drm/i915/gen8: Add 4 level switching infrastructure and lrc support

In 64b (48bit canonical) PPGTT addressing, the PDP0 register contains
the base address to PML4, while the other PDP registers are ignored.

In LRC, the addressing mode must be specified in every context
descriptor, and the base address to PML4 is stored in the reg state.

v2: PML4 update in legacy context switch is left for historic reasons,
the preferred mode of operation is with lrc context based submission.
v3: s/gen8_map_page_directory/gen8_setup_page_directory and
s/gen8_map_page_directory_pointer/gen8_setup_page_directory_pointer.
Also, clflush will be needed for bxt. (Akash)
v4: Squashed lrc-specific code and use a macro to set PML4 register.
v5: Rebase after Mika's ppgtt cleanup / scratch merge patch series.
PDP update in bb_start is only for legacy 32b mode.
v6: Rebase after final merged version of Mika's ppgtt/scratch
patches.
v7: There is no need to update the pml4 register value in
execlists_update_context. (Akash)
v8: Move pd and pdp setup functions to a previous patch, they do not
belong here. (Akash)
v9: Check USES_FULL_48BIT_PPGTT instead of GEN8_CTX_ADDRESSING_MODE in
gen8_emit_bb_start to check if emit pdps is needed. (Akash)

Cc: Akash Goel <akash.goel@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+)
Reviewed-by: Akash Goel <akash.goel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 42 insertions, 18 deletions

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 5bc0ce1347ce..138964afd187 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -196,13 +196,21 @@
 	reg_state[CTX_PDP ## n ## _LDW+1] = lower_32_bits(_addr); \
 }
 
+#define ASSIGN_CTX_PML4(ppgtt, reg_state) { \
+	reg_state[CTX_PDP0_UDW + 1] = upper_32_bits(px_dma(&ppgtt->pml4)); \
+	reg_state[CTX_PDP0_LDW + 1] = lower_32_bits(px_dma(&ppgtt->pml4)); \
+}
+
 enum {
 	ADVANCED_CONTEXT = 0,
-	LEGACY_CONTEXT,
+	LEGACY_32B_CONTEXT,
 	ADVANCED_AD_CONTEXT,
 	LEGACY_64B_CONTEXT
 };
-#define GEN8_CTX_MODE_SHIFT 3
+#define GEN8_CTX_ADDRESSING_MODE_SHIFT 3
+#define GEN8_CTX_ADDRESSING_MODE(dev)  (USES_FULL_48BIT_PPGTT(dev) ?\
+		LEGACY_64B_CONTEXT :\
+		LEGACY_32B_CONTEXT)
 enum {
 	FAULT_AND_HANG = 0,
 	FAULT_AND_HALT, /* Debug only */
@@ -273,7 +281,7 @@ static uint64_t execlists_ctx_descriptor(struct drm_i915_gem_request *rq)
 	WARN_ON(lrca & 0xFFFFFFFF00000FFFULL);
 
 	desc = GEN8_CTX_VALID;
-	desc |= LEGACY_CONTEXT << GEN8_CTX_MODE_SHIFT;
+	desc |= GEN8_CTX_ADDRESSING_MODE(dev) << GEN8_CTX_ADDRESSING_MODE_SHIFT;
 	if (IS_GEN8(ctx_obj->base.dev))
 		desc |= GEN8_CTX_L3LLC_COHERENT;
 	desc |= GEN8_CTX_PRIVILEGE;
@@ -348,10 +356,12 @@ static int execlists_update_context(struct drm_i915_gem_request *rq)
 	reg_state[CTX_RING_TAIL+1] = rq->tail;
 	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj);
 
-	/* True PPGTT with dynamic page allocation: update PDP registers and
-	 * point the unallocated PDPs to the scratch page
-	 */
-	if (ppgtt) {
+	if (ppgtt && !USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
+		/* True 32b PPGTT with dynamic page allocation: update PDP
+		 * registers and point the unallocated PDPs to scratch page.
+		 * PML4 is allocated during ppgtt init, so this is not needed
+		 * in 48-bit mode.
+		 */
 		ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
 		ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
 		ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
@@ -1515,12 +1525,15 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
 	 * Ideally, we should set Force PD Restore in ctx descriptor,
 	 * but we can't. Force Restore would be a second option, but
 	 * it is unsafe in case of lite-restore (because the ctx is
-	 * not idle). */
+	 * not idle). PML4 is allocated during ppgtt init so this is
+	 * not needed in 48-bit.*/
 	if (req->ctx->ppgtt &&
 	    (intel_ring_flag(req->ring) & req->ctx->ppgtt->pd_dirty_rings)) {
-		ret = intel_logical_ring_emit_pdps(req);
-		if (ret)
-			return ret;
+		if (!USES_FULL_48BIT_PPGTT(req->i915)) {
+			ret = intel_logical_ring_emit_pdps(req);
+			if (ret)
+				return ret;
+		}
 
 		req->ctx->ppgtt->pd_dirty_rings &= ~intel_ring_flag(req->ring);
 	}
@@ -2201,13 +2214,24 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o
 	reg_state[CTX_PDP0_UDW] = GEN8_RING_PDP_UDW(ring, 0);
 	reg_state[CTX_PDP0_LDW] = GEN8_RING_PDP_LDW(ring, 0);
 
-	/* With dynamic page allocation, PDPs may not be allocated at this point,
-	 * Point the unallocated PDPs to the scratch page
-	 */
-	ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
-	ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
-	ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
-	ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
+	if (USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
+		/* 64b PPGTT (48bit canonical)
+		 * PDP0_DESCRIPTOR contains the base address to PML4 and
+		 * other PDP Descriptors are ignored.
+		 */
+		ASSIGN_CTX_PML4(ppgtt, reg_state);
+	} else {
+		/* 32b PPGTT
+		 * PDP*_DESCRIPTOR contains the base address of space supported.
+		 * With dynamic page allocation, PDPs may not be allocated at
+		 * this point. Point the unallocated PDPs to the scratch page
+		 */
+		ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
+		ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
+		ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
+		ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
+	}
+
 	if (ring->id == RCS) {
 		reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
 		reg_state[CTX_R_PWR_CLK_STATE] = GEN8_R_PWR_CLK_STATE;