/*
 * iter16 winding-order regression probe for PanVk-Bifrost.
 *
 * Phase 3 of iter16. The 162 CTS dEQP-VK.transform_feedback.simple.winding_*
 * failures (catalogued in iter15) all share the same root cause: iter13's
 * pan_nir_lower_xfb captures one entry per VS invocation, which for non-LIST
 * topologies gives ONE OUTPUT PER INPUT VERTEX. The Vulkan spec requires
 * primitive-decomposed capture: an N-vertex triangle strip must produce
 * 3*(N-2) captured entries with the right per-primitive winding order.
 *
 * This probe exercises the canonical case: triangle strip with 8 input
 * vertices, expecting 18 captured entries arranged as 6 triangles. The
 * verifier accepts any rotation within each primitive (per CTS's rule)
 * but enforces the winding direction.
 *
 * Pre-iter16 behavior (current iter13/r3 driver): captured count = 8
 *   → PROBE FAILS (under-capture).
 * Post-iter16 behavior: captured count = 18 in decomposed order
 *   → PROBE PASSES.
 *
 * Parameterized so we can add LINE_STRIP, TRIANGLE_FAN, *_ADJACENCY tests
 * as the fix expands in Phase 4. For now, only TRIANGLE_STRIP is wired up.
 */

#include <errno.h>
#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdint.h>
#include <vulkan/vulkan.h>

#define VSPV_PATH "probe_winding.vert.spv"

#define STEP(name) do { fprintf(stderr, "[step] " name "\n"); fflush(stderr); } while (0)

#define VK_CHECK(call) do {                                                    \
    VkResult _r = (call);                                                      \
    if (_r != VK_SUCCESS) {                                                    \
        fprintf(stderr, "[fail] " #call " => %d at %s:%d\n",                   \
                (int)_r, __FILE__, __LINE__);                                  \
        exit(2);                                                               \
    }                                                                          \
} while (0)

/* ---- Per-topology expected-output helper (mirrors CTS) ---- */

/*
 * For input vertex count N and topology T, returns the decomposed primitive
 * count and per-primitive vertex layout. CTS test logic uses identical lambdas
 * in vktTransformFeedbackSimpleTests.cpp around line 1241.
 */
struct topo_decomp {
    VkPrimitiveTopology topology;
    const char *name;
    uint32_t verts_per_prim;
    uint32_t (*prim_count)(uint32_t input_count);
    /* Fills out[verts_per_prim] with the input-vertex-IDs that should appear
     * in primitive prim_idx (in CTS winding order; rotations are accepted at
     * verify time). */
    void (*expected)(uint32_t prim_idx, uint32_t *out);
};

/* TRIANGLE_STRIP: 3*(N-2) outputs.
 *   Even prim i: {i, i+1, i+2}
 *   Odd  prim i: {i, i+2, i+1}
 */
static uint32_t prim_count_tri_strip(uint32_t n) {
    return (n >= 2) ? (n - 2) : 0;
}
static void expected_tri_strip(uint32_t i, uint32_t *out) {
    uint32_t iMod2 = i & 1u;
    out[0] = i;
    out[1] = i + 1 + iMod2;
    out[2] = i + 2 - iMod2;
}

/* LINE_STRIP: 2*(N-1) outputs. Each prim i: {i, i+1} */
static uint32_t prim_count_line_strip(uint32_t n) {
    return (n >= 1) ? (n - 1) : 0;
}
static void expected_line_strip(uint32_t i, uint32_t *out) {
    out[0] = i;
    out[1] = i + 1u;
}

/* TRIANGLE_FAN: 3*(N-2) outputs. Each prim i: {i+1, i+2, 0} */
static uint32_t prim_count_tri_fan(uint32_t n) {
    return (n >= 2) ? (n - 2) : 0;
}
static void expected_tri_fan(uint32_t i, uint32_t *out) {
    out[0] = i + 1u;
    out[1] = i + 2u;
    out[2] = 0u;
}

static const struct topo_decomp TOPO_TESTS[] = {
    { VK_PRIMITIVE_TOPOLOGY_TRIANGLE_STRIP, "TRIANGLE_STRIP", 3,
      prim_count_tri_strip, expected_tri_strip },
    { VK_PRIMITIVE_TOPOLOGY_LINE_STRIP, "LINE_STRIP", 2,
      prim_count_line_strip, expected_line_strip },
    { VK_PRIMITIVE_TOPOLOGY_TRIANGLE_FAN, "TRIANGLE_FAN", 3,
      prim_count_tri_fan, expected_tri_fan },
};
#define NUM_TOPO_TESTS (sizeof(TOPO_TESTS) / sizeof(TOPO_TESTS[0]))

/* ---- Vulkan plumbing ---- */

static uint32_t *read_spv(const char *path, size_t *out_bytes) {
    FILE *f = fopen(path, "rb");
    if (!f) { fprintf(stderr, "[fail] open %s: %s\n", path, strerror(errno)); exit(3); }
    fseek(f, 0, SEEK_END);
    long n = ftell(f);
    fseek(f, 0, SEEK_SET);
    uint32_t *buf = malloc((size_t)n);
    fread(buf, 1, (size_t)n, f);
    fclose(f);
    *out_bytes = (size_t)n;
    return buf;
}

static uint32_t pick_host_visible(const VkPhysicalDeviceMemoryProperties *mp,
                                  uint32_t type_bits) {
    VkMemoryPropertyFlags want =
        VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
        VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
    for (uint32_t i = 0; i < mp->memoryTypeCount; i++) {
        if ((type_bits & (1u << i)) &&
            (mp->memoryTypes[i].propertyFlags & want) == want) return i;
    }
    fprintf(stderr, "[fail] no HOST_VISIBLE+COHERENT memtype\n"); exit(4);
}

/* ---- Verifier (rotation-aware, mirrors CTS verifyVertexDataWithWinding) ---- */

/* Returns 1 if got[verts_per_prim] is a rotation of ref[verts_per_prim], 0 else. */
static int rotations_match(const uint32_t *ref, const uint32_t *got, uint32_t vpp) {
    for (uint32_t start = 0; start < vpp; start++) {
        int ok = 1;
        for (uint32_t v = 0; v < vpp; v++) {
            uint32_t r = ref[(start + v) % vpp];
            if (r != got[v]) { ok = 0; break; }
        }
        if (ok) return 1;
    }
    return 0;
}

/* Returns number of mismatched primitives. Prints details for each mismatch. */
static int verify_winding(const struct topo_decomp *t, uint32_t input_count,
                          const uint32_t *got, uint32_t got_count) {
    uint32_t expected_prims = t->prim_count(input_count);
    uint32_t expected_count = expected_prims * t->verts_per_prim;
    if (got_count != expected_count) {
        fprintf(stderr, "[diff] %s: captured count %u, expected %u "
                "(%u prims × %u verts)\n",
                t->name, got_count, expected_count,
                expected_prims, t->verts_per_prim);
        return -1;
    }
    int mismatches = 0;
    for (uint32_t p = 0; p < expected_prims; p++) {
        uint32_t ref[8] = {0};
        t->expected(p, ref);
        const uint32_t *prim_got = got + p * t->verts_per_prim;
        if (!rotations_match(ref, prim_got, t->verts_per_prim)) {
            fprintf(stderr, "[diff] %s prim %u: expected rotation of {",
                    t->name, p);
            for (uint32_t v = 0; v < t->verts_per_prim; v++)
                fprintf(stderr, "%s%u", v ? "," : "", ref[v]);
            fprintf(stderr, "} got {");
            for (uint32_t v = 0; v < t->verts_per_prim; v++)
                fprintf(stderr, "%s%u", v ? "," : "", prim_got[v]);
            fprintf(stderr, "}\n");
            mismatches++;
        }
    }
    return mismatches;
}

/* ---- Per-topology test ---- */

static int run_one_topology(VkDevice dev, VkQueue queue, uint32_t qfam,
                            VkRenderPass dummy_rp,
                            PFN_vkCmdBindTransformFeedbackBuffersEXT pBindXfb,
                            PFN_vkCmdBeginTransformFeedbackEXT pBeginXfb,
                            PFN_vkCmdEndTransformFeedbackEXT pEndXfb,
                            PFN_vkCmdBeginRenderingKHR pBeginRendering,
                            PFN_vkCmdEndRenderingKHR pEndRendering,
                            VkPhysicalDeviceMemoryProperties *mp,
                            VkShaderModule vsm,
                            const struct topo_decomp *t,
                            uint32_t input_count) {
    /* Capacity: expected_prims × verts_per_prim × 4. Pad to 64 entries
     * (256 bytes) so iter13's under-capture is visible (sentinel-filled tail). */
    const uint32_t buf_words = 64;
    const VkDeviceSize buf_bytes = buf_words * sizeof(uint32_t);

    fprintf(stderr, "\n=== %s with %u input verts ===\n", t->name, input_count);

    /* XFB capture buffer */
    VkBufferCreateInfo bci = {
        .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
        .size = buf_bytes,
        .usage = VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT |
                 VK_BUFFER_USAGE_TRANSFER_DST_BIT,
        .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
    };
    VkBuffer xfb_buf;
    VK_CHECK(vkCreateBuffer(dev, &bci, NULL, &xfb_buf));

    VkMemoryRequirements mr;
    vkGetBufferMemoryRequirements(dev, xfb_buf, &mr);
    VkMemoryAllocateInfo mai = {
        .sType = VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO,
        .allocationSize = mr.size,
        .memoryTypeIndex = pick_host_visible(mp, mr.memoryTypeBits),
    };
    VkDeviceMemory xfb_mem;
    VK_CHECK(vkAllocateMemory(dev, &mai, NULL, &xfb_mem));
    VK_CHECK(vkBindBufferMemory(dev, xfb_buf, xfb_mem, 0));
    void *mapped;
    VK_CHECK(vkMapMemory(dev, xfb_mem, 0, VK_WHOLE_SIZE, 0, &mapped));
    /* Sentinel-fill so we can distinguish "captured 0xDEADBEEF" from
     * "GPU didn't write here" — under-capture leaves the tail at sentinel. */
    uint32_t *u32 = (uint32_t *)mapped;
    for (uint32_t i = 0; i < buf_words; i++) u32[i] = 0xDEADBEEFu;

    /* Pipeline */
    VkPipelineLayoutCreateInfo plci = {
        .sType = VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO,
    };
    VkPipelineLayout pl;
    VK_CHECK(vkCreatePipelineLayout(dev, &plci, NULL, &pl));

    VkPipelineShaderStageCreateInfo stages[1] = {
        { .sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO,
          .stage = VK_SHADER_STAGE_VERTEX_BIT, .module = vsm, .pName = "main" },
    };
    VkPipelineVertexInputStateCreateInfo vi = {
        .sType = VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO,
    };
    VkPipelineInputAssemblyStateCreateInfo ia = {
        .sType = VK_STRUCTURE_TYPE_PIPELINE_INPUT_ASSEMBLY_STATE_CREATE_INFO,
        .topology = t->topology,
    };
    VkViewport vp_dummy = { 0, 0, 1, 1, 0.0f, 1.0f };
    VkRect2D sc_dummy = {{0,0}, {1,1}};
    VkPipelineViewportStateCreateInfo vp = {
        .sType = VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO,
        .viewportCount = 1, .pViewports = &vp_dummy,
        .scissorCount = 1, .pScissors = &sc_dummy,
    };
    VkPipelineRasterizationStateCreateInfo rs = {
        .sType = VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO,
        .rasterizerDiscardEnable = VK_TRUE,
        .polygonMode = VK_POLYGON_MODE_FILL,
        .cullMode = VK_CULL_MODE_NONE,
        .lineWidth = 1.0f,
    };
    VkPipelineMultisampleStateCreateInfo ms = {
        .sType = VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO,
        .rasterizationSamples = VK_SAMPLE_COUNT_1_BIT,
    };
    VkPipelineRenderingCreateInfoKHR pri = {
        .sType = VK_STRUCTURE_TYPE_PIPELINE_RENDERING_CREATE_INFO_KHR,
        .colorAttachmentCount = 0,
    };
    VkGraphicsPipelineCreateInfo gpci = {
        .sType = VK_STRUCTURE_TYPE_GRAPHICS_PIPELINE_CREATE_INFO,
        .pNext = &pri,
        .stageCount = 1, .pStages = stages,
        .pVertexInputState = &vi,
        .pInputAssemblyState = &ia,
        .pViewportState = &vp,
        .pRasterizationState = &rs,
        .pMultisampleState = &ms,
        .layout = pl,
    };
    VkPipeline pipe;
    VK_CHECK(vkCreateGraphicsPipelines(dev, VK_NULL_HANDLE, 1, &gpci, NULL, &pipe));

    /* Command buffer */
    VkCommandPoolCreateInfo cpoolci = {
        .sType = VK_STRUCTURE_TYPE_COMMAND_POOL_CREATE_INFO,
        .queueFamilyIndex = qfam,
    };
    VkCommandPool cpool;
    VK_CHECK(vkCreateCommandPool(dev, &cpoolci, NULL, &cpool));
    VkCommandBufferAllocateInfo cbai = {
        .sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO,
        .commandPool = cpool, .level = VK_COMMAND_BUFFER_LEVEL_PRIMARY,
        .commandBufferCount = 1,
    };
    VkCommandBuffer cb;
    VK_CHECK(vkAllocateCommandBuffers(dev, &cbai, &cb));

    VkCommandBufferBeginInfo cbbi = {
        .sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO,
        .flags = VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT,
    };
    VK_CHECK(vkBeginCommandBuffer(cb, &cbbi));

    VkDeviceSize xfb_off = 0, xfb_size = buf_bytes;
    pBindXfb(cb, 0, 1, &xfb_buf, &xfb_off, &xfb_size);

    VkRenderingInfoKHR ri = {
        .sType = VK_STRUCTURE_TYPE_RENDERING_INFO_KHR,
        .renderArea = {{0,0}, {1,1}},
        .layerCount = 1,
        .colorAttachmentCount = 0,
    };
    pBeginRendering(cb, &ri);
    vkCmdBindPipeline(cb, VK_PIPELINE_BIND_POINT_GRAPHICS, pipe);
    pBeginXfb(cb, 0, 0, NULL, NULL);
    vkCmdDraw(cb, input_count, 1, 0, 0);
    pEndXfb(cb, 0, 0, NULL, NULL);
    pEndRendering(cb);

    VkBufferMemoryBarrier bb = {
        .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER,
        .srcAccessMask = VK_ACCESS_TRANSFORM_FEEDBACK_WRITE_BIT_EXT,
        .dstAccessMask = VK_ACCESS_HOST_READ_BIT,
        .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
        .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
        .buffer = xfb_buf, .offset = 0, .size = VK_WHOLE_SIZE,
    };
    vkCmdPipelineBarrier(cb,
        VK_PIPELINE_STAGE_TRANSFORM_FEEDBACK_BIT_EXT,
        VK_PIPELINE_STAGE_HOST_BIT,
        0, 0, NULL, 1, &bb, 0, NULL);
    VK_CHECK(vkEndCommandBuffer(cb));

    /* Submit + wait */
    VkFenceCreateInfo fci = { .sType = VK_STRUCTURE_TYPE_FENCE_CREATE_INFO };
    VkFence fence;
    VK_CHECK(vkCreateFence(dev, &fci, NULL, &fence));
    VkSubmitInfo si = {
        .sType = VK_STRUCTURE_TYPE_SUBMIT_INFO,
        .commandBufferCount = 1, .pCommandBuffers = &cb,
    };
    VK_CHECK(vkQueueSubmit(queue, 1, &si, fence));
    VkResult wr = vkWaitForFences(dev, 1, &fence, VK_TRUE, 10ULL * 1000 * 1000 * 1000);
    if (wr != VK_SUCCESS) {
        fprintf(stderr, "[fail] %s: vkWaitForFences => %d\n", t->name, wr);
        return -1;
    }

    /* Read back: count contiguous non-sentinel words from offset 0. */
    uint32_t captured_count = 0;
    while (captured_count < buf_words && u32[captured_count] != 0xDEADBEEFu)
        captured_count++;

    fprintf(stderr, "[info] %s: captured %u entries (sentinel-stopped)\n",
            t->name, captured_count);
    /* Print first few for debugging */
    if (captured_count > 0) {
        fprintf(stderr, "[info]   first 8: ");
        for (uint32_t i = 0; i < captured_count && i < 8; i++)
            fprintf(stderr, "%u%s", u32[i], (i + 1 < 8 && i + 1 < captured_count) ? "," : "");
        fprintf(stderr, "\n");
    }

    int mismatches = verify_winding(t, input_count, u32, captured_count);

    /* Teardown */
    vkUnmapMemory(dev, xfb_mem);
    vkDestroyFence(dev, fence, NULL);
    vkDestroyCommandPool(dev, cpool, NULL);
    vkDestroyPipeline(dev, pipe, NULL);
    vkDestroyPipelineLayout(dev, pl, NULL);
    vkDestroyBuffer(dev, xfb_buf, NULL);
    vkFreeMemory(dev, xfb_mem, NULL);
    (void)dummy_rp;

    return mismatches;
}

/* ---- main: bring up Vulkan, run all topology tests ---- */

int main(int argc, char **argv) {
    /* Optional CLI: limit to one topology by name */
    const char *only = NULL;
    if (argc > 1) only = argv[1];

    STEP("vkCreateInstance");
    VkApplicationInfo app = {
        .sType = VK_STRUCTURE_TYPE_APPLICATION_INFO,
        .pApplicationName = "panvk-bifrost iter16 winding probe",
        .apiVersion = VK_API_VERSION_1_0,
    };
    const char *inst_exts[] = { "VK_KHR_get_physical_device_properties2" };
    VkInstanceCreateInfo ici = {
        .sType = VK_STRUCTURE_TYPE_INSTANCE_CREATE_INFO,
        .pApplicationInfo = &app,
        .enabledExtensionCount = 1,
        .ppEnabledExtensionNames = inst_exts,
    };
    VkInstance inst;
    VK_CHECK(vkCreateInstance(&ici, NULL, &inst));

    uint32_t n_phys = 0;
    VK_CHECK(vkEnumeratePhysicalDevices(inst, &n_phys, NULL));
    VkPhysicalDevice *phys = calloc(n_phys, sizeof(*phys));
    VK_CHECK(vkEnumeratePhysicalDevices(inst, &n_phys, phys));
    VkPhysicalDevice gpu = phys[0];
    VkPhysicalDeviceMemoryProperties mp;
    vkGetPhysicalDeviceMemoryProperties(gpu, &mp);

    uint32_t n_qf = 0;
    vkGetPhysicalDeviceQueueFamilyProperties(gpu, &n_qf, NULL);
    VkQueueFamilyProperties *qfp = calloc(n_qf, sizeof(*qfp));
    vkGetPhysicalDeviceQueueFamilyProperties(gpu, &n_qf, qfp);
    uint32_t qfam = UINT32_MAX;
    for (uint32_t i = 0; i < n_qf; i++)
        if (qfp[i].queueFlags & VK_QUEUE_GRAPHICS_BIT) { qfam = i; break; }

    STEP("vkCreateDevice");
    const char *dev_exts[] = {
        "VK_KHR_multiview", "VK_KHR_maintenance2",
        "VK_KHR_create_renderpass2", "VK_KHR_depth_stencil_resolve",
        "VK_KHR_dynamic_rendering",
        "VK_EXT_transform_feedback",
    };
    VkPhysicalDeviceTransformFeedbackFeaturesEXT enable_xfb = {
        .sType = VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_TRANSFORM_FEEDBACK_FEATURES_EXT,
        .transformFeedback = VK_TRUE,
        .geometryStreams = VK_FALSE,
    };
    VkPhysicalDeviceDynamicRenderingFeaturesKHR dyn_feat = {
        .sType = VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_DYNAMIC_RENDERING_FEATURES_KHR,
        .pNext = &enable_xfb,
        .dynamicRendering = VK_TRUE,
    };
    float qprio = 1.0f;
    VkDeviceQueueCreateInfo qci = {
        .sType = VK_STRUCTURE_TYPE_DEVICE_QUEUE_CREATE_INFO,
        .queueFamilyIndex = qfam, .queueCount = 1, .pQueuePriorities = &qprio,
    };
    VkDeviceCreateInfo dci = {
        .sType = VK_STRUCTURE_TYPE_DEVICE_CREATE_INFO,
        .pNext = &dyn_feat,
        .queueCreateInfoCount = 1, .pQueueCreateInfos = &qci,
        .enabledExtensionCount = sizeof(dev_exts)/sizeof(dev_exts[0]),
        .ppEnabledExtensionNames = dev_exts,
    };
    VkDevice dev;
    VK_CHECK(vkCreateDevice(gpu, &dci, NULL, &dev));
    VkQueue queue;
    vkGetDeviceQueue(dev, qfam, 0, &queue);

    PFN_vkCmdBindTransformFeedbackBuffersEXT pBindXfb =
        (PFN_vkCmdBindTransformFeedbackBuffersEXT)vkGetDeviceProcAddr(
            dev, "vkCmdBindTransformFeedbackBuffersEXT");
    PFN_vkCmdBeginTransformFeedbackEXT pBeginXfb =
        (PFN_vkCmdBeginTransformFeedbackEXT)vkGetDeviceProcAddr(
            dev, "vkCmdBeginTransformFeedbackEXT");
    PFN_vkCmdEndTransformFeedbackEXT pEndXfb =
        (PFN_vkCmdEndTransformFeedbackEXT)vkGetDeviceProcAddr(
            dev, "vkCmdEndTransformFeedbackEXT");
    PFN_vkCmdBeginRenderingKHR pBeginRendering =
        (PFN_vkCmdBeginRenderingKHR)vkGetDeviceProcAddr(dev, "vkCmdBeginRenderingKHR");
    PFN_vkCmdEndRenderingKHR pEndRendering =
        (PFN_vkCmdEndRenderingKHR)vkGetDeviceProcAddr(dev, "vkCmdEndRenderingKHR");

    /* Shader (shared across topology iterations) */
    size_t spv_bytes = 0;
    uint32_t *spv = read_spv(VSPV_PATH, &spv_bytes);
    VkShaderModuleCreateInfo smci = {
        .sType = VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO,
        .codeSize = spv_bytes, .pCode = spv,
    };
    VkShaderModule vsm;
    VK_CHECK(vkCreateShaderModule(dev, &smci, NULL, &vsm));
    free(spv);

    /* Run each topology test */
    int total_fail = 0;
    int total_tested = 0;
    for (size_t i = 0; i < NUM_TOPO_TESTS; i++) {
        const struct topo_decomp *t = &TOPO_TESTS[i];
        if (only && strcmp(only, t->name) != 0) continue;
        total_tested++;
        int rc = run_one_topology(dev, queue, qfam, VK_NULL_HANDLE,
                                  pBindXfb, pBeginXfb, pEndXfb,
                                  pBeginRendering, pEndRendering,
                                  &mp, vsm, t, 8u);
        if (rc != 0) {
            total_fail++;
            fprintf(stderr, "[FAIL] %s: %d mismatch(es)\n", t->name, rc);
        } else {
            fprintf(stderr, "[PASS] %s\n", t->name);
        }
    }

    vkDestroyShaderModule(dev, vsm, NULL);
    vkDestroyDevice(dev, NULL);
    vkDestroyInstance(inst, NULL);
    free(phys); free(qfp);

    fprintf(stderr, "\n=== SUMMARY: %d/%d topology tests passed ===\n",
            total_tested - total_fail, total_tested);
    return total_fail == 0 ? 0 : 1;
}