提交 bde13ebd 编写于 作者: C Chris Wilson

drm/i915: Introduce i915_ggtt_offset()

This little helper only exists to safely discard the upper unused 32bits
of the general 64-bit VMA address - as we know that all Global GTT
currently are less than 4GiB in size and so that the upper bits must be
zero. In many places, we use a u32 for the global GTT offset and we want
to document where we are discarding the full VMA offset.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471254551-25805-28-git-send-email-chris@chris-wilson.co.uk
上级 058d88c4
......@@ -2008,7 +2008,7 @@ static void i915_dump_lrc_obj(struct seq_file *m,
if (vma->flags & I915_VMA_GLOBAL_BIND)
seq_printf(m, "\tBound in GGTT at 0x%08x\n",
lower_32_bits(vma->node.start));
i915_ggtt_offset(vma));
if (i915_gem_object_get_pages(vma->obj)) {
seq_puts(m, "\tFailed to get pages for context object\n\n");
......
......@@ -3330,7 +3330,7 @@ static inline unsigned long
i915_gem_object_ggtt_offset(struct drm_i915_gem_object *o,
const struct i915_ggtt_view *view)
{
return i915_gem_object_to_ggtt(o, view)->node.start;
return i915_ggtt_offset(i915_gem_object_to_ggtt(o, view));
}
/* i915_gem_fence.c */
......
......@@ -767,7 +767,7 @@ i915_gem_gtt_pread(struct drm_device *dev,
i915_gem_object_pin_pages(obj);
} else {
node.start = vma->node.start;
node.start = i915_ggtt_offset(vma);
node.allocated = false;
ret = i915_gem_object_put_fence(obj);
if (ret)
......@@ -1071,7 +1071,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_private *i915,
i915_gem_object_pin_pages(obj);
} else {
node.start = vma->node.start;
node.start = i915_ggtt_offset(vma);
node.allocated = false;
ret = i915_gem_object_put_fence(obj);
if (ret)
......@@ -1712,7 +1712,7 @@ int i915_gem_fault(struct vm_area_struct *area, struct vm_fault *vmf)
goto err_unpin;
/* Finally, remap it using the new GTT offset */
pfn = ggtt->mappable_base + vma->node.start;
pfn = ggtt->mappable_base + i915_ggtt_offset(vma);
pfn >>= PAGE_SHIFT;
if (unlikely(view.type == I915_GGTT_VIEW_PARTIAL)) {
......@@ -3759,10 +3759,9 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
WARN(i915_vma_is_pinned(vma),
"bo is already pinned in ggtt with incorrect alignment:"
" offset=%08x %08x, req.alignment=%llx, req.map_and_fenceable=%d,"
" offset=%08x, req.alignment=%llx, req.map_and_fenceable=%d,"
" obj->map_and_fenceable=%d\n",
upper_32_bits(vma->node.start),
lower_32_bits(vma->node.start),
i915_ggtt_offset(vma),
alignment,
!!(flags & PIN_MAPPABLE),
obj->map_and_fenceable);
......
......@@ -631,7 +631,8 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
intel_ring_emit(ring, MI_NOOP);
intel_ring_emit(ring, MI_SET_CONTEXT);
intel_ring_emit(ring, req->ctx->engine[RCS].state->node.start | flags);
intel_ring_emit(ring,
i915_ggtt_offset(req->ctx->engine[RCS].state) | flags);
/*
* w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
* WaMiSetContext_Hang:snb,ivb,vlv
......@@ -660,7 +661,8 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
MI_STORE_REGISTER_MEM |
MI_SRM_LRM_GLOBAL_GTT);
intel_ring_emit_reg(ring, last_reg);
intel_ring_emit(ring, engine->scratch->node.start);
intel_ring_emit(ring,
i915_ggtt_offset(engine->scratch));
intel_ring_emit(ring, MI_NOOP);
}
intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
......
......@@ -272,6 +272,15 @@ static inline bool i915_vma_has_active_engine(const struct i915_vma *vma,
return vma->active & BIT(engine);
}
static inline u32 i915_ggtt_offset(const struct i915_vma *vma)
{
GEM_BUG_ON(!i915_vma_is_ggtt(vma));
GEM_BUG_ON(!vma->node.allocated);
GEM_BUG_ON(upper_32_bits(vma->node.start));
GEM_BUG_ON(upper_32_bits(vma->node.start + vma->node.size - 1));
return lower_32_bits(vma->node.start);
}
struct i915_page_dma {
struct page *page;
union {
......
......@@ -358,11 +358,11 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
/* The state page is after PPHWSP */
lrc->ring_lcra =
ce->state->node.start + LRC_STATE_PN * PAGE_SIZE;
i915_ggtt_offset(ce->state) + LRC_STATE_PN * PAGE_SIZE;
lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) |
(guc_engine_id << GUC_ELC_ENGINE_OFFSET);
lrc->ring_begin = ce->ring->vma->node.start;
lrc->ring_begin = i915_ggtt_offset(ce->ring->vma);
lrc->ring_end = lrc->ring_begin + ce->ring->size - 1;
lrc->ring_next_free_location = lrc->ring_begin;
lrc->ring_current_tail_pointer_value = 0;
......@@ -378,7 +378,7 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
* The doorbell, process descriptor, and workqueue are all parts
* of the client object, which the GuC will reference via the GGTT
*/
gfx_addr = client->vma->node.start;
gfx_addr = i915_ggtt_offset(client->vma);
desc.db_trigger_phy = sg_dma_address(client->vma->pages->sgl) +
client->doorbell_offset;
desc.db_trigger_cpu = (uintptr_t)client->client_base +
......@@ -864,7 +864,7 @@ static void guc_create_log(struct intel_guc *guc)
(GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
(GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT);
offset = vma->node.start >> PAGE_SHIFT; /* in pages */
offset = i915_ggtt_offset(vma) >> PAGE_SHIFT; /* in pages */
guc->log_flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
}
......@@ -935,7 +935,8 @@ static void guc_create_ads(struct intel_guc *guc)
policies = (void *)ads + sizeof(struct guc_ads);
init_guc_policies(policies);
ads->scheduler_policies = vma->node.start + sizeof(struct guc_ads);
ads->scheduler_policies =
i915_ggtt_offset(vma) + sizeof(struct guc_ads);
/* MMIO reg state */
reg_state = (void *)policies + sizeof(struct guc_policies);
......@@ -1063,7 +1064,7 @@ int intel_guc_suspend(struct drm_device *dev)
/* any value greater than GUC_POWER_D0 */
data[1] = GUC_POWER_D1;
/* first page is shared data with GuC */
data[2] = ctx->engine[RCS].state->node.start;
data[2] = i915_ggtt_offset(ctx->engine[RCS].state);
return host2guc_action(guc, data, ARRAY_SIZE(data));
}
......@@ -1088,7 +1089,7 @@ int intel_guc_resume(struct drm_device *dev)
data[0] = HOST2GUC_ACTION_EXIT_S_STATE;
data[1] = GUC_POWER_D0;
/* first page is shared data with GuC */
data[2] = ctx->engine[RCS].state->node.start;
data[2] = i915_ggtt_offset(ctx->engine[RCS].state);
return host2guc_action(guc, data, ARRAY_SIZE(data));
}
......@@ -3241,7 +3241,6 @@ u32 intel_fb_gtt_offset(struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj = intel_fb_obj(fb);
struct i915_ggtt_view view;
struct i915_vma *vma;
u64 offset;
intel_fill_fb_ggtt_view(&view, fb, rotation);
......@@ -3250,11 +3249,7 @@ u32 intel_fb_gtt_offset(struct drm_framebuffer *fb,
view.type))
return -1;
offset = vma->node.start;
WARN_ON(upper_32_bits(offset));
return lower_32_bits(offset);
return i915_ggtt_offset(vma);
}
static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
......@@ -11804,7 +11799,8 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
intel_ring_emit(ring, MI_STORE_REGISTER_MEM |
MI_SRM_LRM_GLOBAL_GTT);
intel_ring_emit_reg(ring, DERRMR);
intel_ring_emit(ring, req->engine->scratch->node.start + 256);
intel_ring_emit(ring,
i915_ggtt_offset(req->engine->scratch) + 256);
if (IS_GEN8(dev)) {
intel_ring_emit(ring, 0);
intel_ring_emit(ring, MI_NOOP);
......
......@@ -268,8 +268,8 @@ int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
goto err_unref;
engine->scratch = vma;
DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08llx\n",
engine->name, vma->node.start);
DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
engine->name, i915_ggtt_offset(vma));
return 0;
err_unref:
......
......@@ -248,7 +248,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
info->apertures->ranges[0].base = dev->mode_config.fb_base;
info->apertures->ranges[0].size = ggtt->mappable_end;
info->fix.smem_start = dev->mode_config.fb_base + vma->node.start;
info->fix.smem_start = dev->mode_config.fb_base + i915_ggtt_offset(vma);
info->fix.smem_len = vma->node.size;
vaddr = i915_vma_pin_iomap(vma);
......@@ -275,8 +275,8 @@ static int intelfb_create(struct drm_fb_helper *helper,
/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08llx\n",
fb->width, fb->height, vma->node.start);
DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x\n",
fb->width, fb->height, i915_ggtt_offset(vma));
ifbdev->vma = vma;
mutex_unlock(&dev->struct_mutex);
......
......@@ -194,14 +194,14 @@ static void set_guc_init_params(struct drm_i915_private *dev_priv)
}
if (guc->ads_vma) {
u32 ads = (u32)guc->ads_vma->node.start >> PAGE_SHIFT;
u32 ads = i915_ggtt_offset(guc->ads_vma) >> PAGE_SHIFT;
params[GUC_CTL_DEBUG] |= ads << GUC_ADS_ADDR_SHIFT;
params[GUC_CTL_DEBUG] |= GUC_ADS_ENABLED;
}
/* If GuC submission is enabled, set up additional parameters here */
if (i915.enable_guc_submission) {
u32 pgs = dev_priv->guc.ctx_pool_vma->node.start;
u32 pgs = i915_ggtt_offset(dev_priv->guc.ctx_pool_vma);
u32 ctx_in_16 = GUC_MAX_GPU_CONTEXTS / 16;
pgs >>= PAGE_SHIFT;
......@@ -271,7 +271,7 @@ static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv,
I915_WRITE(DMA_COPY_SIZE, guc_fw->header_size + guc_fw->ucode_size);
/* Set the source address for the new blob */
offset = vma->node.start + guc_fw->header_offset;
offset = i915_ggtt_offset(vma) + guc_fw->header_offset;
I915_WRITE(DMA_ADDR_0_LOW, lower_32_bits(offset));
I915_WRITE(DMA_ADDR_0_HIGH, upper_32_bits(offset) & 0xFFFF);
......
......@@ -315,7 +315,7 @@ intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
desc = ctx->desc_template; /* bits 3-4 */
desc |= engine->ctx_desc_template; /* bits 0-11 */
desc |= ce->state->node.start + LRC_PPHWSP_PN * PAGE_SIZE;
desc |= i915_ggtt_offset(ce->state) + LRC_PPHWSP_PN * PAGE_SIZE;
/* bits 12-31 */
desc |= (u64)ctx->hw_id << GEN8_CTX_ID_SHIFT; /* bits 32-52 */
......@@ -792,7 +792,8 @@ static int intel_lr_context_pin(struct i915_gem_context *ctx,
intel_lr_context_descriptor_update(ctx, engine);
lrc_reg_state[CTX_RING_BUFFER_START+1] = ce->ring->vma->node.start;
lrc_reg_state[CTX_RING_BUFFER_START+1] =
i915_ggtt_offset(ce->ring->vma);
ce->lrc_reg_state = lrc_reg_state;
ce->state->obj->dirty = true;
......@@ -914,7 +915,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
MI_SRM_LRM_GLOBAL_GTT));
wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
wa_ctx_emit(batch, index, engine->scratch->node.start + 256);
wa_ctx_emit(batch, index, i915_ggtt_offset(engine->scratch) + 256);
wa_ctx_emit(batch, index, 0);
wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
......@@ -932,7 +933,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8 |
MI_SRM_LRM_GLOBAL_GTT));
wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
wa_ctx_emit(batch, index, engine->scratch->node.start + 256);
wa_ctx_emit(batch, index, i915_ggtt_offset(engine->scratch) + 256);
wa_ctx_emit(batch, index, 0);
return index;
......@@ -993,7 +994,7 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *engine,
/* WaClearSlmSpaceAtContextSwitch:bdw,chv */
/* Actual scratch location is at 128 bytes offset */
scratch_addr = engine->scratch->node.start + 2 * CACHELINE_BYTES;
scratch_addr = i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;
wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
......@@ -1073,7 +1074,7 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine,
/* Actual scratch location is at 128 bytes offset */
if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) {
u32 scratch_addr =
engine->scratch->node.start + 2 * CACHELINE_BYTES;
i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;
wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
......@@ -1482,7 +1483,8 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
{
struct intel_ring *ring = request->ring;
struct intel_engine_cs *engine = request->engine;
u32 scratch_addr = engine->scratch->node.start + 2 * CACHELINE_BYTES;
u32 scratch_addr =
i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;
bool vf_flush_wa = false, dc_flush_wa = false;
u32 flags = 0;
int ret;
......@@ -1752,7 +1754,7 @@ lrc_setup_hws(struct intel_engine_cs *engine, struct i915_vma *vma)
return PTR_ERR(hws);
engine->status_page.page_addr = hws + hws_offset;
engine->status_page.ggtt_offset = vma->node.start + hws_offset;
engine->status_page.ggtt_offset = i915_ggtt_offset(vma) + hws_offset;
engine->status_page.vma = vma;
return 0;
......@@ -2020,7 +2022,7 @@ populate_lr_context(struct i915_gem_context *ctx,
RING_INDIRECT_CTX_OFFSET(engine->mmio_base), 0);
if (engine->wa_ctx.vma) {
struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx;
u32 ggtt_offset = wa_ctx->vma->node.start;
u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
reg_state[CTX_RCS_INDIRECT_CTX+1] =
(ggtt_offset + wa_ctx->indirect_ctx.offset * sizeof(uint32_t)) |
......
......@@ -801,7 +801,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
swidth = params->src_w;
swidthsw = calc_swidthsw(dev_priv, params->offset_Y, tmp_width);
sheight = params->src_h;
iowrite32(vma->node.start + params->offset_Y, &regs->OBUF_0Y);
iowrite32(i915_ggtt_offset(vma) + params->offset_Y, &regs->OBUF_0Y);
ostride = params->stride_Y;
if (params->format & I915_OVERLAY_YUV_PLANAR) {
......@@ -815,8 +815,10 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
params->src_w/uv_hscale);
swidthsw |= max_t(u32, tmp_U, tmp_V) << 16;
sheight |= (params->src_h/uv_vscale) << 16;
iowrite32(vma->node.start + params->offset_U, &regs->OBUF_0U);
iowrite32(vma->node.start + params->offset_V, &regs->OBUF_0V);
iowrite32(i915_ggtt_offset(vma) + params->offset_U,
&regs->OBUF_0U);
iowrite32(i915_ggtt_offset(vma) + params->offset_V,
&regs->OBUF_0V);
ostride |= params->stride_UV << 16;
}
......@@ -1412,7 +1414,7 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv)
ret = PTR_ERR(vma);
goto out_free_bo;
}
overlay->flip_addr = vma->node.start;
overlay->flip_addr = i915_ggtt_offset(vma);
ret = i915_gem_object_set_to_gtt_domain(reg_bo, true);
if (ret) {
......
......@@ -176,7 +176,7 @@ intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
{
struct intel_ring *ring = req->ring;
u32 scratch_addr =
req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
i915_ggtt_offset(req->engine->scratch) + 2 * CACHELINE_BYTES;
int ret;
ret = intel_ring_begin(req, 6);
......@@ -212,7 +212,7 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
{
struct intel_ring *ring = req->ring;
u32 scratch_addr =
req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
i915_ggtt_offset(req->engine->scratch) + 2 * CACHELINE_BYTES;
u32 flags = 0;
int ret;
......@@ -286,7 +286,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
{
struct intel_ring *ring = req->ring;
u32 scratch_addr =
req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
i915_ggtt_offset(req->engine->scratch) + 2 * CACHELINE_BYTES;
u32 flags = 0;
int ret;
......@@ -371,7 +371,7 @@ static int
gen8_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
{
u32 scratch_addr =
req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
i915_ggtt_offset(req->engine->scratch) + 2 * CACHELINE_BYTES;
u32 flags = 0;
int ret;
......@@ -571,7 +571,7 @@ static int init_ring_common(struct intel_engine_cs *engine)
* registers with the above sequence (the readback of the HEAD registers
* also enforces ordering), otherwise the hw might lose the new ring
* register values. */
I915_WRITE_START(engine, ring->vma->node.start);
I915_WRITE_START(engine, i915_ggtt_offset(ring->vma));
/* WaClearRingBufHeadRegAtInit:ctg,elk */
if (I915_READ_HEAD(engine))
......@@ -586,16 +586,16 @@ static int init_ring_common(struct intel_engine_cs *engine)
/* If the head is still not zero, the ring is dead */
if (wait_for((I915_READ_CTL(engine) & RING_VALID) != 0 &&
I915_READ_START(engine) == ring->vma->node.start &&
I915_READ_START(engine) == i915_ggtt_offset(ring->vma) &&
(I915_READ_HEAD(engine) & HEAD_ADDR) == 0, 50)) {
DRM_ERROR("%s initialization failed "
"ctl %08x (valid? %d) head %08x tail %08x start %08x [expected %08llx]\n",
"ctl %08x (valid? %d) head %08x tail %08x start %08x [expected %08x]\n",
engine->name,
I915_READ_CTL(engine),
I915_READ_CTL(engine) & RING_VALID,
I915_READ_HEAD(engine), I915_READ_TAIL(engine),
I915_READ_START(engine),
ring->vma->node.start);
i915_ggtt_offset(ring->vma));
ret = -EIO;
goto out;
}
......@@ -1716,7 +1716,7 @@ i830_emit_bb_start(struct drm_i915_gem_request *req,
unsigned int dispatch_flags)
{
struct intel_ring *ring = req->ring;
u32 cs_offset = req->engine->scratch->node.start;
u32 cs_offset = i915_ggtt_offset(req->engine->scratch);
int ret;
ret = intel_ring_begin(req, 6);
......@@ -1857,12 +1857,12 @@ static int init_status_page(struct intel_engine_cs *engine)
goto err;
engine->status_page.vma = vma;
engine->status_page.ggtt_offset = vma->node.start;
engine->status_page.ggtt_offset = i915_ggtt_offset(vma);
engine->status_page.page_addr =
i915_gem_object_pin_map(obj, I915_MAP_WB);
DRM_DEBUG_DRIVER("%s hws offset: 0x%08llx\n",
engine->name, vma->node.start);
DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n",
engine->name, i915_ggtt_offset(vma));
return 0;
err:
......@@ -2542,13 +2542,13 @@ static void intel_ring_init_semaphores(struct drm_i915_private *dev_priv,
}
if (INTEL_GEN(dev_priv) >= 8) {
u64 offset = dev_priv->semaphore->node.start;
u32 offset = i915_ggtt_offset(dev_priv->semaphore);
engine->semaphore.sync_to = gen8_ring_sync_to;
engine->semaphore.signal = gen8_xcs_signal;
for (i = 0; i < I915_NUM_ENGINES; i++) {
u64 ring_offset;
u32 ring_offset;
if (i != engine->id)
ring_offset = offset + GEN8_SEMAPHORE_OFFSET(engine->id, i);
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册