Skip to content

L
linux
Commit 99919be7 authored by Thomas Hellström's avatar Thomas Hellström Committed by Matthew Auld
Browse files
Options

drm/i915/gem: Zap the i915_gem_object_blt code 

It's unused with the exception of selftest. Replace a call in the
memory_region live selftest with a call into a corresponding
function in the new migrate code.
Signed-off-by: default avatarThomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: default avatarMatthew Auld <matthew.auld@intel.com>
Signed-off-by: default avatarMatthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210617063018.92802-13-thomas.hellstrom@linux.intel.com
parent 57143f2e
Show whitespace changes
Inline Side-by-side
Showing with 14 additions and 1107 deletions
drivers/gpu/drm/i915/Makefile
View file @ 99919be7
......@@ -143,7 +143,6 @@ gem-y += \
gem/i915_gem_execbuffer.o \
gem/i915_gem_internal.o \
gem/i915_gem_object.o \
gem/i915_gem_object_blt.o \
gem/i915_gem_lmem.o \
gem/i915_gem_mman.o \
gem/i915_gem_pages.o \
......
drivers/gpu/drm/i915/gem/i915_gem_object_blt.c deleted 100644 → 0
View file @ 57143f2e
// SPDX-License-Identifier: MIT
/*
* Copyright © 2019 Intel Corporation
*/
#include "i915_drv.h"
#include "gt/intel_context.h"
#include "gt/intel_engine_pm.h"
#include "gt/intel_gpu_commands.h"
#include "gt/intel_gt.h"
#include "gt/intel_gt_buffer_pool.h"
#include "gt/intel_ring.h"
#include "i915_gem_clflush.h"
#include "i915_gem_object_blt.h"
struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
struct i915_vma *vma,
struct i915_gem_ww_ctx *ww,
u32 value)
{
struct drm_i915_private *i915 = ce->vm->i915;
const u32 block_size = SZ_8M; /* ~1ms at 8GiB/s preemption delay */
struct intel_gt_buffer_pool_node *pool;
struct i915_vma *batch;
u64 offset;
u64 count;
u64 rem;
u32 size;
u32 *cmd;
int err;
GEM_BUG_ON(intel_engine_is_virtual(ce->engine));
intel_engine_pm_get(ce->engine);
count = div_u64(round_up(vma->size, block_size), block_size);
size = (1 + 8 * count) * sizeof(u32);
size = round_up(size, PAGE_SIZE);
pool = intel_gt_get_buffer_pool(ce->engine->gt, size, I915_MAP_WC);
if (IS_ERR(pool)) {
err = PTR_ERR(pool);
goto out_pm;
}
err = i915_gem_object_lock(pool->obj, ww);
if (err)
goto out_put;
batch = i915_vma_instance(pool->obj, ce->vm, NULL);
if (IS_ERR(batch)) {
err = PTR_ERR(batch);
goto out_put;
}
err = i915_vma_pin_ww(batch, ww, 0, 0, PIN_USER);
if (unlikely(err))
goto out_put;
/* we pinned the pool, mark it as such */
intel_gt_buffer_pool_mark_used(pool);
cmd = i915_gem_object_pin_map(pool->obj, pool->type);
if (IS_ERR(cmd)) {
err = PTR_ERR(cmd);
goto out_unpin;
}
rem = vma->size;
offset = vma->node.start;
do {
u32 size = min_t(u64, rem, block_size);
GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
if (GRAPHICS_VER(i915) >= 8) {
*cmd++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (7 - 2);
*cmd++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE;
*cmd++ = 0;
*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
*cmd++ = lower_32_bits(offset);
*cmd++ = upper_32_bits(offset);
*cmd++ = value;
} else {
*cmd++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (6 - 2);
*cmd++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE;
*cmd++ = 0;
*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
*cmd++ = offset;
*cmd++ = value;
}
/* Allow ourselves to be preempted in between blocks. */
*cmd++ = MI_ARB_CHECK;
offset += size;
rem -= size;
} while (rem);
*cmd = MI_BATCH_BUFFER_END;
i915_gem_object_flush_map(pool->obj);
i915_gem_object_unpin_map(pool->obj);
intel_gt_chipset_flush(ce->vm->gt);
batch->private = pool;
return batch;
out_unpin:
i915_vma_unpin(batch);
out_put:
intel_gt_buffer_pool_put(pool);
out_pm:
intel_engine_pm_put(ce->engine);
return ERR_PTR(err);
}
int intel_emit_vma_mark_active(struct i915_vma *vma, struct i915_request *rq)
{
int err;
err = i915_request_await_object(rq, vma->obj, false);
if (err == 0)
err = i915_vma_move_to_active(vma, rq, 0);
if (unlikely(err))
return err;
return intel_gt_buffer_pool_mark_active(vma->private, rq);
}
void intel_emit_vma_release(struct intel_context *ce, struct i915_vma *vma)
{
i915_vma_unpin(vma);
intel_gt_buffer_pool_put(vma->private);
intel_engine_pm_put(ce->engine);
}
static int
move_obj_to_gpu(struct drm_i915_gem_object *obj,
struct i915_request *rq,
bool write)
{
if (obj->cache_dirty & ~obj->cache_coherent)
i915_gem_clflush_object(obj, 0);
return i915_request_await_object(rq, obj, write);
}
int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
struct intel_context *ce,
u32 value)
{
struct i915_gem_ww_ctx ww;
struct i915_request *rq;
struct i915_vma *batch;
struct i915_vma *vma;
int err;
vma = i915_vma_instance(obj, ce->vm, NULL);
if (IS_ERR(vma))
return PTR_ERR(vma);
i915_gem_ww_ctx_init(&ww, true);
intel_engine_pm_get(ce->engine);
retry:
err = i915_gem_object_lock(obj, &ww);
if (err)
goto out;
err = intel_context_pin_ww(ce, &ww);
if (err)
goto out;
err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_USER);
if (err)
goto out_ctx;
batch = intel_emit_vma_fill_blt(ce, vma, &ww, value);
if (IS_ERR(batch)) {
err = PTR_ERR(batch);
goto out_vma;
}
rq = i915_request_create(ce);
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
goto out_batch;
}
err = intel_emit_vma_mark_active(batch, rq);
if (unlikely(err))
goto out_request;
err = move_obj_to_gpu(vma->obj, rq, true);
if (err == 0)
err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
if (unlikely(err))
goto out_request;
if (ce->engine->emit_init_breadcrumb)
err = ce->engine->emit_init_breadcrumb(rq);
if (likely(!err))
err = ce->engine->emit_bb_start(rq,
batch->node.start,
batch->node.size,
0);
out_request:
if (unlikely(err))
i915_request_set_error_once(rq, err);
i915_request_add(rq);
out_batch:
intel_emit_vma_release(ce, batch);
out_vma:
i915_vma_unpin(vma);
out_ctx:
intel_context_unpin(ce);
out:
if (err == -EDEADLK) {
err = i915_gem_ww_ctx_backoff(&ww);
if (!err)
goto retry;
}
i915_gem_ww_ctx_fini(&ww);
intel_engine_pm_put(ce->engine);
return err;
}
/* Wa_1209644611:icl,ehl */
static bool wa_1209644611_applies(struct drm_i915_private *i915, u32 size)
{
u32 height = size >> PAGE_SHIFT;
if (GRAPHICS_VER(i915) != 11)
return false;
return height % 4 == 3 && height <= 8;
}
struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
struct i915_gem_ww_ctx *ww,
struct i915_vma *src,
struct i915_vma *dst)
{
struct drm_i915_private *i915 = ce->vm->i915;
const u32 block_size = SZ_8M; /* ~1ms at 8GiB/s preemption delay */
struct intel_gt_buffer_pool_node *pool;
struct i915_vma *batch;
u64 src_offset, dst_offset;
u64 count, rem;
u32 size, *cmd;
int err;
GEM_BUG_ON(src->size != dst->size);
GEM_BUG_ON(intel_engine_is_virtual(ce->engine));
intel_engine_pm_get(ce->engine);
count = div_u64(round_up(dst->size, block_size), block_size);
size = (1 + 11 * count) * sizeof(u32);
size = round_up(size, PAGE_SIZE);
pool = intel_gt_get_buffer_pool(ce->engine->gt, size, I915_MAP_WC);
if (IS_ERR(pool)) {
err = PTR_ERR(pool);
goto out_pm;
}
err = i915_gem_object_lock(pool->obj, ww);
if (err)
goto out_put;
batch = i915_vma_instance(pool->obj, ce->vm, NULL);
if (IS_ERR(batch)) {
err = PTR_ERR(batch);
goto out_put;
}
err = i915_vma_pin_ww(batch, ww, 0, 0, PIN_USER);
if (unlikely(err))
goto out_put;
/* we pinned the pool, mark it as such */
intel_gt_buffer_pool_mark_used(pool);
cmd = i915_gem_object_pin_map(pool->obj, pool->type);
if (IS_ERR(cmd)) {
err = PTR_ERR(cmd);
goto out_unpin;
}
rem = src->size;
src_offset = src->node.start;
dst_offset = dst->node.start;
do {
size = min_t(u64, rem, block_size);
GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
if (GRAPHICS_VER(i915) >= 9 &&
!wa_1209644611_applies(i915, size)) {
*cmd++ = GEN9_XY_FAST_COPY_BLT_CMD | (10 - 2);
*cmd++ = BLT_DEPTH_32 | PAGE_SIZE;
*cmd++ = 0;
*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
*cmd++ = lower_32_bits(dst_offset);
*cmd++ = upper_32_bits(dst_offset);
*cmd++ = 0;
*cmd++ = PAGE_SIZE;
*cmd++ = lower_32_bits(src_offset);
*cmd++ = upper_32_bits(src_offset);
} else if (GRAPHICS_VER(i915) >= 8) {
*cmd++ = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (10 - 2);
*cmd++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE;
*cmd++ = 0;
*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
*cmd++ = lower_32_bits(dst_offset);
*cmd++ = upper_32_bits(dst_offset);
*cmd++ = 0;
*cmd++ = PAGE_SIZE;
*cmd++ = lower_32_bits(src_offset);
*cmd++ = upper_32_bits(src_offset);
} else {
*cmd++ = SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (6 - 2);
*cmd++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE;
*cmd++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE;
*cmd++ = dst_offset;
*cmd++ = PAGE_SIZE;
*cmd++ = src_offset;
}
/* Allow ourselves to be preempted in between blocks. */
*cmd++ = MI_ARB_CHECK;
src_offset += size;
dst_offset += size;
rem -= size;
} while (rem);
*cmd = MI_BATCH_BUFFER_END;
i915_gem_object_flush_map(pool->obj);
i915_gem_object_unpin_map(pool->obj);
intel_gt_chipset_flush(ce->vm->gt);
batch->private = pool;
return batch;
out_unpin:
i915_vma_unpin(batch);
out_put:
intel_gt_buffer_pool_put(pool);
out_pm:
intel_engine_pm_put(ce->engine);
return ERR_PTR(err);
}
int i915_gem_object_copy_blt(struct drm_i915_gem_object *src,
struct drm_i915_gem_object *dst,
struct intel_context *ce)
{
struct i915_address_space *vm = ce->vm;
struct i915_vma *vma[2], *batch;
struct i915_gem_ww_ctx ww;
struct i915_request *rq;
int err, i;
vma[0] = i915_vma_instance(src, vm, NULL);
if (IS_ERR(vma[0]))
return PTR_ERR(vma[0]);
vma[1] = i915_vma_instance(dst, vm, NULL);
if (IS_ERR(vma[1]))
return PTR_ERR(vma[1]);
i915_gem_ww_ctx_init(&ww, true);
intel_engine_pm_get(ce->engine);
retry:
err = i915_gem_object_lock(src, &ww);
if (!err)
err = i915_gem_object_lock(dst, &ww);
if (!err)
err = intel_context_pin_ww(ce, &ww);
if (err)
goto out;
err = i915_vma_pin_ww(vma[0], &ww, 0, 0, PIN_USER);
if (err)
goto out_ctx;
err = i915_vma_pin_ww(vma[1], &ww, 0, 0, PIN_USER);
if (unlikely(err))
goto out_unpin_src;
batch = intel_emit_vma_copy_blt(ce, &ww, vma[0], vma[1]);
if (IS_ERR(batch)) {
err = PTR_ERR(batch);
goto out_unpin_dst;
}
rq = i915_request_create(ce);
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
goto out_batch;
}
err = intel_emit_vma_mark_active(batch, rq);
if (unlikely(err))
goto out_request;
for (i = 0; i < ARRAY_SIZE(vma); i++) {
err = move_obj_to_gpu(vma[i]->obj, rq, i);
if (unlikely(err))
goto out_request;
}
for (i = 0; i < ARRAY_SIZE(vma); i++) {
unsigned int flags = i ? EXEC_OBJECT_WRITE : 0;
err = i915_vma_move_to_active(vma[i], rq, flags);
if (unlikely(err))
goto out_request;
}
if (rq->engine->emit_init_breadcrumb) {
err = rq->engine->emit_init_breadcrumb(rq);
if (unlikely(err))
goto out_request;
}
err = rq->engine->emit_bb_start(rq,
batch->node.start, batch->node.size,
0);
out_request:
if (unlikely(err))
i915_request_set_error_once(rq, err);
i915_request_add(rq);
out_batch:
intel_emit_vma_release(ce, batch);
out_unpin_dst:
i915_vma_unpin(vma[1]);
out_unpin_src:
i915_vma_unpin(vma[0]);
out_ctx:
intel_context_unpin(ce);
out:
if (err == -EDEADLK) {
err = i915_gem_ww_ctx_backoff(&ww);
if (!err)
goto retry;
}
i915_gem_ww_ctx_fini(&ww);
intel_engine_pm_put(ce->engine);
return err;
}
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftests/i915_gem_object_blt.c"
#endif
drivers/gpu/drm/i915/gem/i915_gem_object_blt.h deleted 100644 → 0
View file @ 57143f2e
/* SPDX-License-Identifier: MIT */
/*
* Copyright © 2019 Intel Corporation
*/
#ifndef __I915_GEM_OBJECT_BLT_H__
#define __I915_GEM_OBJECT_BLT_H__
#include <linux/types.h>
#include "gt/intel_context.h"
#include "gt/intel_engine_pm.h"
#include "i915_vma.h"
struct drm_i915_gem_object;
struct i915_gem_ww_ctx;
struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
struct i915_vma *vma,
struct i915_gem_ww_ctx *ww,
u32 value);
struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
struct i915_gem_ww_ctx *ww,
struct i915_vma *src,
struct i915_vma *dst);
int intel_emit_vma_mark_active(struct i915_vma *vma, struct i915_request *rq);
void intel_emit_vma_release(struct intel_context *ce, struct i915_vma *vma);
int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
struct intel_context *ce,
u32 value);
int i915_gem_object_copy_blt(struct drm_i915_gem_object *src,
struct drm_i915_gem_object *dst,
struct intel_context *ce);
#endif
drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c deleted 100644 → 0
View file @ 57143f2e
// SPDX-License-Identifier: MIT
/*
* Copyright © 2019 Intel Corporation
*/
#include <linux/sort.h>
#include "gt/intel_gt.h"
#include "gt/intel_engine_user.h"
#include "i915_selftest.h"
#include "gem/i915_gem_context.h"
#include "selftests/igt_flush_test.h"
#include "selftests/i915_random.h"
#include "selftests/mock_drm.h"
#include "huge_gem_object.h"
#include "mock_context.h"
static int wrap_ktime_compare(const void *A, const void *B)
{
const ktime_t *a = A, *b = B;
return ktime_compare(*a, *b);
}
static int __perf_fill_blt(struct drm_i915_gem_object *obj)
{
struct drm_i915_private *i915 = to_i915(obj->base.dev);
int inst = 0;
do {
struct intel_engine_cs *engine;
ktime_t t[5];
int pass;
int err;
engine = intel_engine_lookup_user(i915,
I915_ENGINE_CLASS_COPY,
inst++);
if (!engine)
return 0;
intel_engine_pm_get(engine);
for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
struct intel_context *ce = engine->kernel_context;
ktime_t t0, t1;
t0 = ktime_get();
err = i915_gem_object_fill_blt(obj, ce, 0);
if (err)
break;
err = i915_gem_object_wait(obj,
I915_WAIT_ALL,
MAX_SCHEDULE_TIMEOUT);
if (err)
break;
t1 = ktime_get();
t[pass] = ktime_sub(t1, t0);
}
intel_engine_pm_put(engine);
if (err)
return err;
sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
pr_info("%s: blt %zd KiB fill: %lld MiB/s\n",
engine->name,
obj->base.size >> 10,
div64_u64(mul_u32_u32(4 * obj->base.size,
1000 * 1000 * 1000),
t[1] + 2 * t[2] + t[3]) >> 20);
} while (1);
}
static int perf_fill_blt(void *arg)
{
struct drm_i915_private *i915 = arg;
static const unsigned long sizes[] = {
SZ_4K,
SZ_64K,
SZ_2M,
SZ_64M
};
int i;
for (i = 0; i < ARRAY_SIZE(sizes); i++) {
struct drm_i915_gem_object *obj;
int err;
obj = i915_gem_object_create_internal(i915, sizes[i]);
if (IS_ERR(obj))
return PTR_ERR(obj);
err = __perf_fill_blt(obj);
i915_gem_object_put(obj);
if (err)
return err;
}
return 0;
}
static int __perf_copy_blt(struct drm_i915_gem_object *src,
struct drm_i915_gem_object *dst)
{
struct drm_i915_private *i915 = to_i915(src->base.dev);
int inst = 0;
do {
struct intel_engine_cs *engine;
ktime_t t[5];
int pass;
int err = 0;
engine = intel_engine_lookup_user(i915,
I915_ENGINE_CLASS_COPY,
inst++);
if (!engine)
return 0;
intel_engine_pm_get(engine);
for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
struct intel_context *ce = engine->kernel_context;
ktime_t t0, t1;
t0 = ktime_get();
err = i915_gem_object_copy_blt(src, dst, ce);
if (err)
break;
err = i915_gem_object_wait(dst,
I915_WAIT_ALL,
MAX_SCHEDULE_TIMEOUT);
if (err)
break;
t1 = ktime_get();
t[pass] = ktime_sub(t1, t0);
}
intel_engine_pm_put(engine);
if (err)
return err;
sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
pr_info("%s: blt %zd KiB copy: %lld MiB/s\n",
engine->name,
src->base.size >> 10,
div64_u64(mul_u32_u32(4 * src->base.size,
1000 * 1000 * 1000),
t[1] + 2 * t[2] + t[3]) >> 20);
} while (1);
}
static int perf_copy_blt(void *arg)
{
struct drm_i915_private *i915 = arg;
static const unsigned long sizes[] = {
SZ_4K,
SZ_64K,
SZ_2M,
SZ_64M
};
int i;
for (i = 0; i < ARRAY_SIZE(sizes); i++) {
struct drm_i915_gem_object *src, *dst;
int err;
src = i915_gem_object_create_internal(i915, sizes[i]);
if (IS_ERR(src))
return PTR_ERR(src);
dst = i915_gem_object_create_internal(i915, sizes[i]);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto err_src;
}
err = __perf_copy_blt(src, dst);
i915_gem_object_put(dst);
err_src:
i915_gem_object_put(src);
if (err)
return err;
}
return 0;
}
struct igt_thread_arg {
struct intel_engine_cs *engine;
struct i915_gem_context *ctx;
struct file *file;
struct rnd_state prng;
unsigned int n_cpus;
};
static int igt_fill_blt_thread(void *arg)
{
struct igt_thread_arg *thread = arg;
struct intel_engine_cs *engine = thread->engine;
struct rnd_state *prng = &thread->prng;
struct drm_i915_gem_object *obj;
struct i915_gem_context *ctx;
struct intel_context *ce;
unsigned int prio;
IGT_TIMEOUT(end);
u64 total, max;
int err;
ctx = thread->ctx;
if (!ctx) {
ctx = live_context_for_engine(engine, thread->file);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
ctx->sched.priority = prio;
}
ce = i915_gem_context_get_engine(ctx, 0);
GEM_BUG_ON(IS_ERR(ce));
/*
* If we have a tiny shared address space, like for the GGTT
* then we can't be too greedy.
*/
max = ce->vm->total;
if (i915_is_ggtt(ce->vm) || thread->ctx)
max = div_u64(max, thread->n_cpus);
max >>= 4;
total = PAGE_SIZE;
do {
/* Aim to keep the runtime under reasonable bounds! */
const u32 max_phys_size = SZ_64K;
u32 val = prandom_u32_state(prng);
u32 phys_sz;
u32 sz;
u32 *vaddr;
u32 i;
total = min(total, max);
sz = i915_prandom_u32_max_state(total, prng) + 1;
phys_sz = sz % max_phys_size + 1;
sz = round_up(sz, PAGE_SIZE);
phys_sz = round_up(phys_sz, PAGE_SIZE);
phys_sz = min(phys_sz, sz);
pr_debug("%s with phys_sz= %x, sz=%x, val=%x\n", __func__,
phys_sz, sz, val);
obj = huge_gem_object(engine->i915, phys_sz, sz);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto err_flush;
}
vaddr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB);
if (IS_ERR(vaddr)) {
err = PTR_ERR(vaddr);
goto err_put;
}
/*
* Make sure the potentially async clflush does its job, if
* required.
*/
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;
err = i915_gem_object_fill_blt(obj, ce, val);
if (err)
goto err_unpin;
err = i915_gem_object_wait(obj, 0, MAX_SCHEDULE_TIMEOUT);
if (err)
goto err_unpin;
for (i = 0; i < huge_gem_object_phys_size(obj) / sizeof(u32); i += 17) {
if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
drm_clflush_virt_range(&vaddr[i], sizeof(vaddr[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(obj);
i915_gem_object_put(obj);
total <<= 1;
} while (!time_after(jiffies, end));
goto err_flush;
err_unpin:
i915_gem_object_unpin_map(obj);
err_put:
i915_gem_object_put(obj);
err_flush:
if (err == -ENOMEM)
err = 0;
intel_context_put(ce);
return err;
}
static int igt_copy_blt_thread(void *arg)
{
struct igt_thread_arg *thread = arg;
struct intel_engine_cs *engine = thread->engine;
struct rnd_state *prng = &thread->prng;
struct drm_i915_gem_object *src, *dst;
struct i915_gem_context *ctx;
struct intel_context *ce;
unsigned int prio;
IGT_TIMEOUT(end);
u64 total, max;
int err;
ctx = thread->ctx;
if (!ctx) {
ctx = live_context_for_engine(engine, thread->file);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
ctx->sched.priority = prio;
}
ce = i915_gem_context_get_engine(ctx, 0);
GEM_BUG_ON(IS_ERR(ce));
/*
* If we have a tiny shared address space, like for the GGTT
* then we can't be too greedy.
*/
max = ce->vm->total;
if (i915_is_ggtt(ce->vm) || thread->ctx)
max = div_u64(max, thread->n_cpus);
max >>= 4;
total = PAGE_SIZE;
do {
/* Aim to keep the runtime under reasonable bounds! */
const u32 max_phys_size = SZ_64K;
u32 val = prandom_u32_state(prng);
u32 phys_sz;
u32 sz;
u32 *vaddr;
u32 i;
total = min(total, max);
sz = i915_prandom_u32_max_state(total, prng) + 1;
phys_sz = sz % max_phys_size + 1;
sz = round_up(sz, PAGE_SIZE);
phys_sz = round_up(phys_sz, PAGE_SIZE);
phys_sz = min(phys_sz, sz);
pr_debug("%s with phys_sz= %x, sz=%x, val=%x\n", __func__,
phys_sz, sz, val);
src = huge_gem_object(engine->i915, phys_sz, sz);
if (IS_ERR(src)) {
err = PTR_ERR(src);
goto err_flush;
}
vaddr = i915_gem_object_pin_map_unlocked(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(engine->i915, phys_sz, sz);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto err_put_src;
}
vaddr = i915_gem_object_pin_map_unlocked(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;
err = i915_gem_object_copy_blt(src, dst, ce);
if (err)
goto err_unpin;
err = i915_gem_object_wait(dst, 0, MAX_SCHEDULE_TIMEOUT);
if (err)
goto err_unpin;
for (i = 0; i < huge_gem_object_phys_size(dst) / sizeof(u32); i += 17) {
if (!(dst->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
drm_clflush_virt_range(&vaddr[i], sizeof(vaddr[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);
total <<= 1;
} 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;
intel_context_put(ce);
return err;
}
static int igt_threaded_blt(struct intel_engine_cs *engine,
int (*blt_fn)(void *arg),
unsigned int flags)
#define SINGLE_CTX BIT(0)
{
struct igt_thread_arg *thread;
struct task_struct **tsk;
unsigned int n_cpus, i;
I915_RND_STATE(prng);
int err = 0;
n_cpus = num_online_cpus() + 1;
tsk = kcalloc(n_cpus, sizeof(struct task_struct *), GFP_KERNEL);
if (!tsk)
return 0;
thread = kcalloc(n_cpus, sizeof(struct igt_thread_arg), GFP_KERNEL);
if (!thread)
goto out_tsk;
thread[0].file = mock_file(engine->i915);
if (IS_ERR(thread[0].file)) {
err = PTR_ERR(thread[0].file);
goto out_thread;
}
if (flags & SINGLE_CTX) {
thread[0].ctx = live_context_for_engine(engine, thread[0].file);
if (IS_ERR(thread[0].ctx)) {
err = PTR_ERR(thread[0].ctx);
goto out_file;
}
}
for (i = 0; i < n_cpus; ++i) {
thread[i].engine = engine;
thread[i].file = thread[0].file;
thread[i].ctx = thread[0].ctx;
thread[i].n_cpus = n_cpus;
thread[i].prng =
I915_RND_STATE_INITIALIZER(prandom_u32_state(&prng));
tsk[i] = kthread_run(blt_fn, &thread[i], "igt/blt-%d", i);
if (IS_ERR(tsk[i])) {
err = PTR_ERR(tsk[i]);
break;
}
get_task_struct(tsk[i]);
}
yield(); /* start all threads before we kthread_stop() */
for (i = 0; i < n_cpus; ++i) {
int status;
if (IS_ERR_OR_NULL(tsk[i]))
continue;
status = kthread_stop(tsk[i]);
if (status && !err)
err = status;
put_task_struct(tsk[i]);
}
out_file:
fput(thread[0].file);
out_thread:
kfree(thread);
out_tsk:
kfree(tsk);
return err;
}
static int test_copy_engines(struct drm_i915_private *i915,
int (*fn)(void *arg),
unsigned int flags)
{
struct intel_engine_cs *engine;
int ret;
for_each_uabi_class_engine(engine, I915_ENGINE_CLASS_COPY, i915) {
ret = igt_threaded_blt(engine, fn, flags);
if (ret)
return ret;
}
return 0;
}
static int igt_fill_blt(void *arg)
{
return test_copy_engines(arg, igt_fill_blt_thread, 0);
}
static int igt_fill_blt_ctx0(void *arg)
{
return test_copy_engines(arg, igt_fill_blt_thread, SINGLE_CTX);
}
static int igt_copy_blt(void *arg)
{
return test_copy_engines(arg, igt_copy_blt_thread, 0);
}
static int igt_copy_blt_ctx0(void *arg)
{
return test_copy_engines(arg, igt_copy_blt_thread, SINGLE_CTX);
}
int i915_gem_object_blt_live_selftests(struct drm_i915_private *i915)
{
static const struct i915_subtest tests[] = {
SUBTEST(igt_fill_blt),
SUBTEST(igt_fill_blt_ctx0),
SUBTEST(igt_copy_blt),
SUBTEST(igt_copy_blt_ctx0),
};
if (intel_gt_is_wedged(&i915->gt))
return 0;
return i915_live_subtests(tests, i915);
}
int i915_gem_object_blt_perf_selftests(struct drm_i915_private *i915)
{
static const struct i915_subtest tests[] = {
SUBTEST(perf_fill_blt),
SUBTEST(perf_copy_blt),
};
if (intel_gt_is_wedged(&i915->gt))
return 0;
return i915_live_subtests(tests, i915);
}
drivers/gpu/drm/i915/selftests/i915_live_selftests.h
View file @ 99919be7
......@@ -39,7 +39,6 @@ selftest(evict, i915_gem_evict_live_selftests)
selftest(hugepages, i915_gem_huge_page_live_selftests)
selftest(gem_contexts, i915_gem_context_live_selftests)
selftest(gem_execbuf, i915_gem_execbuffer_live_selftests)
selftest(blt, i915_gem_object_blt_live_selftests)
selftest(client, i915_gem_client_blt_live_selftests)
selftest(reset, intel_reset_live_selftests)
selftest(memory_region, intel_memory_region_live_selftests)
......
drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
View file @ 99919be7
......@@ -18,5 +18,4 @@
selftest(engine_cs, intel_engine_cs_perf_selftests)
selftest(request, i915_request_perf_selftests)
selftest(migrate, intel_migrate_perf_selftests)
selftest(blt, i915_gem_object_blt_perf_selftests)
selftest(region, intel_memory_region_perf_selftests)
drivers/gpu/drm/i915/selftests/intel_memory_region.c
View file @ 99919be7
......@@ -15,12 +15,13 @@
#include "gem/i915_gem_context.h"
#include "gem/i915_gem_lmem.h"
#include "gem/i915_gem_region.h"
#include "gem/i915_gem_object_blt.h"
#include "gem/selftests/igt_gem_utils.h"
#include "gem/selftests/mock_context.h"
#include "gt/intel_engine_pm.h"
#include "gt/intel_engine_user.h"
#include "gt/intel_gt.h"
#include "i915_buddy.h"
#include "gt/intel_migrate.h"
#include "i915_memcpy.h"
#include "i915_ttm_buddy_manager.h"
#include "selftests/igt_flush_test.h"
......@@ -808,6 +809,7 @@ static int igt_lmem_write_cpu(void *arg)
PAGE_SIZE - 64,
};
struct intel_engine_cs *engine;
struct i915_request *rq;
u32 *vaddr;
u32 sz;
u32 i;
......@@ -834,14 +836,19 @@ static int igt_lmem_write_cpu(void *arg)
goto out_put;
}
i915_gem_object_lock(obj, NULL);
/* Put the pages into a known state -- from the gpu for added fun */
intel_engine_pm_get(engine);
err = i915_gem_object_fill_blt(obj, engine->kernel_context, 0xdeadbeaf);
intel_engine_pm_put(engine);
if (err)
goto out_unpin;
err = intel_context_migrate_clear(engine->gt->migrate.context, NULL,
obj->mm.pages->sgl, I915_CACHE_NONE,
true, 0xdeadbeaf, &rq);
if (rq) {
dma_resv_add_excl_fence(obj->base.resv, &rq->fence);
i915_request_put(rq);
}
i915_gem_object_lock(obj, NULL);
intel_engine_pm_put(engine);
if (!err)
err = i915_gem_object_set_to_wc_domain(obj, true);
i915_gem_object_unlock(obj);
if (err)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7