aa1cbdb5d0d2 100644
--- a/drivers/hv/Makefile
+++ b/drivers/hv/Makefile
@@ -2,6 +2,7 @@
obj-$(CONFIG_HYPERV) += hv_vmbus.o
obj-$(CONFIG_HYPERV_UTILS) += hv_utils.o
obj-$(CONFIG_HYPERV_BALLOON) += hv_balloon.o
+obj-$(CONFIG_DXGKRNL) += dxgkrnl/
CFLAGS_hv_trace.o = -I$(src)
CFLAGS_hv_balloon.o = -I$(src)
diff --git a/drivers/hv/dxgkrnl/Kconfig b/drivers/hv/dxgkrnl/Kconfig
new file mode 100644
index 000000000000..bcd92bbff939
--- /dev/null
+++ b/drivers/hv/dxgkrnl/Kconfig
@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0
+# Configuration for the hyper-v virtual compute driver (dxgkrnl)
+#
+
+config DXGKRNL
+ tristate "Microsoft Paravirtualized GPU support"
+ depends on HYPERV
+ depends on 64BIT || COMPILE_TEST
+ help
+ This driver supports paravirtualized virtual compute devices, exposed
+ by Microsoft Hyper-V when Linux is running inside of a virtual machine
+ hosted by Windows. The virtual machines needs to be configured to use
+ host compute adapters. The driver name is dxgkrnl.
+
+ An example of such virtual machine is a Windows Subsystem for
+ Linux container. When such container is instantiated, the Windows host
+ assigns compatible host GPU adapters to the container. The corresponding
+ virtual GPU devices appear on the PCI bus in the container. These
+ devices are enumerated and accessed by this driver.
+
+ Communications with the driver are done by using the Microsoft libdxcore
+ library, which translates the D3DKMT interface
+ <https://docs.microsoft.com/en-us/windows-hardware/drivers/ddi/d3dkmthk/>
+ to the driver IOCTLs. The virtual GPU devices are paravirtualized,
+ which means that access to the hardware is done in the host. The driver
+ communicates with the host using Hyper-V VM bus communication channels.
diff --git a/drivers/hv/dxgkrnl/Makefile b/drivers/hv/dxgkrnl/Makefile
new file mode 100644
index 000000000000..76349064b60a
--- /dev/null
+++ b/drivers/hv/dxgkrnl/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for the hyper-v compute device driver (dxgkrnl).
+
+obj-$(CONFIG_DXGKRNL) += dxgkrnl.o
+dxgkrnl-y := dxgmodule.o dxgvmbus.o
diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h
new file mode 100644
index 000000000000..f7900840d1ed
--- /dev/null
+++ b/drivers/hv/dxgkrnl/dxgkrnl.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2022, Microsoft Corporation.
+ *
+ * Author:
+ * Iouri Tarassov <iourit@linux.microsoft.com>
+ *
+ * Dxgkrnl Graphics Driver
+ * Headers for internal objects
+ *
+ */
+
+#ifndef _DXGKRNL_H
+#define _DXGKRNL_H
+
+#include <linux/uuid.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/semaphore.h>
+#include <linux/refcount.h>
+#include <linux/rwsem.h>
+#include <linux/atomic.h>
+#include <linux/spinlock.h>
+#include <linux/gfp.h>
+#include <linux/miscdevice.h>
+#include <linux/pci.h>
+#include <linux/hyperv.h>
+#include <uapi/misc/d3dkmthk.h>
+#include <linux/version.h>
+
+struct dxgadapter;
+
+/*
+ * Driver private data.
+ * A single /dev/dxg device is created per virtual machine.
+ */
+struct dxgdriver{
+ struct dxgglobal *dxgglobal;
+ struct device *dxgdev;
+ struct pci_driver pci_drv;
+ struct hv_driver vmbus_drv;
+};
+extern struct dxgdriver dxgdrv;
+
+#define DXGDEV dxgdrv.dxgdev
+
+struct dxgvmbuschannel {
+ struct vmbus_channel *channel;
+ struct hv_device *hdev;
+ spinlock_t packet_list_mutex;
+ struct list_head packet_list_head;
+ struct kmem_cache *packet_cache;
+ atomic64_t packet_request_id;
+};
+
+int dxgvmbuschannel_init(struct dxgvmbuschannel *ch, struct hv_device *hdev);
+void dxgvmbuschannel_destroy(struct dxgvmbuschannel *ch);
+void dxgvmbuschannel_receive(void *ctx);
+
+/*
+ * The structure defines an offered vGPU vm bus channel.
+ */
+struct dxgvgpuchannel {
+ struct list_head vgpu_ch_list_entry;
+ struct winluid adapter_luid;
+ struct hv_device *hdev;
+};
+
+struct dxgglobal {
+ struct dxgdriver *drvdata;
+ struct dxgvmbuschannel channel;
+ struct hv_device *hdev;
+ u32 num_adapters;
+ u32 vmbus_ver; /* Interface version */
+ struct resource *mem;
+ u64 mmiospace_base;
+ u64 mmiospace_size;
+ struct miscdevice dxgdevice;
+ struct mutex device_mutex;
+
+ /*
+ * List of the vGPU VM bus channels (dxgvgpuchannel)
+ * Protected by device_mutex
+ */
+ struct list_head vgpu_ch_list_head;
+
+ /* protects acces to the global VM bus channel */
+ struct rw_semaphore channel_lock;
+
+ bool global_channel_initialized;
+ bool async_msg_enabled;
+ bool misc_registered;
+ bool pci_registered;
+ bool vmbus_registered;
+};
+
+static inline struct dxgglobal *dxggbl(void)
+{
+ return dxgdrv.dxgglobal;
+}
+
+struct dxgprocess {
+ /* Placeholder */
+};
+
+/*
+ * The convention is that VNBus instance id is a GUID, but the host sets
+ * the lower part of the value to the host adapter LUID. The function
+ * provides the necessary conversion.
+ */
+static inline void guid_to_luid(guid_t *guid, struct winluid *luid)
+{
+ *luid = *(struct winluid *)&guid->b[0];
+}
+
+/*
+ * VM bus interface
+ *
+ */
+
+/*
+ * The interface version is used to ensure that the host and the guest use the
+ * same VM bus protocol. It needs to be incremented every time the VM bus
+ * interface changes. DXGK_VMBUS_LAST_COMPATIBLE_INTERFACE_VERSION is
+ * incremented each time the earlier versions of the interface are no longer
+ * compatible with the current version.
+ */
+#define DXGK_VMBUS_INTERFACE_VERSION_OLD 27
+#define DXGK_VMBUS_INTERFACE_VERSION 40
+#define DXGK_VMBUS_LAST_COMPATIBLE_INTERFACE_VERSION 16
+
+#ifdef DEBUG
+
+void dxgk_validate_ioctls(void);
+
+#define DXG_TRACE(fmt, ...) do { \
+ trace_printk(dev_fmt(fmt) "\n", ##__VA_ARGS__); \
+} while (0)
+
+#define DXG_ERR(fmt, ...) do { \
+ dev_err(DXGDEV, fmt, ##__VA_ARGS__); \
+ trace_printk("*** dxgkerror *** " dev_fmt(fmt) "\n", ##__VA_ARGS__); \
+} while (0)
+
+#else
+
+#define DXG_TRACE(...)
+#define DXG_ERR(fmt, ...) do { \
+ dev_err(DXGDEV, fmt, ##__VA_ARGS__); \
+} while (0)
+
+#endif /* DEBUG */
+
+#endif
diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c
new file mode 100644
index 000000000000..de02edc4d023
--- /dev/null
+++ b/drivers/hv/dxgkrnl/dxgmodule.c
@@ -0,0 +1,506 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2022, Microsoft Corporation.
+ *
+ * Author:
+ * Iouri Tarassov <iourit@linux.microsoft.com>
+ *
+ * Dxgkrnl Graphics Driver
+ * Interface with Linux kernel, PCI driver and the VM bus driver
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/eventfd.h>
+#include <linux/hyperv.h>
+#include <linux/pci.h>
+#include "dxgkrnl.h"
+
+#define PCI_VENDOR_ID_MICROSOFT 0x1414
+#define PCI_DEVICE_ID_VIRTUAL_RENDER 0x008E
+
+#undef pr_fmt
+#define pr_fmt(fmt) "dxgk: " fmt
+
+/*
+ * Interface from dxgglobal
+ */
+
+struct vmbus_channel *dxgglobal_get_vmbus(void)
+{
+ return dxggbl()->channel.channel;
+}
+
+struct dxgvmbuschannel *dxgglobal_get_dxgvmbuschannel(void)
+{
+ return &dxggbl()->channel;
+}
+
+int dxgglobal_acquire_channel_lock(void)
+{
+ struct dxgglobal *dxgglobal = dxggbl();
+
+ down_read(&dxgglobal->channel_lock);
+ if (dxgglobal->channel.channel == NULL) {
+ DXG_ERR("Failed to acquire global channel lock");
+ return -ENODEV;
+ } else {
+ return 0;
+ }
+}
+
+void dxgglobal_release_channel_lock(void)
+{
+ up_read(&dxggbl()->channel_lock);
+}
+
+const struct file_operations dxgk_fops = {
+ .owner = THIS_MODULE,
+};
+
+/*
+ * Interface with the PCI driver
+ */
+
+/*
+ * Part of the PCI config space of the compute device is used for
+ * configuration data. Reading/writing of the PCI config space is forwarded
+ * to the host.
+ *
+ * Below are offsets in the PCI config spaces for various configuration values.
+ */
+
+/* Compute device VM bus channel instance ID */
+#define DXGK_VMBUS_CHANNEL_ID_OFFSET 192
+
+/* DXGK_VMBUS_INTERFACE_VERSION (u32) */
+#define DXGK_VMBUS_VERSION_OFFSET (DXGK_VMBUS_CHANNEL_ID_OFFSET + \
+ sizeof(guid_t))
+
+/* Luid of the virtual GPU on the host (struct winluid) */
+#define DXGK_VMBUS_VGPU_LUID_OFFSET (DXGK_VMBUS_VERSION_OFFSET + \
+ sizeof(u32))
+
+/* The guest writes its capabilities to this address */
+#define DXGK_VMBUS_GUESTCAPS_OFFSET (DXGK_VMBUS_VERSION_OFFSET + \
+ sizeof(u32))
+
+/* Capabilities of the guest driver, reported to the host */
+struct dxgk_vmbus_guestcaps {
+ union {
+ struct {
+ u32 wsl2 : 1;
+ u32 reserved : 31;
+ };
+ u32 guest_caps;
+ };
+};
+
+/*
+ * A helper function to read PCI config space.
+ */
+static int dxg_pci_read_dwords(struct pci_dev *dev, int offset, int size,
+ void *val)
+{
+ int off = offset;
+ int ret;
+ int i;
+
+ /* Make sure the offset and size are 32 bit aligned */
+ if (offset & 3 || size & 3)
+ return -EINVAL;
+
+ for (i = 0; i < size / sizeof(int); i++) {
+ ret = pci_read_config_dword(dev, off, &((int *)val)[i]);
+ if (ret) {
+ DXG_ERR("Failed to read PCI config: %d", off);
+ return ret;
+ }
+ off += sizeof(int);
+ }
+ return 0;
+}
+
+static int dxg_pci_probe_device(struct pci_dev *dev,
+ const struct pci_device_id *id)
+{
+ int ret;
+ guid_t guid;
+ u32 vmbus_interface_ver = DXGK_VMBUS_INTERFACE_VERSION;
+ struct winluid vgpu_luid = {};
+ struct dxgk_vmbus_guestcaps guest_caps = {.wsl2 = 1};
+ struct dxgglobal *dxgglobal = dxggbl();
+
+ mutex_lock(&dxgglobal->device_mutex);
+
+ if (dxgglobal->vmbus_ver == 0) {
+ /* Report capabilities to the host */
+
+ ret = pci_write_config_dword(dev, DXGK_VMBUS_GUESTCAPS_OFFSET,
+ guest_caps.guest_caps);
+ if (ret)
+ goto cleanup;
+
+ /* Negotiate the VM bus version */
+
+ ret = pci_read_config_dword(dev, DXGK_VMBUS_VERSION_OFFSET,
+ &vmbus_interface_ver);
+ if (ret == 0 && vmbus_interface_ver != 0)
+ dxgglobal->vmbus_ver = vmbus_interface_ver;
+ else
+ dxgglobal->vmbus_ver = DXGK_VMBUS_INTERFACE_VERSION_OLD;
+
+ if (dxgglobal->vmbus_ver < DXGK_VMBUS_INTERFACE_VERSION)
+ goto read_channel_id;
+
+ ret = pci_write_config_dword(dev, DXGK_VMBUS_VERSION_OFFSET,
+ DXGK_VMBUS_INTERFACE_VERSION);
+ if (ret)
+ goto cleanup;
+
+ if (dxgglobal->vmbus_ver > DXGK_VMBUS_INTERFACE_VERSION)
+ dxgglobal->vmbus_ver = DXGK_VMBUS_INTERFACE_VERSION;
+ }
+
+read_channel_id:
+
+ /* Get the VM bus channel ID for the virtual GPU */
+ ret = dxg_pci_read_dwords(dev, DXGK_VMBUS_CHANNEL_ID_OFFSET,
+ sizeof(guid), (int *)&guid);
+ if (ret)
+ goto cleanup;
+
+ if (dxgglobal->vmbus_ver >= DXGK_VMBUS_INTERFACE_VERSION) {
+ ret = dxg_pci_read_dwords(dev, DXGK_VMBUS_VGPU_LUID_OFFSET,
+ sizeof(vgpu_luid), &vgpu_luid);
+ if (ret)
+ goto cleanup;
+ }
+
+ DXG_TRACE("Adapter channel: %pUb", &guid);
+ DXG_TRACE("Vmbus interface version: %d", dxgglobal->vmbus_ver);
+ DXG_TRACE("Host luid: %x-%x", vgpu_luid.b, vgpu_luid.a);
+
+cleanup:
+
+ mutex_unlock(&dxgglobal->device_mutex);
+
+ if (ret)
+ DXG_TRACE("err: %d", ret);
+ return ret;
+}
+
+static void dxg_pci_remove_device(struct pci_dev *dev)
+{
+ /* Placeholder */
+}
+
+static struct pci_device_id dxg_pci_id_table[] = {
+ {
+ .vendor = PCI_VENDOR_ID_MICROSOFT,
+ .device = PCI_DEVICE_ID_VIRTUAL_RENDER,
+ .subvendor = PCI_ANY_ID,
+ .subdevice = PCI_ANY_ID
+ },
+ { 0 }
+};
+
+/*
+ * Interface with the VM bus driver
+ */
+
+static int dxgglobal_getiospace(struct dxgglobal *dxgglobal)
+{
+ /* Get mmio space for the global channel */
+ struct hv_device *hdev = dxgglobal->hdev;
+ struct vmbus_channel *channel = hdev->channel;
+ resource_size_t pot_start = 0;
+ resource_size_t pot_end = -1;
+ int ret;
+
+ dxgglobal->mmiospace_size = channel->offermsg.offer.mmio_megabytes;
+ if (dxgglobal->mmiospace_size == 0) {
+ DXG_TRACE("Zero mmio space is offered");
+ return -ENOMEM;
+ }
+ dxgglobal->mmiospace_size <<= 20;
+ DXG_TRACE("mmio offered: %llx", dxgglobal->mmiospace_size);
+
+ ret = vmbus_allocate_mmio(&dxgglobal->mem, hdev, pot_start, pot_end,
+ dxgglobal->mmiospace_size, 0x10000, false);
+ if (ret) {
+ DXG_ERR("Unable to allocate mmio memory: %d", ret);
+ return ret;
+ }
+ dxgglobal->mmiospace_size = dxgglobal->mem->end -
+ dxgglobal->mem->start + 1;
+ dxgglobal->mmiospace_base = dxgglobal->mem->start;
+ DXG_TRACE("mmio allocated %llx %llx %llx %llx",
+ dxgglobal->mmiospace_base, dxgglobal->mmiospace_size,
+ dxgglobal->mem->start, dxgglobal->mem->end);
+
+ return 0;
+}
+
+int dxgglobal_init_global_channel(void)
+{
+ int ret = 0;
+ struct dxgglobal *dxgglobal = dxggbl();
+
+ ret = dxgvmbuschannel_init(&dxgglobal->channel, dxgglobal->hdev);
+ if (ret) {
+ DXG_ERR("dxgvmbuschannel_init failed: %d", ret);
+ goto error;
+ }
+
+ ret = dxgglobal_getiospace(dxgglobal);
+ if (ret) {
+ DXG_ERR("getiospace failed: %d", ret);
+ goto error;
+ }
+
+ hv_set_drvdata(dxgglobal->hdev, dxgglobal);
+
+error:
+ return ret;
+}
+
+void dxgglobal_destroy_global_channel(void)
+{
+ struct dxgglobal *dxgglobal = dxggbl();
+
+ down_write(&dxgglobal->channel_lock);
+
+ dxgglobal->global_channel_initialized = false;
+
+ if (dxgglobal->mem) {
+ vmbus_free_mmio(dxgglobal->mmiospace_base,
+ dxgglobal->mmiospace_size);
+ dxgglobal->mem = NULL;
+ }
+
+ dxgvmbuschannel_destroy(&dxgglobal->channel);
+
+ if (dxgglobal->hdev) {
+ hv_set_drvdata(dxgglobal->hdev, NULL);
+ dxgglobal->hdev = NULL;
+ }
+
+ up_write(&dxgglobal->channel_lock);
+}
+
+static const struct hv_vmbus_device_id dxg_vmbus_id_table[] = {
+ /* Per GPU Device GUID */
+ { HV_GPUP_DXGK_VGPU_GUID },
+ /* Global Dxgkgnl channel for the virtual machine */
+ { HV_GPUP_DXGK_GLOBAL_GUID },
+ { }
+};
+
+static int dxg_probe_vmbus(struct hv_device *hdev,
+ const struct hv_vmbus_device_id *dev_id)
+{
+ int ret = 0;
+ struct winluid luid;
+ struct dxgvgpuchannel *vgpuch;
+ struct dxgglobal *dxgglobal = dxggbl();
+
+ mutex_lock(&dxgglobal->device_mutex);
+
+ if (uuid_le_cmp(hdev->dev_type, dxg_vmbus_id_table[0].guid) == 0) {
+ /* This is a new virtual GPU channel */
+ guid_to_luid(&hdev->channel->offermsg.offer.if_instance, &luid);
+ DXG_TRACE("vGPU channel: %pUb",
+ &hdev->channel->offermsg.offer.if_instance);
+ vgpuch = kzalloc(sizeof(struct dxgvgpuchannel), GFP_KERNEL);
+ if (vgpuch == NULL) {
+ ret = -ENOMEM;
+ goto error;
+ }
+ vgpuch->adapter_luid = luid;
+ vgpuch->hdev = hdev;
+ list_add_tail(&vgpuch->vgpu_ch_list_entry,
+ &dxgglobal->vgpu_ch_list_head);
+ } else if (uuid_le_cmp(hdev->dev_type,
+ dxg_vmbus_id_table[1].guid) == 0) {
+ /* This is the global Dxgkgnl channel */
+ DXG_TRACE("Global channel: %pUb",
+ &hdev->channel->offermsg.offer.if_instance);
+ if (dxgglobal->hdev) {
+ /* This device should appear only once */
+ DXG_ERR("global channel already exists");
+ ret = -EBADE;
+ goto error;
+ }
+ dxgglobal->hdev = hdev;
+ } else {
+ /* Unknown device type */
+ DXG_ERR("Unknown VM bus device type");
+ ret = -ENODEV;
+ }
+
+error:
+
+ mutex_unlock(&dxgglobal->device_mutex);
+
+ return ret;
+}
+
+static int dxg_remove_vmbus(struct hv_device *hdev)
+{
+ int ret = 0;
+ struct dxgvgpuchannel *vgpu_channel;
+ struct dxgglobal *dxgglobal = dxggbl();
+
+ mutex_lock(&dxgglobal->device_mutex);
+
+ if (uuid_le_cmp(hdev->dev_type, dxg_vmbus_id_table[0].guid) == 0) {
+ DXG_TRACE("Remove virtual GPU channel");
+ list_for_each_entry(vgpu_channel,
+ &dxgglobal->vgpu_ch_list_head,
+ vgpu_ch_list_entry) {
+ if (vgpu_channel->hdev == hdev) {
+ list_del(&vgpu_channel->vgpu_ch_list_entry);
+ kfree(vgpu_channel);
+ break;
+ }
+ }
+ } else if (uuid_le_cmp(hdev->dev_type,
+ dxg_vmbus_id_table[1].guid) == 0) {
+ DXG_TRACE("Remove global channel device");
+ dxgglobal_destroy_global_channel();
+ } else {
+ /* Unknown device type */
+ DXG_ERR("Unknown device type");
+ ret = -ENODEV;
+ }
+
+ mutex_unlock(&dxgglobal->device_mutex);
+
+ return ret;
+}
+
+MODULE_DEVICE_TABLE(vmbus, dxg_vmbus_id_table);
+MODULE_DEVICE_TABLE(pci, dxg_pci_id_table);
+
+/*
+ * Global driver data
+ */
+
+struct dxgdriver dxgdrv = {
+ .vmbus_drv.name = KBUILD_MODNAME,
+ .vmbus_drv.id_table = dxg_vmbus_id_table,
+ .vmbus_drv.probe = dxg_probe_vmbus,
+ .vmbus_drv.remove = dxg_remove_vmbus,
+ .vmbus_drv.driver = {
+ .probe_type = PROBE_PREFER_ASYNCHRONOUS,
+ },
+ .pci_drv.name = KBUILD_MODNAME,
+ .pci_drv.id_table = dxg_pci_id_table,
+ .pci_drv.probe = dxg_pci_probe_device,
+ .pci_drv.remove = dxg_pci_remove_device
+};
+
+static struct dxgglobal *dxgglobal_create(void)
+{
+ struct dxgglobal *dxgglobal;
+
+ dxgglobal = kzalloc(sizeof(struct dxgglobal), GFP_KERNEL);
+ if (!dxgglobal)
+ return NULL;
+
+ mutex_init(&dxgglobal->device_mutex);
+
+ INIT_LIST_HEAD(&dxgglobal->vgpu_ch_list_head);
+
+ init_rwsem(&dxgglobal->channel_lock);
+
+ return dxgglobal;
+}
+
+static void dxgglobal_destroy(struct dxgglobal *dxgglobal)
+{
+ if (dxgglobal) {
+ mutex_lock(&dxgglobal->device_mutex);
+ dxgglobal_destroy_global_channel();
+ mutex_unlock(&dxgglobal->device_mutex);
+
+ if (dxgglobal->vmbus_registered)
+ vmbus_driver_unregister(&dxgdrv.vmbus_drv);
+
+ dxgglobal_destroy_global_channel();
+
+ if (dxgglobal->pci_registered)
+ pci_unregister_driver(&dxgdrv.pci_drv);
+
+ if (dxgglobal->misc_registered)
+ misc_deregister(&dxgglobal->dxgdevice);
+
+ dxgglobal->drvdata->dxgdev = NULL;
+
+ kfree(dxgglobal);
+ dxgglobal = NULL;
+ }
+}
+
+static int __init dxg_drv_init(void)
+{
+ int ret;
+ struct dxgglobal *dxgglobal = NULL;
+
+ dxgglobal = dxgglobal_create();
+ if (dxgglobal == NULL) {
+ pr_err("dxgglobal_init failed");
+ ret = -ENOMEM;
+ goto error;
+ }
+ dxgglobal->drvdata = &dxgdrv;
+
+ dxgglobal->dxgdevice.minor = MISC_DYNAMIC_MINOR;
+ dxgglobal->dxgdevice.name = "dxg";
+ dxgglobal->dxgdevice.fops = &dxgk_fops;
+ dxgglobal->dxgdevice.mode = 0666;
+ ret = misc_register(&dxgglobal->dxgdevice);
+ if (ret) {
+ pr_err("misc_register failed: %d", ret);
+ goto error;
+ }
+ dxgglobal->misc_registered = true;
+ dxgdrv.dxgdev = dxgglobal->dxgdevice.this_device;
+ dxgdrv.dxgglobal = dxgglobal;
+
+ ret = vmbus_driver_register(&dxgdrv.vmbus_drv);
+ if (ret) {
+ DXG_ERR("vmbus_driver_register failed: %d", ret);
+ goto error;
+ }
+ dxgglobal->vmbus_registered = true;
+
+ ret = pci_register_driver(&dxgdrv.pci_drv);
+ if (ret) {
+ DXG_ERR("pci_driver_register failed: %d", ret);
+ goto error;
+ }
+ dxgglobal->pci_registered = true;
+
+ return 0;
+
+error:
+ /* This function does the cleanup */
+ dxgglobal_destroy(dxgglobal);
+ dxgdrv.dxgglobal = NULL;
+
+ return ret;
+}
+
+static void __exit dxg_drv_exit(void)
+{
+ dxgglobal_destroy(dxgdrv.dxgglobal);
+}
+
+module_init(dxg_drv_init);
+module_exit(dxg_drv_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Microsoft Dxgkrnl virtual compute device Driver");
diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c
new file mode 100644
index 000000000000..deb880e34377
--- /dev/null
+++ b/drivers/hv/dxgkrnl/dxgvmbus.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2022, Microsoft Corporation.
+ *
+ * Author:
+ * Iouri Tarassov <iourit@linux.microsoft.com>
+ *
+ * Dxgkrnl Graphics Driver
+ * VM bus interface implementation
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <linux/eventfd.h>
+#include <linux/hyperv.h>
+#include <linux/mman.h>
+#include <linux/delay.h>
+#include <linux/pagemap.h>
+#include "dxgkrnl.h"
+#include "dxgvmbus.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "dxgk: " fmt
+
+#define RING_BUFSIZE (256 * 1024)
+
+/*
+ * The structure is used to track VM bus packets, waiting for completion.
+ */
+struct dxgvmbuspacket {
+ struct list_head packet_list_entry;
+ u64 request_id;
+ struct completion wait;
+ void *buffer;
+ u32 buffer_length;
+ int status;
+ bool completed;
+};
+
+int dxgvmbuschannel_init(struct dxgvmbuschannel *ch, struct hv_device *hdev)
+{
+ int ret;
+
+ ch->hdev = hdev;
+ spin_lock_init(&ch->packet_list_mutex);
+ INIT_LIST_HEAD(&ch->packet_list_head);
+ atomic64_set(&ch->packet_request_id, 0);
+
+ ch->packet_cache = kmem_cache_create("DXGK packet cache",
+ sizeof(struct dxgvmbuspacket), 0,
+ 0, NULL);
+ if (ch->packet_cache == NULL) {
+ DXG_ERR("packet_cache alloc failed");
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(5,15,0)
+ hdev->channel->max_pkt_size = DXG_MAX_VM_BUS_PACKET_SIZE;
+#endif
+ ret = vmbus_open(hdev->channel, RING_BUFSIZE, RING_BUFSIZE,
+ NULL, 0, dxgvmbuschannel_receive, ch);
+ if (ret) {
+ DXG_ERR("vmbus_open failed: %d", ret);
+ goto cleanup;
+ }
+
+ ch->channel = hdev->channel;
+
+cleanup:
+
+ return ret;
+}
+
+void dxgvmbuschannel_destroy(struct dxgvmbuschannel *ch)
+{
+ kmem_cache_destroy(ch->packet_cache);
+ ch->packet_cache = NULL;
+
+ if (ch->channel) {
+ vmbus_close(ch->channel);
+ ch->channel = NULL;
+ }
+}
+
+/* Receive callback for messages from the host */
+void dxgvmbuschannel_receive(void *ctx)
+{
+}
diff --git a/drivers/hv/dxgkrnl/dxgvmbus.h b/drivers/hv/dxgkrnl/dxgvmbus.h
new file mode 100644
index 000000000000..6cdca5e03d1f
--- /dev/null
+++ b/drivers/hv/dxgkrnl/dxgvmbus.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2022, Microsoft Corporation.
+ *
+ * Author:
+ * Iouri Tarassov <iourit@linux.microsoft.com>
+ *
+ * Dxgkrnl Graphics Driver
+ * VM bus interface with the host definitions
+ *
+ */
+
+#ifndef _DXGVMBUS_H
+#define _DXGVMBUS_H
+
+#define DXG_MAX_VM_BUS_PACKET_SIZE (1024 * 128)
+
+#endif /* _DXGVMBUS_H */
diff --git a/include/uapi/misc/d3dkmthk.h b/include/uapi/misc/d3dkmthk.h
new file mode 100644
index 000000000000..5d973604400c
--- /dev/null
+++ b/include/uapi/misc/d3dkmthk.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+/*
+ * Copyright (c) 2019, Microsoft Corporation.
+ *
+ * Author:
+ * Iouri Tarassov <iourit@linux.microsoft.com>
+ *
+ * Dxgkrnl Graphics Driver
+ * User mode WDDM interface definitions
+ *
+ */
+
+#ifndef _D3DKMTHK_H
+#define _D3DKMTHK_H
+
+/*
+ * Matches the Windows LUID definition.
+ * LUID is a locally unique identifier (similar to GUID, but not global),
+ * which is guaranteed to be unique intil the computer is rebooted.
+ */
+struct winluid {
+ __u32 a;
+ __u32 b;
+};
+
+#endif /* _D3DKMTHK_H */
^ permalink raw reply related
* [PATCH 02/55] drivers: hv: dxgkrnl: Add VMBus message support, initialize VMBus channels.
From: Eric Curtin @ 2026-03-19 20:24 UTC (permalink / raw)
To: linux-hyperv; +Cc: linux-kernel, iourit, wei.liu, decui, haiyangz
In-Reply-To: <20260319202509.63802-1-eric.curtin@docker.com>
From: Iouri Tarassov <iourit@linux.microsoft.com>
Implement support for sending/receiving VMBus messages between
the host and the guest.
Initialize the VMBus channels and notify the host about IO space
settings of the VMBus global channel.
Signed-off-by: Iouri Tarassov <iourit@linux.microsoft.com>
[kms: forward port to 6.6 from 6.1. No code changes made.]
Signed-off-by: Kelsey Steele <kelseysteele@microsoft.com>
---
drivers/hv/dxgkrnl/dxgkrnl.h | 14 ++
drivers/hv/dxgkrnl/dxgmodule.c | 9 +-
drivers/hv/dxgkrnl/dxgvmbus.c | 318 +++++++++++++++++++++++++++++++++
drivers/hv/dxgkrnl/dxgvmbus.h | 67 +++++++
drivers/hv/dxgkrnl/ioctl.c | 24 +++
drivers/hv/dxgkrnl/misc.h | 72 ++++++++
include/uapi/misc/d3dkmthk.h | 34 ++++
7 files changed, 536 insertions(+), 2 deletions(-)
create mode 100644 drivers/hv/dxgkrnl/ioctl.c
create mode 100644 drivers/hv/dxgkrnl/misc.h
diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h
index f7900840d1ed..52b9e82c51e6 100644
--- a/drivers/hv/dxgkrnl/dxgkrnl.h
+++ b/drivers/hv/dxgkrnl/dxgkrnl.h
@@ -28,6 +28,8 @@
#include <linux/hyperv.h>
#include <uapi/misc/d3dkmthk.h>
#include <linux/version.h>
+#include "misc.h"
+#include <uapi/misc/d3dkmthk.h>
struct dxgadapter;
@@ -100,6 +102,13 @@ static inline struct dxgglobal *dxggbl(void)
return dxgdrv.dxgglobal;
}
+int dxgglobal_init_global_channel(void);
+void dxgglobal_destroy_global_channel(void);
+struct vmbus_channel *dxgglobal_get_vmbus(void);
+struct dxgvmbuschannel *dxgglobal_get_dxgvmbuschannel(void);
+int dxgglobal_acquire_channel_lock(void);
+void dxgglobal_release_channel_lock(void);
+
struct dxgprocess {
/* Placeholder */
};
@@ -130,6 +139,11 @@ static inline void guid_to_luid(guid_t *guid, struct winluid *luid)
#define DXGK_VMBUS_INTERFACE_VERSION 40
#define DXGK_VMBUS_LAST_COMPATIBLE_INTERFACE_VERSION 16
+void dxgvmb_initialize(void);
+int dxgvmb_send_set_iospace_region(u64 start, u64 len);
+
+int ntstatus2int(struct ntstatus status);
+
#ifdef DEBUG
void dxgk_validate_ioctls(void);
diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c
index de02edc4d023..e55639dc0adc 100644
--- a/drivers/hv/dxgkrnl/dxgmodule.c
+++ b/drivers/hv/dxgkrnl/dxgmodule.c
@@ -260,6 +260,13 @@ int dxgglobal_init_global_channel(void)
goto error;
}
+ ret = dxgvmb_send_set_iospace_region(dxgglobal->mmiospace_base,
+ dxgglobal->mmiospace_size);
+ if (ret < 0) {
+ DXG_ERR("send_set_iospace_region failed");
+ goto error;
+ }
+
hv_set_drvdata(dxgglobal->hdev, dxgglobal);
error:
@@ -429,8 +436,6 @@ static void dxgglobal_destroy(struct dxgglobal *dxgglobal)
if (dxgglobal->vmbus_registered)
vmbus_driver_unregister(&dxgdrv.vmbus_drv);
- dxgglobal_destroy_global_channel();
-
if (dxgglobal->pci_registered)
pci_unregister_driver(&dxgdrv.pci_drv);
diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c
index deb880e34377..a4365739826a 100644
--- a/drivers/hv/dxgkrnl/dxgvmbus.c
+++ b/drivers/hv/dxgkrnl/dxgvmbus.c
@@ -40,6 +40,121 @@ struct dxgvmbuspacket {
bool completed;
};
+struct dxgvmb_ext_header {
+ /* Offset from the start of the message to DXGKVMB_COMMAND_BASE */
+ u32 command_offset;
+ u32 reserved;
+ struct winluid vgpu_luid;
+};
+
+#define VMBUSMESSAGEONSTACK 64
+
+struct dxgvmbusmsg {
+/* Points to the allocated buffer */
+ struct dxgvmb_ext_header *hdr;
+/* Points to dxgkvmb_command_vm_to_host or dxgkvmb_command_vgpu_to_host */
+ void *msg;
+/* The vm bus channel, used to pass the message to the host */
+ struct dxgvmbuschannel *channel;
+/* Message size in bytes including the header and the payload */
+ u32 size;
+/* Buffer used for small messages */
+ char msg_on_stack[VMBUSMESSAGEONSTACK];
+};
+
+struct dxgvmbusmsgres {
+/* Points to the allocated buffer */
+ struct dxgvmb_ext_header *hdr;
+/* Points to dxgkvmb_command_vm_to_host or dxgkvmb_command_vgpu_to_host */
+ void *msg;
+/* The vm bus channel, used to pass the message to the host */
+ struct dxgvmbuschannel *channel;
+/* Message size in bytes including the header, the payload and the result */
+ u32 size;
+/* Result buffer size in bytes */
+ u32 res_size;
+/* Points to the result within the allocated buffer */
+ void *res;
+};
+
+static int init_message(struct dxgvmbusmsg *msg,
+ struct dxgprocess *process, u32 size)
+{
+ struct dxgglobal *dxgglobal = dxggbl();
+
+ bool use_ext_header = dxgglobal->vmbus_ver >=
+ DXGK_VMBUS_INTERFACE_VERSION;
+
+ if (use_ext_header)
+ size += sizeof(struct dxgvmb_ext_header);
+ msg->size = size;
+ if (size <= VMBUSMESSAGEONSTACK) {
+ msg->hdr = (void *)msg->msg_on_stack;
+ memset(msg->hdr, 0, size);
+ } else {
+ msg->hdr = vzalloc(size);
+ if (msg->hdr == NULL)
+ return -ENOMEM;
+ }
+ if (use_ext_header) {
+ msg->msg = (char *)&msg->hdr[1];
+ msg->hdr->command_offset = sizeof(msg->hdr[0]);
+ } else {
+ msg->msg = (char *)msg->hdr;
+ }
+ msg->channel = &dxgglobal->channel;
+ return 0;
+}
+
+static void free_message(struct dxgvmbusmsg *msg, struct dxgprocess *process)
+{
+ if (msg->hdr && (char *)msg->hdr != msg->msg_on_stack)
+ vfree(msg->hdr);
+}
+
+/*
+ * Helper functions
+ */
+
+int ntstatus2int(struct ntstatus status)
+{
+ if (NT_SUCCESS(status))
+ return (int)status.v;
+ switch (status.v) {
+ case STATUS_OBJECT_NAME_COLLISION:
+ return -EEXIST;
+ case STATUS_NO_MEMORY:
+ return -ENOMEM;
+ case STATUS_INVALID_PARAMETER:
+ return -EINVAL;
+ case STATUS_OBJECT_NAME_INVALID:
+ case STATUS_OBJECT_NAME_NOT_FOUND:
+ return -ENOENT;
+ case STATUS_TIMEOUT:
+ return -EAGAIN;
+ case STATUS_BUFFER_TOO_SMALL:
+ return -EOVERFLOW;
+ case STATUS_DEVICE_REMOVED:
+ return -ENODEV;
+ case STATUS_ACCESS_DENIED:
+ return -EACCES;
+ case STATUS_NOT_SUPPORTED:
+ return -EPERM;
+ case STATUS_ILLEGAL_INSTRUCTION:
+ return -EOPNOTSUPP;
+ case STATUS_INVALID_HANDLE:
+ return -EBADF;
+ case STATUS_GRAPHICS_ALLOCATION_BUSY:
+ return -EINPROGRESS;
+ case STATUS_OBJECT_TYPE_MISMATCH:
+ return -EPROTOTYPE;
+ case STATUS_NOT_IMPLEMENTED:
+ return -EPERM;
+ default:
+ return -EINVAL;
+ }
+}
+
int dxgvmbuschannel_init(struct dxgvmbuschannel *ch, struct hv_device *hdev)
{
int ret;
@@ -86,7 +201,210 @@ void dxgvmbuschannel_destroy(struct dxgvmbuschannel *ch)
}
}
+static void command_vm_to_host_init1(struct dxgkvmb_command_vm_to_host *command,
+ enum dxgkvmb_commandtype_global type)
+{
+ command->command_type = type;
+ command->process.v = 0;
+ command->command_id = 0;
+ command->channel_type = DXGKVMB_VM_TO_HOST;
+}
+
+static void process_inband_packet(struct dxgvmbuschannel *channel,
+ struct vmpacket_descriptor *desc)
+{
+ u32 packet_length = hv_pkt_datalen(desc);
+ struct dxgkvmb_command_host_to_vm *packet;
+
+ if (packet_length < sizeof(struct dxgkvmb_command_host_to_vm)) {
+ DXG_ERR("Invalid global packet");
+ } else {
+ packet = hv_pkt_data(desc);
+ DXG_TRACE("global packet %d",
+ packet->command_type);
+ switch (packet->command_type) {
+ case DXGK_VMBCOMMAND_SIGNALGUESTEVENT:
+ case DXGK_VMBCOMMAND_SIGNALGUESTEVENTPASSIVE:
+ break;
+ case DXGK_VMBCOMMAND_SENDWNFNOTIFICATION:
+ break;
+ default:
+ DXG_ERR("unexpected host message %d",
+ packet->command_type);
+ }
+ }
+}
+
+static void process_completion_packet(struct dxgvmbuschannel *channel,
+ struct vmpacket_descriptor *desc)
+{
+ struct dxgvmbuspacket *packet = NULL;
+ struct dxgvmbuspacket *entry;
+ u32 packet_length = hv_pkt_datalen(desc);
+ unsigned long flags;
+
+ spin_lock_irqsave(&channel->packet_list_mutex, flags);
+ list_for_each_entry(entry, &channel->packet_list_head,
+ packet_list_entry) {
+ if (desc->trans_id == entry->request_id) {
+ packet = entry;
+ list_del(&packet->packet_list_entry);
+ packet->completed = true;
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&channel->packet_list_mutex, flags);
+ if (packet) {
+ if (packet->buffer_length) {
+ if (packet_length < packet->buffer_length) {
+ DXG_TRACE("invalid size %d Expected:%d",
+ packet_length,
+ packet->buffer_length);
+ packet->status = -EOVERFLOW;
+ } else {
+ memcpy(packet->buffer, hv_pkt_data(desc),
+ packet->buffer_length);
+ }
+ }
+ complete(&packet->wait);
+ } else {
+ DXG_ERR("did not find packet to complete");
+ }
+}
+
/* Receive callback for messages from the host */
void dxgvmbuschannel_receive(void *ctx)
{
+ struct dxgvmbuschannel *channel = ctx;
+ struct vmpacket_descriptor *desc;
+ u32 packet_length = 0;
+
+ foreach_vmbus_pkt(desc, channel->channel) {
+ packet_length = hv_pkt_datalen(desc);
+ DXG_TRACE("next packet (id, size, type): %llu %d %d",
+ desc->trans_id, packet_length, desc->type);
+ if (desc->type == VM_PKT_COMP) {
+ process_completion_packet(channel, desc);
+ } else {
+ if (desc->type != VM_PKT_DATA_INBAND)
+ DXG_ERR("unexpected packet type");
+ else
+ process_inband_packet(channel, desc);
+ }
+ }
+}
+
+int dxgvmb_send_sync_msg(struct dxgvmbuschannel *channel,
+ void *command,
+ u32 cmd_size,
+ void *result,
+ u32 result_size)
+{
+ int ret;
+ struct dxgvmbuspacket *packet = NULL;
+
+ if (cmd_size > DXG_MAX_VM_BUS_PACKET_SIZE ||
+ result_size > DXG_MAX_VM_BUS_PACKET_SIZE) {
+ DXG_ERR("%s invalid data size", __func__);
+ return -EINVAL;
+ }
+
+ packet = kmem_cache_alloc(channel->packet_cache, 0);
+ if (packet == NULL) {
+ DXG_ERR("kmem_cache_alloc failed");
+ return -ENOMEM;
+ }
+
+ packet->request_id = atomic64_inc_return(&channel->packet_request_id);
+ init_completion(&packet->wait);
+ packet->buffer = result;
+ packet->buffer_length = result_size;
+ packet->status = 0;
+ packet->completed = false;
+ spin_lock_irq(&channel->packet_list_mutex);
+ list_add_tail(&packet->packet_list_entry, &channel->packet_list_head);
+ spin_unlock_irq(&channel->packet_list_mutex);
+
+ ret = vmbus_sendpacket(channel->channel, command, cmd_size,
+ packet->request_id, VM_PKT_DATA_INBAND,
+ VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+ if (ret) {
+ DXG_ERR("vmbus_sendpacket failed: %x", ret);
+ spin_lock_irq(&channel->packet_list_mutex);
+ list_del(&packet->packet_list_entry);
+ spin_unlock_irq(&channel->packet_list_mutex);
+ goto cleanup;
+ }
+
+ DXG_TRACE("waiting completion: %llu", packet->request_id);
+ ret = wait_for_completion_killable(&packet->wait);
+ if (ret) {
+ DXG_ERR("wait_for_completion failed: %x", ret);
+ spin_lock_irq(&channel->packet_list_mutex);
+ if (!packet->completed)
+ list_del(&packet->packet_list_entry);
+ spin_unlock_irq(&channel->packet_list_mutex);
+ goto cleanup;
+ }
+ DXG_TRACE("completion done: %llu %x",
+ packet->request_id, packet->status);
+ ret = packet->status;
+
+cleanup:
+
+ kmem_cache_free(channel->packet_cache, packet);
+ if (ret < 0)
+ DXG_TRACE("Error: %x", ret);
+ return ret;
+}
+
+static int
+dxgvmb_send_sync_msg_ntstatus(struct dxgvmbuschannel *channel,
+ void *command, u32 cmd_size)
+{
+ struct ntstatus status;
+ int ret;
+
+ ret = dxgvmb_send_sync_msg(channel, command, cmd_size,
+ &status, sizeof(status));
+ if (ret >= 0)
+ ret = ntstatus2int(status);
+ return ret;
+}
+
+/*
+ * Global messages to the host
+ */
+
+int dxgvmb_send_set_iospace_region(u64 start, u64 len)
+{
+ int ret;
+ struct dxgkvmb_command_setiospaceregion *command;
+ struct dxgvmbusmsg msg;
+ struct dxgglobal *dxgglobal = dxggbl();
+
+ ret = init_message(&msg, NULL, sizeof(*command));
+ if (ret)
+ return ret;
+ command = (void *)msg.msg;
+
+ ret = dxgglobal_acquire_channel_lock();
+ if (ret < 0)
+ goto cleanup;
+
+ command_vm_to_host_init1(&command->hdr,
+ DXGK_VMBCOMMAND_SETIOSPACEREGION);
+ command->start = start;
+ command->length = len;
+ ret = dxgvmb_send_sync_msg_ntstatus(&dxgglobal->channel, msg.hdr,
+ msg.size);
+ if (ret < 0)
+ DXG_ERR("send_set_iospace_region failed %x", ret);
+
+ dxgglobal_release_channel_lock();
+cleanup:
+ free_message(&msg, NULL);
+ if (ret)
+ DXG_TRACE("Error: %d", ret);
+ return ret;
}
diff --git a/drivers/hv/dxgkrnl/dxgvmbus.h b/drivers/hv/dxgkrnl/dxgvmbus.h
index 6cdca5e03d1f..b1bdd6039b73 100644
--- a/drivers/hv/dxgkrnl/dxgvmbus.h
+++ b/drivers/hv/dxgkrnl/dxgvmbus.h
@@ -16,4 +16,71 @@
#define DXG_MAX_VM_BUS_PACKET_SIZE (1024 * 128)
+enum dxgkvmb_commandchanneltype {
+ DXGKVMB_VGPU_TO_HOST,
+ DXGKVMB_VM_TO_HOST,
+ DXGKVMB_HOST_TO_VM
+};
+
+/*
+ *
+ * Commands, sent to the host via the guest global VM bus channel
+ * DXG_GUEST_GLOBAL_VMBUS
+ *
+ */
+
+enum dxgkvmb_commandtype_global {
+ DXGK_VMBCOMMAND_VM_TO_HOST_FIRST = 1000,
+ DXGK_VMBCOMMAND_CREATEPROCESS = DXGK_VMBCOMMAND_VM_TO_HOST_FIRST,
+ DXGK_VMBCOMMAND_DESTROYPROCESS = 1001,
+ DXGK_VMBCOMMAND_OPENSYNCOBJECT = 1002,
+ DXGK_VMBCOMMAND_DESTROYSYNCOBJECT = 1003,
+ DXGK_VMBCOMMAND_CREATENTSHAREDOBJECT = 1004,
+ DXGK_VMBCOMMAND_DESTROYNTSHAREDOBJECT = 1005,
+ DXGK_VMBCOMMAND_SIGNALFENCE = 1006,
+ DXGK_VMBCOMMAND_NOTIFYPROCESSFREEZE = 1007,
+ DXGK_VMBCOMMAND_NOTIFYPROCESSTHAW = 1008,
+ DXGK_VMBCOMMAND_QUERYETWSESSION = 1009,
+ DXGK_VMBCOMMAND_SETIOSPACEREGION = 1010,
+ DXGK_VMBCOMMAND_COMPLETETRANSACTION = 1011,
+ DXGK_VMBCOMMAND_SHAREOBJECTWITHHOST = 1021,
+ DXGK_VMBCOMMAND_INVALID_VM_TO_HOST
+};
+
+/*
+ * Commands, sent by the host to the VM
+ */
+enum dxgkvmb_commandtype_host_to_vm {
+ DXGK_VMBCOMMAND_SIGNALGUESTEVENT,
+ DXGK_VMBCOMMAND_PROPAGATEPRESENTHISTORYTOKEN,
+ DXGK_VMBCOMMAND_SETGUESTDATA,
+ DXGK_VMBCOMMAND_SIGNALGUESTEVENTPASSIVE,
+ DXGK_VMBCOMMAND_SENDWNFNOTIFICATION,
+ DXGK_VMBCOMMAND_INVALID_HOST_TO_VM
+};
+
+struct dxgkvmb_command_vm_to_host {
+ u64 command_id;
+ struct d3dkmthandle process;
+ enum dxgkvmb_commandchanneltype channel_type;
+ enum dxgkvmb_commandtype_global command_type;
+};
+
+struct dxgkvmb_command_host_to_vm {
+ u64 command_id;
+ struct d3dkmthandle process;
+ u32 channel_type : 8;
+ u32 async_msg : 1;
+ u32 reserved : 23;
+ enum dxgkvmb_commandtype_host_to_vm command_type;
+};
+
+/* Returns ntstatus */
+struct dxgkvmb_command_setiospaceregion {
+ struct dxgkvmb_command_vm_to_host hdr;
+ u64 start;
+ u64 length;
+ u32 shared_page_gpadl;
+};
+
#endif /* _DXGVMBUS_H */
diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c
new file mode 100644
index 000000000000..23ecd15b0cd7
--- /dev/null
+++ b/drivers/hv/dxgkrnl/ioctl.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2022, Microsoft Corporation.
+ *
+ * Author:
+ * Iouri Tarassov <iourit@linux.microsoft.com>
+ *
+ * Dxgkrnl Graphics Driver
+ * Ioctl implementation
+ *
+ */
+
+#include <linux/eventfd.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/mman.h>
+
+#include "dxgkrnl.h"
+#include "dxgvmbus.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "dxgk: " fmt
diff --git a/drivers/hv/dxgkrnl/misc.h b/drivers/hv/dxgkrnl/misc.h
new file mode 100644
index 000000000000..4c6047c32a20
--- /dev/null
+++ b/drivers/hv/dxgkrnl/misc.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2022, Microsoft Corporation.
+ *
+ * Author:
+ * Iouri Tarassov <iourit@linux.microsoft.com>
+ *
+ * Dxgkrnl Graphics Driver
+ * Misc definitions
+ *
+ */
+
+#ifndef _MISC_H_
+#define _MISC_H_
+
+extern const struct d3dkmthandle zerohandle;
+
+/*
+ * Synchronization lock hierarchy.
+ *
+ * The higher enum value, the higher is the lock order.
+ * When a lower lock ois held, the higher lock should not be acquired.
+ *
+ * channel_lock
+ * device_mutex
+ */
+
+/*
+ * Some of the Windows return codes, which needs to be translated to Linux
+ * IOCTL return codes. Positive values are success codes and need to be
+ * returned from the driver IOCTLs. libdxcore.so depends on returning
+ * specific return codes.
+ */
+#define STATUS_SUCCESS ((int)(0))
+#define STATUS_OBJECT_NAME_INVALID ((int)(0xC0000033L))
+#define STATUS_DEVICE_REMOVED ((int)(0xC00002B6L))
+#define STATUS_INVALID_HANDLE ((int)(0xC0000008L))
+#define STATUS_ILLEGAL_INSTRUCTION ((int)(0xC000001DL))
+#define STATUS_NOT_IMPLEMENTED ((int)(0xC0000002L))
+#define STATUS_PENDING ((int)(0x00000103L))
+#define STATUS_ACCESS_DENIED ((int)(0xC0000022L))
+#define STATUS_BUFFER_TOO_SMALL ((int)(0xC0000023L))
+#define STATUS_OBJECT_TYPE_MISMATCH ((int)(0xC0000024L))
+#define STATUS_GRAPHICS_ALLOCATION_BUSY ((int)(0xC01E0102L))
+#define STATUS_NOT_SUPPORTED ((int)(0xC00000BBL))
+#define STATUS_TIMEOUT ((int)(0x00000102L))
+#define STATUS_INVALID_PARAMETER ((int)(0xC000000DL))
+#define STATUS_NO_MEMORY ((int)(0xC0000017L))
+#define STATUS_OBJECT_NAME_COLLISION ((int)(0xC0000035L))
+#define STATUS_OBJECT_NAME_NOT_FOUND ((int)(0xC0000034L))
+
+
+#define NT_SUCCESS(status) (status.v >= 0)
+
+#ifndef DEBUG
+
+#define DXGKRNL_ASSERT(exp)
+
+#else
+
+#define DXGKRNL_ASSERT(exp) \
+do { \
+ if (!(exp)) { \
+ dump_stack(); \
+ BUG_ON(true); \
+ } \
+} while (0)
+
+#endif /* DEBUG */
+
+#endif /* _MISC_H_ */
diff --git a/include/uapi/misc/d3dkmthk.h b/include/uapi/misc/d3dkmthk.h
index 5d973604400c..2ea04cc02a1f 100644
--- a/include/uapi/misc/d3dkmthk.h
+++ b/include/uapi/misc/d3dkmthk.h
@@ -14,6 +14,40 @@
#ifndef _D3DKMTHK_H
#define _D3DKMTHK_H
+/*
+ * This structure matches the definition of D3DKMTHANDLE in Windows.
+ * The handle is opaque in user mode. It is used by user mode applications to
+ * represent kernel mode objects, created by dxgkrnl.
+ */
+struct d3dkmthandle {
+ union {
+ struct {
+ __u32 instance : 6;
+ __u32 index : 24;
+ __u32 unique : 2;
+ };
+ __u32 v;
+ };
+};
+
+/*
+ * VM bus messages return Windows' NTSTATUS, which is integer and only negative
+ * value indicates a failure. A positive number is a success and needs to be
+ * returned to user mode as the IOCTL return code. Negative status codes are
+ * converted to Linux error codes.
+ */
+struct ntstatus {
+ union {
+ struct {
+ int code : 16;
+ int facility : 13;
+ int customer : 1;
+ int severity : 2;
+ };
+ int v;
+ };
+};
+
/*
* Matches the Windows LUID definition.
* LUID is a locally unique identifier (similar to GUID, but not global),
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox