Since 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") /dev/kmem zaps ptes when the kernel requests exclusive acccess to an iomem region. And with CONFIG_IO_STRICT_DEVMEM, this is the default for all driver uses.
Except there's two more ways to access pci bars: sysfs and proc mmap support. Let's plug that hole.
For revoke_devmem() to work we need to link our vma into the same address_space, with consistent vma->vm_pgoff. ->pgoff is already adjusted, because that's how (io_)remap_pfn_range works, but for the mapping we need to adjust vma->vm_file->f_mapping. Usually that's done at ->open time, but that's a bit tricky here with all the entry points and arch code. So instead create a fake file and adjust vma->vm_file.
Note this only works for ARCH_GENERIC_PCI_MMAP_RESOURCE. But that seems to be a subset of architectures support STRICT_DEVMEM, so we should be good.
The only difference in access checks left is that sysfs pci mmap does not check for CAP_RAWIO. But I think that makes some sense compared to /dev/mem and proc, where one file gives you access to everything and no ownership applies.
Signed-off-by: Daniel Vetter daniel.vetter@intel.com Cc: Jason Gunthorpe jgg@ziepe.ca Cc: Kees Cook keescook@chromium.org Cc: Dan Williams dan.j.williams@intel.com 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: Dan Williams dan.j.williams@intel.com 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: Bjorn Helgaas bhelgaas@google.com Cc: linux-pci@vger.kernel.org --- drivers/char/mem.c | 16 +++++++++++++++- drivers/pci/mmap.c | 3 +++ include/linux/ioport.h | 2 ++ 3 files changed, 20 insertions(+), 1 deletion(-)
diff --git a/drivers/char/mem.c b/drivers/char/mem.c index abd4ffdc8cde..5e58a326d4ee 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -810,6 +810,7 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig) }
static struct inode *devmem_inode; +static struct vfsmount *devmem_vfs_mount;
#ifdef CONFIG_IO_STRICT_DEVMEM void revoke_devmem(struct resource *res) @@ -843,6 +844,20 @@ void revoke_devmem(struct resource *res)
unmap_mapping_range(inode->i_mapping, res->start, resource_size(res), 1); } + +struct file *devmem_getfile(void) +{ + struct file *file; + + file = alloc_file_pseudo(devmem_inode, devmem_vfs_mount, "devmem", + O_RDWR, &kmem_fops); + if (IS_ERR(file)) + return NULL; + + file->f_mapping = devmem_indoe->i_mapping; + + return file; +} #endif
static int open_port(struct inode *inode, struct file *filp) @@ -1010,7 +1025,6 @@ static struct file_system_type devmem_fs_type = {
static int devmem_init_inode(void) { - static struct vfsmount *devmem_vfs_mount; static int devmem_fs_cnt; struct inode *inode; int rc; diff --git a/drivers/pci/mmap.c b/drivers/pci/mmap.c index b8c9011987f4..63786cc9c746 100644 --- a/drivers/pci/mmap.c +++ b/drivers/pci/mmap.c @@ -7,6 +7,7 @@ * Author: David Woodhouse dwmw2@infradead.org */
+#include <linux/file.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/pci.h> @@ -64,6 +65,8 @@ int pci_mmap_resource_range(struct pci_dev *pdev, int bar, vma->vm_pgoff += (pci_resource_start(pdev, bar) >> PAGE_SHIFT);
vma->vm_ops = &pci_phys_vm_ops; + fput(vma->vm_file); + vma->vm_file = devmem_getfile();
return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, vma->vm_end - vma->vm_start, diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 6c2b06fe8beb..83238cba19fe 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -304,8 +304,10 @@ struct resource *request_free_mem_region(struct resource *base,
#ifdef CONFIG_IO_STRICT_DEVMEM void revoke_devmem(struct resource *res); +struct file *devm_getfile(void); #else static inline void revoke_devmem(struct resource *res) { }; +static inline struct file *devmem_getfile(void) { return NULL; }; #endif
#endif /* __ASSEMBLY__ */