/*
 * v3d_runner — minimal Vulkan compute plumbing for V3D 7.1 on Pi 5.
 *
 * Factored out of tests/bench_vulkan_dispatch.c so successive kernel
 * benches can reuse the device/queue/buffer/pipeline machinery
 * without copy-paste. Kept deliberately small and concrete — no
 * generality beyond what daedalus-fourier needs.
 *
 * License: BSD-2-Clause.
 */
#ifndef DAEDALUS_V3D_RUNNER_H
#define DAEDALUS_V3D_RUNNER_H

#include <stddef.h>
#include <stdint.h>
#include <vulkan/vulkan.h>

typedef struct v3d_runner v3d_runner;

/* Host-visible SSBO. .mapped is a CPU-side pointer to .size bytes. */
typedef struct {
    VkBuffer        buffer;
    VkDeviceMemory  memory;
    void           *mapped;
    size_t          size;
} v3d_buffer;

/* Compute pipeline + its descriptor set (one set per pipeline). */
typedef struct {
    VkPipeline             pipeline;
    VkPipelineLayout       layout;
    VkDescriptorSetLayout  ds_layout;
    VkDescriptorPool       pool;
    VkDescriptorSet        desc_set;
    uint32_t               n_ssbos;
    uint32_t               push_const_size;
    /* Persistent command buffer.  Allocated at create-pipeline time;
     * dispatch sites use v3d_runner_pipeline_cmdbuf_reset() to
     * vkResetCommandBuffer instead of paying vkAllocateCommandBuffers
     * per dispatch.  Pool flagged RESET_COMMAND_BUFFER_BIT so reset
     * is permitted. */
    VkCommandBuffer        cb;
} v3d_pipeline;

/*
 * Create runner: Vulkan instance, V3D physical device, logical
 * device with storageBuffer{8,16}BitAccess features enabled,
 * compute queue, command pool.
 *
 * Returns NULL on failure (writes errors to stderr).
 */
v3d_runner *v3d_runner_create(void);
void        v3d_runner_destroy(v3d_runner *r);

/* Expose a few internals for code that wants direct vkCmd*. */
VkDevice         v3d_runner_device(v3d_runner *r);
VkQueue          v3d_runner_queue(v3d_runner *r);
uint32_t         v3d_runner_queue_family(v3d_runner *r);
VkCommandPool    v3d_runner_cmd_pool(v3d_runner *r);
const char      *v3d_runner_device_name(v3d_runner *r);

/* Storage buffer, HOST_VISIBLE | HOST_COHERENT, mapped on the
 * host side. The mapping persists for the lifetime of the buffer.
 *
 * Returns 0 on success, non-zero on failure.
 *
 * NOTE: prefer v3d_runner_acquire_buffer() on the dispatch hot path —
 * create_buffer/destroy_buffer go straight to vkAllocateMemory each
 * call, which on V3D7's Mesa stack costs ~10-50us.  The acquire/
 * release pair pulls from a freelist and pays vkAllocateMemory only
 * on a cache miss.
 */
int  v3d_runner_create_buffer(v3d_runner *r, size_t size, v3d_buffer *out);
void v3d_runner_destroy_buffer(v3d_runner *r, v3d_buffer *buf);

/*
 * Pooled buffer acquisition.  Returns a v3d_buffer whose .size is the
 * smallest power-of-2 >= the requested size (so callers can pool
 * across similar-sized requests).  Backed by HOST_VISIBLE |
 * HOST_COHERENT memory; mapped pointer is valid.
 *
 * On cache hit: zero-cost reuse of a previously-released buffer.
 * On miss: falls through to v3d_runner_create_buffer().  Release with
 * v3d_runner_release_buffer(); pool drains in v3d_runner_destroy().
 *
 * Lifetime contract: the returned buffer's .mapped contents are
 * UNINITIALISED — the previous user's data may still be present.
 * Callers that need a clean buffer must memset themselves.  This is
 * deliberate; the dispatch hot paths immediately overwrite the
 * buffer with new coefficients / meta anyway.
 *
 * Thread-safety: NOT thread-safe.  A daedalus_ctx is single-threaded
 * by API contract; the pool inherits that constraint.
 */
int  v3d_runner_acquire_buffer(v3d_runner *r, size_t size, v3d_buffer *out);
void v3d_runner_release_buffer(v3d_runner *r, v3d_buffer *buf);

/* Pool diagnostics: total allocated bytes (sum across all size
 * classes, including currently-released entries).  Useful for
 * watermark logging. */
size_t v3d_runner_pool_total_bytes(v3d_runner *r);

/* Compute pipeline from a SPIR-V file path. The descriptor-set
 * layout exposes `n_ssbos` storage buffer bindings at binding
 * indices 0..n_ssbos-1, all visible to the compute stage. A push
 * constant range of `push_const_size` bytes is added if non-zero.
 *
 * The single descriptor set is pre-allocated; bind buffers via
 * v3d_runner_bind_buffers().
 */
int  v3d_runner_create_pipeline(v3d_runner *r,
                                const char  *spv_path,
                                uint32_t     n_ssbos,
                                uint32_t     push_const_size,
                                v3d_pipeline *out);
void v3d_runner_destroy_pipeline(v3d_runner *r, v3d_pipeline *p);

/* Bind SSBOs to the pipeline's descriptor set. `bufs` must have
 * exactly `p->n_ssbos` entries, in binding order. Idempotent —
 * rebind freely between dispatches if buffers change.
 */
int  v3d_runner_bind_buffers(v3d_runner   *r,
                             v3d_pipeline *p,
                             const v3d_buffer *bufs,
                             uint32_t      n);

/* Allocate a primary command buffer from the runner's pool. */
VkCommandBuffer v3d_runner_alloc_cmdbuf(v3d_runner *r);

/* Reset @p->cb so it can be re-recorded.  Returns 0 on success.
 * Replaces v3d_runner_alloc_cmdbuf() on the dispatch hot path —
 * vkResetCommandBuffer is O(1) vs vkAllocateCommandBuffers' ~1-5us
 * driver cost. */
int v3d_runner_pipeline_cmdbuf_reset(v3d_runner *r, v3d_pipeline *p);

/* Submit `cb` to the queue and wait for completion. The classic
 * timed operation. Returns 0 on success.
 */
int v3d_runner_submit_wait(v3d_runner *r, VkCommandBuffer cb);

#endif /* DAEDALUS_V3D_RUNNER_H */