summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gem/selftests
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/i915/gem/selftests')
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/huge_pages.c187
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c42
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c13
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c274
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c8
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c66
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c141
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c141
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h16
9 files changed, 485 insertions, 403 deletions
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index b74729b6f353..8de83c6d81f5 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -10,6 +10,8 @@
#include "gem/i915_gem_pm.h"
+#include "gt/intel_gt.h"
+
#include "igt_gem_utils.h"
#include "mock_context.h"
@@ -877,126 +879,22 @@ out_object_put:
return err;
}
-static struct i915_vma *
-gpu_write_dw(struct i915_vma *vma, u64 offset, u32 val)
-{
- struct drm_i915_private *i915 = vma->vm->i915;
- const int gen = INTEL_GEN(i915);
- unsigned int count = vma->size >> PAGE_SHIFT;
- struct drm_i915_gem_object *obj;
- struct i915_vma *batch;
- unsigned int size;
- u32 *cmd;
- int n;
- int err;
-
- size = (1 + 4 * count) * sizeof(u32);
- size = round_up(size, PAGE_SIZE);
- obj = i915_gem_object_create_internal(i915, size);
- if (IS_ERR(obj))
- return ERR_CAST(obj);
-
- cmd = i915_gem_object_pin_map(obj, I915_MAP_WC);
- if (IS_ERR(cmd)) {
- err = PTR_ERR(cmd);
- goto err;
- }
-
- offset += vma->node.start;
-
- for (n = 0; n < count; n++) {
- if (gen >= 8) {
- *cmd++ = MI_STORE_DWORD_IMM_GEN4;
- *cmd++ = lower_32_bits(offset);
- *cmd++ = upper_32_bits(offset);
- *cmd++ = val;
- } else if (gen >= 4) {
- *cmd++ = MI_STORE_DWORD_IMM_GEN4 |
- (gen < 6 ? MI_USE_GGTT : 0);
- *cmd++ = 0;
- *cmd++ = offset;
- *cmd++ = val;
- } else {
- *cmd++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
- *cmd++ = offset;
- *cmd++ = val;
- }
-
- offset += PAGE_SIZE;
- }
-
- *cmd = MI_BATCH_BUFFER_END;
- i915_gem_chipset_flush(i915);
-
- i915_gem_object_unpin_map(obj);
-
- batch = i915_vma_instance(obj, vma->vm, NULL);
- if (IS_ERR(batch)) {
- err = PTR_ERR(batch);
- goto err;
- }
-
- err = i915_vma_pin(batch, 0, 0, PIN_USER);
- if (err)
- goto err;
-
- return batch;
-
-err:
- i915_gem_object_put(obj);
-
- return ERR_PTR(err);
-}
-
static int gpu_write(struct i915_vma *vma,
struct i915_gem_context *ctx,
struct intel_engine_cs *engine,
- u32 dword,
- u32 value)
+ u32 dw,
+ u32 val)
{
- struct i915_request *rq;
- struct i915_vma *batch;
int err;
- GEM_BUG_ON(!intel_engine_can_store_dword(engine));
-
- batch = gpu_write_dw(vma, dword * sizeof(u32), value);
- if (IS_ERR(batch))
- return PTR_ERR(batch);
-
- rq = igt_request_alloc(ctx, engine);
- if (IS_ERR(rq)) {
- err = PTR_ERR(rq);
- goto err_batch;
- }
-
- i915_vma_lock(batch);
- err = i915_vma_move_to_active(batch, rq, 0);
- i915_vma_unlock(batch);
+ i915_gem_object_lock(vma->obj);
+ err = i915_gem_object_set_to_gtt_domain(vma->obj, true);
+ i915_gem_object_unlock(vma->obj);
if (err)
- goto err_request;
-
- i915_vma_lock(vma);
- err = i915_gem_object_set_to_gtt_domain(vma->obj, false);
- if (err == 0)
- err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
- i915_vma_unlock(vma);
- if (err)
- goto err_request;
-
- err = engine->emit_bb_start(rq,
- batch->node.start, batch->node.size,
- 0);
-err_request:
- if (err)
- i915_request_skip(rq, err);
- i915_request_add(rq);
-err_batch:
- i915_vma_unpin(batch);
- i915_vma_close(batch);
- i915_vma_put(batch);
+ return err;
- return err;
+ return igt_gpu_fill_dw(vma, ctx, engine, dw * sizeof(u32),
+ vma->size >> PAGE_SHIFT, val);
}
static int cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
@@ -1037,8 +935,7 @@ static int __igt_write_huge(struct i915_gem_context *ctx,
u64 size, u64 offset,
u32 dword, u32 val)
{
- struct drm_i915_private *i915 = to_i915(obj->base.dev);
- struct i915_address_space *vm = ctx->vm ?: &i915->ggtt.vm;
+ struct i915_address_space *vm = ctx->vm ?: &engine->gt->ggtt->vm;
unsigned int flags = PIN_USER | PIN_OFFSET_FIXED;
struct i915_vma *vma;
int err;
@@ -1421,6 +1318,9 @@ static int igt_ppgtt_pin_update(void *arg)
struct drm_i915_gem_object *obj;
struct i915_vma *vma;
unsigned int flags = PIN_USER | PIN_OFFSET_FIXED;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+ unsigned int n;
int first, last;
int err;
@@ -1518,11 +1418,20 @@ static int igt_ppgtt_pin_update(void *arg)
* land in the now stale 2M page.
*/
- err = gpu_write(vma, ctx, dev_priv->engine[RCS0], 0, 0xdeadbeaf);
- if (err)
- goto out_unpin;
+ n = 0;
+ for_each_engine(engine, dev_priv, id) {
+ if (!intel_engine_can_store_dword(engine))
+ continue;
- err = cpu_check(obj, 0, 0xdeadbeaf);
+ err = gpu_write(vma, ctx, engine, n++, 0xdeadbeaf);
+ if (err)
+ goto out_unpin;
+ }
+ while (n--) {
+ err = cpu_check(obj, n, 0xdeadbeaf);
+ if (err)
+ goto out_unpin;
+ }
out_unpin:
i915_vma_unpin(vma);
@@ -1598,8 +1507,11 @@ static int igt_shrink_thp(void *arg)
struct drm_i915_private *i915 = ctx->i915;
struct i915_address_space *vm = ctx->vm ?: &i915->ggtt.vm;
struct drm_i915_gem_object *obj;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
struct i915_vma *vma;
unsigned int flags = PIN_USER;
+ unsigned int n;
int err;
/*
@@ -1635,9 +1547,15 @@ static int igt_shrink_thp(void *arg)
if (err)
goto out_unpin;
- err = gpu_write(vma, ctx, i915->engine[RCS0], 0, 0xdeadbeaf);
- if (err)
- goto out_unpin;
+ n = 0;
+ for_each_engine(engine, i915, id) {
+ if (!intel_engine_can_store_dword(engine))
+ continue;
+
+ err = gpu_write(vma, ctx, engine, n++, 0xdeadbeaf);
+ if (err)
+ goto out_unpin;
+ }
i915_vma_unpin(vma);
@@ -1662,7 +1580,12 @@ static int igt_shrink_thp(void *arg)
if (err)
goto out_close;
- err = cpu_check(obj, 0, 0xdeadbeaf);
+ while (n--) {
+ err = cpu_check(obj, n, 0xdeadbeaf);
+ if (err)
+ goto out_unpin;
+ }
+
out_unpin:
i915_vma_unpin(vma);
@@ -1726,7 +1649,7 @@ out_unlock:
return err;
}
-int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
+int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
{
static const struct i915_subtest tests[] = {
SUBTEST(igt_shrink_thp),
@@ -1741,22 +1664,22 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
intel_wakeref_t wakeref;
int err;
- if (!HAS_PPGTT(dev_priv)) {
+ if (!HAS_PPGTT(i915)) {
pr_info("PPGTT not supported, skipping live-selftests\n");
return 0;
}
- if (i915_terminally_wedged(dev_priv))
+ if (intel_gt_is_wedged(&i915->gt))
return 0;
- file = mock_file(dev_priv);
+ file = mock_file(i915);
if (IS_ERR(file))
return PTR_ERR(file);
- mutex_lock(&dev_priv->drm.struct_mutex);
- wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
+ mutex_lock(&i915->drm.struct_mutex);
+ wakeref = intel_runtime_pm_get(&i915->runtime_pm);
- ctx = live_context(dev_priv, file);
+ ctx = live_context(i915, file);
if (IS_ERR(ctx)) {
err = PTR_ERR(ctx);
goto out_unlock;
@@ -1768,10 +1691,10 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
err = i915_subtests(tests, ctx);
out_unlock:
- intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
- mutex_unlock(&dev_priv->drm.struct_mutex);
+ intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+ mutex_unlock(&i915->drm.struct_mutex);
- mock_file_free(dev_priv, file);
+ mock_file_free(i915, file);
return err;
}
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index f3a5eb807c1c..d8804a847945 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -5,14 +5,17 @@
#include "i915_selftest.h"
+#include "gt/intel_gt.h"
+
#include "selftests/igt_flush_test.h"
#include "selftests/mock_drm.h"
+#include "huge_gem_object.h"
#include "mock_context.h"
static int igt_client_fill(void *arg)
{
- struct intel_context *ce = arg;
- struct drm_i915_private *i915 = ce->gem_context->i915;
+ struct drm_i915_private *i915 = arg;
+ struct intel_context *ce = i915->engine[BCS0]->kernel_context;
struct drm_i915_gem_object *obj;
struct rnd_state prng;
IGT_TIMEOUT(end);
@@ -22,15 +25,19 @@ static int igt_client_fill(void *arg)
prandom_seed_state(&prng, i915_selftest.random_seed);
do {
- u32 sz = prandom_u32_state(&prng) % SZ_32M;
+ const u32 max_block_size = S16_MAX * PAGE_SIZE;
+ u32 sz = min_t(u64, ce->vm->total >> 4, prandom_u32_state(&prng));
+ u32 phys_sz = sz % (max_block_size + 1);
u32 val = prandom_u32_state(&prng);
u32 i;
sz = round_up(sz, PAGE_SIZE);
+ phys_sz = round_up(phys_sz, PAGE_SIZE);
- pr_debug("%s with sz=%x, val=%x\n", __func__, sz, val);
+ pr_debug("%s with phys_sz= %x, sz=%x, val=%x\n", __func__,
+ phys_sz, sz, val);
- obj = i915_gem_object_create_internal(i915, sz);
+ obj = huge_gem_object(i915, phys_sz, sz);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto err_flush;
@@ -52,7 +59,8 @@ static int igt_client_fill(void *arg)
* values after we do the set_to_cpu_domain and pick it up as a
* test failure.
*/
- memset32(vaddr, val ^ 0xdeadbeaf, obj->base.size / sizeof(u32));
+ memset32(vaddr, val ^ 0xdeadbeaf,
+ huge_gem_object_phys_size(obj) / sizeof(u32));
if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
obj->cache_dirty = true;
@@ -63,24 +71,13 @@ static int igt_client_fill(void *arg)
if (err)
goto err_unpin;
- /*
- * XXX: For now do the wait without the object resv lock to
- * ensure we don't deadlock.
- */
- err = i915_gem_object_wait(obj,
- I915_WAIT_INTERRUPTIBLE |
- I915_WAIT_ALL,
- MAX_SCHEDULE_TIMEOUT);
- if (err)
- goto err_unpin;
-
i915_gem_object_lock(obj);
err = i915_gem_object_set_to_cpu_domain(obj, false);
i915_gem_object_unlock(obj);
if (err)
goto err_unpin;
- for (i = 0; i < obj->base.size / sizeof(u32); ++i) {
+ for (i = 0; i < huge_gem_object_phys_size(obj) / sizeof(u32); ++i) {
if (vaddr[i] != val) {
pr_err("vaddr[%u]=%x, expected=%x\n", i,
vaddr[i], val);
@@ -100,11 +97,6 @@ err_unpin:
err_put:
i915_gem_object_put(obj);
err_flush:
- mutex_lock(&i915->drm.struct_mutex);
- if (igt_flush_test(i915, I915_WAIT_LOCKED))
- err = -EIO;
- mutex_unlock(&i915->drm.struct_mutex);
-
if (err == -ENOMEM)
err = 0;
@@ -117,11 +109,11 @@ int i915_gem_client_blt_live_selftests(struct drm_i915_private *i915)
SUBTEST(igt_client_fill),
};
- if (i915_terminally_wedged(i915))
+ if (intel_gt_is_wedged(&i915->gt))
return 0;
if (!HAS_ENGINE(i915, BCS0))
return 0;
- return i915_subtests(tests, i915->engine[BCS0]->kernel_context);
+ return i915_live_subtests(tests, i915);
}
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 8f22d3f18422..0ff7a89aadca 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -6,6 +6,8 @@
#include <linux/prime_numbers.h>
+#include "gt/intel_gt.h"
+
#include "i915_selftest.h"
#include "selftests/i915_random.h"
@@ -226,7 +228,9 @@ static int gpu_set(struct drm_i915_gem_object *obj,
intel_ring_advance(rq, cs);
i915_vma_lock(vma);
- err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+ err = i915_request_await_object(rq, vma->obj, true);
+ if (err == 0)
+ err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
i915_vma_unlock(vma);
i915_vma_unpin(vma);
@@ -242,12 +246,15 @@ static bool always_valid(struct drm_i915_private *i915)
static bool needs_fence_registers(struct drm_i915_private *i915)
{
- return !i915_terminally_wedged(i915);
+ return !intel_gt_is_wedged(&i915->gt);
}
static bool needs_mi_store_dword(struct drm_i915_private *i915)
{
- if (i915_terminally_wedged(i915))
+ if (intel_gt_is_wedged(&i915->gt))
+ return false;
+
+ if (!HAS_ENGINE(i915, RCS0))
return false;
return intel_engine_can_store_dword(i915->engine[RCS0]);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index eaa2b16574c7..3e6f4a65d356 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -7,6 +7,7 @@
#include <linux/prime_numbers.h>
#include "gem/i915_gem_pm.h"
+#include "gt/intel_gt.h"
#include "gt/intel_reset.h"
#include "i915_selftest.h"
@@ -31,7 +32,6 @@ static int live_nop_switch(void *arg)
struct intel_engine_cs *engine;
struct i915_gem_context **ctx;
enum intel_engine_id id;
- intel_wakeref_t wakeref;
struct igt_live_test t;
struct drm_file *file;
unsigned long n;
@@ -53,7 +53,6 @@ static int live_nop_switch(void *arg)
return PTR_ERR(file);
mutex_lock(&i915->drm.struct_mutex);
- wakeref = intel_runtime_pm_get(&i915->runtime_pm);
ctx = kcalloc(nctx, sizeof(*ctx), GFP_KERNEL);
if (!ctx) {
@@ -85,7 +84,7 @@ static int live_nop_switch(void *arg)
}
if (i915_request_wait(rq, 0, HZ / 5) < 0) {
pr_err("Failed to populated %d contexts\n", nctx);
- i915_gem_set_wedged(i915);
+ intel_gt_set_wedged(&i915->gt);
err = -EIO;
goto out_unlock;
}
@@ -129,7 +128,7 @@ static int live_nop_switch(void *arg)
if (i915_request_wait(rq, 0, HZ / 5) < 0) {
pr_err("Switching between %ld contexts timed out\n",
prime);
- i915_gem_set_wedged(i915);
+ intel_gt_set_wedged(&i915->gt);
break;
}
@@ -152,76 +151,11 @@ static int live_nop_switch(void *arg)
}
out_unlock:
- intel_runtime_pm_put(&i915->runtime_pm, wakeref);
mutex_unlock(&i915->drm.struct_mutex);
mock_file_free(i915, file);
return err;
}
-static struct i915_vma *
-gpu_fill_dw(struct i915_vma *vma, u64 offset, unsigned long count, u32 value)
-{
- struct drm_i915_gem_object *obj;
- const int gen = INTEL_GEN(vma->vm->i915);
- unsigned long n, size;
- u32 *cmd;
- int err;
-
- size = (4 * count + 1) * sizeof(u32);
- size = round_up(size, PAGE_SIZE);
- obj = i915_gem_object_create_internal(vma->vm->i915, size);
- if (IS_ERR(obj))
- return ERR_CAST(obj);
-
- cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
- if (IS_ERR(cmd)) {
- err = PTR_ERR(cmd);
- goto err;
- }
-
- GEM_BUG_ON(offset + (count - 1) * PAGE_SIZE > vma->node.size);
- offset += vma->node.start;
-
- for (n = 0; n < count; n++) {
- if (gen >= 8) {
- *cmd++ = MI_STORE_DWORD_IMM_GEN4;
- *cmd++ = lower_32_bits(offset);
- *cmd++ = upper_32_bits(offset);
- *cmd++ = value;
- } else if (gen >= 4) {
- *cmd++ = MI_STORE_DWORD_IMM_GEN4 |
- (gen < 6 ? MI_USE_GGTT : 0);
- *cmd++ = 0;
- *cmd++ = offset;
- *cmd++ = value;
- } else {
- *cmd++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
- *cmd++ = offset;
- *cmd++ = value;
- }
- offset += PAGE_SIZE;
- }
- *cmd = MI_BATCH_BUFFER_END;
- i915_gem_object_flush_map(obj);
- i915_gem_object_unpin_map(obj);
-
- vma = i915_vma_instance(obj, vma->vm, NULL);
- if (IS_ERR(vma)) {
- err = PTR_ERR(vma);
- goto err;
- }
-
- err = i915_vma_pin(vma, 0, 0, PIN_USER);
- if (err)
- goto err;
-
- return vma;
-
-err:
- i915_gem_object_put(obj);
- return ERR_PTR(err);
-}
-
static unsigned long real_page_count(struct drm_i915_gem_object *obj)
{
return huge_gem_object_phys_size(obj) >> PAGE_SHIFT;
@@ -237,12 +171,8 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
struct intel_engine_cs *engine,
unsigned int dw)
{
- struct drm_i915_private *i915 = to_i915(obj->base.dev);
- struct i915_address_space *vm = ctx->vm ?: &i915->ggtt.vm;
- struct i915_request *rq;
+ struct i915_address_space *vm = ctx->vm ?: &engine->gt->ggtt->vm;
struct i915_vma *vma;
- struct i915_vma *batch;
- unsigned int flags;
int err;
GEM_BUG_ON(obj->base.size > vm->total);
@@ -253,7 +183,7 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
return PTR_ERR(vma);
i915_gem_object_lock(obj);
- err = i915_gem_object_set_to_gtt_domain(obj, false);
+ err = i915_gem_object_set_to_gtt_domain(obj, true);
i915_gem_object_unlock(obj);
if (err)
return err;
@@ -262,70 +192,23 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
if (err)
return err;
- /* Within the GTT the huge objects maps every page onto
+ /*
+ * Within the GTT the huge objects maps every page onto
* its 1024 real pages (using phys_pfn = dma_pfn % 1024).
* We set the nth dword within the page using the nth
* mapping via the GTT - this should exercise the GTT mapping
* whilst checking that each context provides a unique view
* into the object.
*/
- batch = gpu_fill_dw(vma,
- (dw * real_page_count(obj)) << PAGE_SHIFT |
- (dw * sizeof(u32)),
- real_page_count(obj),
- dw);
- if (IS_ERR(batch)) {
- err = PTR_ERR(batch);
- goto err_vma;
- }
-
- rq = igt_request_alloc(ctx, engine);
- if (IS_ERR(rq)) {
- err = PTR_ERR(rq);
- goto err_batch;
- }
-
- flags = 0;
- if (INTEL_GEN(vm->i915) <= 5)
- flags |= I915_DISPATCH_SECURE;
-
- err = engine->emit_bb_start(rq,
- batch->node.start, batch->node.size,
- flags);
- if (err)
- goto err_request;
-
- i915_vma_lock(batch);
- err = i915_vma_move_to_active(batch, rq, 0);
- i915_vma_unlock(batch);
- if (err)
- goto skip_request;
-
- i915_vma_lock(vma);
- err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
- i915_vma_unlock(vma);
- if (err)
- goto skip_request;
-
- i915_request_add(rq);
-
- i915_vma_unpin(batch);
- i915_vma_close(batch);
- i915_vma_put(batch);
-
+ err = igt_gpu_fill_dw(vma,
+ ctx,
+ engine,
+ (dw * real_page_count(obj)) << PAGE_SHIFT |
+ (dw * sizeof(u32)),
+ real_page_count(obj),
+ dw);
i915_vma_unpin(vma);
- return 0;
-
-skip_request:
- i915_request_skip(rq, err);
-err_request:
- i915_request_add(rq);
-err_batch:
- i915_vma_unpin(batch);
- i915_vma_put(batch);
-err_vma:
- i915_vma_unpin(vma);
return err;
}
@@ -431,6 +314,9 @@ create_test_object(struct i915_gem_context *ctx,
u64 size;
int err;
+ /* Keep in GEM's good graces */
+ i915_retire_requests(ctx->i915);
+
size = min(vm->total / 2, 1024ull * DW_PER_PAGE * PAGE_SIZE);
size = round_down(size, DW_PER_PAGE * PAGE_SIZE);
@@ -507,7 +393,6 @@ static int igt_ctx_exec(void *arg)
dw = 0;
while (!time_after(jiffies, end_time)) {
struct i915_gem_context *ctx;
- intel_wakeref_t wakeref;
ctx = live_context(i915, file);
if (IS_ERR(ctx)) {
@@ -523,8 +408,7 @@ static int igt_ctx_exec(void *arg)
}
}
- with_intel_runtime_pm(&i915->runtime_pm, wakeref)
- err = gpu_fill(obj, ctx, engine, dw);
+ err = gpu_fill(obj, ctx, engine, dw);
if (err) {
pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
ndwords, dw, max_dwords(obj),
@@ -565,6 +449,8 @@ out_unlock:
mock_file_free(i915, file);
if (err)
return err;
+
+ i915_gem_drain_freed_objects(i915);
}
return 0;
@@ -623,7 +509,6 @@ static int igt_shared_ctx_exec(void *arg)
ncontexts = 0;
while (!time_after(jiffies, end_time)) {
struct i915_gem_context *ctx;
- intel_wakeref_t wakeref;
ctx = kernel_context(i915);
if (IS_ERR(ctx)) {
@@ -642,9 +527,7 @@ static int igt_shared_ctx_exec(void *arg)
}
}
- err = 0;
- with_intel_runtime_pm(&i915->runtime_pm, wakeref)
- err = gpu_fill(obj, ctx, engine, dw);
+ err = gpu_fill(obj, ctx, engine, dw);
if (err) {
pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
ndwords, dw, max_dwords(obj),
@@ -678,6 +561,10 @@ static int igt_shared_ctx_exec(void *arg)
dw += rem;
}
+
+ mutex_unlock(&i915->drm.struct_mutex);
+ i915_gem_drain_freed_objects(i915);
+ mutex_lock(&i915->drm.struct_mutex);
}
out_test:
if (igt_live_test_end(&t))
@@ -746,7 +633,7 @@ emit_rpcs_query(struct drm_i915_gem_object *obj,
GEM_BUG_ON(!intel_engine_can_store_dword(ce->engine));
- vma = i915_vma_instance(obj, ce->gem_context->vm, NULL);
+ vma = i915_vma_instance(obj, ce->vm, NULL);
if (IS_ERR(vma))
return PTR_ERR(vma);
@@ -779,13 +666,17 @@ emit_rpcs_query(struct drm_i915_gem_object *obj,
goto err_request;
i915_vma_lock(batch);
- err = i915_vma_move_to_active(batch, rq, 0);
+ err = i915_request_await_object(rq, batch->obj, false);
+ if (err == 0)
+ err = i915_vma_move_to_active(batch, rq, 0);
i915_vma_unlock(batch);
if (err)
goto skip_request;
i915_vma_lock(vma);
- err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+ err = i915_request_await_object(rq, vma->obj, true);
+ if (err == 0)
+ err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
i915_vma_unlock(vma);
if (err)
goto skip_request;
@@ -820,8 +711,7 @@ err_vma:
#define TEST_RESET BIT(2)
static int
-__sseu_prepare(struct drm_i915_private *i915,
- const char *name,
+__sseu_prepare(const char *name,
unsigned int flags,
struct intel_context *ce,
struct igt_spinner **spin)
@@ -837,14 +727,11 @@ __sseu_prepare(struct drm_i915_private *i915,
if (!*spin)
return -ENOMEM;
- ret = igt_spinner_init(*spin, i915);
+ ret = igt_spinner_init(*spin, ce->engine->gt);
if (ret)
goto err_free;
- rq = igt_spinner_create_request(*spin,
- ce->gem_context,
- ce->engine,
- MI_NOOP);
+ rq = igt_spinner_create_request(*spin, ce, MI_NOOP);
if (IS_ERR(rq)) {
ret = PTR_ERR(rq);
goto err_fini;
@@ -870,8 +757,7 @@ err_free:
}
static int
-__read_slice_count(struct drm_i915_private *i915,
- struct intel_context *ce,
+__read_slice_count(struct intel_context *ce,
struct drm_i915_gem_object *obj,
struct igt_spinner *spin,
u32 *rpcs)
@@ -900,7 +786,7 @@ __read_slice_count(struct drm_i915_private *i915,
return ret;
}
- if (INTEL_GEN(i915) >= 11) {
+ if (INTEL_GEN(ce->engine->i915) >= 11) {
s_mask = GEN11_RPCS_S_CNT_MASK;
s_shift = GEN11_RPCS_S_CNT_SHIFT;
} else {
@@ -943,8 +829,7 @@ __check_rpcs(const char *name, u32 rpcs, int slices, unsigned int expected,
}
static int
-__sseu_finish(struct drm_i915_private *i915,
- const char *name,
+__sseu_finish(const char *name,
unsigned int flags,
struct intel_context *ce,
struct drm_i915_gem_object *obj,
@@ -956,19 +841,18 @@ __sseu_finish(struct drm_i915_private *i915,
int ret = 0;
if (flags & TEST_RESET) {
- ret = i915_reset_engine(ce->engine, "sseu");
+ ret = intel_engine_reset(ce->engine, "sseu");
if (ret)
goto out;
}
- ret = __read_slice_count(i915, ce, obj,
+ ret = __read_slice_count(ce, obj,
flags & TEST_RESET ? NULL : spin, &rpcs);
ret = __check_rpcs(name, rpcs, ret, expected, "Context", "!");
if (ret)
goto out;
- ret = __read_slice_count(i915, ce->engine->kernel_context, obj,
- NULL, &rpcs);
+ ret = __read_slice_count(ce->engine->kernel_context, obj, NULL, &rpcs);
ret = __check_rpcs(name, rpcs, ret, slices, "Kernel context", "!");
out:
@@ -976,11 +860,12 @@ out:
igt_spinner_end(spin);
if ((flags & TEST_IDLE) && ret == 0) {
- ret = i915_gem_wait_for_idle(i915, 0, MAX_SCHEDULE_TIMEOUT);
+ ret = i915_gem_wait_for_idle(ce->engine->i915,
+ 0, MAX_SCHEDULE_TIMEOUT);
if (ret)
return ret;
- ret = __read_slice_count(i915, ce, obj, NULL, &rpcs);
+ ret = __read_slice_count(ce, obj, NULL, &rpcs);
ret = __check_rpcs(name, rpcs, ret, expected,
"Context", " after idle!");
}
@@ -989,8 +874,7 @@ out:
}
static int
-__sseu_test(struct drm_i915_private *i915,
- const char *name,
+__sseu_test(const char *name,
unsigned int flags,
struct intel_context *ce,
struct drm_i915_gem_object *obj,
@@ -999,7 +883,7 @@ __sseu_test(struct drm_i915_private *i915,
struct igt_spinner *spin = NULL;
int ret;
- ret = __sseu_prepare(i915, name, flags, ce, &spin);
+ ret = __sseu_prepare(name, flags, ce, &spin);
if (ret)
return ret;
@@ -1007,7 +891,7 @@ __sseu_test(struct drm_i915_private *i915,
if (ret)
goto out_spin;
- ret = __sseu_finish(i915, name, flags, ce, obj,
+ ret = __sseu_finish(name, flags, ce, obj,
hweight32(sseu.slice_mask), spin);
out_spin:
@@ -1025,35 +909,33 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
unsigned int flags)
{
struct intel_engine_cs *engine = i915->engine[RCS0];
- struct intel_sseu default_sseu = engine->sseu;
struct drm_i915_gem_object *obj;
struct i915_gem_context *ctx;
struct intel_context *ce;
struct intel_sseu pg_sseu;
- intel_wakeref_t wakeref;
struct drm_file *file;
int ret;
- if (INTEL_GEN(i915) < 9)
+ if (INTEL_GEN(i915) < 9 || !engine)
return 0;
if (!RUNTIME_INFO(i915)->sseu.has_slice_pg)
return 0;
- if (hweight32(default_sseu.slice_mask) < 2)
+ if (hweight32(engine->sseu.slice_mask) < 2)
return 0;
/*
* Gen11 VME friendly power-gated configuration with half enabled
* sub-slices.
*/
- pg_sseu = default_sseu;
+ pg_sseu = engine->sseu;
pg_sseu.slice_mask = 1;
pg_sseu.subslice_mask =
- ~(~0 << (hweight32(default_sseu.subslice_mask) / 2));
+ ~(~0 << (hweight32(engine->sseu.subslice_mask) / 2));
pr_info("SSEU subtest '%s', flags=%x, def_slices=%u, pg_slices=%u\n",
- name, flags, hweight32(default_sseu.slice_mask),
+ name, flags, hweight32(engine->sseu.slice_mask),
hweight32(pg_sseu.slice_mask));
file = mock_file(i915);
@@ -1061,7 +943,7 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
return PTR_ERR(file);
if (flags & TEST_RESET)
- igt_global_reset_lock(i915);
+ igt_global_reset_lock(&i915->gt);
mutex_lock(&i915->drm.struct_mutex);
@@ -1078,12 +960,10 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
goto out_unlock;
}
- wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
ce = i915_gem_context_get_engine(ctx, RCS0);
if (IS_ERR(ce)) {
ret = PTR_ERR(ce);
- goto out_rpm;
+ goto out_put;
}
ret = intel_context_pin(ce);
@@ -1091,22 +971,22 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
goto out_context;
/* First set the default mask. */
- ret = __sseu_test(i915, name, flags, ce, obj, default_sseu);
+ ret = __sseu_test(name, flags, ce, obj, engine->sseu);
if (ret)
goto out_fail;
/* Then set a power-gated configuration. */
- ret = __sseu_test(i915, name, flags, ce, obj, pg_sseu);
+ ret = __sseu_test(name, flags, ce, obj, pg_sseu);
if (ret)
goto out_fail;
/* Back to defaults. */
- ret = __sseu_test(i915, name, flags, ce, obj, default_sseu);
+ ret = __sseu_test(name, flags, ce, obj, engine->sseu);
if (ret)
goto out_fail;
/* One last power-gated configuration for the road. */
- ret = __sseu_test(i915, name, flags, ce, obj, pg_sseu);
+ ret = __sseu_test(name, flags, ce, obj, pg_sseu);
if (ret)
goto out_fail;
@@ -1117,15 +997,14 @@ out_fail:
intel_context_unpin(ce);
out_context:
intel_context_put(ce);
-out_rpm:
- intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+out_put:
i915_gem_object_put(obj);
out_unlock:
mutex_unlock(&i915->drm.struct_mutex);
if (flags & TEST_RESET)
- igt_global_reset_unlock(i915);
+ igt_global_reset_unlock(&i915->gt);
mock_file_free(i915, file);
@@ -1194,7 +1073,7 @@ static int igt_ctx_readonly(void *arg)
goto out_unlock;
}
- vm = ctx->vm ?: &i915->mm.aliasing_ppgtt->vm;
+ vm = ctx->vm ?: &i915->ggtt.alias->vm;
if (!vm || !vm->has_read_only) {
err = 0;
goto out_unlock;
@@ -1207,8 +1086,6 @@ static int igt_ctx_readonly(void *arg)
unsigned int id;
for_each_engine(engine, i915, id) {
- intel_wakeref_t wakeref;
-
if (!intel_engine_can_store_dword(engine))
continue;
@@ -1223,9 +1100,7 @@ static int igt_ctx_readonly(void *arg)
i915_gem_object_set_readonly(obj);
}
- err = 0;
- with_intel_runtime_pm(&i915->runtime_pm, wakeref)
- err = gpu_fill(obj, ctx, engine, dw);
+ err = gpu_fill(obj, ctx, engine, dw);
if (err) {
pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
ndwords, dw, max_dwords(obj),
@@ -1347,7 +1222,9 @@ static int write_to_scratch(struct i915_gem_context *ctx,
goto err_request;
i915_vma_lock(vma);
- err = i915_vma_move_to_active(vma, rq, 0);
+ err = i915_request_await_object(rq, vma->obj, false);
+ if (err == 0)
+ err = i915_vma_move_to_active(vma, rq, 0);
i915_vma_unlock(vma);
if (err)
goto skip_request;
@@ -1444,7 +1321,9 @@ static int read_from_scratch(struct i915_gem_context *ctx,
goto err_request;
i915_vma_lock(vma);
- err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+ err = i915_request_await_object(rq, vma->obj, true);
+ if (err == 0)
+ err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
i915_vma_unlock(vma);
if (err)
goto skip_request;
@@ -1488,7 +1367,6 @@ static int igt_vm_isolation(void *arg)
struct drm_i915_private *i915 = arg;
struct i915_gem_context *ctx_a, *ctx_b;
struct intel_engine_cs *engine;
- intel_wakeref_t wakeref;
struct igt_live_test t;
struct drm_file *file;
I915_RND_STATE(prng);
@@ -1535,8 +1413,6 @@ static int igt_vm_isolation(void *arg)
GEM_BUG_ON(ctx_b->vm->total != vm_total);
vm_total -= I915_GTT_PAGE_SIZE;
- wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
count = 0;
for_each_engine(engine, i915, id) {
IGT_TIMEOUT(end_time);
@@ -1551,7 +1427,7 @@ static int igt_vm_isolation(void *arg)
div64_u64_rem(i915_prandom_u64_state(&prng),
vm_total, &offset);
- offset &= -sizeof(u32);
+ offset = round_down(offset, alignof_dword);
offset += I915_GTT_PAGE_SIZE;
err = write_to_scratch(ctx_a, engine,
@@ -1560,7 +1436,7 @@ static int igt_vm_isolation(void *arg)
err = read_from_scratch(ctx_b, engine,
offset, &value);
if (err)
- goto out_rpm;
+ goto out_unlock;
if (value) {
pr_err("%s: Read %08x from scratch (offset 0x%08x_%08x), after %lu reads!\n",
@@ -1569,7 +1445,7 @@ static int igt_vm_isolation(void *arg)
lower_32_bits(offset),
this);
err = -EINVAL;
- goto out_rpm;
+ goto out_unlock;
}
this++;
@@ -1579,8 +1455,6 @@ static int igt_vm_isolation(void *arg)
pr_info("Checked %lu scratch offsets across %d engines\n",
count, RUNTIME_INFO(i915)->num_engines);
-out_rpm:
- intel_runtime_pm_put(&i915->runtime_pm, wakeref);
out_unlock:
if (igt_live_test_end(&t))
err = -EIO;
@@ -1736,7 +1610,7 @@ int i915_gem_context_mock_selftests(void)
return err;
}
-int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
+int i915_gem_context_live_selftests(struct drm_i915_private *i915)
{
static const struct i915_subtest tests[] = {
SUBTEST(live_nop_switch),
@@ -1747,8 +1621,8 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
SUBTEST(igt_vm_isolation),
};
- if (i915_terminally_wedged(dev_priv))
+ if (intel_gt_is_wedged(&i915->gt))
return 0;
- return i915_subtests(tests, dev_priv);
+ return i915_live_subtests(tests, i915);
}
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index e3a64edef918..d85d1ce273ca 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -20,7 +20,7 @@ static int igt_dmabuf_export(void *arg)
if (IS_ERR(obj))
return PTR_ERR(obj);
- dmabuf = i915_gem_prime_export(&i915->drm, &obj->base, 0);
+ dmabuf = i915_gem_prime_export(&obj->base, 0);
i915_gem_object_put(obj);
if (IS_ERR(dmabuf)) {
pr_err("i915_gem_prime_export failed with err=%d\n",
@@ -44,7 +44,7 @@ static int igt_dmabuf_import_self(void *arg)
if (IS_ERR(obj))
return PTR_ERR(obj);
- dmabuf = i915_gem_prime_export(&i915->drm, &obj->base, 0);
+ dmabuf = i915_gem_prime_export(&obj->base, 0);
if (IS_ERR(dmabuf)) {
pr_err("i915_gem_prime_export failed with err=%d\n",
(int)PTR_ERR(dmabuf));
@@ -219,7 +219,7 @@ static int igt_dmabuf_export_vmap(void *arg)
if (IS_ERR(obj))
return PTR_ERR(obj);
- dmabuf = i915_gem_prime_export(&i915->drm, &obj->base, 0);
+ dmabuf = i915_gem_prime_export(&obj->base, 0);
if (IS_ERR(dmabuf)) {
pr_err("i915_gem_prime_export failed with err=%d\n",
(int)PTR_ERR(dmabuf));
@@ -266,7 +266,7 @@ static int igt_dmabuf_export_kmap(void *arg)
if (IS_ERR(obj))
return PTR_ERR(obj);
- dmabuf = i915_gem_prime_export(&i915->drm, &obj->base, 0);
+ dmabuf = i915_gem_prime_export(&obj->base, 0);
i915_gem_object_put(obj);
if (IS_ERR(dmabuf)) {
err = PTR_ERR(dmabuf);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 5c81f4b4813a..1d27babff0ce 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -6,6 +6,7 @@
#include <linux/prime_numbers.h>
+#include "gt/intel_gt.h"
#include "gt/intel_gt_pm.h"
#include "huge_gem_object.h"
#include "i915_selftest.h"
@@ -143,7 +144,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
if (offset >= obj->base.size)
continue;
- i915_gem_flush_ggtt_writes(to_i915(obj->base.dev));
+ intel_gt_flush_ggtt_writes(&to_i915(obj->base.dev)->gt);
p = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
cpu = kmap(p) + offset_in_page(offset);
@@ -327,7 +328,8 @@ out:
static int make_obj_busy(struct drm_i915_gem_object *obj)
{
struct drm_i915_private *i915 = to_i915(obj->base.dev);
- struct i915_request *rq;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
struct i915_vma *vma;
int err;
@@ -339,17 +341,24 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
if (err)
return err;
- rq = i915_request_create(i915->engine[RCS0]->kernel_context);
- if (IS_ERR(rq)) {
- i915_vma_unpin(vma);
- return PTR_ERR(rq);
- }
+ for_each_engine(engine, i915, id) {
+ struct i915_request *rq;
+
+ rq = i915_request_create(engine->kernel_context);
+ if (IS_ERR(rq)) {
+ i915_vma_unpin(vma);
+ return PTR_ERR(rq);
+ }
- i915_vma_lock(vma);
- err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
- i915_vma_unlock(vma);
+ i915_vma_lock(vma);
+ err = i915_request_await_object(rq, vma->obj, true);
+ if (err == 0)
+ err = i915_vma_move_to_active(vma, rq,
+ EXEC_OBJECT_WRITE);
+ i915_vma_unlock(vma);
- i915_request_add(rq);
+ i915_request_add(rq);
+ }
i915_vma_unpin(vma);
i915_gem_object_put(obj); /* leave it only alive via its active ref */
@@ -376,9 +385,9 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
static void disable_retire_worker(struct drm_i915_private *i915)
{
- i915_gem_shrinker_unregister(i915);
+ i915_gem_driver_unregister__shrinker(i915);
- intel_gt_pm_get(i915);
+ intel_gt_pm_get(&i915->gt);
cancel_delayed_work_sync(&i915->gem.retire_work);
flush_work(&i915->gem.idle_work);
@@ -386,13 +395,25 @@ static void disable_retire_worker(struct drm_i915_private *i915)
static void restore_retire_worker(struct drm_i915_private *i915)
{
- intel_gt_pm_put(i915);
+ intel_gt_pm_put(&i915->gt);
mutex_lock(&i915->drm.struct_mutex);
igt_flush_test(i915, I915_WAIT_LOCKED);
mutex_unlock(&i915->drm.struct_mutex);
- i915_gem_shrinker_register(i915);
+ i915_gem_driver_register__shrinker(i915);
+}
+
+static void mmap_offset_lock(struct drm_i915_private *i915)
+ __acquires(&i915->drm.vma_offset_manager->vm_lock)
+{
+ write_lock(&i915->drm.vma_offset_manager->vm_lock);
+}
+
+static void mmap_offset_unlock(struct drm_i915_private *i915)
+ __releases(&i915->drm.vma_offset_manager->vm_lock)
+{
+ write_unlock(&i915->drm.vma_offset_manager->vm_lock);
}
static int igt_mmap_offset_exhaustion(void *arg)
@@ -413,7 +434,9 @@ static int igt_mmap_offset_exhaustion(void *arg)
drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
resv.start = hole_start;
resv.size = hole_end - hole_start - 1; /* PAGE_SIZE units */
+ mmap_offset_lock(i915);
err = drm_mm_reserve_node(mm, &resv);
+ mmap_offset_unlock(i915);
if (err) {
pr_err("Failed to trim VMA manager, err=%d\n", err);
goto out_park;
@@ -458,7 +481,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
/* Now fill with busy dead objects that we expect to reap */
for (loop = 0; loop < 3; loop++) {
- if (i915_terminally_wedged(i915))
+ if (intel_gt_is_wedged(&i915->gt))
break;
obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
@@ -474,19 +497,12 @@ static int igt_mmap_offset_exhaustion(void *arg)
pr_err("[loop %d] Failed to busy the object\n", loop);
goto err_obj;
}
-
- /* NB we rely on the _active_ reference to access obj now */
- GEM_BUG_ON(!i915_gem_object_is_active(obj));
- err = create_mmap_offset(obj);
- if (err) {
- pr_err("[loop %d] create_mmap_offset failed with err=%d\n",
- loop, err);
- goto out;
- }
}
out:
+ mmap_offset_lock(i915);
drm_mm_remove_node(&resv);
+ mmap_offset_unlock(i915);
out_park:
restore_retire_worker(i915);
return err;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
index e23d8c9e9298..c21d747e7d05 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
@@ -3,16 +3,19 @@
* Copyright © 2019 Intel Corporation
*/
+#include "gt/intel_gt.h"
+
#include "i915_selftest.h"
#include "selftests/igt_flush_test.h"
#include "selftests/mock_drm.h"
+#include "huge_gem_object.h"
#include "mock_context.h"
static int igt_fill_blt(void *arg)
{
- struct intel_context *ce = arg;
- struct drm_i915_private *i915 = ce->gem_context->i915;
+ struct drm_i915_private *i915 = arg;
+ struct intel_context *ce = i915->engine[BCS0]->kernel_context;
struct drm_i915_gem_object *obj;
struct rnd_state prng;
IGT_TIMEOUT(end);
@@ -21,16 +24,26 @@ static int igt_fill_blt(void *arg)
prandom_seed_state(&prng, i915_selftest.random_seed);
+ /*
+ * XXX: needs some threads to scale all these tests, also maybe throw
+ * in submission from higher priority context to see if we are
+ * preempted for very large objects...
+ */
+
do {
- u32 sz = prandom_u32_state(&prng) % SZ_32M;
+ const u32 max_block_size = S16_MAX * PAGE_SIZE;
+ u32 sz = min_t(u64, ce->vm->total >> 4, prandom_u32_state(&prng));
+ u32 phys_sz = sz % (max_block_size + 1);
u32 val = prandom_u32_state(&prng);
u32 i;
sz = round_up(sz, PAGE_SIZE);
+ phys_sz = round_up(phys_sz, PAGE_SIZE);
- pr_debug("%s with sz=%x, val=%x\n", __func__, sz, val);
+ pr_debug("%s with phys_sz= %x, sz=%x, val=%x\n", __func__,
+ phys_sz, sz, val);
- obj = i915_gem_object_create_internal(i915, sz);
+ obj = huge_gem_object(i915, phys_sz, sz);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto err_flush;
@@ -46,7 +59,8 @@ static int igt_fill_blt(void *arg)
* Make sure the potentially async clflush does its job, if
* required.
*/
- memset32(vaddr, val ^ 0xdeadbeaf, obj->base.size / sizeof(u32));
+ memset32(vaddr, val ^ 0xdeadbeaf,
+ huge_gem_object_phys_size(obj) / sizeof(u32));
if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
obj->cache_dirty = true;
@@ -63,7 +77,7 @@ static int igt_fill_blt(void *arg)
if (err)
goto err_unpin;
- for (i = 0; i < obj->base.size / sizeof(u32); ++i) {
+ for (i = 0; i < huge_gem_object_phys_size(obj) / sizeof(u32); ++i) {
if (vaddr[i] != val) {
pr_err("vaddr[%u]=%x, expected=%x\n", i,
vaddr[i], val);
@@ -83,11 +97,111 @@ err_unpin:
err_put:
i915_gem_object_put(obj);
err_flush:
- mutex_lock(&i915->drm.struct_mutex);
- if (igt_flush_test(i915, I915_WAIT_LOCKED))
- err = -EIO;
- mutex_unlock(&i915->drm.struct_mutex);
+ if (err == -ENOMEM)
+ err = 0;
+
+ return err;
+}
+
+static int igt_copy_blt(void *arg)
+{
+ struct drm_i915_private *i915 = arg;
+ struct intel_context *ce = i915->engine[BCS0]->kernel_context;
+ struct drm_i915_gem_object *src, *dst;
+ struct rnd_state prng;
+ IGT_TIMEOUT(end);
+ u32 *vaddr;
+ int err = 0;
+
+ prandom_seed_state(&prng, i915_selftest.random_seed);
+
+ do {
+ const u32 max_block_size = S16_MAX * PAGE_SIZE;
+ u32 sz = min_t(u64, ce->vm->total >> 4, prandom_u32_state(&prng));
+ u32 phys_sz = sz % (max_block_size + 1);
+ u32 val = prandom_u32_state(&prng);
+ u32 i;
+
+ sz = round_up(sz, PAGE_SIZE);
+ phys_sz = round_up(phys_sz, PAGE_SIZE);
+
+ pr_debug("%s with phys_sz= %x, sz=%x, val=%x\n", __func__,
+ phys_sz, sz, val);
+
+ src = huge_gem_object(i915, phys_sz, sz);
+ if (IS_ERR(src)) {
+ err = PTR_ERR(src);
+ goto err_flush;
+ }
+
+ vaddr = i915_gem_object_pin_map(src, I915_MAP_WB);
+ if (IS_ERR(vaddr)) {
+ err = PTR_ERR(vaddr);
+ goto err_put_src;
+ }
+
+ memset32(vaddr, val,
+ huge_gem_object_phys_size(src) / sizeof(u32));
+
+ i915_gem_object_unpin_map(src);
+
+ if (!(src->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
+ src->cache_dirty = true;
+ dst = huge_gem_object(i915, phys_sz, sz);
+ if (IS_ERR(dst)) {
+ err = PTR_ERR(dst);
+ goto err_put_src;
+ }
+
+ vaddr = i915_gem_object_pin_map(dst, I915_MAP_WB);
+ if (IS_ERR(vaddr)) {
+ err = PTR_ERR(vaddr);
+ goto err_put_dst;
+ }
+
+ memset32(vaddr, val ^ 0xdeadbeaf,
+ huge_gem_object_phys_size(dst) / sizeof(u32));
+
+ if (!(dst->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
+ dst->cache_dirty = true;
+
+ mutex_lock(&i915->drm.struct_mutex);
+ err = i915_gem_object_copy_blt(src, dst, ce);
+ mutex_unlock(&i915->drm.struct_mutex);
+ if (err)
+ goto err_unpin;
+
+ i915_gem_object_lock(dst);
+ err = i915_gem_object_set_to_cpu_domain(dst, false);
+ i915_gem_object_unlock(dst);
+ if (err)
+ goto err_unpin;
+
+ for (i = 0; i < huge_gem_object_phys_size(dst) / sizeof(u32); ++i) {
+ if (vaddr[i] != val) {
+ pr_err("vaddr[%u]=%x, expected=%x\n", i,
+ vaddr[i], val);
+ err = -EINVAL;
+ goto err_unpin;
+ }
+ }
+
+ i915_gem_object_unpin_map(dst);
+
+ i915_gem_object_put(src);
+ i915_gem_object_put(dst);
+ } while (!time_after(jiffies, end));
+
+ goto err_flush;
+
+err_unpin:
+ i915_gem_object_unpin_map(dst);
+err_put_dst:
+ i915_gem_object_put(dst);
+err_put_src:
+ i915_gem_object_put(src);
+err_flush:
if (err == -ENOMEM)
err = 0;
@@ -98,13 +212,14 @@ int i915_gem_object_blt_live_selftests(struct drm_i915_private *i915)
{
static const struct i915_subtest tests[] = {
SUBTEST(igt_fill_blt),
+ SUBTEST(igt_copy_blt),
};
- if (i915_terminally_wedged(i915))
+ if (intel_gt_is_wedged(&i915->gt))
return 0;
if (!HAS_ENGINE(i915, BCS0))
return 0;
- return i915_subtests(tests, i915->engine[BCS0]->kernel_context);
+ return i915_live_subtests(tests, i915);
}
diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
index b232e6d2cd92..57ece53c1075 100644
--- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
+++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
@@ -9,6 +9,8 @@
#include "gem/i915_gem_context.h"
#include "gem/i915_gem_pm.h"
#include "gt/intel_context.h"
+#include "i915_vma.h"
+#include "i915_drv.h"
#include "i915_request.h"
@@ -23,7 +25,7 @@ igt_request_alloc(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
* GGTT space, so do this first before we reserve a seqno for
* ourselves.
*/
- ce = i915_gem_context_get_engine(ctx, engine->id);
+ ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
if (IS_ERR(ce))
return ERR_CAST(ce);
@@ -32,3 +34,140 @@ igt_request_alloc(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
return rq;
}
+
+struct i915_vma *
+igt_emit_store_dw(struct i915_vma *vma,
+ u64 offset,
+ unsigned long count,
+ u32 val)
+{
+ struct drm_i915_gem_object *obj;
+ const int gen = INTEL_GEN(vma->vm->i915);
+ unsigned long n, size;
+ u32 *cmd;
+ int err;
+
+ size = (4 * count + 1) * sizeof(u32);
+ size = round_up(size, PAGE_SIZE);
+ obj = i915_gem_object_create_internal(vma->vm->i915, size);
+ if (IS_ERR(obj))
+ return ERR_CAST(obj);
+
+ cmd = i915_gem_object_pin_map(obj, I915_MAP_WC);
+ if (IS_ERR(cmd)) {
+ err = PTR_ERR(cmd);
+ goto err;
+ }
+
+ GEM_BUG_ON(offset + (count - 1) * PAGE_SIZE > vma->node.size);
+ offset += vma->node.start;
+
+ for (n = 0; n < count; n++) {
+ if (gen >= 8) {
+ *cmd++ = MI_STORE_DWORD_IMM_GEN4;
+ *cmd++ = lower_32_bits(offset);
+ *cmd++ = upper_32_bits(offset);
+ *cmd++ = val;
+ } else if (gen >= 4) {
+ *cmd++ = MI_STORE_DWORD_IMM_GEN4 |
+ (gen < 6 ? MI_USE_GGTT : 0);
+ *cmd++ = 0;
+ *cmd++ = offset;
+ *cmd++ = val;
+ } else {
+ *cmd++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
+ *cmd++ = offset;
+ *cmd++ = val;
+ }
+ offset += PAGE_SIZE;
+ }
+ *cmd = MI_BATCH_BUFFER_END;
+ i915_gem_object_unpin_map(obj);
+
+ vma = i915_vma_instance(obj, vma->vm, NULL);
+ if (IS_ERR(vma)) {
+ err = PTR_ERR(vma);
+ goto err;
+ }
+
+ err = i915_vma_pin(vma, 0, 0, PIN_USER);
+ if (err)
+ goto err;
+
+ return vma;
+
+err:
+ i915_gem_object_put(obj);
+ return ERR_PTR(err);
+}
+
+int igt_gpu_fill_dw(struct i915_vma *vma,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ u64 offset,
+ unsigned long count,
+ u32 val)
+{
+ struct i915_address_space *vm = ctx->vm ?: &engine->gt->ggtt->vm;
+ struct i915_request *rq;
+ struct i915_vma *batch;
+ unsigned int flags;
+ int err;
+
+ GEM_BUG_ON(vma->size > vm->total);
+ GEM_BUG_ON(!intel_engine_can_store_dword(engine));
+ GEM_BUG_ON(!i915_vma_is_pinned(vma));
+
+ batch = igt_emit_store_dw(vma, offset, count, val);
+ if (IS_ERR(batch))
+ return PTR_ERR(batch);
+
+ rq = igt_request_alloc(ctx, engine);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto err_batch;
+ }
+
+ flags = 0;
+ if (INTEL_GEN(vm->i915) <= 5)
+ flags |= I915_DISPATCH_SECURE;
+
+ err = engine->emit_bb_start(rq,
+ batch->node.start, batch->node.size,
+ flags);
+ if (err)
+ goto err_request;
+
+ i915_vma_lock(batch);
+ err = i915_request_await_object(rq, batch->obj, false);
+ if (err == 0)
+ err = i915_vma_move_to_active(batch, rq, 0);
+ i915_vma_unlock(batch);
+ if (err)
+ goto skip_request;
+
+ i915_vma_lock(vma);
+ err = i915_request_await_object(rq, vma->obj, true);
+ if (err == 0)
+ err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+ i915_vma_unlock(vma);
+ if (err)
+ goto skip_request;
+
+ i915_request_add(rq);
+
+ i915_vma_unpin(batch);
+ i915_vma_close(batch);
+ i915_vma_put(batch);
+
+ return 0;
+
+skip_request:
+ i915_request_skip(rq, err);
+err_request:
+ i915_request_add(rq);
+err_batch:
+ i915_vma_unpin(batch);
+ i915_vma_put(batch);
+ return err;
+}
diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h
index 0f17251cf75d..361a7ef866b0 100644
--- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h
+++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h
@@ -7,11 +7,27 @@
#ifndef __IGT_GEM_UTILS_H__
#define __IGT_GEM_UTILS_H__
+#include <linux/types.h>
+
struct i915_request;
struct i915_gem_context;
struct intel_engine_cs;
+struct i915_vma;
struct i915_request *
igt_request_alloc(struct i915_gem_context *ctx, struct intel_engine_cs *engine);
+struct i915_vma *
+igt_emit_store_dw(struct i915_vma *vma,
+ u64 offset,
+ unsigned long count,
+ u32 val);
+
+int igt_gpu_fill_dw(struct i915_vma *vma,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ u64 offset,
+ unsigned long count,
+ u32 val);
+
#endif /* __IGT_GEM_UTILS_H__ */
generated by cgit v1.2.3 (git 2.39.1) at 2024-04-28 02:19:56 +0000