/*
 * Copyright © 2014 Intel Corporation
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 *
 * Authors:
 *    Ben Widawsky <ben@bwidawsk.net>
 *    Michel Thierry <michel.thierry@intel.com>
 *    Thomas Daniel <thomas.daniel@intel.com>
 *    Oscar Mateo <oscar.mateo@intel.com>
 *
 */

/*
 * GEN8 brings an expansion of the HW contexts: "Logical Ring Contexts".
 * These expanded contexts enable a number of new abilities, especially
 * "Execlists" (also implemented in this file).
 *
 * Execlists are the new method by which, on gen8+ hardware, workloads are
 * submitted for execution (as opposed to the legacy, ringbuffer-based, method).
 */

#include <drm/drmP.h>
#include <drm/i915_drm.h>
#include "i915_drv.h"

#define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE)
#define GEN8_LR_CONTEXT_OTHER_SIZE (2 * PAGE_SIZE)

#define GEN8_LR_CONTEXT_ALIGN 4096

#define RING_ELSP(ring)			((ring)->mmio_base+0x230)
#define RING_CONTEXT_CONTROL(ring)	((ring)->mmio_base+0x244)

#define CTX_LRI_HEADER_0		0x01
#define CTX_CONTEXT_CONTROL		0x02
#define CTX_RING_HEAD			0x04
#define CTX_RING_TAIL			0x06
#define CTX_RING_BUFFER_START		0x08
#define CTX_RING_BUFFER_CONTROL		0x0a
#define CTX_BB_HEAD_U			0x0c
#define CTX_BB_HEAD_L			0x0e
#define CTX_BB_STATE			0x10
#define CTX_SECOND_BB_HEAD_U		0x12
#define CTX_SECOND_BB_HEAD_L		0x14
#define CTX_SECOND_BB_STATE		0x16
#define CTX_BB_PER_CTX_PTR		0x18
#define CTX_RCS_INDIRECT_CTX		0x1a
#define CTX_RCS_INDIRECT_CTX_OFFSET	0x1c
#define CTX_LRI_HEADER_1		0x21
#define CTX_CTX_TIMESTAMP		0x22
#define CTX_PDP3_UDW			0x24
#define CTX_PDP3_LDW			0x26
#define CTX_PDP2_UDW			0x28
#define CTX_PDP2_LDW			0x2a
#define CTX_PDP1_UDW			0x2c
#define CTX_PDP1_LDW			0x2e
#define CTX_PDP0_UDW			0x30
#define CTX_PDP0_LDW			0x32
#define CTX_LRI_HEADER_2		0x41
#define CTX_R_PWR_CLK_STATE		0x42
#define CTX_GPGPU_CSR_BASE_ADDRESS	0x44

int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists)
{
	WARN_ON(i915.enable_ppgtt == -1);

	if (enable_execlists == 0)
		return 0;

	if (HAS_LOGICAL_RING_CONTEXTS(dev) && USES_PPGTT(dev))
		return 1;

	return 0;
}

int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
			       struct intel_engine_cs *ring,
			       struct intel_context *ctx,
			       struct drm_i915_gem_execbuffer2 *args,
			       struct list_head *vmas,
			       struct drm_i915_gem_object *batch_obj,
			       u64 exec_start, u32 flags)
{
	/* TODO */
	return 0;
}

void intel_logical_ring_stop(struct intel_engine_cs *ring)
{
	/* TODO */
}

void intel_logical_ring_cleanup(struct intel_engine_cs *ring)
{
	/* TODO */
}

static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *ring)
{
	/* TODO */
	return 0;
}

static int logical_render_ring_init(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring = &dev_priv->ring[RCS];

	ring->name = "render ring";
	ring->id = RCS;
	ring->mmio_base = RENDER_RING_BASE;
	ring->irq_enable_mask =
		GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT;

	return logical_ring_init(dev, ring);
}

static int logical_bsd_ring_init(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring = &dev_priv->ring[VCS];

	ring->name = "bsd ring";
	ring->id = VCS;
	ring->mmio_base = GEN6_BSD_RING_BASE;
	ring->irq_enable_mask =
		GT_RENDER_USER_INTERRUPT << GEN8_VCS1_IRQ_SHIFT;

	return logical_ring_init(dev, ring);
}

static int logical_bsd2_ring_init(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring = &dev_priv->ring[VCS2];

	ring->name = "bds2 ring";
	ring->id = VCS2;
	ring->mmio_base = GEN8_BSD2_RING_BASE;
	ring->irq_enable_mask =
		GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT;

	return logical_ring_init(dev, ring);
}

static int logical_blt_ring_init(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring = &dev_priv->ring[BCS];

	ring->name = "blitter ring";
	ring->id = BCS;
	ring->mmio_base = BLT_RING_BASE;
	ring->irq_enable_mask =
		GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;

	return logical_ring_init(dev, ring);
}

static int logical_vebox_ring_init(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring = &dev_priv->ring[VECS];

	ring->name = "video enhancement ring";
	ring->id = VECS;
	ring->mmio_base = VEBOX_RING_BASE;
	ring->irq_enable_mask =
		GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT;

	return logical_ring_init(dev, ring);
}

int intel_logical_rings_init(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	ret = logical_render_ring_init(dev);
	if (ret)
		return ret;

	if (HAS_BSD(dev)) {
		ret = logical_bsd_ring_init(dev);
		if (ret)
			goto cleanup_render_ring;
	}

	if (HAS_BLT(dev)) {
		ret = logical_blt_ring_init(dev);
		if (ret)
			goto cleanup_bsd_ring;
	}

	if (HAS_VEBOX(dev)) {
		ret = logical_vebox_ring_init(dev);
		if (ret)
			goto cleanup_blt_ring;
	}

	if (HAS_BSD2(dev)) {
		ret = logical_bsd2_ring_init(dev);
		if (ret)
			goto cleanup_vebox_ring;
	}

	ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
	if (ret)
		goto cleanup_bsd2_ring;

	return 0;

cleanup_bsd2_ring:
	intel_logical_ring_cleanup(&dev_priv->ring[VCS2]);
cleanup_vebox_ring:
	intel_logical_ring_cleanup(&dev_priv->ring[VECS]);
cleanup_blt_ring:
	intel_logical_ring_cleanup(&dev_priv->ring[BCS]);
cleanup_bsd_ring:
	intel_logical_ring_cleanup(&dev_priv->ring[VCS]);
cleanup_render_ring:
	intel_logical_ring_cleanup(&dev_priv->ring[RCS]);

	return ret;
}

static int
populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_obj,
		    struct intel_engine_cs *ring, struct intel_ringbuffer *ringbuf)
{
	struct drm_i915_gem_object *ring_obj = ringbuf->obj;
	struct i915_hw_ppgtt *ppgtt = ctx_to_ppgtt(ctx);
	struct page *page;
	uint32_t *reg_state;
	int ret;

	ret = i915_gem_object_set_to_cpu_domain(ctx_obj, true);
	if (ret) {
		DRM_DEBUG_DRIVER("Could not set to CPU domain\n");
		return ret;
	}

	ret = i915_gem_object_get_pages(ctx_obj);
	if (ret) {
		DRM_DEBUG_DRIVER("Could not get object pages\n");
		return ret;
	}

	i915_gem_object_pin_pages(ctx_obj);

	/* The second page of the context object contains some fields which must
	 * be set up prior to the first execution. */
	page = i915_gem_object_get_page(ctx_obj, 1);
	reg_state = kmap_atomic(page);

	/* A context is actually a big batch buffer with several MI_LOAD_REGISTER_IMM
	 * commands followed by (reg, value) pairs. The values we are setting here are
	 * only for the first context restore: on a subsequent save, the GPU will
	 * recreate this batchbuffer with new values (including all the missing
	 * MI_LOAD_REGISTER_IMM commands that we are not initializing here). */
	if (ring->id == RCS)
		reg_state[CTX_LRI_HEADER_0] = MI_LOAD_REGISTER_IMM(14);
	else
		reg_state[CTX_LRI_HEADER_0] = MI_LOAD_REGISTER_IMM(11);
	reg_state[CTX_LRI_HEADER_0] |= MI_LRI_FORCE_POSTED;
	reg_state[CTX_CONTEXT_CONTROL] = RING_CONTEXT_CONTROL(ring);
	reg_state[CTX_CONTEXT_CONTROL+1] =
			_MASKED_BIT_ENABLE((1<<3) | MI_RESTORE_INHIBIT);
	reg_state[CTX_RING_HEAD] = RING_HEAD(ring->mmio_base);
	reg_state[CTX_RING_HEAD+1] = 0;
	reg_state[CTX_RING_TAIL] = RING_TAIL(ring->mmio_base);
	reg_state[CTX_RING_TAIL+1] = 0;
	reg_state[CTX_RING_BUFFER_START] = RING_START(ring->mmio_base);
	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);
	reg_state[CTX_RING_BUFFER_CONTROL] = RING_CTL(ring->mmio_base);
	reg_state[CTX_RING_BUFFER_CONTROL+1] =
			((ringbuf->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID;
	reg_state[CTX_BB_HEAD_U] = ring->mmio_base + 0x168;
	reg_state[CTX_BB_HEAD_U+1] = 0;
	reg_state[CTX_BB_HEAD_L] = ring->mmio_base + 0x140;
	reg_state[CTX_BB_HEAD_L+1] = 0;
	reg_state[CTX_BB_STATE] = ring->mmio_base + 0x110;
	reg_state[CTX_BB_STATE+1] = (1<<5);
	reg_state[CTX_SECOND_BB_HEAD_U] = ring->mmio_base + 0x11c;
	reg_state[CTX_SECOND_BB_HEAD_U+1] = 0;
	reg_state[CTX_SECOND_BB_HEAD_L] = ring->mmio_base + 0x114;
	reg_state[CTX_SECOND_BB_HEAD_L+1] = 0;
	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;
	}
	reg_state[CTX_LRI_HEADER_1] = MI_LOAD_REGISTER_IMM(9);
	reg_state[CTX_LRI_HEADER_1] |= MI_LRI_FORCE_POSTED;
	reg_state[CTX_CTX_TIMESTAMP] = ring->mmio_base + 0x3a8;
	reg_state[CTX_CTX_TIMESTAMP+1] = 0;
	reg_state[CTX_PDP3_UDW] = GEN8_RING_PDP_UDW(ring, 3);
	reg_state[CTX_PDP3_LDW] = GEN8_RING_PDP_LDW(ring, 3);
	reg_state[CTX_PDP2_UDW] = GEN8_RING_PDP_UDW(ring, 2);
	reg_state[CTX_PDP2_LDW] = GEN8_RING_PDP_LDW(ring, 2);
	reg_state[CTX_PDP1_UDW] = GEN8_RING_PDP_UDW(ring, 1);
	reg_state[CTX_PDP1_LDW] = GEN8_RING_PDP_LDW(ring, 1);
	reg_state[CTX_PDP0_UDW] = GEN8_RING_PDP_UDW(ring, 0);
	reg_state[CTX_PDP0_LDW] = GEN8_RING_PDP_LDW(ring, 0);
	reg_state[CTX_PDP3_UDW+1] = upper_32_bits(ppgtt->pd_dma_addr[3]);
	reg_state[CTX_PDP3_LDW+1] = lower_32_bits(ppgtt->pd_dma_addr[3]);
	reg_state[CTX_PDP2_UDW+1] = upper_32_bits(ppgtt->pd_dma_addr[2]);
	reg_state[CTX_PDP2_LDW+1] = lower_32_bits(ppgtt->pd_dma_addr[2]);
	reg_state[CTX_PDP1_UDW+1] = upper_32_bits(ppgtt->pd_dma_addr[1]);
	reg_state[CTX_PDP1_LDW+1] = lower_32_bits(ppgtt->pd_dma_addr[1]);
	reg_state[CTX_PDP0_UDW+1] = upper_32_bits(ppgtt->pd_dma_addr[0]);
	reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->pd_dma_addr[0]);
	if (ring->id == RCS) {
		reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
		reg_state[CTX_R_PWR_CLK_STATE] = 0x20c8;
		reg_state[CTX_R_PWR_CLK_STATE+1] = 0;
	}

	kunmap_atomic(reg_state);

	ctx_obj->dirty = 1;
	set_page_dirty(page);
	i915_gem_object_unpin_pages(ctx_obj);

	return 0;
}

void intel_lr_context_free(struct intel_context *ctx)
{
	int i;

	for (i = 0; i < I915_NUM_RINGS; i++) {
		struct drm_i915_gem_object *ctx_obj = ctx->engine[i].state;
		struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf;

		if (ctx_obj) {
			intel_destroy_ringbuffer_obj(ringbuf);
			kfree(ringbuf);
			i915_gem_object_ggtt_unpin(ctx_obj);
			drm_gem_object_unreference(&ctx_obj->base);
		}
	}
}

static uint32_t get_lr_context_size(struct intel_engine_cs *ring)
{
	int ret = 0;

	WARN_ON(INTEL_INFO(ring->dev)->gen != 8);

	switch (ring->id) {
	case RCS:
		ret = GEN8_LR_CONTEXT_RENDER_SIZE;
		break;
	case VCS:
	case BCS:
	case VECS:
	case VCS2:
		ret = GEN8_LR_CONTEXT_OTHER_SIZE;
		break;
	}

	return ret;
}

int intel_lr_context_deferred_create(struct intel_context *ctx,
				     struct intel_engine_cs *ring)
{
	struct drm_device *dev = ring->dev;
	struct drm_i915_gem_object *ctx_obj;
	uint32_t context_size;
	struct intel_ringbuffer *ringbuf;
	int ret;

	WARN_ON(ctx->legacy_hw_ctx.rcs_state != NULL);

	context_size = round_up(get_lr_context_size(ring), 4096);

	ctx_obj = i915_gem_alloc_context_obj(dev, context_size);
	if (IS_ERR(ctx_obj)) {
		ret = PTR_ERR(ctx_obj);
		DRM_DEBUG_DRIVER("Alloc LRC backing obj failed: %d\n", ret);
		return ret;
	}

	ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN, 0);
	if (ret) {
		DRM_DEBUG_DRIVER("Pin LRC backing obj failed: %d\n", ret);
		drm_gem_object_unreference(&ctx_obj->base);
		return ret;
	}

	ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);
	if (!ringbuf) {
		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s\n",
				ring->name);
		i915_gem_object_ggtt_unpin(ctx_obj);
		drm_gem_object_unreference(&ctx_obj->base);
		ret = -ENOMEM;
		return ret;
	}

	ringbuf->ring = ring;
	ringbuf->size = 32 * PAGE_SIZE;
	ringbuf->effective_size = ringbuf->size;
	ringbuf->head = 0;
	ringbuf->tail = 0;
	ringbuf->space = ringbuf->size;
	ringbuf->last_retired_head = -1;

	/* TODO: For now we put this in the mappable region so that we can reuse
	 * the existing ringbuffer code which ioremaps it. When we start
	 * creating many contexts, this will no longer work and we must switch
	 * to a kmapish interface.
	 */
	ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
	if (ret) {
		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer obj %s: %d\n",
				ring->name, ret);
		goto error;
	}

	ret = populate_lr_context(ctx, ctx_obj, ring, ringbuf);
	if (ret) {
		DRM_DEBUG_DRIVER("Failed to populate LRC: %d\n", ret);
		intel_destroy_ringbuffer_obj(ringbuf);
		goto error;
	}

	ctx->engine[ring->id].ringbuf = ringbuf;
	ctx->engine[ring->id].state = ctx_obj;

	return 0;

error:
	kfree(ringbuf);
	i915_gem_object_ggtt_unpin(ctx_obj);
	drm_gem_object_unreference(&ctx_obj->base);
	return ret;
}