Resources of swapped objects remains on the TTM_PL_SYSTEM manager's
LRU list, which is bad for the LRU walk efficiency.
Rename the device-wide "pinned" list to "unevictable" and move
also resources of swapped-out objects to that list.
An alternative would be to create an "UNEVICTABLE" priority to
be able to keep the pinned- and swapped objects on their
respective manager's LRU without affecting the LRU walk efficiency.
v2:
- Remove a bogus WARN_ON (Christian König)
- Update ttm_resource_[add|del] bulk move (Christian König)
- Fix TTM KUNIT tests (Intel CI)
v3:
- Check for non-NULL bo->resource in ttm_bo_populate().
v4:
- Don't move to LRU tail during swapout until the resource
is properly swapped or there was a swapout failure.
(Intel Ci)
- Add a newline after checkpatch check.
v5:
- Introduce ttm_resource_is_swapped() to avoid a corner-case where
a newly created resource was considered swapped. (Intel CI)
v6:
- Move an assert.
Cc: Christian König <christian.koenig@amd.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240911121859.85387-2-thomas.hellstrom@linux.intel.com
To be able to handle list unlocking while traversing the LRU
list, we want the iterators not only to point to the next
position of the list traversal, but to insert themselves as
list nodes at that point to work around the fact that the
next node might otherwise disappear from the list while
the iterator is pointing to it.
These list nodes need to be easily distinguishable from other
list nodes so that others traversing the list can skip
over them.
So declare a struct ttm_lru_item, with a struct list_head member
and a type enum. This will slightly increase the size of a
struct ttm_resource.
Changes in previous series:
- Update enum ttm_lru_item_type documentation.
v3:
- Introduce ttm_lru_first_res_or_null()
(Christian König, Thomas Hellström)
v5:
- Update also the TTM test code (Xe CI).
Cc: Christian König <christian.koenig@amd.com>
Cc: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240705153206.68526-2-thomas.hellstrom@linux.intel.com
Signed-off-by: Christian König <christian.koenig@amd.com>
make allmodconfig && make W=1 C=1 reports:
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/gpu/drm/ttm/tests/ttm_device_test.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/gpu/drm/ttm/tests/ttm_pool_test.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/gpu/drm/ttm/tests/ttm_resource_test.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/gpu/drm/ttm/tests/ttm_tt_test.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/gpu/drm/ttm/tests/ttm_bo_test.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/gpu/drm/ttm/tests/ttm_mock_manager.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.o
Add the missing invocations of the MODULE_DESCRIPTION() macro.
Signed-off-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Acked-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240624-md-drivers-gpu-drm-ttm-tests-v2-1-76bb765e19c9@quicinc.com
Signed-off-by: Christian König <christian.koenig@amd.com>
BOs in a bulk move have to share the same reservation object. That is
not the case in the ttm_bo_unreserve_bulk subtest. Update
ttm_bo_kunit_init() helper to accept dma_resv object so we can define
buffer objects that share the same resv. Update calls to that helper
accordingly.
Fixes: 995279d280 ("drm/ttm/tests: Add tests for ttm_bo functions")
Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Karolina Stolarek <karolina.stolarek@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/c5bd2df114781b4eb5c1e8295b2ae4ac2c30a179.1718192625.git.karolina.stolarek@intel.com
PREEMPT_RT has a different locking implementation for ww_mutex. The
base mutex of struct ww_mutex is declared as struct WW_MUTEX_BASE. The
latter is defined as `mutex' for non-PREEMPT_RT builds and `rt_mutex'
for PREEMPT_RT builds.
Using mutex_lock() directly on the base mutex in
ttm_bo_reserve_deadlock() leads to compile error on PREEMPT_RT.
The locking-selftest has its own defines to deal with this and it is
probably best to defines the needed one within the test program since
their usefulness is limited outside of well known selftests.
Provide ww_mutex_base_lock() which points to the correct function for
PREEMPT_RT and non-PREEMPT_RT builds.
Fixes: 995279d280 ("drm/ttm/tests: Add tests for ttm_bo functions")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619144630.4DliKOmr@linutronix.de
