[v3,08/16] s390/pci: Remove races against pte updates

Way back it was a reasonable assumptions that iomem mappings never
change the pfn range they point at. But this has changed:

- gpu drivers dynamically manage their memory nowadays, invalidating
ptes with unmap_mapping_range when buffers get moved

- contiguous dma allocations have moved from dedicated carvetouts to
cma regions. This means if we miss the unmap the pfn might contain
pagecache or anon memory (well anything allocated with GFP_MOVEABLE)

- even /dev/mem now invalidates mappings when the kernel requests that
iomem region when CONFIG_IO_STRICT_DEVMEM is set, see commit
3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the
region")

Accessing pfns obtained from ptes without holding all the locks is
therefore no longer a good idea. Fix this.

Since zpci_memcpy_from|toio seems to not do anything nefarious with
locks we just need to open code get_pfn and follow_pfn and make sure
we drop the locks only after we're done. The write function also needs
the copy_from_user move, since we can't take userspace faults while
holding the mmap sem.

v2: Move VM_IO | VM_PFNMAP checks around so they keep returning EINVAL
like before (Gerard)

v3: Polish commit message (Niklas)

Reviewed-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: linux-mm@kvack.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-samsung-soc@vger.kernel.org
Cc: linux-media@vger.kernel.org
Cc: Niklas Schnelle <schnelle@linux.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: linux-s390@vger.kernel.org
Cc: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.com>
---
 arch/s390/pci/pci_mmio.c | 98 +++++++++++++++++++++++-----------------
 1 file changed, 57 insertions(+), 41 deletions(-)

On 10/21/20 10:56 AM, Daniel Vetter wrote:
> Way back it was a reasonable assumptions that iomem mappings never
> change the pfn range they point at. But this has changed:
> 
> - gpu drivers dynamically manage their memory nowadays, invalidating
> ptes with unmap_mapping_range when buffers get moved
> 
> - contiguous dma allocations have moved from dedicated carvetouts to
> cma regions. This means if we miss the unmap the pfn might contain
> pagecache or anon memory (well anything allocated with GFP_MOVEABLE)
> 
> - even /dev/mem now invalidates mappings when the kernel requests that
> iomem region when CONFIG_IO_STRICT_DEVMEM is set, see commit
> 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the
> region")
> 
> Accessing pfns obtained from ptes without holding all the locks is
> therefore no longer a good idea. Fix this.
> 
> Since zpci_memcpy_from|toio seems to not do anything nefarious with
> locks we just need to open code get_pfn and follow_pfn and make sure
> we drop the locks only after we're done. The write function also needs
> the copy_from_user move, since we can't take userspace faults while
> holding the mmap sem.
> 
> v2: Move VM_IO | VM_PFNMAP checks around so they keep returning EINVAL
> like before (Gerard)
> 
> v3: Polish commit message (Niklas)
> 
> Reviewed-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> Cc: Jason Gunthorpe <jgg@ziepe.ca>
> Cc: Dan Williams <dan.j.williams@intel.com>
> Cc: Kees Cook <keescook@chromium.org>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: John Hubbard <jhubbard@nvidia.com>
> Cc: Jérôme Glisse <jglisse@redhat.com>
> Cc: Jan Kara <jack@suse.cz>
> Cc: linux-mm@kvack.org
> Cc: linux-arm-kernel@lists.infradead.org
> Cc: linux-samsung-soc@vger.kernel.org
> Cc: linux-media@vger.kernel.org
> Cc: Niklas Schnelle <schnelle@linux.ibm.com>
> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
> Cc: linux-s390@vger.kernel.org
> Cc: Niklas Schnelle <schnelle@linux.ibm.com>
> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.com>
                                                   ^^^^
This should be ".ch", but since this is clearly a typo and you also send from @ffwll.ch,
I took the liberty and fixed it for this commit and applied your patch to our internal
branch, Heiko or Vasily will then pick it up for the s390 tree.

Thanks!

> ---
>  arch/s390/pci/pci_mmio.c | 98 +++++++++++++++++++++++-----------------
>  1 file changed, 57 insertions(+), 41 deletions(-)
> 
> diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
> index 401cf670a243..1a6adbc68ee8 100644
> --- a/arch/s390/pci/pci_mmio.c
> +++ b/arch/s390/pci/pci_mmio.c
> @@ -119,33 +119,15 @@ static inline int __memcpy_toio_inuser(void __iomem *dst,
>  	return rc;
>  }
>  
> -static long get_pfn(unsigned long user_addr, unsigned long access,
> -		    unsigned long *pfn)
> -{
> -	struct vm_area_struct *vma;
> -	long ret;
> -
> -	mmap_read_lock(current->mm);
> -	ret = -EINVAL;
> -	vma = find_vma(current->mm, user_addr);
> -	if (!vma)
> -		goto out;
> -	ret = -EACCES;
> -	if (!(vma->vm_flags & access))
> -		goto out;
> -	ret = follow_pfn(vma, user_addr, pfn);
> -out:
> -	mmap_read_unlock(current->mm);
> -	return ret;
> -}
> -
>  SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
>  		const void __user *, user_buffer, size_t, length)
>  {
>  	u8 local_buf[64];
>  	void __iomem *io_addr;
>  	void *buf;
> -	unsigned long pfn;
> +	struct vm_area_struct *vma;
> +	pte_t *ptep;
> +	spinlock_t *ptl;
>  	long ret;
>  
>  	if (!zpci_is_enabled())
> @@ -158,7 +140,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
>  	 * We only support write access to MIO capable devices if we are on
>  	 * a MIO enabled system. Otherwise we would have to check for every
>  	 * address if it is a special ZPCI_ADDR and would have to do
> -	 * a get_pfn() which we don't need for MIO capable devices.  Currently
> +	 * a pfn lookup which we don't need for MIO capable devices.  Currently
>  	 * ISM devices are the only devices without MIO support and there is no
>  	 * known need for accessing these from userspace.
>  	 */
> @@ -176,21 +158,37 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
>  	} else
>  		buf = local_buf;
>  
> -	ret = get_pfn(mmio_addr, VM_WRITE, &pfn);
> +	ret = -EFAULT;
> +	if (copy_from_user(buf, user_buffer, length))
> +		goto out_free;
> +
> +	mmap_read_lock(current->mm);
> +	ret = -EINVAL;
> +	vma = find_vma(current->mm, mmio_addr);
> +	if (!vma)
> +		goto out_unlock_mmap;
> +	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
> +		goto out_unlock_mmap;
> +	ret = -EACCES;
> +	if (!(vma->vm_flags & VM_WRITE))
> +		goto out_unlock_mmap;
> +
> +	ret = follow_pte_pmd(vma->vm_mm, mmio_addr, NULL, &ptep, NULL, &ptl);
>  	if (ret)
> -		goto out;
> -	io_addr = (void __iomem *)((pfn << PAGE_SHIFT) |
> +		goto out_unlock_mmap;
> +
> +	io_addr = (void __iomem *)((pte_pfn(*ptep) << PAGE_SHIFT) |
>  			(mmio_addr & ~PAGE_MASK));
>  
> -	ret = -EFAULT;
>  	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE)
> -		goto out;
> -
> -	if (copy_from_user(buf, user_buffer, length))
> -		goto out;
> +		goto out_unlock_pt;
>  
>  	ret = zpci_memcpy_toio(io_addr, buf, length);
> -out:
> +out_unlock_pt:
> +	pte_unmap_unlock(ptep, ptl);
> +out_unlock_mmap:
> +	mmap_read_unlock(current->mm);
> +out_free:
>  	if (buf != local_buf)
>  		kfree(buf);
>  	return ret;
> @@ -274,7 +272,9 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
>  	u8 local_buf[64];
>  	void __iomem *io_addr;
>  	void *buf;
> -	unsigned long pfn;
> +	struct vm_area_struct *vma;
> +	pte_t *ptep;
> +	spinlock_t *ptl;
>  	long ret;
>  
>  	if (!zpci_is_enabled())
> @@ -287,7 +287,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
>  	 * We only support read access to MIO capable devices if we are on
>  	 * a MIO enabled system. Otherwise we would have to check for every
>  	 * address if it is a special ZPCI_ADDR and would have to do
> -	 * a get_pfn() which we don't need for MIO capable devices.  Currently
> +	 * a pfn lookup which we don't need for MIO capable devices.  Currently
>  	 * ISM devices are the only devices without MIO support and there is no
>  	 * known need for accessing these from userspace.
>  	 */
> @@ -306,22 +306,38 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
>  		buf = local_buf;
>  	}
>  
> -	ret = get_pfn(mmio_addr, VM_READ, &pfn);
> +	mmap_read_lock(current->mm);
> +	ret = -EINVAL;
> +	vma = find_vma(current->mm, mmio_addr);
> +	if (!vma)
> +		goto out_unlock_mmap;
> +	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
> +		goto out_unlock_mmap;
> +	ret = -EACCES;
> +	if (!(vma->vm_flags & VM_WRITE))
> +		goto out_unlock_mmap;
> +
> +	ret = follow_pte_pmd(vma->vm_mm, mmio_addr, NULL, &ptep, NULL, &ptl);
>  	if (ret)
> -		goto out;
> -	io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK));
> +		goto out_unlock_mmap;
> +
> +	io_addr = (void __iomem *)((pte_pfn(*ptep) << PAGE_SHIFT) |
> +			(mmio_addr & ~PAGE_MASK));
>  
>  	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) {
>  		ret = -EFAULT;
> -		goto out;
> +		goto out_unlock_pt;
>  	}
>  	ret = zpci_memcpy_fromio(buf, io_addr, length);
> -	if (ret)
> -		goto out;
> -	if (copy_to_user(user_buffer, buf, length))
> +
> +out_unlock_pt:
> +	pte_unmap_unlock(ptep, ptl);
> +out_unlock_mmap:
> +	mmap_read_unlock(current->mm);
> +
> +	if (!ret && copy_to_user(user_buffer, buf, length))
>  		ret = -EFAULT;
>  
> -out:
>  	if (buf != local_buf)
>  		kfree(buf);
>  	return ret;
>