Carry Reflex's present ID through the recorder's submission

vk_sync_submit chains a VkLatencySubmissionPresentIdNV when the device has VK_NV_low_latency2, and on dev the
recorder thread (on by default except on AMD) makes that submission. rec_submit stopped the process on any pNext,
so every NVIDIA GPU with the extension would have failed at its first recorded submission. The recorder now copies
the present ID into its packet and chains it again in submit_run.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
itaskaev2andClaude Opus 5.5 committed 2026-11-10 18:20:16 +01:00
1 parent 3209ea4358
commit c811d0e06d
1 file changed
+17 -4
+17 -4
View File
@@ -318,8 +318,14 @@ int rec_end_cb(VkCommandBuffer cb, int crumb, uint64_t n) {
return 1;
}
// At most two command buffers and one signal: the shape vk_sync.c submits.
typedef struct { uint32_t ncb, nsig; VkCommandBufferSubmitInfo cbi[2]; VkSemaphoreSubmitInfo sig; } A_Submit;
// At most two command buffers and one signal: the shape vk_sync.c submits. The only pNext it chains is Reflex's
// VkLatencySubmissionPresentIdNV (vk_sync_submit), carried as its present ID.
typedef struct {
uint32_t ncb, nsig, has_pid;
uint64_t present_id;
VkCommandBufferSubmitInfo cbi[2];
VkSemaphoreSubmitInfo sig;
} A_Submit;
VkResult rec_submit(const VkSubmitInfo2 *si) {
if (!sub_pending) {
vk_queue_lock();
@@ -328,12 +334,16 @@ VkResult rec_submit(const VkSubmitInfo2 *si) {
return r;
}
sub_pending = 0;
if (si->commandBufferInfoCount > 2 || si->signalSemaphoreInfoCount > 1 || si->waitSemaphoreInfoCount || si->pNext)
const VkBaseInStructure *nx = si->pNext;
int pid = nx && nx->sType == VK_STRUCTURE_TYPE_LATENCY_SUBMISSION_PRESENT_ID_NV && !nx->pNext;
if (si->commandBufferInfoCount > 2 || si->signalSemaphoreInfoCount > 1 || si->waitSemaphoreInfoCount ||
(nx && !pid))
rt_fatal("vk_rec: a submission of %u command buffers, %u waits and %u signals the recorder cannot carry",
si->commandBufferInfoCount, si->waitSemaphoreInfoCount, si->signalSemaphoreInfoCount);
A_Submit *a = put(R_Submit, sizeof *a);
memset(a, 0, sizeof *a);
a->ncb = si->commandBufferInfoCount, a->nsig = si->signalSemaphoreInfoCount;
if (pid) a->has_pid = 1, a->present_id = ((const VkLatencySubmissionPresentIdNV *)nx)->presentID;
for (uint32_t i = 0; i < a->ncb; i++) a->cbi[i] = si->pCommandBufferInfos[i];
if (a->nsig) a->sig = si->pSignalSemaphoreInfos[0];
__atomic_store_n(&q_subs, q_subs + 1, __ATOMIC_RELEASE);
@@ -354,7 +364,10 @@ VkResult rec_submit(const VkSubmitInfo2 *si) {
}
static void submit_run(const A_Submit *a) {
VkSubmitInfo2 si = {.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO_2, .commandBufferInfoCount = a->ncb,
VkLatencySubmissionPresentIdNV lsid = {.sType = VK_STRUCTURE_TYPE_LATENCY_SUBMISSION_PRESENT_ID_NV,
.presentID = a->present_id};
VkSubmitInfo2 si = {.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO_2, .pNext = a->has_pid ? &lsid : NULL,
.commandBufferInfoCount = a->ncb,
.pCommandBufferInfos = a->cbi, .signalSemaphoreInfoCount = a->nsig,
.pSignalSemaphoreInfos = a->nsig ? &a->sig : NULL};
vk_queue_lock();