/*
 * Copyright © 2026 mfritsche / claude-noether
 * SPDX-License-Identifier: MIT
 *
 * iter13: VK_EXT_transform_feedback command handlers for the JM
 * architecture path (Bifrost v6/v7 + Valhall-JM v9).
 *
 * The runtime contract:
 *   - vkCmdBindTransformFeedbackBuffersEXT: stash (gpu_addr, offset, size)
 *     for each slot into cmdbuf->state.gfx.xfb.buffers[].
 *   - vkCmdBeginTransformFeedbackEXT: set cmdbuf->state.gfx.xfb.active = true.
 *     Mark sysvals dirty so the next draw re-emits vs.xfb_address[].
 *   - vkCmdEndTransformFeedbackEXT: set active = false.
 *
 * Counter buffers (firstCounterBuffer/counterBufferCount/pCounterBuffers/
 * pCounterBufferOffsets) are accepted by API but ignored — v1 doesn't
 * support pause/resume. transformFeedbackDraw is advertised as false.
 *
 * Per-draw integration: jm/panvk_vX_cmd_draw.c reads cmdbuf->state.gfx.xfb
 * and populates vs.xfb_address[i] for shader use. The pan_nir_lower_xfb
 * pass in panvk_vX_shader.c emits nir_load_xfb_address(i) which lowers
 * (via panvk_vX_shader.c sysval handler) to a load from the per-draw
 * sysval push area.
 */

#include "vk_log.h"
#include "util/log.h"

#include "panvk_cmd_buffer.h"
#include "panvk_cmd_draw.h"
#include "panvk_buffer.h"
#include "panvk_entrypoints.h"

VKAPI_ATTR void VKAPI_CALL
panvk_per_arch(CmdBindTransformFeedbackBuffersEXT)(
   VkCommandBuffer commandBuffer,
   uint32_t firstBinding,
   uint32_t bindingCount,
   const VkBuffer *pBuffers,
   const VkDeviceSize *pOffsets,
   const VkDeviceSize *pSizes)
{
   VK_FROM_HANDLE(panvk_cmd_buffer, cmdbuf, commandBuffer);
   struct panvk_cmd_graphics_state *gfx = &cmdbuf->state.gfx;

   for (uint32_t i = 0; i < bindingCount; i++) {
      uint32_t slot = firstBinding + i;
      if (slot >= 4)
         continue;

      VK_FROM_HANDLE(panvk_buffer, buf, pBuffers[i]);
      gfx->xfb.buffers[slot].addr = panvk_buffer_gpu_ptr(buf, 0);
      gfx->xfb.buffers[slot].offset = pOffsets[i];
      gfx->xfb.buffers[slot].size =
         (pSizes != NULL && pSizes[i] != VK_WHOLE_SIZE)
            ? pSizes[i]
            : (buf->vk.size - pOffsets[i]);
   }

   if (firstBinding + bindingCount > gfx->xfb.buffer_count)
      gfx->xfb.buffer_count = firstBinding + bindingCount;
}

VKAPI_ATTR void VKAPI_CALL
panvk_per_arch(CmdBeginTransformFeedbackEXT)(
   VkCommandBuffer commandBuffer,
   uint32_t firstCounterBuffer,
   uint32_t counterBufferCount,
   const VkBuffer *pCounterBuffers,
   const VkDeviceSize *pCounterBufferOffsets)
{
   VK_FROM_HANDLE(panvk_cmd_buffer, cmdbuf, commandBuffer);
   struct panvk_cmd_graphics_state *gfx = &cmdbuf->state.gfx;

   /* Counter buffers ignored in v1 — see VkPhysicalDeviceTransformFeedback
    * PropertiesEXT.transformFeedbackDraw = false in panvk_vX_physical_device.c.
    * App is spec-compliant if it does not pass counter buffers (which our
    * features advertisement allows), but warn loudly if it does so we do not
    * silently produce wrong capture state. */
   (void)firstCounterBuffer;
   (void)pCounterBufferOffsets;
   if (counterBufferCount > 0 && pCounterBuffers != NULL) {
      mesa_logw("panvk: CmdBeginTransformFeedbackEXT: counter buffers not "
                "implemented (transformFeedbackDraw=false); XFB resume will "
                "restart at buffer offset 0");
   }

   gfx->xfb.active = true;
   /* Per-draw set_gfx_sysval picks up the change automatically — no
    * explicit dirty marking required (set_gfx_sysval uses memcmp +
    * BITSET to detect state diffs and re-emit sysvals). */
}

VKAPI_ATTR void VKAPI_CALL
panvk_per_arch(CmdEndTransformFeedbackEXT)(
   VkCommandBuffer commandBuffer,
   uint32_t firstCounterBuffer,
   uint32_t counterBufferCount,
   const VkBuffer *pCounterBuffers,
   const VkDeviceSize *pCounterBufferOffsets)
{
   VK_FROM_HANDLE(panvk_cmd_buffer, cmdbuf, commandBuffer);
   struct panvk_cmd_graphics_state *gfx = &cmdbuf->state.gfx;

   (void)firstCounterBuffer;
   (void)counterBufferCount;
   (void)pCounterBuffers;
   (void)pCounterBufferOffsets;

   gfx->xfb.active = false;
}