diff --git a/direct/src/dist/commands.py b/direct/src/dist/commands.py
index 432375c6c1..1d60a7a8b2 100644
--- a/direct/src/dist/commands.py
+++ b/direct/src/dist/commands.py
@@ -116,7 +116,7 @@ from _frozen_importlib import _imp, FrozenImporter
 
 sys.frozen = True
 
-if sys.platform == 'win32':
+if sys.platform == 'win32' and sys.version_info < (3, 10):
     # Make sure the preferred encoding is something we actually support.
     import _bootlocale
     enc = _bootlocale.getpreferredencoding().lower()
diff --git a/direct/src/filter/CommonFilters.py b/direct/src/filter/CommonFilters.py
index 6634b504f2..9242290929 100644
--- a/direct/src/filter/CommonFilters.py
+++ b/direct/src/filter/CommonFilters.py
@@ -20,6 +20,7 @@ from panda3d.core import LVecBase4, LPoint2
 from panda3d.core import AuxBitplaneAttrib
 from panda3d.core import Texture, Shader, ATSNone
 from panda3d.core import FrameBufferProperties
+from panda3d.core import getDefaultCoordinateSystem, CS_zup_right, CS_zup_left
 
 from direct.task.TaskManagerGlobal import taskMgr
 
@@ -52,6 +53,7 @@ o_color = lerp(o_color, k_cartooncolor, cartoon_thresh);
 SSAO_BODY = """//Cg
 
 void vshader(float4 vtx_position : POSITION,
+             float2 vtx_texcoord : TEXCOORD0,
              out float4 l_position : POSITION,
              out float2 l_texcoord : TEXCOORD0,
              out float2 l_texcoordD : TEXCOORD1,
@@ -61,9 +63,9 @@ void vshader(float4 vtx_position : POSITION,
              uniform float4x4 mat_modelproj)
 {
   l_position = mul(mat_modelproj, vtx_position);
-  l_texcoord = vtx_position.xz;
-  l_texcoordD = (vtx_position.xz * texpad_depth.xy) + texpad_depth.xy;
-  l_texcoordN = (vtx_position.xz * texpad_normal.xy) + texpad_normal.xy;
+  l_texcoord = vtx_texcoord;
+  l_texcoordD = vtx_texcoord * texpad_depth.xy * 2;
+  l_texcoordN = vtx_texcoord * texpad_normal.xy * 2;
 }
 
 float3 sphere[16] = float3[](float3(0.53812504, 0.18565957, -0.43192),float3(0.13790712, 0.24864247, 0.44301823),float3(0.33715037, 0.56794053, -0.005789503),float3(-0.6999805, -0.04511441, -0.0019965635),float3(0.06896307, -0.15983082, -0.85477847),float3(0.056099437, 0.006954967, -0.1843352),float3(-0.014653638, 0.14027752, 0.0762037),float3(0.010019933, -0.1924225, -0.034443386),float3(-0.35775623, -0.5301969, -0.43581226),float3(-0.3169221, 0.106360726, 0.015860917),float3(0.010350345, -0.58698344, 0.0046293875),float3(-0.08972908, -0.49408212, 0.3287904),float3(0.7119986, -0.0154690035, -0.09183723),float3(-0.053382345, 0.059675813, -0.5411899),float3(0.035267662, -0.063188605, 0.54602677),float3(-0.47761092, 0.2847911, -0.0271716));
@@ -292,11 +294,19 @@ class CommonFilters:
             text += "{\n"
             text += "  l_position = mul(mat_modelproj, vtx_position);\n"
 
+            # The card is oriented differently depending on our chosen
+            # coordinate system.  We could just use vtx_texcoord, but this
+            # saves on an additional variable.
+            if getDefaultCoordinateSystem() in (CS_zup_right, CS_zup_left):
+                pos = "vtx_position.xz"
+            else:
+                pos = "vtx_position.xy"
+
             for texcoord, padTex in texcoordPadding.items():
                 if padTex is None:
-                    text += "  %s = vtx_position.xz * float2(0.5, 0.5) + float2(0.5, 0.5);\n" % (texcoord)
+                    text += "  %s = %s * float2(0.5, 0.5) + float2(0.5, 0.5);\n" % (texcoord, pos)
                 else:
-                    text += "  %s = (vtx_position.xz * texpad_tx%s.xy) + texpad_tx%s.xy;\n" % (texcoord, padTex, padTex)
+                    text += "  %s = (%s * texpad_tx%s.xy) + texpad_tx%s.xy;\n" % (texcoord, pos, padTex, padTex)
 
                     if "HalfPixelShift" in configuration:
                         text += "  %s += texpix_tx%s.xy * 0.5;\n" % (texcoord, padTex)
diff --git a/direct/src/filter/filterBloomI.py b/direct/src/filter/filterBloomI.py
index 6c44fb3ecb..ddb44c4ad0 100644
--- a/direct/src/filter/filterBloomI.py
+++ b/direct/src/filter/filterBloomI.py
@@ -32,6 +32,7 @@ BLOOM_I = """
 
 
 void vshader(float4 vtx_position : POSITION,
+             float2 vtx_texcoord : TEXCOORD0,
              out float4 l_position : POSITION,
              out float2 l_texcoordNW : TEXCOORD0,
              out float2 l_texcoordNE : TEXCOORD1,
@@ -42,7 +43,7 @@ void vshader(float4 vtx_position : POSITION,
              uniform float4x4 mat_modelproj)
 {
   l_position=mul(mat_modelproj, vtx_position);
-  float2 c=(vtx_position.xz * texpad_src.xy) + texpad_src.xy;
+  float2 c = vtx_texcoord * texpad_src.xy * 2;
   float4 offs = texpix_src * 0.5;
   l_texcoordNW = c + float2( offs.x, -offs.y);
   l_texcoordNE = c + float2( offs.x,  offs.y);
diff --git a/direct/src/filter/filterBloomX.py b/direct/src/filter/filterBloomX.py
index 220cd776b7..c7e40ab326 100644
--- a/direct/src/filter/filterBloomX.py
+++ b/direct/src/filter/filterBloomX.py
@@ -2,6 +2,7 @@ BLOOM_X = """
 //Cg
 
 void vshader(float4 vtx_position : POSITION,
+             float2 vtx_texcoord : TEXCOORD0,
              out float4 l_position : POSITION,
              out float4 l_texcoord0 : TEXCOORD0,
              out float4 l_texcoord1 : TEXCOORD1,
@@ -10,8 +11,8 @@ void vshader(float4 vtx_position : POSITION,
              uniform float4 texpix_src,
              uniform float4x4 mat_modelproj)
 {
-  l_position=mul(mat_modelproj, vtx_position);
-  float2 c=(vtx_position.xz * texpad_src.xy) + texpad_src.xy;
+  l_position = mul(mat_modelproj, vtx_position);
+  float2 c = vtx_texcoord * texpad_src.xy * 2;
   float offset = texpix_src.x;
   float pad = texpad_src.x * 2;
   l_texcoord0 = float4(min(c.x-offset* -4, pad), min(c.x-offset* -3, pad), min(c.x-offset* -2, pad), c.y);
diff --git a/direct/src/filter/filterBloomY.py b/direct/src/filter/filterBloomY.py
index 18e2885b1e..0b6cc9d5f8 100644
--- a/direct/src/filter/filterBloomY.py
+++ b/direct/src/filter/filterBloomY.py
@@ -2,6 +2,7 @@ BLOOM_Y = """
 //Cg
 
 void vshader(float4 vtx_position : POSITION,
+             float2 vtx_texcoord : TEXCOORD0,
              out float4 l_position : POSITION,
              out float4 l_texcoord0 : TEXCOORD0,
              out float4 l_texcoord1 : TEXCOORD1,
@@ -11,7 +12,7 @@ void vshader(float4 vtx_position : POSITION,
              uniform float4x4 mat_modelproj)
 {
   l_position=mul(mat_modelproj, vtx_position);
-  float2 c=(vtx_position.xz * texpad_src.xy) + texpad_src.xy;
+  float2 c = vtx_texcoord * texpad_src.xy * 2;
   float offset = texpix_src.y;
   float pad = texpad_src.y * 2;
   l_texcoord0 = float4(min(c.y-offset* -4, pad), min(c.y-offset* -3, pad), min(c.y-offset* -2, pad), c.x);
diff --git a/direct/src/filter/filterBlurX.py b/direct/src/filter/filterBlurX.py
index b472a5d7a7..426c1dc9a7 100644
--- a/direct/src/filter/filterBlurX.py
+++ b/direct/src/filter/filterBlurX.py
@@ -4,14 +4,14 @@ BLUR_X = """
 //Cg profile arbvp1 arbfp1
 
 void vshader(float4 vtx_position : POSITION,
-             float2 vtx_texcoord0 : TEXCOORD0,
+             float2 vtx_texcoord : TEXCOORD0,
              out float4 l_position : POSITION,
-      	     out float2 l_texcoord0 : TEXCOORD0,
+             out float2 l_texcoord0 : TEXCOORD0,
              uniform float4 texpad_src,
              uniform float4x4 mat_modelproj)
 {
-  l_position=mul(mat_modelproj, vtx_position);
-  l_texcoord0 = (vtx_position.xz * texpad_src.xy) + texpad_src.xy;
+  l_position = mul(mat_modelproj, vtx_position);
+  l_texcoord0 = vtx_texcoord * texpad_src.xy * 2;
 }
 
 
diff --git a/direct/src/filter/filterBlurY.py b/direct/src/filter/filterBlurY.py
index 173c7a73b5..00d0980b30 100644
--- a/direct/src/filter/filterBlurY.py
+++ b/direct/src/filter/filterBlurY.py
@@ -4,14 +4,14 @@ BLUR_Y = """
 //Cg profile arbvp1 arbfp1
 
 void vshader(float4 vtx_position : POSITION,
-             float2 vtx_texcoord0 : TEXCOORD0,
+             float2 vtx_texcoord : TEXCOORD0,
              out float4 l_position : POSITION,
-      	     out float2 l_texcoord0 : TEXCOORD0,
+             out float2 l_texcoord0 : TEXCOORD0,
              uniform float4 texpad_src,
              uniform float4x4 mat_modelproj)
 {
-  l_position=mul(mat_modelproj, vtx_position);
-  l_texcoord0 = (vtx_position.xz * texpad_src.xy) + texpad_src.xy;
+  l_position = mul(mat_modelproj, vtx_position);
+  l_texcoord0 = vtx_texcoord * texpad_src.xy * 2;
 }
 
 
diff --git a/direct/src/filter/filterCopy.py b/direct/src/filter/filterCopy.py
index d9770fb04b..dee3dadace 100644
--- a/direct/src/filter/filterCopy.py
+++ b/direct/src/filter/filterCopy.py
@@ -3,13 +3,14 @@ COPY = """
 
 
 void vshader(float4 vtx_position : POSITION,
+             float2 vtx_texcoord : TEXCOORD0,
              out float4 l_position : POSITION,
              out float2 l_texcoord : TEXCOORD0,
              uniform float4 texpad_src,
              uniform float4x4 mat_modelproj)
 {
-  l_position=mul(mat_modelproj, vtx_position);
-  l_texcoord = (vtx_position.xz * texpad_src.xy) + texpad_src.xy;
+  l_position = mul(mat_modelproj, vtx_position);
+  l_texcoord = vtx_texcoord * texpad_src.xy * 2;
 }
 
 void fshader(float2 l_texcoord : TEXCOORD0,
diff --git a/direct/src/filter/filterDown4.py b/direct/src/filter/filterDown4.py
index 14595dbbd7..d0c7ab4d2c 100644
--- a/direct/src/filter/filterDown4.py
+++ b/direct/src/filter/filterDown4.py
@@ -2,6 +2,7 @@ DOWN_4 = """
 //Cg
 
 void vshader(float4 vtx_position : POSITION,
+             float2 vtx_texcoord : TEXCOORD0,
              out float4 l_position : POSITION,
              out float2 l_texcoordNW : TEXCOORD0,
              out float2 l_texcoordNE : TEXCOORD1,
@@ -11,8 +12,8 @@ void vshader(float4 vtx_position : POSITION,
              uniform float4 texpix_src,
              uniform float4x4 mat_modelproj)
 {
-  l_position=mul(mat_modelproj, vtx_position);
-  float2 c=(vtx_position.xz * texpad_src.xy) + texpad_src.xy;
+  l_position = mul(mat_modelproj, vtx_position);
+  float2 c = vtx_texcoord * texpad_src.xy * 2;
   l_texcoordNW = c + float2( texpix_src.x, -texpix_src.y);
   l_texcoordNE = c + float2( texpix_src.x,  texpix_src.y);
   l_texcoordSW = c + float2(-texpix_src.x, -texpix_src.y);
diff --git a/direct/src/showbase/BufferViewer.py b/direct/src/showbase/BufferViewer.py
index 8c6c2c72e9..8c1ec73712 100644
--- a/direct/src/showbase/BufferViewer.py
+++ b/direct/src/showbase/BufferViewer.py
@@ -240,10 +240,10 @@ class BufferViewer(DirectObject):
             offsetx = (ringoffset[ring]*2.0) / float(sizex)
             offsety = (ringoffset[ring]*2.0) / float(sizey)
             bright = ringbright[ring]
-            vwriter.addData3f(-1-offsetx, 0, -1-offsety)
-            vwriter.addData3f(1+offsetx, 0, -1-offsety)
-            vwriter.addData3f(1+offsetx, 0,  1+offsety)
-            vwriter.addData3f(-1-offsetx, 0,  1+offsety)
+            vwriter.addData3f(Vec3.rfu(-1 - offsetx, 0, -1 - offsety))
+            vwriter.addData3f(Vec3.rfu( 1 + offsetx, 0, -1 - offsety))
+            vwriter.addData3f(Vec3.rfu( 1 + offsetx, 0,  1 + offsety))
+            vwriter.addData3f(Vec3.rfu(-1 - offsetx, 0,  1 + offsety))
             cwriter.addData3f(bright, bright, bright)
             cwriter.addData3f(bright, bright, bright)
             cwriter.addData3f(bright, bright, bright)
diff --git a/panda/src/display/graphicsEngine.cxx b/panda/src/display/graphicsEngine.cxx
index d6dc3c678d..8053b13a9a 100644
--- a/panda/src/display/graphicsEngine.cxx
+++ b/panda/src/display/graphicsEngine.cxx
@@ -1409,6 +1409,10 @@ cull_and_draw_together(GraphicsEngine::Windows wlist,
     GraphicsOutput *win = wlist[wi];
     if (win->is_active() && win->get_gsg()->is_active()) {
       if (win->flip_ready()) {
+        if (display_cat.is_spam()) {
+          display_cat.spam()
+            << "Flipping window " << win->get_name() << "\n";
+        }
         PStatTimer timer(_flip_pcollector, current_thread);
         win->begin_flip();
         win->end_flip();
@@ -1423,6 +1427,11 @@ cull_and_draw_together(GraphicsEngine::Windows wlist,
           gsg->pop_group_marker();
         }
 
+        if (display_cat.is_spam()) {
+          display_cat.spam()
+            << "Culling and drawing window " << win->get_name() << "\n";
+        }
+
         int num_display_regions = win->get_num_active_display_regions();
         for (int i = 0; i < num_display_regions; i++) {
           PT(DisplayRegion) dr = win->get_active_display_region(i);
@@ -1434,6 +1443,10 @@ cull_and_draw_together(GraphicsEngine::Windows wlist,
 
         if (_auto_flip) {
           if (win->flip_ready()) {
+            if (display_cat.is_spam()) {
+              display_cat.spam()
+                << "Flipping window " << win->get_name() << "\n";
+            }
             PStatTimer timer(_flip_pcollector, current_thread);
             win->begin_flip();
             win->end_flip();
@@ -1530,6 +1543,11 @@ cull_to_bins(GraphicsEngine::Windows wlist, Thread *current_thread) {
   for (size_t wi = 0; wi < wlist_size; ++wi) {
     GraphicsOutput *win = wlist[wi];
     if (win->is_active() && win->get_gsg()->is_active()) {
+      if (display_cat.is_spam()) {
+        display_cat.spam()
+          << "Culling window " << win->get_name() << "\n";
+      }
+
       GraphicsStateGuardian *gsg = win->get_gsg();
       PStatTimer timer(win->get_cull_window_pcollector(), current_thread);
       int num_display_regions = win->get_num_active_display_regions();
@@ -1687,6 +1705,10 @@ draw_bins(const GraphicsEngine::Windows &wlist, Thread *current_thread) {
 
       GraphicsOutput *host = win->get_host();
       if (host->flip_ready()) {
+        if (display_cat.is_spam()) {
+          display_cat.spam()
+            << "Flipping window " << win->get_name() << "\n";
+        }
         PStatTimer timer(_flip_pcollector, current_thread);
         host->begin_flip();
         host->end_flip();
@@ -1720,6 +1742,10 @@ draw_bins(const GraphicsEngine::Windows &wlist, Thread *current_thread) {
 
         if (_auto_flip) {
           if (win->flip_ready()) {
+            if (display_cat.is_spam()) {
+              display_cat.spam()
+                << "Flipping window " << win->get_name() << "\n";
+            }
             PStatGPUTimer timer(gsg, _flip_pcollector, current_thread);
             win->begin_flip();
             win->end_flip();
@@ -1790,6 +1816,11 @@ flip_windows(const GraphicsEngine::Windows &wlist, Thread *current_thread) {
   for (i = 0; i < num_windows; ++i) {
     GraphicsOutput *win = wlist[i];
     if (win->flip_ready()) {
+      if (display_cat.is_spam()) {
+        display_cat.spam()
+          << "Flipping window " << win->get_name() << "\n";
+      }
+
       nassertv(warray_count < num_windows);
       warray[warray_count] = win;
       ++warray_count;
@@ -2217,6 +2248,11 @@ void GraphicsEngine::
 do_resort_windows() {
   _windows_sorted = true;
 
+  if (display_cat.is_spam()) {
+    display_cat.spam()
+      << "Re-sorting window list.\n";
+  }
+
   _app.resort_windows();
   Threads::const_iterator ti;
   for (ti = _threads.begin(); ti != _threads.end(); ++ti) {
diff --git a/panda/src/windisplay/winGraphicsPipe.cxx b/panda/src/windisplay/winGraphicsPipe.cxx
index 4815262a77..28787c43b3 100644
--- a/panda/src/windisplay/winGraphicsPipe.cxx
+++ b/panda/src/windisplay/winGraphicsPipe.cxx
@@ -247,6 +247,71 @@ WinGraphicsPipe() {
     }
   }
 
+  if (windisplay_cat.is_debug()) {
+    windisplay_cat.debug()
+      << "Detected display devices:\n";
+
+    DISPLAY_DEVICEA device;
+    device.cb = sizeof(device);
+    for (DWORD devnum = 0; EnumDisplayDevicesA(nullptr, devnum, &device, 0); ++devnum) {
+      std::ostream &out = windisplay_cat.debug();
+      out << "  " << device.DeviceName << " [" << device.DeviceString << "]";
+      if (device.StateFlags & DISPLAY_DEVICE_ACTIVE) {
+        out << " (active)";
+      }
+      if (device.StateFlags & DISPLAY_DEVICE_MULTI_DRIVER) {
+        out << " (multi-driver)";
+      }
+      if (device.StateFlags & DISPLAY_DEVICE_PRIMARY_DEVICE) {
+        out << " (primary)";
+      }
+      if (device.StateFlags & DISPLAY_DEVICE_MIRRORING_DRIVER) {
+        out << " (mirroring)";
+      }
+      if (device.StateFlags & DISPLAY_DEVICE_REMOVABLE) {
+        out << " (removable)";
+      }
+      out << "\n";
+    }
+
+    int nmonitor = GetSystemMetrics(SM_CMONITORS);
+    windisplay_cat.debug()
+      << "Detected " << nmonitor << " monitors, "
+      << (GetSystemMetrics(SM_SAMEDISPLAYFORMAT) != 0 ? "" : "NOT ")
+      << "sharing same display format:\n";
+
+    EnumDisplayMonitors(
+      nullptr,
+      nullptr,
+      [](HMONITOR monitor, HDC dc, LPRECT rect, LPARAM param) -> BOOL {
+        MONITORINFOEXA info;
+        info.cbSize = sizeof(info);
+        if (GetMonitorInfoA(monitor, &info)) {
+          std::ostream &out = windisplay_cat.debug() << "  ";
+
+          DISPLAY_DEVICEA device;
+          device.cb = sizeof(device);
+          device.StateFlags = 0;
+          if (EnumDisplayDevicesA(info.szDevice, 0, &device, 0)) {
+            out << device.DeviceName << " [" << device.DeviceString << "]";
+          }
+          else {
+            out << info.szDevice << " (device enum failed)";
+          }
+
+          if (info.dwFlags & MONITORINFOF_PRIMARY) {
+            out << " (primary)";
+          }
+          if (info.rcWork.left != 0 || info.rcWork.top != 0) {
+            out << " (at " << info.rcWork.left << "x" << info.rcWork.top << ")";
+          }
+          out << "\n";
+        }
+        return TRUE;
+      },
+      0);
+  }
+
 #ifdef HAVE_DX9
   // Use D3D to get display info.  This is disabled by default as it is slow.
   if (request_dxdisplay_information) {