Ported from https://github.com/NotRexed/Hookshot/pull/1795 (the net diff of its
branch, onto Longshot main). Without buffer mirrors (integrated GPUs, Intel), the
replay copies uniform buffers as submitted by default and replays in submit order;
a submitted copy is reused within a recording. RX_VK_UB_SNAPSHOT=0/1 forces either
way, and RX_VK_UB_SNAPSHOT_REUSE reads as env_on reads a switch (unset: on).

Co-authored-by: Copilot App <[email protected]>

@@ -406,6 +406,11 @@ struct RecordingRes {
     uint64_t before = 0;           // (what the recording used of the streams before this one)
     uint32_t idle = 0;             // (recordings of the slot that stayed in the first stream)
     std::unordered_map<const void*, std::pair<VkBuffer, uint64_t>> c1_at;   // (c1 of a stage: uploaded once a recording)
+    // (hookshot-deck) a uniform buffer copied as submitted (RX_VK_UB_SNAPSHOT), by its address and size: the copy serves the

@@ -3050,1 +3057,4 @@
+                                                      dev.props.deviceType == VK_PHYSICAL_DEVICE_TYPE_INTEGRATED_GPU);
+            logf("vk: uniform buffers %s (RX_VK_UB_SNAPSHOT=%d)", on ? "copied as submitted" : "bound in place", on ? 1 : 0);
+            return on;        }();
         BufferRef b = snapshot ? BufferRef{} : gpu_buffer_bind(u.addr, n, false);

@@ -3046,0 +3046,4 @@
+        // over the ones submitted (the per-object matrices are in memory it reuses frame after frame). On Intel the depth
+        // prepass drew the Kokiri ground with other objects' matrices, out of sight: the depth there stayed far, and the fog
+        // pass painted sky over the ground (the white forest on Intel Core Ultra iGPUs, still there after the split-submission
+        // fence fix #2419). On a Steam Deck on main 6749ba21, bound in place, 1 of 3 starts froze in a conversation (a capture's

@@ -3050,0 +3054,4 @@
+            const char* e = getenv("RX_VK_UB_SNAPSHOT");
+            const bool on = e ? env_on("RX_VK_UB_SNAPSHOT")
+                              : !pools_mirrored() && (dev.props.vendorID == 0x8086 ||
+                                                      dev.props.deviceType == VK_PHYSICAL_DEVICE_TYPE_INTEGRATED_GPU);

@@ -3050,0 +3056,4 @@
+                              : !pools_mirrored() && (dev.props.vendorID == 0x8086 ||
+                                                      dev.props.deviceType == VK_PHYSICAL_DEVICE_TYPE_INTEGRATED_GPU);
+            logf("vk: uniform buffers %s (RX_VK_UB_SNAPSHOT=%d)", on ? "copied as submitted" : "bound in place", on ? 1 : 0);
+            return on;        }();

@@ -3050,2 +3059,4 @@
+            return on;        }();
         BufferRef b = snapshot ? BufferRef{} : gpu_buffer_bind(u.addr, n, false);
         if (b && b.offset % align == 0) return {b.buffer, b.offset, n};
+        static const bool snap_reuse = [] {   // (unset: on; set, as env_on reads it)

@@ -3052,0 +3064,4 @@
+            return !e || !env_value_off(e);
+        }();
+        const uint64_t snap_key = u.addr * 0x9E3779B97F4A7C15ull ^ n;
+        const uint64_t view = snapshot && snap_reuse ? memory_capture_view() : 0;

@@ -3059,2 +3080,2 @@
-            logf("vk: uniform buffer %#llx +%#llx copied into the stream (%s; %lld so)", (unsigned long long)u.addr,
-                 (unsigned long long)n, b ? "unaligned" : "outside the pools", (long long)copied);
+        // (a copy that could not be read is not kept for the recording's later bindings: each gets its own, as before)
+        if (memory_read_as_submitted(u.addr, cur->mapped + at, n) && view) cur->ub_snap[snap_key] = {u.addr, n, view, cur->stream, at};

@@ -0,0 +51,4 @@
+'''
+
+# (mirrors, integrated or discrete, vendor, RX_VK_UB_SNAPSHOT, expected)
+CASES = [("0", "i", "1002", "unset", "copy"),    # (an AMD APU, the Steam Deck: no mirrors)