drm/i915: Use fault-injection to force the shrinker to run in live GTT tests

It is possible whilst allocating the page-directory tree for a ppgtt
bind that the shrinker may run and reap unused parts of the tree. If the
shrinker happens to remove a chunk of the tree that the
allocate_va_range has already processed, we may then try to insert into
the dangling tree. This test uses the fault-injection framework to force
the shrinker to be invoked before we allocate new pages, i.e. new chunks
of the PD tree.

References: https://bugs.freedesktop.org/show_bug.cgi?id=99295
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index a4d8cfd77c3ce1d43dec4388847b41a23585eb55..68ff072f8b764c08dae6aebe35c9abcb23b610c6 100644 (file)
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -65,6 +65,7 @@ config DRM_I915_SELFTEST
        bool "Enable selftests upon driver load"
        depends on DRM_I915
        default n
+       select FAULT_INJECTION
        select PRIME_NUMBERS
        help
          Choose this option to allow the driver to perform selftests upon

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f7ff2df0c0c52cd75081c2ca11443c0171e2bc16..80b653fb37228752bb9d0016320c3fcb91268118 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2485,6 +2485,8 @@ struct drm_i915_private {
        /* Used to save the pipe-to-encoder mapping for audio */
        struct intel_encoder *av_enc_map[I915_MAX_PIPES];
 
+       I915_SELFTEST_DECLARE(struct fault_attr vm_fault);
+
        /*
         * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
         * will be rejected. Instead look for a better place.

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 9daea3cd9cdc2f70817247d0e8dafe51ceb23604..f8ac69380a0fd6dd95c15dd308fcb6b30f0ff277 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -23,6 +23,9 @@
  *
  */
 
+#include <linux/slab.h> /* fault-inject.h is not standalone! */
+
+#include <linux/fault-inject.h>
 #include <linux/log2.h>
 #include <linux/random.h>
 #include <linux/seq_file.h>
@@ -345,6 +348,9 @@ static int __setup_page_dma(struct drm_i915_private *dev_priv,
 {
        struct device *kdev = &dev_priv->drm.pdev->dev;
 
+       if (I915_SELFTEST_ONLY(should_fail(&dev_priv->vm_fault, 1)))
+               i915_gem_shrink_all(dev_priv);
+
        p->page = alloc_page(flags);
        if (!p->page)
                return -ENOMEM;

diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index e43777b7221140365a5189bfa865d115bdc0c3ed..9d7d86f1733dbdde6c1f774489fddce2033ea235 100644 (file)
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -36,6 +36,8 @@ struct i915_selftest {
 };
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include <linux/fault-inject.h>
+
 extern struct i915_selftest i915_selftest;
 
 int i915_mock_selftests(void);

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index d0ec74671ef8298e605e5ddc376f691b08a315b3..2e571bbe98ae27388fc43eb9861e230ef88936dc 100644 (file)
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -271,11 +271,14 @@ static void close_object_list(struct list_head *objects,
                              struct i915_address_space *vm)
 {
        struct drm_i915_gem_object *obj, *on;
+       int ignored;
 
        list_for_each_entry_safe(obj, on, objects, st_link) {
                struct i915_vma *vma;
 
                vma = i915_vma_instance(obj, vm, NULL);
+               if (!IS_ERR(vma))
+                       ignored = i915_vma_unbind(vma);
                /* Only ppgtt vma may be closed before the object is freed */
                if (!IS_ERR(vma) && !i915_vma_is_ggtt(vma))
                        i915_vma_close(vma);
@@ -677,6 +680,95 @@ err_obj:
        return 0;
 }
 
+static int __shrink_hole(struct drm_i915_private *i915,
+                        struct i915_address_space *vm,
+                        u64 hole_start, u64 hole_end,
+                        unsigned long end_time)
+{
+       struct drm_i915_gem_object *obj;
+       unsigned long flags = PIN_OFFSET_FIXED | PIN_USER;
+       unsigned int order = 12;
+       LIST_HEAD(objects);
+       int err = 0;
+       u64 addr;
+
+       /* Keep creating larger objects until one cannot fit into the hole */
+       for (addr = hole_start; addr < hole_end; ) {
+               struct i915_vma *vma;
+               u64 size = BIT_ULL(order++);
+
+               size = min(size, hole_end - addr);
+               obj = fake_dma_object(i915, size);
+               if (IS_ERR(obj)) {
+                       err = PTR_ERR(obj);
+                       break;
+               }
+
+               list_add(&obj->st_link, &objects);
+
+               vma = i915_vma_instance(obj, vm, NULL);
+               if (IS_ERR(vma)) {
+                       err = PTR_ERR(vma);
+                       break;
+               }
+
+               GEM_BUG_ON(vma->size != size);
+
+               err = i915_vma_pin(vma, 0, 0, addr | flags);
+               if (err) {
+                       pr_err("%s failed to pin object at %llx + %llx in hole [%llx - %llx], with err=%d\n",
+                              __func__, addr, size, hole_start, hole_end, err);
+                       break;
+               }
+
+               if (!drm_mm_node_allocated(&vma->node) ||
+                   i915_vma_misplaced(vma, 0, 0, addr | flags)) {
+                       pr_err("%s incorrect at %llx + %llx\n",
+                              __func__, addr, size);
+                       i915_vma_unpin(vma);
+                       err = i915_vma_unbind(vma);
+                       err = -EINVAL;
+                       break;
+               }
+
+               i915_vma_unpin(vma);
+               addr += size;
+
+               if (igt_timeout(end_time,
+                               "%s timed out at ofset %llx [%llx - %llx]\n",
+                               __func__, addr, hole_start, hole_end)) {
+                       err = -EINTR;
+                       break;
+               }
+       }
+
+       close_object_list(&objects, vm);
+       return err;
+}
+
+static int shrink_hole(struct drm_i915_private *i915,
+                      struct i915_address_space *vm,
+                      u64 hole_start, u64 hole_end,
+                      unsigned long end_time)
+{
+       unsigned long prime;
+       int err;
+
+       i915->vm_fault.probability = 999;
+       atomic_set(&i915->vm_fault.times, -1);
+
+       for_each_prime_number_from(prime, 0, ULONG_MAX - 1) {
+               i915->vm_fault.interval = prime;
+               err = __shrink_hole(i915, vm, hole_start, hole_end, end_time);
+               if (err)
+                       break;
+       }
+
+       memset(&i915->vm_fault, 0, sizeof(i915->vm_fault));
+
+       return err;
+}
+
 static int exercise_ppgtt(struct drm_i915_private *dev_priv,
                          int (*func)(struct drm_i915_private *i915,
                                      struct i915_address_space *vm,
@@ -735,6 +827,11 @@ static int igt_ppgtt_lowlevel(void *arg)
        return exercise_ppgtt(arg, lowlevel_hole);
 }
 
+static int igt_ppgtt_shrink(void *arg)
+{
+       return exercise_ppgtt(arg, shrink_hole);
+}
+
 static int sort_holes(void *priv, struct list_head *A, struct list_head *B)
 {
        struct drm_mm_node *a = list_entry(A, typeof(*a), hole_stack);
@@ -812,6 +909,7 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915)
                SUBTEST(igt_ppgtt_drunk),
                SUBTEST(igt_ppgtt_walk),
                SUBTEST(igt_ppgtt_fill),
+               SUBTEST(igt_ppgtt_shrink),
                SUBTEST(igt_ggtt_lowlevel),
                SUBTEST(igt_ggtt_drunk),
                SUBTEST(igt_ggtt_walk),