diff --git a/kernel-open/nvidia-uvm/uvm_devmem.c b/kernel-open/nvidia-uvm/uvm_devmem.c
index 38ca9713f5..bfa5b5f006 100644
--- a/kernel-open/nvidia-uvm/uvm_devmem.c
+++ b/kernel-open/nvidia-uvm/uvm_devmem.c
@@ -613,6 +613,18 @@ void uvm_devmem_device_p2p_init(uvm_parent_gpu_t *parent_gpu)
 
     parent_gpu->device_p2p_initialised = false;
 
+    if (parent_gpu->rm_info.gpuArch >= NV2080_CTRL_MC_ARCH_INFO_ARCHITECTURE_GB100) {
+        // Static BAR1 is also the GPU peer aperture on non-coherent Blackwell.
+        // Registering it as P2PDMA memory would replace its pagemap operations
+        // and conflict with the BAR1-as-sysmem PTEs used for GPU peer access.
+        UVM_DBG_PRINT("Skipping PCI P2PDMA static BAR1 registration on non-coherent GPU %s "
+                      "(size 0x%llx, write-combined %u)\n",
+                      uvm_parent_gpu_name(parent_gpu),
+                      parent_gpu->static_bar1_size,
+                      parent_gpu->static_bar1_write_combined);
+        return;
+    }
+
     // RM sets static_bar1_size when it has created a contiguous BAR mapping
     // large enough to cover all of GPU memory that will be allocated to
     // userspace buffers. This is required to support the P2PDMA feature to
diff --git a/kernel-open/nvidia-uvm/uvm_gpu.h b/kernel-open/nvidia-uvm/uvm_gpu.h
index 7761f569cb..dedbfcce51 100644
--- a/kernel-open/nvidia-uvm/uvm_gpu.h
+++ b/kernel-open/nvidia-uvm/uvm_gpu.h
@@ -1825,13 +1825,6 @@ NvU64 uvm_parent_gpu_canonical_address(uvm_parent_gpu_t *parent_gpu, NvU64 addr)
 
 static bool uvm_parent_gpu_is_coherent(const uvm_parent_gpu_t *parent_gpu)
 {
-    // Blackwell+ consumer GPUs (e.g. 5090) use BAR1 P2P via the SYS_COH
-    // aperture rewrite in nvGpuOpsBuildExternalAllocPtes. UVM's P2P
-    // registration path must take the coherent route to match, otherwise
-    // the ZONE_DEVICE peer DMA setup conflicts with BAR1-as-sysmem PTEs.
-    if (parent_gpu->rm_info.gpuArch >= NV2080_CTRL_MC_ARCH_INFO_ARCHITECTURE_GB100)
-        return true;
-
     return parent_gpu->system_bus.memory_window_end > parent_gpu->system_bus.memory_window_start;
 }