User is reporting what smells like notifier vs folio deadlock, where
migrate_pages_batch() on core kernel side is holding folio lock(s) and
then interacting with the mappings of it, however those mappings are
tied to some userptr, which means calling into the notifier callback and
grabbing the notifier lock. With perfect timing it looks possible that
the pages we pulled from the hmm fault can get sniped by
migrate_pages_batch() at the same time that we are holding the notifier
lock to mark the pages as accessed/dirty, but at this point we also want
to grab the folio locks(s) to mark them as dirty, but if they are
contended from notifier/migrate_pages_batch side then we deadlock since
folio lock won't be dropped until we drop the notifier lock.
Fortunately the mark_page_accessed/dirty is not really needed in the
first place it seems and should have already been done by hmm fault, so
just remove it.
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4765
Fixes: 0a98219bcc ("drm/xe/hmm: Don't dereference struct page pointers without notifier lock")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250414132539.26654-2-matthew.auld@intel.com
(cherry picked from commit bd7c0cb695)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
The assert incorrectly checks the total length processed which
can in fact be greater than the number of pages. Fix.
Fixes: 0a98219bcc ("drm/xe/hmm: Don't dereference struct page pointers without notifier lock")
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250307100109.21397-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 70e5043ba8)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
If userptr pages are freed after a call to the xe mmu notifier,
the device will not be blocked out from theoretically accessing
these pages unless they are also unmapped from the iommu, and
this violates some aspects of the iommu-imposed security.
Ensure that userptrs are unmapped in the mmu notifier to
mitigate this. A naive attempt would try to free the sg table, but
the sg table itself may be accessed by a concurrent bind
operation, so settle for only unmapping.
v3:
- Update lockdep asserts.
- Fix a typo (Matthew Auld)
Fixes: 81e058a3e7 ("drm/xe: Introduce helper to populate userptr")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304173342.22009-4-thomas.hellstrom@linux.intel.com
(cherry picked from commit ba767b9d01)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
The pnfs that we obtain from hmm_range_fault() point to pages that
we don't have a reference on, and the guarantee that they are still
in the cpu page-tables is that the notifier lock must be held and the
notifier seqno is still valid.
So while building the sg table and marking the pages accesses / dirty
we need to hold this lock with a validated seqno.
However, the lock is reclaim tainted which makes
sg_alloc_table_from_pages_segment() unusable, since it internally
allocates memory.
Instead build the sg-table manually. For the non-iommu case
this might lead to fewer coalesces, but if that's a problem it can
be fixed up later in the resource cursor code. For the iommu case,
the whole sg-table may still be coalesced to a single contigous
device va region.
This avoids marking pages that we don't own dirty and accessed, and
it also avoid dereferencing struct pages that we don't own.
v2:
- Use assert to check whether hmm pfns are valid (Matthew Auld)
- Take into account that large pages may cross range boundaries
(Matthew Auld)
v3:
- Don't unnecessarily check for a non-freed sg-table. (Matthew Auld)
- Add a missing up_read() in an error path. (Matthew Auld)
Fixes: 81e058a3e7 ("drm/xe: Introduce helper to populate userptr")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304173342.22009-3-thomas.hellstrom@linux.intel.com
(cherry picked from commit ea3e66d280)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Add proper #ifndef around the xe_hmm.h header, proper spacing
and since the documentation mostly follows kerneldoc format,
make it kerneldoc. Also prepare for upcoming -stable fixes.
Fixes: 81e058a3e7 ("drm/xe: Introduce helper to populate userptr")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304173342.22009-2-thomas.hellstrom@linux.intel.com
(cherry picked from commit bbe2b06b55)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Currently we just leave it uninitialised, which at first looks harmless,
however we also don't zero out the pfn array, and with pfn_flags_mask
the idea is to be able set individual flags for a given range of pfn or
completely ignore them, outside of default_flags. So here we end up with
pfn[i] & pfn_flags_mask, and if both are uninitialised we might get back
an unexpected flags value, like asking for read only with default_flags,
but getting back write on top, leading to potentially bogus behaviour.
To fix this ensure we zero the pfn_flags_mask, such that hmm only
considers the default_flags and not also the initial pfn[i] value.
v2 (Thomas):
- Prefer proper initializer.
Fixes: 81e058a3e7 ("drm/xe: Introduce helper to populate userptr")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226174748.294285-2-matthew.auld@intel.com
(cherry picked from commit dd8c01e42f)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Introduce a helper function xe_userptr_populate_range to populate
a userptr range. This functions calls hmm_range_fault to read
CPU page tables and populate all pfns/pages of this virtual address
range. For system memory page, dma-mapping is performed
to get a dma-address which can be used later for GPU to access pages.
v1: Address review comments:
separate a npage_in_range function (Matt)
reparameterize function xe_userptr_populate_range function (Matt)
move mmu_interval_read_begin() call into while loop (Thomas)
s/mark_range_accessed/xe_mark_range_accessed (Thomas)
use set_page_dirty_lock (vs set_page_dirty) (Thomas)
move a few checking in xe_vma_userptr_pin_pages to hmm.c (Matt)
v2: Remove device private page support. Only support system
pages for now. use dma-map-sg rather than dma-map-page (Matt/Thomas)
v3: Address review comments:
Squash patch "drm/xe: Introduce a helper to free sg table" to current
patch (Matt)
start and end addresses are already page aligned (Matt)
Do mmap_read_lock and mmap_read_unlock for hmm_range_fault incase of
non system allocator call. (Matt)
Drop kthread_use_mm and kthread_unuse_mm. (Matt)
No need of kernel-doc for static functions.(Matt)
Modify function names. (Matt)
Free sgtable incase of dma_map_sgtable failure.(Matt)
Modify loop for hmm_range_fault.(Matt)
v4: Remove the dummy function for xe_hmm_userptr_populate_range
since CONFIG_HMM_MIRROR is needed. (Matt)
Change variable names start/end to userptr_start/userptr_end.(Matt)
v5: Remove device private page support info from commit message. Since
the patch doesn't support device page handling. (Thomas)
Signed-off-by: Oak Zeng <oak.zeng@intel.com>
Co-developed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@intel.com>
Cc: Brian Welty <brian.welty@intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240412095237.1048599-2-himal.prasad.ghimiray@intel.com
