Some of the WA are to be applied during context save but before restore and
some at the end of context save/restore but before executing the instructions
in the ring, WA batch buffers are created for this purpose and these WA cannot
be applied using normal means. Each context has two registers to load the
offsets of these batch buffers. If they are non-zero, HW understands that it
need to execute these batches.
v1: In this version two separate ring_buffer objects were used to load WA
instructions for indirect and per context batch buffers and they were part
of every context.
v2: Chris suggested to include additional page in context and use it to load
these WA instead of creating separate objects. This will simplify lot of things
as we need not explicity pin/unpin them. Thomas Daniel further pointed that GuC
is planning to use a similar setup to share data between GuC and driver and
WA batch buffers can probably share that page. However after discussions with
Dave who is implementing GuC changes, he suggested to use an independent page
for the reasons - GuC area might grow and these WA are initialized only once and
are not changed afterwards so we can share them share across all contexts.
The page is updated with WA during render ring init. This has an advantage of
not adding more special cases to default_context.
The size of indirect and percontext batch buffers are not fixed during init,
the functions that load instructions are modified to report the no of commands
inserted and the size is now calculated after the batch is updated.
The functions also accept an offset field which is helpful if we would like to
have multiple batches at different offsets within the page and select them
based on some criteria. This is not a requirement at this point but could
help in future (Dave).
(Thanks to Chris, Dave and Thomas for their reviews and inputs)
Signed-off-by: Rafael Barbalho <rafael.barbalho@xxxxxxxxx>
Signed-off-by: Arun Siluvery <arun.siluvery@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/intel_lrc.c | 179 +++++++++++++++++++++++++++++++-
drivers/gpu/drm/i915/intel_ringbuffer.h | 18 ++++
2 files changed, 193 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0413b8f..cad274a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -211,6 +211,7 @@ enum {
FAULT_AND_CONTINUE /* Unsupported */
};
#define GEN8_CTX_ID_SHIFT 32
+#define CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT 0x17
static int intel_lr_context_pin(struct intel_engine_cs *ring,
struct intel_context *ctx);
@@ -1077,6 +1078,109 @@ static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
return 0;
}
+static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring,
+ uint32_t offset,
+ uint32_t *num_dwords)
+{
+ uint32_t index;
+ struct page *page;
+ uint32_t *cmd;
+
+ page = i915_gem_object_get_page(ring->wa_ctx.obj, 0);
+ cmd = kmap_atomic(page);
+
+ index = offset;
+
+ /* FIXME: fill one cacheline with NOOPs.
+ * Replace these instructions with WA
+ */
+ while (index < (offset + 16))
+ cmd[index++] = MI_NOOP;
+
+ /*
+ * MI_BATCH_BUFFER_END is not required in Indirect ctx BB because
+ * execution depends on the length specified in terms of cache lines
+ * in the register CTX_RCS_INDIRECT_CTX
+ */
+
+ kunmap_atomic(cmd);
+
+ if (index > (PAGE_SIZE / sizeof(uint32_t)))
+ return -EINVAL;
+
+ *num_dwords = index - offset;
+
+ return 0;
+}
+
+static int gen8_init_perctx_bb(struct intel_engine_cs *ring,
+ uint32_t offset,
+ uint32_t *num_dwords)
+{
+ uint32_t index;
+ struct page *page;
+ uint32_t *cmd;
+
+ page = i915_gem_object_get_page(ring->wa_ctx.obj, 0);
+ cmd = kmap_atomic(page);
+
+ index = offset;
+
+ /* FIXME: fill one cacheline with NOOPs.
+ * Replace these instructions with WA
+ */
+ while (index < (offset + 16))
+ cmd[index++] = MI_NOOP;
+
+ cmd[index - 1] = MI_BATCH_BUFFER_END;
+
+ kunmap_atomic(cmd);
+
+ if (index > (PAGE_SIZE / sizeof(uint32_t)))
+ return -EINVAL;
+
+ *num_dwords = index - offset;
+
+ return 0;
+}
+
+static int intel_init_workaround_bb(struct intel_engine_cs *ring)
+{
+ int ret;
+ uint32_t num_dwords;
+ struct i915_ctx_workarounds *wa_ctx = &ring->wa_ctx;
+
+ if (ring->scratch.obj == NULL) {
+ DRM_ERROR("scratch page not allocated for %s\n", ring->name);
+ return -EINVAL;
+ }
+
+ if (INTEL_INFO(ring->dev)->gen == 8) {
+ wa_ctx->indctx_batch_offset = 0;
+
+ ret = gen8_init_indirectctx_bb(ring,
+ wa_ctx->indctx_batch_offset,
+ &num_dwords);
+ if (ret)
+ return ret;
+
+ wa_ctx->indctx_batch_size = round_up(num_dwords, CACHELINE_DWORDS);
+ wa_ctx->perctx_batch_offset = wa_ctx->indctx_batch_size;
+
+ ret = gen8_init_perctx_bb(ring,
+ wa_ctx->perctx_batch_offset,
+ &num_dwords);
+ if (ret)
+ return ret;
+ } else {
+ WARN(INTEL_INFO(ring->dev)->gen >= 8,
+ "WA batch buffer is not initialized for Gen%d\n",
+ INTEL_INFO(ring->dev)->gen);
+ }
+
+ return 0;
+}
+
static int gen8_init_common_ring(struct intel_engine_cs *ring)
{
struct drm_device *dev = ring->dev;
@@ -1382,6 +1486,40 @@ static int gen8_init_rcs_context(struct intel_engine_cs *ring,
return intel_lr_context_render_state_init(ring, ctx);
}
+static int lrc_setup_wa_ctx_obj(struct intel_engine_cs *ring, u32 size)
+{
+ int ret;
+ struct drm_device *dev = ring->dev;
+
+ WARN_ON(ring->id != RCS);
+
+ size = roundup(size, PAGE_SIZE);
+ ring->wa_ctx.obj = i915_gem_alloc_object(dev, size);
+ if (!ring->wa_ctx.obj) {
+ DRM_DEBUG_DRIVER("alloc LRC WA ctx backing obj failed.\n");
+ return -ENOMEM;
+ }
+
+ ret = i915_gem_obj_ggtt_pin(ring->wa_ctx.obj, GEN8_LR_CONTEXT_ALIGN, 0);
+ if (ret) {
+ DRM_DEBUG_DRIVER("pin LRC WA ctx backing obj failed: %d\n",
+ ret);
+ drm_gem_object_unreference(&ring->wa_ctx.obj->base);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void lrc_destroy_wa_ctx_obj(struct intel_engine_cs *ring)
+{
+ WARN_ON(ring->id != RCS);
+
+ i915_gem_object_ggtt_unpin(ring->wa_ctx.obj);
+ drm_gem_object_unreference(&ring->wa_ctx.obj->base);
+ ring->wa_ctx.obj = NULL;
+}
+
/**
* intel_logical_ring_cleanup() - deallocate the Engine Command Streamer
*
@@ -1474,7 +1612,29 @@ static int logical_render_ring_init(struct drm_device *dev)
if (ret)
return ret;
- return intel_init_pipe_control(ring);
+ if (INTEL_INFO(ring->dev)->gen >= 8) {
+ ret = lrc_setup_wa_ctx_obj(ring, PAGE_SIZE);
+ if (ret) {
+ DRM_DEBUG_DRIVER("Failed to setup context WA page: %d\n",
+ ret);
+ return ret;
+ }
+
+ ret = intel_init_workaround_bb(ring);
+ if (ret) {
+ lrc_destroy_wa_ctx_obj(ring);
+ DRM_ERROR("WA batch buffers are not initialized: %d\n",
+ ret);
+ }
+ }
+
+ ret = intel_init_pipe_control(ring);
+ if (ret) {
+ if (ring->wa_ctx.obj)
+ lrc_destroy_wa_ctx_obj(ring);
+ }
+
+ return ret;
}
static int logical_bsd_ring_init(struct drm_device *dev)
@@ -1754,15 +1914,26 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o
reg_state[CTX_SECOND_BB_STATE] = ring->mmio_base + 0x118;
reg_state[CTX_SECOND_BB_STATE+1] = 0;
if (ring->id == RCS) {
- /* TODO: according to BSpec, the register state context
- * for CHV does not have these. OTOH, these registers do
- * exist in CHV. I'm waiting for a clarification */
reg_state[CTX_BB_PER_CTX_PTR] = ring->mmio_base + 0x1c0;
reg_state[CTX_BB_PER_CTX_PTR+1] = 0;
reg_state[CTX_RCS_INDIRECT_CTX] = ring->mmio_base + 0x1c4;
reg_state[CTX_RCS_INDIRECT_CTX+1] = 0;
reg_state[CTX_RCS_INDIRECT_CTX_OFFSET] = ring->mmio_base + 0x1c8;
reg_state[CTX_RCS_INDIRECT_CTX_OFFSET+1] = 0;
+ if (ring->wa_ctx.obj) {
+ reg_state[CTX_RCS_INDIRECT_CTX+1] =
+ (i915_gem_obj_ggtt_offset(ring->wa_ctx.obj) +
+ ring->wa_ctx.indctx_batch_offset * sizeof(uint32_t)) |
+ (ring->wa_ctx.indctx_batch_size / CACHELINE_DWORDS);
+
+ reg_state[CTX_RCS_INDIRECT_CTX_OFFSET+1] =
+ CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT << 6;
+
+ reg_state[CTX_BB_PER_CTX_PTR+1] =
+ (i915_gem_obj_ggtt_offset(ring->wa_ctx.obj) +
+ ring->wa_ctx.perctx_batch_offset * sizeof(uint32_t)) |
+ 0x01;
+ }
}
reg_state[CTX_LRI_HEADER_1] = MI_LOAD_REGISTER_IMM(9);
reg_state[CTX_LRI_HEADER_1] |= MI_LRI_FORCE_POSTED;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 39f6dfc..1f38af3 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -12,6 +12,7 @@
* workarounds!
*/
#define CACHELINE_BYTES 64
+#define CACHELINE_DWORDS (CACHELINE_BYTES / sizeof(uint32_t))
/*
* Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use"
@@ -119,6 +120,22 @@ struct intel_ringbuffer {
struct intel_context;
+/*
+ * we use a single page to load ctx workarounds so all of these
+ * values are referred in terms of dwords
+ *
+ * offset field - helpful in case if we want to have multiple batches
+ * at different offsets based on some conditions. It is not a requirement
+ * at the moment but provides an option for future use.
+ * indctx_batch_size - HW expects this value in terms of cachelines
+ */
+struct i915_ctx_workarounds {
+ u32 indctx_batch_offset;
+ u32 indctx_batch_size;
+ u32 perctx_batch_offset;
+ struct drm_i915_gem_object *obj;
+};
+
struct intel_engine_cs {
const char *name;
enum intel_ring_id {
@@ -142,6 +159,7 @@ struct intel_engine_cs {
struct i915_gem_batch_pool batch_pool;
struct intel_hw_status_page status_page;
+ struct i915_ctx_workarounds wa_ctx;
unsigned irq_refcount; /* protected by dev_priv->irq_lock */
u32 irq_enable_mask; /* bitmask to enable ring interrupt */
--
2.3.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
