=== Overview
arm64 has a feature called Top Byte Ignore, which allows to embed pointer tags into the top byte of each pointer. Userspace programs (such as HWASan, a memory debugging tool [1]) might use this feature and pass tagged user pointers to the kernel through syscalls or other interfaces.
Right now the kernel is already able to handle user faults with tagged pointers, due to these patches:
1. 81cddd65 ("arm64: traps: fix userspace cache maintenance emulation on a tagged pointer") 2. 7dcd9dd8 ("arm64: hw_breakpoint: fix watchpoint matching for tagged pointers") 3. 276e9327 ("arm64: entry: improve data abort handling of tagged pointers")
This patchset extends tagged pointer support to syscall arguments.
As per the proposed ABI change [3], tagged pointers are only allowed to be passed to syscalls when they point to memory ranges obtained by anonymous mmap() or sbrk() (see the patchset [3] for more details).
For non-memory syscalls this is done by untaging user pointers when the kernel performs pointer checking to find out whether the pointer comes from userspace (most notably in access_ok). The untagging is done only when the pointer is being checked, the tag is preserved as the pointer makes its way through the kernel and stays tagged when the kernel dereferences the pointer when perfoming user memory accesses.
The mmap and mremap (only new_addr) syscalls do not currently accept tagged addresses. Architectures may interpret the tag as a background colour for the corresponding vma.
Other memory syscalls (mprotect, etc.) don't do user memory accesses but rather deal with memory ranges, and untagged pointers are better suited to describe memory ranges internally. Thus for memory syscalls we untag pointers completely when they enter the kernel.
=== Other approaches
One of the alternative approaches to untagging that was considered is to completely strip the pointer tag as the pointer enters the kernel with some kind of a syscall wrapper, but that won't work with the countless number of different ioctl calls. With this approach we would need a custom wrapper for each ioctl variation, which doesn't seem practical.
An alternative approach to untagging pointers in memory syscalls prologues is to inspead allow tagged pointers to be passed to find_vma() (and other vma related functions) and untag them there. Unfortunately, a lot of find_vma() callers then compare or subtract the returned vma start and end fields against the pointer that was being searched. Thus this approach would still require changing all find_vma() callers.
=== Testing
The following testing approaches has been taken to find potential issues with user pointer untagging:
1. Static testing (with sparse [2] and separately with a custom static analyzer based on Clang) to track casts of __user pointers to integer types to find places where untagging needs to be done.
2. Static testing with grep to find parts of the kernel that call find_vma() (and other similar functions) or directly compare against vm_start/vm_end fields of vma.
3. Static testing with grep to find parts of the kernel that compare user pointers with TASK_SIZE or other similar consts and macros.
4. Dynamic testing: adding BUG_ON(has_tag(addr)) to find_vma() and running a modified syzkaller version that passes tagged pointers to the kernel.
Based on the results of the testing the requried patches have been added to the patchset.
=== Notes
This patchset is meant to be merged together with "arm64 relaxed ABI" [3].
This patchset is a prerequisite for ARM's memory tagging hardware feature support [4].
This patchset has been merged into the Pixel 2 & 3 kernel trees and is now being used to enable testing of Pixel phones with HWASan.
Thanks!
[1] http://clang.llvm.org/docs/HardwareAssistedAddressSanitizerDesign.html
[2] https://github.com/lucvoo/sparse-dev/commit/5f960cb10f56ec2017c128ef9d16060e...
[3] https://lkml.org/lkml/2019/6/12/745
[4] https://community.arm.com/processors/b/blog/posts/arm-a-profile-architecture...
=== History
Changes in v19: - Rebased onto 7b5cf701 (5.3-rc1+).
Changes in v18: - Reverted the selftest back to not using the LD_PRELOAD approach. - Added prctl(PR_SET_TAGGED_ADDR_CTRL) call to the selftest. - Reworded the patch descriptions to make them less oriented on arm64 only. - Catalin's patch: "I added a Kconfig option and dropped the prctl args zero check. There is some minor clean-up as well".
Changes in v17: - The "uaccess: add noop untagged_addr definition" patch is dropped, as it was merged into upstream named as "uaccess: add noop untagged_addr definition". - Merged "mm, arm64: untag user pointers in do_pages_move" into "mm, arm64: untag user pointers passed to memory syscalls". - Added "arm64: Introduce prctl() options to control the tagged user addresses ABI" patch from Catalin. - Add tags_lib.so to tools/testing/selftests/arm64/.gitignore. - Added a comment clarifying untagged in mremap. - Moved untagging back into mlx4_get_umem_mr() for the IB patch.
Changes in v16: - Moved untagging for memory syscalls from arm64 wrappers back to generic code. - Dropped untagging for the following memory syscalls: brk, mmap, munmap; mremap (only dropped for new_address); mmap_pgoff (not used on arm64); remap_file_pages (deprecated); shmat, shmdt (work on shared memory). - Changed kselftest to LD_PRELOAD a shared library that overrides malloc to return tagged pointers. - Rebased onto 5.2-rc3.
Changes in v15: - Removed unnecessary untagging from radeon_ttm_tt_set_userptr(). - Removed unnecessary untagging from amdgpu_ttm_tt_set_userptr(). - Moved untagging to validate_range() in userfaultfd code. - Moved untagging to ib_uverbs_(re)reg_mr() from mlx4_get_umem_mr(). - Rebased onto 5.1.
Changes in v14: - Moved untagging for most memory syscalls to an arm64 specific implementation, instead of doing that in the common code. - Dropped "net, arm64: untag user pointers in tcp_zerocopy_receive", since the provided user pointers don't come from an anonymous map and thus are not covered by this ABI relaxation. - Dropped "kernel, arm64: untag user pointers in prctl_set_mm*". - Moved untagging from __check_mem_type() to tee_shm_register(). - Updated untagging for the amdgpu and radeon drivers to cover the MMU notifier, as suggested by Felix. - Since this ABI relaxation doesn't actually allow tagged instruction pointers, dropped the following patches: - Dropped "tracing, arm64: untag user pointers in seq_print_user_ip". - Dropped "uprobes, arm64: untag user pointers in find_active_uprobe". - Dropped "bpf, arm64: untag user pointers in stack_map_get_build_id_offset". - Rebased onto 5.1-rc7 (37624b58).
Changes in v13: - Simplified untagging in tcp_zerocopy_receive(). - Looked at find_vma() callers in drivers/, which allowed to identify a few other places where untagging is needed. - Added patch "mm, arm64: untag user pointers in get_vaddr_frames". - Added patch "drm/amdgpu, arm64: untag user pointers in amdgpu_ttm_tt_get_user_pages". - Added patch "drm/radeon, arm64: untag user pointers in radeon_ttm_tt_pin_userptr". - Added patch "IB/mlx4, arm64: untag user pointers in mlx4_get_umem_mr". - Added patch "media/v4l2-core, arm64: untag user pointers in videobuf_dma_contig_user_get". - Added patch "tee/optee, arm64: untag user pointers in check_mem_type". - Added patch "vfio/type1, arm64: untag user pointers".
Changes in v12: - Changed untagging in tcp_zerocopy_receive() to also untag zc->address. - Fixed untagging in prctl_set_mm* to only untag pointers for vma lookups and validity checks, but leave them as is for actual user space accesses. - Updated the link to the v2 of the "arm64 relaxed ABI" patchset [3]. - Dropped the documentation patch, as the "arm64 relaxed ABI" patchset [3] handles that.
Changes in v11: - Added "uprobes, arm64: untag user pointers in find_active_uprobe" patch. - Added "bpf, arm64: untag user pointers in stack_map_get_build_id_offset" patch. - Fixed "tracing, arm64: untag user pointers in seq_print_user_ip" to correctly perform subtration with a tagged addr. - Moved untagged_addr() from SYSCALL_DEFINE3(mprotect) and SYSCALL_DEFINE4(pkey_mprotect) to do_mprotect_pkey(). - Moved untagged_addr() definition for other arches from include/linux/memory.h to include/linux/mm.h. - Changed untagging in strn*_user() to perform userspace accesses through tagged pointers. - Updated the documentation to mention that passing tagged pointers to memory syscalls is allowed. - Updated the test to use malloc'ed memory instead of stack memory.
Changes in v10: - Added "mm, arm64: untag user pointers passed to memory syscalls" back. - New patch "fs, arm64: untag user pointers in fs/userfaultfd.c". - New patch "net, arm64: untag user pointers in tcp_zerocopy_receive". - New patch "kernel, arm64: untag user pointers in prctl_set_mm*". - New patch "tracing, arm64: untag user pointers in seq_print_user_ip".
Changes in v9: - Rebased onto 4.20-rc6. - Used u64 instead of __u64 in type casts in the untagged_addr macro for arm64. - Added braces around (addr) in the untagged_addr macro for other arches.
Changes in v8: - Rebased onto 65102238 (4.20-rc1). - Added a note to the cover letter on why syscall wrappers/shims that untag user pointers won't work. - Added a note to the cover letter that this patchset has been merged into the Pixel 2 kernel tree. - Documentation fixes, in particular added a list of syscalls that don't support tagged user pointers.
Changes in v7: - Rebased onto 17b57b18 (4.19-rc6). - Dropped the "arm64: untag user address in __do_user_fault" patch, since the existing patches already handle user faults properly. - Dropped the "usb, arm64: untag user addresses in devio" patch, since the passed pointer must come from a vma and therefore be untagged. - Dropped the "arm64: annotate user pointers casts detected by sparse" patch (see the discussion to the replies of the v6 of this patchset). - Added more context to the cover letter. - Updated Documentation/arm64/tagged-pointers.txt.
Changes in v6: - Added annotations for user pointer casts found by sparse. - Rebased onto 050cdc6c (4.19-rc1+).
Changes in v5: - Added 3 new patches that add untagging to places found with static analysis. - Rebased onto 44c929e1 (4.18-rc8).
Changes in v4: - Added a selftest for checking that passing tagged pointers to the kernel succeeds. - Rebased onto 81e97f013 (4.18-rc1+).
Changes in v3: - Rebased onto e5c51f30 (4.17-rc6+). - Added linux-arch@ to the list of recipients.
Changes in v2: - Rebased onto 2d618bdf (4.17-rc3+). - Removed excessive untagging in gup.c. - Removed untagging pointers returned from __uaccess_mask_ptr.
Changes in v1: - Rebased onto 4.17-rc1.
Changes in RFC v2: - Added "#ifndef untagged_addr..." fallback in linux/uaccess.h instead of defining it for each arch individually. - Updated Documentation/arm64/tagged-pointers.txt. - Dropped "mm, arm64: untag user addresses in memory syscalls". - Rebased onto 3eb2ce82 (4.16-rc7).
Signed-off-by: Andrey Konovalov andreyknvl@google.com
Andrey Konovalov (14): arm64: untag user pointers in access_ok and __uaccess_mask_ptr lib: untag user pointers in strn*_user mm: untag user pointers passed to memory syscalls mm: untag user pointers in mm/gup.c mm: untag user pointers in get_vaddr_frames fs/namespace: untag user pointers in copy_mount_options userfaultfd: untag user pointers drm/amdgpu: untag user pointers drm/radeon: untag user pointers in radeon_gem_userptr_ioctl IB/mlx4: untag user pointers in mlx4_get_umem_mr media/v4l2-core: untag user pointers in videobuf_dma_contig_user_get tee/shm: untag user pointers in tee_shm_register vfio/type1: untag user pointers in vaddr_get_pfn selftests, arm64: add a selftest for passing tagged pointers to kernel
Catalin Marinas (1): arm64: Introduce prctl() options to control the tagged user addresses ABI
arch/arm64/Kconfig | 9 +++ arch/arm64/include/asm/processor.h | 8 ++ arch/arm64/include/asm/thread_info.h | 1 + arch/arm64/include/asm/uaccess.h | 12 ++- arch/arm64/kernel/process.c | 73 +++++++++++++++++++ .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 + drivers/gpu/drm/radeon/radeon_gem.c | 2 + drivers/infiniband/hw/mlx4/mr.c | 7 +- drivers/media/v4l2-core/videobuf-dma-contig.c | 9 ++- drivers/tee/tee_shm.c | 1 + drivers/vfio/vfio_iommu_type1.c | 2 + fs/namespace.c | 2 +- fs/userfaultfd.c | 22 +++--- include/uapi/linux/prctl.h | 5 ++ kernel/sys.c | 12 +++ lib/strncpy_from_user.c | 3 +- lib/strnlen_user.c | 3 +- mm/frame_vector.c | 2 + mm/gup.c | 4 + mm/madvise.c | 2 + mm/mempolicy.c | 3 + mm/migrate.c | 2 +- mm/mincore.c | 2 + mm/mlock.c | 4 + mm/mprotect.c | 2 + mm/mremap.c | 7 ++ mm/msync.c | 2 + tools/testing/selftests/arm64/.gitignore | 1 + tools/testing/selftests/arm64/Makefile | 11 +++ .../testing/selftests/arm64/run_tags_test.sh | 12 +++ tools/testing/selftests/arm64/tags_test.c | 29 ++++++++ 32 files changed, 233 insertions(+), 25 deletions(-) create mode 100644 tools/testing/selftests/arm64/.gitignore create mode 100644 tools/testing/selftests/arm64/Makefile create mode 100755 tools/testing/selftests/arm64/run_tags_test.sh create mode 100644 tools/testing/selftests/arm64/tags_test.c
This patch is a part of a series that extends kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.
In amdgpu_gem_userptr_ioctl() and amdgpu_amdkfd_gpuvm.c/init_user_pages() an MMU notifier is set up with a (tagged) userspace pointer. The untagged address should be used so that MMU notifiers for the untagged address get correctly matched up with the right BO. This patch untag user pointers in amdgpu_gem_userptr_ioctl() for the GEM case and in amdgpu_amdkfd_gpuvm_ alloc_memory_of_gpu() for the KFD case. This also makes sure that an untagged pointer is passed to amdgpu_ttm_tt_get_user_pages(), which uses it for vma lookups.
Reviewed-by: Kees Cook keescook@chromium.org Suggested-by: Felix Kuehling Felix.Kuehling@amd.com Acked-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Andrey Konovalov andreyknvl@google.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 1d3ee9c42f7e..00468ebf8b76 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1103,7 +1103,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( alloc_flags = 0; if (!offset || !*offset) return -EINVAL; - user_addr = *offset; + user_addr = untagged_addr(*offset); } else if (flags & (ALLOC_MEM_FLAGS_DOORBELL | ALLOC_MEM_FLAGS_MMIO_REMAP)) { domain = AMDGPU_GEM_DOMAIN_GTT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 939f8305511b..d7855842fd51 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -291,6 +291,8 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, uint32_t handle; int r;
+ args->addr = untagged_addr(args->addr); + if (offset_in_page(args->addr | args->size)) return -EINVAL;
This patch is a part of a series that extends kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.
In radeon_gem_userptr_ioctl() an MMU notifier is set up with a (tagged) userspace pointer. The untagged address should be used so that MMU notifiers for the untagged address get correctly matched up with the right BO. This funcation also calls radeon_ttm_tt_pin_userptr(), which uses provided user pointers for vma lookups, which can only by done with untagged pointers.
This patch untags user pointers in radeon_gem_userptr_ioctl().
Reviewed-by: Khalid Aziz khalid.aziz@oracle.com Reviewed-by: Kees Cook keescook@chromium.org Suggested-by: Felix Kuehling Felix.Kuehling@amd.com Acked-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Andrey Konovalov andreyknvl@google.com --- drivers/gpu/drm/radeon/radeon_gem.c | 2 ++ 1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index d8bc5d2dfd61..89353098b627 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -296,6 +296,8 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data, uint32_t handle; int r;
+ args->addr = untagged_addr(args->addr); + if (offset_in_page(args->addr | args->size)) return -EINVAL;
This patch is a part of a series that extends kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.
videobuf_dma_contig_user_get() uses provided user pointers for vma lookups, which can only by done with untagged pointers.
Untag the pointers in this function.
Reviewed-by: Khalid Aziz khalid.aziz@oracle.com Reviewed-by: Kees Cook keescook@chromium.org Acked-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Andrey Konovalov andreyknvl@google.com --- drivers/media/v4l2-core/videobuf-dma-contig.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c index 76b4ac7b1678..aeb2f497c683 100644 --- a/drivers/media/v4l2-core/videobuf-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf-dma-contig.c @@ -157,6 +157,7 @@ static void videobuf_dma_contig_user_put(struct videobuf_dma_contig_memory *mem) static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem, struct videobuf_buffer *vb) { + unsigned long untagged_baddr = untagged_addr(vb->baddr); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long prev_pfn, this_pfn; @@ -164,22 +165,22 @@ static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem, unsigned int offset; int ret;
- offset = vb->baddr & ~PAGE_MASK; + offset = untagged_baddr & ~PAGE_MASK; mem->size = PAGE_ALIGN(vb->size + offset); ret = -EINVAL;
down_read(&mm->mmap_sem);
- vma = find_vma(mm, vb->baddr); + vma = find_vma(mm, untagged_baddr); if (!vma) goto out_up;
- if ((vb->baddr + mem->size) > vma->vm_end) + if ((untagged_baddr + mem->size) > vma->vm_end) goto out_up;
pages_done = 0; prev_pfn = 0; /* kill warning */ - user_address = vb->baddr; + user_address = untagged_baddr;
while (pages_done < (mem->size >> PAGE_SHIFT)) { ret = follow_pfn(vma, user_address, &this_pfn);
On 31/07/2019 17:50, Dave Hansen wrote:
On 7/23/19 10:58 AM, Andrey Konovalov wrote:
The mmap and mremap (only new_addr) syscalls do not currently accept tagged addresses. Architectures may interpret the tag as a background colour for the corresponding vma.
What the heck is a "background colour"? :)
Good point, this is some jargon that we started using for MTE, the idea being that the kernel could set a tag value (specified during mmap()) as "background colour" for anonymous pages allocated in that range.
Anyway, this patch series is not about MTE. Andrey, for v20 (if any), I think it's best to drop this last sentence to avoid any confusion.
Kevin
On Thu, Aug 1, 2019 at 2:11 PM Kevin Brodsky kevin.brodsky@arm.com wrote:
On 31/07/2019 17:50, Dave Hansen wrote:
On 7/23/19 10:58 AM, Andrey Konovalov wrote:
The mmap and mremap (only new_addr) syscalls do not currently accept tagged addresses. Architectures may interpret the tag as a background colour for the corresponding vma.
What the heck is a "background colour"? :)
Good point, this is some jargon that we started using for MTE, the idea being that the kernel could set a tag value (specified during mmap()) as "background colour" for anonymous pages allocated in that range.
Anyway, this patch series is not about MTE. Andrey, for v20 (if any), I think it's best to drop this last sentence to avoid any confusion.
Sure, thanks!
Kevin
On 8/1/19 5:48 AM, Andrey Konovalov wrote:
On Thu, Aug 1, 2019 at 2:11 PM Kevin Brodsky kevin.brodsky@arm.com wrote:
On 31/07/2019 17:50, Dave Hansen wrote:
On 7/23/19 10:58 AM, Andrey Konovalov wrote:
The mmap and mremap (only new_addr) syscalls do not currently accept tagged addresses. Architectures may interpret the tag as a background colour for the corresponding vma.
What the heck is a "background colour"? :)
Good point, this is some jargon that we started using for MTE, the idea being that the kernel could set a tag value (specified during mmap()) as "background colour" for anonymous pages allocated in that range.
Anyway, this patch series is not about MTE. Andrey, for v20 (if any), I think it's best to drop this last sentence to avoid any confusion.
Sure, thanks!
OK, but what does that mean for tagged addresses getting passed to mmap/mremap? That sentence read to me like "architectures might allow tags for ...something...". So do we accept tagged addresses into those syscalls?
On Thu, Aug 01, 2019 at 08:36:47AM -0700, Dave Hansen wrote:
On 8/1/19 5:48 AM, Andrey Konovalov wrote:
On Thu, Aug 1, 2019 at 2:11 PM Kevin Brodsky kevin.brodsky@arm.com wrote:
On 31/07/2019 17:50, Dave Hansen wrote:
On 7/23/19 10:58 AM, Andrey Konovalov wrote:
The mmap and mremap (only new_addr) syscalls do not currently accept tagged addresses. Architectures may interpret the tag as a background colour for the corresponding vma.
What the heck is a "background colour"? :)
Good point, this is some jargon that we started using for MTE, the idea being that the kernel could set a tag value (specified during mmap()) as "background colour" for anonymous pages allocated in that range.
Anyway, this patch series is not about MTE. Andrey, for v20 (if any), I think it's best to drop this last sentence to avoid any confusion.
Indeed, the part with the "background colour" and even the "currently" adverb should be dropped.
Also, if we merge the patches via different trees anyway, I don't think there is a need for Andrey to integrate them with his series. We can pick them up directly in the arm64 tree (once the review finished).
OK, but what does that mean for tagged addresses getting passed to mmap/mremap? That sentence read to me like "architectures might allow tags for ...something...". So do we accept tagged addresses into those syscalls?
If mmap() does not return a tagged address, the reasoning is that it should not accept one as an address hint (with or without MAP_FIXED). Note that these docs should only describe the top-byte-ignore ABI while leaving the memory tagging for a future patchset.
In that future patchset, we may want to update the mmap() ABI to allow, only in conjunction with PROT_MTE, a tagged pointer as an address argument. In such case mmap() will return a tagged address and the pages pre-coloured (on fault) with the tag requested by the user. As I said, that's to be discussed later in the year.
dri-devel@lists.freedesktop.org
-
Andrey Konovalov -
Catalin Marinas -
Dave Hansen -
Kevin Brodsky