[libc] Explicitly pin memory for the HSA memory transfer (llvm#73973)

Summary:
This portion of code handles mapping the RPC client memory over to the
device. HSA copies need to be between two slices of memory that HSA has
allocated. Previously we used coarse-grained memory to act as the host
source. However, the support for this varies depending on the kernel and
version and should not be relied upon. This patch changes that handling
to use the `hsa_amd_memory_lock` API to explicitly pin memory to a
location sufficient for a DMA transfer to the GPU.

libc/utils/gpu/loader/amdgpu/Loader.cpp

@@ -482,20 +482,20 @@ int load(int argc, char **argv, char **envp, void *image, size_t size,
     handle_error(err);
 
   void *rpc_client_buffer;
-  if (hsa_status_t err = hsa_amd_memory_pool_allocate(
-          coarsegrained_pool, rpc_get_client_size(),
-          /*flags=*/0, &rpc_client_buffer))
+  if (hsa_status_t err = hsa_amd_memory_lock(
+          const_cast<void *>(rpc_get_client_buffer(device_id)),
+          rpc_get_client_size(),
+          /*agents=*/nullptr, 0, &rpc_client_buffer))
     handle_error(err);
-  std::memcpy(rpc_client_buffer, rpc_get_client_buffer(device_id),
-              rpc_get_client_size());
 
   // Copy the RPC client buffer to the address pointed to by the symbol.
   if (hsa_status_t err =
           hsa_memcpy(*reinterpret_cast<void **>(rpc_client_host), dev_agent,
                      rpc_client_buffer, host_agent, rpc_get_client_size()))
     handle_error(err);
 
-  if (hsa_status_t err = hsa_amd_memory_pool_free(rpc_client_buffer))
+  if (hsa_status_t err = hsa_amd_memory_unlock(
+          const_cast<void *>(rpc_get_client_buffer(device_id))))
     handle_error(err);
   if (hsa_status_t err = hsa_amd_memory_pool_free(rpc_client_host))
     handle_error(err);